diff --git a/src/annotateBed/annotateBed.cpp b/src/annotateBed/annotateBed.cpp
index 10477d36e4cec1a2b672673645c5ff6da4ea147b..9dcf45ac6db5d6718b92d27655f40a6fe725a561 100644
--- a/src/annotateBed/annotateBed.cpp
+++ b/src/annotateBed/annotateBed.cpp
@@ -13,7 +13,7 @@
#include "annotateBed.h"
// build
-BedAnnotate::BedAnnotate(const string &mainFile, const vector<string> &annoFileNames,
+BedAnnotate::BedAnnotate(const string &mainFile, const vector<string> &annoFileNames,
const vector<string> &annoTitles, bool forceStrand, bool reportCounts, bool reportBoth) :
_mainFile(mainFile),
@@ -24,36 +24,36 @@ BedAnnotate::BedAnnotate(const string &mainFile, const vector<string> &annoFileN
_reportBoth(reportBoth)
{
_bed = new BedFile(_mainFile);
-}
+}
// destroy and delete the open file pointers
BedAnnotate::~BedAnnotate(void) {
- delete _bed;
+ delete _bed;
CloseAnnoFiles();
}
void BedAnnotate::OpenAnnoFiles() {
- for (size_t i=0; i < _annoFileNames.size(); ++i) {
- BedFile *file = new BedFile(_annoFileNames[i]);
- file->Open();
- _annoFiles.push_back(file);
- }
+ for (size_t i=0; i < _annoFileNames.size(); ++i) {
+ BedFile *file = new BedFile(_annoFileNames[i]);
+ file->Open();
+ _annoFiles.push_back(file);
+ }
}
void BedAnnotate::CloseAnnoFiles() {
- for (size_t i=0; i < _annoFiles.size(); ++i) {
- BedFile *file = _annoFiles[i];
- delete file;
- _annoFiles[i] = NULL;
- }
+ for (size_t i=0; i < _annoFiles.size(); ++i) {
+ BedFile *file = _annoFiles[i];
+ delete file;
+ _annoFiles[i] = NULL;
+ }
}
void BedAnnotate::PrintHeader() {
- // print a hash to indicate header and then write a tab
+ // print a hash to indicate header and then write a tab
// for each field in the main file.
printf("#");
for (size_t i = 0; i < _bed->bedType; ++i)
@@ -74,135 +74,135 @@ void BedAnnotate::PrintHeader() {
void BedAnnotate::InitializeMainFile() {
- // process each chromosome
- masterBedCovListMap::iterator chromItr = _bed->bedCovListMap.begin();
- masterBedCovListMap::iterator chromEnd = _bed->bedCovListMap.end();
- for (; chromItr != chromEnd; ++chromItr) {
- // for each chrom, process each bin
- binsToBedCovLists::iterator binItr = chromItr->second.begin();
- binsToBedCovLists::iterator binEnd = chromItr->second.end();
- for (; binItr != binEnd; ++binItr) {
+ // process each chromosome
+ masterBedCovListMap::iterator chromItr = _bed->bedCovListMap.begin();
+ masterBedCovListMap::iterator chromEnd = _bed->bedCovListMap.end();
+ for (; chromItr != chromEnd; ++chromItr) {
+ // for each chrom, process each bin
+ binsToBedCovLists::iterator binItr = chromItr->second.begin();
+ binsToBedCovLists::iterator binEnd = chromItr->second.end();
+ for (; binItr != binEnd; ++binItr) {
// initialize BEDCOVLIST in this chrom/bin
- vector<BEDCOVLIST>::iterator bedItr = binItr->second.begin();
- vector<BEDCOVLIST>::iterator bedEnd = binItr->second.end();
- for (; bedItr != bedEnd; ++bedItr) {
- // initialize the depthMaps, counts, etc. for each anno file.
+ vector<BEDCOVLIST>::iterator bedItr = binItr->second.begin();
+ vector<BEDCOVLIST>::iterator bedEnd = binItr->second.end();
+ for (; bedItr != bedEnd; ++bedItr) {
+ // initialize the depthMaps, counts, etc. for each anno file.
for (size_t i = 0; i < _annoFiles.size(); ++i) {
map<unsigned int, DEPTH> dummy;
bedItr->depthMapList.push_back(dummy);
bedItr->counts.push_back(0);
bedItr->minOverlapStarts.push_back(INT_MAX);
}
- }
- }
+ }
+ }
}
}
void BedAnnotate::AnnotateBed() {
-
- // load the "main" bed file into a map so
- // that we can easily compare each annoFile to it for overlaps
- _bed->loadBedCovListFileIntoMap();
+
+ // load the "main" bed file into a map so
+ // that we can easily compare each annoFile to it for overlaps
+ _bed->loadBedCovListFileIntoMap();
// open the annotations files for processing;
- OpenAnnoFiles();
+ OpenAnnoFiles();
// initialize counters, depths, etc. for the main file
InitializeMainFile();
-
- // annotate the main file with the coverage from the annotation files.
+
+ // annotate the main file with the coverage from the annotation files.
for (size_t annoIndex = 0; annoIndex < _annoFiles.size(); ++annoIndex) {
// grab the current annotation file.
- BedFile *anno = _annoFiles[annoIndex];
+ BedFile *anno = _annoFiles[annoIndex];
int lineNum = 0;
- BED a, nullBed;
- BedLineStatus bedStatus;
-
- // process each entry in the current anno file
- while ((bedStatus = anno->GetNextBed(a, lineNum)) != BED_INVALID) {
- if (bedStatus == BED_VALID) {
- _bed->countListHits(a, annoIndex, _forceStrand);
- a = nullBed;
- }
- }
- }
-
- // report the annotations of the main file from the anno file.
- ReportAnnotations();
- // close the annotations files;
- CloseAnnoFiles();
+ BED a, nullBed;
+ BedLineStatus bedStatus;
+
+ // process each entry in the current anno file
+ while ((bedStatus = anno->GetNextBed(a, lineNum)) != BED_INVALID) {
+ if (bedStatus == BED_VALID) {
+ _bed->countListHits(a, annoIndex, _forceStrand);
+ a = nullBed;
+ }
+ }
+ }
+
+ // report the annotations of the main file from the anno file.
+ ReportAnnotations();
+ // close the annotations files;
+ CloseAnnoFiles();
}
void BedAnnotate::ReportAnnotations() {
-
+
if (_annoTitles.size() > 0) {
PrintHeader();
}
- // process each chromosome
- masterBedCovListMap::const_iterator chromItr = _bed->bedCovListMap.begin();
- masterBedCovListMap::const_iterator chromEnd = _bed->bedCovListMap.end();
- for (; chromItr != chromEnd; ++chromItr) {
- // for each chrom, process each bin
- binsToBedCovLists::const_iterator binItr = chromItr->second.begin();
- binsToBedCovLists::const_iterator binEnd = chromItr->second.end();
- for (; binItr != binEnd; ++binItr) {
- // for each chrom & bin, compute and report
+ // process each chromosome
+ masterBedCovListMap::const_iterator chromItr = _bed->bedCovListMap.begin();
+ masterBedCovListMap::const_iterator chromEnd = _bed->bedCovListMap.end();
+ for (; chromItr != chromEnd; ++chromItr) {
+ // for each chrom, process each bin
+ binsToBedCovLists::const_iterator binItr = chromItr->second.begin();
+ binsToBedCovLists::const_iterator binEnd = chromItr->second.end();
+ for (; binItr != binEnd; ++binItr) {
+ // for each chrom & bin, compute and report
// the observed coverage for each feature
- vector<BEDCOVLIST>::const_iterator bedItr = binItr->second.begin();
- vector<BEDCOVLIST>::const_iterator bedEnd = binItr->second.end();
- for (; bedItr != bedEnd; ++bedItr) {
- // print the main BED entry.
- _bed->reportBedTab(*bedItr);
-
+ vector<BEDCOVLIST>::const_iterator bedItr = binItr->second.begin();
+ vector<BEDCOVLIST>::const_iterator bedEnd = binItr->second.end();
+ for (; bedItr != bedEnd; ++bedItr) {
+ // print the main BED entry.
+ _bed->reportBedTab(*bedItr);
+
// now report the coverage from each annotation file.
for (size_t i = 0; i < _annoFiles.size(); ++i) {
- unsigned int totalLength = 0;
- int zeroDepthCount = 0; // number of bases with zero depth
- int depth = 0; // tracks the depth at the current base
-
- // the start is either the first base in the feature OR
- // the leftmost position of an overlapping feature. e.g. (s = start):
- // A ----------
- // B s ------------
- int start = min(bedItr->minOverlapStarts[i], bedItr->start);
-
- map<unsigned int, DEPTH>::const_iterator depthItr;
- map<unsigned int, DEPTH>::const_iterator depthEnd;
-
- // compute the coverage observed at each base in the feature marching from start to end.
- for (CHRPOS pos = start+1; pos <= bedItr->end; pos++) {
- // map pointer grabbing the starts and ends observed at this position
- depthItr = bedItr->depthMapList[i].find(pos);
+ unsigned int totalLength = 0;
+ int zeroDepthCount = 0; // number of bases with zero depth
+ int depth = 0; // tracks the depth at the current base
+
+ // the start is either the first base in the feature OR
+ // the leftmost position of an overlapping feature. e.g. (s = start):
+ // A ----------
+ // B s ------------
+ int start = min(bedItr->minOverlapStarts[i], bedItr->start);
+
+ map<unsigned int, DEPTH>::const_iterator depthItr;
+ map<unsigned int, DEPTH>::const_iterator depthEnd;
+
+ // compute the coverage observed at each base in the feature marching from start to end.
+ for (CHRPOS pos = start+1; pos <= bedItr->end; pos++) {
+ // map pointer grabbing the starts and ends observed at this position
+ depthItr = bedItr->depthMapList[i].find(pos);
depthEnd = bedItr->depthMapList[i].end();
-
- // increment coverage if starts observed at this position.
- if (depthItr != depthEnd)
- depth += depthItr->second.starts;
- // update zero depth
- if ((pos > bedItr->start) && (pos <= bedItr->end) && (depth == 0))
- zeroDepthCount++;
- // decrement coverage if ends observed at this position.
- if (depthItr != depthEnd)
- depth = depth - depthItr->second.ends;
- }
- // Summarize the coverage for the current interval,
- CHRPOS length = bedItr->end - bedItr->start;
- totalLength += length;
- int nonZeroBases = (length - zeroDepthCount);
- float fractCovered = (float) nonZeroBases / length;
- if (_reportCounts == false && _reportBoth == false)
- printf("%f\t", fractCovered);
- else if (_reportCounts == true && _reportBoth == false)
- printf("%d\t", bedItr->counts[i]);
+
+ // increment coverage if starts observed at this position.
+ if (depthItr != depthEnd)
+ depth += depthItr->second.starts;
+ // update zero depth
+ if ((pos > bedItr->start) && (pos <= bedItr->end) && (depth == 0))
+ zeroDepthCount++;
+ // decrement coverage if ends observed at this position.
+ if (depthItr != depthEnd)
+ depth = depth - depthItr->second.ends;
+ }
+ // Summarize the coverage for the current interval,
+ CHRPOS length = bedItr->end - bedItr->start;
+ totalLength += length;
+ int nonZeroBases = (length - zeroDepthCount);
+ float fractCovered = (float) nonZeroBases / length;
+ if (_reportCounts == false && _reportBoth == false)
+ printf("%f\t", fractCovered);
+ else if (_reportCounts == true && _reportBoth == false)
+ printf("%d\t", bedItr->counts[i]);
else if (_reportCounts == false && _reportBoth == true)
- printf("%d\t%f\t", bedItr->counts[i], fractCovered);
- }
- // print newline for next feature.
+ printf("%d\t%f\t", bedItr->counts[i], fractCovered);
+ }
+ // print newline for next feature.
printf("\n");
- }
- }
- }
+ }
+ }
+ }
}
diff --git a/src/annotateBed/annotateBed.h b/src/annotateBed/annotateBed.h
index fe02ecb3dfe782f63f1db65c9137aef1861b410e..1928e61e37f6dd66cc079a07bc78b6f052beafb1 100644
--- a/src/annotateBed/annotateBed.h
+++ b/src/annotateBed/annotateBed.h
@@ -9,7 +9,7 @@
Licenced under the GNU General Public License 2.0 license.
******************************************************************************/
-#ifndef ANNOTATEBED_H
+#ifndef ANNOTATEBED_H
#define ANNOTATEBED_H
#include "bedFile.h"
@@ -35,41 +35,41 @@ class BedAnnotate {
public:
- // constructor
- BedAnnotate(const string &mainFile, const vector<string> &annoFileNames,
- const vector<string> &annoTitles, bool forceStrand, bool reportCounts, bool reportBoth);
+ // constructor
+ BedAnnotate(const string &mainFile, const vector<string> &annoFileNames,
+ const vector<string> &annoTitles, bool forceStrand, bool reportCounts, bool reportBoth);
+
+ // destructor
+ ~BedAnnotate(void);
+
+ // annotate the master file with all of the annotation files.
+ void AnnotateBed();
- // destructor
- ~BedAnnotate(void);
-
- // annotate the master file with all of the annotation files.
- void AnnotateBed();
-
private:
- // input files.
- string _mainFile;
+ // input files.
+ string _mainFile;
vector<string> _annoFileNames;
vector<string> _annoTitles;
-
- // instance of a bed file class.
+
+ // instance of a bed file class.
BedFile *_bed;
vector<BedFile*> _annoFiles;
-
- // do we care about strandedness when counting coverage?
- bool _forceStrand;
+
+ // do we care about strandedness when counting coverage?
+ bool _forceStrand;
bool _reportCounts;
bool _reportBoth;
-
- // private function for reporting coverage information
- void ReportAnnotations();
-
+
+ // private function for reporting coverage information
+ void ReportAnnotations();
+
void OpenAnnoFiles();
-
+
void CloseAnnoFiles();
-
+
void PrintHeader();
-
+
void InitializeMainFile();
};
#endif /* ANNOTATEBED_H */
diff --git a/src/annotateBed/annotateMain.cpp b/src/annotateBed/annotateMain.cpp
index 65a440709137f52a7c6ce126ceda16f2883f6e33..eb094409d76d8d665de4943eafc97ba2368fde92 100644
--- a/src/annotateBed/annotateMain.cpp
+++ b/src/annotateBed/annotateMain.cpp
@@ -25,135 +25,135 @@ void ShowHelp(void);
int main(int argc, char* argv[]) {
- // our configuration variables
- bool showHelp = false;
-
- // input file
- string mainFile;
-
- // parm flags
- bool forceStrand = false;
- bool haveBed = false;
- bool haveFiles = false;
- bool haveTitles = false;
+ // our configuration variables
+ bool showHelp = false;
+
+ // input file
+ string mainFile;
+
+ // parm flags
+ bool forceStrand = false;
+ bool haveBed = false;
+ bool haveFiles = false;
+ bool haveTitles = false;
bool reportCounts = false;
- bool reportBoth = false;
+ bool reportBoth = false;
// list of annotation files / names
- vector<string> inputFiles;
- vector<string> inputTitles;
-
- // check to see if we should print out some help
- if(argc <= 1) showHelp = true;
-
- for(int i = 1; i < argc; i++) {
- int parameterLength = (int)strlen(argv[i]);
-
- if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
- (PARAMETER_CHECK("--help", 5, parameterLength))) {
- showHelp = true;
- }
- }
-
- if(showHelp) ShowHelp();
-
- // do some parsing (all of these parameters require 2 strings)
- for(int i = 1; i < argc; i++) {
-
- int parameterLength = (int)strlen(argv[i]);
-
- if(PARAMETER_CHECK("-i", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveBed = true;
- mainFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-files", 6, parameterLength)) {
- if ((i+1) < argc) {
- haveFiles = true;
+ vector<string> inputFiles;
+ vector<string> inputTitles;
+
+ // check to see if we should print out some help
+ if(argc <= 1) showHelp = true;
+
+ for(int i = 1; i < argc; i++) {
+ int parameterLength = (int)strlen(argv[i]);
+
+ if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
+ (PARAMETER_CHECK("--help", 5, parameterLength))) {
+ showHelp = true;
+ }
+ }
+
+ if(showHelp) ShowHelp();
+
+ // do some parsing (all of these parameters require 2 strings)
+ for(int i = 1; i < argc; i++) {
+
+ int parameterLength = (int)strlen(argv[i]);
+
+ if(PARAMETER_CHECK("-i", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveBed = true;
+ mainFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-files", 6, parameterLength)) {
+ if ((i+1) < argc) {
+ haveFiles = true;
i = i+1;
string file = argv[i];
- while (file[0] != '-' && i < argc) {
+ while (file[0] != '-' && i < argc) {
inputFiles.push_back(file);
i++;
if (i < argc)
file = argv[i];
- }
+ }
i--;
- }
- }
- else if(PARAMETER_CHECK("-names", 6, parameterLength)) {
- if ((i+1) < argc) {
- haveTitles = true;
+ }
+ }
+ else if(PARAMETER_CHECK("-names", 6, parameterLength)) {
+ if ((i+1) < argc) {
+ haveTitles = true;
i = i+1;
string title = argv[i];
- while (title[0] != '-' && i < argc) {
+ while (title[0] != '-' && i < argc) {
inputTitles.push_back(title);
i++;
if (i < argc)
title = argv[i];
- }
+ }
i--;
- }
- }
- else if(PARAMETER_CHECK("-counts", 7, parameterLength)) {
- reportCounts = true;
- }
- else if(PARAMETER_CHECK("-both", 5, parameterLength)) {
- reportBoth = true;
- }
- else if (PARAMETER_CHECK("-s", 2, parameterLength)) {
- forceStrand = true;
- }
- else {
- cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
- showHelp = true;
- }
- }
-
- // make sure we have both input files
- if (!haveBed || !haveFiles) {
- cerr << endl << "*****" << endl << "*****ERROR: Need -i and -files files. " << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (!showHelp) {
- BedAnnotate *ba = new BedAnnotate(mainFile, inputFiles, inputTitles, forceStrand, reportCounts, reportBoth);
+ }
+ }
+ else if(PARAMETER_CHECK("-counts", 7, parameterLength)) {
+ reportCounts = true;
+ }
+ else if(PARAMETER_CHECK("-both", 5, parameterLength)) {
+ reportBoth = true;
+ }
+ else if (PARAMETER_CHECK("-s", 2, parameterLength)) {
+ forceStrand = true;
+ }
+ else {
+ cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
+ showHelp = true;
+ }
+ }
+
+ // make sure we have both input files
+ if (!haveBed || !haveFiles) {
+ cerr << endl << "*****" << endl << "*****ERROR: Need -i and -files files. " << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (!showHelp) {
+ BedAnnotate *ba = new BedAnnotate(mainFile, inputFiles, inputTitles, forceStrand, reportCounts, reportBoth);
ba->AnnotateBed();
- delete ba;
- return 0;
- }
- else {
- ShowHelp();
- }
+ delete ba;
+ return 0;
+ }
+ else {
+ ShowHelp();
+ }
}
void ShowHelp(void) {
-
- cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
-
- cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
-
- cerr << "Summary: Annotates the depth & breadth of coverage of features from multiple files" << endl;
- cerr << "\t on the intervals in -i." << endl << endl;
-
- cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -i <bed/gff/vcf> -files FILE1 FILE2 .. FILEn" << endl << endl;
-
- cerr << "Options: " << endl;
-
- cerr << "\t-names\t" << "A list of names (one / file) to describe each file in -i." << endl;
- cerr << "\t\tThese names will be printed as a header line." << endl << endl;
-
- cerr << "\t-counts\t" << "Report the count of features in each file that overlap -i." << endl;
- cerr << "\t\t- Default is to report the fraction of -i covered by each file." << endl << endl;
-
- cerr << "\t-both\t" << "Report the counts followed by the % coverage." << endl;
- cerr << "\t\t- Default is to report the fraction of -i covered by each file." << endl << endl;
-
- cerr << "\t-s\t" << "Force strandedness. That is, only include hits in A that" << endl;
- cerr << "\t\toverlap B on the same strand." << endl;
- cerr << "\t\t- By default, hits are included without respect to strand." << endl << endl;
-
- exit(1);
+
+ cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
+
+ cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
+
+ cerr << "Summary: Annotates the depth & breadth of coverage of features from multiple files" << endl;
+ cerr << "\t on the intervals in -i." << endl << endl;
+
+ cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -i <bed/gff/vcf> -files FILE1 FILE2 .. FILEn" << endl << endl;
+
+ cerr << "Options: " << endl;
+
+ cerr << "\t-names\t" << "A list of names (one / file) to describe each file in -i." << endl;
+ cerr << "\t\tThese names will be printed as a header line." << endl << endl;
+
+ cerr << "\t-counts\t" << "Report the count of features in each file that overlap -i." << endl;
+ cerr << "\t\t- Default is to report the fraction of -i covered by each file." << endl << endl;
+
+ cerr << "\t-both\t" << "Report the counts followed by the % coverage." << endl;
+ cerr << "\t\t- Default is to report the fraction of -i covered by each file." << endl << endl;
+
+ cerr << "\t-s\t" << "Force strandedness. That is, only include hits in A that" << endl;
+ cerr << "\t\toverlap B on the same strand." << endl;
+ cerr << "\t\t- By default, hits are included without respect to strand." << endl << endl;
+
+ exit(1);
}
diff --git a/src/bamToBed/bamToBed.cpp b/src/bamToBed/bamToBed.cpp
index 7f46b466d12318d358e3b15c79e80ffea7885282..fa042fe9382b04b4466862712054f7e974a4de21 100644
--- a/src/bamToBed/bamToBed.cpp
+++ b/src/bamToBed/bamToBed.cpp
@@ -17,7 +17,7 @@
using namespace BamTools;
#include <vector>
-#include <algorithm> // for swap()
+#include <algorithm> // for swap()
#include <iostream>
#include <fstream>
#include <stdlib.h>
@@ -38,392 +38,392 @@ void ShowHelp(void);
void ConvertBamToBed(const string &bamFile, const bool &useEditDistance, const string &bamTag,
const bool &writeBed12, const bool &obeySplits, const string &color, const bool &useCigar);
void ConvertBamToBedpe(const string &bamFile, const bool &useEditDistance);
-
+
void PrintBed(const BamAlignment &bam, const RefVector &refs, bool useEditDistance, const string &bamTag, bool obeySplits, bool useCigar);
void PrintBed12(const BamAlignment &bam, const RefVector &refs, bool useEditDistance, const string &bamTag, string color = "255,0,0");
void PrintBedPE(const BamAlignment &bam1, const BamAlignment &bam2,
const RefVector &refs, bool useEditDistance);
-void ParseCigarBed12(const vector<CigarOp> &cigar, vector<int> &blockStarts,
+void ParseCigarBed12(const vector<CigarOp> &cigar, vector<int> &blockStarts,
vector<int> &blockEnds, int &alignmentEnd);
string BuildCigarString(const vector<CigarOp> &cigar);
-
+
bool IsCorrectMappingForBEDPE (const BamAlignment &bam);
int main(int argc, char* argv[]) {
- // our configuration variables
- bool showHelp = false;
+ // our configuration variables
+ bool showHelp = false;
- // input files
- string bamFile = "stdin";
- string color = "255,0,0";
+ // input files
+ string bamFile = "stdin";
+ string color = "255,0,0";
string tag = "";
-
- bool haveBam = true;
- bool haveColor = false;
- bool haveOtherTag = false;
- bool writeBedPE = false;
- bool writeBed12 = false;
- bool useEditDistance = false;
- bool useAlignmentScore = false;
+
+ bool haveBam = true;
+ bool haveColor = false;
+ bool haveOtherTag = false;
+ bool writeBedPE = false;
+ bool writeBed12 = false;
+ bool useEditDistance = false;
+ bool useAlignmentScore = false;
bool useCigar = false;
- bool obeySplits = false;
-
- // check to see if we should print out some help
-
- for(int i = 1; i < argc; i++) {
- int parameterLength = (int)strlen(argv[i]);
-
- if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
- (PARAMETER_CHECK("--help", 5, parameterLength))) {
- showHelp = true;
- }
- }
-
- if(showHelp) ShowHelp();
-
- // do some parsing (all of these parameters require 2 strings)
- for(int i = 1; i < argc; i++) {
-
- int parameterLength = (int)strlen(argv[i]);
-
- if(PARAMETER_CHECK("-i", 2, parameterLength)) {
- if ((i+1) < argc) {
- bamFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-bedpe", 6, parameterLength)) {
- writeBedPE = true;
- }
- else if(PARAMETER_CHECK("-bed12", 6, parameterLength)) {
- writeBed12 = true;
- }
- else if(PARAMETER_CHECK("-split", 6, parameterLength)) {
- obeySplits = true;
- }
- else if(PARAMETER_CHECK("-ed", 3, parameterLength)) {
- useEditDistance = true;
- }
- else if(PARAMETER_CHECK("-cigar", 6, parameterLength)) {
- useCigar = true;
- }
- else if(PARAMETER_CHECK("-as", 3, parameterLength)) {
- useAlignmentScore = true;
- }
- else if(PARAMETER_CHECK("-color", 6, parameterLength)) {
- if ((i+1) < argc) {
- haveColor = true;
- color = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-tag", 4, parameterLength)) {
- if ((i+1) < argc) {
- haveOtherTag = true;
- tag = argv[i + 1];
- i++;
- }
- }
- else {
- cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
- showHelp = true;
- }
- }
-
- // make sure we have an input files
- if (haveBam == false) {
- cerr << endl << "*****" << endl << "*****ERROR: Need -i (BAM) file. " << endl << "*****" << endl;
- showHelp = true;
- }
- if (haveColor == true && writeBed12 == false) {
- cerr << endl << "*****" << endl << "*****ERROR: Cannot use color without BED12. " << endl << "*****" << endl;
- showHelp = true;
- }
- if (useEditDistance == true && obeySplits == true) {
- cerr << endl << "*****" << endl << "*****ERROR: Cannot use -ed with -splits. Edit distances cannot be computed for each \'chunk\'." << endl << "*****" << endl;
- showHelp = true;
- }
- if (useEditDistance == true && useCigar == true) {
- cerr << endl << "*****" << endl << "*****ERROR: Cannot use -cigar with -splits. Not yet supported." << endl << "*****" << endl;
- showHelp = true;
- }
- if (useEditDistance == true && haveOtherTag == true) {
- cerr << endl << "*****" << endl << "*****ERROR: Cannot use -ed with -tag. Choose one or the other." << endl << "*****" << endl;
- showHelp = true;
- }
- if (writeBedPE == true && haveOtherTag == true) {
- cerr << endl << "*****" << endl << "*****ERROR: Cannot use -tag with -bedpe." << endl << "*****" << endl;
- showHelp = true;
- }
- // if there are no problems, let's convert BAM to BED or BEDPE
- if (!showHelp) {
- if (writeBedPE == false)
- ConvertBamToBed(bamFile, useEditDistance, tag, writeBed12, obeySplits, color, useCigar); // BED or "blocked BED"
- else
- ConvertBamToBedpe(bamFile, useEditDistance); // BEDPE
- }
- else {
- ShowHelp();
- }
+ bool obeySplits = false;
+
+ // check to see if we should print out some help
+
+ for(int i = 1; i < argc; i++) {
+ int parameterLength = (int)strlen(argv[i]);
+
+ if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
+ (PARAMETER_CHECK("--help", 5, parameterLength))) {
+ showHelp = true;
+ }
+ }
+
+ if(showHelp) ShowHelp();
+
+ // do some parsing (all of these parameters require 2 strings)
+ for(int i = 1; i < argc; i++) {
+
+ int parameterLength = (int)strlen(argv[i]);
+
+ if(PARAMETER_CHECK("-i", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ bamFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-bedpe", 6, parameterLength)) {
+ writeBedPE = true;
+ }
+ else if(PARAMETER_CHECK("-bed12", 6, parameterLength)) {
+ writeBed12 = true;
+ }
+ else if(PARAMETER_CHECK("-split", 6, parameterLength)) {
+ obeySplits = true;
+ }
+ else if(PARAMETER_CHECK("-ed", 3, parameterLength)) {
+ useEditDistance = true;
+ }
+ else if(PARAMETER_CHECK("-cigar", 6, parameterLength)) {
+ useCigar = true;
+ }
+ else if(PARAMETER_CHECK("-as", 3, parameterLength)) {
+ useAlignmentScore = true;
+ }
+ else if(PARAMETER_CHECK("-color", 6, parameterLength)) {
+ if ((i+1) < argc) {
+ haveColor = true;
+ color = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-tag", 4, parameterLength)) {
+ if ((i+1) < argc) {
+ haveOtherTag = true;
+ tag = argv[i + 1];
+ i++;
+ }
+ }
+ else {
+ cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
+ showHelp = true;
+ }
+ }
+
+ // make sure we have an input files
+ if (haveBam == false) {
+ cerr << endl << "*****" << endl << "*****ERROR: Need -i (BAM) file. " << endl << "*****" << endl;
+ showHelp = true;
+ }
+ if (haveColor == true && writeBed12 == false) {
+ cerr << endl << "*****" << endl << "*****ERROR: Cannot use color without BED12. " << endl << "*****" << endl;
+ showHelp = true;
+ }
+ if (useEditDistance == true && obeySplits == true) {
+ cerr << endl << "*****" << endl << "*****ERROR: Cannot use -ed with -splits. Edit distances cannot be computed for each \'chunk\'." << endl << "*****" << endl;
+ showHelp = true;
+ }
+ if (useEditDistance == true && useCigar == true) {
+ cerr << endl << "*****" << endl << "*****ERROR: Cannot use -cigar with -splits. Not yet supported." << endl << "*****" << endl;
+ showHelp = true;
+ }
+ if (useEditDistance == true && haveOtherTag == true) {
+ cerr << endl << "*****" << endl << "*****ERROR: Cannot use -ed with -tag. Choose one or the other." << endl << "*****" << endl;
+ showHelp = true;
+ }
+ if (writeBedPE == true && haveOtherTag == true) {
+ cerr << endl << "*****" << endl << "*****ERROR: Cannot use -tag with -bedpe." << endl << "*****" << endl;
+ showHelp = true;
+ }
+ // if there are no problems, let's convert BAM to BED or BEDPE
+ if (!showHelp) {
+ if (writeBedPE == false)
+ ConvertBamToBed(bamFile, useEditDistance, tag, writeBed12, obeySplits, color, useCigar); // BED or "blocked BED"
+ else
+ ConvertBamToBedpe(bamFile, useEditDistance); // BEDPE
+ }
+ else {
+ ShowHelp();
+ }
}
void ShowHelp(void) {
- cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
-
- cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
+ cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
+
+ cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
- cerr << "Summary: Converts BAM alignments to BED6 or BEDPE format." << endl << endl;
+ cerr << "Summary: Converts BAM alignments to BED6 or BEDPE format." << endl << endl;
- cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -i <bam> " << endl << endl;
+ cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -i <bam> " << endl << endl;
- cerr << "Options: " << endl;
-
- cerr << "\t-bedpe\t" << "Write BEDPE format." << endl;
- cerr << "\t\t- Requires BAM to be grouped or sorted by query." << endl << endl;
-
- cerr << "\t-bed12\t" << "Write \"blocked\" BED format (aka \"BED12\")." << endl << endl;
- cerr << "\t\thttp://genome-test.cse.ucsc.edu/FAQ/FAQformat#format1" << endl << endl;
+ cerr << "Options: " << endl;
- cerr << "\t-split\t" << "Report \"split\" BAM alignments as separate BED entries." << endl << endl;
-
- cerr << "\t-ed\t" << "Use BAM edit distance (NM tag) for BED score." << endl;
- cerr << "\t\t- Default for BED is to use mapping quality." << endl;
- cerr << "\t\t- Default for BEDPE is to use the minimum of" << endl;
- cerr << "\t\t the two mapping qualities for the pair." << endl;
- cerr << "\t\t- When -ed is used with -bedpe, the total edit" << endl;
- cerr << "\t\t distance from the two mates is reported." << endl << endl;
+ cerr << "\t-bedpe\t" << "Write BEDPE format." << endl;
+ cerr << "\t\t- Requires BAM to be grouped or sorted by query." << endl << endl;
- cerr << "\t-tag\t" << "Use other NUMERIC BAM alignment tag for BED score." << endl;
- cerr << "\t\t- Default for BED is to use mapping quality." << endl;
- cerr << "\t\t Disallowed with BEDPE output." << endl << endl;
+ cerr << "\t-bed12\t" << "Write \"blocked\" BED format (aka \"BED12\")." << endl << endl;
+ cerr << "\t\thttp://genome-test.cse.ucsc.edu/FAQ/FAQformat#format1" << endl << endl;
- cerr << "\t-color\t" << "An R,G,B string for the color used with BED12 format." << endl;
- cerr << "\t\tDefault is (255,0,0)." << endl << endl;
-
- cerr << "\t-cigar\t" << "Add the CIGAR string to the BED entry as a 7th column." << endl << endl;
+ cerr << "\t-split\t" << "Report \"split\" BAM alignments as separate BED entries." << endl << endl;
+ cerr << "\t-ed\t" << "Use BAM edit distance (NM tag) for BED score." << endl;
+ cerr << "\t\t- Default for BED is to use mapping quality." << endl;
+ cerr << "\t\t- Default for BEDPE is to use the minimum of" << endl;
+ cerr << "\t\t the two mapping qualities for the pair." << endl;
+ cerr << "\t\t- When -ed is used with -bedpe, the total edit" << endl;
+ cerr << "\t\t distance from the two mates is reported." << endl << endl;
- // end the program here
- exit(1);
+ cerr << "\t-tag\t" << "Use other NUMERIC BAM alignment tag for BED score." << endl;
+ cerr << "\t\t- Default for BED is to use mapping quality." << endl;
+ cerr << "\t\t Disallowed with BEDPE output." << endl << endl;
+
+ cerr << "\t-color\t" << "An R,G,B string for the color used with BED12 format." << endl;
+ cerr << "\t\tDefault is (255,0,0)." << endl << endl;
+
+ cerr << "\t-cigar\t" << "Add the CIGAR string to the BED entry as a 7th column." << endl << endl;
+
+
+ // end the program here
+ exit(1);
}
void ConvertBamToBed(const string &bamFile, const bool &useEditDistance, const string &bamTag,
const bool &writeBed12, const bool &obeySplits, const string &color, const bool &useCigar) {
- // open the BAM file
- BamReader reader;
- reader.Open(bamFile);
-
- // get header & reference information
- string header = reader.GetHeaderText();
- RefVector refs = reader.GetReferenceData();
-
- // rip through the BAM file and convert each mapped entry to BED
- BamAlignment bam;
- while (reader.GetNextAlignment(bam)) {
- if (bam.IsMapped() == true) {
- if (writeBed12 == false) // BED
- PrintBed(bam, refs, useEditDistance, bamTag, obeySplits, useCigar);
- else //"blocked" BED
- PrintBed12(bam, refs, useEditDistance, bamTag, color);
- }
- }
- reader.Close();
+ // open the BAM file
+ BamReader reader;
+ reader.Open(bamFile);
+
+ // get header & reference information
+ string header = reader.GetHeaderText();
+ RefVector refs = reader.GetReferenceData();
+
+ // rip through the BAM file and convert each mapped entry to BED
+ BamAlignment bam;
+ while (reader.GetNextAlignment(bam)) {
+ if (bam.IsMapped() == true) {
+ if (writeBed12 == false) // BED
+ PrintBed(bam, refs, useEditDistance, bamTag, obeySplits, useCigar);
+ else //"blocked" BED
+ PrintBed12(bam, refs, useEditDistance, bamTag, color);
+ }
+ }
+ reader.Close();
}
/*
Assumptions:
- 1. The BAM file is grouped/sorted by query name,
+ 1. The BAM file is grouped/sorted by query name,
not alignment position
*/
void ConvertBamToBedpe(const string &bamFile, const bool &useEditDistance) {
- // open the BAM file
- BamReader reader;
- reader.Open(bamFile);
-
- // get header & reference information
- string header = reader.GetHeaderText();
- RefVector refs = reader.GetReferenceData();
-
- // rip through the BAM file and convert each mapped entry to BEDPE
- BamAlignment bam1, bam2;
- while (reader.GetNextAlignment(bam1)) {
- // the alignment must be paired
- if (bam1.IsPaired() == true) {
- // grab the second alignment for the pair.
- reader.GetNextAlignment(bam2);
-
- // require that the alignments are from the same query
- if (bam1.Name == bam2.Name) {
- PrintBedPE(bam1, bam2, refs, useEditDistance);
- }
- else {
- cerr << "*****ERROR: -bedpe requires BAM to be sorted/grouped by query name. " << endl;
- exit(1);
- }
- }
- }
- reader.Close();
+ // open the BAM file
+ BamReader reader;
+ reader.Open(bamFile);
+
+ // get header & reference information
+ string header = reader.GetHeaderText();
+ RefVector refs = reader.GetReferenceData();
+
+ // rip through the BAM file and convert each mapped entry to BEDPE
+ BamAlignment bam1, bam2;
+ while (reader.GetNextAlignment(bam1)) {
+ // the alignment must be paired
+ if (bam1.IsPaired() == true) {
+ // grab the second alignment for the pair.
+ reader.GetNextAlignment(bam2);
+
+ // require that the alignments are from the same query
+ if (bam1.Name == bam2.Name) {
+ PrintBedPE(bam1, bam2, refs, useEditDistance);
+ }
+ else {
+ cerr << "*****ERROR: -bedpe requires BAM to be sorted/grouped by query name. " << endl;
+ exit(1);
+ }
+ }
+ }
+ reader.Close();
}
void ParseCigarBed12(const vector<CigarOp> &cigar, vector<int> &blockStarts, vector<int> &blockLengths, unsigned int &alignmentEnd) {
- int currPosition = 0;
- int blockLength = 0;
-
- // Rip through the CIGAR ops and figure out if there is more
- // than one block for this alignment
- vector<CigarOp>::const_iterator cigItr = cigar.begin();
- vector<CigarOp>::const_iterator cigEnd = cigar.end();
- for (; cigItr != cigEnd; ++cigItr) {
- switch (cigItr->Type) {
- case ('M') :
- blockLength += cigItr->Length;
- currPosition += cigItr->Length;
- case ('I') : break;
- case ('S') : break;
- case ('D') : break;
- blockLength += cigItr->Length;
- currPosition += cigItr->Length;
- case ('P') : break;
- case ('N') :
- blockStarts.push_back(currPosition + cigItr->Length);
- blockLengths.push_back(blockLength);
- currPosition += cigItr->Length;
- blockLength = 0;
- case ('H') : break; // for 'H' - do nothing, move to next op
- default :
- printf("ERROR: Invalid Cigar op type\n"); // shouldn't get here
- exit(1);
- }
- }
- // add the kast block and set the
- // alignment end (i.e., relative to the start)
- blockLengths.push_back(blockLength);
- alignmentEnd = currPosition;
+ int currPosition = 0;
+ int blockLength = 0;
+
+ // Rip through the CIGAR ops and figure out if there is more
+ // than one block for this alignment
+ vector<CigarOp>::const_iterator cigItr = cigar.begin();
+ vector<CigarOp>::const_iterator cigEnd = cigar.end();
+ for (; cigItr != cigEnd; ++cigItr) {
+ switch (cigItr->Type) {
+ case ('M') :
+ blockLength += cigItr->Length;
+ currPosition += cigItr->Length;
+ case ('I') : break;
+ case ('S') : break;
+ case ('D') : break;
+ blockLength += cigItr->Length;
+ currPosition += cigItr->Length;
+ case ('P') : break;
+ case ('N') :
+ blockStarts.push_back(currPosition + cigItr->Length);
+ blockLengths.push_back(blockLength);
+ currPosition += cigItr->Length;
+ blockLength = 0;
+ case ('H') : break; // for 'H' - do nothing, move to next op
+ default :
+ printf("ERROR: Invalid Cigar op type\n"); // shouldn't get here
+ exit(1);
+ }
+ }
+ // add the kast block and set the
+ // alignment end (i.e., relative to the start)
+ blockLengths.push_back(blockLength);
+ alignmentEnd = currPosition;
}
string BuildCigarString(const vector<CigarOp> &cigar) {
stringstream cigarString;
-
- for (size_t i = 0; i < cigar.size(); ++i) {
- //cerr << cigar[i].Type << " " << cigar[i].Length << endl;
- switch (cigar[i].Type) {
- case ('M') :
- case ('I') :
- case ('D') :
- case ('N') :
- case ('S') :
- case ('H') :
- case ('P') :
+
+ for (size_t i = 0; i < cigar.size(); ++i) {
+ //cerr << cigar[i].Type << " " << cigar[i].Length << endl;
+ switch (cigar[i].Type) {
+ case ('M') :
+ case ('I') :
+ case ('D') :
+ case ('N') :
+ case ('S') :
+ case ('H') :
+ case ('P') :
cigarString << cigar[i].Length << cigar[i].Type;
}
- }
+ }
return cigarString.str();
}
void PrintBed(const BamAlignment &bam, const RefVector &refs, bool useEditDistance, const string &bamTag, bool obeySplits, bool useCigar) {
- // set the strand
- string strand = "+";
- if (bam.IsReverseStrand() == true) strand = "-";
+ // set the strand
+ string strand = "+";
+ if (bam.IsReverseStrand() == true) strand = "-";
- // set the name of the feature based on the sequence
- string name = bam.Name;
- if (bam.IsFirstMate() == true) name += "/1";
- if (bam.IsSecondMate() == true) name += "/2";
+ // set the name of the feature based on the sequence
+ string name = bam.Name;
+ if (bam.IsFirstMate() == true) name += "/1";
+ if (bam.IsSecondMate() == true) name += "/2";
- // get the unpadded (parm = false) end position based on the CIGAR
- unsigned int alignmentEnd = bam.GetEndPosition(false);
+ // get the unpadded (parm = false) end position based on the CIGAR
+ unsigned int alignmentEnd = bam.GetEndPosition(false);
// report the entire BAM footprint as a single BED entry
if (obeySplits == false) {
- // report the alignment in BED6 format.
- if (useEditDistance == false && bamTag == "") {
- printf("%s\t%d\t%d\t\%s\t%d\t%s", refs.at(bam.RefID).RefName.c_str(), bam.Position,
- alignmentEnd, name.c_str(), bam.MapQuality, strand.c_str());
- }
- else if (useEditDistance == true && bamTag == "") {
- uint32_t editDistance;
- if (bam.GetTag("NM", editDistance)) {
- printf("%s\t%d\t%d\t\%s\t%u\t%s", refs.at(bam.RefID).RefName.c_str(), bam.Position,
- alignmentEnd, name.c_str(), editDistance, strand.c_str());
- }
- else {
- cerr << "The edit distance tag (NM) was not found in the BAM file. Please disable -ed. Exiting\n";
- exit(1);
- }
- }
- else if (useEditDistance == false && bamTag != "") {
- int32_t tagValue;
- if (bam.GetTag(bamTag, tagValue)) {
- printf("%s\t%d\t%d\t\%s\t%d\t%s", refs.at(bam.RefID).RefName.c_str(), bam.Position,
- alignmentEnd, name.c_str(), tagValue, strand.c_str());
- }
- else {
- cerr << "The requested tag (" << bamTag << ") was not found in the BAM file. Exiting\n";
- exit(1);
- }
- }
-
- // does the user want CIGAR as well?
- if (useCigar == false) {
+ // report the alignment in BED6 format.
+ if (useEditDistance == false && bamTag == "") {
+ printf("%s\t%d\t%d\t\%s\t%d\t%s", refs.at(bam.RefID).RefName.c_str(), bam.Position,
+ alignmentEnd, name.c_str(), bam.MapQuality, strand.c_str());
+ }
+ else if (useEditDistance == true && bamTag == "") {
+ uint32_t editDistance;
+ if (bam.GetTag("NM", editDistance)) {
+ printf("%s\t%d\t%d\t\%s\t%u\t%s", refs.at(bam.RefID).RefName.c_str(), bam.Position,
+ alignmentEnd, name.c_str(), editDistance, strand.c_str());
+ }
+ else {
+ cerr << "The edit distance tag (NM) was not found in the BAM file. Please disable -ed. Exiting\n";
+ exit(1);
+ }
+ }
+ else if (useEditDistance == false && bamTag != "") {
+ int32_t tagValue;
+ if (bam.GetTag(bamTag, tagValue)) {
+ printf("%s\t%d\t%d\t\%s\t%d\t%s", refs.at(bam.RefID).RefName.c_str(), bam.Position,
+ alignmentEnd, name.c_str(), tagValue, strand.c_str());
+ }
+ else {
+ cerr << "The requested tag (" << bamTag << ") was not found in the BAM file. Exiting\n";
+ exit(1);
+ }
+ }
+
+ // does the user want CIGAR as well?
+ if (useCigar == false) {
printf("\n");
- }
- else {
+ }
+ else {
string cigar = BuildCigarString(bam.CigarData);
printf("\t%s\n", cigar.c_str());
- }
- }
+ }
+ }
// Report each chunk of the BAM alignment as a discrete BED entry
// For example 10M100N10M would be reported as two seprate BED entries of length 10
- else {
+ else {
vector<BED> bedBlocks;
- // Load the alignment blocks in bam into the bedBlocks vector.
+ // Load the alignment blocks in bam into the bedBlocks vector.
// Don't trigger a new block when a "D" (deletion) CIGAR op is found.
getBamBlocks(bam, refs, bedBlocks, false);
-
+
vector<BED>::const_iterator bedItr = bedBlocks.begin();
- vector<BED>::const_iterator bedEnd = bedBlocks.end();
- for (; bedItr != bedEnd; ++bedItr) {
- printf("%s\t%d\t%d\t\%s\t%d\t%s\n", refs.at(bam.RefID).RefName.c_str(), bedItr->start,
- bedItr->end, name.c_str(), bam.MapQuality, strand.c_str());
- }
- }
+ vector<BED>::const_iterator bedEnd = bedBlocks.end();
+ for (; bedItr != bedEnd; ++bedItr) {
+ printf("%s\t%d\t%d\t\%s\t%d\t%s\n", refs.at(bam.RefID).RefName.c_str(), bedItr->start,
+ bedItr->end, name.c_str(), bam.MapQuality, strand.c_str());
+ }
+ }
}
void PrintBed12(const BamAlignment &bam, const RefVector &refs, bool useEditDistance, const string &bamTag, string color) {
- // set the strand
- string strand = "+";
- if (bam.IsReverseStrand()) strand = "-";
-
- // set the name of the feature based on the sequence
- string name = bam.Name;
- if (bam.IsFirstMate()) name += "/1";
- if (bam.IsSecondMate()) name += "/2";
-
- // parse the CIGAR string and figure out the alignment blocks
- unsigned int alignmentEnd;
- vector<int> blockLengths;
- vector<int> blockStarts;
- blockStarts.push_back(0);
-
- // extract the block starts and lengths from the CIGAR string
- ParseCigarBed12(bam.CigarData, blockStarts, blockLengths, alignmentEnd);
- alignmentEnd += bam.Position;
-
+ // set the strand
+ string strand = "+";
+ if (bam.IsReverseStrand()) strand = "-";
+
+ // set the name of the feature based on the sequence
+ string name = bam.Name;
+ if (bam.IsFirstMate()) name += "/1";
+ if (bam.IsSecondMate()) name += "/2";
+
+ // parse the CIGAR string and figure out the alignment blocks
+ unsigned int alignmentEnd;
+ vector<int> blockLengths;
+ vector<int> blockStarts;
+ blockStarts.push_back(0);
+
+ // extract the block starts and lengths from the CIGAR string
+ ParseCigarBed12(bam.CigarData, blockStarts, blockLengths, alignmentEnd);
+ alignmentEnd += bam.Position;
+
// write BED6 portion
if (useEditDistance == false && bamTag == "") {
printf("%s\t%d\t%d\t\%s\t%d\t%s\t", refs.at(bam.RefID).RefName.c_str(), bam.Position,
@@ -440,125 +440,125 @@ void PrintBed12(const BamAlignment &bam, const RefVector &refs, bool useEditDist
exit(1);
}
}
- else if (useEditDistance == false && bamTag != "") {
- int32_t tagValue;
- if (bam.GetTag(bamTag, tagValue)) {
- printf("%s\t%d\t%d\t\%s\t%d\t%s\n", refs.at(bam.RefID).RefName.c_str(), bam.Position,
- alignmentEnd, name.c_str(), tagValue, strand.c_str());
- }
- else {
- cerr << "The requested tag (" << bamTag << ") was not found in the BAM file. Exiting\n";
- exit(1);
- }
- }
-
- // write the colors, etc.
- printf("%d\t%d\t%s\t%d\t", bam.Position, alignmentEnd, color.c_str(), (int) blockStarts.size());
-
- // now write the lengths portion
- unsigned int b;
- for (b = 0; b < blockLengths.size() - 1; ++b) {
- printf("%d,", blockLengths[b]);
- }
- printf("%d\t", blockLengths[b]);
-
- // now write the starts portion
- for (b = 0; b < blockStarts.size() - 1; ++b) {
- printf("%d,", blockStarts[b]);
- }
- printf("%d\n", blockStarts[b]);
+ else if (useEditDistance == false && bamTag != "") {
+ int32_t tagValue;
+ if (bam.GetTag(bamTag, tagValue)) {
+ printf("%s\t%d\t%d\t\%s\t%d\t%s\n", refs.at(bam.RefID).RefName.c_str(), bam.Position,
+ alignmentEnd, name.c_str(), tagValue, strand.c_str());
+ }
+ else {
+ cerr << "The requested tag (" << bamTag << ") was not found in the BAM file. Exiting\n";
+ exit(1);
+ }
+ }
+
+ // write the colors, etc.
+ printf("%d\t%d\t%s\t%d\t", bam.Position, alignmentEnd, color.c_str(), (int) blockStarts.size());
+
+ // now write the lengths portion
+ unsigned int b;
+ for (b = 0; b < blockLengths.size() - 1; ++b) {
+ printf("%d,", blockLengths[b]);
+ }
+ printf("%d\t", blockLengths[b]);
+
+ // now write the starts portion
+ for (b = 0; b < blockStarts.size() - 1; ++b) {
+ printf("%d,", blockStarts[b]);
+ }
+ printf("%d\n", blockStarts[b]);
}
void PrintBedPE(const BamAlignment &bam1, const BamAlignment &bam2, const RefVector &refs, bool useEditDistance) {
- // initialize BEDPE variables
- string chrom1, chrom2, strand1, strand2;
- int start1, start2, end1, end2;
- uint32_t editDistance1, editDistance2;
- start1 = start2 = end1 = end2 = -1;
- chrom1 = chrom2 = strand1 = strand2 = ".";
- editDistance1 = editDistance2 = 0;
- uint16_t minMapQuality = 0;
-
- // extract relevant info for end 1
- if (bam1.IsMapped()) {
- chrom1 = refs.at(bam1.RefID).RefName;
- start1 = bam1.Position;
- end1 = bam1.GetEndPosition(false);
- strand1 = "+";
- if (bam1.IsReverseStrand()) strand1 = "-";
-
- // extract the edit distance from the NM tag
- // if possible. otherwise, complain.
- if (useEditDistance == true && bam1.GetTag("NM", editDistance1) == false) {
- cerr << "The edit distance tag (NM) was not found in the BAM file. Please disable -ed. Exiting\n";
- exit(1);
- }
- }
-
- // extract relevant info for end 2
- if (bam2.IsMapped()) {
- chrom2 = refs.at(bam2.RefID).RefName;
- start2 = bam2.Position;
- end2 = bam2.GetEndPosition(false);
- strand2 = "+";
- if (bam2.IsReverseStrand()) strand2 = "-";
-
- // extract the edit distance from the NM tag
- // if possible. otherwise, complain.
- if (useEditDistance == true && bam2.GetTag("NM", editDistance2) == false) {
- cerr << "The edit distance tag (NM) was not found in the BAM file. Please disable -ed. Exiting\n";
- exit(1);
- }
- }
-
- // swap the ends if necessary
- if ( chrom1 > chrom2 || ((chrom1 == chrom2) && (start1 > start2)) ) {
- swap(chrom1, chrom2);
- swap(start1, start2);
- swap(end1, end2);
- swap(strand1, strand2);
- }
-
- // report BEDPE using min mapQuality
- if (useEditDistance == false) {
- // compute the minimum mapping quality b/w the two ends of the pair.
- if (bam1.IsMapped() == true && bam2.IsMapped() == true)
- minMapQuality = min(bam1.MapQuality, bam2.MapQuality);
-
- printf("%s\t%d\t%d\t\%s\t%d\t%d\t%s\t%d\t%s\t%s\n",
- chrom1.c_str(), start1, end1, chrom2.c_str(), start2, end2,
- bam1.Name.c_str(), minMapQuality, strand1.c_str(), strand2.c_str());
- }
- // report BEDPE using total edit distance
- else {
- uint16_t totalEditDistance = 0;
- if (bam1.IsMapped() == true && bam2.IsMapped() == true)
- totalEditDistance = editDistance1 + editDistance2;
- else if (bam1.IsMapped() == true)
- totalEditDistance = editDistance1;
- else if (bam2.IsMapped() == true)
- totalEditDistance = editDistance2;
-
- printf("%s\t%d\t%d\t\%s\t%d\t%d\t%s\t%d\t%s\t%s\n",
- chrom1.c_str(), start1, end1, chrom2.c_str(), start2, end2,
- bam1.Name.c_str(), totalEditDistance, strand1.c_str(), strand2.c_str());
- }
+ // initialize BEDPE variables
+ string chrom1, chrom2, strand1, strand2;
+ int start1, start2, end1, end2;
+ uint32_t editDistance1, editDistance2;
+ start1 = start2 = end1 = end2 = -1;
+ chrom1 = chrom2 = strand1 = strand2 = ".";
+ editDistance1 = editDistance2 = 0;
+ uint16_t minMapQuality = 0;
+
+ // extract relevant info for end 1
+ if (bam1.IsMapped()) {
+ chrom1 = refs.at(bam1.RefID).RefName;
+ start1 = bam1.Position;
+ end1 = bam1.GetEndPosition(false);
+ strand1 = "+";
+ if (bam1.IsReverseStrand()) strand1 = "-";
+
+ // extract the edit distance from the NM tag
+ // if possible. otherwise, complain.
+ if (useEditDistance == true && bam1.GetTag("NM", editDistance1) == false) {
+ cerr << "The edit distance tag (NM) was not found in the BAM file. Please disable -ed. Exiting\n";
+ exit(1);
+ }
+ }
+
+ // extract relevant info for end 2
+ if (bam2.IsMapped()) {
+ chrom2 = refs.at(bam2.RefID).RefName;
+ start2 = bam2.Position;
+ end2 = bam2.GetEndPosition(false);
+ strand2 = "+";
+ if (bam2.IsReverseStrand()) strand2 = "-";
+
+ // extract the edit distance from the NM tag
+ // if possible. otherwise, complain.
+ if (useEditDistance == true && bam2.GetTag("NM", editDistance2) == false) {
+ cerr << "The edit distance tag (NM) was not found in the BAM file. Please disable -ed. Exiting\n";
+ exit(1);
+ }
+ }
+
+ // swap the ends if necessary
+ if ( chrom1 > chrom2 || ((chrom1 == chrom2) && (start1 > start2)) ) {
+ swap(chrom1, chrom2);
+ swap(start1, start2);
+ swap(end1, end2);
+ swap(strand1, strand2);
+ }
+
+ // report BEDPE using min mapQuality
+ if (useEditDistance == false) {
+ // compute the minimum mapping quality b/w the two ends of the pair.
+ if (bam1.IsMapped() == true && bam2.IsMapped() == true)
+ minMapQuality = min(bam1.MapQuality, bam2.MapQuality);
+
+ printf("%s\t%d\t%d\t\%s\t%d\t%d\t%s\t%d\t%s\t%s\n",
+ chrom1.c_str(), start1, end1, chrom2.c_str(), start2, end2,
+ bam1.Name.c_str(), minMapQuality, strand1.c_str(), strand2.c_str());
+ }
+ // report BEDPE using total edit distance
+ else {
+ uint16_t totalEditDistance = 0;
+ if (bam1.IsMapped() == true && bam2.IsMapped() == true)
+ totalEditDistance = editDistance1 + editDistance2;
+ else if (bam1.IsMapped() == true)
+ totalEditDistance = editDistance1;
+ else if (bam2.IsMapped() == true)
+ totalEditDistance = editDistance2;
+
+ printf("%s\t%d\t%d\t\%s\t%d\t%d\t%s\t%d\t%s\t%s\n",
+ chrom1.c_str(), start1, end1, chrom2.c_str(), start2, end2,
+ bam1.Name.c_str(), totalEditDistance, strand1.c_str(), strand2.c_str());
+ }
}
// deprecated.
bool IsCorrectMappingForBEDPE (const BamAlignment &bam) {
- if ( (bam.RefID == bam.MateRefID) && (bam.InsertSize > 0) ) {
- return true;
- }
- else if ( (bam.RefID == bam.MateRefID) && (bam.InsertSize == 0) && bam.IsFirstMate() ) {
- return true;
- }
- else if ( (bam.RefID != bam.MateRefID) && bam.IsFirstMate() ) {
- return true;
- }
- else return false;
+ if ( (bam.RefID == bam.MateRefID) && (bam.InsertSize > 0) ) {
+ return true;
+ }
+ else if ( (bam.RefID == bam.MateRefID) && (bam.InsertSize == 0) && bam.IsFirstMate() ) {
+ return true;
+ }
+ else if ( (bam.RefID != bam.MateRefID) && bam.IsFirstMate() ) {
+ return true;
+ }
+ else return false;
}
diff --git a/src/bed12ToBed6/bed12ToBed6.cpp b/src/bed12ToBed6/bed12ToBed6.cpp
index e73471b6176f1f99e3eb4459becaf30e5a5092ee..a0273664e04d20e4c10d91f8a3631f3cc9fccb69 100644
--- a/src/bed12ToBed6/bed12ToBed6.cpp
+++ b/src/bed12ToBed6/bed12ToBed6.cpp
@@ -37,115 +37,115 @@ void ProcessBed(istream &bedInput, BedFile *bed);
int main(int argc, char* argv[]) {
- // our configuration variables
- bool showHelp = false;
-
- // input files
- string bedFile = "stdin";
- bool haveBed = true;
-
- for(int i = 1; i < argc; i++) {
- int parameterLength = (int)strlen(argv[i]);
-
- if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
- (PARAMETER_CHECK("--help", 5, parameterLength))) {
- showHelp = true;
- }
- }
-
- if(showHelp) ShowHelp();
-
- // do some parsing (all of these parameters require 2 strings)
- for(int i = 1; i < argc; i++) {
-
- int parameterLength = (int)strlen(argv[i]);
-
- if(PARAMETER_CHECK("-i", 2, parameterLength)) {
- if ((i+1) < argc) {
- bedFile = argv[i + 1];
- i++;
- }
- }
- else {
- cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
- showHelp = true;
- }
- }
-
- // make sure we have an input files
- if (!haveBed ) {
- cerr << endl << "*****" << endl << "*****ERROR: Need -i (BED) file. " << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (!showHelp) {
- BedFile *bed = new BedFile(bedFile);
- DetermineBedInput(bed);
- }
- else {
- ShowHelp();
- }
+ // our configuration variables
+ bool showHelp = false;
+
+ // input files
+ string bedFile = "stdin";
+ bool haveBed = true;
+
+ for(int i = 1; i < argc; i++) {
+ int parameterLength = (int)strlen(argv[i]);
+
+ if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
+ (PARAMETER_CHECK("--help", 5, parameterLength))) {
+ showHelp = true;
+ }
+ }
+
+ if(showHelp) ShowHelp();
+
+ // do some parsing (all of these parameters require 2 strings)
+ for(int i = 1; i < argc; i++) {
+
+ int parameterLength = (int)strlen(argv[i]);
+
+ if(PARAMETER_CHECK("-i", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ bedFile = argv[i + 1];
+ i++;
+ }
+ }
+ else {
+ cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
+ showHelp = true;
+ }
+ }
+
+ // make sure we have an input files
+ if (!haveBed ) {
+ cerr << endl << "*****" << endl << "*****ERROR: Need -i (BED) file. " << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (!showHelp) {
+ BedFile *bed = new BedFile(bedFile);
+ DetermineBedInput(bed);
+ }
+ else {
+ ShowHelp();
+ }
}
void ShowHelp(void) {
- cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
-
- cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
+ cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
- cerr << "Summary: Splits BED12 features into discrete BED6 features." << endl << endl;
+ cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
- cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -i <bed12>" << endl << endl;
+ cerr << "Summary: Splits BED12 features into discrete BED6 features." << endl << endl;
+ cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -i <bed12>" << endl << endl;
- // end the program here
- exit(1);
+
+ // end the program here
+ exit(1);
}
void DetermineBedInput(BedFile *bed) {
-
- // dealing with a proper file
- if (bed->bedFile != "stdin") {
-
- ifstream bedStream(bed->bedFile.c_str(), ios::in);
- if ( !bedStream ) {
- cerr << "Error: The requested bed file (" << bed->bedFile << ") could not be opened. Exiting!" << endl;
- exit (1);
- }
- ProcessBed(bedStream, bed);
- }
- // reading from stdin
- else {
- ProcessBed(cin, bed);
- }
+
+ // dealing with a proper file
+ if (bed->bedFile != "stdin") {
+
+ ifstream bedStream(bed->bedFile.c_str(), ios::in);
+ if ( !bedStream ) {
+ cerr << "Error: The requested bed file (" << bed->bedFile << ") could not be opened. Exiting!" << endl;
+ exit (1);
+ }
+ ProcessBed(bedStream, bed);
+ }
+ // reading from stdin
+ else {
+ ProcessBed(cin, bed);
+ }
}
void ProcessBed(istream &bedInput, BedFile *bed) {
- // process each BED entry and convert to BAM
- BED bedEntry, nullBed;
- int lineNum = 0;
- BedLineStatus bedStatus;
- // open the BED file for reading.
- bed->Open();
- while ((bedStatus = bed->GetNextBed(bedEntry, lineNum)) != BED_INVALID) {
- if (bedStatus == BED_VALID) {
-
- bedVector bedBlocks; // vec to store the discrete BED "blocks" from a
+ // process each BED entry and convert to BAM
+ BED bedEntry, nullBed;
+ int lineNum = 0;
+ BedLineStatus bedStatus;
+ // open the BED file for reading.
+ bed->Open();
+ while ((bedStatus = bed->GetNextBed(bedEntry, lineNum)) != BED_INVALID) {
+ if (bedStatus == BED_VALID) {
+
+ bedVector bedBlocks; // vec to store the discrete BED "blocks" from a
splitBedIntoBlocks(bedEntry, lineNum, bedBlocks);
-
+
vector<BED>::const_iterator bedItr = bedBlocks.begin();
- vector<BED>::const_iterator bedEnd = bedBlocks.end();
- for (; bedItr != bedEnd; ++bedItr) {
- printf ("%s\t%d\t%d\t%s\t%s\t%s\n", bedItr->chrom.c_str(), bedItr->start, bedItr->end, bedItr->name.c_str(),
- bedItr->score.c_str(), bedItr->strand.c_str());
- }
- bedEntry = nullBed;
- }
- }
- // close up
- bed->Close();
+ vector<BED>::const_iterator bedEnd = bedBlocks.end();
+ for (; bedItr != bedEnd; ++bedItr) {
+ printf ("%s\t%d\t%d\t%s\t%s\t%s\n", bedItr->chrom.c_str(), bedItr->start, bedItr->end, bedItr->name.c_str(),
+ bedItr->score.c_str(), bedItr->strand.c_str());
+ }
+ bedEntry = nullBed;
+ }
+ }
+ // close up
+ bed->Close();
}
diff --git a/src/bedToBam/bedToBam.cpp b/src/bedToBam/bedToBam.cpp
index 010fbb20fabdc202fd15c322a50981d5efc49cc0..78d9f6d65760af41c509316e56ff53e098267f75 100644
--- a/src/bedToBam/bedToBam.cpp
+++ b/src/bedToBam/bedToBam.cpp
@@ -45,309 +45,309 @@ int reg2bin(int beg, int end);
int main(int argc, char* argv[]) {
- // our configuration variables
- bool showHelp = false;
-
- // input files
- string bedFile = "stdin";
- string genomeFile;
-
- unsigned int mapQual = 255;
-
- bool haveBed = true;
- bool haveGenome = false;
- bool haveMapQual = false;
- bool isBED12 = false;
- bool uncompressedBam = false;
-
- for(int i = 1; i < argc; i++) {
- int parameterLength = (int)strlen(argv[i]);
-
- if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
- (PARAMETER_CHECK("--help", 5, parameterLength))) {
- showHelp = true;
- }
- }
-
- if(showHelp) ShowHelp();
-
- // do some parsing (all of these parameters require 2 strings)
- for(int i = 1; i < argc; i++) {
-
- int parameterLength = (int)strlen(argv[i]);
-
- if(PARAMETER_CHECK("-i", 2, parameterLength)) {
- if ((i+1) < argc) {
- bedFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-g", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveGenome = true;
- genomeFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-mapq", 5, parameterLength)) {
- haveMapQual = true;
- if ((i+1) < argc) {
- mapQual = atoi(argv[i + 1]);
- i++;
- }
- }
- else if(PARAMETER_CHECK("-bed12", 6, parameterLength)) {
- isBED12 = true;
- }
- else if(PARAMETER_CHECK("-ubam", 5, parameterLength)) {
+ // our configuration variables
+ bool showHelp = false;
+
+ // input files
+ string bedFile = "stdin";
+ string genomeFile;
+
+ unsigned int mapQual = 255;
+
+ bool haveBed = true;
+ bool haveGenome = false;
+ bool haveMapQual = false;
+ bool isBED12 = false;
+ bool uncompressedBam = false;
+
+ for(int i = 1; i < argc; i++) {
+ int parameterLength = (int)strlen(argv[i]);
+
+ if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
+ (PARAMETER_CHECK("--help", 5, parameterLength))) {
+ showHelp = true;
+ }
+ }
+
+ if(showHelp) ShowHelp();
+
+ // do some parsing (all of these parameters require 2 strings)
+ for(int i = 1; i < argc; i++) {
+
+ int parameterLength = (int)strlen(argv[i]);
+
+ if(PARAMETER_CHECK("-i", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ bedFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-g", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveGenome = true;
+ genomeFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-mapq", 5, parameterLength)) {
+ haveMapQual = true;
+ if ((i+1) < argc) {
+ mapQual = atoi(argv[i + 1]);
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-bed12", 6, parameterLength)) {
+ isBED12 = true;
+ }
+ else if(PARAMETER_CHECK("-ubam", 5, parameterLength)) {
uncompressedBam = true;
- }
- else {
- cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
- showHelp = true;
- }
- }
-
- // make sure we have an input files
- if (!haveBed ) {
- cerr << endl << "*****" << endl << "*****ERROR: Need -i (BED) file. " << endl << "*****" << endl;
- showHelp = true;
- }
- if (!haveGenome ) {
- cerr << endl << "*****" << endl << "*****ERROR: Need -g (genome) file. " << endl << "*****" << endl;
- showHelp = true;
- }
- if (mapQual < 0 || mapQual > 255) {
- cerr << endl << "*****" << endl << "*****ERROR: MAPQ must be in range [0,255]. " << endl << "*****" << endl;
- showHelp = true;
- }
-
-
- if (!showHelp) {
- BedFile *bed = new BedFile(bedFile);
- GenomeFile *genome = new GenomeFile(genomeFile);
-
+ }
+ else {
+ cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
+ showHelp = true;
+ }
+ }
+
+ // make sure we have an input files
+ if (!haveBed ) {
+ cerr << endl << "*****" << endl << "*****ERROR: Need -i (BED) file. " << endl << "*****" << endl;
+ showHelp = true;
+ }
+ if (!haveGenome ) {
+ cerr << endl << "*****" << endl << "*****ERROR: Need -g (genome) file. " << endl << "*****" << endl;
+ showHelp = true;
+ }
+ if (mapQual < 0 || mapQual > 255) {
+ cerr << endl << "*****" << endl << "*****ERROR: MAPQ must be in range [0,255]. " << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+
+ if (!showHelp) {
+ BedFile *bed = new BedFile(bedFile);
+ GenomeFile *genome = new GenomeFile(genomeFile);
+
ProcessBed(cin, bed, genome, isBED12, mapQual, uncompressedBam);
- }
- else {
- ShowHelp();
- }
+ }
+ else {
+ ShowHelp();
+ }
}
void ShowHelp(void) {
- cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
-
- cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
+ cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
+
+ cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
- cerr << "Summary: Converts feature records to BAM format." << endl << endl;
+ cerr << "Summary: Converts feature records to BAM format." << endl << endl;
- cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -i <bed/gff/vcf> -g <genome>" << endl << endl;
+ cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -i <bed/gff/vcf> -g <genome>" << endl << endl;
- cerr << "Options: " << endl;
+ cerr << "Options: " << endl;
- cerr << "\t-mapq\t" << "Set the mappinq quality for the BAM records." << endl;
- cerr << "\t\t(INT) Default: 255" << endl << endl;
+ cerr << "\t-mapq\t" << "Set the mappinq quality for the BAM records." << endl;
+ cerr << "\t\t(INT) Default: 255" << endl << endl;
- cerr << "\t-bed12\t" << "The BED file is in BED12 format. The BAM CIGAR" << endl;
- cerr << "\t\tstring will reflect BED \"blocks\"." << endl << endl;
+ cerr << "\t-bed12\t" << "The BED file is in BED12 format. The BAM CIGAR" << endl;
+ cerr << "\t\tstring will reflect BED \"blocks\"." << endl << endl;
- cerr << "\t-ubam\t" << "Write uncompressed BAM output. Default is to write compressed BAM." << endl << endl;
+ cerr << "\t-ubam\t" << "Write uncompressed BAM output. Default is to write compressed BAM." << endl << endl;
- cerr << "Notes: " << endl;
- cerr << "\t(1) BED files must be at least BED4 to be amenable to BAM (needs name field)." << endl << endl;
+ cerr << "Notes: " << endl;
+ cerr << "\t(1) BED files must be at least BED4 to be amenable to BAM (needs name field)." << endl << endl;
- // end the program here
- exit(1);
+ // end the program here
+ exit(1);
}
void ProcessBed(istream &bedInput, BedFile *bed, GenomeFile *genome, bool isBED12, int mapQual, bool uncompressedBam) {
- BamWriter *writer = new BamWriter();
-
- // build a BAM header from the genomeFile
- RefVector refs;
- string bamHeader;
- map<string, int, std::less<string> > chromToId;
- MakeBamHeader(genome->getGenomeFileName(), refs, bamHeader, chromToId);
-
- // open a BAM and add the reference headers to the BAM file
- writer->Open("stdout", bamHeader, refs, uncompressedBam);
-
-
- // process each BED entry and convert to BAM
- BED bedEntry, nullBed;
- int lineNum = 0;
- BedLineStatus bedStatus;
- // open the BED file for reading.
- bed->Open();
- while ((bedStatus = bed->GetNextBed(bedEntry, lineNum)) != BED_INVALID) {
- if (bedStatus == BED_VALID) {
- BamAlignment bamEntry;
- if (bed->bedType >= 4) {
- ConvertBedToBam(bedEntry, bamEntry, chromToId, isBED12, mapQual, lineNum);
- writer->SaveAlignment(bamEntry);
- }
- else {
- cerr << "Error: BED entry without name found at line: " << lineNum << ". Exiting!" << endl;
- exit (1);
- }
- bedEntry = nullBed;
- }
- }
- // close up
- bed->Close();
- writer->Close();
+ BamWriter *writer = new BamWriter();
+
+ // build a BAM header from the genomeFile
+ RefVector refs;
+ string bamHeader;
+ map<string, int, std::less<string> > chromToId;
+ MakeBamHeader(genome->getGenomeFileName(), refs, bamHeader, chromToId);
+
+ // open a BAM and add the reference headers to the BAM file
+ writer->Open("stdout", bamHeader, refs, uncompressedBam);
+
+
+ // process each BED entry and convert to BAM
+ BED bedEntry, nullBed;
+ int lineNum = 0;
+ BedLineStatus bedStatus;
+ // open the BED file for reading.
+ bed->Open();
+ while ((bedStatus = bed->GetNextBed(bedEntry, lineNum)) != BED_INVALID) {
+ if (bedStatus == BED_VALID) {
+ BamAlignment bamEntry;
+ if (bed->bedType >= 4) {
+ ConvertBedToBam(bedEntry, bamEntry, chromToId, isBED12, mapQual, lineNum);
+ writer->SaveAlignment(bamEntry);
+ }
+ else {
+ cerr << "Error: BED entry without name found at line: " << lineNum << ". Exiting!" << endl;
+ exit (1);
+ }
+ bedEntry = nullBed;
+ }
+ }
+ // close up
+ bed->Close();
+ writer->Close();
}
-void ConvertBedToBam(const BED &bed, BamAlignment &bam, map<string, int, std::less<string> > &chromToId,
+void ConvertBedToBam(const BED &bed, BamAlignment &bam, map<string, int, std::less<string> > &chromToId,
bool isBED12, int mapQual, int lineNum) {
-
- bam.Name = bed.name;
- bam.Position = bed.start;
- bam.Bin = reg2bin(bed.start, bed.end);
-
- // hard-code the sequence and qualities.
- int bedLength = bed.end - bed.start;
-
- // set dummy seq and qual strings. the input is BED,
- // so the sequence is inherently the same as it's
- // reference genome.
- // Thanks to James M. Ward for pointing this out.
- bam.QueryBases = "";
- bam.Qualities = "";
-
- // chrom and map quality
- bam.RefID = chromToId[bed.chrom];
- bam.MapQuality = mapQual;
-
- // set the BAM FLAG
- bam.AlignmentFlag = 0;
- if (bed.strand == "-")
- bam.SetIsReverseStrand(true);
-
- bam.MatePosition = -1;
- bam.InsertSize = 0;
- bam.MateRefID = -1;
-
- bam.CigarData.clear();
-
- if (isBED12 == false) {
- CigarOp cOp;
- cOp.Type = 'M';
- cOp.Length = bedLength;
- bam.CigarData.push_back(cOp);
- }
- // we're being told that the input is BED12.
- else{
-
- // does it smell like BED12? if so, process it.
- if (bed.otherFields.size() == 6) {
-
- // extract the relevant BED fields to convert BED12 to BAM
- // namely: blockCount, blockStarts, blockEnds
- unsigned int blockCount = atoi(bed.otherFields[3].c_str());
-
- vector<int> blockSizes, blockStarts;
- Tokenize(bed.otherFields[4], blockSizes, ",");
- Tokenize(bed.otherFields[5], blockStarts, ",");
-
- // make sure this is a well-formed BED12 entry.
- if (blockSizes.size() != blockCount) {
- cerr << "Error: Number of BED blocks does not match blockCount at line: " << lineNum << ". Exiting!" << endl;
- exit (1);
- }
- else {
- // does the first block start after the bed.start?
- // if so, we need to do some "splicing"
- if (blockStarts[0] > 0) {
- CigarOp cOp;
- cOp.Length = blockStarts[0];
- cOp.Type = 'N';
- bam.CigarData.push_back(cOp);
- }
- // handle the "middle" blocks
- for (unsigned int i = 0; i < blockCount - 1; ++i) {
- CigarOp cOp;
- cOp.Length = blockSizes[i];
- cOp.Type = 'M';
- bam.CigarData.push_back(cOp);
-
- if (blockStarts[i+1] > (blockStarts[i] + blockSizes[i])) {
- CigarOp cOp;
- cOp.Length = (blockStarts[i+1] - (blockStarts[i] + blockSizes[i]));
- cOp.Type = 'N';
- bam.CigarData.push_back(cOp);
- }
- }
- // handle the last block.
- CigarOp cOp;
- cOp.Length = blockSizes[blockCount - 1];
- cOp.Type = 'M';
- bam.CigarData.push_back(cOp);
- }
- }
- // it doesn't smell like BED12. complain.
- else {
- cerr << "You've indicated that the input file is in BED12 format, yet the relevant fields cannot be found. Exiting." << endl << endl;
- exit(1);
- }
- }
+
+ bam.Name = bed.name;
+ bam.Position = bed.start;
+ bam.Bin = reg2bin(bed.start, bed.end);
+
+ // hard-code the sequence and qualities.
+ int bedLength = bed.end - bed.start;
+
+ // set dummy seq and qual strings. the input is BED,
+ // so the sequence is inherently the same as it's
+ // reference genome.
+ // Thanks to James M. Ward for pointing this out.
+ bam.QueryBases = "";
+ bam.Qualities = "";
+
+ // chrom and map quality
+ bam.RefID = chromToId[bed.chrom];
+ bam.MapQuality = mapQual;
+
+ // set the BAM FLAG
+ bam.AlignmentFlag = 0;
+ if (bed.strand == "-")
+ bam.SetIsReverseStrand(true);
+
+ bam.MatePosition = -1;
+ bam.InsertSize = 0;
+ bam.MateRefID = -1;
+
+ bam.CigarData.clear();
+
+ if (isBED12 == false) {
+ CigarOp cOp;
+ cOp.Type = 'M';
+ cOp.Length = bedLength;
+ bam.CigarData.push_back(cOp);
+ }
+ // we're being told that the input is BED12.
+ else{
+
+ // does it smell like BED12? if so, process it.
+ if (bed.otherFields.size() == 6) {
+
+ // extract the relevant BED fields to convert BED12 to BAM
+ // namely: blockCount, blockStarts, blockEnds
+ unsigned int blockCount = atoi(bed.otherFields[3].c_str());
+
+ vector<int> blockSizes, blockStarts;
+ Tokenize(bed.otherFields[4], blockSizes, ",");
+ Tokenize(bed.otherFields[5], blockStarts, ",");
+
+ // make sure this is a well-formed BED12 entry.
+ if (blockSizes.size() != blockCount) {
+ cerr << "Error: Number of BED blocks does not match blockCount at line: " << lineNum << ". Exiting!" << endl;
+ exit (1);
+ }
+ else {
+ // does the first block start after the bed.start?
+ // if so, we need to do some "splicing"
+ if (blockStarts[0] > 0) {
+ CigarOp cOp;
+ cOp.Length = blockStarts[0];
+ cOp.Type = 'N';
+ bam.CigarData.push_back(cOp);
+ }
+ // handle the "middle" blocks
+ for (unsigned int i = 0; i < blockCount - 1; ++i) {
+ CigarOp cOp;
+ cOp.Length = blockSizes[i];
+ cOp.Type = 'M';
+ bam.CigarData.push_back(cOp);
+
+ if (blockStarts[i+1] > (blockStarts[i] + blockSizes[i])) {
+ CigarOp cOp;
+ cOp.Length = (blockStarts[i+1] - (blockStarts[i] + blockSizes[i]));
+ cOp.Type = 'N';
+ bam.CigarData.push_back(cOp);
+ }
+ }
+ // handle the last block.
+ CigarOp cOp;
+ cOp.Length = blockSizes[blockCount - 1];
+ cOp.Type = 'M';
+ bam.CigarData.push_back(cOp);
+ }
+ }
+ // it doesn't smell like BED12. complain.
+ else {
+ cerr << "You've indicated that the input file is in BED12 format, yet the relevant fields cannot be found. Exiting." << endl << endl;
+ exit(1);
+ }
+ }
}
-void MakeBamHeader(const string &genomeFile, RefVector &refs, string &header,
+void MakeBamHeader(const string &genomeFile, RefVector &refs, string &header,
map<string, int, std::less<string> > &chromToId) {
-
- // make a genome map of the genome file.
- GenomeFile genome(genomeFile);
-
- header += "@HD\tVN:1.0\tSO:unsorted\n";
- header += "@PG\tID:BEDTools_bedToBam\tVN:V";
- header += VERSION;
- header += "\n";
-
- int chromId = 0;
- vector<string> chromList = genome.getChromList();
- sort(chromList.begin(), chromList.end());
-
- // create a BAM header (@SQ) entry for each chrom in the BEDTools genome file.
- vector<string>::const_iterator genomeItr = chromList.begin();
- vector<string>::const_iterator genomeEnd = chromList.end();
- for (; genomeItr != genomeEnd; ++genomeItr) {
- chromToId[*genomeItr] = chromId;
- chromId++;
-
- // add to the header text
- int size = genome.getChromSize(*genomeItr);
- string chromLine = "@SQ\tSN:" + *genomeItr + "\tAS:" + genomeFile + "\tLN:" + ToString(size) + "\n";
- header += chromLine;
-
- // create a chrom entry and add it to
- // the RefVector
- RefData chrom;
- chrom.RefName = *genomeItr;
- chrom.RefLength = size;
- chrom.RefHasAlignments = false;
- refs.push_back(chrom);
- }
+
+ // make a genome map of the genome file.
+ GenomeFile genome(genomeFile);
+
+ header += "@HD\tVN:1.0\tSO:unsorted\n";
+ header += "@PG\tID:BEDTools_bedToBam\tVN:V";
+ header += VERSION;
+ header += "\n";
+
+ int chromId = 0;
+ vector<string> chromList = genome.getChromList();
+ sort(chromList.begin(), chromList.end());
+
+ // create a BAM header (@SQ) entry for each chrom in the BEDTools genome file.
+ vector<string>::const_iterator genomeItr = chromList.begin();
+ vector<string>::const_iterator genomeEnd = chromList.end();
+ for (; genomeItr != genomeEnd; ++genomeItr) {
+ chromToId[*genomeItr] = chromId;
+ chromId++;
+
+ // add to the header text
+ int size = genome.getChromSize(*genomeItr);
+ string chromLine = "@SQ\tSN:" + *genomeItr + "\tAS:" + genomeFile + "\tLN:" + ToString(size) + "\n";
+ header += chromLine;
+
+ // create a chrom entry and add it to
+ // the RefVector
+ RefData chrom;
+ chrom.RefName = *genomeItr;
+ chrom.RefLength = size;
+ chrom.RefHasAlignments = false;
+ refs.push_back(chrom);
+ }
}
/* Taken directly from the SAMTools spec
calculate bin given an alignment in [beg,end) (zero-based, half-close, half-open) */
int reg2bin(int beg, int end) {
- --end;
- if (beg>>14 == end>>14) return ((1<<15)-1)/7 + (beg>>14);
- if (beg>>17 == end>>17) return ((1<<12)-1)/7 + (beg>>17);
- if (beg>>20 == end>>20) return ((1<<9)-1)/7 + (beg>>20);
- if (beg>>23 == end>>23) return ((1<<6)-1)/7 + (beg>>23);
- if (beg>>26 == end>>26) return ((1<<3)-1)/7 + (beg>>26);
- return 0;
-}
+ --end;
+ if (beg>>14 == end>>14) return ((1<<15)-1)/7 + (beg>>14);
+ if (beg>>17 == end>>17) return ((1<<12)-1)/7 + (beg>>17);
+ if (beg>>20 == end>>20) return ((1<<9)-1)/7 + (beg>>20);
+ if (beg>>23 == end>>23) return ((1<<6)-1)/7 + (beg>>23);
+ if (beg>>26 == end>>26) return ((1<<3)-1)/7 + (beg>>26);
+ return 0;
+}
diff --git a/src/bedToIgv/bedToIgv.cpp b/src/bedToIgv/bedToIgv.cpp
index 66ce31dd8cf9987fe47db7a971b182201e6bdba6..d98e80f96f2d632a63606ae0d98462b54db13a49 100644
--- a/src/bedToIgv/bedToIgv.cpp
+++ b/src/bedToIgv/bedToIgv.cpp
@@ -30,7 +30,7 @@ using namespace std;
// function declarations
void ShowHelp(void);
-void DetermineBedInput(BedFile *bed, string path, string sortType, string session,
+void DetermineBedInput(BedFile *bed, string path, string sortType, string session,
bool collapse, bool useNames, string imageType, int slop);
void ProcessBed(istream &bedInput, BedFile *bed, string path, string sortType, string session,
bool collapse, bool useNames, string imageType, int slop);
@@ -38,181 +38,181 @@ void ProcessBed(istream &bedInput, BedFile *bed, string path, string sortType, s
int main(int argc, char* argv[]) {
- // our configuration variables
- bool showHelp = false;
+ // our configuration variables
+ bool showHelp = false;
- // input files
- string bedFile = "stdin";
+ // input files
+ string bedFile = "stdin";
string imagePath = "./";
string sortType = "none";
- string session = "none";
+ string session = "none";
int slop = 0;
string imageType = "png";
-
- bool haveBed = true;
- bool collapse = false;
+
+ bool haveBed = true;
+ bool collapse = false;
bool useNames = false;
- for(int i = 1; i < argc; i++) {
- int parameterLength = (int)strlen(argv[i]);
-
- if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
- (PARAMETER_CHECK("--help", 5, parameterLength))) {
- showHelp = true;
- }
- }
-
- if(showHelp) ShowHelp();
-
- // do some parsing (all of these parameters require 2 strings)
- for(int i = 1; i < argc; i++) {
-
- int parameterLength = (int)strlen(argv[i]);
-
- if(PARAMETER_CHECK("-i", 2, parameterLength)) {
- if ((i+1) < argc) {
- bedFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-path", 5, parameterLength)) {
- if ((i+1) < argc) {
- imagePath = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-sort", 5, parameterLength)) {
- if ((i+1) < argc) {
- sortType = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-sess", 5, parameterLength)) {
- if ((i+1) < argc) {
- session = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-clps", 5, parameterLength)) {
+ for(int i = 1; i < argc; i++) {
+ int parameterLength = (int)strlen(argv[i]);
+
+ if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
+ (PARAMETER_CHECK("--help", 5, parameterLength))) {
+ showHelp = true;
+ }
+ }
+
+ if(showHelp) ShowHelp();
+
+ // do some parsing (all of these parameters require 2 strings)
+ for(int i = 1; i < argc; i++) {
+
+ int parameterLength = (int)strlen(argv[i]);
+
+ if(PARAMETER_CHECK("-i", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ bedFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-path", 5, parameterLength)) {
+ if ((i+1) < argc) {
+ imagePath = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-sort", 5, parameterLength)) {
+ if ((i+1) < argc) {
+ sortType = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-sess", 5, parameterLength)) {
+ if ((i+1) < argc) {
+ session = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-clps", 5, parameterLength)) {
collapse = true;
- }
- else if(PARAMETER_CHECK("-name", 5, parameterLength)) {
+ }
+ else if(PARAMETER_CHECK("-name", 5, parameterLength)) {
useNames = true;
- }
- else if(PARAMETER_CHECK("-slop", 5, parameterLength)) {
- if ((i+1) < argc) {
- slop = atoi(argv[i + 1]);
- i++;
- }
- }
- else if(PARAMETER_CHECK("-img", 4, parameterLength)) {
- if ((i+1) < argc) {
- imageType = argv[i + 1];
- i++;
- }
- }
- else {
- cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
- showHelp = true;
- }
- }
-
- // make sure we have an input files
- if (!haveBed ) {
- cerr << endl << "*****" << endl << "*****ERROR: Need -i (BED) file. " << endl << "*****" << endl;
- showHelp = true;
- }
- if (sortType != "none") {
- if ((sortType != "base") && (sortType != "position") && (sortType != "strand") &&
- (sortType != "quality") && (sortType != "sample") && (sortType != "readGroup")) {
- cerr << endl << "*****" << endl << "*****ERROR: Invalid sort option. " << endl << "*****" << endl;
- showHelp = true;
- }
- }
+ }
+ else if(PARAMETER_CHECK("-slop", 5, parameterLength)) {
+ if ((i+1) < argc) {
+ slop = atoi(argv[i + 1]);
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-img", 4, parameterLength)) {
+ if ((i+1) < argc) {
+ imageType = argv[i + 1];
+ i++;
+ }
+ }
+ else {
+ cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
+ showHelp = true;
+ }
+ }
+
+ // make sure we have an input files
+ if (!haveBed ) {
+ cerr << endl << "*****" << endl << "*****ERROR: Need -i (BED) file. " << endl << "*****" << endl;
+ showHelp = true;
+ }
+ if (sortType != "none") {
+ if ((sortType != "base") && (sortType != "position") && (sortType != "strand") &&
+ (sortType != "quality") && (sortType != "sample") && (sortType != "readGroup")) {
+ cerr << endl << "*****" << endl << "*****ERROR: Invalid sort option. " << endl << "*****" << endl;
+ showHelp = true;
+ }
+ }
if (slop < 0) {
- cerr << endl << "*****" << endl << "*****ERROR: Slop must be >= 0. " << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (!showHelp) {
- BedFile *bed = new BedFile(bedFile);
- DetermineBedInput(bed, imagePath, sortType, session, collapse, useNames, imageType, slop);
- }
- else {
- ShowHelp();
- }
+ cerr << endl << "*****" << endl << "*****ERROR: Slop must be >= 0. " << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (!showHelp) {
+ BedFile *bed = new BedFile(bedFile);
+ DetermineBedInput(bed, imagePath, sortType, session, collapse, useNames, imageType, slop);
+ }
+ else {
+ ShowHelp();
+ }
}
void ShowHelp(void) {
- cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
-
- cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
+ cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
- cerr << "Summary: Creates a batch script to create IGV images " << endl;
- cerr << " at each interval defined in a BED/GFF/VCF file." << endl << endl;
+ cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
- cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -i <bed/gff/vcf>" << endl << endl;
+ cerr << "Summary: Creates a batch script to create IGV images " << endl;
+ cerr << " at each interval defined in a BED/GFF/VCF file." << endl << endl;
- cerr << "Options: " << endl;
+ cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -i <bed/gff/vcf>" << endl << endl;
- cerr << "\t-path\t" << "The full path to which the IGV snapshots should be written." << endl;
- cerr << "\t\t(STRING) Default: ./" << endl << endl;
+ cerr << "Options: " << endl;
- cerr << "\t-sess\t" << "The full path to an existing IGV session file to be " << endl;
- cerr << "\t\tloaded prior to taking snapshots." << endl << endl;
- cerr << "\t\t(STRING) Default is for no session to be loaded." << endl << endl;
-
- cerr << "\t-sort\t" << "The type of BAM sorting you would like to apply to each image. " << endl;
- cerr << "\t\tOptions: base, position, strand, quality, sample, and readGroup" << endl;
- cerr << "\t\tDefault is to apply no sorting at all." << endl << endl;
+ cerr << "\t-path\t" << "The full path to which the IGV snapshots should be written." << endl;
+ cerr << "\t\t(STRING) Default: ./" << endl << endl;
- cerr << "\t-clps\t" << "Collapse the aligned reads prior to taking a snapshot. " << endl;
- cerr << "\t\tDefault is to no collapse." << endl << endl;
+ cerr << "\t-sess\t" << "The full path to an existing IGV session file to be " << endl;
+ cerr << "\t\tloaded prior to taking snapshots." << endl << endl;
+ cerr << "\t\t(STRING) Default is for no session to be loaded." << endl << endl;
- cerr << "\t-name\t" << "Use the \"name\" field (column 4) for each image's filename. " << endl;
- cerr << "\t\tDefault is to use the \"chr:start-pos.ext\"." << endl << endl;
-
- cerr << "\t-slop\t" << "Number of flanking base pairs on the left & right of the image." << endl;
- cerr << "\t\t- (INT) Default = 0." << endl << endl;
+ cerr << "\t-sort\t" << "The type of BAM sorting you would like to apply to each image. " << endl;
+ cerr << "\t\tOptions: base, position, strand, quality, sample, and readGroup" << endl;
+ cerr << "\t\tDefault is to apply no sorting at all." << endl << endl;
- cerr << "\t-img\t" << "The type of image to be created. " << endl;
- cerr << "\t\tOptions: png, eps, svg" << endl;
- cerr << "\t\tDefault is png." << endl << endl;
+ cerr << "\t-clps\t" << "Collapse the aligned reads prior to taking a snapshot. " << endl;
+ cerr << "\t\tDefault is to no collapse." << endl << endl;
- cerr << "Notes: " << endl;
- cerr << "\t(1) The resulting script is meant to be run from within the IGV GUI version 1.5 or later." << endl;
+ cerr << "\t-name\t" << "Use the \"name\" field (column 4) for each image's filename. " << endl;
+ cerr << "\t\tDefault is to use the \"chr:start-pos.ext\"." << endl << endl;
+
+ cerr << "\t-slop\t" << "Number of flanking base pairs on the left & right of the image." << endl;
+ cerr << "\t\t- (INT) Default = 0." << endl << endl;
+
+ cerr << "\t-img\t" << "The type of image to be created. " << endl;
+ cerr << "\t\tOptions: png, eps, svg" << endl;
+ cerr << "\t\tDefault is png." << endl << endl;
+
+ cerr << "Notes: " << endl;
+ cerr << "\t(1) The resulting script is meant to be run from within the IGV GUI version 1.5 or later." << endl;
cerr << "\t(2) Unless you use the -sess option, it is assumed that prior to running the script, " << endl;
cerr << "\t\tyou have loaded the proper genome, tracks and data files." << endl << endl;
- // end the program here
- exit(1);
+ // end the program here
+ exit(1);
}
-void DetermineBedInput(BedFile *bed, string path, string sortType, string session,
+void DetermineBedInput(BedFile *bed, string path, string sortType, string session,
bool collapse, bool useNames, string imageType, int slop) {
-
- // dealing with a proper file
- if (bed->bedFile != "stdin") {
-
- ifstream bedStream(bed->bedFile.c_str(), ios::in);
- if ( !bedStream ) {
- cerr << "Error: The requested bed file (" << bed->bedFile << ") could not be opened. Exiting!" << endl;
- exit (1);
- }
- ProcessBed(bedStream, bed, path, sortType, session, collapse, useNames, imageType, slop);
- }
- // reading from stdin
- else {
- ProcessBed(cin, bed, path, sortType, session, collapse, useNames, imageType, slop);
- }
+
+ // dealing with a proper file
+ if (bed->bedFile != "stdin") {
+
+ ifstream bedStream(bed->bedFile.c_str(), ios::in);
+ if ( !bedStream ) {
+ cerr << "Error: The requested bed file (" << bed->bedFile << ") could not be opened. Exiting!" << endl;
+ exit (1);
+ }
+ ProcessBed(bedStream, bed, path, sortType, session, collapse, useNames, imageType, slop);
+ }
+ // reading from stdin
+ else {
+ ProcessBed(cin, bed, path, sortType, session, collapse, useNames, imageType, slop);
+ }
}
-void ProcessBed(istream &bedInput, BedFile *bed, string path, string sortType, string session,
+void ProcessBed(istream &bedInput, BedFile *bed, string path, string sortType, string session,
bool collapse, bool useNames, string imageType, int slop) {
// set the image path
@@ -221,27 +221,27 @@ void ProcessBed(istream &bedInput, BedFile *bed, string path, string sortType, s
// should we load a session
if (session != "none")
cout << "load " << session << endl;
-
-
- BED bedEntry, nullBed;
- int lineNum = 0;
- BedLineStatus bedStatus;
-
- bed->Open();
- // process each BED entry and convert to an IGV request
- while ((bedStatus = bed->GetNextBed(bedEntry, lineNum)) != BED_INVALID) {
- if (bedStatus == BED_VALID) {
-
+
+
+ BED bedEntry, nullBed;
+ int lineNum = 0;
+ BedLineStatus bedStatus;
+
+ bed->Open();
+ // process each BED entry and convert to an IGV request
+ while ((bedStatus = bed->GetNextBed(bedEntry, lineNum)) != BED_INVALID) {
+ if (bedStatus == BED_VALID) {
+
string filename = bedEntry.chrom + ":" + ToString(bedEntry.start) + "-" + ToString(bedEntry.end);
string locus = bedEntry.chrom + ":" + ToString(bedEntry.start - slop) + "-" + ToString(bedEntry.end + slop);
-
+
if (useNames == true) {
if (bedEntry.name.empty() == false)
filename = filename + "_" + bedEntry.name;
else {
cerr << "Error: You requested that filenames be based upon the name field. However, it appears to be empty. Exiting!" << endl;
- exit (1);
- }
+ exit (1);
+ }
}
if (slop > 0) {
filename = filename + "_" + "slop" + ToString(slop);
@@ -249,21 +249,21 @@ void ProcessBed(istream &bedInput, BedFile *bed, string path, string sortType, s
// goto
cout << "goto " << locus << endl;
- // sort
+ // sort
if (sortType != "none")
cout << "sort " << sortType << endl;
-
+
// collapse
if (collapse == true)
cout << "collapse" << endl;
-
+
// snapshot
cout << "snapshot " << filename << "." << imageType << endl;
-
+
// reset
- bedEntry = nullBed;
- }
- }
- // close up
- bed->Close();
+ bedEntry = nullBed;
+ }
+ }
+ // close up
+ bed->Close();
}
diff --git a/src/closestBed/closestBed.cpp b/src/closestBed/closestBed.cpp
index 68d770fc17227bb3b037b6b817a07833fe5971cb..6eda4f952029b7c3d8fe733f6c70e30a4d1376c7 100644
--- a/src/closestBed/closestBed.cpp
+++ b/src/closestBed/closestBed.cpp
@@ -13,213 +13,213 @@
#include "closestBed.h"
const int MAXSLOP = 256000000; // 2*MAXSLOP = 512 megabases.
- // We don't want to keep looking if we
- // can't find a nearby feature within 512 Mb.
+ // We don't want to keep looking if we
+ // can't find a nearby feature within 512 Mb.
const int SLOPGROWTH = 2048000;
/*
- Constructor
+ Constructor
*/
BedClosest::BedClosest(string &bedAFile, string &bedBFile, bool forceStrand, string &tieMode, bool reportDistance) {
- _bedAFile = bedAFile;
- _bedBFile = bedBFile;
- _forceStrand = forceStrand;
- _tieMode = tieMode;
+ _bedAFile = bedAFile;
+ _bedBFile = bedBFile;
+ _forceStrand = forceStrand;
+ _tieMode = tieMode;
_reportDistance = reportDistance;
- _bedA = new BedFile(bedAFile);
- _bedB = new BedFile(bedBFile);
-
- FindClosestBed();
+ _bedA = new BedFile(bedAFile);
+ _bedB = new BedFile(bedBFile);
+
+ FindClosestBed();
}
/*
- Destructor
+ Destructor
*/
BedClosest::~BedClosest(void) {
}
void BedClosest::FindWindowOverlaps(BED &a, vector<BED> &hits) {
-
- int slop = 0; // start out just looking for overlaps
- // within the current bin (~128Kb)
- // update the current feature's start and end
+ int slop = 0; // start out just looking for overlaps
+ // within the current bin (~128Kb)
+
+ // update the current feature's start and end
- CHRPOS aFudgeStart = 0;
- CHRPOS aFudgeEnd;
- int numOverlaps = 0;
- vector<BED> closestB;
- float maxOverlap = 0;
- CHRPOS minDistance = INT_MAX;
- vector<CHRPOS> distances;
+ CHRPOS aFudgeStart = 0;
+ CHRPOS aFudgeEnd;
+ int numOverlaps = 0;
+ vector<BED> closestB;
+ float maxOverlap = 0;
+ CHRPOS minDistance = INT_MAX;
+ vector<CHRPOS> distances;
// is there at least one feature in B on the same chrom
// as the current A feature?
- if(_bedB->bedMap.find(a.chrom) != _bedB->bedMap.end()) {
-
- while ((numOverlaps == 0) && (slop <= MAXSLOP)) {
-
- // add some slop (starting at 0 bases) to a in hopes
- // of finding a hit in B
- if ((static_cast<int>(a.start) - slop) > 0)
- aFudgeStart = a.start - slop;
- else
- aFudgeStart = 0;
-
- if ((static_cast<int>(a.start) + slop) < (2 * MAXSLOP))
- aFudgeEnd = a.end + slop;
- else
- aFudgeEnd = 2 * MAXSLOP;
-
- // THE HEAVY LIFTING
- // search for hits with the current slop added
- _bedB->FindOverlapsPerBin(a.chrom, aFudgeStart, aFudgeEnd, a.strand, hits, _forceStrand);
-
- vector<BED>::const_iterator h = hits.begin();
- vector<BED>::const_iterator hitsEnd = hits.end();
- for (; h != hitsEnd; ++h) {
-
- numOverlaps++;
-
- // do the actual features overlap?
- int s = max(a.start, h->start);
- int e = min(a.end, h->end);
- int overlapBases = (e - s); // the number of overlapping bases b/w a and b
- int aLength = (a.end - a.start); // the length of a in b.p.
-
- // there is overlap
- if (s < e) {
- // is there enough overlap (default ~ 1bp)
- float overlap = (float) overlapBases / (float) aLength;
- if ( overlap > 0 ) {
- // is this hit the closest?
- if (overlap > maxOverlap) {
- maxOverlap = overlap;
-
- closestB.clear();
- closestB.push_back(*h);
- distances.clear();
+ if(_bedB->bedMap.find(a.chrom) != _bedB->bedMap.end()) {
+
+ while ((numOverlaps == 0) && (slop <= MAXSLOP)) {
+
+ // add some slop (starting at 0 bases) to a in hopes
+ // of finding a hit in B
+ if ((static_cast<int>(a.start) - slop) > 0)
+ aFudgeStart = a.start - slop;
+ else
+ aFudgeStart = 0;
+
+ if ((static_cast<int>(a.start) + slop) < (2 * MAXSLOP))
+ aFudgeEnd = a.end + slop;
+ else
+ aFudgeEnd = 2 * MAXSLOP;
+
+ // THE HEAVY LIFTING
+ // search for hits with the current slop added
+ _bedB->FindOverlapsPerBin(a.chrom, aFudgeStart, aFudgeEnd, a.strand, hits, _forceStrand);
+
+ vector<BED>::const_iterator h = hits.begin();
+ vector<BED>::const_iterator hitsEnd = hits.end();
+ for (; h != hitsEnd; ++h) {
+
+ numOverlaps++;
+
+ // do the actual features overlap?
+ int s = max(a.start, h->start);
+ int e = min(a.end, h->end);
+ int overlapBases = (e - s); // the number of overlapping bases b/w a and b
+ int aLength = (a.end - a.start); // the length of a in b.p.
+
+ // there is overlap
+ if (s < e) {
+ // is there enough overlap (default ~ 1bp)
+ float overlap = (float) overlapBases / (float) aLength;
+ if ( overlap > 0 ) {
+ // is this hit the closest?
+ if (overlap > maxOverlap) {
+ maxOverlap = overlap;
+
+ closestB.clear();
+ closestB.push_back(*h);
+ distances.clear();
distances.push_back(0);
- }
- else if (overlap == maxOverlap) {
- closestB.push_back(*h);
- distances.push_back(0);
- }
- }
- }
- // the hit is to the "left" of A
- else if (h->end < a.start){
- if ((a.start - h->end) < minDistance) {
- minDistance = a.start - h->end;
-
- closestB.clear();
- closestB.push_back(*h);
- distances.clear();
+ }
+ else if (overlap == maxOverlap) {
+ closestB.push_back(*h);
+ distances.push_back(0);
+ }
+ }
+ }
+ // the hit is to the "left" of A
+ else if (h->end < a.start){
+ if ((a.start - h->end) < minDistance) {
+ minDistance = a.start - h->end;
+
+ closestB.clear();
+ closestB.push_back(*h);
+ distances.clear();
+ distances.push_back(minDistance);
+ }
+ else if ((a.start - h->end) == minDistance) {
+ closestB.push_back(*h);
+ distances.push_back(minDistance);
+ }
+ }
+ // the hit is to the "right" of A
+ else {
+ if ((h->start - a.end) < minDistance) {
+ minDistance = h->start - a.end;
+
+ closestB.clear();
+ closestB.push_back(*h);
+ distances.clear();
distances.push_back(minDistance);
- }
- else if ((a.start - h->end) == minDistance) {
- closestB.push_back(*h);
- distances.push_back(minDistance);
- }
- }
- // the hit is to the "right" of A
- else {
- if ((h->start - a.end) < minDistance) {
- minDistance = h->start - a.end;
-
- closestB.clear();
- closestB.push_back(*h);
- distances.clear();
+ }
+ else if ((h->start - a.end) == minDistance) {
+ closestB.push_back(*h);
distances.push_back(minDistance);
- }
- else if ((h->start - a.end) == minDistance) {
- closestB.push_back(*h);
- distances.push_back(minDistance);
- }
- }
- }
- // if no overlaps were found, we'll widen the range
- // by SLOPGROWTH in each direction and search again.
- slop += SLOPGROWTH;
- }
- }
- // there is no feature in B on the same chromosome as A
- else {
- _bedA->reportBedTab(a);
- if (_reportDistance == true) {
- _bedB->reportNullBedTab();
- cout << -1 << endl;
+ }
+ }
+ }
+ // if no overlaps were found, we'll widen the range
+ // by SLOPGROWTH in each direction and search again.
+ slop += SLOPGROWTH;
+ }
+ }
+ // there is no feature in B on the same chromosome as A
+ else {
+ _bedA->reportBedTab(a);
+ if (_reportDistance == true) {
+ _bedB->reportNullBedTab();
+ cout << -1 << endl;
}
else
- _bedB->reportNullBedNewLine();
- }
+ _bedB->reportNullBedNewLine();
+ }
// report the closest feature(s) in B to the current A feature.
// obey the user's reporting request (_tieMode)
- if (numOverlaps > 0) {
-
- if (closestB.size() == 1 || _tieMode == "first") {
- _bedA->reportBedTab(a);
- if (_reportDistance == true) {
- _bedB->reportBedTab(closestB[0]);
- cout << distances[0] << endl;
+ if (numOverlaps > 0) {
+
+ if (closestB.size() == 1 || _tieMode == "first") {
+ _bedA->reportBedTab(a);
+ if (_reportDistance == true) {
+ _bedB->reportBedTab(closestB[0]);
+ cout << distances[0] << endl;
}
else
- _bedB->reportBedNewLine(closestB[0]);
- }
- else {
- if (_tieMode == "all") {
+ _bedB->reportBedNewLine(closestB[0]);
+ }
+ else {
+ if (_tieMode == "all") {
size_t i = 0;
- for (vector<BED>::iterator b = closestB.begin(); b != closestB.end(); ++b) {
- _bedA->reportBedTab(a);
- if (_reportDistance == true) {
- _bedB->reportBedTab(*b);
- cout << distances[i++] <<endl;
+ for (vector<BED>::iterator b = closestB.begin(); b != closestB.end(); ++b) {
+ _bedA->reportBedTab(a);
+ if (_reportDistance == true) {
+ _bedB->reportBedTab(*b);
+ cout << distances[i++] <<endl;
}
else
- _bedB->reportBedNewLine(*b);
- }
- }
- else if (_tieMode == "last") {
- _bedA->reportBedTab(a);
- if (_reportDistance == true) {
- _bedB->reportBedTab(closestB[closestB.size()-1]);
- cout << distances[distances.size() - 1]<<endl;
+ _bedB->reportBedNewLine(*b);
+ }
+ }
+ else if (_tieMode == "last") {
+ _bedA->reportBedTab(a);
+ if (_reportDistance == true) {
+ _bedB->reportBedTab(closestB[closestB.size()-1]);
+ cout << distances[distances.size() - 1]<<endl;
}
else
_bedB->reportBedNewLine(closestB[closestB.size()-1]);
- }
- }
- }
+ }
+ }
+ }
}
-
+
void BedClosest::FindClosestBed() {
- // load the "B" bed file into a map so
- // that we can easily compare "A" to it for overlaps
- _bedB->loadBedFileIntoMap();
-
- BED a, nullBed;
- int lineNum = 0; // current input line number
- vector<BED> hits; // vector of potential hits
- hits.reserve(100);
- BedLineStatus bedStatus;
-
- _bedA->Open();
- // process each entry in A in search of the closest feature in B
- while ((bedStatus = _bedA->GetNextBed(a, lineNum)) != BED_INVALID) {
- if (bedStatus == BED_VALID) {
- FindWindowOverlaps(a, hits);
- hits.clear();
- a = nullBed;
- }
- }
- _bedA->Close();
+ // load the "B" bed file into a map so
+ // that we can easily compare "A" to it for overlaps
+ _bedB->loadBedFileIntoMap();
+
+ BED a, nullBed;
+ int lineNum = 0; // current input line number
+ vector<BED> hits; // vector of potential hits
+ hits.reserve(100);
+ BedLineStatus bedStatus;
+
+ _bedA->Open();
+ // process each entry in A in search of the closest feature in B
+ while ((bedStatus = _bedA->GetNextBed(a, lineNum)) != BED_INVALID) {
+ if (bedStatus == BED_VALID) {
+ FindWindowOverlaps(a, hits);
+ hits.clear();
+ a = nullBed;
+ }
+ }
+ _bedA->Close();
}
// END ClosestBed
diff --git a/src/closestBed/closestBed.h b/src/closestBed/closestBed.h
index c1f4182ae381dd06ec2dad6cda4cb81c6074895d..06d77c74f12cd630b93e3eaeeae12c604ba8ca8a 100644
--- a/src/closestBed/closestBed.h
+++ b/src/closestBed/closestBed.h
@@ -26,29 +26,29 @@ class BedClosest {
public:
- // constructor
- BedClosest(string &bedAFile, string &bedBFile, bool forceStrand, string &tieMode, bool reportDistance);
-
- // destructor
- ~BedClosest(void);
-
- // find the closest feature in B to A
- void FindClosestBed();
-
+ // constructor
+ BedClosest(string &bedAFile, string &bedBFile, bool forceStrand, string &tieMode, bool reportDistance);
+
+ // destructor
+ ~BedClosest(void);
+
+ // find the closest feature in B to A
+ void FindClosestBed();
+
private:
-
- // data
- string _bedAFile;
- string _bedBFile;
- string _tieMode;
- bool _forceStrand;
- bool _reportDistance;
-
- BedFile *_bedA, *_bedB;
-
- // methods
- void reportNullB();
- void FindWindowOverlaps(BED &, vector<BED> &);
+
+ // data
+ string _bedAFile;
+ string _bedBFile;
+ string _tieMode;
+ bool _forceStrand;
+ bool _reportDistance;
+
+ BedFile *_bedA, *_bedB;
+
+ // methods
+ void reportNullB();
+ void FindWindowOverlaps(BED &, vector<BED> &);
};
#endif /* CLOSEST_H */
diff --git a/src/closestBed/closestMain.cpp b/src/closestBed/closestMain.cpp
index 9c397eabd022259262a86728d5133399f4da4851..bb8c6ce546c7a69aae364f492090a4e2799f241d 100644
--- a/src/closestBed/closestMain.cpp
+++ b/src/closestBed/closestMain.cpp
@@ -25,126 +25,126 @@ void ShowHelp(void);
int main(int argc, char* argv[]) {
- // our configuration variables
- bool showHelp = false;
-
- // input files
- string bedAFile;
- string bedBFile;
- string tieMode = "all";
-
- bool haveBedA = false;
- bool haveBedB = false;
- bool haveTieMode = false;
- bool forceStrand = false;
+ // our configuration variables
+ bool showHelp = false;
+
+ // input files
+ string bedAFile;
+ string bedBFile;
+ string tieMode = "all";
+
+ bool haveBedA = false;
+ bool haveBedB = false;
+ bool haveTieMode = false;
+ bool forceStrand = false;
bool reportDistance = false;
- // check to see if we should print out some help
- if(argc <= 1) showHelp = true;
-
- for(int i = 1; i < argc; i++) {
- int parameterLength = (int)strlen(argv[i]);
-
- if( (PARAMETER_CHECK("-h", 2, parameterLength)) ||
- (PARAMETER_CHECK("--help", 5, parameterLength))) {
- showHelp = true;
- }
- }
-
- if(showHelp) ShowHelp();
-
- // do some parsing (all of these parameters require 2 strings)
- for(int i = 1; i < argc; i++) {
-
- int parameterLength = (int)strlen(argv[i]);
-
- if(PARAMETER_CHECK("-a", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveBedA = true;
- bedAFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-b", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveBedB = true;
- bedBFile = argv[i + 1];
- i++;
- }
- }
- else if (PARAMETER_CHECK("-s", 2, parameterLength)) {
- forceStrand = true;
- }
- else if (PARAMETER_CHECK("-d", 2, parameterLength)) {
- reportDistance = true;
- }
- else if (PARAMETER_CHECK("-t", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveTieMode = true;
- tieMode = argv[i + 1];
- i++;
- }
- }
- }
-
- // make sure we have both input files
- if (!haveBedA || !haveBedB) {
- cerr << endl << "*****" << endl << "*****ERROR: Need -a and -b files. " << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (haveTieMode && (tieMode != "all") && (tieMode != "first")
- && (tieMode != "last")) {
- cerr << endl << "*****" << endl << "*****ERROR: Request \"all\" or \"first\" or \"last\" for Tie Mode (-t)" << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (!showHelp) {
- BedClosest *bc = new BedClosest(bedAFile, bedBFile, forceStrand, tieMode, reportDistance);
- delete bc;
- return 0;
- }
- else {
- ShowHelp();
- }
+ // check to see if we should print out some help
+ if(argc <= 1) showHelp = true;
+
+ for(int i = 1; i < argc; i++) {
+ int parameterLength = (int)strlen(argv[i]);
+
+ if( (PARAMETER_CHECK("-h", 2, parameterLength)) ||
+ (PARAMETER_CHECK("--help", 5, parameterLength))) {
+ showHelp = true;
+ }
+ }
+
+ if(showHelp) ShowHelp();
+
+ // do some parsing (all of these parameters require 2 strings)
+ for(int i = 1; i < argc; i++) {
+
+ int parameterLength = (int)strlen(argv[i]);
+
+ if(PARAMETER_CHECK("-a", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveBedA = true;
+ bedAFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-b", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveBedB = true;
+ bedBFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if (PARAMETER_CHECK("-s", 2, parameterLength)) {
+ forceStrand = true;
+ }
+ else if (PARAMETER_CHECK("-d", 2, parameterLength)) {
+ reportDistance = true;
+ }
+ else if (PARAMETER_CHECK("-t", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveTieMode = true;
+ tieMode = argv[i + 1];
+ i++;
+ }
+ }
+ }
+
+ // make sure we have both input files
+ if (!haveBedA || !haveBedB) {
+ cerr << endl << "*****" << endl << "*****ERROR: Need -a and -b files. " << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (haveTieMode && (tieMode != "all") && (tieMode != "first")
+ && (tieMode != "last")) {
+ cerr << endl << "*****" << endl << "*****ERROR: Request \"all\" or \"first\" or \"last\" for Tie Mode (-t)" << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (!showHelp) {
+ BedClosest *bc = new BedClosest(bedAFile, bedBFile, forceStrand, tieMode, reportDistance);
+ delete bc;
+ return 0;
+ }
+ else {
+ ShowHelp();
+ }
}
void ShowHelp(void) {
- cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
-
- cerr << "Authors: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
- cerr << "\t Erik Arner, Riken" << endl << endl;
-
- cerr << "Summary: For each feature in A, finds the closest " << endl;
- cerr << "\t feature (upstream or downstream) in B." << endl << endl;
-
- cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -a <bed/gff/vcf> -b <bed/gff/vcf>" << endl << endl;
-
- cerr << "Options: " << endl;
- cerr << "\t-s\t" << "Force strandedness. That is, find the closest feature in B" << endl;
- cerr << "\t\tthat overlaps A on the same strand." << endl;
- cerr << "\t\t- By default, overlaps are reported without respect to strand." << endl << endl;
-
- cerr << "\t-d\t" << "In addition to the closest feature in B, " << endl;
- cerr << "\t\treport its distance to A as an extra column." << endl;
- cerr << "\t\t- The reported distance for overlapping features will be 0." << endl << endl;
-
-
- cerr << "\t-t\t" << "How ties for closest feature are handled. This occurs when two" << endl;
- cerr << "\t\tfeatures in B have exactly the same overlap with A." << endl;
- cerr << "\t\tBy default, all such features in B are reported." << endl;
- cerr << "\t\tHere are all the options:" << endl;
- cerr << "\t\t- \"all\" Report all ties (default)." << endl;
- cerr << "\t\t- \"first\" Report the first tie that occurred in the B file." << endl;
- cerr << "\t\t- \"last\" Report the last tie that occurred in the B file." << endl << endl;
-
- cerr << "Notes: " << endl;
- cerr << "\tReports \"none\" for chrom and \"-1\" for all other fields when a feature" << endl;
- cerr << "\tis not found in B on the same chromosome as the feature in A." << endl;
- cerr << "\tE.g. none\t-1\t-1" << endl << endl;
-
- // end the program here
- exit(1);
+ cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
+
+ cerr << "Authors: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
+ cerr << "\t Erik Arner, Riken" << endl << endl;
+
+ cerr << "Summary: For each feature in A, finds the closest " << endl;
+ cerr << "\t feature (upstream or downstream) in B." << endl << endl;
+
+ cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -a <bed/gff/vcf> -b <bed/gff/vcf>" << endl << endl;
+
+ cerr << "Options: " << endl;
+ cerr << "\t-s\t" << "Force strandedness. That is, find the closest feature in B" << endl;
+ cerr << "\t\tthat overlaps A on the same strand." << endl;
+ cerr << "\t\t- By default, overlaps are reported without respect to strand." << endl << endl;
+
+ cerr << "\t-d\t" << "In addition to the closest feature in B, " << endl;
+ cerr << "\t\treport its distance to A as an extra column." << endl;
+ cerr << "\t\t- The reported distance for overlapping features will be 0." << endl << endl;
+
+
+ cerr << "\t-t\t" << "How ties for closest feature are handled. This occurs when two" << endl;
+ cerr << "\t\tfeatures in B have exactly the same overlap with A." << endl;
+ cerr << "\t\tBy default, all such features in B are reported." << endl;
+ cerr << "\t\tHere are all the options:" << endl;
+ cerr << "\t\t- \"all\" Report all ties (default)." << endl;
+ cerr << "\t\t- \"first\" Report the first tie that occurred in the B file." << endl;
+ cerr << "\t\t- \"last\" Report the last tie that occurred in the B file." << endl << endl;
+
+ cerr << "Notes: " << endl;
+ cerr << "\tReports \"none\" for chrom and \"-1\" for all other fields when a feature" << endl;
+ cerr << "\tis not found in B on the same chromosome as the feature in A." << endl;
+ cerr << "\tE.g. none\t-1\t-1" << endl << endl;
+
+ // end the program here
+ exit(1);
}
diff --git a/src/complementBed/complementBed.cpp b/src/complementBed/complementBed.cpp
index 33b48e3ca065dff263dd17b24fadff3691eb9dd1..f14d1d8d362790eb29e1ee823d377d4f8ea3f240 100644
--- a/src/complementBed/complementBed.cpp
+++ b/src/complementBed/complementBed.cpp
@@ -14,12 +14,12 @@
BedComplement::BedComplement(string &bedFile, string &genomeFile) {
- _bedFile = bedFile;
- _genomeFile = genomeFile;
-
- _bed = new BedFile(bedFile);
- _genome = new GenomeFile(genomeFile);
-
+ _bedFile = bedFile;
+ _genomeFile = genomeFile;
+
+ _bed = new BedFile(bedFile);
+ _genome = new GenomeFile(genomeFile);
+
}
@@ -28,61 +28,61 @@ BedComplement::~BedComplement(void) {
//
-// Merge overlapping BED entries into a single entry
+// Merge overlapping BED entries into a single entry
//
void BedComplement::ComplementBed() {
- // load the "B" bed file into a map so
- // that we can easily compare "A" to it for overlaps
- _bed->loadBedFileIntoMapNoBin();
-
- vector<short> chromMasks;
- string currChrom;
-
- // loop through each chromosome and merge their BED entries
- masterBedMapNoBin::const_iterator m = _bed->bedMapNoBin.begin();
- masterBedMapNoBin::const_iterator mEnd = _bed->bedMapNoBin.end();
+ // load the "B" bed file into a map so
+ // that we can easily compare "A" to it for overlaps
+ _bed->loadBedFileIntoMapNoBin();
+
+ vector<short> chromMasks;
+ string currChrom;
+
+ // loop through each chromosome and merge their BED entries
+ masterBedMapNoBin::const_iterator m = _bed->bedMapNoBin.begin();
+ masterBedMapNoBin::const_iterator mEnd = _bed->bedMapNoBin.end();
for (; m != mEnd; ++m) {
- currChrom = m->first;
- CHRPOS currChromSize = _genome->getChromSize(currChrom);
-
- // bedList is already sorted by start position.
- vector<BED> bedList = m->second;
-
- // create a flag for every base on the chrom.
- vector<short> chromMasks(currChromSize, 0);
-
- vector<BED>::const_iterator bIt = bedList.begin();
- vector<BED>::const_iterator bEnd = bedList.end();
- for ( ; bIt != bEnd; ++bIt) {
-
- // sanity check the end of the bed entry
- if (bIt->end > currChromSize) {
- cout << "End of BED entry exceeds chromosome length. Please correct." << endl;
- _bed->reportBedNewLine(*bIt);
- exit(1);
- }
-
- // mask all of the positions spanned by this BED entry.
- for (CHRPOS b = bIt->start; b < bIt->end; b++)
- chromMasks[b] = 1;
- }
-
- CHRPOS i = 0;
- CHRPOS start;
- while (i < chromMasks.size()) {
- if (chromMasks[i] == 0) {
- start = i;
- while ((chromMasks[i] == 0) && (i < chromMasks.size()))
- i++;
-
- if (start > 0)
- cout << currChrom << "\t" << start << "\t" << i << endl;
- else
- cout << currChrom << "\t" << 0 << "\t" << i << endl;
- }
- i++;
- }
- }
+ currChrom = m->first;
+ CHRPOS currChromSize = _genome->getChromSize(currChrom);
+
+ // bedList is already sorted by start position.
+ vector<BED> bedList = m->second;
+
+ // create a flag for every base on the chrom.
+ vector<short> chromMasks(currChromSize, 0);
+
+ vector<BED>::const_iterator bIt = bedList.begin();
+ vector<BED>::const_iterator bEnd = bedList.end();
+ for ( ; bIt != bEnd; ++bIt) {
+
+ // sanity check the end of the bed entry
+ if (bIt->end > currChromSize) {
+ cout << "End of BED entry exceeds chromosome length. Please correct." << endl;
+ _bed->reportBedNewLine(*bIt);
+ exit(1);
+ }
+
+ // mask all of the positions spanned by this BED entry.
+ for (CHRPOS b = bIt->start; b < bIt->end; b++)
+ chromMasks[b] = 1;
+ }
+
+ CHRPOS i = 0;
+ CHRPOS start;
+ while (i < chromMasks.size()) {
+ if (chromMasks[i] == 0) {
+ start = i;
+ while ((chromMasks[i] == 0) && (i < chromMasks.size()))
+ i++;
+
+ if (start > 0)
+ cout << currChrom << "\t" << start << "\t" << i << endl;
+ else
+ cout << currChrom << "\t" << 0 << "\t" << i << endl;
+ }
+ i++;
+ }
+ }
}
diff --git a/src/complementBed/complementBed.h b/src/complementBed/complementBed.h
index bdd958e0611a2fb5d697ee1efd03b5b1d9e09139..a04cc964ec3f2bd6a59178fddc68aae232951cf7 100644
--- a/src/complementBed/complementBed.h
+++ b/src/complementBed/complementBed.h
@@ -29,7 +29,7 @@ class BedComplement {
public:
- // constructor
+ // constructor
BedComplement(string &bedFile, string &genomeFile);
// destructor
@@ -38,9 +38,9 @@ public:
void ComplementBed();
private:
-
- string _bedFile;
- string _genomeFile;
- BedFile *_bed;
- GenomeFile *_genome;
+
+ string _bedFile;
+ string _genomeFile;
+ BedFile *_bed;
+ GenomeFile *_genome;
};
diff --git a/src/complementBed/complementMain.cpp b/src/complementBed/complementMain.cpp
index dc3116c0b49f0d75964b4069466f0cc2359fa290..4087ce0dfea9cc83ff4efff2ade22318c30e44ec 100644
--- a/src/complementBed/complementMain.cpp
+++ b/src/complementBed/complementMain.cpp
@@ -26,91 +26,91 @@ void ShowHelp(void);
int main(int argc, char* argv[]) {
- // our configuration variables
- bool showHelp = false;
-
- // input files
- string bedFile = "stdin";
- string genomeFile;
-
- bool haveBed = true;
- bool haveGenome = false;
-
- for(int i = 1; i < argc; i++) {
- int parameterLength = (int)strlen(argv[i]);
-
- if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
- (PARAMETER_CHECK("--help", 5, parameterLength))) {
- showHelp = true;
- }
- }
-
- if(showHelp) ShowHelp();
-
- // do some parsing (all of these parameters require 2 strings)
- for(int i = 1; i < argc; i++) {
-
- int parameterLength = (int)strlen(argv[i]);
-
- if(PARAMETER_CHECK("-i", 2, parameterLength)) {
- if ((i+1) < argc) {
- bedFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-g", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveGenome = true;
- genomeFile = argv[i + 1];
- i++;
- }
- }
- else {
- cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
- showHelp = true;
- }
- }
-
- // make sure we have both input files
- if (!haveBed || !haveGenome) {
- cerr << endl << "*****" << endl << "*****ERROR: Need -i BED file and -g Genome file. " << endl << "*****" << endl;
- showHelp = true;
- }
- if (!showHelp) {
- BedComplement *bc = new BedComplement(bedFile, genomeFile);
- bc->ComplementBed();
- return 0;
- }
- else {
- ShowHelp();
- }
+ // our configuration variables
+ bool showHelp = false;
+
+ // input files
+ string bedFile = "stdin";
+ string genomeFile;
+
+ bool haveBed = true;
+ bool haveGenome = false;
+
+ for(int i = 1; i < argc; i++) {
+ int parameterLength = (int)strlen(argv[i]);
+
+ if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
+ (PARAMETER_CHECK("--help", 5, parameterLength))) {
+ showHelp = true;
+ }
+ }
+
+ if(showHelp) ShowHelp();
+
+ // do some parsing (all of these parameters require 2 strings)
+ for(int i = 1; i < argc; i++) {
+
+ int parameterLength = (int)strlen(argv[i]);
+
+ if(PARAMETER_CHECK("-i", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ bedFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-g", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveGenome = true;
+ genomeFile = argv[i + 1];
+ i++;
+ }
+ }
+ else {
+ cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
+ showHelp = true;
+ }
+ }
+
+ // make sure we have both input files
+ if (!haveBed || !haveGenome) {
+ cerr << endl << "*****" << endl << "*****ERROR: Need -i BED file and -g Genome file. " << endl << "*****" << endl;
+ showHelp = true;
+ }
+ if (!showHelp) {
+ BedComplement *bc = new BedComplement(bedFile, genomeFile);
+ bc->ComplementBed();
+ return 0;
+ }
+ else {
+ ShowHelp();
+ }
}
void ShowHelp(void) {
-
- cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
-
- cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
-
- cerr << "Summary: Returns the base pair complement of a feature file." << endl << endl;
-
- cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -i <bed/gff/vcf> -g <genome>" << endl << endl;
-
- cerr << "Notes: " << endl;
- cerr << "\t(1) The genome file should tab delimited and structured as follows:" << endl;
- cerr << "\t <chromName><TAB><chromSize>" << endl << endl;
- cerr << "\tFor example, Human (hg19):" << endl;
- cerr << "\tchr1\t249250621" << endl;
- cerr << "\tchr2\t243199373" << endl;
- cerr << "\t..." << endl;
- cerr << "\tchr18_gl000207_random\t4262" << endl << endl;
-
- cerr << "Tips: " << endl;
- cerr << "\tOne can use the UCSC Genome Browser's MySQL database to extract" << endl;
- cerr << "\tchromosome sizes. For example, H. sapiens:" << endl << endl;
- cerr << "\tmysql --user=genome --host=genome-mysql.cse.ucsc.edu -A -e /" << endl;
- cerr << "\t\"select chrom, size from hg19.chromInfo\" > hg19.genome" << endl << endl;
-
- exit(1);
-
+
+ cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
+
+ cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
+
+ cerr << "Summary: Returns the base pair complement of a feature file." << endl << endl;
+
+ cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -i <bed/gff/vcf> -g <genome>" << endl << endl;
+
+ cerr << "Notes: " << endl;
+ cerr << "\t(1) The genome file should tab delimited and structured as follows:" << endl;
+ cerr << "\t <chromName><TAB><chromSize>" << endl << endl;
+ cerr << "\tFor example, Human (hg19):" << endl;
+ cerr << "\tchr1\t249250621" << endl;
+ cerr << "\tchr2\t243199373" << endl;
+ cerr << "\t..." << endl;
+ cerr << "\tchr18_gl000207_random\t4262" << endl << endl;
+
+ cerr << "Tips: " << endl;
+ cerr << "\tOne can use the UCSC Genome Browser's MySQL database to extract" << endl;
+ cerr << "\tchromosome sizes. For example, H. sapiens:" << endl << endl;
+ cerr << "\tmysql --user=genome --host=genome-mysql.cse.ucsc.edu -A -e /" << endl;
+ cerr << "\t\"select chrom, size from hg19.chromInfo\" > hg19.genome" << endl << endl;
+
+ exit(1);
+
}
diff --git a/src/coverageBed/coverageBed.cpp b/src/coverageBed/coverageBed.cpp
index fd69d9b45a94d83c868d5e021c9d06b3c0d9e1ae..df1a224591ced7654d0f499a2475342664d386b7 100644
--- a/src/coverageBed/coverageBed.cpp
+++ b/src/coverageBed/coverageBed.cpp
@@ -13,222 +13,222 @@
#include "coverageBed.h"
// build
-BedCoverage::BedCoverage(string &bedAFile, string &bedBFile, bool forceStrand,
+BedCoverage::BedCoverage(string &bedAFile, string &bedBFile, bool forceStrand,
bool writeHistogram, bool bamInput, bool obeySplits, bool eachBase) {
-
- _bedAFile = bedAFile;
- _bedBFile = bedBFile;
-
- _bedA = new BedFile(bedAFile);
- _bedB = new BedFile(bedBFile);
-
- _forceStrand = forceStrand;
+
+ _bedAFile = bedAFile;
+ _bedBFile = bedBFile;
+
+ _bedA = new BedFile(bedAFile);
+ _bedB = new BedFile(bedBFile);
+
+ _forceStrand = forceStrand;
_obeySplits = obeySplits;
_eachBase = eachBase;
- _writeHistogram = writeHistogram;
- _bamInput = bamInput;
-
-
- if (_bamInput == false)
- CollectCoverageBed();
- else
- CollectCoverageBam(_bedA->bedFile);
+ _writeHistogram = writeHistogram;
+ _bamInput = bamInput;
+
+
+ if (_bamInput == false)
+ CollectCoverageBed();
+ else
+ CollectCoverageBam(_bedA->bedFile);
}
// destroy
BedCoverage::~BedCoverage(void) {
- delete _bedA;
- delete _bedB;
+ delete _bedA;
+ delete _bedB;
}
void BedCoverage::CollectCoverageBed() {
-
- // load the "B" bed file into a map so
- // that we can easily compare "A" to it for overlaps
- _bedB->loadBedCovFileIntoMap();
-
- int lineNum = 0; // current input line number
- BED a, nullBed;
- BedLineStatus bedStatus;
-
- _bedA->Open();
- // process each entry in A
- while ((bedStatus = _bedA->GetNextBed(a, lineNum)) != BED_INVALID) {
- if (bedStatus == BED_VALID) {
- // process the BED entry as a single block
+
+ // load the "B" bed file into a map so
+ // that we can easily compare "A" to it for overlaps
+ _bedB->loadBedCovFileIntoMap();
+
+ int lineNum = 0; // current input line number
+ BED a, nullBed;
+ BedLineStatus bedStatus;
+
+ _bedA->Open();
+ // process each entry in A
+ while ((bedStatus = _bedA->GetNextBed(a, lineNum)) != BED_INVALID) {
+ if (bedStatus == BED_VALID) {
+ // process the BED entry as a single block
if (_obeySplits == false)
- _bedB->countHits(a, _forceStrand);
- // split the BED into discrete blocksand process each independently.
- else {
- bedVector bedBlocks;
+ _bedB->countHits(a, _forceStrand);
+ // split the BED into discrete blocksand process each independently.
+ else {
+ bedVector bedBlocks;
splitBedIntoBlocks(a, lineNum, bedBlocks);
-
- // use countSplitHits to avoid over-counting each split chunk
- // as distinct read coverage.
- _bedB->countSplitHits(bedBlocks, _forceStrand);
- }
- a = nullBed;
- }
- }
- _bedA->Close();
-
- // report the coverage (summary or histogram) for BED B.
- ReportCoverage();
+
+ // use countSplitHits to avoid over-counting each split chunk
+ // as distinct read coverage.
+ _bedB->countSplitHits(bedBlocks, _forceStrand);
+ }
+ a = nullBed;
+ }
+ }
+ _bedA->Close();
+
+ // report the coverage (summary or histogram) for BED B.
+ ReportCoverage();
}
void BedCoverage::CollectCoverageBam(string bamFile) {
- // load the "B" bed file into a map so
- // that we can easily compare "A" to it for overlaps
- _bedB->loadBedCovFileIntoMap();
-
- // open the BAM file
- BamReader reader;
- reader.Open(bamFile);
-
- // get header & reference information
- string header = reader.GetHeaderText();
- RefVector refs = reader.GetReferenceData();
-
- // convert each aligned BAM entry to BED
- // and compute coverage on B
- BamAlignment bam;
- while (reader.GetNextAlignment(bam)) {
- if (bam.IsMapped()) {
- // treat the BAM alignment as a single "block"
- if (_obeySplits == false) {
- // construct a new BED entry from the current BAM alignment.
- BED a;
- a.chrom = refs.at(bam.RefID).RefName;
- a.start = bam.Position;
- a.end = bam.GetEndPosition(false);
- a.strand = "+";
- if (bam.IsReverseStrand()) a.strand = "-";
-
- _bedB->countHits(a, _forceStrand);
- }
- // split the BAM alignment into discrete blocks and
- // look for overlaps only within each block.
- else {
- // vec to store the discrete BED "blocks" from a
- bedVector bedBlocks;
- // since we are counting coverage, we do want to split blocks when a
+ // load the "B" bed file into a map so
+ // that we can easily compare "A" to it for overlaps
+ _bedB->loadBedCovFileIntoMap();
+
+ // open the BAM file
+ BamReader reader;
+ reader.Open(bamFile);
+
+ // get header & reference information
+ string header = reader.GetHeaderText();
+ RefVector refs = reader.GetReferenceData();
+
+ // convert each aligned BAM entry to BED
+ // and compute coverage on B
+ BamAlignment bam;
+ while (reader.GetNextAlignment(bam)) {
+ if (bam.IsMapped()) {
+ // treat the BAM alignment as a single "block"
+ if (_obeySplits == false) {
+ // construct a new BED entry from the current BAM alignment.
+ BED a;
+ a.chrom = refs.at(bam.RefID).RefName;
+ a.start = bam.Position;
+ a.end = bam.GetEndPosition(false);
+ a.strand = "+";
+ if (bam.IsReverseStrand()) a.strand = "-";
+
+ _bedB->countHits(a, _forceStrand);
+ }
+ // split the BAM alignment into discrete blocks and
+ // look for overlaps only within each block.
+ else {
+ // vec to store the discrete BED "blocks" from a
+ bedVector bedBlocks;
+ // since we are counting coverage, we do want to split blocks when a
// deletion (D) CIGAR op is encountered (hence the true for the last parm)
- getBamBlocks(bam, refs, bedBlocks, true);
- // use countSplitHits to avoid over-counting each split chunk
- // as distinct read coverage.
- _bedB->countSplitHits(bedBlocks, _forceStrand);
- }
- }
- }
- // report the coverage (summary or histogram) for BED B.
- ReportCoverage();
- // close the BAM file
- reader.Close();
+ getBamBlocks(bam, refs, bedBlocks, true);
+ // use countSplitHits to avoid over-counting each split chunk
+ // as distinct read coverage.
+ _bedB->countSplitHits(bedBlocks, _forceStrand);
+ }
+ }
+ }
+ // report the coverage (summary or histogram) for BED B.
+ ReportCoverage();
+ // close the BAM file
+ reader.Close();
}
void BedCoverage::ReportCoverage() {
- map<unsigned int, unsigned int> allDepthHist;
- unsigned int totalLength = 0;
-
- // process each chromosome
- masterBedCovMap::const_iterator chromItr = _bedB->bedCovMap.begin();
- masterBedCovMap::const_iterator chromEnd = _bedB->bedCovMap.end();
- for (; chromItr != chromEnd; ++chromItr)
- {
- // for each chrom, process each bin
- binsToBedCovs::const_iterator binItr = chromItr->second.begin();
- binsToBedCovs::const_iterator binEnd = chromItr->second.end();
- for (; binItr != binEnd; ++binItr)
- {
- // for each chrom & bin, compute and report
+ map<unsigned int, unsigned int> allDepthHist;
+ unsigned int totalLength = 0;
+
+ // process each chromosome
+ masterBedCovMap::const_iterator chromItr = _bedB->bedCovMap.begin();
+ masterBedCovMap::const_iterator chromEnd = _bedB->bedCovMap.end();
+ for (; chromItr != chromEnd; ++chromItr)
+ {
+ // for each chrom, process each bin
+ binsToBedCovs::const_iterator binItr = chromItr->second.begin();
+ binsToBedCovs::const_iterator binEnd = chromItr->second.end();
+ for (; binItr != binEnd; ++binItr)
+ {
+ // for each chrom & bin, compute and report
// the observed coverage for each feature
- vector<BEDCOV>::const_iterator bedItr = binItr->second.begin();
- vector<BEDCOV>::const_iterator bedEnd = binItr->second.end();
- for (; bedItr != bedEnd; ++bedItr)
- {
- int zeroDepthCount = 0; // number of bases with zero depth
- int depth = 0; // tracks the depth at the current base
-
- // the start is either the first base in the feature OR
- // the leftmost position of an overlapping feature. e.g. (s = start):
- // A ----------
- // B s ------------
- int start = min(bedItr->minOverlapStart, bedItr->start);
-
- // track the numnber of bases in the feature covered by
- // 0, 1, 2, ... n features in A
- map<unsigned int, unsigned int> depthHist;
- map<unsigned int, DEPTH>::const_iterator depthItr;
-
- // compute the coverage observed at each base in the feature marching from start to end.
- for (CHRPOS pos = start+1; pos <= bedItr->end; pos++)
- {
- // map pointer grabbing the starts and ends observed at this position
- depthItr = bedItr->depthMap.find(pos);
- // increment coverage if starts observed at this position.
- if (depthItr != bedItr->depthMap.end())
- depth += depthItr->second.starts;
- // update coverage assuming the current position is within the current B feature
- if ((pos > bedItr->start) && (pos <= bedItr->end)) {
- if (depth == 0) zeroDepthCount++;
- // update our histograms, assuming we are not reporting "per-base" coverage.
- if (_eachBase == false) {
- depthHist[depth]++;
- allDepthHist[depth]++;
- }
- else {
- _bedB->reportBedTab(*bedItr);
- printf("%d\t%d\n", pos-bedItr->start, depth);
- }
- }
- // decrement coverage if ends observed at this position.
- if (depthItr != bedItr->depthMap.end())
- depth = depth - depthItr->second.ends;
- }
-
- // Summarize the coverage for the current interval,
- // assuming the user has not requested "per-base" coverage.
+ vector<BEDCOV>::const_iterator bedItr = binItr->second.begin();
+ vector<BEDCOV>::const_iterator bedEnd = binItr->second.end();
+ for (; bedItr != bedEnd; ++bedItr)
+ {
+ int zeroDepthCount = 0; // number of bases with zero depth
+ int depth = 0; // tracks the depth at the current base
+
+ // the start is either the first base in the feature OR
+ // the leftmost position of an overlapping feature. e.g. (s = start):
+ // A ----------
+ // B s ------------
+ int start = min(bedItr->minOverlapStart, bedItr->start);
+
+ // track the numnber of bases in the feature covered by
+ // 0, 1, 2, ... n features in A
+ map<unsigned int, unsigned int> depthHist;
+ map<unsigned int, DEPTH>::const_iterator depthItr;
+
+ // compute the coverage observed at each base in the feature marching from start to end.
+ for (CHRPOS pos = start+1; pos <= bedItr->end; pos++)
+ {
+ // map pointer grabbing the starts and ends observed at this position
+ depthItr = bedItr->depthMap.find(pos);
+ // increment coverage if starts observed at this position.
+ if (depthItr != bedItr->depthMap.end())
+ depth += depthItr->second.starts;
+ // update coverage assuming the current position is within the current B feature
+ if ((pos > bedItr->start) && (pos <= bedItr->end)) {
+ if (depth == 0) zeroDepthCount++;
+ // update our histograms, assuming we are not reporting "per-base" coverage.
+ if (_eachBase == false) {
+ depthHist[depth]++;
+ allDepthHist[depth]++;
+ }
+ else {
+ _bedB->reportBedTab(*bedItr);
+ printf("%d\t%d\n", pos-bedItr->start, depth);
+ }
+ }
+ // decrement coverage if ends observed at this position.
+ if (depthItr != bedItr->depthMap.end())
+ depth = depth - depthItr->second.ends;
+ }
+
+ // Summarize the coverage for the current interval,
+ // assuming the user has not requested "per-base" coverage.
if (_eachBase == false) {
- CHRPOS length = bedItr->end - bedItr->start;
- totalLength += length;
- int nonZeroBases = (length - zeroDepthCount);
- float fractCovered = (float) nonZeroBases / length;
-
- // print a summary of the coverage
- if (_writeHistogram == false) {
- _bedB->reportBedTab(*bedItr);
- printf("%d\t%d\t%d\t%0.7f\n", bedItr->count, nonZeroBases, length, fractCovered);
- }
- // report the number of bases with coverage == x
- else {
- map<unsigned int, unsigned int>::const_iterator histItr = depthHist.begin();
- map<unsigned int, unsigned int>::const_iterator histEnd = depthHist.end();
- for (; histItr != histEnd; ++histItr)
- {
- float fractAtThisDepth = (float) histItr->second / length;
- _bedB->reportBedTab(*bedItr);
- printf("%d\t%d\t%d\t%0.7f\n", histItr->first, histItr->second, length, fractAtThisDepth);
- }
- }
- }
- }
- }
- }
- // report a histogram of coverage among _all_
- // features in B.
- if (_writeHistogram == true) {
- map<unsigned int, unsigned int>::const_iterator histItr = allDepthHist.begin();
- map<unsigned int, unsigned int>::const_iterator histEnd = allDepthHist.end();
- for (; histItr != histEnd; ++histItr) {
- float fractAtThisDepth = (float) histItr->second / totalLength;
- printf("all\t%d\t%d\t%d\t%0.7f\n", histItr->first, histItr->second, totalLength, fractAtThisDepth);
- }
- }
+ CHRPOS length = bedItr->end - bedItr->start;
+ totalLength += length;
+ int nonZeroBases = (length - zeroDepthCount);
+ float fractCovered = (float) nonZeroBases / length;
+
+ // print a summary of the coverage
+ if (_writeHistogram == false) {
+ _bedB->reportBedTab(*bedItr);
+ printf("%d\t%d\t%d\t%0.7f\n", bedItr->count, nonZeroBases, length, fractCovered);
+ }
+ // report the number of bases with coverage == x
+ else {
+ map<unsigned int, unsigned int>::const_iterator histItr = depthHist.begin();
+ map<unsigned int, unsigned int>::const_iterator histEnd = depthHist.end();
+ for (; histItr != histEnd; ++histItr)
+ {
+ float fractAtThisDepth = (float) histItr->second / length;
+ _bedB->reportBedTab(*bedItr);
+ printf("%d\t%d\t%d\t%0.7f\n", histItr->first, histItr->second, length, fractAtThisDepth);
+ }
+ }
+ }
+ }
+ }
+ }
+ // report a histogram of coverage among _all_
+ // features in B.
+ if (_writeHistogram == true) {
+ map<unsigned int, unsigned int>::const_iterator histItr = allDepthHist.begin();
+ map<unsigned int, unsigned int>::const_iterator histEnd = allDepthHist.end();
+ for (; histItr != histEnd; ++histItr) {
+ float fractAtThisDepth = (float) histItr->second / totalLength;
+ printf("all\t%d\t%d\t%d\t%0.7f\n", histItr->first, histItr->second, totalLength, fractAtThisDepth);
+ }
+ }
}
diff --git a/src/coverageBed/coverageBed.h b/src/coverageBed/coverageBed.h
index 3f192e392b410052bf1eaaad608947bcff66b83d..e5b33e0bb903f95c9994b9996935a1dc55fee4b5 100644
--- a/src/coverageBed/coverageBed.h
+++ b/src/coverageBed/coverageBed.h
@@ -9,7 +9,7 @@
Licenced under the GNU General Public License 2.0 license.
******************************************************************************/
-#ifndef COVERAGEBED_H
+#ifndef COVERAGEBED_H
#define COVERAGEBED_H
#include "bedFile.h"
@@ -35,42 +35,42 @@ class BedCoverage {
public:
- // constructor
- BedCoverage(string &bedAFile, string &bedBFile, bool forceStrand, bool writeHistogram,
- bool bamInput, bool obeySplits, bool eachBase);
+ // constructor
+ BedCoverage(string &bedAFile, string &bedBFile, bool forceStrand, bool writeHistogram,
+ bool bamInput, bool obeySplits, bool eachBase);
+
+ // destructor
+ ~BedCoverage(void);
- // destructor
- ~BedCoverage(void);
-
private:
- // input files.
- string _bedAFile;
- string _bedBFile;
-
- // instance of a bed file class.
- BedFile *_bedA, *_bedB;
-
- // do we care about strandedness when counting coverage?
- bool _forceStrand;
-
- // should we write a histogram for each feature in B?
- bool _writeHistogram;
-
- // are we dealing with BAM input for "A"?
- bool _bamInput;
-
- // should we split BED/BAM into discrete blocks?
+ // input files.
+ string _bedAFile;
+ string _bedBFile;
+
+ // instance of a bed file class.
+ BedFile *_bedA, *_bedB;
+
+ // do we care about strandedness when counting coverage?
+ bool _forceStrand;
+
+ // should we write a histogram for each feature in B?
+ bool _writeHistogram;
+
+ // are we dealing with BAM input for "A"?
+ bool _bamInput;
+
+ // should we split BED/BAM into discrete blocks?
bool _obeySplits;
-
+
// should discrete coverage be reported for each base in each feature?
bool _eachBase;
-
- // private function for reporting coverage information
- void ReportCoverage();
-
- void CollectCoverageBed();
- void CollectCoverageBam(string bamFile);
+ // private function for reporting coverage information
+ void ReportCoverage();
+
+ void CollectCoverageBed();
+
+ void CollectCoverageBam(string bamFile);
};
#endif /* COVERAGEBED_H */
diff --git a/src/coverageBed/coverageMain.cpp b/src/coverageBed/coverageMain.cpp
index c04d257c6bab91fd56084e70aa02ff6a4426123b..7b687af5cdcc59dd91e4f114003af3d164d3fa67 100644
--- a/src/coverageBed/coverageMain.cpp
+++ b/src/coverageBed/coverageMain.cpp
@@ -25,138 +25,138 @@ void ShowHelp(void);
int main(int argc, char* argv[]) {
- // our configuration variables
- bool showHelp = false;
-
- // input files
- string bedAFile;
- string bedBFile;
-
- // parm flags
- bool forceStrand = false;
- bool writeHistogram = false;
- bool eachBase = false;
+ // our configuration variables
+ bool showHelp = false;
+
+ // input files
+ string bedAFile;
+ string bedBFile;
+
+ // parm flags
+ bool forceStrand = false;
+ bool writeHistogram = false;
+ bool eachBase = false;
bool obeySplits = false;
- bool bamInput = false;
- bool haveBedA = false;
- bool haveBedB = false;
-
- // check to see if we should print out some help
- if(argc <= 1) showHelp = true;
-
- for(int i = 1; i < argc; i++) {
- int parameterLength = (int)strlen(argv[i]);
-
- if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
- (PARAMETER_CHECK("--help", 5, parameterLength))) {
- showHelp = true;
- }
- }
-
- if(showHelp) ShowHelp();
-
- // do some parsing (all of these parameters require 2 strings)
- for(int i = 1; i < argc; i++) {
-
- int parameterLength = (int)strlen(argv[i]);
-
- if(PARAMETER_CHECK("-a", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveBedA = true;
- bedAFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-abam", 5, parameterLength)) {
- if ((i+1) < argc) {
- haveBedA = true;
- bamInput = true;
- bedAFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-b", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveBedB = true;
- bedBFile = argv[i + 1];
- i++;
- }
- }
- else if (PARAMETER_CHECK("-s", 2, parameterLength)) {
- forceStrand = true;
- }
- else if (PARAMETER_CHECK("-hist", 5, parameterLength)) {
- writeHistogram = true;
- }
- else if(PARAMETER_CHECK("-d", 2, parameterLength)) {
- eachBase = true;
- }
- else if (PARAMETER_CHECK("-split", 6, parameterLength)) {
- obeySplits = true;
- }
- else {
- cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
- showHelp = true;
- }
- }
-
- // make sure we have both input files
- if (!haveBedA || !haveBedB) {
- cerr << endl << "*****" << endl << "*****ERROR: Need -a and -b files. " << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (!showHelp) {
- BedCoverage *bg = new BedCoverage(bedAFile, bedBFile, forceStrand, writeHistogram, bamInput, obeySplits, eachBase);
- delete bg;
- return 0;
- }
- else {
- ShowHelp();
- }
+ bool bamInput = false;
+ bool haveBedA = false;
+ bool haveBedB = false;
+
+ // check to see if we should print out some help
+ if(argc <= 1) showHelp = true;
+
+ for(int i = 1; i < argc; i++) {
+ int parameterLength = (int)strlen(argv[i]);
+
+ if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
+ (PARAMETER_CHECK("--help", 5, parameterLength))) {
+ showHelp = true;
+ }
+ }
+
+ if(showHelp) ShowHelp();
+
+ // do some parsing (all of these parameters require 2 strings)
+ for(int i = 1; i < argc; i++) {
+
+ int parameterLength = (int)strlen(argv[i]);
+
+ if(PARAMETER_CHECK("-a", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveBedA = true;
+ bedAFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-abam", 5, parameterLength)) {
+ if ((i+1) < argc) {
+ haveBedA = true;
+ bamInput = true;
+ bedAFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-b", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveBedB = true;
+ bedBFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if (PARAMETER_CHECK("-s", 2, parameterLength)) {
+ forceStrand = true;
+ }
+ else if (PARAMETER_CHECK("-hist", 5, parameterLength)) {
+ writeHistogram = true;
+ }
+ else if(PARAMETER_CHECK("-d", 2, parameterLength)) {
+ eachBase = true;
+ }
+ else if (PARAMETER_CHECK("-split", 6, parameterLength)) {
+ obeySplits = true;
+ }
+ else {
+ cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
+ showHelp = true;
+ }
+ }
+
+ // make sure we have both input files
+ if (!haveBedA || !haveBedB) {
+ cerr << endl << "*****" << endl << "*****ERROR: Need -a and -b files. " << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (!showHelp) {
+ BedCoverage *bg = new BedCoverage(bedAFile, bedBFile, forceStrand, writeHistogram, bamInput, obeySplits, eachBase);
+ delete bg;
+ return 0;
+ }
+ else {
+ ShowHelp();
+ }
}
void ShowHelp(void) {
-
- cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
-
- cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
-
- cerr << "Summary: Returns the depth and breadth of coverage of features from A" << endl;
- cerr << "\t on the intervals in B." << endl << endl;
-
- cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -a <bed/gff/vcf> -b <bed/gff/vcf>" << endl << endl;
-
- cerr << "Options: " << endl;
-
- cerr << "\t-abam\t" << "The A input file is in BAM format." << endl << endl;
-
- cerr << "\t-s\t" << "Force strandedness. That is, only include hits in A that" << endl;
- cerr << "\t\toverlap B on the same strand." << endl;
- cerr << "\t\t- By default, hits are included without respect to strand." << endl << endl;
-
- cerr << "\t-hist\t" << "Report a histogram of coverage for each feature in B" << endl;
- cerr << "\t\tas well as a summary histogram for _all_ features in B." << endl << endl;
- cerr << "\t\tOutput (tab delimited) after each feature in B:" << endl;
- cerr << "\t\t 1) depth\n\t\t 2) # bases at depth\n\t\t 3) size of B\n\t\t 4) % of B at depth" << endl << endl;
-
- cerr << "\t-d\t" << "Report the depth at each position in each B feature." << endl;
- cerr << "\t\tPositions reported are one based. Each position" << endl;
- cerr << "\t\tand depth follow the complete B feature." << endl << endl;
-
- cerr << "\t-split\t" << "Treat \"split\" BAM or BED12 entries as distinct BED intervals." << endl;
- cerr << "\t\twhen computing coverage." << endl;
- cerr << "\t\tFor BAM files, this uses the CIGAR \"N\" and \"D\" operations " << endl;
- cerr << "\t\tto infer the blocks for computing coverage." << endl;
- cerr << "\t\tFor BED12 files, this uses the BlockCount, BlockStarts," << endl;
- cerr << "\t\tand BlockEnds fields (i.e., columns 10,11,12)." << endl << endl;
-
- cerr << "Default Output: " << endl;
- cerr << "\t" << " After each entry in B, reports: " << endl;
- cerr << "\t 1) The number of features in A that overlapped the B interval." << endl;
- cerr << "\t 2) The number of bases in B that had non-zero coverage." << endl;
- cerr << "\t 3) The length of the entry in B." << endl;
- cerr << "\t 4) The fraction of bases in B that had non-zero coverage." << endl << endl;
-
- exit(1);
+
+ cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
+
+ cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
+
+ cerr << "Summary: Returns the depth and breadth of coverage of features from A" << endl;
+ cerr << "\t on the intervals in B." << endl << endl;
+
+ cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -a <bed/gff/vcf> -b <bed/gff/vcf>" << endl << endl;
+
+ cerr << "Options: " << endl;
+
+ cerr << "\t-abam\t" << "The A input file is in BAM format." << endl << endl;
+
+ cerr << "\t-s\t" << "Force strandedness. That is, only include hits in A that" << endl;
+ cerr << "\t\toverlap B on the same strand." << endl;
+ cerr << "\t\t- By default, hits are included without respect to strand." << endl << endl;
+
+ cerr << "\t-hist\t" << "Report a histogram of coverage for each feature in B" << endl;
+ cerr << "\t\tas well as a summary histogram for _all_ features in B." << endl << endl;
+ cerr << "\t\tOutput (tab delimited) after each feature in B:" << endl;
+ cerr << "\t\t 1) depth\n\t\t 2) # bases at depth\n\t\t 3) size of B\n\t\t 4) % of B at depth" << endl << endl;
+
+ cerr << "\t-d\t" << "Report the depth at each position in each B feature." << endl;
+ cerr << "\t\tPositions reported are one based. Each position" << endl;
+ cerr << "\t\tand depth follow the complete B feature." << endl << endl;
+
+ cerr << "\t-split\t" << "Treat \"split\" BAM or BED12 entries as distinct BED intervals." << endl;
+ cerr << "\t\twhen computing coverage." << endl;
+ cerr << "\t\tFor BAM files, this uses the CIGAR \"N\" and \"D\" operations " << endl;
+ cerr << "\t\tto infer the blocks for computing coverage." << endl;
+ cerr << "\t\tFor BED12 files, this uses the BlockCount, BlockStarts," << endl;
+ cerr << "\t\tand BlockEnds fields (i.e., columns 10,11,12)." << endl << endl;
+
+ cerr << "Default Output: " << endl;
+ cerr << "\t" << " After each entry in B, reports: " << endl;
+ cerr << "\t 1) The number of features in A that overlapped the B interval." << endl;
+ cerr << "\t 2) The number of bases in B that had non-zero coverage." << endl;
+ cerr << "\t 3) The length of the entry in B." << endl;
+ cerr << "\t 4) The fraction of bases in B that had non-zero coverage." << endl << endl;
+
+ exit(1);
}
diff --git a/src/fastaFromBed/fastaFromBed.cpp b/src/fastaFromBed/fastaFromBed.cpp
index 9b70f9cf29837390a8d7386bd25e3dec14c1420b..bc4a5a6d2abf5f6ff9fecd3ec62240ca08c94747 100644
--- a/src/fastaFromBed/fastaFromBed.cpp
+++ b/src/fastaFromBed/fastaFromBed.cpp
@@ -13,40 +13,40 @@
#include "fastaFromBed.h"
-Bed2Fa::Bed2Fa(bool &useName, string &dbFile, string &bedFile,
+Bed2Fa::Bed2Fa(bool &useName, string &dbFile, string &bedFile,
string &fastaOutFile, bool &useFasta, bool &useStrand) {
- if (useName) {
- _useName = true;
- }
-
- _dbFile = dbFile;
- _bedFile = bedFile;
- _fastaOutFile = fastaOutFile;
- _useFasta = useFasta;
- _useStrand = useStrand;
-
- _bed = new BedFile(_bedFile);
-
- // Figure out what the output file should be.
- if (fastaOutFile == "stdout") {
+ if (useName) {
+ _useName = true;
+ }
+
+ _dbFile = dbFile;
+ _bedFile = bedFile;
+ _fastaOutFile = fastaOutFile;
+ _useFasta = useFasta;
+ _useStrand = useStrand;
+
+ _bed = new BedFile(_bedFile);
+
+ // Figure out what the output file should be.
+ if (fastaOutFile == "stdout") {
_faOut = &cout;
}
else {
- // Make sure we can open the file.
- ofstream fa(fastaOutFile.c_str(), ios::out);
- if ( !fa ) {
- cerr << "Error: The requested fasta output file (" << fastaOutFile << ") could not be opened. Exiting!" << endl;
- exit (1);
- }
- else {
- fa.close();
- _faOut = new ofstream(fastaOutFile.c_str(), ios::out);
- }
- }
-
- // Extract the requested intervals from the FASTA input file.
- ExtractDNA();
+ // Make sure we can open the file.
+ ofstream fa(fastaOutFile.c_str(), ios::out);
+ if ( !fa ) {
+ cerr << "Error: The requested fasta output file (" << fastaOutFile << ") could not be opened. Exiting!" << endl;
+ exit (1);
+ }
+ else {
+ fa.close();
+ _faOut = new ofstream(fastaOutFile.c_str(), ios::out);
+ }
+ }
+
+ // Extract the requested intervals from the FASTA input file.
+ ExtractDNA();
}
@@ -58,37 +58,37 @@ Bed2Fa::~Bed2Fa(void) {
// ReportDNA
//******************************************************************************
void Bed2Fa::ReportDNA(const BED &bed, const string &currDNA, const string &currChrom) {
-
- if ( (bed.start <= currDNA.size()) && (bed.end <= currDNA.size()) ) {
-
- string dna = currDNA.substr(bed.start, ((bed.end - bed.start)));
- // revcomp if necessary. Thanks to Thomas Doktor.
- if ((_useStrand == true) && (bed.strand == "-"))
- reverseComplement(dna);
-
- if (!(_useName)) {
- if (_useFasta == true) {
- if (_useStrand == true)
- *_faOut << ">" << currChrom << ":" << bed.start << "-" << bed.end << "(" << bed.strand << ")" << endl << dna << endl;
- else
- *_faOut << ">" << currChrom << ":" << bed.start << "-" << bed.end << endl << dna << endl;
- }
- else {
- if (_useStrand == true)
- *_faOut << currChrom << ":" << bed.start << "-" << bed.end << "(" << bed.strand << ")" << "\t" << dna << endl;
- else
- *_faOut << currChrom << ":" << bed.start << "-" << bed.end << "\t" << dna << endl;
- }
- }
- else {
- if (_useFasta == true)
- *_faOut << ">" << bed.name << endl << dna << endl;
- else
- *_faOut << bed.name << "\t" << dna << endl;
- }
+
+ if ( (bed.start <= currDNA.size()) && (bed.end <= currDNA.size()) ) {
+
+ string dna = currDNA.substr(bed.start, ((bed.end - bed.start)));
+ // revcomp if necessary. Thanks to Thomas Doktor.
+ if ((_useStrand == true) && (bed.strand == "-"))
+ reverseComplement(dna);
+
+ if (!(_useName)) {
+ if (_useFasta == true) {
+ if (_useStrand == true)
+ *_faOut << ">" << currChrom << ":" << bed.start << "-" << bed.end << "(" << bed.strand << ")" << endl << dna << endl;
+ else
+ *_faOut << ">" << currChrom << ":" << bed.start << "-" << bed.end << endl << dna << endl;
+ }
+ else {
+ if (_useStrand == true)
+ *_faOut << currChrom << ":" << bed.start << "-" << bed.end << "(" << bed.strand << ")" << "\t" << dna << endl;
+ else
+ *_faOut << currChrom << ":" << bed.start << "-" << bed.end << "\t" << dna << endl;
+ }
+ }
+ else {
+ if (_useFasta == true)
+ *_faOut << ">" << bed.name << endl << dna << endl;
+ else
+ *_faOut << bed.name << "\t" << dna << endl;
+ }
}
- else cerr << "Feature (" << bed.chrom << ":" << bed.start << "-" << bed.end << ") beyond "
- << currChrom << " size (" << currDNA.size() << " bp). Skipping." << endl;
+ else cerr << "Feature (" << bed.chrom << ":" << bed.start << "-" << bed.end << ") beyond "
+ << currChrom << " size (" << currDNA.size() << " bp). Skipping." << endl;
}
@@ -98,53 +98,53 @@ void Bed2Fa::ReportDNA(const BED &bed, const string &currDNA, const string &curr
//******************************************************************************
void Bed2Fa::ExtractDNA() {
- /* Make sure that we can oen all of the files successfully*/
-
- // open the fasta database for reading
- ifstream faDb(_dbFile.c_str(), ios::in);
- if ( !faDb ) {
- cerr << "Error: The requested fasta database file (" << _dbFile << ") could not be opened. Exiting!" << endl;
- exit (1);
- }
-
- // load the BED file into an unbinned map.
- _bed->loadBedFileIntoMapNoBin();
-
- //Read the fastaDb chromosome by chromosome
- string fastaDbLine;
- string currChrom;
- string currDNA = "";
- currDNA.reserve(500000000);
-
- while (getline(faDb,fastaDbLine)) {
- if (fastaDbLine.find(">",0) != 0 ) {
- currDNA += fastaDbLine;
- }
- else {
- if (currDNA.size() > 0) {
-
- vector<BED>::const_iterator bedItr = _bed->bedMapNoBin[currChrom].begin();
- vector<BED>::const_iterator bedEnd = _bed->bedMapNoBin[currChrom].end();
- // loop through each BED entry for this chrom and print the sequence
+ /* Make sure that we can oen all of the files successfully*/
+
+ // open the fasta database for reading
+ ifstream faDb(_dbFile.c_str(), ios::in);
+ if ( !faDb ) {
+ cerr << "Error: The requested fasta database file (" << _dbFile << ") could not be opened. Exiting!" << endl;
+ exit (1);
+ }
+
+ // load the BED file into an unbinned map.
+ _bed->loadBedFileIntoMapNoBin();
+
+ //Read the fastaDb chromosome by chromosome
+ string fastaDbLine;
+ string currChrom;
+ string currDNA = "";
+ currDNA.reserve(500000000);
+
+ while (getline(faDb,fastaDbLine)) {
+ if (fastaDbLine.find(">",0) != 0 ) {
+ currDNA += fastaDbLine;
+ }
+ else {
+ if (currDNA.size() > 0) {
+
+ vector<BED>::const_iterator bedItr = _bed->bedMapNoBin[currChrom].begin();
+ vector<BED>::const_iterator bedEnd = _bed->bedMapNoBin[currChrom].end();
+ // loop through each BED entry for this chrom and print the sequence
for (; bedItr != bedEnd; ++bedItr) {
- ReportDNA(*bedItr, currDNA, currChrom);
+ ReportDNA(*bedItr, currDNA, currChrom);
}
- currDNA = "";
- }
- currChrom = fastaDbLine.substr(1, fastaDbLine.find_first_of(" ")-1);
- }
- }
-
- // process the last chromosome in the fasta file.
- if (currDNA.size() > 0) {
- vector<BED>::const_iterator bedItr = _bed->bedMapNoBin[currChrom].begin();
- vector<BED>::const_iterator bedEnd = _bed->bedMapNoBin[currChrom].end();
- // loop through each BED entry for this chrom and print the sequence
+ currDNA = "";
+ }
+ currChrom = fastaDbLine.substr(1, fastaDbLine.find_first_of(" ")-1);
+ }
+ }
+
+ // process the last chromosome in the fasta file.
+ if (currDNA.size() > 0) {
+ vector<BED>::const_iterator bedItr = _bed->bedMapNoBin[currChrom].begin();
+ vector<BED>::const_iterator bedEnd = _bed->bedMapNoBin[currChrom].end();
+ // loop through each BED entry for this chrom and print the sequence
for (; bedItr != bedEnd; ++bedItr) {
ReportDNA(*bedItr, currDNA, currChrom);
}
- currDNA = "";
- }
+ currDNA = "";
+ }
}
diff --git a/src/fastaFromBed/fastaFromBed.h b/src/fastaFromBed/fastaFromBed.h
index e8d4ab0a4355e3a82a5f772a61769dcce11f84a5..383d1416b497940595a1049c24ae8d423859b511 100644
--- a/src/fastaFromBed/fastaFromBed.h
+++ b/src/fastaFromBed/fastaFromBed.h
@@ -26,29 +26,29 @@ using namespace std;
class Bed2Fa {
public:
-
- // constructor
- Bed2Fa(bool &useName, string &dbFile, string &bedFile, string &fastaOutFile,
- bool &useFasta, bool &useStrand);
- // destructor
- ~Bed2Fa(void);
+ // constructor
+ Bed2Fa(bool &useName, string &dbFile, string &bedFile, string &fastaOutFile,
+ bool &useFasta, bool &useStrand);
- void ExtractDNA();
+ // destructor
+ ~Bed2Fa(void);
+
+ void ExtractDNA();
void ReportDNA(const BED &bed, const string &currDNA, const string &currChrom);
-
+
private:
-
- bool _useName;
- string _dbFile;
- string _bedFile;
- string _fastaOutFile;
- bool _useFasta;
- bool _useStrand;
-
- // instance of a bed file class.
- BedFile *_bed;
+
+ bool _useName;
+ string _dbFile;
+ string _bedFile;
+ string _fastaOutFile;
+ bool _useFasta;
+ bool _useStrand;
+
+ // instance of a bed file class.
+ BedFile *_bed;
ostream *_faOut;
};
diff --git a/src/fastaFromBed/fastaFromBedMain.cpp b/src/fastaFromBed/fastaFromBedMain.cpp
index 6342c9f20b395b6490afe94a1f741049971327bf..c31676d93228329dad44141c43b5d790aa8471d9 100644
--- a/src/fastaFromBed/fastaFromBedMain.cpp
+++ b/src/fastaFromBed/fastaFromBedMain.cpp
@@ -26,121 +26,121 @@ void ShowHelp(void);
int main(int argc, char* argv[]) {
- // our configuration variables
- bool showHelp = false;
-
- // input files
- string fastaDbFile;
- string bedFile;
-
- // output files
- string fastaOutFile;
-
- // checks for existence of parameters
- bool haveFastaDb = false;
- bool haveBed = false;
- bool haveFastaOut = false;
- bool useNameOnly = false;
- bool useFasta = true;
- bool useStrand = false;
-
- // check to see if we should print out some help
- if(argc <= 1) showHelp = true;
-
- for(int i = 1; i < argc; i++) {
- int parameterLength = (int)strlen(argv[i]);
-
- if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
- (PARAMETER_CHECK("--help", 5, parameterLength))) {
- showHelp = true;
- }
- }
-
- if(showHelp) ShowHelp();
-
- // do some parsing (all of these parameters require 2 strings)
- for(int i = 1; i < argc; i++) {
-
- int parameterLength = (int)strlen(argv[i]);
-
- if(PARAMETER_CHECK("-fi", 3, parameterLength)) {
- if ((i+1) < argc) {
- haveFastaDb = true;
- fastaDbFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-fo", 3, parameterLength)) {
- if ((i+1) < argc) {
- haveFastaOut = true;
- fastaOutFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-bed", 4, parameterLength)) {
- if ((i+1) < argc) {
- haveBed = true;
- bedFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-name", 5, parameterLength)) {
- useNameOnly = true;
- }
- else if(PARAMETER_CHECK("-tab", 4, parameterLength)) {
- useFasta = false;
- }
- else if(PARAMETER_CHECK("-s", 2, parameterLength)) {
- useStrand = true;
- }
- else {
- cerr << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
- showHelp = true;
- }
- }
-
- if (!haveFastaDb || !haveFastaOut || !haveBed) {
- showHelp = true;
- }
-
- if (!showHelp) {
-
- Bed2Fa *b2f = new Bed2Fa(useNameOnly, fastaDbFile, bedFile, fastaOutFile, useFasta, useStrand);
- delete b2f;
-
- return 0;
- }
- else {
- ShowHelp();
- }
+ // our configuration variables
+ bool showHelp = false;
+
+ // input files
+ string fastaDbFile;
+ string bedFile;
+
+ // output files
+ string fastaOutFile;
+
+ // checks for existence of parameters
+ bool haveFastaDb = false;
+ bool haveBed = false;
+ bool haveFastaOut = false;
+ bool useNameOnly = false;
+ bool useFasta = true;
+ bool useStrand = false;
+
+ // check to see if we should print out some help
+ if(argc <= 1) showHelp = true;
+
+ for(int i = 1; i < argc; i++) {
+ int parameterLength = (int)strlen(argv[i]);
+
+ if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
+ (PARAMETER_CHECK("--help", 5, parameterLength))) {
+ showHelp = true;
+ }
+ }
+
+ if(showHelp) ShowHelp();
+
+ // do some parsing (all of these parameters require 2 strings)
+ for(int i = 1; i < argc; i++) {
+
+ int parameterLength = (int)strlen(argv[i]);
+
+ if(PARAMETER_CHECK("-fi", 3, parameterLength)) {
+ if ((i+1) < argc) {
+ haveFastaDb = true;
+ fastaDbFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-fo", 3, parameterLength)) {
+ if ((i+1) < argc) {
+ haveFastaOut = true;
+ fastaOutFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-bed", 4, parameterLength)) {
+ if ((i+1) < argc) {
+ haveBed = true;
+ bedFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-name", 5, parameterLength)) {
+ useNameOnly = true;
+ }
+ else if(PARAMETER_CHECK("-tab", 4, parameterLength)) {
+ useFasta = false;
+ }
+ else if(PARAMETER_CHECK("-s", 2, parameterLength)) {
+ useStrand = true;
+ }
+ else {
+ cerr << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
+ showHelp = true;
+ }
+ }
+
+ if (!haveFastaDb || !haveFastaOut || !haveBed) {
+ showHelp = true;
+ }
+
+ if (!showHelp) {
+
+ Bed2Fa *b2f = new Bed2Fa(useNameOnly, fastaDbFile, bedFile, fastaOutFile, useFasta, useStrand);
+ delete b2f;
+
+ return 0;
+ }
+ else {
+ ShowHelp();
+ }
}
void ShowHelp(void) {
-
- cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
-
- cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
-
- cerr << "Summary: Extract DNA sequences into a fasta file based on feature coordinates." << endl << endl;
- cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -fi <fasta> -bed <bed/gff/vcf> -fo <fasta> " << endl << endl;
+ cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
- cerr << "Options: " << endl;
- cerr << "\t-fi\tInput FASTA file" << endl;
- cerr << "\t-bed\tBED/GFF/VCF file of ranges to extract from -fi" << endl;
- cerr << "\t-fo\tOutput file (can be FASTA or TAB-delimited)" << endl;
- cerr << "\t-name\tUse the name field for the FASTA header" << endl;
+ cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
- cerr << "\t-tab\tWrite output in TAB delimited format." << endl;
- cerr << "\t\t- Default is FASTA format." << endl << endl;
+ cerr << "Summary: Extract DNA sequences into a fasta file based on feature coordinates." << endl << endl;
- cerr << "\t-s\tForce strandedness. If the feature occupies the antisense strand," << endl;
- cerr << "\t\tthe sequence will be reverse complemented." << endl;
- cerr << "\t\t- By default, strand information is ignored." << endl << endl;
+ cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -fi <fasta> -bed <bed/gff/vcf> -fo <fasta> " << endl << endl;
+ cerr << "Options: " << endl;
+ cerr << "\t-fi\tInput FASTA file" << endl;
+ cerr << "\t-bed\tBED/GFF/VCF file of ranges to extract from -fi" << endl;
+ cerr << "\t-fo\tOutput file (can be FASTA or TAB-delimited)" << endl;
+ cerr << "\t-name\tUse the name field for the FASTA header" << endl;
+ cerr << "\t-tab\tWrite output in TAB delimited format." << endl;
+ cerr << "\t\t- Default is FASTA format." << endl << endl;
+
+ cerr << "\t-s\tForce strandedness. If the feature occupies the antisense strand," << endl;
+ cerr << "\t\tthe sequence will be reverse complemented." << endl;
+ cerr << "\t\t- By default, strand information is ignored." << endl << endl;
+
+
+
+ // end the program here
+ exit(1);
- // end the program here
- exit(1);
-
}
diff --git a/src/fjoin/fjoin.cpp b/src/fjoin/fjoin.cpp
index c1cbfa0c16357ddfbd8490af6d5ede994d12aca4..8159118366b698c3e2c7e5fd4533ed26a29b6b1a 100644
--- a/src/fjoin/fjoin.cpp
+++ b/src/fjoin/fjoin.cpp
@@ -20,144 +20,144 @@ bool leftOf(const BED &a, const BED &b);
bool BedIntersect::processHits(BED &a, vector<BED> &hits) {
// how many overlaps are there b/w the bed and the set of hits?
int s, e, overlapBases;
- int numOverlaps = 0;
+ int numOverlaps = 0;
bool hitsFound = false;
- int aLength = (a.end - a.start); // the length of a in b.p.
-
- // loop through the hits and report those that meet the user's criteria
- vector<BED>::const_iterator h = hits.begin();
- vector<BED>::const_iterator hitsEnd = hits.end();
- for (; h != hitsEnd; ++h) {
- s = max(a.start, h->start);
- e = min(a.end, h->end);
- overlapBases = (e - s); // the number of overlapping bases b/w a and b
-
- // is there enough overlap relative to the user's request? (default ~ 1bp)
- if ( ( (float) overlapBases / (float) aLength ) >= _overlapFraction ) {
- // Report the hit if the user doesn't care about reciprocal overlap between A and B.
- if (_reciprocal == false) {
- hitsFound = true;
- numOverlaps++;
- if (_printable == true)
- ReportOverlapDetail(overlapBases, a, *h, s, e);
- }
- // we require there to be sufficient __reciprocal__ overlap
- else {
- int bLength = (h->end - h->start);
- float bOverlap = ( (float) overlapBases / (float) bLength );
- if (bOverlap >= _overlapFraction) {
- hitsFound = true;
- numOverlaps++;
- if (_printable == true)
- ReportOverlapDetail(overlapBases, a, *h, s, e);
- }
- }
- }
- }
- // report the summary of the overlaps if requested.
- ReportOverlapSummary(a, numOverlaps);
- // were hits found for this BED feature?
- return hitsFound;
+ int aLength = (a.end - a.start); // the length of a in b.p.
+
+ // loop through the hits and report those that meet the user's criteria
+ vector<BED>::const_iterator h = hits.begin();
+ vector<BED>::const_iterator hitsEnd = hits.end();
+ for (; h != hitsEnd; ++h) {
+ s = max(a.start, h->start);
+ e = min(a.end, h->end);
+ overlapBases = (e - s); // the number of overlapping bases b/w a and b
+
+ // is there enough overlap relative to the user's request? (default ~ 1bp)
+ if ( ( (float) overlapBases / (float) aLength ) >= _overlapFraction ) {
+ // Report the hit if the user doesn't care about reciprocal overlap between A and B.
+ if (_reciprocal == false) {
+ hitsFound = true;
+ numOverlaps++;
+ if (_printable == true)
+ ReportOverlapDetail(overlapBases, a, *h, s, e);
+ }
+ // we require there to be sufficient __reciprocal__ overlap
+ else {
+ int bLength = (h->end - h->start);
+ float bOverlap = ( (float) overlapBases / (float) bLength );
+ if (bOverlap >= _overlapFraction) {
+ hitsFound = true;
+ numOverlaps++;
+ if (_printable == true)
+ ReportOverlapDetail(overlapBases, a, *h, s, e);
+ }
+ }
+ }
+ }
+ // report the summary of the overlaps if requested.
+ ReportOverlapSummary(a, numOverlaps);
+ // were hits found for this BED feature?
+ return hitsFound;
}
/*
- Constructor
+ Constructor
*/
-BedIntersect::BedIntersect(string bedAFile, string bedBFile, bool anyHit,
- bool writeA, bool writeB, bool writeOverlap, bool writeAllOverlap,
- float overlapFraction, bool noHit, bool writeCount, bool forceStrand,
- bool reciprocal, bool obeySplits, bool bamInput, bool bamOutput) {
-
- _bedAFile = bedAFile;
- _bedBFile = bedBFile;
- _anyHit = anyHit;
- _noHit = noHit;
- _writeA = writeA;
- _writeB = writeB;
- _writeOverlap = writeOverlap;
- _writeAllOverlap = writeAllOverlap;
- _writeCount = writeCount;
- _overlapFraction = overlapFraction;
- _forceStrand = forceStrand;
- _reciprocal = reciprocal;
+BedIntersect::BedIntersect(string bedAFile, string bedBFile, bool anyHit,
+ bool writeA, bool writeB, bool writeOverlap, bool writeAllOverlap,
+ float overlapFraction, bool noHit, bool writeCount, bool forceStrand,
+ bool reciprocal, bool obeySplits, bool bamInput, bool bamOutput) {
+
+ _bedAFile = bedAFile;
+ _bedBFile = bedBFile;
+ _anyHit = anyHit;
+ _noHit = noHit;
+ _writeA = writeA;
+ _writeB = writeB;
+ _writeOverlap = writeOverlap;
+ _writeAllOverlap = writeAllOverlap;
+ _writeCount = writeCount;
+ _overlapFraction = overlapFraction;
+ _forceStrand = forceStrand;
+ _reciprocal = reciprocal;
_obeySplits = obeySplits;
- _bamInput = bamInput;
- _bamOutput = bamOutput;
-
- if (_anyHit || _noHit || _writeCount)
- _printable = false;
- else
+ _bamInput = bamInput;
+ _bamOutput = bamOutput;
+
+ if (_anyHit || _noHit || _writeCount)
+ _printable = false;
+ else
_printable = true;
-
- // create new BED file objects for A and B
- _bedA = new BedFile(bedAFile);
- _bedB = new BedFile(bedBFile);
-
- IntersectBed();
+
+ // create new BED file objects for A and B
+ _bedA = new BedFile(bedAFile);
+ _bedB = new BedFile(bedBFile);
+
+ IntersectBed();
}
/*
- Destructor
+ Destructor
*/
BedIntersect::~BedIntersect(void) {
}
-
-
+
+
bool leftOf(const BED &a, const BED &b) {
return (a.end <= b.start);
}
void BedIntersect::ReportOverlapDetail(const int &overlapBases, const BED &a, const BED &b,
- const CHRPOS &s, const CHRPOS &e) {
- // default. simple intersection only
- if (_writeA == false && _writeB == false && _writeOverlap == false) {
- _bedA->reportBedRangeNewLine(a,s,e);
- }
- // -wa -wbwrite the original A and B
- else if (_writeA == true && _writeB == true) {
- _bedA->reportBedTab(a);
- _bedB->reportBedNewLine(b);
- }
- // -wa write just the original A
- else if (_writeA == true) {
- _bedA->reportBedNewLine(a);
- }
- // -wb write the intersected portion of A and the original B
- else if (_writeB == true) {
- _bedA->reportBedRangeTab(a,s,e);
- _bedB->reportBedNewLine(b);
- }
- // -wo write the original A and B plus the no. of overlapping bases.
- else if (_writeOverlap == true) {
- _bedA->reportBedTab(a);
- _bedB->reportBedTab(b);
- printf("%d\n", overlapBases);
- }
+ const CHRPOS &s, const CHRPOS &e) {
+ // default. simple intersection only
+ if (_writeA == false && _writeB == false && _writeOverlap == false) {
+ _bedA->reportBedRangeNewLine(a,s,e);
+ }
+ // -wa -wbwrite the original A and B
+ else if (_writeA == true && _writeB == true) {
+ _bedA->reportBedTab(a);
+ _bedB->reportBedNewLine(b);
+ }
+ // -wa write just the original A
+ else if (_writeA == true) {
+ _bedA->reportBedNewLine(a);
+ }
+ // -wb write the intersected portion of A and the original B
+ else if (_writeB == true) {
+ _bedA->reportBedRangeTab(a,s,e);
+ _bedB->reportBedNewLine(b);
+ }
+ // -wo write the original A and B plus the no. of overlapping bases.
+ else if (_writeOverlap == true) {
+ _bedA->reportBedTab(a);
+ _bedB->reportBedTab(b);
+ printf("%d\n", overlapBases);
+ }
}
void BedIntersect::ReportOverlapSummary(const BED &a, const int &numOverlapsFound) {
- // -u just report the fact that there was >= 1 overlaps
- if (_anyHit && (numOverlapsFound >= 1)) {
- _bedA->reportBedNewLine(a);
- }
- // -c report the total number of features overlapped in B
- else if (_writeCount) {
- _bedA->reportBedTab(a);
- printf("%d\n", numOverlapsFound);
- }
- // -v report iff there were no overlaps
- else if (_noHit && (numOverlapsFound == 0)) {
- _bedA->reportBedNewLine(a);
- }
- // -wao the user wants to force the reporting of 0 overlap
- else if (_writeAllOverlap && (numOverlapsFound == 0)) {
- _bedA->reportBedTab(a);
- _bedB->reportNullBedTab();
- printf("0\n");
- }
+ // -u just report the fact that there was >= 1 overlaps
+ if (_anyHit && (numOverlapsFound >= 1)) {
+ _bedA->reportBedNewLine(a);
+ }
+ // -c report the total number of features overlapped in B
+ else if (_writeCount) {
+ _bedA->reportBedTab(a);
+ printf("%d\n", numOverlapsFound);
+ }
+ // -v report iff there were no overlaps
+ else if (_noHit && (numOverlapsFound == 0)) {
+ _bedA->reportBedNewLine(a);
+ }
+ // -wao the user wants to force the reporting of 0 overlap
+ else if (_writeAllOverlap && (numOverlapsFound == 0)) {
+ _bedA->reportBedTab(a);
+ _bedB->reportNullBedTab();
+ printf("0\n");
+ }
}
@@ -169,29 +169,29 @@ void BedIntersect::Scan(BED *x, vector<BED *> *windowX, BedLineStatus xStatus,
return;
}
- std::vector<BED *>::iterator wYIter = windowY->begin();
+ std::vector<BED *>::iterator wYIter = windowY->begin();
while (wYIter != windowY->end()) {
- if (leftOf(*(*wYIter), *x) == true) {
+ if (leftOf(*(*wYIter), *x) == true) {
(*wYIter)->finished = true;
wYIter = windowY->erase(wYIter); // erase auto-increments to the next position
- }
+ }
else if (overlaps((*wYIter)->start, (*wYIter)->end, x->start, x->end) > 0) {
- if (_lastPick == 0) {
+ if (_lastPick == 0) {
AddHits(x, *(*wYIter));
- }
+ }
else {
AddHits(*wYIter, *x);
}
- ++wYIter; // force incrementing
+ ++wYIter; // force incrementing
}
}
if (leftOf(*x,y) == false)
windowX->push_back(x);
else {
x->finished = true;
- }
+ }
// dump the buffered results (if any)
- FlushOutputBuffer();
+ FlushOutputBuffer();
}
@@ -203,14 +203,14 @@ void BedIntersect::AddHits(BED *x, const BED &y) {
void BedIntersect::FlushOutputBuffer(bool final) {
- while (_outputBuffer.empty() == false)
- {
+ while (_outputBuffer.empty() == false)
+ {
if (final == false && _outputBuffer.front()->finished == false)
break;
-
- processHits(*_outputBuffer.front(), _outputBuffer.front()->overlaps);
+
+ processHits(*_outputBuffer.front(), _outputBuffer.front()->overlaps);
// remove the finished BED entry from the heap
- delete _outputBuffer.front();
+ delete _outputBuffer.front();
_outputBuffer.pop();
}
}
@@ -218,129 +218,129 @@ void BedIntersect::FlushOutputBuffer(bool final) {
vector<BED*>* BedIntersect::GetWindow(const string &chrom, bool isA) {
- // iterator to test if a window for a given chrom exists.
- map<string, vector<BED*> >::iterator it;
-
- // grab the current window for A or B, depending on
- // the request. if a window hasn't yet been created
- // for the requested chrom, create one.
-
- if (isA) {
- it = _windowA.find(chrom);
- if (it != _windowA.end()) {
- return & _windowA[chrom];
- }
- else {
- _windowA.insert(pair<string, vector<BED *> >(chrom, vector<BED *>()));
- return & _windowA[chrom];
- }
- }
- else {
- it = _windowB.find(chrom);
- if (it != _windowB.end()) {
- return & _windowB[chrom];
- }
- else {
- _windowB.insert(pair<string, vector<BED *> >(chrom, vector<BED *>()));
- return & _windowB[chrom];
- }
- }
+ // iterator to test if a window for a given chrom exists.
+ map<string, vector<BED*> >::iterator it;
+
+ // grab the current window for A or B, depending on
+ // the request. if a window hasn't yet been created
+ // for the requested chrom, create one.
+
+ if (isA) {
+ it = _windowA.find(chrom);
+ if (it != _windowA.end()) {
+ return & _windowA[chrom];
+ }
+ else {
+ _windowA.insert(pair<string, vector<BED *> >(chrom, vector<BED *>()));
+ return & _windowA[chrom];
+ }
+ }
+ else {
+ it = _windowB.find(chrom);
+ if (it != _windowB.end()) {
+ return & _windowB[chrom];
+ }
+ else {
+ _windowB.insert(pair<string, vector<BED *> >(chrom, vector<BED *>()));
+ return & _windowB[chrom];
+ }
+ }
}
void BedIntersect::ChromSwitch(const string &chrom) {
-
- vector<BED*>::iterator windowAIter = _windowA[chrom].begin();
- vector<BED*>::iterator windowAEnd = _windowA[chrom].end();
- for (; windowAIter != windowAEnd; ++windowAIter)
- (*windowAIter)->finished = true;
-
- vector<BED*>::iterator windowBIter = _windowB[chrom].begin();
- vector<BED*>::iterator windowBEnd = _windowB[chrom].end();
- for (; windowBIter != windowBEnd; ++windowBIter)
- (*windowBIter)->finished = true;
-
- FlushOutputBuffer();
+
+ vector<BED*>::iterator windowAIter = _windowA[chrom].begin();
+ vector<BED*>::iterator windowAEnd = _windowA[chrom].end();
+ for (; windowAIter != windowAEnd; ++windowAIter)
+ (*windowAIter)->finished = true;
+
+ vector<BED*>::iterator windowBIter = _windowB[chrom].begin();
+ vector<BED*>::iterator windowBEnd = _windowB[chrom].end();
+ for (; windowBIter != windowBEnd; ++windowBIter)
+ (*windowBIter)->finished = true;
+
+ FlushOutputBuffer();
}
-void BedIntersect::IntersectBed() {
-
- int aLineNum = 0;
- int bLineNum = 0;
-
+void BedIntersect::IntersectBed() {
+
+ int aLineNum = 0;
+ int bLineNum = 0;
+
// current feature from each file
- BED *a, *b, *prevA, *prevB;
-
- // status of the current lines
- BedLineStatus aStatus, bStatus;
-
+ BED *a, *b, *prevA, *prevB;
+
+ // status of the current lines
+ BedLineStatus aStatus, bStatus;
+
// open the files; get the first line from each
_bedA->Open();
_bedB->Open();
-
- prevA = NULL;
- prevB = NULL;
+
+ prevA = NULL;
+ prevB = NULL;
a = new BED();
b = new BED();
aStatus = _bedA->GetNextBed(*a, aLineNum);
bStatus = _bedB->GetNextBed(*b, bLineNum);
-
+
while (aStatus != BED_INVALID || bStatus != BED_INVALID) {
-
+
if ((a->start <= b->start) && (a->chrom == b->chrom)) {
- prevA = a;
+ prevA = a;
_lastPick = 0;
- Scan(a, GetWindow(a->chrom, true), aStatus,
- *b, GetWindow(a->chrom, false), bStatus);
+ Scan(a, GetWindow(a->chrom, true), aStatus,
+ *b, GetWindow(a->chrom, false), bStatus);
a = new BED();
aStatus = _bedA->GetNextBed(*a, aLineNum);
}
else if ((a->start > b->start) && (a->chrom == b->chrom)) {
- prevB = b;
+ prevB = b;
_lastPick = 1;
- Scan(b, GetWindow(b->chrom, false), bStatus,
- *a, GetWindow(b->chrom, true), aStatus);
-
- b = new BED();
+ Scan(b, GetWindow(b->chrom, false), bStatus,
+ *a, GetWindow(b->chrom, true), aStatus);
+
+ b = new BED();
bStatus = _bedB->GetNextBed(*b, bLineNum);
}
- else if (a->chrom != b->chrom) {
- // A was most recently read
- if (_lastPick == 0) {
- prevB = b;
- while (b->chrom == prevA->chrom){
- _windowB[prevA->chrom].push_back(b);
- b = new BED();
- bStatus = _bedB->GetNextBed(*b, bLineNum);
- }
- Scan(prevA, GetWindow(prevA->chrom, true), aStatus,
- *prevB, GetWindow(prevA->chrom, false), bStatus);
- }
- // B was most recently read
- else {
- prevA = a;
- while (a->chrom == prevB->chrom) {
- _windowA[prevB->chrom].push_back(a);
- a = new BED();
- aStatus = _bedA->GetNextBed(*a, aLineNum);
- }
- Scan(prevB, GetWindow(prevB->chrom, false), bStatus,
- *prevA, GetWindow(prevB->chrom, true), aStatus);
- }
- FlushOutputBuffer(true);
- }
- if (prevA!=NULL&&prevB!=NULL)
- cout << prevA->chrom << " " << a->chrom << " " << a->start << " "
- << prevB->chrom << " " << b->chrom << " " << b->start << "\n";
- if (aStatus == BED_INVALID) a->start = INT_MAX;
- if (bStatus == BED_INVALID) b->start = INT_MAX;
+ else if (a->chrom != b->chrom) {
+ // A was most recently read
+ if (_lastPick == 0) {
+ prevB = b;
+ while (b->chrom == prevA->chrom){
+ _windowB[prevA->chrom].push_back(b);
+ b = new BED();
+ bStatus = _bedB->GetNextBed(*b, bLineNum);
+ }
+ Scan(prevA, GetWindow(prevA->chrom, true), aStatus,
+ *prevB, GetWindow(prevA->chrom, false), bStatus);
+ }
+ // B was most recently read
+ else {
+ prevA = a;
+ while (a->chrom == prevB->chrom) {
+ _windowA[prevB->chrom].push_back(a);
+ a = new BED();
+ aStatus = _bedA->GetNextBed(*a, aLineNum);
+ }
+ Scan(prevB, GetWindow(prevB->chrom, false), bStatus,
+ *prevA, GetWindow(prevB->chrom, true), aStatus);
+ }
+ FlushOutputBuffer(true);
+ }
+ if (prevA!=NULL&&prevB!=NULL)
+ cout << prevA->chrom << " " << a->chrom << " " << a->start << " "
+ << prevB->chrom << " " << b->chrom << " " << b->start << "\n";
+ if (aStatus == BED_INVALID) a->start = INT_MAX;
+ if (bStatus == BED_INVALID) b->start = INT_MAX;
}
// clear out the final bit of staged output
FlushOutputBuffer(true);
-
+
// close the files
_bedA->Close();
_bedB->Close();
diff --git a/src/fjoin/fjoin.h b/src/fjoin/fjoin.h
index 5cc847040bac1222499b3e1b4b9a5646c0c5e61d..dd0a111bed3e188013bbb85442e880c5ae1c629e 100644
--- a/src/fjoin/fjoin.h
+++ b/src/fjoin/fjoin.h
@@ -33,82 +33,82 @@ class BedIntersect {
public:
- // constructor
- BedIntersect(string bedAFile, string bedBFile, bool anyHit,
- bool writeA, bool writeB, bool writeOverlap, bool writeAllOverlap,
- float overlapFraction, bool noHit, bool writeCount, bool forceStrand,
- bool reciprocal, bool obeySplits, bool bamInput, bool bamOutput);
-
- // destructor
- ~BedIntersect(void);
-
+ // constructor
+ BedIntersect(string bedAFile, string bedBFile, bool anyHit,
+ bool writeA, bool writeB, bool writeOverlap, bool writeAllOverlap,
+ float overlapFraction, bool noHit, bool writeCount, bool forceStrand,
+ bool reciprocal, bool obeySplits, bool bamInput, bool bamOutput);
+
+ // destructor
+ ~BedIntersect(void);
+
private:
-
- //------------------------------------------------
- // private attributes
- //------------------------------------------------
- string _bedAFile;
- string _bedBFile;
-
- bool _writeA; // should the original A feature be reported?
- bool _writeB; // should the original B feature be reported?
- bool _writeOverlap;
- bool _writeAllOverlap;
-
- bool _forceStrand;
- bool _reciprocal;
- float _overlapFraction;
-
- bool _anyHit;
- bool _noHit;
- bool _writeCount; // do we want a count of the number of overlaps in B?
+
+ //------------------------------------------------
+ // private attributes
+ //------------------------------------------------
+ string _bedAFile;
+ string _bedBFile;
+
+ bool _writeA; // should the original A feature be reported?
+ bool _writeB; // should the original B feature be reported?
+ bool _writeOverlap;
+ bool _writeAllOverlap;
+
+ bool _forceStrand;
+ bool _reciprocal;
+ float _overlapFraction;
+
+ bool _anyHit;
+ bool _noHit;
+ bool _writeCount; // do we want a count of the number of overlaps in B?
bool _obeySplits;
- bool _bamInput;
- bool _bamOutput;
-
+ bool _bamInput;
+ bool _bamOutput;
+
bool _printable;
-
+
queue<BED*> _outputBuffer;
bool _lastPick;
-
- map<string, vector<BED*> > _windowA;
- map<string, vector<BED*> > _windowB;
-
- // instance of a bed file class.
- BedFile *_bedA, *_bedB;
-
- //------------------------------------------------
- // private methods
- //------------------------------------------------
- void IntersectBed(istream &bedInput);
-
- void Scan(BED *x, vector<BED *> *windowX, BedLineStatus xStatus,
+
+ map<string, vector<BED*> > _windowA;
+ map<string, vector<BED*> > _windowB;
+
+ // instance of a bed file class.
+ BedFile *_bedA, *_bedB;
+
+ //------------------------------------------------
+ // private methods
+ //------------------------------------------------
+ void IntersectBed(istream &bedInput);
+
+ void Scan(BED *x, vector<BED *> *windowX, BedLineStatus xStatus,
const BED &y, vector<BED *> *windowY, BedLineStatus yStatus);
void AddHits(BED *x, const BED &y);
-
+
void FlushOutputBuffer(bool final = false);
-
- vector<BED*>* GetWindow(const string &chrom, bool isA);
-
- void ChromSwitch(const string &chrom);
-
- void IntersectBed();
-
- void IntersectBam(string bamFile);
-
+
+ vector<BED*>* GetWindow(const string &chrom, bool isA);
+
+ void ChromSwitch(const string &chrom);
+
+ void IntersectBed();
+
+ void IntersectBam(string bamFile);
+
bool processHits(BED &a, vector<BED> &hits);
-
- bool FindOverlaps(const BED &a, vector<BED> &hits);
-
- bool FindOneOrMoreOverlap(const BED &a);
-
- void ReportOverlapDetail(const int &overlapBases, const BED &a, const BED &b,
- const CHRPOS &s, const CHRPOS &e);
- void ReportOverlapSummary(const BED &a, const int &numOverlapsFound);
-
+
+ bool FindOverlaps(const BED &a, vector<BED> &hits);
+
+ bool FindOneOrMoreOverlap(const BED &a);
+
+ void ReportOverlapDetail(const int &overlapBases, const BED &a, const BED &b,
+ const CHRPOS &s, const CHRPOS &e);
+ void ReportOverlapSummary(const BED &a, const int &numOverlapsFound);
+
void ReportHits(set<BED> &A, set<BED> &B);
-
+
};
#endif /* INTERSECTBED_H */
diff --git a/src/fjoin/fjoinMain.cpp b/src/fjoin/fjoinMain.cpp
index 3d91a7caaea8e13659ee025ddef83713734efd5b..48a2ad982a1c6c6074ce53879beb1287cdfb2ef9 100644
--- a/src/fjoin/fjoinMain.cpp
+++ b/src/fjoin/fjoinMain.cpp
@@ -26,246 +26,246 @@ void ShowHelp(void);
int main(int argc, char* argv[]) {
- // our configuration variables
- bool showHelp = false;
-
- // input files
- string bedAFile;
- string bedBFile;
-
- // input arguments
- float overlapFraction = 1E-9;
-
- bool haveBedA = false;
- bool haveBedB = false;
- bool noHit = false;
- bool anyHit = false;
- bool writeA = false;
- bool writeB = false;
- bool writeCount = false;
- bool writeOverlap = false;
- bool writeAllOverlap = false;
- bool haveFraction = false;
- bool reciprocalFraction = false;
- bool forceStrand = false;
+ // our configuration variables
+ bool showHelp = false;
+
+ // input files
+ string bedAFile;
+ string bedBFile;
+
+ // input arguments
+ float overlapFraction = 1E-9;
+
+ bool haveBedA = false;
+ bool haveBedB = false;
+ bool noHit = false;
+ bool anyHit = false;
+ bool writeA = false;
+ bool writeB = false;
+ bool writeCount = false;
+ bool writeOverlap = false;
+ bool writeAllOverlap = false;
+ bool haveFraction = false;
+ bool reciprocalFraction = false;
+ bool forceStrand = false;
bool obeySplits = false;
- bool inputIsBam = false;
- bool outputIsBam = true;
-
- // check to see if we should print out some help
- if(argc <= 1) showHelp = true;
-
- for(int i = 1; i < argc; i++) {
- int parameterLength = (int)strlen(argv[i]);
-
- if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
- (PARAMETER_CHECK("--help", 5, parameterLength))) {
- showHelp = true;
- }
- }
-
- if(showHelp) ShowHelp();
-
- // do some parsing (all of these parameters require 2 strings)
- for(int i = 1; i < argc; i++) {
-
- int parameterLength = (int)strlen(argv[i]);
-
- if(PARAMETER_CHECK("-a", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveBedA = true;
- outputIsBam = false;
- bedAFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-abam", 5, parameterLength)) {
- if ((i+1) < argc) {
- haveBedA = true;
- inputIsBam = true;
- bedAFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-b", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveBedB = true;
- bedBFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-bed", 4, parameterLength)) {
- outputIsBam = false;
- }
- else if(PARAMETER_CHECK("-u", 2, parameterLength)) {
- anyHit = true;
- }
- else if(PARAMETER_CHECK("-f", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveFraction = true;
- overlapFraction = atof(argv[i + 1]);
- i++;
- }
- }
- else if(PARAMETER_CHECK("-wa", 3, parameterLength)) {
- writeA = true;
- }
- else if(PARAMETER_CHECK("-wb", 3, parameterLength)) {
- writeB = true;
- }
- else if(PARAMETER_CHECK("-wo", 3, parameterLength)) {
- writeOverlap = true;
- }
- else if(PARAMETER_CHECK("-wao", 4, parameterLength)) {
- writeAllOverlap = true;
- writeOverlap = true;
- }
- else if(PARAMETER_CHECK("-c", 2, parameterLength)) {
- writeCount = true;
- }
- else if(PARAMETER_CHECK("-r", 2, parameterLength)) {
- reciprocalFraction = true;
- }
- else if (PARAMETER_CHECK("-v", 2, parameterLength)) {
- noHit = true;
- }
- else if (PARAMETER_CHECK("-s", 2, parameterLength)) {
- forceStrand = true;
- }
- else if (PARAMETER_CHECK("-split", 6, parameterLength)) {
- obeySplits = true;
- }
- else {
- cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
- showHelp = true;
- }
- }
-
- // make sure we have both input files
- if (!haveBedA || !haveBedB) {
- cerr << endl << "*****" << endl << "*****ERROR: Need -a and -b files. " << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (anyHit && noHit) {
- cerr << endl << "*****" << endl << "*****ERROR: Request either -u OR -v, not both." << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (writeB && writeCount) {
- cerr << endl << "*****" << endl << "*****ERROR: Request either -wb OR -c, not both." << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (writeCount && writeOverlap) {
- cerr << endl << "*****" << endl << "*****ERROR: Request either -wb OR -wo, not both." << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (writeA && writeOverlap) {
- cerr << endl << "*****" << endl << "*****ERROR: Request either -wa OR -wo, not both." << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (writeB && writeOverlap) {
- cerr << endl << "*****" << endl << "*****ERROR: Request either -wb OR -wo, not both." << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (reciprocalFraction && !haveFraction) {
- cerr << endl << "*****" << endl << "*****ERROR: If using -r, you need to define -f." << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (anyHit && writeCount) {
- cerr << endl << "*****" << endl << "*****ERROR: Request either -u OR -c, not both." << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (anyHit && writeB) {
- cerr << endl << "*****" << endl << "*****ERROR: Request either -u OR -wb, not both." << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (anyHit && writeOverlap) {
- cerr << endl << "*****" << endl << "*****ERROR: Request either -u OR -wo, not both." << endl << "*****" << endl;
- showHelp = true;
- }
-
-
- if (!showHelp) {
-
- BedIntersect *bi = new BedIntersect(bedAFile, bedBFile, anyHit, writeA, writeB, writeOverlap,
- writeAllOverlap, overlapFraction, noHit, writeCount, forceStrand,
- reciprocalFraction, obeySplits, inputIsBam, outputIsBam);
- delete bi;
- return 0;
- }
- else {
- ShowHelp();
- }
+ bool inputIsBam = false;
+ bool outputIsBam = true;
+
+ // check to see if we should print out some help
+ if(argc <= 1) showHelp = true;
+
+ for(int i = 1; i < argc; i++) {
+ int parameterLength = (int)strlen(argv[i]);
+
+ if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
+ (PARAMETER_CHECK("--help", 5, parameterLength))) {
+ showHelp = true;
+ }
+ }
+
+ if(showHelp) ShowHelp();
+
+ // do some parsing (all of these parameters require 2 strings)
+ for(int i = 1; i < argc; i++) {
+
+ int parameterLength = (int)strlen(argv[i]);
+
+ if(PARAMETER_CHECK("-a", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveBedA = true;
+ outputIsBam = false;
+ bedAFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-abam", 5, parameterLength)) {
+ if ((i+1) < argc) {
+ haveBedA = true;
+ inputIsBam = true;
+ bedAFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-b", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveBedB = true;
+ bedBFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-bed", 4, parameterLength)) {
+ outputIsBam = false;
+ }
+ else if(PARAMETER_CHECK("-u", 2, parameterLength)) {
+ anyHit = true;
+ }
+ else if(PARAMETER_CHECK("-f", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveFraction = true;
+ overlapFraction = atof(argv[i + 1]);
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-wa", 3, parameterLength)) {
+ writeA = true;
+ }
+ else if(PARAMETER_CHECK("-wb", 3, parameterLength)) {
+ writeB = true;
+ }
+ else if(PARAMETER_CHECK("-wo", 3, parameterLength)) {
+ writeOverlap = true;
+ }
+ else if(PARAMETER_CHECK("-wao", 4, parameterLength)) {
+ writeAllOverlap = true;
+ writeOverlap = true;
+ }
+ else if(PARAMETER_CHECK("-c", 2, parameterLength)) {
+ writeCount = true;
+ }
+ else if(PARAMETER_CHECK("-r", 2, parameterLength)) {
+ reciprocalFraction = true;
+ }
+ else if (PARAMETER_CHECK("-v", 2, parameterLength)) {
+ noHit = true;
+ }
+ else if (PARAMETER_CHECK("-s", 2, parameterLength)) {
+ forceStrand = true;
+ }
+ else if (PARAMETER_CHECK("-split", 6, parameterLength)) {
+ obeySplits = true;
+ }
+ else {
+ cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
+ showHelp = true;
+ }
+ }
+
+ // make sure we have both input files
+ if (!haveBedA || !haveBedB) {
+ cerr << endl << "*****" << endl << "*****ERROR: Need -a and -b files. " << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (anyHit && noHit) {
+ cerr << endl << "*****" << endl << "*****ERROR: Request either -u OR -v, not both." << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (writeB && writeCount) {
+ cerr << endl << "*****" << endl << "*****ERROR: Request either -wb OR -c, not both." << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (writeCount && writeOverlap) {
+ cerr << endl << "*****" << endl << "*****ERROR: Request either -wb OR -wo, not both." << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (writeA && writeOverlap) {
+ cerr << endl << "*****" << endl << "*****ERROR: Request either -wa OR -wo, not both." << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (writeB && writeOverlap) {
+ cerr << endl << "*****" << endl << "*****ERROR: Request either -wb OR -wo, not both." << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (reciprocalFraction && !haveFraction) {
+ cerr << endl << "*****" << endl << "*****ERROR: If using -r, you need to define -f." << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (anyHit && writeCount) {
+ cerr << endl << "*****" << endl << "*****ERROR: Request either -u OR -c, not both." << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (anyHit && writeB) {
+ cerr << endl << "*****" << endl << "*****ERROR: Request either -u OR -wb, not both." << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (anyHit && writeOverlap) {
+ cerr << endl << "*****" << endl << "*****ERROR: Request either -u OR -wo, not both." << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+
+ if (!showHelp) {
+
+ BedIntersect *bi = new BedIntersect(bedAFile, bedBFile, anyHit, writeA, writeB, writeOverlap,
+ writeAllOverlap, overlapFraction, noHit, writeCount, forceStrand,
+ reciprocalFraction, obeySplits, inputIsBam, outputIsBam);
+ delete bi;
+ return 0;
+ }
+ else {
+ ShowHelp();
+ }
}
void ShowHelp(void) {
- cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
-
- cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
-
- cerr << "Summary: Report overlaps between two feature files." << endl << endl;
-
- cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -a <bed/gff/vcf> -b <bed/gff/vcf>" << endl << endl;
-
- cerr << "Options: " << endl;
-
- cerr << "\t-abam\t" << "The A input file is in BAM format. Output will be BAM as well." << endl << endl;
-
- cerr << "\t-bed\t" << "When using BAM input (-abam), write output as BED. The default" << endl;
- cerr << "\t\tis to write output in BAM when using -abam." << endl << endl;
-
- cerr << "\t-wa\t" << "Write the original entry in A for each overlap." << endl << endl;
-
- cerr << "\t-wb\t" << "Write the original entry in B for each overlap." << endl;
- cerr << "\t\t- Useful for knowing _what_ A overlaps. Restricted by -f and -r." << endl << endl;
-
- cerr << "\t-wo\t" << "Write the original A and B entries plus the number of base" << endl;
- cerr << "\t\tpairs of overlap between the two features." << endl;
- cerr << "\t\t- Overlaps restricted by -f and -r." << endl;
- cerr << "\t\t Only A features with overlap are reported." << endl << endl;
-
- cerr << "\t-wao\t" << "Write the original A and B entries plus the number of base" << endl;
- cerr << "\t\tpairs of overlap between the two features." << endl;
- cerr << "\t\t- Overlapping features restricted by -f and -r." << endl;
- cerr << "\t\t However, A features w/o overlap are also reported" << endl;
- cerr << "\t\t with a NULL B feature and overlap = 0." << endl << endl;
-
- cerr << "\t-u\t" << "Write the original A entry _once_ if _any_ overlaps found in B." << endl;
- cerr << "\t\t- In other words, just report the fact >=1 hit was found." << endl;
- cerr << "\t\t- Overlaps restricted by -f and -r." << endl << endl;
-
- cerr << "\t-c\t" << "For each entry in A, report the number of overlaps with B." << endl;
- cerr << "\t\t- Reports 0 for A entries that have no overlap with B." << endl;
- cerr << "\t\t- Overlaps restricted by -f and -r." << endl << endl;
-
- cerr << "\t-v\t" << "Only report those entries in A that have _no overlaps_ with B." << endl;
- cerr << "\t\t- Similar to \"grep -v\" (an homage)." << endl << endl;
-
- cerr << "\t-f\t" << "Minimum overlap required as a fraction of A." << endl;
- cerr << "\t\t- Default is 1E-9 (i.e., 1bp)." << endl;
- cerr << "\t\t- FLOAT (e.g. 0.50)" << endl << endl;
-
- cerr << "\t-r\t" << "Require that the fraction overlap be reciprocal for A and B." << endl;
- cerr << "\t\t- In other words, if -f is 0.90 and -r is used, this requires" << endl;
- cerr << "\t\t that B overlap 90% of A and A _also_ overlaps 90% of B." << endl << endl;
-
- cerr << "\t-s\t" << "Force strandedness. That is, only report hits in B that" << endl;
- cerr << "\t\toverlap A on the same strand." << endl;
- cerr << "\t\t- By default, overlaps are reported without respect to strand." << endl << endl;
-
- cerr << "\t-split\t" << "Treat \"split\" BAM or BED12 entries as distinct BED intervals." << endl << endl;
-
-
- // end the program here
- exit(1);
+ cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
+
+ cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
+
+ cerr << "Summary: Report overlaps between two feature files." << endl << endl;
+
+ cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -a <bed/gff/vcf> -b <bed/gff/vcf>" << endl << endl;
+
+ cerr << "Options: " << endl;
+
+ cerr << "\t-abam\t" << "The A input file is in BAM format. Output will be BAM as well." << endl << endl;
+
+ cerr << "\t-bed\t" << "When using BAM input (-abam), write output as BED. The default" << endl;
+ cerr << "\t\tis to write output in BAM when using -abam." << endl << endl;
+
+ cerr << "\t-wa\t" << "Write the original entry in A for each overlap." << endl << endl;
+
+ cerr << "\t-wb\t" << "Write the original entry in B for each overlap." << endl;
+ cerr << "\t\t- Useful for knowing _what_ A overlaps. Restricted by -f and -r." << endl << endl;
+
+ cerr << "\t-wo\t" << "Write the original A and B entries plus the number of base" << endl;
+ cerr << "\t\tpairs of overlap between the two features." << endl;
+ cerr << "\t\t- Overlaps restricted by -f and -r." << endl;
+ cerr << "\t\t Only A features with overlap are reported." << endl << endl;
+
+ cerr << "\t-wao\t" << "Write the original A and B entries plus the number of base" << endl;
+ cerr << "\t\tpairs of overlap between the two features." << endl;
+ cerr << "\t\t- Overlapping features restricted by -f and -r." << endl;
+ cerr << "\t\t However, A features w/o overlap are also reported" << endl;
+ cerr << "\t\t with a NULL B feature and overlap = 0." << endl << endl;
+
+ cerr << "\t-u\t" << "Write the original A entry _once_ if _any_ overlaps found in B." << endl;
+ cerr << "\t\t- In other words, just report the fact >=1 hit was found." << endl;
+ cerr << "\t\t- Overlaps restricted by -f and -r." << endl << endl;
+
+ cerr << "\t-c\t" << "For each entry in A, report the number of overlaps with B." << endl;
+ cerr << "\t\t- Reports 0 for A entries that have no overlap with B." << endl;
+ cerr << "\t\t- Overlaps restricted by -f and -r." << endl << endl;
+
+ cerr << "\t-v\t" << "Only report those entries in A that have _no overlaps_ with B." << endl;
+ cerr << "\t\t- Similar to \"grep -v\" (an homage)." << endl << endl;
+
+ cerr << "\t-f\t" << "Minimum overlap required as a fraction of A." << endl;
+ cerr << "\t\t- Default is 1E-9 (i.e., 1bp)." << endl;
+ cerr << "\t\t- FLOAT (e.g. 0.50)" << endl << endl;
+
+ cerr << "\t-r\t" << "Require that the fraction overlap be reciprocal for A and B." << endl;
+ cerr << "\t\t- In other words, if -f is 0.90 and -r is used, this requires" << endl;
+ cerr << "\t\t that B overlap 90% of A and A _also_ overlaps 90% of B." << endl << endl;
+
+ cerr << "\t-s\t" << "Force strandedness. That is, only report hits in B that" << endl;
+ cerr << "\t\toverlap A on the same strand." << endl;
+ cerr << "\t\t- By default, overlaps are reported without respect to strand." << endl << endl;
+
+ cerr << "\t-split\t" << "Treat \"split\" BAM or BED12 entries as distinct BED intervals." << endl << endl;
+
+
+ // end the program here
+ exit(1);
}
diff --git a/src/genomeCoverageBed/genomeCoverageBed.cpp b/src/genomeCoverageBed/genomeCoverageBed.cpp
index d841e4cb06c733a96d9e2835a690a740e35c7fbc..0bd4ff10c67cd26a47a8dbe6701cf51a4684ecd9 100644
--- a/src/genomeCoverageBed/genomeCoverageBed.cpp
+++ b/src/genomeCoverageBed/genomeCoverageBed.cpp
@@ -12,88 +12,88 @@
#include "lineFileUtilities.h"
#include "genomeCoverageBed.h"
-
-BedGenomeCoverage::BedGenomeCoverage(string bedFile, string genomeFile, bool eachBase,
- bool startSites, bool bedGraph, bool bedGraphAll,
- int max, bool bamInput, bool obeySplits,
- bool filterByStrand, string requestedStrand) {
-
- _bedFile = bedFile;
- _genomeFile = genomeFile;
- _eachBase = eachBase;
- _startSites = startSites;
- _bedGraph = bedGraph;
- _bedGraphAll = bedGraphAll;
- _max = max;
- _bamInput = bamInput;
- _obeySplits = obeySplits;
- _filterByStrand = filterByStrand;
- _requestedStrand = requestedStrand;
-
- _bed = new BedFile(bedFile);
- _genome = new GenomeFile(genomeFile);
-
- if (_bamInput == false)
- CoverageBed();
- else
- CoverageBam(_bed->bedFile);
+
+BedGenomeCoverage::BedGenomeCoverage(string bedFile, string genomeFile, bool eachBase,
+ bool startSites, bool bedGraph, bool bedGraphAll,
+ int max, bool bamInput, bool obeySplits,
+ bool filterByStrand, string requestedStrand) {
+
+ _bedFile = bedFile;
+ _genomeFile = genomeFile;
+ _eachBase = eachBase;
+ _startSites = startSites;
+ _bedGraph = bedGraph;
+ _bedGraphAll = bedGraphAll;
+ _max = max;
+ _bamInput = bamInput;
+ _obeySplits = obeySplits;
+ _filterByStrand = filterByStrand;
+ _requestedStrand = requestedStrand;
+
+ _bed = new BedFile(bedFile);
+ _genome = new GenomeFile(genomeFile);
+
+ if (_bamInput == false)
+ CoverageBed();
+ else
+ CoverageBam(_bed->bedFile);
}
BedGenomeCoverage::~BedGenomeCoverage(void) {
- delete _bed;
- delete _genome;
+ delete _bed;
+ delete _genome;
}
void BedGenomeCoverage::ResetChromCoverage() {
- _currChromName = "";
- _currChromSize = 0 ;
- std::vector<DEPTH>().swap(_currChromCoverage);
+ _currChromName = "";
+ _currChromSize = 0 ;
+ std::vector<DEPTH>().swap(_currChromCoverage);
}
void BedGenomeCoverage::StartNewChrom(const string& newChrom) {
- // If we've moved beyond the first encountered chromosomes,
- // process the results of the previous chromosome.
- if (_currChromName.length() > 0) {
- ReportChromCoverage(_currChromCoverage, _currChromSize,
- _currChromName, _currChromDepthHist);
- }
-
- // empty the previous chromosome and reserve new
- std::vector<DEPTH>().swap(_currChromCoverage);
-
- if (_visitedChromosomes.find(newChrom) != _visitedChromosomes.end()) {
- cerr << "Input error: Chromosome " << _currChromName
- << " found in non-sequential lines. This suggests that the input file is not sorted correctly." << endl;
-
- }
- _visitedChromosomes.insert(newChrom);
-
- _currChromName = newChrom;
-
- // get the current chrom size and allocate space
- _currChromSize = _genome->getChromSize(_currChromName);
-
- if (_currChromSize >= 0)
- _currChromCoverage.resize(_currChromSize);
- else {
- cerr << "Input error: Chromosome " << _currChromName << " found in your BED file but not in your genome file." << endl;
- exit(1);
- }
+ // If we've moved beyond the first encountered chromosomes,
+ // process the results of the previous chromosome.
+ if (_currChromName.length() > 0) {
+ ReportChromCoverage(_currChromCoverage, _currChromSize,
+ _currChromName, _currChromDepthHist);
+ }
+
+ // empty the previous chromosome and reserve new
+ std::vector<DEPTH>().swap(_currChromCoverage);
+
+ if (_visitedChromosomes.find(newChrom) != _visitedChromosomes.end()) {
+ cerr << "Input error: Chromosome " << _currChromName
+ << " found in non-sequential lines. This suggests that the input file is not sorted correctly." << endl;
+
+ }
+ _visitedChromosomes.insert(newChrom);
+
+ _currChromName = newChrom;
+
+ // get the current chrom size and allocate space
+ _currChromSize = _genome->getChromSize(_currChromName);
+
+ if (_currChromSize >= 0)
+ _currChromCoverage.resize(_currChromSize);
+ else {
+ cerr << "Input error: Chromosome " << _currChromName << " found in your BED file but not in your genome file." << endl;
+ exit(1);
+ }
}
void BedGenomeCoverage::AddCoverage(int start, int end) {
- // process the first line for this chromosome.
- // make sure the coordinates fit within the chrom
- if (start < _currChromSize)
- _currChromCoverage[start].starts++;
- if (end < _currChromSize)
- _currChromCoverage[end].ends++;
- else
- _currChromCoverage[_currChromSize-1].ends++;
+ // process the first line for this chromosome.
+ // make sure the coordinates fit within the chrom
+ if (start < _currChromSize)
+ _currChromCoverage[start].starts++;
+ if (end < _currChromSize)
+ _currChromCoverage[end].ends++;
+ else
+ _currChromCoverage[_currChromSize-1].ends++;
}
@@ -111,231 +111,231 @@ void BedGenomeCoverage::AddBlockedCoverage(const vector<BED> &bedBlocks) {
void BedGenomeCoverage::CoverageBed() {
- BED a, nullBed;
- int lineNum = 0; // current input line number
- BedLineStatus bedStatus;
-
- ResetChromCoverage();
-
- _bed->Open();
- while ( (bedStatus = _bed->GetNextBed(a, lineNum)) != BED_INVALID ) {
- if (bedStatus == BED_VALID) {
- if (_filterByStrand == true) {
- if (a.strand.empty()) {
- cerr << "Input error: Interval is missing a strand value on line " << lineNum << "." <<endl;
- exit(1);
- }
- if ( ! (a.strand == "-" || a.strand == "+") ) {
- cerr << "Input error: Invalid strand value (" << a.strand << ") on line " << lineNum << "." << endl;
- exit(1);
- }
- // skip if the strand is not what the user requested.
- if (a.strand != _requestedStrand)
- continue;
- }
+ BED a, nullBed;
+ int lineNum = 0; // current input line number
+ BedLineStatus bedStatus;
+
+ ResetChromCoverage();
+
+ _bed->Open();
+ while ( (bedStatus = _bed->GetNextBed(a, lineNum)) != BED_INVALID ) {
+ if (bedStatus == BED_VALID) {
+ if (_filterByStrand == true) {
+ if (a.strand.empty()) {
+ cerr << "Input error: Interval is missing a strand value on line " << lineNum << "." <<endl;
+ exit(1);
+ }
+ if ( ! (a.strand == "-" || a.strand == "+") ) {
+ cerr << "Input error: Invalid strand value (" << a.strand << ") on line " << lineNum << "." << endl;
+ exit(1);
+ }
+ // skip if the strand is not what the user requested.
+ if (a.strand != _requestedStrand)
+ continue;
+ }
// are we on a new chromosome?
- if (a.chrom != _currChromName)
- StartNewChrom(a.chrom);
+ if (a.chrom != _currChromName)
+ StartNewChrom(a.chrom);
- if (_obeySplits == true) {
- bedVector bedBlocks; // vec to store the discrete BED "blocks"
+ if (_obeySplits == true) {
+ bedVector bedBlocks; // vec to store the discrete BED "blocks"
splitBedIntoBlocks(a, lineNum, bedBlocks);
- AddBlockedCoverage(bedBlocks);
- }
- else
- AddCoverage(a.start, a.end-1);
- }
- }
- _bed->Close();
- PrintFinalCoverage();
+ AddBlockedCoverage(bedBlocks);
+ }
+ else
+ AddCoverage(a.start, a.end-1);
+ }
+ }
+ _bed->Close();
+ PrintFinalCoverage();
}
void BedGenomeCoverage::PrintFinalCoverage()
{
- // process the results of the last chromosome.
- ReportChromCoverage(_currChromCoverage, _currChromSize,
- _currChromName, _currChromDepthHist);
- if (_eachBase == false && _bedGraph == false && _bedGraphAll == false) {
- ReportGenomeCoverage(_currChromDepthHist);
- }
+ // process the results of the last chromosome.
+ ReportChromCoverage(_currChromCoverage, _currChromSize,
+ _currChromName, _currChromDepthHist);
+ if (_eachBase == false && _bedGraph == false && _bedGraphAll == false) {
+ ReportGenomeCoverage(_currChromDepthHist);
+ }
}
void BedGenomeCoverage::CoverageBam(string bamFile) {
ResetChromCoverage();
-
- // open the BAM file
- BamReader reader;
- reader.Open(bamFile);
-
- // get header & reference information
- string header = reader.GetHeaderText();
- RefVector refs = reader.GetReferenceData();
-
- // convert each aligned BAM entry to BED
- // and compute coverage on B
- BamAlignment bam;
- while (reader.GetNextAlignment(bam)) {
-
- // skip if the read is unaligned
- if (bam.IsMapped() == false)
+
+ // open the BAM file
+ BamReader reader;
+ reader.Open(bamFile);
+
+ // get header & reference information
+ string header = reader.GetHeaderText();
+ RefVector refs = reader.GetReferenceData();
+
+ // convert each aligned BAM entry to BED
+ // and compute coverage on B
+ BamAlignment bam;
+ while (reader.GetNextAlignment(bam)) {
+
+ // skip if the read is unaligned
+ if (bam.IsMapped() == false)
+ continue;
+
+ // skip if we care about strands and the strand isn't what
+ // the user wanted
+ if ( (_filterByStrand == true) &&
+ ((_requestedStrand == "-") != bam.IsReverseStrand()) )
continue;
-
- // skip if we care about strands and the strand isn't what
- // the user wanted
- if ( (_filterByStrand == true) &&
- ((_requestedStrand == "-") != bam.IsReverseStrand()) )
- continue;
-
- // extract the chrom, start and end from the BAM alignment
- string chrom(refs.at(bam.RefID).RefName);
+
+ // extract the chrom, start and end from the BAM alignment
+ string chrom(refs.at(bam.RefID).RefName);
CHRPOS start = bam.Position;
CHRPOS end = bam.GetEndPosition(false) - 1;
-
+
// are we on a new chromosome?
- if ( chrom != _currChromName )
- StartNewChrom(chrom);
+ if ( chrom != _currChromName )
+ StartNewChrom(chrom);
// add coverage accordingly.
- if (_obeySplits) {
- bedVector bedBlocks;
- // since we are counting coverage, we do want to split blocks when a
- // deletion (D) CIGAR op is encountered (hence the true for the last parm)
+ if (_obeySplits) {
+ bedVector bedBlocks;
+ // since we are counting coverage, we do want to split blocks when a
+ // deletion (D) CIGAR op is encountered (hence the true for the last parm)
getBamBlocks(bam, refs, bedBlocks, true);
AddBlockedCoverage(bedBlocks);
}
else
- AddCoverage(start, end);
- }
- // close the BAM
- reader.Close();
- PrintFinalCoverage();
+ AddCoverage(start, end);
+ }
+ // close the BAM
+ reader.Close();
+ PrintFinalCoverage();
}
void BedGenomeCoverage::ReportChromCoverage(const vector<DEPTH> &chromCov, const int &chromSize, const string &chrom, chromHistMap &chromDepthHist) {
-
- if (_eachBase) {
- int depth = 0; // initialize the depth
- for (int pos = 0; pos < chromSize; pos++) {
-
- depth += chromCov[pos].starts;
- // report the depth for this position.
- cout << chrom << "\t" << pos+1 << "\t" << depth << endl;
- depth = depth - chromCov[pos].ends;
- }
- }
- else if (_bedGraph == true || _bedGraphAll == true) {
- ReportChromCoverageBedGraph(chromCov, chromSize, chrom);
- }
- else {
-
- int depth = 0; // initialize the depth
-
- for (int pos = 0; pos < chromSize; pos++) {
-
- depth += chromCov[pos].starts;
-
- // add the depth at this position to the depth histogram
- // for this chromosome. if the depth is greater than the
- // maximum bin requested, then readjust the depth to be the max
- if (depth >= _max) {
- chromDepthHist[chrom][_max]++;
- }
- else {
- chromDepthHist[chrom][depth]++;
- }
- depth = depth - chromCov[pos].ends;
- }
- // report the histogram for each chromosome
- histMap::const_iterator depthIt = chromDepthHist[chrom].begin();
- histMap::const_iterator depthEnd = chromDepthHist[chrom].end();
- for (; depthIt != depthEnd; ++depthIt) {
- int depth = depthIt->first;
- unsigned int numBasesAtDepth = depthIt->second;
- cout << chrom << "\t" << depth << "\t" << numBasesAtDepth << "\t"
- << chromSize << "\t" << (float) ((float)numBasesAtDepth / (float)chromSize) << endl;
- }
- }
+
+ if (_eachBase) {
+ int depth = 0; // initialize the depth
+ for (int pos = 0; pos < chromSize; pos++) {
+
+ depth += chromCov[pos].starts;
+ // report the depth for this position.
+ cout << chrom << "\t" << pos+1 << "\t" << depth << endl;
+ depth = depth - chromCov[pos].ends;
+ }
+ }
+ else if (_bedGraph == true || _bedGraphAll == true) {
+ ReportChromCoverageBedGraph(chromCov, chromSize, chrom);
+ }
+ else {
+
+ int depth = 0; // initialize the depth
+
+ for (int pos = 0; pos < chromSize; pos++) {
+
+ depth += chromCov[pos].starts;
+
+ // add the depth at this position to the depth histogram
+ // for this chromosome. if the depth is greater than the
+ // maximum bin requested, then readjust the depth to be the max
+ if (depth >= _max) {
+ chromDepthHist[chrom][_max]++;
+ }
+ else {
+ chromDepthHist[chrom][depth]++;
+ }
+ depth = depth - chromCov[pos].ends;
+ }
+ // report the histogram for each chromosome
+ histMap::const_iterator depthIt = chromDepthHist[chrom].begin();
+ histMap::const_iterator depthEnd = chromDepthHist[chrom].end();
+ for (; depthIt != depthEnd; ++depthIt) {
+ int depth = depthIt->first;
+ unsigned int numBasesAtDepth = depthIt->second;
+ cout << chrom << "\t" << depth << "\t" << numBasesAtDepth << "\t"
+ << chromSize << "\t" << (float) ((float)numBasesAtDepth / (float)chromSize) << endl;
+ }
+ }
}
void BedGenomeCoverage::ReportGenomeCoverage(chromHistMap &chromDepthHist) {
-
- // get the list of chromosome names in the genome
- vector<string> chromList = _genome->getChromList();
-
- unsigned int genomeSize = 0;
- vector<string>::const_iterator chromItr = chromList.begin();
- vector<string>::const_iterator chromEnd = chromList.end();
- for (; chromItr != chromEnd; ++chromItr) {
- string chrom = *chromItr;
- genomeSize += _genome->getChromSize(chrom);
- // if there were no reads for a give chromosome, then
- // add the length of the chrom to the 0 bin.
- if ( chromDepthHist.find(chrom) == chromDepthHist.end() ) {
- chromDepthHist[chrom][0] += _genome->getChromSize(chrom);
- }
- }
-
- histMap genomeHist; // depth histogram for the entire genome
-
- // loop through each chromosome and add the depth and number of bases at each depth
- // to the aggregate histogram for the entire genome
- for (chromHistMap::iterator chromIt = chromDepthHist.begin(); chromIt != chromDepthHist.end(); ++chromIt) {
- string chrom = chromIt->first;
- for (histMap::iterator depthIt = chromDepthHist[chrom].begin(); depthIt != chromDepthHist[chrom].end(); ++depthIt) {
- int depth = depthIt->first;
- unsigned int numBasesAtDepth = depthIt->second;
- genomeHist[depth] += numBasesAtDepth;
- }
- }
-
- // loop through the depths for the entire genome
- // and report the number and fraction of bases in
- // the entire genome that are at said depth.
- for (histMap::iterator genomeDepthIt = genomeHist.begin(); genomeDepthIt != genomeHist.end(); ++genomeDepthIt) {
- int depth = genomeDepthIt->first;
- unsigned int numBasesAtDepth = genomeDepthIt->second;
-
- cout << "genome" << "\t" << depth << "\t" << numBasesAtDepth << "\t"
- << genomeSize << "\t" << (float) ((float)numBasesAtDepth / (float)genomeSize) << endl;
- }
+
+ // get the list of chromosome names in the genome
+ vector<string> chromList = _genome->getChromList();
+
+ unsigned int genomeSize = 0;
+ vector<string>::const_iterator chromItr = chromList.begin();
+ vector<string>::const_iterator chromEnd = chromList.end();
+ for (; chromItr != chromEnd; ++chromItr) {
+ string chrom = *chromItr;
+ genomeSize += _genome->getChromSize(chrom);
+ // if there were no reads for a give chromosome, then
+ // add the length of the chrom to the 0 bin.
+ if ( chromDepthHist.find(chrom) == chromDepthHist.end() ) {
+ chromDepthHist[chrom][0] += _genome->getChromSize(chrom);
+ }
+ }
+
+ histMap genomeHist; // depth histogram for the entire genome
+
+ // loop through each chromosome and add the depth and number of bases at each depth
+ // to the aggregate histogram for the entire genome
+ for (chromHistMap::iterator chromIt = chromDepthHist.begin(); chromIt != chromDepthHist.end(); ++chromIt) {
+ string chrom = chromIt->first;
+ for (histMap::iterator depthIt = chromDepthHist[chrom].begin(); depthIt != chromDepthHist[chrom].end(); ++depthIt) {
+ int depth = depthIt->first;
+ unsigned int numBasesAtDepth = depthIt->second;
+ genomeHist[depth] += numBasesAtDepth;
+ }
+ }
+
+ // loop through the depths for the entire genome
+ // and report the number and fraction of bases in
+ // the entire genome that are at said depth.
+ for (histMap::iterator genomeDepthIt = genomeHist.begin(); genomeDepthIt != genomeHist.end(); ++genomeDepthIt) {
+ int depth = genomeDepthIt->first;
+ unsigned int numBasesAtDepth = genomeDepthIt->second;
+
+ cout << "genome" << "\t" << depth << "\t" << numBasesAtDepth << "\t"
+ << genomeSize << "\t" << (float) ((float)numBasesAtDepth / (float)genomeSize) << endl;
+ }
}
void BedGenomeCoverage::ReportChromCoverageBedGraph(const vector<DEPTH> &chromCov, const int &chromSize, const string &chrom) {
- int depth = 0; // initialize the depth
- int lastStart = -1;
- int lastDepth = -1;
-
- for (int pos = 0; pos < chromSize; pos++) {
- depth += chromCov[pos].starts;
-
- if (depth != lastDepth) {
- // Coverage depth has changed, print the last interval coverage (if any)
- // Print if:
- // (1) depth>0 (the default running mode),
- // (2) depth==0 and the user requested to print zero covered regions (_bedGraphAll)
- if ( (lastDepth != -1) && (lastDepth > 0 || _bedGraphAll) ) {
- cout << chrom << "\t" << lastStart << "\t" << pos << "\t" << lastDepth << endl;
- }
- //Set current position as the new interval start + depth
- lastDepth = depth;
- lastStart = pos;
- }
- // Default: the depth has not changed, so we will not print anything.
- // Proceed until the depth changes.
- // Update depth
- depth = depth - chromCov[pos].ends;
- }
- //Print information about the last position
- if ( (lastDepth != -1) && (lastDepth > 0 || _bedGraphAll) ) {
- cout << chrom << "\t" << lastStart << "\t" << chromSize << "\t" << lastDepth << endl;
- }
+ int depth = 0; // initialize the depth
+ int lastStart = -1;
+ int lastDepth = -1;
+
+ for (int pos = 0; pos < chromSize; pos++) {
+ depth += chromCov[pos].starts;
+
+ if (depth != lastDepth) {
+ // Coverage depth has changed, print the last interval coverage (if any)
+ // Print if:
+ // (1) depth>0 (the default running mode),
+ // (2) depth==0 and the user requested to print zero covered regions (_bedGraphAll)
+ if ( (lastDepth != -1) && (lastDepth > 0 || _bedGraphAll) ) {
+ cout << chrom << "\t" << lastStart << "\t" << pos << "\t" << lastDepth << endl;
+ }
+ //Set current position as the new interval start + depth
+ lastDepth = depth;
+ lastStart = pos;
+ }
+ // Default: the depth has not changed, so we will not print anything.
+ // Proceed until the depth changes.
+ // Update depth
+ depth = depth - chromCov[pos].ends;
+ }
+ //Print information about the last position
+ if ( (lastDepth != -1) && (lastDepth > 0 || _bedGraphAll) ) {
+ cout << chrom << "\t" << lastStart << "\t" << chromSize << "\t" << lastDepth << endl;
+ }
}
diff --git a/src/genomeCoverageBed/genomeCoverageBed.h b/src/genomeCoverageBed/genomeCoverageBed.h
index bcf286cb4e6f2972c3383810801bffa648e228a3..7422e2b320cd22ba40250d4825dc5fc7fa689e40 100644
--- a/src/genomeCoverageBed/genomeCoverageBed.h
+++ b/src/genomeCoverageBed/genomeCoverageBed.h
@@ -40,50 +40,50 @@ class BedGenomeCoverage {
public:
- // constructor
- BedGenomeCoverage(string bedFile, string genomeFile, bool eachBase, bool startSites,
- bool bedGraph, bool bedGraphAll, int max, bool bamInput, bool obeySplits,
+ // constructor
+ BedGenomeCoverage(string bedFile, string genomeFile, bool eachBase, bool startSites,
+ bool bedGraph, bool bedGraphAll, int max, bool bamInput, bool obeySplits,
bool filterByStrand, string requestedStrand);
- // destructor
- ~BedGenomeCoverage(void);
+ // destructor
+ ~BedGenomeCoverage(void);
private:
- // data (parms)
- string _bedFile;
- string _genomeFile;
- bool _bamInput;
- bool _eachBase;
- bool _startSites;
- bool _bedGraph;
- bool _bedGraphAll;
- int _max;
+ // data (parms)
+ string _bedFile;
+ string _genomeFile;
+ bool _bamInput;
+ bool _eachBase;
+ bool _startSites;
+ bool _bedGraph;
+ bool _bedGraphAll;
+ int _max;
bool _obeySplits;
- bool _filterByStrand;
- string _requestedStrand;
-
- BedFile *_bed;
- GenomeFile *_genome;
+ bool _filterByStrand;
+ string _requestedStrand;
+
+ BedFile *_bed;
+ GenomeFile *_genome;
// data for internal processing
- chromDepthMap _chromCov;
- string _currChromName ;
- vector<DEPTH> _currChromCoverage;
- chromHistMap _currChromDepthHist;
- int _currChromSize ;
- set<string> _visitedChromosomes;
-
-
- // methods
- void CoverageBed();
- void CoverageBam(string bamFile);
- void ReportChromCoverage(const vector<DEPTH> &, const int &chromSize, const string &chrom, chromHistMap&);
- void ReportGenomeCoverage(chromHistMap &chromDepthHist);
- void ReportChromCoverageBedGraph(const vector<DEPTH> &chromCov, const int &chromSize, const string &chrom);
- void ResetChromCoverage();
- void StartNewChrom (const string& chrom);
- void AddCoverage (int start, int end);
+ chromDepthMap _chromCov;
+ string _currChromName ;
+ vector<DEPTH> _currChromCoverage;
+ chromHistMap _currChromDepthHist;
+ int _currChromSize ;
+ set<string> _visitedChromosomes;
+
+
+ // methods
+ void CoverageBed();
+ void CoverageBam(string bamFile);
+ void ReportChromCoverage(const vector<DEPTH> &, const int &chromSize, const string &chrom, chromHistMap&);
+ void ReportGenomeCoverage(chromHistMap &chromDepthHist);
+ void ReportChromCoverageBedGraph(const vector<DEPTH> &chromCov, const int &chromSize, const string &chrom);
+ void ResetChromCoverage();
+ void StartNewChrom (const string& chrom);
+ void AddCoverage (int start, int end);
void AddBlockedCoverage(const vector<BED> &bedBlocks);
- void PrintFinalCoverage();
+ void PrintFinalCoverage();
};
diff --git a/src/genomeCoverageBed/genomeCoverageMain.cpp b/src/genomeCoverageBed/genomeCoverageMain.cpp
index 27d426858cf89083c53730755bdc152527e3d692..a652d9360d7b23baa069d86f784934cf334cfb91 100644
--- a/src/genomeCoverageBed/genomeCoverageMain.cpp
+++ b/src/genomeCoverageBed/genomeCoverageMain.cpp
@@ -26,201 +26,201 @@ void ShowHelp(void);
int main(int argc, char* argv[]) {
- // our configuration variables
- bool showHelp = false;
-
- // input files
- string bedFile;
- string genomeFile;
- int max = INT_MAX;
-
- bool haveBed = false;
- bool bamInput = false;
- bool haveGenome = false;
- bool startSites = false;
- bool bedGraph = false;
- bool bedGraphAll = false;
- bool eachBase = false;
- bool obeySplits = false;
- bool filterByStrand = false;
- string requestedStrand = "X";
-
- // check to see if we should print out some help
- if(argc <= 1) showHelp = true;
-
- for(int i = 1; i < argc; i++) {
- int parameterLength = (int)strlen(argv[i]);
-
- if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
- (PARAMETER_CHECK("--help", 5, parameterLength))) {
- showHelp = true;
- }
- }
-
- if(showHelp) ShowHelp();
-
- // do some parsing (all of these parameters require 2 strings)
- for(int i = 1; i < argc; i++) {
-
- int parameterLength = (int)strlen(argv[i]);
-
- if(PARAMETER_CHECK("-i", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveBed = true;
- bedFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-ibam", 5, parameterLength)) {
- if ((i+1) < argc) {
- haveBed = true;
- bamInput = true;
- bedFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-g", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveGenome = true;
- genomeFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-d", 2, parameterLength)) {
- eachBase = true;
- }
- else if(PARAMETER_CHECK("-bg", 3, parameterLength)) {
- bedGraph = true;
- }
- else if(PARAMETER_CHECK("-bga", 4, parameterLength)) {
- bedGraphAll = true;
- }
- else if(PARAMETER_CHECK("-max", 4, parameterLength)) {
- if ((i+1) < argc) {
- max = atoi(argv[i + 1]);
- i++;
- }
- }
- else if(PARAMETER_CHECK("-split", 6, parameterLength)) {
- obeySplits = true;
- }
- else if(PARAMETER_CHECK("-strand", 7, parameterLength)) {
- if ((i+1) < argc) {
- filterByStrand = true;
- requestedStrand = argv[i+1][0];
- if (!(requestedStrand == "-" || requestedStrand == "+")) {
- cerr << "*****ERROR: invalid -strand value (" << requestedStrand << "). Allowed options are + or -" << endl;
- showHelp = true;
- }
- i++;
- }
- else {
- cerr << "*****ERROR: -strand options requires a value: + or -" << endl;
- showHelp = true;
- }
- }
- else {
- cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
- showHelp = true;
- }
- }
-
- // make sure we have both input files
- if (!haveBed || !haveGenome) {
- cerr << endl << "*****" << endl << "*****ERROR: Need both a BED (-i) and a genome (-g) file. " << endl << "*****" << endl;
- showHelp = true;
- }
- if (bedGraph && eachBase) {
- cerr << endl << "*****" << endl << "*****ERROR: Use -d or -bg, not both" << endl << "*****" << endl;
- showHelp = true;
- }
- if (bedGraphAll && eachBase) {
- cerr << endl << "*****" << endl << "*****ERROR: Use -d or -bga, not both" << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (!showHelp) {
-
- BedGenomeCoverage *bc = new BedGenomeCoverage(bedFile, genomeFile, eachBase,
- startSites, bedGraph, bedGraphAll,
+ // our configuration variables
+ bool showHelp = false;
+
+ // input files
+ string bedFile;
+ string genomeFile;
+ int max = INT_MAX;
+
+ bool haveBed = false;
+ bool bamInput = false;
+ bool haveGenome = false;
+ bool startSites = false;
+ bool bedGraph = false;
+ bool bedGraphAll = false;
+ bool eachBase = false;
+ bool obeySplits = false;
+ bool filterByStrand = false;
+ string requestedStrand = "X";
+
+ // check to see if we should print out some help
+ if(argc <= 1) showHelp = true;
+
+ for(int i = 1; i < argc; i++) {
+ int parameterLength = (int)strlen(argv[i]);
+
+ if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
+ (PARAMETER_CHECK("--help", 5, parameterLength))) {
+ showHelp = true;
+ }
+ }
+
+ if(showHelp) ShowHelp();
+
+ // do some parsing (all of these parameters require 2 strings)
+ for(int i = 1; i < argc; i++) {
+
+ int parameterLength = (int)strlen(argv[i]);
+
+ if(PARAMETER_CHECK("-i", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveBed = true;
+ bedFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-ibam", 5, parameterLength)) {
+ if ((i+1) < argc) {
+ haveBed = true;
+ bamInput = true;
+ bedFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-g", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveGenome = true;
+ genomeFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-d", 2, parameterLength)) {
+ eachBase = true;
+ }
+ else if(PARAMETER_CHECK("-bg", 3, parameterLength)) {
+ bedGraph = true;
+ }
+ else if(PARAMETER_CHECK("-bga", 4, parameterLength)) {
+ bedGraphAll = true;
+ }
+ else if(PARAMETER_CHECK("-max", 4, parameterLength)) {
+ if ((i+1) < argc) {
+ max = atoi(argv[i + 1]);
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-split", 6, parameterLength)) {
+ obeySplits = true;
+ }
+ else if(PARAMETER_CHECK("-strand", 7, parameterLength)) {
+ if ((i+1) < argc) {
+ filterByStrand = true;
+ requestedStrand = argv[i+1][0];
+ if (!(requestedStrand == "-" || requestedStrand == "+")) {
+ cerr << "*****ERROR: invalid -strand value (" << requestedStrand << "). Allowed options are + or -" << endl;
+ showHelp = true;
+ }
+ i++;
+ }
+ else {
+ cerr << "*****ERROR: -strand options requires a value: + or -" << endl;
+ showHelp = true;
+ }
+ }
+ else {
+ cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
+ showHelp = true;
+ }
+ }
+
+ // make sure we have both input files
+ if (!haveBed || !haveGenome) {
+ cerr << endl << "*****" << endl << "*****ERROR: Need both a BED (-i) and a genome (-g) file. " << endl << "*****" << endl;
+ showHelp = true;
+ }
+ if (bedGraph && eachBase) {
+ cerr << endl << "*****" << endl << "*****ERROR: Use -d or -bg, not both" << endl << "*****" << endl;
+ showHelp = true;
+ }
+ if (bedGraphAll && eachBase) {
+ cerr << endl << "*****" << endl << "*****ERROR: Use -d or -bga, not both" << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (!showHelp) {
+
+ BedGenomeCoverage *bc = new BedGenomeCoverage(bedFile, genomeFile, eachBase,
+ startSites, bedGraph, bedGraphAll,
max, bamInput, obeySplits,
- filterByStrand, requestedStrand);
- delete bc;
-
- return 0;
- }
- else {
- ShowHelp();
- }
+ filterByStrand, requestedStrand);
+ delete bc;
+
+ return 0;
+ }
+ else {
+ ShowHelp();
+ }
}
void ShowHelp(void) {
-
- cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
-
- cerr << "Authors: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
- cerr << " Assaf Gordon, CSHL" << endl << endl;
-
- cerr << "Summary: Compute the coverage of a feature file among a genome." << endl << endl;
-
- cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -i <bed/gff/vcf> -g <genome>" << endl << endl;
-
- cerr << "Options: " << endl;
-
- cerr << "\t-ibam\t" << "The input file is in BAM format." << endl;
- cerr << "\t\tNote: BAM _must_ be sorted by position" << endl << endl;
-
- cerr << "\t-d\t" << "Report the depth at each genome position." << endl;
- cerr << "\t\tDefault behavior is to report a histogram." << endl << endl;
-
- cerr << "\t-bg\t" << "Report depth in BedGraph format. For details, see:" << endl;
- cerr << "\t\tgenome.ucsc.edu/goldenPath/help/bedgraph.html" << endl << endl;
-
- cerr << "\t-bga\t" << "Report depth in BedGraph format, as above (-bg)." << endl;
- cerr << "\t\tHowever with this option, regions with zero " << endl;
- cerr << "\t\tcoverage are also reported. This allows one to" << endl;
- cerr << "\t\tquickly extract all regions of a genome with 0 " << endl;
- cerr << "\t\tcoverage by applying: \"grep -w 0$\" to the output." << endl << endl;
-
- cerr << "\t-split\t" << "Treat \"split\" BAM or BED12 entries as distinct BED intervals." << endl;
- cerr << "\t\twhen computing coverage." << endl;
- cerr << "\t\tFor BAM files, this uses the CIGAR \"N\" and \"D\" operations " << endl;
- cerr << "\t\tto infer the blocks for computing coverage." << endl;
- cerr << "\t\tFor BED12 files, this uses the BlockCount, BlockStarts, and BlockEnds" << endl;
- cerr << "\t\tfields (i.e., columns 10,11,12)." << endl << endl;
-
- cerr << "\t-strand\t" << "Calculate coverage of intervals from a specific strand." << endl;
- cerr << "\t\tWith BED files, requires at least 6 columns (strand is column 6). " << endl;
- cerr << "\t\t- (STRING): can be + or -" << endl << endl;
-
-
- cerr << "\t-max\t" << "Combine all positions with a depth >= max into" << endl;
- cerr << "\t\ta single bin in the histogram. Irrelevant" << endl;
- cerr << "\t\tfor -d and -bedGraph" << endl;
- cerr << "\t\t- (INTEGER)" << endl << endl;
-
- cerr << "Notes: " << endl;
- cerr << "\t(1) The genome file should tab delimited and structured as follows:" << endl;
- cerr << "\t <chromName><TAB><chromSize>" << endl << endl;
- cerr << "\tFor example, Human (hg19):" << endl;
- cerr << "\tchr1\t249250621" << endl;
- cerr << "\tchr2\t243199373" << endl;
- cerr << "\t..." << endl;
- cerr << "\tchr18_gl000207_random\t4262" << endl << endl;
-
- cerr << "\t(2) The input BED (-i) file must be grouped by chromosome." << endl;
- cerr << "\t A simple \"sort -k 1,1 <BED> > <BED>.sorted\" will suffice."<< endl << endl;
-
- cerr << "\t(3) The input BAM (-ibam) file must be sorted by position." << endl;
- cerr << "\t A \"samtools sort <BAM>\" should suffice."<< endl << endl;
-
- cerr << "Tips: " << endl;
- cerr << "\tOne can use the UCSC Genome Browser's MySQL database to extract" << endl;
- cerr << "\tchromosome sizes. For example, H. sapiens:" << endl << endl;
- cerr << "\tmysql --user=genome --host=genome-mysql.cse.ucsc.edu -A -e /" << endl;
- cerr << "\t\"select chrom, size from hg19.chromInfo\" > hg19.genome" << endl << endl;
-
-
- // end the program here
- exit(1);
+
+ cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
+
+ cerr << "Authors: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
+ cerr << " Assaf Gordon, CSHL" << endl << endl;
+
+ cerr << "Summary: Compute the coverage of a feature file among a genome." << endl << endl;
+
+ cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -i <bed/gff/vcf> -g <genome>" << endl << endl;
+
+ cerr << "Options: " << endl;
+
+ cerr << "\t-ibam\t" << "The input file is in BAM format." << endl;
+ cerr << "\t\tNote: BAM _must_ be sorted by position" << endl << endl;
+
+ cerr << "\t-d\t" << "Report the depth at each genome position." << endl;
+ cerr << "\t\tDefault behavior is to report a histogram." << endl << endl;
+
+ cerr << "\t-bg\t" << "Report depth in BedGraph format. For details, see:" << endl;
+ cerr << "\t\tgenome.ucsc.edu/goldenPath/help/bedgraph.html" << endl << endl;
+
+ cerr << "\t-bga\t" << "Report depth in BedGraph format, as above (-bg)." << endl;
+ cerr << "\t\tHowever with this option, regions with zero " << endl;
+ cerr << "\t\tcoverage are also reported. This allows one to" << endl;
+ cerr << "\t\tquickly extract all regions of a genome with 0 " << endl;
+ cerr << "\t\tcoverage by applying: \"grep -w 0$\" to the output." << endl << endl;
+
+ cerr << "\t-split\t" << "Treat \"split\" BAM or BED12 entries as distinct BED intervals." << endl;
+ cerr << "\t\twhen computing coverage." << endl;
+ cerr << "\t\tFor BAM files, this uses the CIGAR \"N\" and \"D\" operations " << endl;
+ cerr << "\t\tto infer the blocks for computing coverage." << endl;
+ cerr << "\t\tFor BED12 files, this uses the BlockCount, BlockStarts, and BlockEnds" << endl;
+ cerr << "\t\tfields (i.e., columns 10,11,12)." << endl << endl;
+
+ cerr << "\t-strand\t" << "Calculate coverage of intervals from a specific strand." << endl;
+ cerr << "\t\tWith BED files, requires at least 6 columns (strand is column 6). " << endl;
+ cerr << "\t\t- (STRING): can be + or -" << endl << endl;
+
+
+ cerr << "\t-max\t" << "Combine all positions with a depth >= max into" << endl;
+ cerr << "\t\ta single bin in the histogram. Irrelevant" << endl;
+ cerr << "\t\tfor -d and -bedGraph" << endl;
+ cerr << "\t\t- (INTEGER)" << endl << endl;
+
+ cerr << "Notes: " << endl;
+ cerr << "\t(1) The genome file should tab delimited and structured as follows:" << endl;
+ cerr << "\t <chromName><TAB><chromSize>" << endl << endl;
+ cerr << "\tFor example, Human (hg19):" << endl;
+ cerr << "\tchr1\t249250621" << endl;
+ cerr << "\tchr2\t243199373" << endl;
+ cerr << "\t..." << endl;
+ cerr << "\tchr18_gl000207_random\t4262" << endl << endl;
+
+ cerr << "\t(2) The input BED (-i) file must be grouped by chromosome." << endl;
+ cerr << "\t A simple \"sort -k 1,1 <BED> > <BED>.sorted\" will suffice."<< endl << endl;
+
+ cerr << "\t(3) The input BAM (-ibam) file must be sorted by position." << endl;
+ cerr << "\t A \"samtools sort <BAM>\" should suffice."<< endl << endl;
+
+ cerr << "Tips: " << endl;
+ cerr << "\tOne can use the UCSC Genome Browser's MySQL database to extract" << endl;
+ cerr << "\tchromosome sizes. For example, H. sapiens:" << endl << endl;
+ cerr << "\tmysql --user=genome --host=genome-mysql.cse.ucsc.edu -A -e /" << endl;
+ cerr << "\t\"select chrom, size from hg19.chromInfo\" > hg19.genome" << endl << endl;
+
+
+ // end the program here
+ exit(1);
}
diff --git a/src/groupBy/groupBy.cpp b/src/groupBy/groupBy.cpp
index a7d4969aa69eab9f7662e06a8ff767a9764e3ea4..c49038b119af238dca39db862a96f9ea166297ca 100644
--- a/src/groupBy/groupBy.cpp
+++ b/src/groupBy/groupBy.cpp
@@ -68,7 +68,7 @@ double ToDouble(const string &element);
void TabPrintPost (string element);
void TabPrintPre (string element);
void CommaPrint (string element);
-
+
int main(int argc, char* argv[]) {
// input files
@@ -76,19 +76,19 @@ int main(int argc, char* argv[]) {
string groupColumnsString = "1,2,3";
string opsColumnString;
string opsString;
-
+
// our configuration variables
bool showHelp = false;
- bool haveOpColumns = false;
- bool haveOps = true;
-
+ bool haveOpColumns = false;
+ bool haveOps = true;
+
// check to see if we should print out some help
if(argc <= 1) showHelp = true;
for(int i = 1; i < argc; i++) {
int parameterLength = (int)strlen(argv[i]);
- if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
+ if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
(PARAMETER_CHECK("--help", 5, parameterLength))) {
showHelp = true;
}
@@ -106,51 +106,51 @@ int main(int argc, char* argv[]) {
cerr << endl << "*****ERROR: -i parameter requires a value." << endl << endl;
ShowHelp();
break;
- }
+ }
else {
- inFile = argv[i + 1];
- i++;
+ inFile = argv[i + 1];
+ i++;
}
}
else if (PARAMETER_CHECK("-grp", 4, parameterLength) || PARAMETER_CHECK("-g", 2, parameterLength)) {
- if ((i+1) >= argc || LOOKS_LIKE_A_PARAM(argv[i+1])) {
- cerr << endl << "*****ERROR: -grp parameter requires a value." << endl << endl;
+ if ((i+1) >= argc || LOOKS_LIKE_A_PARAM(argv[i+1])) {
+ cerr << endl << "*****ERROR: -grp parameter requires a value." << endl << endl;
ShowHelp();
- break;
- }
- else {
- groupColumnsString = argv[i + 1];
- i++;
- }
+ break;
+ }
+ else {
+ groupColumnsString = argv[i + 1];
+ i++;
+ }
}
else if(PARAMETER_CHECK("-opCols", 7, parameterLength) || PARAMETER_CHECK("-c", 2, parameterLength)) {
- if ((i+1) >= argc || LOOKS_LIKE_A_PARAM(argv[i+1])) {
- cerr << endl << "*****ERROR: -opCols parameter requires a value." << endl << endl;
+ if ((i+1) >= argc || LOOKS_LIKE_A_PARAM(argv[i+1])) {
+ cerr << endl << "*****ERROR: -opCols parameter requires a value." << endl << endl;
ShowHelp();
- break;
- }
- else {
- haveOpColumns = true;
- opsColumnString = argv[i + 1];
- i++;
- }
+ break;
+ }
+ else {
+ haveOpColumns = true;
+ opsColumnString = argv[i + 1];
+ i++;
+ }
}
else if(PARAMETER_CHECK("-ops", 4, parameterLength) || PARAMETER_CHECK("-o", 2, parameterLength)) {
- if ((i+1) >= argc || LOOKS_LIKE_A_PARAM(argv[i+1])) {
- cerr << endl << "*****ERROR: -ops parameter requires a value." << endl << endl;
+ if ((i+1) >= argc || LOOKS_LIKE_A_PARAM(argv[i+1])) {
+ cerr << endl << "*****ERROR: -ops parameter requires a value." << endl << endl;
ShowHelp();
break;
- }
- else {
- haveOps = true;
- opsString = argv[i + 1];
- i++;
- }
+ }
+ else {
+ haveOps = true;
+ opsString = argv[i + 1];
+ i++;
+ }
}
else {
cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
showHelp = true;
- }
+ }
}
if (!haveOpColumns) {
@@ -165,45 +165,45 @@ int main(int argc, char* argv[]) {
(ops[i] != "mode") && (ops[i] != "median") && (ops[i] != "antimode") && (ops[i] != "stdev") &&
(ops[i] != "sstdev") && (ops[i] != "count") && (ops[i] != "collapse") && (ops[i] != "freqdesc") &&
(ops[i] != "freqasc")) {
- cerr << endl << "*****" << endl << "*****ERROR: Invalid operation selection \"" << ops[i] << endl << "*****" << endl;
- showHelp = true;
+ cerr << endl << "*****" << endl << "*****ERROR: Invalid operation selection \"" << ops[i] << endl << "*****" << endl;
+ showHelp = true;
}
}
if (!showHelp) {
-
+
// Split the column string sent by the user into discrete column numbers
// A comma separated string is expected.
vector<int> groupColumnsInt;
Tokenize(groupColumnsString, groupColumnsInt, ",");
-
+
vector<int> opColumnsInt;
Tokenize(opsColumnString, opColumnsInt, ",");
-
- // sanity check the group columns
+
+ // sanity check the group columns
for(size_t i = 0; i < groupColumnsInt.size(); ++i) {
int groupColumnInt = groupColumnsInt[i];
if (groupColumnInt < 1) {
- cerr << endl << "*****" << endl << "*****ERROR: group columns must be >=1. " << endl << "*****" << endl;
- ShowHelp();
+ cerr << endl << "*****" << endl << "*****ERROR: group columns must be >=1. " << endl << "*****" << endl;
+ ShowHelp();
}
}
-
- // sanity check the op columns
+
+ // sanity check the op columns
for(size_t i = 0; i < opColumnsInt.size(); ++i) {
int opColumnInt = opColumnsInt[i];
if (opColumnInt < 1) {
- cerr << endl << "*****" << endl << "*****ERROR: op columns must be >=1. " << endl << "*****" << endl;
- ShowHelp();
+ cerr << endl << "*****" << endl << "*****ERROR: op columns must be >=1. " << endl << "*****" << endl;
+ ShowHelp();
}
}
-
+
// sanity check that there are equal number of opColumns and ops
if (ops.size() != opColumnsInt.size()) {
- cerr << endl << "*****" << endl << "*****ERROR: There must be equal number of ops and opCols. " << endl << "*****" << endl;
- ShowHelp();
+ cerr << endl << "*****" << endl << "*****ERROR: There must be equal number of ops and opCols. " << endl << "*****" << endl;
+ ShowHelp();
}
GroupBy(inFile, groupColumnsInt, opColumnsInt, ops);
- }
+ }
else {
ShowHelp();
}
@@ -212,20 +212,20 @@ int main(int argc, char* argv[]) {
void ShowHelp(void) {
cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
-
+
cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
cerr << "Summary: Summarizes a dataset column based upon" << endl;
cerr << "\t common column groupings. Akin to the SQL \"group by\" command." << endl << endl;
-
+
cerr << "Usage: " << PROGRAM_NAME << " -i <input> -g <group_column(s)> -c <op_column(s)> -o <ops> " << endl << endl;
cerr << "Options: " << endl;
cerr << "\t-i\t\t" << "Input file. Use \"stdin\" for pipes." << endl << endl;
-
+
cerr << "\t-g -grp\t\t" << "Specify the columns (1-based) for the grouping." << endl;
cerr << "\t\t\tThe columns must be comma separated." << endl;
- cerr << "\t\t\t- Default: 1,2,3" << endl << endl;
+ cerr << "\t\t\t- Default: 1,2,3" << endl << endl;
cerr << "\t-c -opCols\t" << "Specify the column (1-based) that should be summarized." << endl;
cerr << "\t\t\t- Required." << endl << endl;
@@ -234,7 +234,7 @@ void ShowHelp(void) {
cerr << "\t\t\tValid operations:" << endl;
cerr << "\t\t\t sum, count, min, max," << endl;
cerr << "\t\t\t mean, median, mode, antimode," << endl;
- cerr << "\t\t\t stdev, sstdev (sample standard dev.)," << endl;
+ cerr << "\t\t\t stdev, sstdev (sample standard dev.)," << endl;
cerr << "\t\t\t collapse (i.e., print a comma separated list), " << endl;
cerr << "\t\t\t freqdesc (i.e., print desc. list of values:freq)" << endl;
cerr << "\t\t\t freqasc (i.e., print asc. list of values:freq)" << endl;
@@ -250,49 +250,49 @@ void ShowHelp(void) {
cerr << "\tchr1 10 20 A 11000 10000" << endl << endl;
cerr << "\t$ groupBy -i ex1.out -g 1,2,3,4 -c 8,9 -o collapse,mean" << endl;
cerr << "\tchr1 10 20 A B.1,B.2, 5500" << endl << endl;
-
+
cerr << "Notes: " << endl;
cerr << "\t(1) The input file/stream should be sorted/grouped by the -grp. columns" << endl << endl;
cerr << "\t(2) If -i is unspecified, input is assumed to come from stdin." << endl << endl;
-
+
// end the program here
exit(1);
}
-void GroupBy (const string &inFile,
- const vector<int> &groupColumns,
- const vector<int> &opColumns,
+void GroupBy (const string &inFile,
+ const vector<int> &groupColumns,
+ const vector<int> &opColumns,
const vector<string> &ops) {
-
+
// current line number
int lineNum = 0;
// string representing current line
string inLine;
-
+
// vector of strings holding the tokenized current line
vector<string> inFields;
inFields.reserve(20);
-
+
// keys for the current and previous group
vector<string> prevGroup(0);
vector<string> currGroup(0);
-
+
// vector (one per column) of vector (one per value/column) of the opColumn values for the current group
vector< vector<string> > values;
for( size_t i = 0; i < opColumns.size(); i++ ) {
values.push_back( vector<string>() );
}
-
+
// check the status of the current line
TabLineStatus tabLineStatus;
-
+
// open a new tab file, loop through it line by line
// and summarize the data for a given group when the group
// fields change
- TabFile *_tab = new TabFile(inFile);
+ TabFile *_tab = new TabFile(inFile);
_tab->Open();
while ((tabLineStatus = _tab->GetNextTabLine(inFields, lineNum)) != TAB_INVALID) {
if (tabLineStatus == TAB_VALID) {
@@ -331,16 +331,16 @@ void GroupBy (const string &inFile,
void ReportSummary(const vector<string> &group, const vector<vector<string> > &data, const vector<string> &ops) {
-
+
vector<string> result;
for( size_t i = 0; i < data.size(); i++ ) {
-
+
string op = ops[i];
std::stringstream buffer;
vector<double> dataF;
// are we doing a numeric conversion? if so, convert the strings to doubles.
if ((op == "sum") || (op == "max") || (op == "min") || (op == "mean") ||
- (op == "median") || (op == "stdev") || (op == "sstdev"))
+ (op == "median") || (op == "stdev") || (op == "sstdev"))
{
transform(data[i].begin(), data[i].end(), back_inserter(dataF), ToDouble);
}
@@ -395,7 +395,7 @@ void ReportSummary(const vector<string> &group, const vector<vector<string> > &d
buffer << setprecision (PRECISION) << data[i].size();
result.push_back(buffer.str());
}
- else if ((op == "mode") || (op == "antimode") ||
+ else if ((op == "mode") || (op == "antimode") ||
(op == "freqdesc") || (op == "freqasc")) {
// compute the frequency of each unique value
map<string, int> freqs;
@@ -404,7 +404,7 @@ void ReportSummary(const vector<string> &group, const vector<vector<string> > &d
for (; dIt != dEnd; ++dIt) {
freqs[*dIt]++;
}
-
+
// grab the mode and the anti mode
string mode, antiMode;
int count = 0;
@@ -429,25 +429,25 @@ void ReportSummary(const vector<string> &group, const vector<vector<string> > &d
result.push_back(buffer.str());
}
else if (op == "freqdesc" || op == "freqasc") {
- // pair for the num times a values was
+ // pair for the num times a values was
// observed (1) and the value itself (2)
pair<int, string> freqPair;
vector< pair<int, string> > freqList;
-
+
// create a list of pairs of all the observed values (second)
// and their occurences (first)
map<string,int>::const_iterator mapIter = freqs.begin();
- map<string,int>::const_iterator mapEnd = freqs.end();
+ map<string,int>::const_iterator mapEnd = freqs.end();
for(; mapIter != mapEnd; ++mapIter)
freqList.push_back( make_pair(mapIter->second, mapIter->first) );
-
+
// sort the list of pairs in the requested order by the frequency
// this will make the value that was observed least/most bubble to the top
if (op == "freqdesc")
sort(freqList.begin(), freqList.end(), ValueGreaterThan());
else if (op == "freqasc")
sort(freqList.begin(), freqList.end(), ValueLessThan());
-
+
// record all of the values and their frequencies.
vector< pair<int, string> >::const_iterator iter = freqList.begin();
vector< pair<int, string> >::const_iterator iterEnd = freqList.end();
@@ -492,8 +492,8 @@ void addValue (const vector<string> &fromList, vector<string> &toList, int index
toList.push_back(fromList.at(index));
}
catch(std::out_of_range& e) {
- cerr << endl << "*****" << endl << "*****ERROR: requested column exceeds the number of columns in file at line "
- << lineNum << ". Exiting." << endl << "*****" << endl;
+ cerr << endl << "*****" << endl << "*****ERROR: requested column exceeds the number of columns in file at line "
+ << lineNum << ". Exiting." << endl << "*****" << endl;
exit(1);
}
}
diff --git a/src/intersectBed/intersectBed.cpp b/src/intersectBed/intersectBed.cpp
index b6aae98e4b8885f2d14fe7fd6e32190130b875fa..8e94677ea531b62bb40d638f3d8d577a60fc0dc0 100644
--- a/src/intersectBed/intersectBed.cpp
+++ b/src/intersectBed/intersectBed.cpp
@@ -19,101 +19,101 @@ bool BedIntersect::processHits(const BED &a, const vector<BED> &hits, bool print
// how many overlaps are there b/w the bed and the set of hits?
int s, e, overlapBases;
- int numOverlaps = 0;
+ int numOverlaps = 0;
bool hitsFound = false;
- int aLength = (a.end - a.start); // the length of a in b.p.
-
- // loop through the hits and report those that meet the user's criteria
- vector<BED>::const_iterator h = hits.begin();
- vector<BED>::const_iterator hitsEnd = hits.end();
- for (; h != hitsEnd; ++h) {
- s = max(a.start, h->start);
- e = min(a.end, h->end);
- overlapBases = (e - s); // the number of overlapping bases b/w a and b
-
- // is there enough overlap relative to the user's request? (default ~ 1bp)
- if ( ( (float) overlapBases / (float) aLength ) >= _overlapFraction ) {
- // Report the hit if the user doesn't care about reciprocal overlap between A and B.
- if (_reciprocal == false) {
- hitsFound = true;
- numOverlaps++;
- if (printable == true)
- ReportOverlapDetail(overlapBases, a, *h, s, e);
- }
- // we require there to be sufficient __reciprocal__ overlap
- else {
- int bLength = (h->end - h->start);
- float bOverlap = ( (float) overlapBases / (float) bLength );
- if (bOverlap >= _overlapFraction) {
- hitsFound = true;
- numOverlaps++;
- if (printable == true)
- ReportOverlapDetail(overlapBases, a, *h, s, e);
- }
- }
- }
- }
- // report the summary of the overlaps if requested.
- ReportOverlapSummary(a, numOverlaps);
- // were hits found for this BED feature?
- return hitsFound;
+ int aLength = (a.end - a.start); // the length of a in b.p.
+
+ // loop through the hits and report those that meet the user's criteria
+ vector<BED>::const_iterator h = hits.begin();
+ vector<BED>::const_iterator hitsEnd = hits.end();
+ for (; h != hitsEnd; ++h) {
+ s = max(a.start, h->start);
+ e = min(a.end, h->end);
+ overlapBases = (e - s); // the number of overlapping bases b/w a and b
+
+ // is there enough overlap relative to the user's request? (default ~ 1bp)
+ if ( ( (float) overlapBases / (float) aLength ) >= _overlapFraction ) {
+ // Report the hit if the user doesn't care about reciprocal overlap between A and B.
+ if (_reciprocal == false) {
+ hitsFound = true;
+ numOverlaps++;
+ if (printable == true)
+ ReportOverlapDetail(overlapBases, a, *h, s, e);
+ }
+ // we require there to be sufficient __reciprocal__ overlap
+ else {
+ int bLength = (h->end - h->start);
+ float bOverlap = ( (float) overlapBases / (float) bLength );
+ if (bOverlap >= _overlapFraction) {
+ hitsFound = true;
+ numOverlaps++;
+ if (printable == true)
+ ReportOverlapDetail(overlapBases, a, *h, s, e);
+ }
+ }
+ }
+ }
+ // report the summary of the overlaps if requested.
+ ReportOverlapSummary(a, numOverlaps);
+ // were hits found for this BED feature?
+ return hitsFound;
}
/*
- Constructor
+ Constructor
*/
-BedIntersect::BedIntersect(string bedAFile, string bedBFile, bool anyHit,
- bool writeA, bool writeB, bool writeOverlap, bool writeAllOverlap,
- float overlapFraction, bool noHit, bool writeCount, bool forceStrand,
- bool reciprocal, bool obeySplits, bool bamInput, bool bamOutput, bool isUncompressedBam) {
-
- _bedAFile = bedAFile;
- _bedBFile = bedBFile;
- _anyHit = anyHit;
- _noHit = noHit;
- _writeA = writeA;
- _writeB = writeB;
- _writeOverlap = writeOverlap;
- _writeAllOverlap = writeAllOverlap;
- _writeCount = writeCount;
- _overlapFraction = overlapFraction;
- _forceStrand = forceStrand;
- _reciprocal = reciprocal;
+BedIntersect::BedIntersect(string bedAFile, string bedBFile, bool anyHit,
+ bool writeA, bool writeB, bool writeOverlap, bool writeAllOverlap,
+ float overlapFraction, bool noHit, bool writeCount, bool forceStrand,
+ bool reciprocal, bool obeySplits, bool bamInput, bool bamOutput, bool isUncompressedBam) {
+
+ _bedAFile = bedAFile;
+ _bedBFile = bedBFile;
+ _anyHit = anyHit;
+ _noHit = noHit;
+ _writeA = writeA;
+ _writeB = writeB;
+ _writeOverlap = writeOverlap;
+ _writeAllOverlap = writeAllOverlap;
+ _writeCount = writeCount;
+ _overlapFraction = overlapFraction;
+ _forceStrand = forceStrand;
+ _reciprocal = reciprocal;
_obeySplits = obeySplits;
- _bamInput = bamInput;
- _bamOutput = bamOutput;
+ _bamInput = bamInput;
+ _bamOutput = bamOutput;
_isUncompressedBam = isUncompressedBam;
-
- // create new BED file objects for A and B
- _bedA = new BedFile(bedAFile);
- _bedB = new BedFile(bedBFile);
-
- if (_bamInput == false)
- IntersectBed();
- else
- IntersectBam(bedAFile);
+
+ // create new BED file objects for A and B
+ _bedA = new BedFile(bedAFile);
+ _bedB = new BedFile(bedBFile);
+
+ if (_bamInput == false)
+ IntersectBed();
+ else
+ IntersectBam(bedAFile);
}
/*
- Destructor
+ Destructor
*/
BedIntersect::~BedIntersect(void) {
}
bool BedIntersect::FindOverlaps(const BED &a, vector<BED> &hits) {
-
- bool hitsFound = false;
- // should we print each overlap, or does the user want summary information?
- bool printable = true;
- if (_anyHit || _noHit || _writeCount)
- printable = false;
+ bool hitsFound = false;
+
+ // should we print each overlap, or does the user want summary information?
+ bool printable = true;
+ if (_anyHit || _noHit || _writeCount)
+ printable = false;
- // collect and report the sufficient hits
- _bedB->FindOverlapsPerBin(a.chrom, a.start, a.end, a.strand, hits, _forceStrand);
+ // collect and report the sufficient hits
+ _bedB->FindOverlapsPerBin(a.chrom, a.start, a.end, a.strand, hits, _forceStrand);
hitsFound = processHits(a, hits, printable);
return hitsFound;
@@ -121,217 +121,217 @@ bool BedIntersect::FindOverlaps(const BED &a, vector<BED> &hits) {
void BedIntersect::ReportOverlapDetail(const int &overlapBases, const BED &a, const BED &b,
- const CHRPOS &s, const CHRPOS &e) {
- // default. simple intersection only
- if (_writeA == false && _writeB == false && _writeOverlap == false) {
- _bedA->reportBedRangeNewLine(a,s,e);
- }
- // -wa -wbwrite the original A and B
- else if (_writeA == true && _writeB == true) {
- _bedA->reportBedTab(a);
- _bedB->reportBedNewLine(b);
- }
- // -wa write just the original A
- else if (_writeA == true) {
- _bedA->reportBedNewLine(a);
- }
- // -wb write the intersected portion of A and the original B
- else if (_writeB == true) {
- _bedA->reportBedRangeTab(a,s,e);
- _bedB->reportBedNewLine(b);
- }
- // -wo write the original A and B plus the no. of overlapping bases.
- else if (_writeOverlap == true) {
- _bedA->reportBedTab(a);
- _bedB->reportBedTab(b);
- printf("%d\n", overlapBases);
- }
+ const CHRPOS &s, const CHRPOS &e) {
+ // default. simple intersection only
+ if (_writeA == false && _writeB == false && _writeOverlap == false) {
+ _bedA->reportBedRangeNewLine(a,s,e);
+ }
+ // -wa -wbwrite the original A and B
+ else if (_writeA == true && _writeB == true) {
+ _bedA->reportBedTab(a);
+ _bedB->reportBedNewLine(b);
+ }
+ // -wa write just the original A
+ else if (_writeA == true) {
+ _bedA->reportBedNewLine(a);
+ }
+ // -wb write the intersected portion of A and the original B
+ else if (_writeB == true) {
+ _bedA->reportBedRangeTab(a,s,e);
+ _bedB->reportBedNewLine(b);
+ }
+ // -wo write the original A and B plus the no. of overlapping bases.
+ else if (_writeOverlap == true) {
+ _bedA->reportBedTab(a);
+ _bedB->reportBedTab(b);
+ printf("%d\n", overlapBases);
+ }
}
void BedIntersect::ReportOverlapSummary(const BED &a, const int &numOverlapsFound) {
- // -u just report the fact that there was >= 1 overlaps
- if (_anyHit && (numOverlapsFound >= 1)) {
- _bedA->reportBedNewLine(a);
- }
- // -c report the total number of features overlapped in B
- else if (_writeCount) {
- _bedA->reportBedTab(a);
- printf("%d\n", numOverlapsFound);
- }
- // -v report iff there were no overlaps
- else if (_noHit && (numOverlapsFound == 0)) {
- _bedA->reportBedNewLine(a);
- }
- // -wao the user wants to force the reporting of 0 overlap
- else if (_writeAllOverlap && (numOverlapsFound == 0)) {
- _bedA->reportBedTab(a);
- _bedB->reportNullBedTab();
- printf("0\n");
- }
+ // -u just report the fact that there was >= 1 overlaps
+ if (_anyHit && (numOverlapsFound >= 1)) {
+ _bedA->reportBedNewLine(a);
+ }
+ // -c report the total number of features overlapped in B
+ else if (_writeCount) {
+ _bedA->reportBedTab(a);
+ printf("%d\n", numOverlapsFound);
+ }
+ // -v report iff there were no overlaps
+ else if (_noHit && (numOverlapsFound == 0)) {
+ _bedA->reportBedNewLine(a);
+ }
+ // -wao the user wants to force the reporting of 0 overlap
+ else if (_writeAllOverlap && (numOverlapsFound == 0)) {
+ _bedA->reportBedTab(a);
+ _bedB->reportNullBedTab();
+ printf("0\n");
+ }
}
bool BedIntersect::FindOneOrMoreOverlap(const BED &a) {
- bool overlapsFound;
- if (_reciprocal == false) {
- overlapsFound = _bedB->FindOneOrMoreOverlapsPerBin(a.chrom, a.start, a.end, a.strand,
- _forceStrand, _overlapFraction);
- }
- else {
- overlapsFound = _bedB->FindOneOrMoreReciprocalOverlapsPerBin(a.chrom, a.start, a.end, a.strand,
- _forceStrand, _overlapFraction);
- }
- return overlapsFound;
+ bool overlapsFound;
+ if (_reciprocal == false) {
+ overlapsFound = _bedB->FindOneOrMoreOverlapsPerBin(a.chrom, a.start, a.end, a.strand,
+ _forceStrand, _overlapFraction);
+ }
+ else {
+ overlapsFound = _bedB->FindOneOrMoreReciprocalOverlapsPerBin(a.chrom, a.start, a.end, a.strand,
+ _forceStrand, _overlapFraction);
+ }
+ return overlapsFound;
}
-
+
void BedIntersect::IntersectBed() {
- // load the "B" file into a map in order to
- // compare each entry in A to it in search of overlaps.
- _bedB->loadBedFileIntoMap();
-
- int lineNum = 0;
- vector<BED> hits;
- hits.reserve(100);
- BED a, nullBed;
- BedLineStatus bedStatus;
-
- // open the "A" file, process each BED entry and searh for overlaps.
- _bedA->Open();
- while ((bedStatus = _bedA->GetNextBed(a, lineNum)) != BED_INVALID) {
- if (bedStatus == BED_VALID) {
- // treat the BED as a single "block"
- if (_obeySplits == false) {
- FindOverlaps(a, hits);
- hits.clear();
- a = nullBed;
- }
- // split the BED12 into blocks and look for overlaps in each discrete block
+ // load the "B" file into a map in order to
+ // compare each entry in A to it in search of overlaps.
+ _bedB->loadBedFileIntoMap();
+
+ int lineNum = 0;
+ vector<BED> hits;
+ hits.reserve(100);
+ BED a, nullBed;
+ BedLineStatus bedStatus;
+
+ // open the "A" file, process each BED entry and searh for overlaps.
+ _bedA->Open();
+ while ((bedStatus = _bedA->GetNextBed(a, lineNum)) != BED_INVALID) {
+ if (bedStatus == BED_VALID) {
+ // treat the BED as a single "block"
+ if (_obeySplits == false) {
+ FindOverlaps(a, hits);
+ hits.clear();
+ a = nullBed;
+ }
+ // split the BED12 into blocks and look for overlaps in each discrete block
else {
bedVector bedBlocks; // vec to store the discrete BED "blocks"
splitBedIntoBlocks(a, lineNum, bedBlocks);
-
+
vector<BED>::const_iterator bedItr = bedBlocks.begin();
- vector<BED>::const_iterator bedEnd = bedBlocks.end();
- for (; bedItr != bedEnd; ++bedItr) {
- FindOverlaps(*bedItr, hits);
+ vector<BED>::const_iterator bedEnd = bedBlocks.end();
+ for (; bedItr != bedEnd; ++bedItr) {
+ FindOverlaps(*bedItr, hits);
hits.clear();
- }
- a = nullBed;
+ }
+ a = nullBed;
}
- }
- }
- _bedA->Close();
+ }
+ }
+ _bedA->Close();
}
void BedIntersect::IntersectBam(string bamFile) {
- // load the "B" bed file into a map so
- // that we can easily compare "A" to it for overlaps
- _bedB->loadBedFileIntoMap();
-
- // open the BAM file
- BamReader reader;
- BamWriter writer;
- reader.Open(bamFile);
-
- // get header & reference information
- string header = reader.GetHeaderText();
- RefVector refs = reader.GetReferenceData();
-
- // open a BAM output to stdout if we are writing BAM
- if (_bamOutput == true) {
- // open our BAM writer
+ // load the "B" bed file into a map so
+ // that we can easily compare "A" to it for overlaps
+ _bedB->loadBedFileIntoMap();
+
+ // open the BAM file
+ BamReader reader;
+ BamWriter writer;
+ reader.Open(bamFile);
+
+ // get header & reference information
+ string header = reader.GetHeaderText();
+ RefVector refs = reader.GetReferenceData();
+
+ // open a BAM output to stdout if we are writing BAM
+ if (_bamOutput == true) {
+ // open our BAM writer
writer.Open("stdout", header, refs, _isUncompressedBam);
- }
-
- vector<BED> hits;
- // reserve some space
- hits.reserve(100);
-
- _bedA->bedType = 6;
- BamAlignment bam;
- // get each set of alignments for each pair.
- while (reader.GetNextAlignment(bam)) {
-
- if (bam.IsMapped()) {
- BED a;
- a.chrom = refs.at(bam.RefID).RefName;
- a.start = bam.Position;
- a.end = bam.GetEndPosition(false);
-
- // build the name field from the BAM alignment.
- a.name = bam.Name;
- if (bam.IsFirstMate()) a.name += "/1";
- if (bam.IsSecondMate()) a.name += "/2";
-
- a.score = ToString(bam.MapQuality);
-
- a.strand = "+";
- if (bam.IsReverseStrand()) a.strand = "-";
-
- if (_bamOutput == true) {
- bool overlapsFound = false;
- // treat the BAM alignment as a single "block"
- if (_obeySplits == false) {
- overlapsFound = FindOneOrMoreOverlap(a);
- }
- // split the BAM alignment into discrete blocks and
- // look for overlaps only within each block.
- else {
+ }
+
+ vector<BED> hits;
+ // reserve some space
+ hits.reserve(100);
+
+ _bedA->bedType = 6;
+ BamAlignment bam;
+ // get each set of alignments for each pair.
+ while (reader.GetNextAlignment(bam)) {
+
+ if (bam.IsMapped()) {
+ BED a;
+ a.chrom = refs.at(bam.RefID).RefName;
+ a.start = bam.Position;
+ a.end = bam.GetEndPosition(false);
+
+ // build the name field from the BAM alignment.
+ a.name = bam.Name;
+ if (bam.IsFirstMate()) a.name += "/1";
+ if (bam.IsSecondMate()) a.name += "/2";
+
+ a.score = ToString(bam.MapQuality);
+
+ a.strand = "+";
+ if (bam.IsReverseStrand()) a.strand = "-";
+
+ if (_bamOutput == true) {
+ bool overlapsFound = false;
+ // treat the BAM alignment as a single "block"
+ if (_obeySplits == false) {
+ overlapsFound = FindOneOrMoreOverlap(a);
+ }
+ // split the BAM alignment into discrete blocks and
+ // look for overlaps only within each block.
+ else {
bool overlapFoundForBlock;
- bedVector bedBlocks; // vec to store the discrete BED "blocks" from a
- // we don't want to split on "D" ops, hence the "false"
+ bedVector bedBlocks; // vec to store the discrete BED "blocks" from a
+ // we don't want to split on "D" ops, hence the "false"
getBamBlocks(bam, refs, bedBlocks, false);
-
+
vector<BED>::const_iterator bedItr = bedBlocks.begin();
- vector<BED>::const_iterator bedEnd = bedBlocks.end();
- for (; bedItr != bedEnd; ++bedItr) {
- overlapFoundForBlock = FindOneOrMoreOverlap(a);
- if (overlapFoundForBlock == true)
+ vector<BED>::const_iterator bedEnd = bedBlocks.end();
+ for (; bedItr != bedEnd; ++bedItr) {
+ overlapFoundForBlock = FindOneOrMoreOverlap(a);
+ if (overlapFoundForBlock == true)
overlapsFound = true;
- }
- }
- if (overlapsFound == true) {
- if (_noHit == false)
- writer.SaveAlignment(bam);
- }
- else {
- if (_noHit == true) {
- writer.SaveAlignment(bam);
- }
- }
- }
- else {
- // treat the BAM alignment as a single BED "block"
- if (_obeySplits == false) {
- FindOverlaps(a, hits);
- hits.clear();
- }
- // split the BAM alignment into discrete BED blocks and
- // look for overlaps only within each block.
- else {
- bedVector bedBlocks; // vec to store the discrete BED "blocks" from a
+ }
+ }
+ if (overlapsFound == true) {
+ if (_noHit == false)
+ writer.SaveAlignment(bam);
+ }
+ else {
+ if (_noHit == true) {
+ writer.SaveAlignment(bam);
+ }
+ }
+ }
+ else {
+ // treat the BAM alignment as a single BED "block"
+ if (_obeySplits == false) {
+ FindOverlaps(a, hits);
+ hits.clear();
+ }
+ // split the BAM alignment into discrete BED blocks and
+ // look for overlaps only within each block.
+ else {
+ bedVector bedBlocks; // vec to store the discrete BED "blocks" from a
getBamBlocks(bam, refs, bedBlocks, false);
vector<BED>::const_iterator bedItr = bedBlocks.begin();
- vector<BED>::const_iterator bedEnd = bedBlocks.end();
- for (; bedItr != bedEnd; ++bedItr) {
- FindOverlaps(*bedItr, hits);
+ vector<BED>::const_iterator bedEnd = bedBlocks.end();
+ for (; bedItr != bedEnd; ++bedItr) {
+ FindOverlaps(*bedItr, hits);
hits.clear();
- }
- }
- }
- }
- }
-
- // close the relevant BAM files.
- reader.Close();
- if (_bamOutput == true) {
- writer.Close();
- }
+ }
+ }
+ }
+ }
+ }
+
+ // close the relevant BAM files.
+ reader.Close();
+ if (_bamOutput == true) {
+ writer.Close();
+ }
}
diff --git a/src/intersectBed/intersectBed.h b/src/intersectBed/intersectBed.h
index b7524f2797149a91bbe0ca2f611d5fcf67fe7044..a24cf56836a21f47411c9aa62f7c8c56ba26ca22 100644
--- a/src/intersectBed/intersectBed.h
+++ b/src/intersectBed/intersectBed.h
@@ -32,62 +32,62 @@ class BedIntersect {
public:
- // constructor
- BedIntersect(string bedAFile, string bedBFile, bool anyHit,
- bool writeA, bool writeB, bool writeOverlap, bool writeAllOverlap,
- float overlapFraction, bool noHit, bool writeCount, bool forceStrand,
- bool reciprocal, bool obeySplits, bool bamInput, bool bamOutput, bool isUncompressedBam);
-
- // destructor
- ~BedIntersect(void);
-
+ // constructor
+ BedIntersect(string bedAFile, string bedBFile, bool anyHit,
+ bool writeA, bool writeB, bool writeOverlap, bool writeAllOverlap,
+ float overlapFraction, bool noHit, bool writeCount, bool forceStrand,
+ bool reciprocal, bool obeySplits, bool bamInput, bool bamOutput, bool isUncompressedBam);
+
+ // destructor
+ ~BedIntersect(void);
+
private:
-
- //------------------------------------------------
- // private attributes
- //------------------------------------------------
- string _bedAFile;
- string _bedBFile;
-
- bool _writeA; // should the original A feature be reported?
- bool _writeB; // should the original B feature be reported?
- bool _writeOverlap;
- bool _writeAllOverlap;
-
- bool _forceStrand;
- bool _reciprocal;
- float _overlapFraction;
-
- bool _anyHit;
- bool _noHit;
- bool _writeCount; // do we want a count of the number of overlaps in B?
+
+ //------------------------------------------------
+ // private attributes
+ //------------------------------------------------
+ string _bedAFile;
+ string _bedBFile;
+
+ bool _writeA; // should the original A feature be reported?
+ bool _writeB; // should the original B feature be reported?
+ bool _writeOverlap;
+ bool _writeAllOverlap;
+
+ bool _forceStrand;
+ bool _reciprocal;
+ float _overlapFraction;
+
+ bool _anyHit;
+ bool _noHit;
+ bool _writeCount; // do we want a count of the number of overlaps in B?
bool _obeySplits;
- bool _bamInput;
- bool _bamOutput;
+ bool _bamInput;
+ bool _bamOutput;
bool _isUncompressedBam;
-
- // instance of a bed file class.
- BedFile *_bedA, *_bedB;
- //------------------------------------------------
- // private methods
- //------------------------------------------------
- void IntersectBed(istream &bedInput);
+ // instance of a bed file class.
+ BedFile *_bedA, *_bedB;
- void IntersectBed();
+ //------------------------------------------------
+ // private methods
+ //------------------------------------------------
+ void IntersectBed(istream &bedInput);
+
+ void IntersectBed();
+
+ void IntersectBam(string bamFile);
- void IntersectBam(string bamFile);
-
bool processHits(const BED &a, const vector<BED> &hits, bool printable);
-
- bool FindOverlaps(const BED &a, vector<BED> &hits);
-
- bool FindOneOrMoreOverlap(const BED &a);
-
- void ReportOverlapDetail(const int &overlapBases, const BED &a, const BED &b,
- const CHRPOS &s, const CHRPOS &e);
- void ReportOverlapSummary(const BED &a, const int &numOverlapsFound);
-
+
+ bool FindOverlaps(const BED &a, vector<BED> &hits);
+
+ bool FindOneOrMoreOverlap(const BED &a);
+
+ void ReportOverlapDetail(const int &overlapBases, const BED &a, const BED &b,
+ const CHRPOS &s, const CHRPOS &e);
+ void ReportOverlapSummary(const BED &a, const int &numOverlapsFound);
+
};
#endif /* INTERSECTBED_H */
diff --git a/src/intersectBed/intersectMain.cpp b/src/intersectBed/intersectMain.cpp
index 42cb38a1812f278e53f9636b173b0142795a2d36..e6d35cd5c03b339cc5f811323ab82bd7918f2368 100644
--- a/src/intersectBed/intersectMain.cpp
+++ b/src/intersectBed/intersectMain.cpp
@@ -26,251 +26,251 @@ void ShowHelp(void);
int main(int argc, char* argv[]) {
- // our configuration variables
- bool showHelp = false;
-
- // input files
- string bedAFile;
- string bedBFile;
-
- // input arguments
- float overlapFraction = 1E-9;
-
- bool haveBedA = false;
- bool haveBedB = false;
- bool noHit = false;
- bool anyHit = false;
- bool writeA = false;
- bool writeB = false;
- bool writeCount = false;
- bool writeOverlap = false;
- bool writeAllOverlap = false;
- bool haveFraction = false;
- bool reciprocalFraction = false;
- bool forceStrand = false;
+ // our configuration variables
+ bool showHelp = false;
+
+ // input files
+ string bedAFile;
+ string bedBFile;
+
+ // input arguments
+ float overlapFraction = 1E-9;
+
+ bool haveBedA = false;
+ bool haveBedB = false;
+ bool noHit = false;
+ bool anyHit = false;
+ bool writeA = false;
+ bool writeB = false;
+ bool writeCount = false;
+ bool writeOverlap = false;
+ bool writeAllOverlap = false;
+ bool haveFraction = false;
+ bool reciprocalFraction = false;
+ bool forceStrand = false;
bool obeySplits = false;
- bool inputIsBam = false;
- bool outputIsBam = true;
- bool uncompressedBam = false;
- // check to see if we should print out some help
- if(argc <= 1) showHelp = true;
-
- for(int i = 1; i < argc; i++) {
- int parameterLength = (int)strlen(argv[i]);
-
- if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
- (PARAMETER_CHECK("--help", 5, parameterLength))) {
- showHelp = true;
- }
- }
-
- if(showHelp) ShowHelp();
-
- // do some parsing (all of these parameters require 2 strings)
- for(int i = 1; i < argc; i++) {
-
- int parameterLength = (int)strlen(argv[i]);
-
- if(PARAMETER_CHECK("-a", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveBedA = true;
- outputIsBam = false;
- bedAFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-abam", 5, parameterLength)) {
- if ((i+1) < argc) {
- haveBedA = true;
- inputIsBam = true;
- bedAFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-b", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveBedB = true;
- bedBFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-bed", 4, parameterLength)) {
- outputIsBam = false;
- }
- else if(PARAMETER_CHECK("-u", 2, parameterLength)) {
- anyHit = true;
- }
- else if(PARAMETER_CHECK("-f", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveFraction = true;
- overlapFraction = atof(argv[i + 1]);
- i++;
- }
- }
- else if(PARAMETER_CHECK("-wa", 3, parameterLength)) {
- writeA = true;
- }
- else if(PARAMETER_CHECK("-wb", 3, parameterLength)) {
- writeB = true;
- }
- else if(PARAMETER_CHECK("-wo", 3, parameterLength)) {
- writeOverlap = true;
- }
- else if(PARAMETER_CHECK("-wao", 4, parameterLength)) {
- writeAllOverlap = true;
- writeOverlap = true;
- }
- else if(PARAMETER_CHECK("-c", 2, parameterLength)) {
- writeCount = true;
- }
- else if(PARAMETER_CHECK("-r", 2, parameterLength)) {
- reciprocalFraction = true;
- }
- else if (PARAMETER_CHECK("-v", 2, parameterLength)) {
- noHit = true;
- }
- else if (PARAMETER_CHECK("-s", 2, parameterLength)) {
- forceStrand = true;
- }
- else if (PARAMETER_CHECK("-split", 6, parameterLength)) {
- obeySplits = true;
- }
- else if(PARAMETER_CHECK("-ubam", 5, parameterLength)) {
+ bool inputIsBam = false;
+ bool outputIsBam = true;
+ bool uncompressedBam = false;
+ // check to see if we should print out some help
+ if(argc <= 1) showHelp = true;
+
+ for(int i = 1; i < argc; i++) {
+ int parameterLength = (int)strlen(argv[i]);
+
+ if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
+ (PARAMETER_CHECK("--help", 5, parameterLength))) {
+ showHelp = true;
+ }
+ }
+
+ if(showHelp) ShowHelp();
+
+ // do some parsing (all of these parameters require 2 strings)
+ for(int i = 1; i < argc; i++) {
+
+ int parameterLength = (int)strlen(argv[i]);
+
+ if(PARAMETER_CHECK("-a", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveBedA = true;
+ outputIsBam = false;
+ bedAFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-abam", 5, parameterLength)) {
+ if ((i+1) < argc) {
+ haveBedA = true;
+ inputIsBam = true;
+ bedAFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-b", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveBedB = true;
+ bedBFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-bed", 4, parameterLength)) {
+ outputIsBam = false;
+ }
+ else if(PARAMETER_CHECK("-u", 2, parameterLength)) {
+ anyHit = true;
+ }
+ else if(PARAMETER_CHECK("-f", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveFraction = true;
+ overlapFraction = atof(argv[i + 1]);
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-wa", 3, parameterLength)) {
+ writeA = true;
+ }
+ else if(PARAMETER_CHECK("-wb", 3, parameterLength)) {
+ writeB = true;
+ }
+ else if(PARAMETER_CHECK("-wo", 3, parameterLength)) {
+ writeOverlap = true;
+ }
+ else if(PARAMETER_CHECK("-wao", 4, parameterLength)) {
+ writeAllOverlap = true;
+ writeOverlap = true;
+ }
+ else if(PARAMETER_CHECK("-c", 2, parameterLength)) {
+ writeCount = true;
+ }
+ else if(PARAMETER_CHECK("-r", 2, parameterLength)) {
+ reciprocalFraction = true;
+ }
+ else if (PARAMETER_CHECK("-v", 2, parameterLength)) {
+ noHit = true;
+ }
+ else if (PARAMETER_CHECK("-s", 2, parameterLength)) {
+ forceStrand = true;
+ }
+ else if (PARAMETER_CHECK("-split", 6, parameterLength)) {
+ obeySplits = true;
+ }
+ else if(PARAMETER_CHECK("-ubam", 5, parameterLength)) {
uncompressedBam = true;
- }
- else {
- cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
- showHelp = true;
- }
- }
-
- // make sure we have both input files
- if (!haveBedA || !haveBedB) {
- cerr << endl << "*****" << endl << "*****ERROR: Need -a and -b files. " << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (anyHit && noHit) {
- cerr << endl << "*****" << endl << "*****ERROR: Request either -u OR -v, not both." << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (writeB && writeCount) {
- cerr << endl << "*****" << endl << "*****ERROR: Request either -wb OR -c, not both." << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (writeCount && writeOverlap) {
- cerr << endl << "*****" << endl << "*****ERROR: Request either -wb OR -wo, not both." << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (writeA && writeOverlap) {
- cerr << endl << "*****" << endl << "*****ERROR: Request either -wa OR -wo, not both." << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (writeB && writeOverlap) {
- cerr << endl << "*****" << endl << "*****ERROR: Request either -wb OR -wo, not both." << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (reciprocalFraction && !haveFraction) {
- cerr << endl << "*****" << endl << "*****ERROR: If using -r, you need to define -f." << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (anyHit && writeCount) {
- cerr << endl << "*****" << endl << "*****ERROR: Request either -u OR -c, not both." << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (anyHit && writeB) {
- cerr << endl << "*****" << endl << "*****ERROR: Request either -u OR -wb, not both." << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (anyHit && writeOverlap) {
- cerr << endl << "*****" << endl << "*****ERROR: Request either -u OR -wo, not both." << endl << "*****" << endl;
- showHelp = true;
- }
-
-
- if (!showHelp) {
-
- BedIntersect *bi = new BedIntersect(bedAFile, bedBFile, anyHit, writeA, writeB, writeOverlap,
- writeAllOverlap, overlapFraction, noHit, writeCount, forceStrand,
- reciprocalFraction, obeySplits, inputIsBam, outputIsBam, uncompressedBam);
- delete bi;
- return 0;
- }
- else {
- ShowHelp();
- }
+ }
+ else {
+ cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
+ showHelp = true;
+ }
+ }
+
+ // make sure we have both input files
+ if (!haveBedA || !haveBedB) {
+ cerr << endl << "*****" << endl << "*****ERROR: Need -a and -b files. " << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (anyHit && noHit) {
+ cerr << endl << "*****" << endl << "*****ERROR: Request either -u OR -v, not both." << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (writeB && writeCount) {
+ cerr << endl << "*****" << endl << "*****ERROR: Request either -wb OR -c, not both." << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (writeCount && writeOverlap) {
+ cerr << endl << "*****" << endl << "*****ERROR: Request either -wb OR -wo, not both." << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (writeA && writeOverlap) {
+ cerr << endl << "*****" << endl << "*****ERROR: Request either -wa OR -wo, not both." << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (writeB && writeOverlap) {
+ cerr << endl << "*****" << endl << "*****ERROR: Request either -wb OR -wo, not both." << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (reciprocalFraction && !haveFraction) {
+ cerr << endl << "*****" << endl << "*****ERROR: If using -r, you need to define -f." << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (anyHit && writeCount) {
+ cerr << endl << "*****" << endl << "*****ERROR: Request either -u OR -c, not both." << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (anyHit && writeB) {
+ cerr << endl << "*****" << endl << "*****ERROR: Request either -u OR -wb, not both." << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (anyHit && writeOverlap) {
+ cerr << endl << "*****" << endl << "*****ERROR: Request either -u OR -wo, not both." << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+
+ if (!showHelp) {
+
+ BedIntersect *bi = new BedIntersect(bedAFile, bedBFile, anyHit, writeA, writeB, writeOverlap,
+ writeAllOverlap, overlapFraction, noHit, writeCount, forceStrand,
+ reciprocalFraction, obeySplits, inputIsBam, outputIsBam, uncompressedBam);
+ delete bi;
+ return 0;
+ }
+ else {
+ ShowHelp();
+ }
}
void ShowHelp(void) {
- cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
-
- cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
-
- cerr << "Summary: Report overlaps between two feature files." << endl << endl;
-
- cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -a <bed/gff/vcf> -b <bed/gff/vcf>" << endl << endl;
-
- cerr << "Options: " << endl;
-
- cerr << "\t-abam\t" << "The A input file is in BAM format. Output will be BAM as well." << endl << endl;
-
- cerr << "\t-ubam\t" << "Write uncompressed BAM output. Default is to write compressed BAM." << endl << endl;
-
- cerr << "\t-bed\t" << "When using BAM input (-abam), write output as BED. The default" << endl;
- cerr << "\t\tis to write output in BAM when using -abam." << endl << endl;
-
- cerr << "\t-wa\t" << "Write the original entry in A for each overlap." << endl << endl;
-
- cerr << "\t-wb\t" << "Write the original entry in B for each overlap." << endl;
- cerr << "\t\t- Useful for knowing _what_ A overlaps. Restricted by -f and -r." << endl << endl;
-
- cerr << "\t-wo\t" << "Write the original A and B entries plus the number of base" << endl;
- cerr << "\t\tpairs of overlap between the two features." << endl;
- cerr << "\t\t- Overlaps restricted by -f and -r." << endl;
- cerr << "\t\t Only A features with overlap are reported." << endl << endl;
-
- cerr << "\t-wao\t" << "Write the original A and B entries plus the number of base" << endl;
- cerr << "\t\tpairs of overlap between the two features." << endl;
- cerr << "\t\t- Overlapping features restricted by -f and -r." << endl;
- cerr << "\t\t However, A features w/o overlap are also reported" << endl;
- cerr << "\t\t with a NULL B feature and overlap = 0." << endl << endl;
-
- cerr << "\t-u\t" << "Write the original A entry _once_ if _any_ overlaps found in B." << endl;
- cerr << "\t\t- In other words, just report the fact >=1 hit was found." << endl;
- cerr << "\t\t- Overlaps restricted by -f and -r." << endl << endl;
-
- cerr << "\t-c\t" << "For each entry in A, report the number of overlaps with B." << endl;
- cerr << "\t\t- Reports 0 for A entries that have no overlap with B." << endl;
- cerr << "\t\t- Overlaps restricted by -f and -r." << endl << endl;
-
- cerr << "\t-v\t" << "Only report those entries in A that have _no overlaps_ with B." << endl;
- cerr << "\t\t- Similar to \"grep -v\" (an homage)." << endl << endl;
-
- cerr << "\t-f\t" << "Minimum overlap required as a fraction of A." << endl;
- cerr << "\t\t- Default is 1E-9 (i.e., 1bp)." << endl;
- cerr << "\t\t- FLOAT (e.g. 0.50)" << endl << endl;
-
- cerr << "\t-r\t" << "Require that the fraction overlap be reciprocal for A and B." << endl;
- cerr << "\t\t- In other words, if -f is 0.90 and -r is used, this requires" << endl;
- cerr << "\t\t that B overlap 90% of A and A _also_ overlaps 90% of B." << endl << endl;
-
- cerr << "\t-s\t" << "Force strandedness. That is, only report hits in B that" << endl;
- cerr << "\t\toverlap A on the same strand." << endl;
- cerr << "\t\t- By default, overlaps are reported without respect to strand." << endl << endl;
-
- cerr << "\t-split\t" << "Treat \"split\" BAM or BED12 entries as distinct BED intervals." << endl << endl;
-
-
- // end the program here
- exit(1);
+ cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
+
+ cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
+
+ cerr << "Summary: Report overlaps between two feature files." << endl << endl;
+
+ cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -a <bed/gff/vcf> -b <bed/gff/vcf>" << endl << endl;
+
+ cerr << "Options: " << endl;
+
+ cerr << "\t-abam\t" << "The A input file is in BAM format. Output will be BAM as well." << endl << endl;
+
+ cerr << "\t-ubam\t" << "Write uncompressed BAM output. Default is to write compressed BAM." << endl << endl;
+
+ cerr << "\t-bed\t" << "When using BAM input (-abam), write output as BED. The default" << endl;
+ cerr << "\t\tis to write output in BAM when using -abam." << endl << endl;
+
+ cerr << "\t-wa\t" << "Write the original entry in A for each overlap." << endl << endl;
+
+ cerr << "\t-wb\t" << "Write the original entry in B for each overlap." << endl;
+ cerr << "\t\t- Useful for knowing _what_ A overlaps. Restricted by -f and -r." << endl << endl;
+
+ cerr << "\t-wo\t" << "Write the original A and B entries plus the number of base" << endl;
+ cerr << "\t\tpairs of overlap between the two features." << endl;
+ cerr << "\t\t- Overlaps restricted by -f and -r." << endl;
+ cerr << "\t\t Only A features with overlap are reported." << endl << endl;
+
+ cerr << "\t-wao\t" << "Write the original A and B entries plus the number of base" << endl;
+ cerr << "\t\tpairs of overlap between the two features." << endl;
+ cerr << "\t\t- Overlapping features restricted by -f and -r." << endl;
+ cerr << "\t\t However, A features w/o overlap are also reported" << endl;
+ cerr << "\t\t with a NULL B feature and overlap = 0." << endl << endl;
+
+ cerr << "\t-u\t" << "Write the original A entry _once_ if _any_ overlaps found in B." << endl;
+ cerr << "\t\t- In other words, just report the fact >=1 hit was found." << endl;
+ cerr << "\t\t- Overlaps restricted by -f and -r." << endl << endl;
+
+ cerr << "\t-c\t" << "For each entry in A, report the number of overlaps with B." << endl;
+ cerr << "\t\t- Reports 0 for A entries that have no overlap with B." << endl;
+ cerr << "\t\t- Overlaps restricted by -f and -r." << endl << endl;
+
+ cerr << "\t-v\t" << "Only report those entries in A that have _no overlaps_ with B." << endl;
+ cerr << "\t\t- Similar to \"grep -v\" (an homage)." << endl << endl;
+
+ cerr << "\t-f\t" << "Minimum overlap required as a fraction of A." << endl;
+ cerr << "\t\t- Default is 1E-9 (i.e., 1bp)." << endl;
+ cerr << "\t\t- FLOAT (e.g. 0.50)" << endl << endl;
+
+ cerr << "\t-r\t" << "Require that the fraction overlap be reciprocal for A and B." << endl;
+ cerr << "\t\t- In other words, if -f is 0.90 and -r is used, this requires" << endl;
+ cerr << "\t\t that B overlap 90% of A and A _also_ overlaps 90% of B." << endl << endl;
+
+ cerr << "\t-s\t" << "Force strandedness. That is, only report hits in B that" << endl;
+ cerr << "\t\toverlap A on the same strand." << endl;
+ cerr << "\t\t- By default, overlaps are reported without respect to strand." << endl << endl;
+
+ cerr << "\t-split\t" << "Treat \"split\" BAM or BED12 entries as distinct BED intervals." << endl << endl;
+
+
+ // end the program here
+ exit(1);
}
diff --git a/src/linksBed/linksBed.cpp b/src/linksBed/linksBed.cpp
index 3c0173e0ad6cf613d57d029ee0401ada4ad5e4ba..bf1a74c8891ad606f9e3e283ec229a38abd5824f 100644
--- a/src/linksBed/linksBed.cpp
+++ b/src/linksBed/linksBed.cpp
@@ -16,14 +16,14 @@
// Constructor
//
BedLinks::BedLinks(string &bedFile, string &base, string &org, string &db) {
- _bedFile = bedFile;
- _bed = new BedFile(bedFile);
-
- _base = base;
- _org = org;
- _db = db;
-
- CreateLinks();
+ _bedFile = bedFile;
+ _bed = new BedFile(bedFile);
+
+ _base = base;
+ _org = org;
+ _db = db;
+
+ CreateLinks();
}
//
@@ -35,88 +35,88 @@ BedLinks::~BedLinks(void) {
void BedLinks::WriteURL(BED &bed, string &base) {
- string position = bed.chrom;
- std::stringstream posStream;
- posStream << ":" << bed.start << "-" << bed.end;
- position.append(posStream.str());
-
- cout << "<tr>" << endl;
- cout << "\t<td>" << endl;
- cout << "\t\t<a href=" << base << position << ">";
- cout << bed.chrom << ":" << bed.start << "-" << bed.end;
- cout << "</a>" << endl;
- cout << "\t</td>" << endl;
-
- if (_bed->bedType == 4) {
- cout << "\t<td>" << endl;
- cout << bed.name << endl;
- cout << "\t</td>" << endl;
- }
- else if (_bed->bedType == 5) {
- cout << "\t<td>" << endl;
- cout << bed.name << endl;
- cout << "\t</td>" << endl;
-
- cout << "\t<td>" << endl;
- cout << bed.score << endl;
- cout << "\t</td>" << endl;
- }
- else if ((_bed->bedType == 6) || (_bed->bedType == 9) || (_bed->bedType == 12)) {
- cout << "\t<td>" << endl;
- cout << bed.name << endl;
- cout << "\t</td>" << endl;
-
- cout << "\t<td>" << endl;
- cout << bed.score << endl;
- cout << "\t</td>" << endl;
-
- cout << "\t<td>" << endl;
- cout << bed.strand << endl;
- cout << "\t</td>" << endl;
- }
- cout << "</tr>" << endl;
+ string position = bed.chrom;
+ std::stringstream posStream;
+ posStream << ":" << bed.start << "-" << bed.end;
+ position.append(posStream.str());
+
+ cout << "<tr>" << endl;
+ cout << "\t<td>" << endl;
+ cout << "\t\t<a href=" << base << position << ">";
+ cout << bed.chrom << ":" << bed.start << "-" << bed.end;
+ cout << "</a>" << endl;
+ cout << "\t</td>" << endl;
+
+ if (_bed->bedType == 4) {
+ cout << "\t<td>" << endl;
+ cout << bed.name << endl;
+ cout << "\t</td>" << endl;
+ }
+ else if (_bed->bedType == 5) {
+ cout << "\t<td>" << endl;
+ cout << bed.name << endl;
+ cout << "\t</td>" << endl;
+
+ cout << "\t<td>" << endl;
+ cout << bed.score << endl;
+ cout << "\t</td>" << endl;
+ }
+ else if ((_bed->bedType == 6) || (_bed->bedType == 9) || (_bed->bedType == 12)) {
+ cout << "\t<td>" << endl;
+ cout << bed.name << endl;
+ cout << "\t</td>" << endl;
+
+ cout << "\t<td>" << endl;
+ cout << bed.score << endl;
+ cout << "\t</td>" << endl;
+
+ cout << "\t<td>" << endl;
+ cout << bed.strand << endl;
+ cout << "\t</td>" << endl;
+ }
+ cout << "</tr>" << endl;
}
void BedLinks::CreateLinks() {
- // construct the html base.
- string org = _org;
- string db = _db;
- string base = _base;
- base.append("/cgi-bin/hgTracks?org=");
- base.append(org);
- base.append("&db=");
- base.append(db);
- base.append("&position=");
-
- // create the HTML header
- cout << "<html>" << endl <<"\t<body>" << endl;
- cout << "<title>" << _bedFile << "</title>" << endl;
-
- // start the table of entries
- cout << "<br>Firefox users: Press and hold the \"apple\" or \"alt\" key and click link to open in new tab." << endl;
- cout << "<p style=\"font-family:courier\">" << endl;
- cout << "<table border=\"0\" align=\"justify\"" << endl;
- cout << "<h3>BED Entries from: stdin </h3>" << endl;
-
- int lineNum = 0;
- BED bedEntry, nullBed;
- BedLineStatus bedStatus;
-
- _bed->Open();
- while ((bedStatus = _bed->GetNextBed(bedEntry, lineNum)) != BED_INVALID) {
- if (bedStatus == BED_VALID) {
- WriteURL(bedEntry, base);
- bedEntry = nullBed;
- }
- }
- _bed->Close();
-
- cout << "</table>" << endl;
- cout << "</p>" << endl;
- cout << "\t</body>" << endl <<"</html>" << endl;
+ // construct the html base.
+ string org = _org;
+ string db = _db;
+ string base = _base;
+ base.append("/cgi-bin/hgTracks?org=");
+ base.append(org);
+ base.append("&db=");
+ base.append(db);
+ base.append("&position=");
+
+ // create the HTML header
+ cout << "<html>" << endl <<"\t<body>" << endl;
+ cout << "<title>" << _bedFile << "</title>" << endl;
+
+ // start the table of entries
+ cout << "<br>Firefox users: Press and hold the \"apple\" or \"alt\" key and click link to open in new tab." << endl;
+ cout << "<p style=\"font-family:courier\">" << endl;
+ cout << "<table border=\"0\" align=\"justify\"" << endl;
+ cout << "<h3>BED Entries from: stdin </h3>" << endl;
+
+ int lineNum = 0;
+ BED bedEntry, nullBed;
+ BedLineStatus bedStatus;
+
+ _bed->Open();
+ while ((bedStatus = _bed->GetNextBed(bedEntry, lineNum)) != BED_INVALID) {
+ if (bedStatus == BED_VALID) {
+ WriteURL(bedEntry, base);
+ bedEntry = nullBed;
+ }
+ }
+ _bed->Close();
+
+ cout << "</table>" << endl;
+ cout << "</p>" << endl;
+ cout << "\t</body>" << endl <<"</html>" << endl;
}
diff --git a/src/linksBed/linksBed.h b/src/linksBed/linksBed.h
index 4d812239419d91eb1fd37b651464778914bf3f0b..941c2e9290329976c17d0b810018eb4543c42a22 100644
--- a/src/linksBed/linksBed.h
+++ b/src/linksBed/linksBed.h
@@ -24,21 +24,21 @@ class BedLinks {
public:
- // constructor
- BedLinks(string &bedFile, string &base, string &org, string &db);
-
- // destructor
- ~BedLinks(void);
-
-private:
- string _bedFile;
- string _base;
- string _org;
- string _db;
-
- // instance of a bed file class.
- BedFile *_bed;
-
- void WriteURL(BED &bed, string &base);
- void CreateLinks(); // the default. sorts by chrom (asc.) then by start (asc.)
+ // constructor
+ BedLinks(string &bedFile, string &base, string &org, string &db);
+
+ // destructor
+ ~BedLinks(void);
+
+private:
+ string _bedFile;
+ string _base;
+ string _org;
+ string _db;
+
+ // instance of a bed file class.
+ BedFile *_bed;
+
+ void WriteURL(BED &bed, string &base);
+ void CreateLinks(); // the default. sorts by chrom (asc.) then by start (asc.)
};
diff --git a/src/linksBed/linksMain.cpp b/src/linksBed/linksMain.cpp
index 2bc1822d62fb0b60593dd891148fe80505c98168..f4e5500d68686694b9262285f43d9608bf05828c 100644
--- a/src/linksBed/linksMain.cpp
+++ b/src/linksBed/linksMain.cpp
@@ -26,104 +26,104 @@ void ShowHelp(void);
int main(int argc, char* argv[]) {
- // our configuration variables
- bool showHelp = false;
-
- // input files
- string bedFile = "stdin";
- bool haveBed = true;
-
- /* Defaults for everyone else */
- string org = "human";
- string db = "hg18";
- string base = "http://genome.ucsc.edu";
-
- for(int i = 1; i < argc; i++) {
- int parameterLength = (int)strlen(argv[i]);
-
- if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
- (PARAMETER_CHECK("--help", 5, parameterLength))) {
- showHelp = true;
- }
- }
-
- if(showHelp) ShowHelp();
-
- // do some parsing (all of these parameters require 2 strings)
- for(int i = 1; i < argc; i++) {
-
- int parameterLength = (int)strlen(argv[i]);
-
- if(PARAMETER_CHECK("-i", 2, parameterLength)) {
- if ((i+1) < argc) {
- bedFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-base", 5, parameterLength)) {
- if ((i+1) < argc) {
- base = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-org", 4, parameterLength)) {
- if ((i+1) < argc) {
- org = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-db", 3, parameterLength)) {
- if ((i+1) < argc) {
- db = argv[i + 1];
- i++;
- }
- }
- else {
- cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
- showHelp = true;
- }
- }
-
- // make sure we have both input files
- if (!haveBed) {
- cerr << endl << "*****" << endl << "*****ERROR: Need -i BED file. " << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (!showHelp) {
- BedLinks *bl = new BedLinks(bedFile, base, org, db);
- delete bl;
- return 0;
- }
- else {
- ShowHelp();
- }
+ // our configuration variables
+ bool showHelp = false;
+
+ // input files
+ string bedFile = "stdin";
+ bool haveBed = true;
+
+ /* Defaults for everyone else */
+ string org = "human";
+ string db = "hg18";
+ string base = "http://genome.ucsc.edu";
+
+ for(int i = 1; i < argc; i++) {
+ int parameterLength = (int)strlen(argv[i]);
+
+ if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
+ (PARAMETER_CHECK("--help", 5, parameterLength))) {
+ showHelp = true;
+ }
+ }
+
+ if(showHelp) ShowHelp();
+
+ // do some parsing (all of these parameters require 2 strings)
+ for(int i = 1; i < argc; i++) {
+
+ int parameterLength = (int)strlen(argv[i]);
+
+ if(PARAMETER_CHECK("-i", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ bedFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-base", 5, parameterLength)) {
+ if ((i+1) < argc) {
+ base = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-org", 4, parameterLength)) {
+ if ((i+1) < argc) {
+ org = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-db", 3, parameterLength)) {
+ if ((i+1) < argc) {
+ db = argv[i + 1];
+ i++;
+ }
+ }
+ else {
+ cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
+ showHelp = true;
+ }
+ }
+
+ // make sure we have both input files
+ if (!haveBed) {
+ cerr << endl << "*****" << endl << "*****ERROR: Need -i BED file. " << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (!showHelp) {
+ BedLinks *bl = new BedLinks(bedFile, base, org, db);
+ delete bl;
+ return 0;
+ }
+ else {
+ ShowHelp();
+ }
}
void ShowHelp(void) {
- cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
-
- cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
-
- cerr << "Summary: Creates HTML links to an UCSC Genome Browser from a feature file." << endl << endl;
- cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -i <bed/gff/vcf> > out.html" << endl << endl;
-
- cerr << "Options: " << endl;
- cerr << "\t-base\t" << "The browser basename. Default: http://genome.ucsc.edu " << endl;
- cerr << "\t-org\t" << "The organism. Default: human" << endl;
- cerr << "\t-db\t" << "The build. Default: hg18" << endl << endl;
-
- cerr << "Example: " << endl;
- cerr << "\t" << "By default, the links created will point to human (hg18) UCSC browser." << endl;
- cerr << "\tIf you have a local mirror, you can override this behavior by supplying" << endl;
- cerr << "\tthe -base, -org, and -db options." << endl << endl;
- cerr << "\t" << "For example, if the URL of your local mirror for mouse MM9 is called: " << endl;
- cerr << "\thttp://mymirror.myuniversity.edu, then you would use the following:" << endl;
- cerr << "\t" << "-base http://mymirror.myuniversity.edu" << endl;
- cerr << "\t" << "-org mouse" << endl;
- cerr << "\t" << "-db mm9" << endl;
-
-
- exit(1);
+ cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
+
+ cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
+
+ cerr << "Summary: Creates HTML links to an UCSC Genome Browser from a feature file." << endl << endl;
+ cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -i <bed/gff/vcf> > out.html" << endl << endl;
+
+ cerr << "Options: " << endl;
+ cerr << "\t-base\t" << "The browser basename. Default: http://genome.ucsc.edu " << endl;
+ cerr << "\t-org\t" << "The organism. Default: human" << endl;
+ cerr << "\t-db\t" << "The build. Default: hg18" << endl << endl;
+
+ cerr << "Example: " << endl;
+ cerr << "\t" << "By default, the links created will point to human (hg18) UCSC browser." << endl;
+ cerr << "\tIf you have a local mirror, you can override this behavior by supplying" << endl;
+ cerr << "\tthe -base, -org, and -db options." << endl << endl;
+ cerr << "\t" << "For example, if the URL of your local mirror for mouse MM9 is called: " << endl;
+ cerr << "\thttp://mymirror.myuniversity.edu, then you would use the following:" << endl;
+ cerr << "\t" << "-base http://mymirror.myuniversity.edu" << endl;
+ cerr << "\t" << "-org mouse" << endl;
+ cerr << "\t" << "-db mm9" << endl;
+
+
+ exit(1);
}
diff --git a/src/maskFastaFromBed/maskFastaFromBed.cpp b/src/maskFastaFromBed/maskFastaFromBed.cpp
index 66e3df11a7d55b7e21be1ee33f6761a13337a059..654ff6dbcd28abb1c14babc67ca241864f4a46cf 100644
--- a/src/maskFastaFromBed/maskFastaFromBed.cpp
+++ b/src/maskFastaFromBed/maskFastaFromBed.cpp
@@ -15,20 +15,20 @@
MaskFastaFromBed::MaskFastaFromBed(string &fastaInFile, string &bedFile, string &fastaOutFile, bool &softMask) {
- _softMask = false;
- if (softMask) {
- _softMask = true;
- }
-
- _fastaInFile = fastaInFile;
- _bedFile = bedFile;
- _fastaOutFile = fastaOutFile;
-
- _bed = new BedFile(_bedFile);
-
- _bed->loadBedFileIntoMapNoBin();
-
- MaskFasta();
+ _softMask = false;
+ if (softMask) {
+ _softMask = true;
+ }
+
+ _fastaInFile = fastaInFile;
+ _bedFile = bedFile;
+ _fastaOutFile = fastaOutFile;
+
+ _bed = new BedFile(_bedFile);
+
+ _bed->loadBedFileIntoMapNoBin();
+
+ MaskFasta();
}
@@ -41,119 +41,119 @@ MaskFastaFromBed::~MaskFastaFromBed(void) {
//******************************************************************************
void MaskFastaFromBed::MaskFasta() {
- /* Make sure that we can open all of the files successfully*/
-
- // open the fasta database for reading
- ifstream fa(_fastaInFile.c_str(), ios::in);
- if ( !fa ) {
- cerr << "Error: The requested fasta file (" << _fastaInFile << ") could not be opened. Exiting!" << endl;
- exit (1);
- }
-
- // open the fasta database for reading
- ofstream faOut(_fastaOutFile.c_str(), ios::out);
- if ( !faOut ) {
- cerr << "Error: The requested fasta output file (" << _fastaOutFile << ") could not be opened. Exiting!" << endl;
- exit (1);
- }
-
-
- /* Read the fastaDb chromosome by chromosome*/
- string fastaInLine;
- string currChrom;
- string currDNA = "";
- currDNA.reserve(500000000);
- int fastaWidth = -1;
- bool widthSet = false;
- int start, end, length;
- string replacement;
-
- while (getline(fa,fastaInLine)) {
-
- if (fastaInLine.find(">",0) != 0 ) {
- if (widthSet == false) {
- fastaWidth = fastaInLine.size();
- widthSet = true;
- }
- currDNA += fastaInLine;
- }
- else {
- if (currDNA.size() > 0) {
-
- vector<BED> bedList = _bed->bedMapNoBin[currChrom];
-
- /*
- loop through each BED entry for this chrom and
- mask the requested sequence in the FASTA file.
- */
- for (unsigned int i = 0; i < bedList.size(); i++) {
- start = bedList[i].start;
- end = bedList[i].end;
- length = end - start;
-
- /*
- (1) if soft masking, extract the sequence, lowercase it,
- then put it back
- (2) otherwise replace with Ns
- */
- if (_softMask) {
- replacement = currDNA.substr(start, length);
- toLowerCase(replacement);
- currDNA.replace(start, length, replacement);
- }
- else {
- string hardmask(length, 'N');
- currDNA.replace(start, length, hardmask);
- }
- }
- // write the masked chrom to the output file
- PrettyPrintChrom(faOut, currChrom, currDNA, fastaWidth);
- }
-
- // reset for the next chromosome.
- currChrom = fastaInLine.substr(1, fastaInLine.find_first_of(" ")-1);
- currDNA = "";
- }
- }
-
- // process the last chromosome.
- // exact same logic as in the main loop.
- if (currDNA.size() > 0) {
-
- vector<BED> bedList = _bed->bedMapNoBin[currChrom];
-
- for (unsigned int i = 0; i < bedList.size(); i++) {
- start = bedList[i].start;
- end = bedList[i].end;
- length = end - start;
-
- if (_softMask) {
- replacement = currDNA.substr(start, length);
- toLowerCase(replacement);
- currDNA.replace(start, length, replacement);
- }
- else {
- string hardmask(length, 'N');
- currDNA.replace(start, length, hardmask);
- }
- }
- PrettyPrintChrom(faOut, currChrom, currDNA, fastaWidth);
- }
-
- // closed for business.
- fa.close();
- faOut.close();
+ /* Make sure that we can open all of the files successfully*/
+
+ // open the fasta database for reading
+ ifstream fa(_fastaInFile.c_str(), ios::in);
+ if ( !fa ) {
+ cerr << "Error: The requested fasta file (" << _fastaInFile << ") could not be opened. Exiting!" << endl;
+ exit (1);
+ }
+
+ // open the fasta database for reading
+ ofstream faOut(_fastaOutFile.c_str(), ios::out);
+ if ( !faOut ) {
+ cerr << "Error: The requested fasta output file (" << _fastaOutFile << ") could not be opened. Exiting!" << endl;
+ exit (1);
+ }
+
+
+ /* Read the fastaDb chromosome by chromosome*/
+ string fastaInLine;
+ string currChrom;
+ string currDNA = "";
+ currDNA.reserve(500000000);
+ int fastaWidth = -1;
+ bool widthSet = false;
+ int start, end, length;
+ string replacement;
+
+ while (getline(fa,fastaInLine)) {
+
+ if (fastaInLine.find(">",0) != 0 ) {
+ if (widthSet == false) {
+ fastaWidth = fastaInLine.size();
+ widthSet = true;
+ }
+ currDNA += fastaInLine;
+ }
+ else {
+ if (currDNA.size() > 0) {
+
+ vector<BED> bedList = _bed->bedMapNoBin[currChrom];
+
+ /*
+ loop through each BED entry for this chrom and
+ mask the requested sequence in the FASTA file.
+ */
+ for (unsigned int i = 0; i < bedList.size(); i++) {
+ start = bedList[i].start;
+ end = bedList[i].end;
+ length = end - start;
+
+ /*
+ (1) if soft masking, extract the sequence, lowercase it,
+ then put it back
+ (2) otherwise replace with Ns
+ */
+ if (_softMask) {
+ replacement = currDNA.substr(start, length);
+ toLowerCase(replacement);
+ currDNA.replace(start, length, replacement);
+ }
+ else {
+ string hardmask(length, 'N');
+ currDNA.replace(start, length, hardmask);
+ }
+ }
+ // write the masked chrom to the output file
+ PrettyPrintChrom(faOut, currChrom, currDNA, fastaWidth);
+ }
+
+ // reset for the next chromosome.
+ currChrom = fastaInLine.substr(1, fastaInLine.find_first_of(" ")-1);
+ currDNA = "";
+ }
+ }
+
+ // process the last chromosome.
+ // exact same logic as in the main loop.
+ if (currDNA.size() > 0) {
+
+ vector<BED> bedList = _bed->bedMapNoBin[currChrom];
+
+ for (unsigned int i = 0; i < bedList.size(); i++) {
+ start = bedList[i].start;
+ end = bedList[i].end;
+ length = end - start;
+
+ if (_softMask) {
+ replacement = currDNA.substr(start, length);
+ toLowerCase(replacement);
+ currDNA.replace(start, length, replacement);
+ }
+ else {
+ string hardmask(length, 'N');
+ currDNA.replace(start, length, hardmask);
+ }
+ }
+ PrettyPrintChrom(faOut, currChrom, currDNA, fastaWidth);
+ }
+
+ // closed for business.
+ fa.close();
+ faOut.close();
}
void MaskFastaFromBed::PrettyPrintChrom(ofstream &out, string chrom, const string &sequence, int width) {
-
- int seqLength = sequence.size();
-
- out << ">" << chrom << endl;
- for(int i = 0; i < seqLength; i += width) {
- if (i + width < seqLength) out << sequence.substr(i, width) << endl;
- else out << sequence.substr(i, seqLength-i) << endl;
- }
+
+ int seqLength = sequence.size();
+
+ out << ">" << chrom << endl;
+ for(int i = 0; i < seqLength; i += width) {
+ if (i + width < seqLength) out << sequence.substr(i, width) << endl;
+ else out << sequence.substr(i, seqLength-i) << endl;
+ }
}
diff --git a/src/maskFastaFromBed/maskFastaFromBed.h b/src/maskFastaFromBed/maskFastaFromBed.h
index bfeb383abc9deaec0490a5ffe72a79dd9c97baa0..1b7a3590b2722285ad11ae14eaaccb8dee2ed2ea 100644
--- a/src/maskFastaFromBed/maskFastaFromBed.h
+++ b/src/maskFastaFromBed/maskFastaFromBed.h
@@ -16,7 +16,7 @@
#include <vector>
#include <iostream>
#include <fstream>
-#include <cctype> /* for tolower */
+#include <cctype> /* for tolower */
using namespace std;
@@ -26,28 +26,28 @@ using namespace std;
class MaskFastaFromBed {
public:
-
- // constructor
- MaskFastaFromBed(string &fastaInFile, string &bedFile, string &fastaOutFile, bool &softMask);
- // destructor
- ~MaskFastaFromBed(void);
+ // constructor
+ MaskFastaFromBed(string &fastaInFile, string &bedFile, string &fastaOutFile, bool &softMask);
+
+ // destructor
+ ~MaskFastaFromBed(void);
+
-
private:
-
- bool _softMask;
-
- string _fastaInFile;
- string _bedFile;
- string _fastaOutFile;
-
- // instance of a bed file class.
- BedFile *_bed;
-
- void MaskFasta();
-
- void PrettyPrintChrom(ofstream &out, string chrom, const string &sequence, int width);
+
+ bool _softMask;
+
+ string _fastaInFile;
+ string _bedFile;
+ string _fastaOutFile;
+
+ // instance of a bed file class.
+ BedFile *_bed;
+
+ void MaskFasta();
+
+ void PrettyPrintChrom(ofstream &out, string chrom, const string &sequence, int width);
};
diff --git a/src/maskFastaFromBed/maskFastaFromBedMain.cpp b/src/maskFastaFromBed/maskFastaFromBedMain.cpp
index b48dcb217a088e5616c0f3d3eef3743119de6e49..0978436d9d5e05f01dc3fe48aa2fcc5809bfa05b 100644
--- a/src/maskFastaFromBed/maskFastaFromBedMain.cpp
+++ b/src/maskFastaFromBed/maskFastaFromBedMain.cpp
@@ -26,106 +26,106 @@ void ShowHelp(void);
int main(int argc, char* argv[]) {
- // our configuration variables
- bool showHelp = false;
-
- // input files
- string fastaInFile;
- string bedFile;
-
- // output files
- string fastaOutFile;
-
- // checks for existence of parameters
- bool haveFastaIn = false;
- bool haveBed = false;
- bool haveFastaOut = false;
- bool softMask = false;
-
- // check to see if we should print out some help
- if(argc <= 1) showHelp = true;
-
- for(int i = 1; i < argc; i++) {
- int parameterLength = (int)strlen(argv[i]);
-
- if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
- (PARAMETER_CHECK("--help", 5, parameterLength))) {
- showHelp = true;
- }
- }
-
- if(showHelp) ShowHelp();
-
- // do some parsing (all of these parameters require 2 strings)
- for(int i = 1; i < argc; i++) {
-
- int parameterLength = (int)strlen(argv[i]);
-
- if(PARAMETER_CHECK("-fi", 3, parameterLength)) {
- if ((i+1) < argc) {
- haveFastaIn = true;
- fastaInFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-fo", 3, parameterLength)) {
- if ((i+1) < argc) {
- haveFastaOut = true;
- fastaOutFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-bed", 4, parameterLength)) {
- if ((i+1) < argc) {
- haveBed = true;
- bedFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-soft", 5, parameterLength)) {
- softMask = true;
- }
- else {
- cerr << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
- showHelp = true;
- }
- }
-
- if (!haveFastaIn || !haveFastaOut || !haveBed) {
- showHelp = true;
- }
-
- if (!showHelp) {
-
- MaskFastaFromBed *maskFasta = new MaskFastaFromBed(fastaInFile, bedFile, fastaOutFile, softMask);
- delete maskFasta;
- return 0;
- }
- else {
- ShowHelp();
- }
+ // our configuration variables
+ bool showHelp = false;
+
+ // input files
+ string fastaInFile;
+ string bedFile;
+
+ // output files
+ string fastaOutFile;
+
+ // checks for existence of parameters
+ bool haveFastaIn = false;
+ bool haveBed = false;
+ bool haveFastaOut = false;
+ bool softMask = false;
+
+ // check to see if we should print out some help
+ if(argc <= 1) showHelp = true;
+
+ for(int i = 1; i < argc; i++) {
+ int parameterLength = (int)strlen(argv[i]);
+
+ if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
+ (PARAMETER_CHECK("--help", 5, parameterLength))) {
+ showHelp = true;
+ }
+ }
+
+ if(showHelp) ShowHelp();
+
+ // do some parsing (all of these parameters require 2 strings)
+ for(int i = 1; i < argc; i++) {
+
+ int parameterLength = (int)strlen(argv[i]);
+
+ if(PARAMETER_CHECK("-fi", 3, parameterLength)) {
+ if ((i+1) < argc) {
+ haveFastaIn = true;
+ fastaInFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-fo", 3, parameterLength)) {
+ if ((i+1) < argc) {
+ haveFastaOut = true;
+ fastaOutFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-bed", 4, parameterLength)) {
+ if ((i+1) < argc) {
+ haveBed = true;
+ bedFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-soft", 5, parameterLength)) {
+ softMask = true;
+ }
+ else {
+ cerr << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
+ showHelp = true;
+ }
+ }
+
+ if (!haveFastaIn || !haveFastaOut || !haveBed) {
+ showHelp = true;
+ }
+
+ if (!showHelp) {
+
+ MaskFastaFromBed *maskFasta = new MaskFastaFromBed(fastaInFile, bedFile, fastaOutFile, softMask);
+ delete maskFasta;
+ return 0;
+ }
+ else {
+ ShowHelp();
+ }
}
void ShowHelp(void) {
-
- cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
-
- cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
-
- cerr << "Summary: Mask a fasta file based on feature coordinates." << endl << endl;
- cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -fi <fasta> -out <fasta> -bed <bed/gff/vcf>" << endl << endl;
+ cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
- cerr << "Options:" << endl;
- cerr << "\t-fi\tInput FASTA file" << endl;
- cerr << "\t-bed\tBED/GFF/VCF file of ranges to mask in -fi" << endl;
- cerr << "\t-fo\tOutput FASTA file" << endl;
- cerr << "\t-soft\tEnforce \"soft\" masking. That is, instead of masking with Ns," << endl;
- cerr << "\t\tmask with lower-case bases." << endl;
+ cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
+
+ cerr << "Summary: Mask a fasta file based on feature coordinates." << endl << endl;
+
+ cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -fi <fasta> -out <fasta> -bed <bed/gff/vcf>" << endl << endl;
+
+ cerr << "Options:" << endl;
+ cerr << "\t-fi\tInput FASTA file" << endl;
+ cerr << "\t-bed\tBED/GFF/VCF file of ranges to mask in -fi" << endl;
+ cerr << "\t-fo\tOutput FASTA file" << endl;
+ cerr << "\t-soft\tEnforce \"soft\" masking. That is, instead of masking with Ns," << endl;
+ cerr << "\t\tmask with lower-case bases." << endl;
+
+ // end the program here
+ exit(1);
- // end the program here
- exit(1);
-
}
diff --git a/src/mergeBed/mergeBed.cpp b/src/mergeBed/mergeBed.cpp
index acaff78c574c43aa7d6ba3088ca6d2722056f1e6..4cb56e762780a87a2a40d12ec073787226b40877 100644
--- a/src/mergeBed/mergeBed.cpp
+++ b/src/mergeBed/mergeBed.cpp
@@ -14,14 +14,14 @@
void ReportMergedNames(const map<string, bool> &names) {
- unsigned int n = 0;
- map<string, bool>::const_iterator nameItr = names.begin();
- map<string, bool>::const_iterator nameEnd = names.end();
- for (; nameItr != nameEnd; ++nameItr) {
- if (n < (names.size() - 1)) {cout << nameItr->first << ";";}
- else {cout << nameItr->first;}
- n++;
- }
+ unsigned int n = 0;
+ map<string, bool>::const_iterator nameItr = names.begin();
+ map<string, bool>::const_iterator nameEnd = names.end();
+ for (; nameItr != nameEnd; ++nameItr) {
+ if (n < (names.size() - 1)) {cout << nameItr->first << ";";}
+ else {cout << nameItr->first;}
+ n++;
+ }
}
// ===============
@@ -29,18 +29,18 @@ void ReportMergedNames(const map<string, bool> &names) {
// ===============
BedMerge::BedMerge(string &bedFile, bool &numEntries, int &maxDistance, bool &forceStrand, bool &reportNames) {
- _bedFile = bedFile;
- _numEntries = numEntries;
- _maxDistance = -1 * maxDistance;
- _forceStrand = forceStrand;
- _reportNames = reportNames;
-
- _bed = new BedFile(bedFile);
-
- if (_forceStrand == false)
- MergeBed();
- else
- MergeBedStranded();
+ _bedFile = bedFile;
+ _numEntries = numEntries;
+ _maxDistance = -1 * maxDistance;
+ _forceStrand = forceStrand;
+ _reportNames = reportNames;
+
+ _bed = new BedFile(bedFile);
+
+ if (_forceStrand == false)
+ MergeBed();
+ else
+ MergeBedStranded();
}
@@ -56,117 +56,117 @@ BedMerge::~BedMerge(void) {
// =====================================================
void BedMerge::MergeBed() {
- // load the "B" bed file into a map so
- // that we can easily compare "A" to it for overlaps
- _bed->loadBedFileIntoMapNoBin();
-
- // loop through each chromosome and merge their BED entries
- for (masterBedMapNoBin::iterator m = _bed->bedMapNoBin.begin(); m != _bed->bedMapNoBin.end(); ++m) {
-
- // bedList is already sorted by start position.
- vector<BED> bedList = m->second;
-
- CHRPOS minStart = INT_MAX;
- CHRPOS maxEnd = 0;
- bool OIP = false; // OIP = Overlap In Progress. Lame, I realize.
- int prev = -1;
- unsigned int curr = 0;
- int mergeCount = 1;
- map<string, bool> names;
-
- // loop through the BED entries for this chromosome
- // and look for overlaps
- for (curr = 0; curr < bedList.size(); ++curr) {
-
- // make sure prev points to an actual element
- if (prev < 0) {
- prev = curr;
- continue;
- }
-
- // Is there an overlap between the current and previous entries?
- if ( overlaps(bedList[prev].start, bedList[prev].end,
- bedList[curr].start, bedList[curr].end) >= _maxDistance) {
- OIP = true;
- mergeCount++;
- minStart = min(bedList[prev].start, min(minStart, bedList[curr].start));
- maxEnd = max(bedList[prev].end, max(maxEnd, bedList[curr].end));
-
- names[bedList[prev].name] = true;
- names[bedList[curr].name] = true;
- }
- else if ( overlaps(minStart, maxEnd,
- bedList[curr].start, bedList[curr].end) >= _maxDistance) {
- mergeCount++;
- minStart = min(minStart, bedList[curr].start);
- maxEnd = max(maxEnd, bedList[curr].end);
- names[bedList[curr].name] = true;
- }
- else {
- // was there an overlap befor the current entry broke it?
- if (OIP) {
- if (_numEntries) {
- cout << bedList[prev].chrom << "\t" << minStart << "\t" << maxEnd << "\t" << mergeCount << endl;
- }
- else if (_reportNames) {
- cout << bedList[prev].chrom << "\t" << minStart << "\t" << maxEnd << "\t";
- ReportMergedNames(names);
- cout << endl;
- }
- else {
- cout << bedList[prev].chrom << "\t" << minStart << "\t" << maxEnd << endl;
- }
- }
- else {
- if (_numEntries) {
- cout << bedList[prev].chrom << "\t" << bedList[prev].start << "\t" << bedList[prev].end << "\t" << mergeCount << endl;
- }
- else if (_reportNames) {
- cout << bedList[prev].chrom << "\t" << bedList[prev].start << "\t" << bedList[prev].end << "\t" << bedList[prev].name << endl;
- }
- else {
- cout << bedList[prev].chrom << "\t" << bedList[prev].start << "\t" << bedList[prev].end << endl;
- }
- }
-
- // reset things for the next overlapping "block"
- OIP = false;
- mergeCount = 1;
- minStart = INT_MAX;
- maxEnd = 0;
-
- names.clear();
- names[bedList[curr].name] = true;
- }
- prev = curr;
- }
-
- // clean up based on the last entry for the current chromosome
- if (OIP) {
- if (_numEntries) {
- cout << bedList[prev].chrom << "\t" << minStart << "\t" << maxEnd << "\t" << mergeCount << endl;
- }
- else if (_reportNames) {
- cout << bedList[prev].chrom << "\t" << minStart << "\t" << maxEnd << "\t";
- ReportMergedNames(names);
- cout << endl;
- }
- else {
- cout << bedList[prev].chrom << "\t" << minStart << "\t" << maxEnd << endl;
- }
- }
- else {
- if (_numEntries) {
- cout << bedList[prev].chrom << "\t" << bedList[prev].start << "\t" << bedList[prev].end << "\t" << mergeCount << endl;
- }
- else if (_reportNames) {
- cout << bedList[prev].chrom << "\t" << bedList[prev].start << "\t" << bedList[prev].end << "\t" << bedList[prev].name << endl;
- }
- else {
- cout << bedList[prev].chrom << "\t" << bedList[prev].start << "\t" << bedList[prev].end << endl;
- }
- }
- }
+ // load the "B" bed file into a map so
+ // that we can easily compare "A" to it for overlaps
+ _bed->loadBedFileIntoMapNoBin();
+
+ // loop through each chromosome and merge their BED entries
+ for (masterBedMapNoBin::iterator m = _bed->bedMapNoBin.begin(); m != _bed->bedMapNoBin.end(); ++m) {
+
+ // bedList is already sorted by start position.
+ vector<BED> bedList = m->second;
+
+ CHRPOS minStart = INT_MAX;
+ CHRPOS maxEnd = 0;
+ bool OIP = false; // OIP = Overlap In Progress. Lame, I realize.
+ int prev = -1;
+ unsigned int curr = 0;
+ int mergeCount = 1;
+ map<string, bool> names;
+
+ // loop through the BED entries for this chromosome
+ // and look for overlaps
+ for (curr = 0; curr < bedList.size(); ++curr) {
+
+ // make sure prev points to an actual element
+ if (prev < 0) {
+ prev = curr;
+ continue;
+ }
+
+ // Is there an overlap between the current and previous entries?
+ if ( overlaps(bedList[prev].start, bedList[prev].end,
+ bedList[curr].start, bedList[curr].end) >= _maxDistance) {
+ OIP = true;
+ mergeCount++;
+ minStart = min(bedList[prev].start, min(minStart, bedList[curr].start));
+ maxEnd = max(bedList[prev].end, max(maxEnd, bedList[curr].end));
+
+ names[bedList[prev].name] = true;
+ names[bedList[curr].name] = true;
+ }
+ else if ( overlaps(minStart, maxEnd,
+ bedList[curr].start, bedList[curr].end) >= _maxDistance) {
+ mergeCount++;
+ minStart = min(minStart, bedList[curr].start);
+ maxEnd = max(maxEnd, bedList[curr].end);
+ names[bedList[curr].name] = true;
+ }
+ else {
+ // was there an overlap befor the current entry broke it?
+ if (OIP) {
+ if (_numEntries) {
+ cout << bedList[prev].chrom << "\t" << minStart << "\t" << maxEnd << "\t" << mergeCount << endl;
+ }
+ else if (_reportNames) {
+ cout << bedList[prev].chrom << "\t" << minStart << "\t" << maxEnd << "\t";
+ ReportMergedNames(names);
+ cout << endl;
+ }
+ else {
+ cout << bedList[prev].chrom << "\t" << minStart << "\t" << maxEnd << endl;
+ }
+ }
+ else {
+ if (_numEntries) {
+ cout << bedList[prev].chrom << "\t" << bedList[prev].start << "\t" << bedList[prev].end << "\t" << mergeCount << endl;
+ }
+ else if (_reportNames) {
+ cout << bedList[prev].chrom << "\t" << bedList[prev].start << "\t" << bedList[prev].end << "\t" << bedList[prev].name << endl;
+ }
+ else {
+ cout << bedList[prev].chrom << "\t" << bedList[prev].start << "\t" << bedList[prev].end << endl;
+ }
+ }
+
+ // reset things for the next overlapping "block"
+ OIP = false;
+ mergeCount = 1;
+ minStart = INT_MAX;
+ maxEnd = 0;
+
+ names.clear();
+ names[bedList[curr].name] = true;
+ }
+ prev = curr;
+ }
+
+ // clean up based on the last entry for the current chromosome
+ if (OIP) {
+ if (_numEntries) {
+ cout << bedList[prev].chrom << "\t" << minStart << "\t" << maxEnd << "\t" << mergeCount << endl;
+ }
+ else if (_reportNames) {
+ cout << bedList[prev].chrom << "\t" << minStart << "\t" << maxEnd << "\t";
+ ReportMergedNames(names);
+ cout << endl;
+ }
+ else {
+ cout << bedList[prev].chrom << "\t" << minStart << "\t" << maxEnd << endl;
+ }
+ }
+ else {
+ if (_numEntries) {
+ cout << bedList[prev].chrom << "\t" << bedList[prev].start << "\t" << bedList[prev].end << "\t" << mergeCount << endl;
+ }
+ else if (_reportNames) {
+ cout << bedList[prev].chrom << "\t" << bedList[prev].start << "\t" << bedList[prev].end << "\t" << bedList[prev].name << endl;
+ }
+ else {
+ cout << bedList[prev].chrom << "\t" << bedList[prev].start << "\t" << bedList[prev].end << endl;
+ }
+ }
+ }
}
@@ -175,140 +175,140 @@ void BedMerge::MergeBed() {
// ==================================================================================
void BedMerge::MergeBedStranded() {
- // load the "B" bed file into a map so
- // that we can easily compare "A" to it for overlaps
- _bed->loadBedFileIntoMapNoBin();
+ // load the "B" bed file into a map so
+ // that we can easily compare "A" to it for overlaps
+ _bed->loadBedFileIntoMapNoBin();
- // loop through each chromosome and merge their BED entries
- masterBedMapNoBin::const_iterator m = _bed->bedMapNoBin.begin();
- masterBedMapNoBin::const_iterator mEnd = _bed->bedMapNoBin.end();
+ // loop through each chromosome and merge their BED entries
+ masterBedMapNoBin::const_iterator m = _bed->bedMapNoBin.begin();
+ masterBedMapNoBin::const_iterator mEnd = _bed->bedMapNoBin.end();
for (; m != mEnd; ++m) {
- // bedList is already sorted by start position.
- vector<BED> bedList = m->second;
-
- // make a list of the two strands to merge separately.
- vector<string> strands(2);
- strands[0] = "+";
- strands[1] = "-";
-
- // do two passes, one for each strand.
- for (unsigned int s = 0; s < strands.size(); s++) {
-
- CHRPOS minStart = INT_MAX;
- CHRPOS maxEnd = 0;
- bool OIP = false; // OIP = Overlap In Progress. Lame, I realize.
- int prev = -1;
- unsigned int curr = 0;
- int mergeCount = 1;
- int numOnStrand = 0;
- map<string, bool> names;
-
- // loop through the BED entries for this chromosome
- // and look for overlaps
- for (curr = 0; curr < bedList.size(); ++curr) {
-
- // if forcing strandedness, move on if the hit
- // is not on the current strand.
-
- if (bedList[curr].strand != strands[s]) {
- continue; // continue force the next iteration of the for loop.
- }
- else {
- numOnStrand++;
- }
-
- // make sure prev points to an actual element on the
- // current strand
- if (prev < 0) {
- if (bedList[curr].strand == strands[s]) {
- prev = curr;
- }
- continue;
- }
-
- if ( overlaps(bedList[prev].start, bedList[prev].end,
- bedList[curr].start, bedList[curr].end) >= _maxDistance) {
- OIP = true;
- mergeCount++;
- minStart = min(bedList[prev].start, min(minStart, bedList[curr].start));
- maxEnd = max(bedList[prev].end, max(maxEnd, bedList[curr].end));
-
- names[bedList[prev].name] = true;
- names[bedList[curr].name] = true;
- }
- else if ( overlaps(minStart, maxEnd,
- bedList[curr].start, bedList[curr].end) >= _maxDistance) {
- mergeCount++;
- minStart = min(minStart, bedList[curr].start);
- maxEnd = max(maxEnd, bedList[curr].end);
- names[bedList[curr].name] = true;
- }
- else {
-
- // was there an overlap before the current entry broke it?
- if (OIP) {
- if (_numEntries) {
- cout << bedList[prev].chrom << "\t" << minStart << "\t" << maxEnd << "\t" << mergeCount << "\t" << strands[s] << endl;
- }
- else if (_reportNames) {
- cout << bedList[prev].chrom << "\t" << minStart << "\t" << maxEnd << "\t";
- ReportMergedNames(names);
- cout << "\t" << strands[s] << endl;
- }
- else {
- cout << bedList[prev].chrom << "\t" << minStart << "\t" << maxEnd << "\t" << strands[s] << endl;
- }
- }
- else {
- if ((_numEntries) && (numOnStrand > 0)) {
- cout << bedList[prev].chrom << "\t" << bedList[prev].start << "\t" << bedList[prev].end << "\t" << mergeCount << "\t" << strands[s] << endl;
- }
- else if (_reportNames) {
- cout << bedList[prev].chrom << "\t" << bedList[prev].start << "\t" << bedList[prev].end << "\t" << bedList[prev].name << "\t" << strands[s] << endl;
- }
- else if (numOnStrand > 0) {
- cout << bedList[prev].chrom << "\t" << bedList[prev].start << "\t" << bedList[prev].end << "\t" << strands[s] << endl;
- }
- }
-
- // reset things for the next overlapping "block"
- OIP = false;
- mergeCount = 1;
- minStart = INT_MAX;
- maxEnd = 0;
- names.clear();
-
- // add the name of the current element in prep for the next block
- names[bedList[curr].name] = true;
- }
- prev = curr;
- }
-
- // clean up based on the last entry for the current chromosome
- if (OIP) {
- if (_numEntries) {
- cout << bedList[prev].chrom << "\t" << minStart << "\t" << maxEnd << "\t" << mergeCount << "\t" << strands[s] << endl;
- }
- else if (_reportNames) {
- cout << bedList[prev].chrom << "\t" << minStart << "\t" << maxEnd << "\t";
- ReportMergedNames(names);
- cout << "\t" << strands[s] << endl;
- }
- else {
- cout << bedList[prev].chrom << "\t" << minStart << "\t" << maxEnd << "\t" << strands[s] << endl;
- }
- }
- else {
- if ((_numEntries) && (numOnStrand > 0)) {
- cout << bedList[prev].chrom << "\t" << bedList[prev].start << "\t" << bedList[prev].end << "\t" << mergeCount << "\t" << strands[s] << endl;
- }
- else if ((_reportNames) && (numOnStrand > 0)) {
- cout << bedList[prev].chrom << "\t" << bedList[prev].start << "\t" << bedList[prev].end << "\t" << bedList[prev].name << "\t" << strands[s] << endl;
- }
- else if (numOnStrand > 0) {
- cout << bedList[prev].chrom << "\t" << bedList[prev].start << "\t" << bedList[prev].end << "\t" << strands[s] << endl;
- }
- }
- }
- }
+ // bedList is already sorted by start position.
+ vector<BED> bedList = m->second;
+
+ // make a list of the two strands to merge separately.
+ vector<string> strands(2);
+ strands[0] = "+";
+ strands[1] = "-";
+
+ // do two passes, one for each strand.
+ for (unsigned int s = 0; s < strands.size(); s++) {
+
+ CHRPOS minStart = INT_MAX;
+ CHRPOS maxEnd = 0;
+ bool OIP = false; // OIP = Overlap In Progress. Lame, I realize.
+ int prev = -1;
+ unsigned int curr = 0;
+ int mergeCount = 1;
+ int numOnStrand = 0;
+ map<string, bool> names;
+
+ // loop through the BED entries for this chromosome
+ // and look for overlaps
+ for (curr = 0; curr < bedList.size(); ++curr) {
+
+ // if forcing strandedness, move on if the hit
+ // is not on the current strand.
+
+ if (bedList[curr].strand != strands[s]) {
+ continue; // continue force the next iteration of the for loop.
+ }
+ else {
+ numOnStrand++;
+ }
+
+ // make sure prev points to an actual element on the
+ // current strand
+ if (prev < 0) {
+ if (bedList[curr].strand == strands[s]) {
+ prev = curr;
+ }
+ continue;
+ }
+
+ if ( overlaps(bedList[prev].start, bedList[prev].end,
+ bedList[curr].start, bedList[curr].end) >= _maxDistance) {
+ OIP = true;
+ mergeCount++;
+ minStart = min(bedList[prev].start, min(minStart, bedList[curr].start));
+ maxEnd = max(bedList[prev].end, max(maxEnd, bedList[curr].end));
+
+ names[bedList[prev].name] = true;
+ names[bedList[curr].name] = true;
+ }
+ else if ( overlaps(minStart, maxEnd,
+ bedList[curr].start, bedList[curr].end) >= _maxDistance) {
+ mergeCount++;
+ minStart = min(minStart, bedList[curr].start);
+ maxEnd = max(maxEnd, bedList[curr].end);
+ names[bedList[curr].name] = true;
+ }
+ else {
+
+ // was there an overlap before the current entry broke it?
+ if (OIP) {
+ if (_numEntries) {
+ cout << bedList[prev].chrom << "\t" << minStart << "\t" << maxEnd << "\t" << mergeCount << "\t" << strands[s] << endl;
+ }
+ else if (_reportNames) {
+ cout << bedList[prev].chrom << "\t" << minStart << "\t" << maxEnd << "\t";
+ ReportMergedNames(names);
+ cout << "\t" << strands[s] << endl;
+ }
+ else {
+ cout << bedList[prev].chrom << "\t" << minStart << "\t" << maxEnd << "\t" << strands[s] << endl;
+ }
+ }
+ else {
+ if ((_numEntries) && (numOnStrand > 0)) {
+ cout << bedList[prev].chrom << "\t" << bedList[prev].start << "\t" << bedList[prev].end << "\t" << mergeCount << "\t" << strands[s] << endl;
+ }
+ else if (_reportNames) {
+ cout << bedList[prev].chrom << "\t" << bedList[prev].start << "\t" << bedList[prev].end << "\t" << bedList[prev].name << "\t" << strands[s] << endl;
+ }
+ else if (numOnStrand > 0) {
+ cout << bedList[prev].chrom << "\t" << bedList[prev].start << "\t" << bedList[prev].end << "\t" << strands[s] << endl;
+ }
+ }
+
+ // reset things for the next overlapping "block"
+ OIP = false;
+ mergeCount = 1;
+ minStart = INT_MAX;
+ maxEnd = 0;
+ names.clear();
+
+ // add the name of the current element in prep for the next block
+ names[bedList[curr].name] = true;
+ }
+ prev = curr;
+ }
+
+ // clean up based on the last entry for the current chromosome
+ if (OIP) {
+ if (_numEntries) {
+ cout << bedList[prev].chrom << "\t" << minStart << "\t" << maxEnd << "\t" << mergeCount << "\t" << strands[s] << endl;
+ }
+ else if (_reportNames) {
+ cout << bedList[prev].chrom << "\t" << minStart << "\t" << maxEnd << "\t";
+ ReportMergedNames(names);
+ cout << "\t" << strands[s] << endl;
+ }
+ else {
+ cout << bedList[prev].chrom << "\t" << minStart << "\t" << maxEnd << "\t" << strands[s] << endl;
+ }
+ }
+ else {
+ if ((_numEntries) && (numOnStrand > 0)) {
+ cout << bedList[prev].chrom << "\t" << bedList[prev].start << "\t" << bedList[prev].end << "\t" << mergeCount << "\t" << strands[s] << endl;
+ }
+ else if ((_reportNames) && (numOnStrand > 0)) {
+ cout << bedList[prev].chrom << "\t" << bedList[prev].start << "\t" << bedList[prev].end << "\t" << bedList[prev].name << "\t" << strands[s] << endl;
+ }
+ else if (numOnStrand > 0) {
+ cout << bedList[prev].chrom << "\t" << bedList[prev].start << "\t" << bedList[prev].end << "\t" << strands[s] << endl;
+ }
+ }
+ }
+ }
}
diff --git a/src/mergeBed/mergeBed.h b/src/mergeBed/mergeBed.h
index 4567865a581e10a4f90bb06531afb297486c0ec9..37b721565bd39a87a62542f117aea9561e2a9c66 100644
--- a/src/mergeBed/mergeBed.h
+++ b/src/mergeBed/mergeBed.h
@@ -28,7 +28,7 @@ class BedMerge {
public:
- // constructor
+ // constructor
BedMerge(string &bedFile, bool &numEntries, int &maxDistance, bool &forceStrand, bool &reportNames);
// destructor
@@ -38,13 +38,13 @@ public:
void MergeBedStranded();
private:
-
- string _bedFile;
- bool _numEntries;
- bool _forceStrand;
- bool _reportNames;
- int _maxDistance;
- // instance of a bed file class.
- BedFile *_bed;
+
+ string _bedFile;
+ bool _numEntries;
+ bool _forceStrand;
+ bool _reportNames;
+ int _maxDistance;
+ // instance of a bed file class.
+ BedFile *_bed;
};
diff --git a/src/mergeBed/mergeMain.cpp b/src/mergeBed/mergeMain.cpp
index e730d627d67087c710d18da569bb4eb4f9ca2ddb..c756e38a09e50675f3dcad982fe137c2b03d121d 100644
--- a/src/mergeBed/mergeMain.cpp
+++ b/src/mergeBed/mergeMain.cpp
@@ -26,112 +26,112 @@ void ShowHelp(void);
int main(int argc, char* argv[]) {
- // our configuration variables
- bool showHelp = false;
-
- // input files
- string bedFile = "stdin";
- int maxDistance = 0;
-
- // input arguments
- bool haveBed = true;
- bool numEntries = false;
- bool haveMaxDistance = false;
- bool forceStrand = false;
- bool reportNames = false;
-
- for(int i = 1; i < argc; i++) {
- int parameterLength = (int)strlen(argv[i]);
-
- if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
- (PARAMETER_CHECK("--help", 5, parameterLength))) {
- showHelp = true;
- }
- }
-
- if(showHelp) ShowHelp();
-
- // do some parsing (all of these parameters require 2 strings)
- for(int i = 1; i < argc; i++) {
-
- int parameterLength = (int)strlen(argv[i]);
-
- if(PARAMETER_CHECK("-i", 2, parameterLength)) {
- if ((i+1) < argc) {
- bedFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-n", 2, parameterLength)) {
- numEntries = true;
- }
- else if(PARAMETER_CHECK("-d", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveMaxDistance = true;
- maxDistance = atoi(argv[i + 1]);
- i++;
- }
- }
- else if (PARAMETER_CHECK("-s", 2, parameterLength)) {
- forceStrand = true;
- }
- else if (PARAMETER_CHECK("-nms", 4, parameterLength)) {
- reportNames = true;
- }
- else {
- cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
- showHelp = true;
- }
- }
-
- // make sure we have both input files
- if (!haveBed) {
- cerr << endl << "*****" << endl << "*****ERROR: Need -i BED file. " << endl << "*****" << endl;
- showHelp = true;
- }
- if (reportNames && numEntries) {
- cerr << endl << "*****" << endl << "*****ERROR: Request either -n OR -nms, not both." << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (!showHelp) {
- BedMerge *bm = new BedMerge(bedFile, numEntries, maxDistance, forceStrand, reportNames);
- delete bm;
- return 0;
- }
- else {
- ShowHelp();
- }
+ // our configuration variables
+ bool showHelp = false;
+
+ // input files
+ string bedFile = "stdin";
+ int maxDistance = 0;
+
+ // input arguments
+ bool haveBed = true;
+ bool numEntries = false;
+ bool haveMaxDistance = false;
+ bool forceStrand = false;
+ bool reportNames = false;
+
+ for(int i = 1; i < argc; i++) {
+ int parameterLength = (int)strlen(argv[i]);
+
+ if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
+ (PARAMETER_CHECK("--help", 5, parameterLength))) {
+ showHelp = true;
+ }
+ }
+
+ if(showHelp) ShowHelp();
+
+ // do some parsing (all of these parameters require 2 strings)
+ for(int i = 1; i < argc; i++) {
+
+ int parameterLength = (int)strlen(argv[i]);
+
+ if(PARAMETER_CHECK("-i", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ bedFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-n", 2, parameterLength)) {
+ numEntries = true;
+ }
+ else if(PARAMETER_CHECK("-d", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveMaxDistance = true;
+ maxDistance = atoi(argv[i + 1]);
+ i++;
+ }
+ }
+ else if (PARAMETER_CHECK("-s", 2, parameterLength)) {
+ forceStrand = true;
+ }
+ else if (PARAMETER_CHECK("-nms", 4, parameterLength)) {
+ reportNames = true;
+ }
+ else {
+ cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
+ showHelp = true;
+ }
+ }
+
+ // make sure we have both input files
+ if (!haveBed) {
+ cerr << endl << "*****" << endl << "*****ERROR: Need -i BED file. " << endl << "*****" << endl;
+ showHelp = true;
+ }
+ if (reportNames && numEntries) {
+ cerr << endl << "*****" << endl << "*****ERROR: Request either -n OR -nms, not both." << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (!showHelp) {
+ BedMerge *bm = new BedMerge(bedFile, numEntries, maxDistance, forceStrand, reportNames);
+ delete bm;
+ return 0;
+ }
+ else {
+ ShowHelp();
+ }
}
void ShowHelp(void) {
- cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
-
- cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
-
- cerr << "Summary: Merges overlapping BED/GFF/VCF entries into a single interval." << endl << endl;
+ cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
- cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -i <bed/gff/vcf>" << endl << endl;
+ cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
- cerr << "Options: " << endl;
- cerr << "\t-s\t" << "Force strandedness. That is, only merge features" << endl;
- cerr << "\t\tthat are the same strand." << endl;
- cerr << "\t\t- By default, merging is done without respect to strand." << endl << endl;
+ cerr << "Summary: Merges overlapping BED/GFF/VCF entries into a single interval." << endl << endl;
- cerr << "\t-n\t" << "Report the number of BED entries that were merged." << endl;
- cerr << "\t\t- Note: \"1\" is reported if no merging occurred." << endl << endl;
+ cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -i <bed/gff/vcf>" << endl << endl;
+ cerr << "Options: " << endl;
+ cerr << "\t-s\t" << "Force strandedness. That is, only merge features" << endl;
+ cerr << "\t\tthat are the same strand." << endl;
+ cerr << "\t\t- By default, merging is done without respect to strand." << endl << endl;
- cerr << "\t-d\t" << "Maximum distance between features allowed for features" << endl;
- cerr << "\t\tto be merged." << endl;
- cerr << "\t\t- Def. 0. That is, overlapping & book-ended features are merged." << endl;
- cerr << "\t\t- (INTEGER)" << endl << endl;
-
- cerr << "\t-nms\t" << "Report the names of the merged features separated by semicolons." << endl << endl;
-
+ cerr << "\t-n\t" << "Report the number of BED entries that were merged." << endl;
+ cerr << "\t\t- Note: \"1\" is reported if no merging occurred." << endl << endl;
- // end the program here
- exit(1);
+
+ cerr << "\t-d\t" << "Maximum distance between features allowed for features" << endl;
+ cerr << "\t\tto be merged." << endl;
+ cerr << "\t\t- Def. 0. That is, overlapping & book-ended features are merged." << endl;
+ cerr << "\t\t- (INTEGER)" << endl << endl;
+
+ cerr << "\t-nms\t" << "Report the names of the merged features separated by semicolons." << endl << endl;
+
+
+ // end the program here
+ exit(1);
}
diff --git a/src/overlap/overlap.cpp b/src/overlap/overlap.cpp
index c7024f63545aa1c8c8e35cd00d4dd0caa12492f0..63ef656911ef9ae238217058b0bd4020e66bbaba 100644
--- a/src/overlap/overlap.cpp
+++ b/src/overlap/overlap.cpp
@@ -34,169 +34,169 @@ void ComputeOverlaps(istream &input, short &s1Col, short &e1Col, short &s2Col, s
int main(int argc, char* argv[]) {
- // input files
- string inFile = "stdin";
- string columns;
-
- // our configuration variables
- bool showHelp = false;
- bool haveInFile = true;
- bool haveColumns = false;
-
-
- for(int i = 1; i < argc; i++) {
- int parameterLength = (int)strlen(argv[i]);
-
- if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
- (PARAMETER_CHECK("--help", 5, parameterLength))) {
- showHelp = true;
- }
- }
-
- if(showHelp) ShowHelp();
-
- // do some parsing (all of these parameters require 2 strings)
- for(int i = 1; i < argc; i++) {
-
- int parameterLength = (int)strlen(argv[i]);
-
- if(PARAMETER_CHECK("-i", 2, parameterLength)) {
- if ((i+1) < argc) {
- inFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-cols", 5, parameterLength)) {
- haveColumns = true;
- columns = argv[i + 1];
- i++;
- }
- else {
- cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
- showHelp = true;
- }
- }
-
- // make sure we have an input files
- if (!haveInFile ) {
- cerr << endl << "*****" << endl << "*****ERROR: Need -i file. " << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (!showHelp) {
-
- // Split the column string sent by the user into discrete column numbers
- // A comma separated string is expected.
- vector<string> posColumns;
- Tokenize(columns, posColumns, ",");
-
- if (posColumns.size() != 4) {
- cerr << endl << "*****" << endl << "*****ERROR: Please specify 4, comma-separated position columns. " << endl << "*****" << endl;
- ShowHelp();
- }
- else {
- short s1, e1, s2, e2;
- s1 = atoi(posColumns[0].c_str());
- e1 = atoi(posColumns[1].c_str());
- s2 = atoi(posColumns[2].c_str());
- e2 = atoi(posColumns[3].c_str());
-
- DetermineInput(inFile, s1, e1, s2, e2);
- }
- }
- else {
- ShowHelp();
- }
+ // input files
+ string inFile = "stdin";
+ string columns;
+
+ // our configuration variables
+ bool showHelp = false;
+ bool haveInFile = true;
+ bool haveColumns = false;
+
+
+ for(int i = 1; i < argc; i++) {
+ int parameterLength = (int)strlen(argv[i]);
+
+ if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
+ (PARAMETER_CHECK("--help", 5, parameterLength))) {
+ showHelp = true;
+ }
+ }
+
+ if(showHelp) ShowHelp();
+
+ // do some parsing (all of these parameters require 2 strings)
+ for(int i = 1; i < argc; i++) {
+
+ int parameterLength = (int)strlen(argv[i]);
+
+ if(PARAMETER_CHECK("-i", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ inFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-cols", 5, parameterLength)) {
+ haveColumns = true;
+ columns = argv[i + 1];
+ i++;
+ }
+ else {
+ cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
+ showHelp = true;
+ }
+ }
+
+ // make sure we have an input files
+ if (!haveInFile ) {
+ cerr << endl << "*****" << endl << "*****ERROR: Need -i file. " << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (!showHelp) {
+
+ // Split the column string sent by the user into discrete column numbers
+ // A comma separated string is expected.
+ vector<string> posColumns;
+ Tokenize(columns, posColumns, ",");
+
+ if (posColumns.size() != 4) {
+ cerr << endl << "*****" << endl << "*****ERROR: Please specify 4, comma-separated position columns. " << endl << "*****" << endl;
+ ShowHelp();
+ }
+ else {
+ short s1, e1, s2, e2;
+ s1 = atoi(posColumns[0].c_str());
+ e1 = atoi(posColumns[1].c_str());
+ s2 = atoi(posColumns[2].c_str());
+ e2 = atoi(posColumns[3].c_str());
+
+ DetermineInput(inFile, s1, e1, s2, e2);
+ }
+ }
+ else {
+ ShowHelp();
+ }
}
void ShowHelp(void) {
- cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
-
- cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
-
- cerr << "Summary: Computes the amount of overlap (positive values)" << endl;
- cerr << "\t or distance (negative values) between genome features" << endl;
- cerr << "\t and reports the result at the end of the same line." << endl << endl;
-
- cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -i <input> -cols s1,e1,s2,e2 " << endl << endl;
-
- cerr << "Options: " << endl;
- cerr << "\t-i\t" << "Input file. Use \"stdin\" for pipes." << endl << endl;
-
- cerr << "\t-cols\t" << "Specify the columns (1-based) for the starts and ends of the" << endl;
- cerr << "\t\tfeatures for which you'd like to compute the overlap/distance." << endl;
- cerr << "\t\tThe columns must be listed in the following order: " << endl << endl;
- cerr << "\t\tstart1,end1,start2,end2" << endl << endl;
-
- cerr << "Example: " << endl;
- cerr << "\t$ windowBed -a A.bed -b B.bed -w 10" << endl;
- cerr << "\tchr1 10 20 A chr1 15 25 B" << endl;
- cerr << "\tchr1 10 20 C chr1 25 35 D" << endl << endl;
- cerr << "\t$ windowBed -a A.bed -b B.bed -w 10 | overlap -i stdin -cols 2,3,6,7" << endl;
- cerr << "\tchr1 10 20 A chr1 15 25 B 5" << endl;
- cerr << "\tchr1 10 20 C chr1 25 35 D -5" << endl;
-
- // end the program here
- exit(1);
+ cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
+
+ cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
+
+ cerr << "Summary: Computes the amount of overlap (positive values)" << endl;
+ cerr << "\t or distance (negative values) between genome features" << endl;
+ cerr << "\t and reports the result at the end of the same line." << endl << endl;
+
+ cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -i <input> -cols s1,e1,s2,e2 " << endl << endl;
+
+ cerr << "Options: " << endl;
+ cerr << "\t-i\t" << "Input file. Use \"stdin\" for pipes." << endl << endl;
+
+ cerr << "\t-cols\t" << "Specify the columns (1-based) for the starts and ends of the" << endl;
+ cerr << "\t\tfeatures for which you'd like to compute the overlap/distance." << endl;
+ cerr << "\t\tThe columns must be listed in the following order: " << endl << endl;
+ cerr << "\t\tstart1,end1,start2,end2" << endl << endl;
+
+ cerr << "Example: " << endl;
+ cerr << "\t$ windowBed -a A.bed -b B.bed -w 10" << endl;
+ cerr << "\tchr1 10 20 A chr1 15 25 B" << endl;
+ cerr << "\tchr1 10 20 C chr1 25 35 D" << endl << endl;
+ cerr << "\t$ windowBed -a A.bed -b B.bed -w 10 | overlap -i stdin -cols 2,3,6,7" << endl;
+ cerr << "\tchr1 10 20 A chr1 15 25 B 5" << endl;
+ cerr << "\tchr1 10 20 C chr1 25 35 D -5" << endl;
+
+ // end the program here
+ exit(1);
}
void DetermineInput(string &inFile, short &s1Col, short &e1Col, short &s2Col, short &e2Col) {
-
-
- if (inFile != "stdin") { // process a file
-
- ifstream in(inFile.c_str(), ios::in);
- if ( !in ) {
- cerr << "Error: The requested input file (" << inFile << ") could not be opened. Exiting!" << endl;
- exit (1);
- }
- ComputeOverlaps(in, s1Col, e1Col, s2Col, e2Col);
- }
- else ComputeOverlaps(cin, s1Col, e1Col, s2Col, e2Col);
+
+
+ if (inFile != "stdin") { // process a file
+
+ ifstream in(inFile.c_str(), ios::in);
+ if ( !in ) {
+ cerr << "Error: The requested input file (" << inFile << ") could not be opened. Exiting!" << endl;
+ exit (1);
+ }
+ ComputeOverlaps(in, s1Col, e1Col, s2Col, e2Col);
+ }
+ else ComputeOverlaps(cin, s1Col, e1Col, s2Col, e2Col);
}
-
+
void ComputeOverlaps(istream &input, short &s1Col, short &e1Col, short &s2Col, short &e2Col) {
-
- int lineNum = 0;
- string inLine;
- vector<string> inFields;
-
- int overlap;
-
- char *s1End, *e1End, *s2End, *e2End;
- long s1, e1, s2, e2;
-
- while (getline(input, inLine)) {
- lineNum++;
- Tokenize(inLine, inFields);
-
- if (inFields.size() > 1) {
-
- // test if columns 2 and 3 are integers. If so, assume BED.
- s1 = strtol(inFields[s1Col-1].c_str(), &s1End, 10);
- e1 = strtol(inFields[e1Col-1].c_str(), &e1End, 10);
- s2 = strtol(inFields[s2Col-1].c_str(), &s2End, 10);
- e2 = strtol(inFields[e2Col-1].c_str(), &e2End, 10);
-
- // strtol will set pointers to the start of the string if non-integral, base 10
- // if they all check out, we have valid numeric columns. Otherwise, complain.
- if (s1End != inFields[s1Col-1].c_str() &&
- e1End != inFields[e1Col-1].c_str() &&
- s2End != inFields[s2Col-1].c_str() &&
- e2End != inFields[e2Col-1].c_str()) {
-
- overlap = overlaps(s1, e1, s2, e2);
- printf("%s\t%d\n", inLine.c_str(), overlap);
- }
- else {
- cerr << "One of your columns appears to be non-numeric at line " << lineNum << ". Exiting..." << endl << endl;
- exit(1);
- }
- }
- inFields.clear();
- }
+
+ int lineNum = 0;
+ string inLine;
+ vector<string> inFields;
+
+ int overlap;
+
+ char *s1End, *e1End, *s2End, *e2End;
+ long s1, e1, s2, e2;
+
+ while (getline(input, inLine)) {
+ lineNum++;
+ Tokenize(inLine, inFields);
+
+ if (inFields.size() > 1) {
+
+ // test if columns 2 and 3 are integers. If so, assume BED.
+ s1 = strtol(inFields[s1Col-1].c_str(), &s1End, 10);
+ e1 = strtol(inFields[e1Col-1].c_str(), &e1End, 10);
+ s2 = strtol(inFields[s2Col-1].c_str(), &s2End, 10);
+ e2 = strtol(inFields[e2Col-1].c_str(), &e2End, 10);
+
+ // strtol will set pointers to the start of the string if non-integral, base 10
+ // if they all check out, we have valid numeric columns. Otherwise, complain.
+ if (s1End != inFields[s1Col-1].c_str() &&
+ e1End != inFields[e1Col-1].c_str() &&
+ s2End != inFields[s2Col-1].c_str() &&
+ e2End != inFields[e2Col-1].c_str()) {
+
+ overlap = overlaps(s1, e1, s2, e2);
+ printf("%s\t%d\n", inLine.c_str(), overlap);
+ }
+ else {
+ cerr << "One of your columns appears to be non-numeric at line " << lineNum << ". Exiting..." << endl << endl;
+ exit(1);
+ }
+ }
+ inFields.clear();
+ }
}
diff --git a/src/pairToBed/pairToBed.cpp b/src/pairToBed/pairToBed.cpp
index dcb1245f765234c5ad6cb4cdea32f03a9762aaf8..16227a85f5ef645424c1dea550c3a215d5444b75 100644
--- a/src/pairToBed/pairToBed.cpp
+++ b/src/pairToBed/pairToBed.cpp
@@ -15,49 +15,49 @@
bool IsCorrectMappingForBEDPE (const BamAlignment &bam) {
- if ( (bam.RefID == bam.MateRefID) && (bam.InsertSize > 0) ) {
- return true;
- }
- else if ( (bam.RefID == bam.MateRefID) && (bam.InsertSize == 0) && bam.IsFirstMate() ) {
- return true;
- }
- else if ( (bam.RefID != bam.MateRefID) && bam.IsFirstMate() ) {
- return true;
- }
- else return false;
+ if ( (bam.RefID == bam.MateRefID) && (bam.InsertSize > 0) ) {
+ return true;
+ }
+ else if ( (bam.RefID == bam.MateRefID) && (bam.InsertSize == 0) && bam.IsFirstMate() ) {
+ return true;
+ }
+ else if ( (bam.RefID != bam.MateRefID) && bam.IsFirstMate() ) {
+ return true;
+ }
+ else return false;
}
/*
- Constructor
+ Constructor
*/
-BedIntersectPE::BedIntersectPE(string bedAFilePE, string bedBFile, float overlapFraction,
- string searchType, bool forceStrand, bool bamInput,
- bool bamOutput, bool uncompressedBam, bool useEditDistance) {
-
- _bedAFilePE = bedAFilePE;
- _bedBFile = bedBFile;
- _overlapFraction = overlapFraction;
- _forceStrand = forceStrand;
- _useEditDistance = useEditDistance;
- _searchType = searchType;
- _bamInput = bamInput;
- _bamOutput = bamOutput;
+BedIntersectPE::BedIntersectPE(string bedAFilePE, string bedBFile, float overlapFraction,
+ string searchType, bool forceStrand, bool bamInput,
+ bool bamOutput, bool uncompressedBam, bool useEditDistance) {
+
+ _bedAFilePE = bedAFilePE;
+ _bedBFile = bedBFile;
+ _overlapFraction = overlapFraction;
+ _forceStrand = forceStrand;
+ _useEditDistance = useEditDistance;
+ _searchType = searchType;
+ _bamInput = bamInput;
+ _bamOutput = bamOutput;
_isUncompressedBam = uncompressedBam;
-
- _bedA = new BedFilePE(bedAFilePE);
- _bedB = new BedFile(bedBFile);
-
- if (_bamInput == false)
- IntersectBedPE();
- else
- IntersectBamPE(_bedAFilePE);
+
+ _bedA = new BedFilePE(bedAFilePE);
+ _bedB = new BedFile(bedBFile);
+
+ if (_bamInput == false)
+ IntersectBedPE();
+ else
+ IntersectBamPE(_bedAFilePE);
}
/*
- Destructor
+ Destructor
*/
BedIntersectPE::~BedIntersectPE(void) {
@@ -67,453 +67,453 @@ BedIntersectPE::~BedIntersectPE(void) {
void BedIntersectPE::FindOverlaps(const BEDPE &a, vector<BED> &hits1, vector<BED> &hits2, const string &type) {
- // list of hits on each end of BEDPE
- // that exceed the requested overlap fraction
- vector<BED> qualityHits1;
- vector<BED> qualityHits2;
-
- // count of hits on each end of BEDPE
- // that exceed the requested overlap fraction
- int numOverlapsEnd1 = 0;
- int numOverlapsEnd2 = 0;
-
- // make sure we have a valid chromosome before we search
- if (a.chrom1 != ".") {
- // Find the quality hits between ***end1*** of the BEDPE and the B BED file
- _bedB->FindOverlapsPerBin(a.chrom1, a.start1, a.end1, a.strand1, hits1, _forceStrand);
-
- vector<BED>::const_iterator h = hits1.begin();
- vector<BED>::const_iterator hitsEnd = hits1.end();
- for (; h != hitsEnd; ++h) {
-
- int s = max(a.start1, h->start);
- int e = min(a.end1, h->end);
- int overlapBases = (e - s); // the number of overlapping bases b/w a and b
- int aLength = (a.end1 - a.start1); // the length of a in b.p.
-
- // is there enough overlap relative to the user's request? (default ~ 1bp)
- if ( ( (float) overlapBases / (float) aLength ) >= _overlapFraction ) {
- numOverlapsEnd1++;
-
- if (type == "either") {
- _bedA->reportBedPETab(a);
- _bedB->reportBedNewLine(*h);
- }
- else {
- qualityHits1.push_back(*h);
- }
- }
- }
- }
-
-
- // make sure we have a valid chromosome before we search
- if (a.chrom2 != ".") {
- // Now find the quality hits between ***end2*** of the BEDPE and the B BED file
- _bedB->FindOverlapsPerBin(a.chrom2, a.start2, a.end2, a.strand2, hits2, _forceStrand);
-
- vector<BED>::const_iterator h = hits2.begin();
- vector<BED>::const_iterator hitsEnd = hits2.end();
- for (; h != hitsEnd; ++h) {
-
- int s = max(a.start2, h->start);
- int e = min(a.end2, h->end);
- int overlapBases = (e - s); // the number of overlapping bases b/w a and b
- int aLength = (a.end2 - a.start2); // the length of a in b.p.
-
- // is there enough overlap relative to the user's request? (default ~ 1bp)
- if ( ( (float) overlapBases / (float) aLength ) >= _overlapFraction ) {
- numOverlapsEnd2++;
-
- if (type == "either") {
- _bedA->reportBedPETab(a);
- _bedB->reportBedNewLine(*h);
- }
- else {
- qualityHits2.push_back(*h);
- }
- }
- }
- }
-
- // Now report the hits depending on what the user has requested.
- if (type == "neither") {
- if ( (numOverlapsEnd1 == 0) && (numOverlapsEnd2 == 0) ) {
- _bedA->reportBedPENewLine(a);
- }
- }
- else if (type == "notboth") {
- if ( (numOverlapsEnd1 == 0) && (numOverlapsEnd2 == 0) ) {
- _bedA->reportBedPENewLine(a);
- }
- else if ( (numOverlapsEnd1 > 0) && (numOverlapsEnd2 == 0) ) {
- for (vector<BED>::iterator q = qualityHits1.begin(); q != qualityHits1.end(); ++q) {
- _bedA->reportBedPETab(a);
- _bedB->reportBedNewLine(*q);
- }
- }
- else if ( (numOverlapsEnd1 == 0) && (numOverlapsEnd2 > 0) ) {
- for (vector<BED>::iterator q = qualityHits2.begin(); q != qualityHits2.end(); ++q) {
- _bedA->reportBedPETab(a);
- _bedB->reportBedNewLine(*q);
- }
- }
- }
- else if (type == "xor") {
- if ( (numOverlapsEnd1 > 0) && (numOverlapsEnd2 == 0) ) {
- for (vector<BED>::iterator q = qualityHits1.begin(); q != qualityHits1.end(); ++q) {
- _bedA->reportBedPETab(a);
- _bedB->reportBedNewLine(*q);
- }
- }
- else if ( (numOverlapsEnd1 == 0) && (numOverlapsEnd2 > 0) ) {
- for (vector<BED>::iterator q = qualityHits2.begin(); q != qualityHits2.end(); ++q) {
- _bedA->reportBedPETab(a);
- _bedB->reportBedNewLine(*q);
- }
- }
- }
- else if (type == "both") {
- if ( (numOverlapsEnd1 > 0) && (numOverlapsEnd2 > 0) ) {
- for (vector<BED>::iterator q = qualityHits1.begin(); q != qualityHits1.end(); ++q) {
- _bedA->reportBedPETab(a);
- _bedB->reportBedNewLine(*q);
- }
- for (vector<BED>::iterator q = qualityHits2.begin(); q != qualityHits2.end(); ++q) {
- _bedA->reportBedPETab(a);
- _bedB->reportBedNewLine(*q);
- }
- }
- }
+ // list of hits on each end of BEDPE
+ // that exceed the requested overlap fraction
+ vector<BED> qualityHits1;
+ vector<BED> qualityHits2;
+
+ // count of hits on each end of BEDPE
+ // that exceed the requested overlap fraction
+ int numOverlapsEnd1 = 0;
+ int numOverlapsEnd2 = 0;
+
+ // make sure we have a valid chromosome before we search
+ if (a.chrom1 != ".") {
+ // Find the quality hits between ***end1*** of the BEDPE and the B BED file
+ _bedB->FindOverlapsPerBin(a.chrom1, a.start1, a.end1, a.strand1, hits1, _forceStrand);
+
+ vector<BED>::const_iterator h = hits1.begin();
+ vector<BED>::const_iterator hitsEnd = hits1.end();
+ for (; h != hitsEnd; ++h) {
+
+ int s = max(a.start1, h->start);
+ int e = min(a.end1, h->end);
+ int overlapBases = (e - s); // the number of overlapping bases b/w a and b
+ int aLength = (a.end1 - a.start1); // the length of a in b.p.
+
+ // is there enough overlap relative to the user's request? (default ~ 1bp)
+ if ( ( (float) overlapBases / (float) aLength ) >= _overlapFraction ) {
+ numOverlapsEnd1++;
+
+ if (type == "either") {
+ _bedA->reportBedPETab(a);
+ _bedB->reportBedNewLine(*h);
+ }
+ else {
+ qualityHits1.push_back(*h);
+ }
+ }
+ }
+ }
+
+
+ // make sure we have a valid chromosome before we search
+ if (a.chrom2 != ".") {
+ // Now find the quality hits between ***end2*** of the BEDPE and the B BED file
+ _bedB->FindOverlapsPerBin(a.chrom2, a.start2, a.end2, a.strand2, hits2, _forceStrand);
+
+ vector<BED>::const_iterator h = hits2.begin();
+ vector<BED>::const_iterator hitsEnd = hits2.end();
+ for (; h != hitsEnd; ++h) {
+
+ int s = max(a.start2, h->start);
+ int e = min(a.end2, h->end);
+ int overlapBases = (e - s); // the number of overlapping bases b/w a and b
+ int aLength = (a.end2 - a.start2); // the length of a in b.p.
+
+ // is there enough overlap relative to the user's request? (default ~ 1bp)
+ if ( ( (float) overlapBases / (float) aLength ) >= _overlapFraction ) {
+ numOverlapsEnd2++;
+
+ if (type == "either") {
+ _bedA->reportBedPETab(a);
+ _bedB->reportBedNewLine(*h);
+ }
+ else {
+ qualityHits2.push_back(*h);
+ }
+ }
+ }
+ }
+
+ // Now report the hits depending on what the user has requested.
+ if (type == "neither") {
+ if ( (numOverlapsEnd1 == 0) && (numOverlapsEnd2 == 0) ) {
+ _bedA->reportBedPENewLine(a);
+ }
+ }
+ else if (type == "notboth") {
+ if ( (numOverlapsEnd1 == 0) && (numOverlapsEnd2 == 0) ) {
+ _bedA->reportBedPENewLine(a);
+ }
+ else if ( (numOverlapsEnd1 > 0) && (numOverlapsEnd2 == 0) ) {
+ for (vector<BED>::iterator q = qualityHits1.begin(); q != qualityHits1.end(); ++q) {
+ _bedA->reportBedPETab(a);
+ _bedB->reportBedNewLine(*q);
+ }
+ }
+ else if ( (numOverlapsEnd1 == 0) && (numOverlapsEnd2 > 0) ) {
+ for (vector<BED>::iterator q = qualityHits2.begin(); q != qualityHits2.end(); ++q) {
+ _bedA->reportBedPETab(a);
+ _bedB->reportBedNewLine(*q);
+ }
+ }
+ }
+ else if (type == "xor") {
+ if ( (numOverlapsEnd1 > 0) && (numOverlapsEnd2 == 0) ) {
+ for (vector<BED>::iterator q = qualityHits1.begin(); q != qualityHits1.end(); ++q) {
+ _bedA->reportBedPETab(a);
+ _bedB->reportBedNewLine(*q);
+ }
+ }
+ else if ( (numOverlapsEnd1 == 0) && (numOverlapsEnd2 > 0) ) {
+ for (vector<BED>::iterator q = qualityHits2.begin(); q != qualityHits2.end(); ++q) {
+ _bedA->reportBedPETab(a);
+ _bedB->reportBedNewLine(*q);
+ }
+ }
+ }
+ else if (type == "both") {
+ if ( (numOverlapsEnd1 > 0) && (numOverlapsEnd2 > 0) ) {
+ for (vector<BED>::iterator q = qualityHits1.begin(); q != qualityHits1.end(); ++q) {
+ _bedA->reportBedPETab(a);
+ _bedB->reportBedNewLine(*q);
+ }
+ for (vector<BED>::iterator q = qualityHits2.begin(); q != qualityHits2.end(); ++q) {
+ _bedA->reportBedPETab(a);
+ _bedB->reportBedNewLine(*q);
+ }
+ }
+ }
}
bool BedIntersectPE::FindOneOrMoreOverlaps(const BEDPE &a, const string &type) {
- // flags for the existence of hits on each end of BEDPE
- // that exceed the requested overlap fraction
- bool end1Found = false;
- bool end2Found = false;
-
- // Look for overlaps in end 1 assuming we have an aligned chromosome.
- if (a.chrom1 != ".") {
- end1Found = _bedB->FindOneOrMoreOverlapsPerBin(a.chrom1, a.start1, a.end1, a.strand1,
- _forceStrand, _overlapFraction);
-
- // can we bail out without checking end2?
- if ((type == "either") && (end1Found == true)) return true;
- else if ((type == "neither") && (end1Found == true)) return false;
- else if ((type == "notboth") && (end1Found == false)) return true;
- else if ((type == "both") && (end1Found == false)) return false;
- }
-
- // Now look for overlaps in end 2 assuming we have an aligned chromosome.
- if (a.chrom2 != ".") {
- end2Found = _bedB->FindOneOrMoreOverlapsPerBin(a.chrom2, a.start2, a.end2, a.strand2,
- _forceStrand, _overlapFraction);
-
- if ((type == "either") && (end2Found == true)) return true;
- else if ((type == "neither") && (end2Found == true)) return false;
- else if ((type == "notboth") && (end2Found == false)) return true;
- else if ((type == "both") && (end2Found == false)) return false;
- }
-
- // Now report the hits depending on what the user has requested.
- if (type == "notboth") {
- if ( (end1Found == false) || (end2Found == false) ) return true;
- else return false;
- }
- else if (type == "either") {
- if ( (end1Found == false) && (end2Found == false) ) return false;
- }
- else if (type == "neither") {
- if ( (end1Found == false) && (end2Found == false) ) return true;
- else return false;
- }
- else if (type == "xor") {
- if ( (end1Found == true) && (end2Found == false) ) return true;
- else if ( (end1Found == false) && (end2Found == true) ) return true;
- else return false;
- }
- else if (type == "both") {
- if ( (end1Found == true) && (end2Found == true) ) return true;
- return false;
- }
- return false;
+ // flags for the existence of hits on each end of BEDPE
+ // that exceed the requested overlap fraction
+ bool end1Found = false;
+ bool end2Found = false;
+
+ // Look for overlaps in end 1 assuming we have an aligned chromosome.
+ if (a.chrom1 != ".") {
+ end1Found = _bedB->FindOneOrMoreOverlapsPerBin(a.chrom1, a.start1, a.end1, a.strand1,
+ _forceStrand, _overlapFraction);
+
+ // can we bail out without checking end2?
+ if ((type == "either") && (end1Found == true)) return true;
+ else if ((type == "neither") && (end1Found == true)) return false;
+ else if ((type == "notboth") && (end1Found == false)) return true;
+ else if ((type == "both") && (end1Found == false)) return false;
+ }
+
+ // Now look for overlaps in end 2 assuming we have an aligned chromosome.
+ if (a.chrom2 != ".") {
+ end2Found = _bedB->FindOneOrMoreOverlapsPerBin(a.chrom2, a.start2, a.end2, a.strand2,
+ _forceStrand, _overlapFraction);
+
+ if ((type == "either") && (end2Found == true)) return true;
+ else if ((type == "neither") && (end2Found == true)) return false;
+ else if ((type == "notboth") && (end2Found == false)) return true;
+ else if ((type == "both") && (end2Found == false)) return false;
+ }
+
+ // Now report the hits depending on what the user has requested.
+ if (type == "notboth") {
+ if ( (end1Found == false) || (end2Found == false) ) return true;
+ else return false;
+ }
+ else if (type == "either") {
+ if ( (end1Found == false) && (end2Found == false) ) return false;
+ }
+ else if (type == "neither") {
+ if ( (end1Found == false) && (end2Found == false) ) return true;
+ else return false;
+ }
+ else if (type == "xor") {
+ if ( (end1Found == true) && (end2Found == false) ) return true;
+ else if ( (end1Found == false) && (end2Found == true) ) return true;
+ else return false;
+ }
+ else if (type == "both") {
+ if ( (end1Found == true) && (end2Found == true) ) return true;
+ return false;
+ }
+ return false;
}
void BedIntersectPE::FindSpanningOverlaps(const BEDPE &a, vector<BED> &hits, const string &type) {
- // count of hits on _between_ end of BEDPE
- // that exceed the requested overlap fraction
- int numOverlaps = 0;
- CHRPOS spanStart = 0;
- CHRPOS spanEnd = 0;
- CHRPOS spanLength = 0;
-
- if ((type == "ispan") || (type == "notispan")) {
- spanStart = a.end1;
- spanEnd = a.start2;
- if (a.end1 > a.start2) {
- spanStart = a.end2;
- spanEnd = a.start1;
- }
- }
- else if ((type == "ospan") || (type == "notospan")) {
- spanStart = a.start1;
- spanEnd = a.end2;
- if (a.start1 > a.start2) {
- spanStart = a.start2;
- spanEnd = a.end1;
- }
- }
- spanLength = spanEnd - spanStart;
-
- // get the hits for the span
- _bedB->FindOverlapsPerBin(a.chrom1, spanStart, spanEnd, a.strand1, hits, _forceStrand);
-
- vector<BED>::const_iterator h = hits.begin();
- vector<BED>::const_iterator hitsEnd = hits.end();
- for (; h != hitsEnd; ++h) {
-
- int s = max(spanStart, h->start);
- int e = min(spanEnd, h->end);
- int overlapBases = (e - s); // the number of overlapping bases b/w a and b
- int spanLength = (spanEnd - spanStart); // the length of a in b.p.
-
- // is there enough overlap relative to the user's request? (default ~ 1bp)
- if ( ( (float) overlapBases / (float) spanLength ) >= _overlapFraction ) {
- numOverlaps++;
- if ((type == "ispan") || (type == "ospan")) {
- _bedA->reportBedPETab(a);
- _bedB->reportBedNewLine(*h);
- }
- }
- }
-
- if ( ( (type == "notispan") || (type == "notospan") ) && numOverlaps == 0 ) {
- _bedA->reportBedPENewLine(a);
- }
+ // count of hits on _between_ end of BEDPE
+ // that exceed the requested overlap fraction
+ int numOverlaps = 0;
+ CHRPOS spanStart = 0;
+ CHRPOS spanEnd = 0;
+ CHRPOS spanLength = 0;
+
+ if ((type == "ispan") || (type == "notispan")) {
+ spanStart = a.end1;
+ spanEnd = a.start2;
+ if (a.end1 > a.start2) {
+ spanStart = a.end2;
+ spanEnd = a.start1;
+ }
+ }
+ else if ((type == "ospan") || (type == "notospan")) {
+ spanStart = a.start1;
+ spanEnd = a.end2;
+ if (a.start1 > a.start2) {
+ spanStart = a.start2;
+ spanEnd = a.end1;
+ }
+ }
+ spanLength = spanEnd - spanStart;
+
+ // get the hits for the span
+ _bedB->FindOverlapsPerBin(a.chrom1, spanStart, spanEnd, a.strand1, hits, _forceStrand);
+
+ vector<BED>::const_iterator h = hits.begin();
+ vector<BED>::const_iterator hitsEnd = hits.end();
+ for (; h != hitsEnd; ++h) {
+
+ int s = max(spanStart, h->start);
+ int e = min(spanEnd, h->end);
+ int overlapBases = (e - s); // the number of overlapping bases b/w a and b
+ int spanLength = (spanEnd - spanStart); // the length of a in b.p.
+
+ // is there enough overlap relative to the user's request? (default ~ 1bp)
+ if ( ( (float) overlapBases / (float) spanLength ) >= _overlapFraction ) {
+ numOverlaps++;
+ if ((type == "ispan") || (type == "ospan")) {
+ _bedA->reportBedPETab(a);
+ _bedB->reportBedNewLine(*h);
+ }
+ }
+ }
+
+ if ( ( (type == "notispan") || (type == "notospan") ) && numOverlaps == 0 ) {
+ _bedA->reportBedPENewLine(a);
+ }
}
bool BedIntersectPE::FindOneOrMoreSpanningOverlaps(const BEDPE &a, const string &type) {
- int spanStart = 0;
- int spanEnd = 0;
- int spanLength = 0;
- bool overlapFound;
-
- if ((type == "ispan") || (type == "notispan")) {
- spanStart = a.end1;
- spanEnd = a.start2;
- if (a.end1 > a.start2) {
- spanStart = a.end2;
- spanEnd = a.start1;
- }
- }
- else if ((type == "ospan") || (type == "notospan")) {
- spanStart = a.start1;
- spanEnd = a.end2;
- if (a.start1 > a.start2) {
- spanStart = a.start2;
- spanEnd = a.end1;
- }
- }
- spanLength = spanEnd - spanStart;
-
- overlapFound = _bedB->FindOneOrMoreOverlapsPerBin(a.chrom1, spanStart, spanEnd, a.strand1,
- _forceStrand, _overlapFraction);
-
- return overlapFound;
+ int spanStart = 0;
+ int spanEnd = 0;
+ int spanLength = 0;
+ bool overlapFound;
+
+ if ((type == "ispan") || (type == "notispan")) {
+ spanStart = a.end1;
+ spanEnd = a.start2;
+ if (a.end1 > a.start2) {
+ spanStart = a.end2;
+ spanEnd = a.start1;
+ }
+ }
+ else if ((type == "ospan") || (type == "notospan")) {
+ spanStart = a.start1;
+ spanEnd = a.end2;
+ if (a.start1 > a.start2) {
+ spanStart = a.start2;
+ spanEnd = a.end1;
+ }
+ }
+ spanLength = spanEnd - spanStart;
+
+ overlapFound = _bedB->FindOneOrMoreOverlapsPerBin(a.chrom1, spanStart, spanEnd, a.strand1,
+ _forceStrand, _overlapFraction);
+
+ return overlapFound;
}
void BedIntersectPE::IntersectBedPE() {
- // load the "B" bed file into a map so
- // that we can easily compare "A" to it for overlaps
- _bedB->loadBedFileIntoMap();
-
- int lineNum = 0; // current input line number
- vector<BED> hits, hits1, hits2; // vector of potential hits
-
- // reserve some space
- hits.reserve(100);
- hits1.reserve(100);
- hits2.reserve(100);
-
- BEDPE a, nullBedPE;
- BedLineStatus bedStatus;
-
- _bedA->Open();
- while ((bedStatus = _bedA->GetNextBedPE(a, lineNum)) != BED_INVALID) {
- if (bedStatus == BED_VALID) {
- if ( (_searchType == "ispan") || (_searchType == "ospan") ||
- (_searchType == "notispan") || (_searchType == "notospan") ) {
- if (a.chrom1 == a.chrom2) {
- FindSpanningOverlaps(a, hits, _searchType);
- hits.clear();
- }
- }
- else {
- FindOverlaps(a, hits1, hits2, _searchType);
- hits1.clear();
- hits2.clear();
- }
- a = nullBedPE;
- }
- }
- _bedA->Close();
+ // load the "B" bed file into a map so
+ // that we can easily compare "A" to it for overlaps
+ _bedB->loadBedFileIntoMap();
+
+ int lineNum = 0; // current input line number
+ vector<BED> hits, hits1, hits2; // vector of potential hits
+
+ // reserve some space
+ hits.reserve(100);
+ hits1.reserve(100);
+ hits2.reserve(100);
+
+ BEDPE a, nullBedPE;
+ BedLineStatus bedStatus;
+
+ _bedA->Open();
+ while ((bedStatus = _bedA->GetNextBedPE(a, lineNum)) != BED_INVALID) {
+ if (bedStatus == BED_VALID) {
+ if ( (_searchType == "ispan") || (_searchType == "ospan") ||
+ (_searchType == "notispan") || (_searchType == "notospan") ) {
+ if (a.chrom1 == a.chrom2) {
+ FindSpanningOverlaps(a, hits, _searchType);
+ hits.clear();
+ }
+ }
+ else {
+ FindOverlaps(a, hits1, hits2, _searchType);
+ hits1.clear();
+ hits2.clear();
+ }
+ a = nullBedPE;
+ }
+ }
+ _bedA->Close();
}
void BedIntersectPE::IntersectBamPE(string bamFile) {
-
- // load the "B" bed file into a map so
- // that we can easily compare "A" to it for overlaps
- _bedB->loadBedFileIntoMap();
-
- // open the BAM file
- BamReader reader;
- BamWriter writer;
- reader.Open(bamFile);
-
- // get header & reference information
- string header = reader.GetHeaderText();
- RefVector refs = reader.GetReferenceData();
-
- // open a BAM output to stdout if we are writing BAM
- if (_bamOutput == true) {
- // open our BAM writer
- writer.Open("stdout", header, refs, _isUncompressedBam);
- }
-
- // track the previous and current sequence
- // names so that we can identify blocks of
- // alignments for a given read ID.
- string prevName, currName;
- prevName = currName = "";
-
- vector<BamAlignment> alignments; // vector of BAM alignments for a given ID in a BAM file.
- alignments.reserve(100);
-
- _bedA->bedType = 10; // it's a full BEDPE given it's BAM
-
- // rip through the BAM file and convert each mapped entry to BEDPE
- BamAlignment bam1, bam2;
- while (reader.GetNextAlignment(bam1)) {
- // the alignment must be paired
- if (bam1.IsPaired() == true) {
- // grab the second alignment for the pair.
- reader.GetNextAlignment(bam2);
-
- // require that the alignments are from the same query
- if (bam1.Name == bam2.Name) {
- ProcessBamBlock(bam1, bam2, refs, writer);
- }
- else {
- cerr << "*****ERROR: -bedpe requires BAM to be sorted or grouped by query name. " << endl;
- exit(1);
- }
- }
- }
- // close up
- reader.Close();
- if (_bamOutput == true) {
- writer.Close();
- }
+
+ // load the "B" bed file into a map so
+ // that we can easily compare "A" to it for overlaps
+ _bedB->loadBedFileIntoMap();
+
+ // open the BAM file
+ BamReader reader;
+ BamWriter writer;
+ reader.Open(bamFile);
+
+ // get header & reference information
+ string header = reader.GetHeaderText();
+ RefVector refs = reader.GetReferenceData();
+
+ // open a BAM output to stdout if we are writing BAM
+ if (_bamOutput == true) {
+ // open our BAM writer
+ writer.Open("stdout", header, refs, _isUncompressedBam);
+ }
+
+ // track the previous and current sequence
+ // names so that we can identify blocks of
+ // alignments for a given read ID.
+ string prevName, currName;
+ prevName = currName = "";
+
+ vector<BamAlignment> alignments; // vector of BAM alignments for a given ID in a BAM file.
+ alignments.reserve(100);
+
+ _bedA->bedType = 10; // it's a full BEDPE given it's BAM
+
+ // rip through the BAM file and convert each mapped entry to BEDPE
+ BamAlignment bam1, bam2;
+ while (reader.GetNextAlignment(bam1)) {
+ // the alignment must be paired
+ if (bam1.IsPaired() == true) {
+ // grab the second alignment for the pair.
+ reader.GetNextAlignment(bam2);
+
+ // require that the alignments are from the same query
+ if (bam1.Name == bam2.Name) {
+ ProcessBamBlock(bam1, bam2, refs, writer);
+ }
+ else {
+ cerr << "*****ERROR: -bedpe requires BAM to be sorted or grouped by query name. " << endl;
+ exit(1);
+ }
+ }
+ }
+ // close up
+ reader.Close();
+ if (_bamOutput == true) {
+ writer.Close();
+ }
}
-void BedIntersectPE::ProcessBamBlock (const BamAlignment &bam1, const BamAlignment &bam2,
+void BedIntersectPE::ProcessBamBlock (const BamAlignment &bam1, const BamAlignment &bam2,
const RefVector &refs, BamWriter &writer) {
-
- vector<BED> hits, hits1, hits2; // vector of potential hits
- hits.reserve(1000); // reserve some space
- hits1.reserve(1000);
- hits2.reserve(1000);
-
- bool overlapsFound; // flag to indicate if overlaps were found
-
- if ( (_searchType == "either") || (_searchType == "xor") ||
- (_searchType == "both") || (_searchType == "notboth") ||
- (_searchType == "neither") ) {
-
- // create a new BEDPE feature from the BAM alignments.
- BEDPE a;
- ConvertBamToBedPE(bam1, bam2, refs, a);
- if (_bamOutput == true) { // BAM output
- // write to BAM if correct hits found
- overlapsFound = FindOneOrMoreOverlaps(a, _searchType);
- if (overlapsFound == true) {
- writer.SaveAlignment(bam1);
- writer.SaveAlignment(bam2);
- }
- }
- else { // BEDPE output
- FindOverlaps(a, hits1, hits2, _searchType);
- hits1.clear();
- hits2.clear();
- }
- }
- else if ( (_searchType == "ispan") || (_searchType == "ospan") ) {
- // only look for ispan and ospan when both ends are mapped.
- if (bam1.IsMapped() && bam2.IsMapped()) {
- // only do an inspan or outspan check if the alignment is intrachromosomal
- if (bam1.RefID == bam2.RefID) {
- // create a new BEDPE feature from the BAM alignments.
- BEDPE a;
- ConvertBamToBedPE(bam1, bam2, refs, a);
- if (_bamOutput == true) { // BAM output
- // look for overlaps, and write to BAM if >=1 were found
- overlapsFound = FindOneOrMoreSpanningOverlaps(a, _searchType);
- if (overlapsFound == true) {
- writer.SaveAlignment(bam1);
- writer.SaveAlignment(bam2);
- }
- }
- else { // BEDPE output
- FindSpanningOverlaps(a, hits, _searchType);
- hits.clear();
- }
- }
- }
- }
- else if ( (_searchType == "notispan") || (_searchType == "notospan") ) {
- // only look for notispan and notospan when both ends are mapped.
- if (bam1.IsMapped() && bam2.IsMapped()) {
- // only do an inspan or outspan check if the alignment is intrachromosomal
- if (bam1.RefID == bam2.RefID) {
- // create a new BEDPE feature from the BAM alignments.
- BEDPE a;
- ConvertBamToBedPE(bam1, bam2, refs, a);
- if (_bamOutput == true) { // BAM output
- // write to BAM if there were no overlaps
- overlapsFound = FindOneOrMoreSpanningOverlaps(a, _searchType);
- if (overlapsFound == false) {
- writer.SaveAlignment(bam1);
- writer.SaveAlignment(bam2);
- }
- }
- else { // BEDPE output
- FindSpanningOverlaps(a, hits, _searchType);
- hits.clear();
- }
- }
- // if inter-chromosomal or orphaned, we know it's not ispan and not ospan
- else if (_bamOutput == true) {
- writer.SaveAlignment(bam1);
- writer.SaveAlignment(bam2);
- }
- }
- // if both ends aren't mapped, we know that it's notispan and not ospan
- else if (_bamOutput == true) {
- writer.SaveAlignment(bam1);
- writer.SaveAlignment(bam2);
- }
- }
+
+ vector<BED> hits, hits1, hits2; // vector of potential hits
+ hits.reserve(1000); // reserve some space
+ hits1.reserve(1000);
+ hits2.reserve(1000);
+
+ bool overlapsFound; // flag to indicate if overlaps were found
+
+ if ( (_searchType == "either") || (_searchType == "xor") ||
+ (_searchType == "both") || (_searchType == "notboth") ||
+ (_searchType == "neither") ) {
+
+ // create a new BEDPE feature from the BAM alignments.
+ BEDPE a;
+ ConvertBamToBedPE(bam1, bam2, refs, a);
+ if (_bamOutput == true) { // BAM output
+ // write to BAM if correct hits found
+ overlapsFound = FindOneOrMoreOverlaps(a, _searchType);
+ if (overlapsFound == true) {
+ writer.SaveAlignment(bam1);
+ writer.SaveAlignment(bam2);
+ }
+ }
+ else { // BEDPE output
+ FindOverlaps(a, hits1, hits2, _searchType);
+ hits1.clear();
+ hits2.clear();
+ }
+ }
+ else if ( (_searchType == "ispan") || (_searchType == "ospan") ) {
+ // only look for ispan and ospan when both ends are mapped.
+ if (bam1.IsMapped() && bam2.IsMapped()) {
+ // only do an inspan or outspan check if the alignment is intrachromosomal
+ if (bam1.RefID == bam2.RefID) {
+ // create a new BEDPE feature from the BAM alignments.
+ BEDPE a;
+ ConvertBamToBedPE(bam1, bam2, refs, a);
+ if (_bamOutput == true) { // BAM output
+ // look for overlaps, and write to BAM if >=1 were found
+ overlapsFound = FindOneOrMoreSpanningOverlaps(a, _searchType);
+ if (overlapsFound == true) {
+ writer.SaveAlignment(bam1);
+ writer.SaveAlignment(bam2);
+ }
+ }
+ else { // BEDPE output
+ FindSpanningOverlaps(a, hits, _searchType);
+ hits.clear();
+ }
+ }
+ }
+ }
+ else if ( (_searchType == "notispan") || (_searchType == "notospan") ) {
+ // only look for notispan and notospan when both ends are mapped.
+ if (bam1.IsMapped() && bam2.IsMapped()) {
+ // only do an inspan or outspan check if the alignment is intrachromosomal
+ if (bam1.RefID == bam2.RefID) {
+ // create a new BEDPE feature from the BAM alignments.
+ BEDPE a;
+ ConvertBamToBedPE(bam1, bam2, refs, a);
+ if (_bamOutput == true) { // BAM output
+ // write to BAM if there were no overlaps
+ overlapsFound = FindOneOrMoreSpanningOverlaps(a, _searchType);
+ if (overlapsFound == false) {
+ writer.SaveAlignment(bam1);
+ writer.SaveAlignment(bam2);
+ }
+ }
+ else { // BEDPE output
+ FindSpanningOverlaps(a, hits, _searchType);
+ hits.clear();
+ }
+ }
+ // if inter-chromosomal or orphaned, we know it's not ispan and not ospan
+ else if (_bamOutput == true) {
+ writer.SaveAlignment(bam1);
+ writer.SaveAlignment(bam2);
+ }
+ }
+ // if both ends aren't mapped, we know that it's notispan and not ospan
+ else if (_bamOutput == true) {
+ writer.SaveAlignment(bam1);
+ writer.SaveAlignment(bam2);
+ }
+ }
}
diff --git a/src/pairToBed/pairToBed.h b/src/pairToBed/pairToBed.h
index a52380a05fda11afab1454f4c807b54e57ef622b..d168a236980b1df57f6ad9825a665438a31a5091 100644
--- a/src/pairToBed/pairToBed.h
+++ b/src/pairToBed/pairToBed.h
@@ -41,121 +41,121 @@ class BedIntersectPE {
public:
- // constructor
- BedIntersectPE(string bedAFilePE, string bedBFile, float overlapFraction,
- string searchType, bool forceStrand, bool bamInput, bool bamOutput, bool uncompressedBam, bool useEditDistance);
+ // constructor
+ BedIntersectPE(string bedAFilePE, string bedBFile, float overlapFraction,
+ string searchType, bool forceStrand, bool bamInput, bool bamOutput, bool uncompressedBam, bool useEditDistance);
- // destructor
- ~BedIntersectPE(void);
+ // destructor
+ ~BedIntersectPE(void);
- void FindOverlaps(const BEDPE &, vector<BED> &hits1, vector<BED> &hits2, const string &type);
-
- bool FindOneOrMoreOverlaps(const BEDPE &, const string &type);
+ void FindOverlaps(const BEDPE &, vector<BED> &hits1, vector<BED> &hits2, const string &type);
- void FindSpanningOverlaps(const BEDPE &a, vector<BED> &hits, const string &type);
- bool FindOneOrMoreSpanningOverlaps(const BEDPE &a, const string &type);
+ bool FindOneOrMoreOverlaps(const BEDPE &, const string &type);
+
+ void FindSpanningOverlaps(const BEDPE &a, vector<BED> &hits, const string &type);
+ bool FindOneOrMoreSpanningOverlaps(const BEDPE &a, const string &type);
+
+ void IntersectBedPE();
+ void IntersectBamPE(string bamFile);
+
+ void DetermineBedPEInput();
- void IntersectBedPE();
- void IntersectBamPE(string bamFile);
-
- void DetermineBedPEInput();
-
private:
- string _bedAFilePE;
- string _bedBFile;
- float _overlapFraction;
- string _searchType;
- bool _forceStrand;
- bool _useEditDistance;
- bool _bamInput;
- bool _bamOutput;
- bool _isUncompressedBam;
+ string _bedAFilePE;
+ string _bedBFile;
+ float _overlapFraction;
+ string _searchType;
+ bool _forceStrand;
+ bool _useEditDistance;
+ bool _bamInput;
+ bool _bamOutput;
+ bool _isUncompressedBam;
- // instance of a paired-end bed file class.
- BedFilePE *_bedA;
+ // instance of a paired-end bed file class.
+ BedFilePE *_bedA;
- // instance of a bed file class.
- BedFile *_bedB;
+ // instance of a bed file class.
+ BedFile *_bedB;
- inline
- void ConvertBamToBedPE(const BamAlignment &bam1, const BamAlignment &bam2, const RefVector &refs, BEDPE &a) {
+ inline
+ void ConvertBamToBedPE(const BamAlignment &bam1, const BamAlignment &bam2, const RefVector &refs, BEDPE &a) {
- // initialize BEDPE variables
- a.start1 = a.start2 = a.end1 = a.end2 = -1;
- a.chrom1 = a.chrom2 = ".";
+ // initialize BEDPE variables
+ a.start1 = a.start2 = a.end1 = a.end2 = -1;
+ a.chrom1 = a.chrom2 = ".";
a.strand1 = a.strand2 = '.';
- uint32_t editDistance1, editDistance2;
- editDistance1 = editDistance2 = 0;
-
- // take the qname from end 1.
- a.name = bam1.Name;
-
- // end 1
- if (bam1.IsMapped()) {
- a.chrom1 = refs.at(bam1.RefID).RefName;
- a.start1 = bam1.Position;
- a.end1 = bam1.GetEndPosition();
- a.strand1 = "+";
- if (bam1.IsReverseStrand()) a.strand1 = "-";
-
- // extract the edit distance from the NM tag
- // if possible. otherwise, complain.
- if (_useEditDistance == true) {
- if (bam1.GetTag("NM", editDistance1) == false) {
- cerr << "The edit distance tag (NM) was not found in the BAM file. Please disable -ed. Exiting\n";
- exit(1);
- }
- }
- }
-
- // end 2
- if (bam2.IsMapped()) {
- a.chrom2 = refs.at(bam2.RefID).RefName;
- a.start2 = bam2.Position;
- a.end2 = bam2.GetEndPosition();
- a.strand2 = "+";
- if (bam2.IsReverseStrand()) a.strand2 = "-";
-
- // extract the edit distance from the NM tag
- // if possible. otherwise, complain.
- if (_useEditDistance == true) {
- if (bam2.GetTag("NM", editDistance2) == false) {
- cerr << "The edit distance tag (NM) was not found in the BAM file. Please disable -ed. Exiting\n";
- exit(1);
- }
- }
- }
-
- // swap the ends if necessary
- if ( a.chrom1 > a.chrom2 || ((a.chrom1 == a.chrom2) && (a.start1 > a.start2)) ) {
- swap(a.chrom1, a.chrom2);
- swap(a.start1, a.start2);
- swap(a.end1, a.end2);
- swap(a.strand1, a.strand2);
- }
-
- // compute the minimum mapping quality b/w the two ends of the pair.
- a.score = "0";
- if (_useEditDistance == false) {
- if (bam1.IsMapped() == true && bam2.IsMapped() == true)
- a.score = ToString(min(bam1.MapQuality, bam2.MapQuality));
- }
- // BEDPE using edit distance
- else {
- if (bam1.IsMapped() == true && bam2.IsMapped() == true)
- a.score = ToString((int) (editDistance1 + editDistance2));
- else if (bam1.IsMapped() == true)
- a.score = ToString((int) editDistance1);
- else if (bam2.IsMapped() == true)
- a.score = ToString((int) editDistance2);
- }
- };
-
- inline
- void ProcessBamBlock (const BamAlignment &bam1, const BamAlignment &bam2,
- const RefVector &refs,
- BamWriter &writer);
+ uint32_t editDistance1, editDistance2;
+ editDistance1 = editDistance2 = 0;
+
+ // take the qname from end 1.
+ a.name = bam1.Name;
+
+ // end 1
+ if (bam1.IsMapped()) {
+ a.chrom1 = refs.at(bam1.RefID).RefName;
+ a.start1 = bam1.Position;
+ a.end1 = bam1.GetEndPosition();
+ a.strand1 = "+";
+ if (bam1.IsReverseStrand()) a.strand1 = "-";
+
+ // extract the edit distance from the NM tag
+ // if possible. otherwise, complain.
+ if (_useEditDistance == true) {
+ if (bam1.GetTag("NM", editDistance1) == false) {
+ cerr << "The edit distance tag (NM) was not found in the BAM file. Please disable -ed. Exiting\n";
+ exit(1);
+ }
+ }
+ }
+
+ // end 2
+ if (bam2.IsMapped()) {
+ a.chrom2 = refs.at(bam2.RefID).RefName;
+ a.start2 = bam2.Position;
+ a.end2 = bam2.GetEndPosition();
+ a.strand2 = "+";
+ if (bam2.IsReverseStrand()) a.strand2 = "-";
+
+ // extract the edit distance from the NM tag
+ // if possible. otherwise, complain.
+ if (_useEditDistance == true) {
+ if (bam2.GetTag("NM", editDistance2) == false) {
+ cerr << "The edit distance tag (NM) was not found in the BAM file. Please disable -ed. Exiting\n";
+ exit(1);
+ }
+ }
+ }
+
+ // swap the ends if necessary
+ if ( a.chrom1 > a.chrom2 || ((a.chrom1 == a.chrom2) && (a.start1 > a.start2)) ) {
+ swap(a.chrom1, a.chrom2);
+ swap(a.start1, a.start2);
+ swap(a.end1, a.end2);
+ swap(a.strand1, a.strand2);
+ }
+
+ // compute the minimum mapping quality b/w the two ends of the pair.
+ a.score = "0";
+ if (_useEditDistance == false) {
+ if (bam1.IsMapped() == true && bam2.IsMapped() == true)
+ a.score = ToString(min(bam1.MapQuality, bam2.MapQuality));
+ }
+ // BEDPE using edit distance
+ else {
+ if (bam1.IsMapped() == true && bam2.IsMapped() == true)
+ a.score = ToString((int) (editDistance1 + editDistance2));
+ else if (bam1.IsMapped() == true)
+ a.score = ToString((int) editDistance1);
+ else if (bam2.IsMapped() == true)
+ a.score = ToString((int) editDistance2);
+ }
+ };
+
+ inline
+ void ProcessBamBlock (const BamAlignment &bam1, const BamAlignment &bam2,
+ const RefVector &refs,
+ BamWriter &writer);
};
#endif /* PEINTERSECTBED_H */
diff --git a/src/pairToBed/pairToBedMain.cpp b/src/pairToBed/pairToBedMain.cpp
index a57177f392a91be3fc02f2358c4dd905118776f1..068e6e3db1755a811f303edd844e2755693ec5c0 100644
--- a/src/pairToBed/pairToBedMain.cpp
+++ b/src/pairToBed/pairToBedMain.cpp
@@ -25,201 +25,201 @@ void ShowHelp(void);
int main(int argc, char* argv[]) {
- // our configuration variables
- bool showHelp = false;
-
- // input files
- string bedAFile;
- string bedBFile;
-
- // input arguments
- float overlapFraction = 1E-9;
- string searchType = "either";
-
- // flags to track parameters
- bool haveBedA = false;
- bool haveBedB = false;
- bool haveSearchType = false;
- bool haveFraction = false;
- bool forceStrand = false;
- bool useEditDistance = false;
- bool inputIsBam = false;
- bool outputIsBam = true;
- bool uncompressedBam = false;
-
- // check to see if we should print out some help
- if(argc <= 1) showHelp = true;
-
- for(int i = 1; i < argc; i++) {
- int parameterLength = (int)strlen(argv[i]);
-
- if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
- (PARAMETER_CHECK("--help", 5, parameterLength))) {
- showHelp = true;
- }
- }
-
- if(showHelp) ShowHelp();
-
- // do some parsing (all of these parameters require 2 strings)
- for(int i = 1; i < argc; i++) {
-
- int parameterLength = (int)strlen(argv[i]);
-
- if(PARAMETER_CHECK("-a", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveBedA = true;
- outputIsBam = false;
- bedAFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-abam", 5, parameterLength)) {
- if ((i+1) < argc) {
- haveBedA = true;
- inputIsBam = true;
- bedAFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-b", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveBedB = true;
- bedBFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-bedpe", 6, parameterLength)) {
- outputIsBam = false;
- }
- else if(PARAMETER_CHECK("-ed", 3, parameterLength)) {
- useEditDistance = true;
- }
- else if(PARAMETER_CHECK("-type", 5, parameterLength)) {
- if ((i+1) < argc) {
- haveSearchType = true;
- searchType = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-f", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveFraction = true;
- overlapFraction = atof(argv[i + 1]);
- i++;
- }
- }
- else if (PARAMETER_CHECK("-s", 2, parameterLength)) {
- forceStrand = true;
- }
- else if(PARAMETER_CHECK("-ubam", 5, parameterLength)) {
+ // our configuration variables
+ bool showHelp = false;
+
+ // input files
+ string bedAFile;
+ string bedBFile;
+
+ // input arguments
+ float overlapFraction = 1E-9;
+ string searchType = "either";
+
+ // flags to track parameters
+ bool haveBedA = false;
+ bool haveBedB = false;
+ bool haveSearchType = false;
+ bool haveFraction = false;
+ bool forceStrand = false;
+ bool useEditDistance = false;
+ bool inputIsBam = false;
+ bool outputIsBam = true;
+ bool uncompressedBam = false;
+
+ // check to see if we should print out some help
+ if(argc <= 1) showHelp = true;
+
+ for(int i = 1; i < argc; i++) {
+ int parameterLength = (int)strlen(argv[i]);
+
+ if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
+ (PARAMETER_CHECK("--help", 5, parameterLength))) {
+ showHelp = true;
+ }
+ }
+
+ if(showHelp) ShowHelp();
+
+ // do some parsing (all of these parameters require 2 strings)
+ for(int i = 1; i < argc; i++) {
+
+ int parameterLength = (int)strlen(argv[i]);
+
+ if(PARAMETER_CHECK("-a", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveBedA = true;
+ outputIsBam = false;
+ bedAFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-abam", 5, parameterLength)) {
+ if ((i+1) < argc) {
+ haveBedA = true;
+ inputIsBam = true;
+ bedAFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-b", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveBedB = true;
+ bedBFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-bedpe", 6, parameterLength)) {
+ outputIsBam = false;
+ }
+ else if(PARAMETER_CHECK("-ed", 3, parameterLength)) {
+ useEditDistance = true;
+ }
+ else if(PARAMETER_CHECK("-type", 5, parameterLength)) {
+ if ((i+1) < argc) {
+ haveSearchType = true;
+ searchType = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-f", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveFraction = true;
+ overlapFraction = atof(argv[i + 1]);
+ i++;
+ }
+ }
+ else if (PARAMETER_CHECK("-s", 2, parameterLength)) {
+ forceStrand = true;
+ }
+ else if(PARAMETER_CHECK("-ubam", 5, parameterLength)) {
uncompressedBam = true;
- }
- else {
- cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
- showHelp = true;
- }
- }
-
-
- // make sure we have both input files
- if (!haveBedA || !haveBedB) {
- cerr << endl << "*****" << endl << "*****ERROR: Need -a and -b files. " << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (haveSearchType && (searchType != "either") && (searchType != "neither") && (searchType != "both")
- && (searchType != "xor") && (searchType != "notboth") && (searchType != "ispan")
- && (searchType != "ospan") && (searchType != "notispan") && (searchType != "notospan")) {
- cerr << endl << "*****" << endl << "*****ERROR: Request \"either\" or \"both\" or \"neither\" or \"xor\" or \"notboth\" or \"ispan\" or \"ospan\" or \"notispan\" or \"notospan\"" << endl << "*****" << endl;
- showHelp = true;
- }
-
- if ( ((searchType == "ispan") || (searchType == "ospan") || (searchType == "notispan") || (searchType == "notospan"))
- && forceStrand ) {
- cerr << endl << "*****" << endl << "*****ERROR: Cannot enforce strandedness with selected searchtype" << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (useEditDistance && (inputIsBam == false || outputIsBam == true)) {
- cerr << endl << "*****" << endl << "*****ERROR: -ed must be used with -bedpe and -abam." << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (!showHelp) {
-
- BedIntersectPE *bi = new BedIntersectPE(bedAFile, bedBFile, overlapFraction,
- searchType, forceStrand, inputIsBam,
- outputIsBam, uncompressedBam, useEditDistance);
- delete bi;
- return 0;
- }
- else {
- ShowHelp();
- }
+ }
+ else {
+ cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
+ showHelp = true;
+ }
+ }
+
+
+ // make sure we have both input files
+ if (!haveBedA || !haveBedB) {
+ cerr << endl << "*****" << endl << "*****ERROR: Need -a and -b files. " << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (haveSearchType && (searchType != "either") && (searchType != "neither") && (searchType != "both")
+ && (searchType != "xor") && (searchType != "notboth") && (searchType != "ispan")
+ && (searchType != "ospan") && (searchType != "notispan") && (searchType != "notospan")) {
+ cerr << endl << "*****" << endl << "*****ERROR: Request \"either\" or \"both\" or \"neither\" or \"xor\" or \"notboth\" or \"ispan\" or \"ospan\" or \"notispan\" or \"notospan\"" << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if ( ((searchType == "ispan") || (searchType == "ospan") || (searchType == "notispan") || (searchType == "notospan"))
+ && forceStrand ) {
+ cerr << endl << "*****" << endl << "*****ERROR: Cannot enforce strandedness with selected searchtype" << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (useEditDistance && (inputIsBam == false || outputIsBam == true)) {
+ cerr << endl << "*****" << endl << "*****ERROR: -ed must be used with -bedpe and -abam." << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (!showHelp) {
+
+ BedIntersectPE *bi = new BedIntersectPE(bedAFile, bedBFile, overlapFraction,
+ searchType, forceStrand, inputIsBam,
+ outputIsBam, uncompressedBam, useEditDistance);
+ delete bi;
+ return 0;
+ }
+ else {
+ ShowHelp();
+ }
}
void ShowHelp(void) {
- cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
-
- cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
-
- cerr << "Summary: Report overlaps between a BEDPE file and a BED/GFF/VCF file." << endl << endl;
-
- cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -a <bedpe> -b <bed/gff/vcf>" << endl << endl;
-
- cerr << "Options: " << endl;
-
- cerr << "\t-abam\t" << "The A input file is in BAM format. Output will be BAM as well." << endl;
- cerr << "\t\t- Requires BAM to be grouped or sorted by query." << endl << endl;
-
- cerr << "\t-ubam\t" << "Write uncompressed BAM output. Default is to write compressed BAM." << endl << endl;
- cerr << "\t\tis to write output in BAM when using -abam." << endl << endl;
-
- cerr << "\t-bedpe\t" << "When using BAM input (-abam), write output as BEDPE. The default" << endl;
- cerr << "\t\tis to write output in BAM when using -abam." << endl << endl;
-
- cerr << "\t-ed\t" << "Use BAM total edit distance (NM tag) for BEDPE score." << endl;
- cerr << "\t\t- Default for BEDPE is to use the minimum of" << endl;
- cerr << "\t\t of the two mapping qualities for the pair." << endl;
- cerr << "\t\t- When -ed is used the total edit distance" << endl;
- cerr << "\t\t from the two mates is reported as the score." << endl << endl;
-
- cerr << "\t-f\t" << "Minimum overlap required as fraction of A (e.g. 0.05)." << endl;
- cerr << "\t\tDefault is 1E-9 (effectively 1bp)." << endl << endl;
-
- cerr << "\t-s\t" << "Enforce strandedness when finding overlaps." << endl;
- cerr << "\t\tDefault is to ignore stand." << endl;
- cerr << "\t\tNot applicable with -type inspan or -type outspan." << endl << endl;
-
- cerr << "\t-type \t" << "Approach to reporting overlaps between BEDPE and BED." << endl << endl;
- cerr << "\t\teither\tReport overlaps if either end of A overlaps B." << endl;
- cerr << "\t\t\t- Default." << endl;
-
- cerr << "\t\tneither\tReport A if neither end of A overlaps B." << endl;
-
- cerr << "\t\tboth\tReport overlaps if both ends of A overlap B." << endl;
-
- cerr << "\t\txor\tReport overlaps if one and only one end of A overlaps B." << endl;
-
- cerr << "\t\tnotboth\tReport overlaps if neither end or one and only one " << endl;
- cerr << "\t\t\tend of A overlap B. That is, xor + neither." << endl << endl;
-
- cerr << "\t\tispan\tReport overlaps between [end1, start2] of A and B." << endl;
- cerr << "\t\t\t- Note: If chrom1 <> chrom2, entry is ignored." << endl << endl;
-
- cerr << "\t\tospan\tReport overlaps between [start1, end2] of A and B." << endl;
- cerr << "\t\t\t- Note: If chrom1 <> chrom2, entry is ignored." << endl << endl;
-
- cerr << "\t\tnotispan\tReport A if ispan of A doesn't overlap B." << endl;
- cerr << "\t\t\t\t- Note: If chrom1 <> chrom2, entry is ignored." << endl << endl;
-
- cerr << "\t\tnotospan\tReport A if ospan of A doesn't overlap B." << endl;
- cerr << "\t\t\t\t- Note: If chrom1 <> chrom2, entry is ignored." << endl << endl;
-
- cerr << "Refer to the BEDTools manual for BEDPE format." << endl << endl;
-
- exit(1);
+ cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
+
+ cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
+
+ cerr << "Summary: Report overlaps between a BEDPE file and a BED/GFF/VCF file." << endl << endl;
+
+ cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -a <bedpe> -b <bed/gff/vcf>" << endl << endl;
+
+ cerr << "Options: " << endl;
+
+ cerr << "\t-abam\t" << "The A input file is in BAM format. Output will be BAM as well." << endl;
+ cerr << "\t\t- Requires BAM to be grouped or sorted by query." << endl << endl;
+
+ cerr << "\t-ubam\t" << "Write uncompressed BAM output. Default is to write compressed BAM." << endl << endl;
+ cerr << "\t\tis to write output in BAM when using -abam." << endl << endl;
+
+ cerr << "\t-bedpe\t" << "When using BAM input (-abam), write output as BEDPE. The default" << endl;
+ cerr << "\t\tis to write output in BAM when using -abam." << endl << endl;
+
+ cerr << "\t-ed\t" << "Use BAM total edit distance (NM tag) for BEDPE score." << endl;
+ cerr << "\t\t- Default for BEDPE is to use the minimum of" << endl;
+ cerr << "\t\t of the two mapping qualities for the pair." << endl;
+ cerr << "\t\t- When -ed is used the total edit distance" << endl;
+ cerr << "\t\t from the two mates is reported as the score." << endl << endl;
+
+ cerr << "\t-f\t" << "Minimum overlap required as fraction of A (e.g. 0.05)." << endl;
+ cerr << "\t\tDefault is 1E-9 (effectively 1bp)." << endl << endl;
+
+ cerr << "\t-s\t" << "Enforce strandedness when finding overlaps." << endl;
+ cerr << "\t\tDefault is to ignore stand." << endl;
+ cerr << "\t\tNot applicable with -type inspan or -type outspan." << endl << endl;
+
+ cerr << "\t-type \t" << "Approach to reporting overlaps between BEDPE and BED." << endl << endl;
+ cerr << "\t\teither\tReport overlaps if either end of A overlaps B." << endl;
+ cerr << "\t\t\t- Default." << endl;
+
+ cerr << "\t\tneither\tReport A if neither end of A overlaps B." << endl;
+
+ cerr << "\t\tboth\tReport overlaps if both ends of A overlap B." << endl;
+
+ cerr << "\t\txor\tReport overlaps if one and only one end of A overlaps B." << endl;
+
+ cerr << "\t\tnotboth\tReport overlaps if neither end or one and only one " << endl;
+ cerr << "\t\t\tend of A overlap B. That is, xor + neither." << endl << endl;
+
+ cerr << "\t\tispan\tReport overlaps between [end1, start2] of A and B." << endl;
+ cerr << "\t\t\t- Note: If chrom1 <> chrom2, entry is ignored." << endl << endl;
+
+ cerr << "\t\tospan\tReport overlaps between [start1, end2] of A and B." << endl;
+ cerr << "\t\t\t- Note: If chrom1 <> chrom2, entry is ignored." << endl << endl;
+
+ cerr << "\t\tnotispan\tReport A if ispan of A doesn't overlap B." << endl;
+ cerr << "\t\t\t\t- Note: If chrom1 <> chrom2, entry is ignored." << endl << endl;
+
+ cerr << "\t\tnotospan\tReport A if ospan of A doesn't overlap B." << endl;
+ cerr << "\t\t\t\t- Note: If chrom1 <> chrom2, entry is ignored." << endl << endl;
+
+ cerr << "Refer to the BEDTools manual for BEDPE format." << endl << endl;
+
+ exit(1);
}
diff --git a/src/pairToPair/pairToPair.cpp b/src/pairToPair/pairToPair.cpp
index 5f6b4c83657c4329ffaa7fd850857a248f8397f2..4241c44b8d2f8e13c26164c946cadd4b09920a55 100644
--- a/src/pairToPair/pairToPair.cpp
+++ b/src/pairToPair/pairToPair.cpp
@@ -14,28 +14,29 @@
/*
- Constructor
+ Constructor
*/
-PairToPair::PairToPair(string &bedAFilePE, string &bedBFilePE, float &overlapFraction,
- string searchType, bool ignoreStrand, int slop, bool strandedSlop) {
-
- _bedAFilePE = bedAFilePE;
- _bedBFilePE = bedBFilePE;
- _overlapFraction = overlapFraction;
- _searchType = searchType;
- _ignoreStrand = ignoreStrand;
+PairToPair::PairToPair(string &bedAFilePE, string &bedBFilePE, float &overlapFraction,
+ string searchType, bool ignoreStrand, bool reqDiffNames, int slop, bool strandedSlop) {
+
+ _bedAFilePE = bedAFilePE;
+ _bedBFilePE = bedBFilePE;
+ _overlapFraction = overlapFraction;
+ _searchType = searchType;
+ _ignoreStrand = ignoreStrand;
+ _reqDiffNames = reqDiffNames;
_slop = slop;
_strandedSlop = strandedSlop;
-
- _bedA = new BedFilePE(bedAFilePE);
- _bedB = new BedFilePE(bedBFilePE);
-
- IntersectPairs();
+
+ _bedA = new BedFilePE(bedAFilePE);
+ _bedB = new BedFilePE(bedBFilePE);
+
+ IntersectPairs();
}
/*
- Destructor
+ Destructor
*/
PairToPair::~PairToPair(void) {
}
@@ -43,68 +44,45 @@ PairToPair::~PairToPair(void) {
void PairToPair::IntersectPairs() {
-
- // load the "B" bed file into a map so
- // that we can easily compare "A" to it for overlaps
- _bedB->loadBedPEFileIntoMap();
-
- int lineNum = 0;
- vector<MATE> hitsA1B1, hitsA1B2, hitsA2B1, hitsA2B2;
- // reserve some space
- hitsA1B1.reserve(100); hitsA1B2.reserve(100); hitsA2B1.reserve(100); hitsA2B2.reserve(100);
-
- BedLineStatus bedStatus;
- BEDPE a, nullBedPE;
-
- _bedA->Open();
- while ((bedStatus = _bedA->GetNextBedPE(a, lineNum)) != BED_INVALID) {
- if (bedStatus == BED_VALID) {
+
+ // load the "B" bed file into a map so
+ // that we can easily compare "A" to it for overlaps
+ _bedB->loadBedPEFileIntoMap();
+
+ int lineNum = 0;
+ BedLineStatus bedStatus;
+ BEDPE a, nullBedPE;
+
+ _bedA->Open();
+ while ((bedStatus = _bedA->GetNextBedPE(a, lineNum)) != BED_INVALID) {
+ if (bedStatus == BED_VALID) {
// identify overlaps b/w the pairs
- FindOverlaps(a, hitsA1B1, hitsA1B2, hitsA2B1, hitsA2B2);
-
- // reset space for next BEDPE
- hitsA1B1.clear(); hitsA1B2.clear(); hitsA2B1.clear(); hitsA2B2.clear();
- a = nullBedPE;
- }
- }
- _bedA->Close();
+ FindOverlaps(a);
+ a = nullBedPE;
+ }
+ }
+ _bedA->Close();
}
// END IntersectPE
-void PairToPair::FindOverlaps(const BEDPE &a,
- vector<MATE> &hitsA1B1,
- vector<MATE> &hitsA1B2,
- vector<MATE> &hitsA2B1,
- vector<MATE> &hitsA2B2) {
-
- // list of hits on each end of BEDPE
- // that exceed the requested overlap fraction
- vector<MATE> qualityHitsA1B1;
- vector<MATE> qualityHitsA1B2;
- vector<MATE> qualityHitsA2B1;
- vector<MATE> qualityHitsA2B2;
-
- // count of hits on each end of BEDPE
- // that exceed the requested overlap fraction
- int numOverlapsA1B1 = 0;
- int numOverlapsA1B2 = 0;
- int numOverlapsA2B1 = 0;
- int numOverlapsA2B2 = 0;
-
- // add the appropriate slop to the starts and ends
+void PairToPair::FindOverlaps(const BEDPE &a) {
+ //
+ vector<MATE> hitsA1B1, hitsA1B2, hitsA2B1, hitsA2B2;
+
+ // add the appropriate slop to the starts and ends
CHRPOS start1 = a.start1;
CHRPOS end1 = a.end1;
CHRPOS start2 = a.start2;
CHRPOS end2 = a.end2;
-
+
if (_strandedSlop == true) {
- if (a.strand1 == "+")
+ if (a.strand1 == "+")
end1 += _slop;
else
start1 -= _slop;
- if (a.strand2 == "+")
+ if (a.strand2 == "+")
end2 += _slop;
else
start2 -= _slop;
@@ -113,142 +91,109 @@ void PairToPair::FindOverlaps(const BEDPE &a,
start1 -= _slop;
start2 -= _slop;
end1 += _slop;
- end2 += _slop;
+ end2 += _slop;
}
- // Find the _potential_ hits between each end of A and B
- _bedB->FindOverlapsPerBin(1, a.chrom1, start1, end1, a.strand1, hitsA1B1, !(_ignoreStrand)); // hits b/w A1 & B1
- _bedB->FindOverlapsPerBin(1, a.chrom2, start2, end2, a.strand2, hitsA2B1, !(_ignoreStrand)); // hits b/w A2 & B1
- _bedB->FindOverlapsPerBin(2, a.chrom1, start1, end1, a.strand1, hitsA1B2, !(_ignoreStrand)); // hits b/w A1 & B2
- _bedB->FindOverlapsPerBin(2, a.chrom2, start2, end2, a.strand2, hitsA2B2, !(_ignoreStrand)); // hits b/w A2 & B2
-
- // Now, reduce to the set of hits on each end of A and B
- // that meet the required overlap fraction and orientation.
- // FindQualityHitsBetweenEnds(start1, end1, start2, end2, hitsA1B1, qualityHitsA1B1, numOverlapsA1B1); // quality hits b/w A1 & B1
- // FindQualityHitsBetweenEnds(start1, end1, start2, end2, hitsA1B2, qualityHitsA1B2, numOverlapsA1B2); // quality hits b/w A1 & B2
- // FindQualityHitsBetweenEnds(start1, end1, start2, end2, hitsA2B1, qualityHitsA2B1, numOverlapsA2B1); // quality hits b/w A2 & B1
- // FindQualityHitsBetweenEnds(start1, end1, start2, end2, hitsA2B2, qualityHitsA2B2, numOverlapsA2B2); // quality hits b/w A2 & B2
- FindQualityHitsBetweenEnds(start1, end1, hitsA1B1, qualityHitsA1B1, numOverlapsA1B1); // quality hits b/w A1 & B1
- FindQualityHitsBetweenEnds(start1, end1, hitsA1B2, qualityHitsA1B2, numOverlapsA1B2); // quality hits b/w A1 & B2
- FindQualityHitsBetweenEnds(start2, end2, hitsA2B1, qualityHitsA2B1, numOverlapsA2B1); // quality hits b/w A2 & B1
- FindQualityHitsBetweenEnds(start2, end2, hitsA2B2, qualityHitsA2B2, numOverlapsA2B2); // quality hits b/w A2 & B2
-
-
- int matchCount1 = 0;
- int matchCount2 = 0;
- if (_searchType == "neither" || _searchType == "both") {
- if ((numOverlapsA1B1 > 0) || (numOverlapsA2B2 > 0))
- FindHitsOnBothEnds(a, qualityHitsA1B1, qualityHitsA2B2, matchCount1);
- if ((numOverlapsA1B2 > 0) || (numOverlapsA2B1 > 0))
- FindHitsOnBothEnds(a, qualityHitsA2B1, qualityHitsA1B2, matchCount2);
-
- // report the fact that no hits were found iff _searchType is neither.
- if ((matchCount1 == 0) && (matchCount2 == 0) && (_searchType == "neither")) {
- _bedA->reportBedPENewLine(a);
- }
- }
- else if (_searchType == "either") {
- FindHitsOnEitherEnd(a, qualityHitsA1B1, qualityHitsA2B2, matchCount1);
- FindHitsOnEitherEnd(a, qualityHitsA2B1, qualityHitsA1B2, matchCount2);
- }
+ // Find the _potential_ hits between each end of A and B
+ _bedB->FindOverlapsPerBin(1, a.chrom1, start1, end1, a.name, a.strand1, hitsA1B1, _overlapFraction, !(_ignoreStrand), _reqDiffNames); // hits b/w A1 & B1
+ _bedB->FindOverlapsPerBin(1, a.chrom2, start2, end2, a.name, a.strand2, hitsA2B1, _overlapFraction, !(_ignoreStrand), _reqDiffNames); // hits b/w A2 & B1
+ _bedB->FindOverlapsPerBin(2, a.chrom1, start1, end1, a.name, a.strand1, hitsA1B2, _overlapFraction, !(_ignoreStrand), _reqDiffNames); // hits b/w A1 & B2
+ _bedB->FindOverlapsPerBin(2, a.chrom2, start2, end2, a.name, a.strand2, hitsA2B2, _overlapFraction, !(_ignoreStrand), _reqDiffNames); // hits b/w A2 & B2
+
+ unsigned int matchCount1 = (hitsA1B1.size() + hitsA2B2.size());
+ unsigned int matchCount2 = (hitsA2B1.size() + hitsA1B2.size());
+
+
+ // report the fact that no hits were found iff _searchType is neither.
+ if ((matchCount1 == 0) && (matchCount2 == 0) && (_searchType == "neither")) {
+ _bedA->reportBedPENewLine(a);
+ }
+ else if (_searchType == "both") {
+ if ((hitsA1B1.size() > 0) || (hitsA2B2.size() > 0))
+ FindHitsOnBothEnds(a, hitsA1B1, hitsA2B2);
+ if ((hitsA2B1.size() > 0) || (hitsA1B2.size() > 0))
+ FindHitsOnBothEnds(a, hitsA2B1, hitsA1B2);
+ }
+ else if (_searchType == "either") {
+ FindHitsOnEitherEnd(a, hitsA1B1, hitsA2B2);
+ FindHitsOnEitherEnd(a, hitsA2B1, hitsA1B2);
+ }
}
-void PairToPair::FindQualityHitsBetweenEnds(CHRPOS start, CHRPOS end, const vector<MATE> &hits,
- vector<MATE> &qualityHits, int &numOverlaps) {
+void PairToPair::FindHitsOnBothEnds(const BEDPE &a, const vector<MATE> &qualityHitsEnd1,
+ const vector<MATE> &qualityHitsEnd2) {
- vector<MATE>::const_iterator h = hits.begin();
- vector<MATE>::const_iterator hitsEnd = hits.end();
- for (; h != hitsEnd; ++h) {
- int s = max(start, h->bed.start);
- int e = min(end, h->bed.end);
+ map<unsigned int, vector<MATE>, less<int> > hitsMap;
- // is there enough overlap (default ~ 1bp)
- if ( ((float)(e-s) / (float)(end - start)) >= _overlapFraction ) {
- numOverlaps++;
- qualityHits.push_back(*h);
- }
- }
-}
+ for (vector<MATE>::const_iterator h = qualityHitsEnd1.begin(); h != qualityHitsEnd1.end(); ++h) {
+ hitsMap[h->lineNum].push_back(*h);
+ }
+ for (vector<MATE>::const_iterator h = qualityHitsEnd2.begin(); h != qualityHitsEnd2.end(); ++h) {
+ hitsMap[h->lineNum].push_back(*h);
+ }
+
+ for (map<unsigned int, vector<MATE>, less<unsigned int> >::iterator m = hitsMap.begin(); m != hitsMap.end(); ++m) {
+ if (m->second.size() == 2) {
+ MATE b1 = m->second[0];
+ MATE b2 = m->second[1];
-void PairToPair::FindHitsOnBothEnds(const BEDPE &a, const vector<MATE> &qualityHitsEnd1,
- const vector<MATE> &qualityHitsEnd2, int &matchCount) {
-
- map<unsigned int, vector<MATE>, less<int> > hitsMap;
-
- for (vector<MATE>::const_iterator h = qualityHitsEnd1.begin(); h != qualityHitsEnd1.end(); ++h) {
- hitsMap[h->lineNum].push_back(*h);
- matchCount++;
- }
- for (vector<MATE>::const_iterator h = qualityHitsEnd2.begin(); h != qualityHitsEnd2.end(); ++h) {
- hitsMap[h->lineNum].push_back(*h);
- matchCount++;
- }
-
- for (map<unsigned int, vector<MATE>, less<unsigned int> >::iterator m = hitsMap.begin(); m != hitsMap.end(); ++m) {
- if (m->second.size() == 2) {
-
- MATE b1 = m->second[0];
- MATE b2 = m->second[1];
-
- if (_searchType == "both") {
- _bedA->reportBedPETab(a);
- printf("%s\t%d\t%d\t%s\t%d\t%d\t%s\t%s\t%s\t%s", b1.bed.chrom.c_str(), b1.bed.start, b1.bed.end,
- b2.bed.chrom.c_str(), b2.bed.start, b2.bed.end,
- b1.bed.name.c_str(), b1.bed.score.c_str(),
- b1.bed.strand.c_str(), b2.bed.strand.c_str());
- for (size_t i = 0; i < b1.bed.otherFields.size(); ++i)
+ if (_searchType == "both") {
+ _bedA->reportBedPETab(a);
+ printf("%s\t%d\t%d\t%s\t%d\t%d\t%s\t%s\t%s\t%s", b1.bed.chrom.c_str(), b1.bed.start, b1.bed.end,
+ b2.bed.chrom.c_str(), b2.bed.start, b2.bed.end,
+ b1.bed.name.c_str(), b1.bed.score.c_str(),
+ b1.bed.strand.c_str(), b2.bed.strand.c_str());
+ for (size_t i = 0; i < b1.bed.otherFields.size(); ++i)
printf("\t%s", b1.bed.otherFields[i].c_str());
printf("\n");
- }
- }
- }
+ }
+ }
+ }
}
-void PairToPair::FindHitsOnEitherEnd(const BEDPE &a, const vector<MATE> &qualityHitsEnd1,
- const vector<MATE> &qualityHitsEnd2, int &matchCount) {
-
- map<unsigned int, vector<MATE>, less<int> > hitsMap;
-
- for (vector<MATE>::const_iterator h = qualityHitsEnd1.begin(); h != qualityHitsEnd1.end(); ++h) {
- hitsMap[h->lineNum].push_back(*h);
- matchCount++;
- }
- for (vector<MATE>::const_iterator h = qualityHitsEnd2.begin(); h != qualityHitsEnd2.end(); ++h) {
- hitsMap[h->lineNum].push_back(*h);
- matchCount++;
- }
-
- for (map<unsigned int, vector<MATE>, less<unsigned int> >::iterator m = hitsMap.begin(); m != hitsMap.end(); ++m) {
- if (m->second.size() >= 1) {
-
- if ((m->second.size()) == 2) {
- MATE b1 = m->second[0];
- MATE b2 = m->second[1];
-
- _bedA->reportBedPETab(a);
- printf("%s\t%d\t%d\t%s\t%d\t%d\t%s\t%s\t%s\t%s", b1.bed.chrom.c_str(), b1.bed.start, b1.bed.end,
- b2.bed.chrom.c_str(), b2.bed.start, b2.bed.end,
- b1.bed.name.c_str(), b1.bed.score.c_str(),
+void PairToPair::FindHitsOnEitherEnd(const BEDPE &a, const vector<MATE> &qualityHitsEnd1,
+ const vector<MATE> &qualityHitsEnd2) {
+
+ map<unsigned int, vector<MATE>, less<int> > hitsMap;
+
+ for (vector<MATE>::const_iterator h = qualityHitsEnd1.begin(); h != qualityHitsEnd1.end(); ++h) {
+ hitsMap[h->lineNum].push_back(*h);
+ }
+ for (vector<MATE>::const_iterator h = qualityHitsEnd2.begin(); h != qualityHitsEnd2.end(); ++h) {
+ hitsMap[h->lineNum].push_back(*h);
+ }
+
+ for (map<unsigned int, vector<MATE>, less<unsigned int> >::iterator m = hitsMap.begin(); m != hitsMap.end(); ++m) {
+ if (m->second.size() >= 1) {
+
+ if ((m->second.size()) == 2) {
+ MATE b1 = m->second[0];
+ MATE b2 = m->second[1];
+
+ _bedA->reportBedPETab(a);
+ printf("%s\t%d\t%d\t%s\t%d\t%d\t%s\t%s\t%s\t%s", b1.bed.chrom.c_str(), b1.bed.start, b1.bed.end,
+ b2.bed.chrom.c_str(), b2.bed.start, b2.bed.end,
+ b1.bed.name.c_str(), b1.bed.score.c_str(),
b1.bed.strand.c_str(), b2.bed.strand.c_str());
for (size_t i = 0; i < b1.bed.otherFields.size(); ++i)
- printf("\t%s", b1.bed.otherFields[i].c_str());
+ printf("\t%s", b1.bed.otherFields[i].c_str());
printf("\n");
- }
- else {
- MATE b1 = m->second[0];
-
- _bedA->reportBedPETab(a);
- printf("%s\t%d\t%d\t%s\t%d\t%d\t%s\t%s\t%s\t%s", b1.bed.chrom.c_str(), b1.bed.start, b1.bed.end,
- b1.mate->bed.chrom.c_str(), b1.mate->bed.start, b1.mate->bed.end,
- b1.bed.name.c_str(), b1.bed.score.c_str(),
+ }
+ else {
+ MATE b1 = m->second[0];
+
+ _bedA->reportBedPETab(a);
+ printf("%s\t%d\t%d\t%s\t%d\t%d\t%s\t%s\t%s\t%s", b1.bed.chrom.c_str(), b1.bed.start, b1.bed.end,
+ b1.mate->bed.chrom.c_str(), b1.mate->bed.start, b1.mate->bed.end,
+ b1.bed.name.c_str(), b1.bed.score.c_str(),
b1.bed.strand.c_str(), b1.mate->bed.strand.c_str());
for (size_t i = 0; i < b1.bed.otherFields.size(); ++i)
- printf("\t%s", b1.bed.otherFields[i].c_str());
- printf("\n");
+ printf("\t%s", b1.bed.otherFields[i].c_str());
+ printf("\n");
}
- }
- }
+ }
+ }
}
diff --git a/src/pairToPair/pairToPair.h b/src/pairToPair/pairToPair.h
index e30e4a282cacfa81539350913023c88321b8ac52..d69c57242a2eb5d0aa8fb356ea36d0262cf8137a 100644
--- a/src/pairToPair/pairToPair.h
+++ b/src/pairToPair/pairToPair.h
@@ -29,46 +29,48 @@ class PairToPair {
public:
- // constructor
- PairToPair(string &bedAFilePE, string &bedBFilePE, float &overlapFraction,
- string searchType, bool ignoreStrand, int slop, bool strandedSlop);
+ // constructor
+ PairToPair(string &bedAFilePE, string &bedBFilePE, float &overlapFraction,
+ string searchType, bool ignoreStrand, bool reqDiffNames, int slop, bool strandedSlop);
- // destructor
- ~PairToPair(void);
+ // destructor
+ ~PairToPair(void);
+
+ void IntersectPairs();
- void IntersectPairs();
-
private:
- string _bedAFilePE;
- string _bedBFilePE;
-
- float _overlapFraction;
- string _searchType;
- bool _ignoreStrand;
+ string _bedAFilePE;
+ string _bedBFilePE;
+
+ float _overlapFraction;
+ string _searchType;
+ bool _ignoreStrand;
+ bool _reqDiffNames;
int _slop;
bool _strandedSlop;
- // instance of a paired-end bed file class.
- BedFilePE *_bedA;
+ // instance of a paired-end bed file class.
+ BedFilePE *_bedA;
+
+ // instance of a bed file class.
+ BedFilePE *_bedB;
- // instance of a bed file class.
- BedFilePE *_bedB;
-
- // methods
- void FindOverlaps(const BEDPE &a, vector<MATE> &hitsA1B1, vector<MATE> &hitsA1B2,
- vector<MATE> &hitsA2B1, vector<MATE> &hitsA2B2);
+ // methods
+ // void FindOverlaps(const BEDPE &a, vector<MATE> &hitsA1B1, vector<MATE> &hitsA1B2,
+ // vector<MATE> &hitsA2B1, vector<MATE> &hitsA2B2);
+ void FindOverlaps(const BEDPE &a);
void FindQualityHitsBetweenEnds(CHRPOS start, CHRPOS end,
const vector<MATE> &hits, vector<MATE> &qualityHits, int &numOverlaps);
-
- void FindHitsOnBothEnds(const BEDPE &a, const vector<MATE> &qualityHitsEnd1,
- const vector<MATE> &qualityHitsEnd2, int &matchCount);
-
- void FindHitsOnEitherEnd(const BEDPE &a, const vector<MATE> &qualityHitsEnd1,
- const vector<MATE> &qualityHitsEnd2, int &matchCount);
-
+
+ void FindHitsOnBothEnds(const BEDPE &a, const vector<MATE> &qualityHitsEnd1,
+ const vector<MATE> &qualityHitsEnd2);
+
+ void FindHitsOnEitherEnd(const BEDPE &a, const vector<MATE> &qualityHitsEnd1,
+ const vector<MATE> &qualityHitsEnd2);
+
};
#endif /* PAIRTOPAIR_H */
diff --git a/src/pairToPair/pairToPairMain.cpp b/src/pairToPair/pairToPairMain.cpp
index 1cf03f22bdc828aa487c6b72c3634990872dbf70..97115f68f7b87f6b19a655e781bc8c8dae720395 100644
--- a/src/pairToPair/pairToPairMain.cpp
+++ b/src/pairToPair/pairToPairMain.cpp
@@ -25,155 +25,164 @@ void ShowHelp(void);
int main(int argc, char* argv[]) {
- // our configuration variables
- bool showHelp = false;
-
- // input files
- string bedAFile;
- string bedBFile;
-
- // input arguments
- float overlapFraction = 1E-9;
+ // our configuration variables
+ bool showHelp = false;
+
+ // input files
+ string bedAFile;
+ string bedBFile;
+
+ // input arguments
+ float overlapFraction = 1E-9;
int slop = 0;
- string searchType = "both";
-
- // flags to track parameters
- bool haveBedA = false;
- bool haveBedB = false;
- bool haveSearchType = false;
- bool haveFraction = false;
- bool ignoreStrand = false;
- bool haveSlop = false;
+ string searchType = "both";
+
+ // flags to track parameters
+ bool haveBedA = false;
+ bool haveBedB = false;
+ bool haveSearchType = false;
+ bool haveFraction = false;
+ bool ignoreStrand = false;
+ bool requireDifferentNames = false;
+ bool haveSlop = false;
bool strandedSlop = false;
- // check to see if we should print out some help
- if(argc <= 1) showHelp = true;
-
- for(int i = 1; i < argc; i++) {
- int parameterLength = (int)strlen(argv[i]);
-
- if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
- (PARAMETER_CHECK("--help", 5, parameterLength))) {
- showHelp = true;
- }
- }
-
- if(showHelp) ShowHelp();
-
- // do some parsing (all of these parameters require 2 strings)
- for(int i = 1; i < argc; i++) {
-
- int parameterLength = (int)strlen(argv[i]);
-
- if(PARAMETER_CHECK("-a", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveBedA = true;
- bedAFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-b", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveBedB = true;
- bedBFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-type", 5, parameterLength)) {
- if ((i+1) < argc) {
- haveSearchType = true;
- searchType = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-f", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveFraction = true;
- overlapFraction = atof(argv[i + 1]);
- i++;
- }
- }
- else if(PARAMETER_CHECK("-slop", 5, parameterLength)) {
- if ((i+1) < argc) {
- haveSlop = true;
- slop = atoi(argv[i + 1]);
- i++;
- }
- }
- else if(PARAMETER_CHECK("-ss", 3, parameterLength)) {
+ // check to see if we should print out some help
+ if(argc <= 1) showHelp = true;
+
+ for(int i = 1; i < argc; i++) {
+ int parameterLength = (int)strlen(argv[i]);
+
+ if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
+ (PARAMETER_CHECK("--help", 5, parameterLength))) {
+ showHelp = true;
+ }
+ }
+
+ if(showHelp) ShowHelp();
+
+ // do some parsing (all of these parameters require 2 strings)
+ for(int i = 1; i < argc; i++) {
+
+ int parameterLength = (int)strlen(argv[i]);
+
+ if(PARAMETER_CHECK("-a", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveBedA = true;
+ bedAFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-b", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveBedB = true;
+ bedBFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-type", 5, parameterLength)) {
+ if ((i+1) < argc) {
+ haveSearchType = true;
+ searchType = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-f", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveFraction = true;
+ overlapFraction = atof(argv[i + 1]);
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-slop", 5, parameterLength)) {
+ if ((i+1) < argc) {
+ haveSlop = true;
+ slop = atoi(argv[i + 1]);
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-ss", 3, parameterLength)) {
strandedSlop = true;
- }
- else if(PARAMETER_CHECK("-is", 3, parameterLength)) {
- ignoreStrand = true;
- }
- else {
- cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
- showHelp = true;
- }
- }
-
-
- // make sure we have both input files
- if (!haveBedA || !haveBedB) {
- cerr << endl << "*****" << endl << "*****ERROR: Need -a and -b files. " << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (haveSearchType && (searchType != "neither") && (searchType != "both") && (searchType != "either")) {
- cerr << endl << "*****" << endl << "*****ERROR: Request \"both\" or \"neither\"" << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (strandedSlop == true && haveSlop == false) {
- cerr << endl << "*****" << endl << "*****ERROR: Need a -slop value if requesting -ss." << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (!showHelp) {
-
- PairToPair *bi = new PairToPair(bedAFile, bedBFile, overlapFraction, searchType, ignoreStrand, slop, strandedSlop);
- delete bi;
- return 0;
- }
- else {
- ShowHelp();
- }
+ }
+ else if(PARAMETER_CHECK("-rdn", 4, parameterLength)) {
+ requireDifferentNames = true;
+ }
+ else if(PARAMETER_CHECK("-is", 3, parameterLength)) {
+ ignoreStrand = true;
+ }
+ else {
+ cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
+ showHelp = true;
+ }
+ }
+
+
+ // make sure we have both input files
+ if (!haveBedA || !haveBedB) {
+ cerr << endl << "*****" << endl << "*****ERROR: Need -a and -b files. " << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (haveSearchType && (searchType != "neither") && (searchType != "both") && (searchType != "either")) {
+ cerr << endl << "*****" << endl << "*****ERROR: Request \"both\" or \"neither\"" << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (strandedSlop == true && haveSlop == false) {
+ cerr << endl << "*****" << endl << "*****ERROR: Need a -slop value if requesting -ss." << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (!showHelp) {
+
+ PairToPair *bi = new PairToPair(bedAFile, bedBFile, overlapFraction, searchType,
+ ignoreStrand, requireDifferentNames, slop, strandedSlop);
+ delete bi;
+ return 0;
+ }
+ else {
+ ShowHelp();
+ }
}
void ShowHelp(void) {
- cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
-
- cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
-
- cerr << "Summary: Report overlaps between two paired-end BED files (BEDPE)." << endl << endl;
+ cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
+
+ cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
- cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -a <BEDPE> -b <BEDPE>" << endl << endl;
+ cerr << "Summary: Report overlaps between two paired-end BED files (BEDPE)." << endl << endl;
- cerr << "Options: " << endl;
- cerr << "\t-f\t" << "Minimum overlap required as fraction of A (e.g. 0.05)." << endl;
- cerr << "\t\tDefault is 1E-9 (effectively 1bp)." << endl << endl;
+ cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -a <BEDPE> -b <BEDPE>" << endl << endl;
- cerr << "\t-type \t" << "Approach to reporting overlaps between A and B." << endl << endl;
- cerr << "\t\tneither\tReport overlaps if neither end of A overlaps B." << endl;
+ cerr << "Options: " << endl;
+ cerr << "\t-f\t" << "Minimum overlap required as fraction of A (e.g. 0.05)." << endl;
+ cerr << "\t\tDefault is 1E-9 (effectively 1bp)." << endl << endl;
- cerr << "\t\teither\tReport overlaps if either ends of A overlap B." << endl;
+ cerr << "\t-type \t" << "Approach to reporting overlaps between A and B." << endl << endl;
+ cerr << "\t\tneither\tReport overlaps if neither end of A overlaps B." << endl;
- cerr << "\t\tboth\tReport overlaps if both ends of A overlap B." << endl;
- cerr << "\t\t\t- Default = both." << endl << endl;
+ cerr << "\t\teither\tReport overlaps if either ends of A overlap B." << endl;
- cerr << "\t-slop \t" << "The amount of slop (in b.p.). to be added to each footprint." << endl;
+ cerr << "\t\tboth\tReport overlaps if both ends of A overlap B." << endl;
+ cerr << "\t\t\t- Default = both." << endl << endl;
+
+ cerr << "\t-slop \t" << "The amount of slop (in b.p.). to be added to each footprint." << endl;
cerr << "\t\t*Note*: Slop is subtracted from start1 and start2 and added to end1 and end2." << endl << endl;
-
- cerr << "\t-ss\t" << "Add slop based to each BEDPE footprint based on strand." << endl;
- cerr << "\t\t- If strand is \"+\", slop is only added to the end coordinates." << endl;
- cerr << "\t\t- If strand is \"-\", slop is only added to the start coordinates." << endl;
- cerr << "\t\t- By default, slop is added in both directions." << endl << endl;
-
- cerr << "\t-is\t" << "Ignore strands when searching for overlaps." << endl;
- cerr << "\t\t- By default, strands are enforced." << endl << endl;
-
- cerr << "Refer to the BEDTools manual for BEDPE format." << endl << endl;
-
- // end the program here
- exit(1);
+
+ cerr << "\t-ss\t" << "Add slop based to each BEDPE footprint based on strand." << endl;
+ cerr << "\t\t- If strand is \"+\", slop is only added to the end coordinates." << endl;
+ cerr << "\t\t- If strand is \"-\", slop is only added to the start coordinates." << endl;
+ cerr << "\t\t- By default, slop is added in both directions." << endl << endl;
+
+ cerr << "\t-is\t" << "Ignore strands when searching for overlaps." << endl;
+ cerr << "\t\t- By default, strands are enforced." << endl << endl;
+
+ cerr << "\t-rdn\t" << "Require the hits to have different names (i.e. avoid self-hits)." << endl;
+ cerr << "\t\t- By default, same names are allowed." << endl << endl;
+
+
+ cerr << "Refer to the BEDTools manual for BEDPE format." << endl << endl;
+
+ // end the program here
+ exit(1);
}
diff --git a/src/shuffleBed/shuffleBed.cpp b/src/shuffleBed/shuffleBed.cpp
index 9e0fdded98a6ef81ef9606374b7b0fa001cf2ed1..5306f9f45ee8fc7f41ec014f0822a5d5b292abb1 100644
--- a/src/shuffleBed/shuffleBed.cpp
+++ b/src/shuffleBed/shuffleBed.cpp
@@ -15,47 +15,47 @@
BedShuffle::BedShuffle(string &bedFile, string &genomeFile, string &excludeFile, bool &haveSeed, bool &haveExclude, bool &sameChrom, int &seed) {
- _bedFile = bedFile;
- _genomeFile = genomeFile;
- _excludeFile = excludeFile;
- _sameChrom = sameChrom;
- _haveExclude = haveExclude;
- _haveSeed = haveSeed;
-
-
- // use the supplied seed for the random
- // number generation if given. else,
- // roll our own.
- if (_haveSeed) {
- _seed = seed;
- srand(seed);
- }
- else {
- srand((unsigned)time(0));
- }
-
- _bed = new BedFile(bedFile);
- _genome = new GenomeFile(genomeFile);
- _chroms = _genome->getChromList();
- _numChroms = _genome->getNumberOfChroms();
-
- if (_haveExclude) {
- _exclude = new BedFile(excludeFile);
- _exclude->loadBedFileIntoMap();
- }
-
- if (_bed->bedFile != "stdin") { // process a file
- if (_haveExclude)
- ShuffleWithExclusions();
- else
- Shuffle();
- }
- else { // process stdin
- if (_haveExclude)
- ShuffleWithExclusions();
- else
- Shuffle();
- }
+ _bedFile = bedFile;
+ _genomeFile = genomeFile;
+ _excludeFile = excludeFile;
+ _sameChrom = sameChrom;
+ _haveExclude = haveExclude;
+ _haveSeed = haveSeed;
+
+
+ // use the supplied seed for the random
+ // number generation if given. else,
+ // roll our own.
+ if (_haveSeed) {
+ _seed = seed;
+ srand(seed);
+ }
+ else {
+ srand((unsigned)time(0));
+ }
+
+ _bed = new BedFile(bedFile);
+ _genome = new GenomeFile(genomeFile);
+ _chroms = _genome->getChromList();
+ _numChroms = _genome->getNumberOfChroms();
+
+ if (_haveExclude) {
+ _exclude = new BedFile(excludeFile);
+ _exclude->loadBedFileIntoMap();
+ }
+
+ if (_bed->bedFile != "stdin") { // process a file
+ if (_haveExclude)
+ ShuffleWithExclusions();
+ else
+ Shuffle();
+ }
+ else { // process stdin
+ if (_haveExclude)
+ ShuffleWithExclusions();
+ else
+ Shuffle();
+ }
}
@@ -66,144 +66,144 @@ BedShuffle::~BedShuffle(void) {
void BedShuffle::Shuffle() {
- int lineNum = 0;
- BED bedEntry, nullBed; // used to store the current BED line from the BED file.
- BedLineStatus bedStatus;
-
- _bed->Open();
- while ((bedStatus = _bed->GetNextBed(bedEntry, lineNum)) != BED_INVALID) {
- if (bedStatus == BED_VALID) {
- ChooseLocus(bedEntry);
- _bed->reportBedNewLine(bedEntry);
- bedEntry = nullBed;
- }
- }
- _bed->Close();
+ int lineNum = 0;
+ BED bedEntry, nullBed; // used to store the current BED line from the BED file.
+ BedLineStatus bedStatus;
+
+ _bed->Open();
+ while ((bedStatus = _bed->GetNextBed(bedEntry, lineNum)) != BED_INVALID) {
+ if (bedStatus == BED_VALID) {
+ ChooseLocus(bedEntry);
+ _bed->reportBedNewLine(bedEntry);
+ bedEntry = nullBed;
+ }
+ }
+ _bed->Close();
}
void BedShuffle::ShuffleWithExclusions() {
- int lineNum = 0;
- BED bedEntry, nullBed; // used to store the current BED line from the BED file.
- BedLineStatus bedStatus;
- vector<BED> hits;
- hits.reserve(100);
-
- _bed->Open();
- while ((bedStatus = _bed->GetNextBed(bedEntry, lineNum)) != BED_INVALID) {
- if (bedStatus == BED_VALID) {
- // choose a random locus
- ChooseLocus(bedEntry);
-
- // test to see if the chosen locus overlaps
- // with an exclude region
- _exclude->FindOverlapsPerBin(bedEntry.chrom, bedEntry.start, bedEntry.end, bedEntry.strand, hits, false);
-
- bool haveOverlap = false;
- vector<BED>::const_iterator hitsItr = hits.begin();
- vector<BED>::const_iterator hitsEnd = hits.end();
- for (; hitsItr != hitsEnd; ++hitsItr) {
-
- int s = max(bedEntry.start, hitsItr->start);
- int e = min(bedEntry.end, hitsItr->end);
-
- if ( (e - s) > 0) {
- haveOverlap = true;
- break; /* stop looking. one overlap is enough*/
- }
- }
-
- /*
- keep looking as long as the chosen
- locus happens to overlap with regions
- that the user wishes to exclude.
- */
- int tries = 0;
- while ((haveOverlap == true) && (tries <= MAX_TRIES)) {
-
- // choose a new locus
- ChooseLocus(bedEntry);
-
- vector<BED> hits;
- _exclude->FindOverlapsPerBin(bedEntry.chrom, bedEntry.start, bedEntry.end,
- bedEntry.strand, hits, false);
-
- haveOverlap = false;
- vector<BED>::const_iterator hitsItr = hits.begin();
- vector<BED>::const_iterator hitsEnd = hits.end();
- for (; hitsItr != hitsEnd; ++hitsItr) {
-
- int s = max(bedEntry.start, hitsItr->start);
- int e = min(bedEntry.end, hitsItr->end);
-
- if ( (e - s) > 0) {
- haveOverlap = true;
- break; // stop looking. one overlap is enough
- }
- }
- tries++;
- }
-
- if (tries > MAX_TRIES) {
- cerr << "Error, line " << lineNum << ": tried " << MAX_TRIES << " potential loci for entry, but could not avoid excluded regions. Ignoring entry and moving on." << endl;
- }
- else {
- _bed->reportBedNewLine(bedEntry);
- }
- }
- bedEntry = nullBed;
- }
- _bed->Close();
+ int lineNum = 0;
+ BED bedEntry, nullBed; // used to store the current BED line from the BED file.
+ BedLineStatus bedStatus;
+ vector<BED> hits;
+ hits.reserve(100);
+
+ _bed->Open();
+ while ((bedStatus = _bed->GetNextBed(bedEntry, lineNum)) != BED_INVALID) {
+ if (bedStatus == BED_VALID) {
+ // choose a random locus
+ ChooseLocus(bedEntry);
+
+ // test to see if the chosen locus overlaps
+ // with an exclude region
+ _exclude->FindOverlapsPerBin(bedEntry.chrom, bedEntry.start, bedEntry.end, bedEntry.strand, hits, false);
+
+ bool haveOverlap = false;
+ vector<BED>::const_iterator hitsItr = hits.begin();
+ vector<BED>::const_iterator hitsEnd = hits.end();
+ for (; hitsItr != hitsEnd; ++hitsItr) {
+
+ int s = max(bedEntry.start, hitsItr->start);
+ int e = min(bedEntry.end, hitsItr->end);
+
+ if ( (e - s) > 0) {
+ haveOverlap = true;
+ break; /* stop looking. one overlap is enough*/
+ }
+ }
+
+ /*
+ keep looking as long as the chosen
+ locus happens to overlap with regions
+ that the user wishes to exclude.
+ */
+ int tries = 0;
+ while ((haveOverlap == true) && (tries <= MAX_TRIES)) {
+
+ // choose a new locus
+ ChooseLocus(bedEntry);
+
+ vector<BED> hits;
+ _exclude->FindOverlapsPerBin(bedEntry.chrom, bedEntry.start, bedEntry.end,
+ bedEntry.strand, hits, false);
+
+ haveOverlap = false;
+ vector<BED>::const_iterator hitsItr = hits.begin();
+ vector<BED>::const_iterator hitsEnd = hits.end();
+ for (; hitsItr != hitsEnd; ++hitsItr) {
+
+ int s = max(bedEntry.start, hitsItr->start);
+ int e = min(bedEntry.end, hitsItr->end);
+
+ if ( (e - s) > 0) {
+ haveOverlap = true;
+ break; // stop looking. one overlap is enough
+ }
+ }
+ tries++;
+ }
+
+ if (tries > MAX_TRIES) {
+ cerr << "Error, line " << lineNum << ": tried " << MAX_TRIES << " potential loci for entry, but could not avoid excluded regions. Ignoring entry and moving on." << endl;
+ }
+ else {
+ _bed->reportBedNewLine(bedEntry);
+ }
+ }
+ bedEntry = nullBed;
+ }
+ _bed->Close();
}
void BedShuffle::ChooseLocus(BED &bedEntry) {
-
- string chrom = bedEntry.chrom;
- CHRPOS start = bedEntry.start;
- CHRPOS end = bedEntry.end;
- CHRPOS length = end - start;
-
- string randomChrom;
- CHRPOS randomStart;
- CHRPOS chromSize;
-
- if (_sameChrom == false) {
- randomChrom = _chroms[rand() % _numChroms];
- chromSize = _genome->getChromSize(randomChrom);
- randomStart = rand() % chromSize;
- bedEntry.chrom = randomChrom;
- bedEntry.start = randomStart;
- bedEntry.end = randomStart + length;
- }
- else {
- chromSize = _genome->getChromSize(chrom);
- randomStart = rand() % chromSize;
- bedEntry.start = randomStart;
- bedEntry.end = randomStart + length;
- }
-
- // ensure that the chosen location doesn't go past
- // the length of the chromosome. if so, keep looking
- // for a new spot.
- while (bedEntry.end > chromSize) {
- if (_sameChrom == false) {
- randomChrom = _chroms[rand() % _numChroms];
- chromSize = _genome->getChromSize(randomChrom);
- randomStart = rand() % chromSize;
- bedEntry.chrom = randomChrom;
- bedEntry.start = randomStart;
- bedEntry.end = randomStart + length;
- }
- else {
- chromSize = _genome->getChromSize(chrom);
- randomStart = rand() % chromSize;
- bedEntry.start = randomStart;
- bedEntry.end = randomStart + length;
- }
- }
+
+ string chrom = bedEntry.chrom;
+ CHRPOS start = bedEntry.start;
+ CHRPOS end = bedEntry.end;
+ CHRPOS length = end - start;
+
+ string randomChrom;
+ CHRPOS randomStart;
+ CHRPOS chromSize;
+
+ if (_sameChrom == false) {
+ randomChrom = _chroms[rand() % _numChroms];
+ chromSize = _genome->getChromSize(randomChrom);
+ randomStart = rand() % chromSize;
+ bedEntry.chrom = randomChrom;
+ bedEntry.start = randomStart;
+ bedEntry.end = randomStart + length;
+ }
+ else {
+ chromSize = _genome->getChromSize(chrom);
+ randomStart = rand() % chromSize;
+ bedEntry.start = randomStart;
+ bedEntry.end = randomStart + length;
+ }
+
+ // ensure that the chosen location doesn't go past
+ // the length of the chromosome. if so, keep looking
+ // for a new spot.
+ while (bedEntry.end > chromSize) {
+ if (_sameChrom == false) {
+ randomChrom = _chroms[rand() % _numChroms];
+ chromSize = _genome->getChromSize(randomChrom);
+ randomStart = rand() % chromSize;
+ bedEntry.chrom = randomChrom;
+ bedEntry.start = randomStart;
+ bedEntry.end = randomStart + length;
+ }
+ else {
+ chromSize = _genome->getChromSize(chrom);
+ randomStart = rand() % chromSize;
+ bedEntry.start = randomStart;
+ bedEntry.end = randomStart + length;
+ }
+ }
}
diff --git a/src/shuffleBed/shuffleBed.h b/src/shuffleBed/shuffleBed.h
index 9f99af46e7cf853d28aaa7daa8aa18609d0d941f..5dde6108476c4ff9cc0e84f8b034823a05ada353 100644
--- a/src/shuffleBed/shuffleBed.h
+++ b/src/shuffleBed/shuffleBed.h
@@ -30,36 +30,36 @@ class BedShuffle {
public:
- // constructor
- BedShuffle(string &bedFile, string &genomeFile, string &excludeFile,
- bool &haveSeed, bool &haveExclude, bool &sameChrom, int &seed);
+ // constructor
+ BedShuffle(string &bedFile, string &genomeFile, string &excludeFile,
+ bool &haveSeed, bool &haveExclude, bool &sameChrom, int &seed);
- // destructor
- ~BedShuffle(void);
+ // destructor
+ ~BedShuffle(void);
private:
- string _bedFile;
- string _genomeFile;
- string _excludeFile;
- int _seed;
- bool _sameChrom;
- bool _haveExclude;
- bool _haveSeed;
-
-
- // The BED file from which to compute coverage.
- BedFile *_bed;
- BedFile *_exclude;
-
- GenomeFile *_genome;
-
- vector<string> _chroms;
- int _numChroms;
-
- // methods
- void Shuffle();
- void ShuffleWithExclusions();
-
- void ChooseLocus(BED &);
+ string _bedFile;
+ string _genomeFile;
+ string _excludeFile;
+ int _seed;
+ bool _sameChrom;
+ bool _haveExclude;
+ bool _haveSeed;
+
+
+ // The BED file from which to compute coverage.
+ BedFile *_bed;
+ BedFile *_exclude;
+
+ GenomeFile *_genome;
+
+ vector<string> _chroms;
+ int _numChroms;
+
+ // methods
+ void Shuffle();
+ void ShuffleWithExclusions();
+
+ void ChooseLocus(BED &);
};
diff --git a/src/shuffleBed/shuffleBedMain.cpp b/src/shuffleBed/shuffleBedMain.cpp
index a9890329a9d74a59321f7f346c31256ae67fc79e..eabb79346d1cdaf3fa0be9e4215f54f2bb077c8a 100644
--- a/src/shuffleBed/shuffleBedMain.cpp
+++ b/src/shuffleBed/shuffleBedMain.cpp
@@ -26,129 +26,129 @@ void ShowHelp(void);
int main(int argc, char* argv[]) {
- // our configuration variables
- bool showHelp = false;
-
- // input files
- string bedFile = "stdin";
- string excludeFile;
- string genomeFile;
-
- bool haveBed = true;
- bool haveGenome = false;
- bool haveExclude = false;
- bool haveSeed = false;
- int seed = -1;
- bool sameChrom = false;
-
-
- for(int i = 1; i < argc; i++) {
- int parameterLength = (int)strlen(argv[i]);
-
- if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
- (PARAMETER_CHECK("--help", 5, parameterLength))) {
- showHelp = true;
- }
- }
-
- if(showHelp) ShowHelp();
-
- // do some parsing (all of these parameters require 2 strings)
- for(int i = 1; i < argc; i++) {
-
- int parameterLength = (int)strlen(argv[i]);
-
- if(PARAMETER_CHECK("-i", 2, parameterLength)) {
- if ((i+1) < argc) {
- bedFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-g", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveGenome = true;
- genomeFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-excl", 5, parameterLength)) {
- if ((i+1) < argc) {
- haveExclude = true;
- excludeFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-seed", 5, parameterLength)) {
- if ((i+1) < argc) {
- haveSeed = true;
- seed = atoi(argv[i + 1]);
- i++;
- }
- }
- else if(PARAMETER_CHECK("-chrom", 6, parameterLength)) {
- sameChrom = true;
- }
- else {
- cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
- showHelp = true;
- }
- }
-
- // make sure we have both input files
- if (!haveBed || !haveGenome) {
- cerr << endl << "*****" << endl << "*****ERROR: Need both a BED (-i) and a genome (-g) file. " << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (!showHelp) {
- BedShuffle *bc = new BedShuffle(bedFile, genomeFile, excludeFile, haveSeed, haveExclude, sameChrom, seed);
- delete bc;
- return 0;
- }
- else {
- ShowHelp();
- }
+ // our configuration variables
+ bool showHelp = false;
+
+ // input files
+ string bedFile = "stdin";
+ string excludeFile;
+ string genomeFile;
+
+ bool haveBed = true;
+ bool haveGenome = false;
+ bool haveExclude = false;
+ bool haveSeed = false;
+ int seed = -1;
+ bool sameChrom = false;
+
+
+ for(int i = 1; i < argc; i++) {
+ int parameterLength = (int)strlen(argv[i]);
+
+ if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
+ (PARAMETER_CHECK("--help", 5, parameterLength))) {
+ showHelp = true;
+ }
+ }
+
+ if(showHelp) ShowHelp();
+
+ // do some parsing (all of these parameters require 2 strings)
+ for(int i = 1; i < argc; i++) {
+
+ int parameterLength = (int)strlen(argv[i]);
+
+ if(PARAMETER_CHECK("-i", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ bedFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-g", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveGenome = true;
+ genomeFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-excl", 5, parameterLength)) {
+ if ((i+1) < argc) {
+ haveExclude = true;
+ excludeFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-seed", 5, parameterLength)) {
+ if ((i+1) < argc) {
+ haveSeed = true;
+ seed = atoi(argv[i + 1]);
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-chrom", 6, parameterLength)) {
+ sameChrom = true;
+ }
+ else {
+ cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
+ showHelp = true;
+ }
+ }
+
+ // make sure we have both input files
+ if (!haveBed || !haveGenome) {
+ cerr << endl << "*****" << endl << "*****ERROR: Need both a BED (-i) and a genome (-g) file. " << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (!showHelp) {
+ BedShuffle *bc = new BedShuffle(bedFile, genomeFile, excludeFile, haveSeed, haveExclude, sameChrom, seed);
+ delete bc;
+ return 0;
+ }
+ else {
+ ShowHelp();
+ }
}
void ShowHelp(void) {
-
- cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
-
- cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
-
- cerr << "Summary: Randomly permute the locations of a feature file among a genome." << endl << endl;
-
- cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -i <bed/gff/vcf> -g <genome>" << endl << endl;
-
- cerr << "Options: " << endl;
- cerr << "\t-excl\t" << "A BED/GFF/VCF file of coordinates in which features in -i" << endl;
- cerr << "\t\tshould not be placed (e.g. gaps.bed)." << endl << endl;
-
- cerr << "\t-chrom\t" << "Keep features in -i on the same chromosome."<< endl;
- cerr << "\t\t- By default, the chrom and position are randomly chosen." << endl << endl;
-
- cerr << "\t-seed\t" << "Supply an integer seed for the shuffling." << endl;
- cerr << "\t\t- By default, the seed is chosen automatically." << endl;
- cerr << "\t\t- (INTEGER)" << endl << endl;
-
-
- cerr << "Notes: " << endl;
- cerr << "\t(1) The genome file should tab delimited and structured as follows:" << endl;
- cerr << "\t <chromName><TAB><chromSize>" << endl << endl;
- cerr << "\tFor example, Human (hg19):" << endl;
- cerr << "\tchr1\t249250621" << endl;
- cerr << "\tchr2\t243199373" << endl;
- cerr << "\t..." << endl;
- cerr << "\tchr18_gl000207_random\t4262" << endl << endl;
-
-
- cerr << "Tips: " << endl;
- cerr << "\tOne can use the UCSC Genome Browser's MySQL database to extract" << endl;
- cerr << "\tchromosome sizes. For example, H. sapiens:" << endl << endl;
- cerr << "\tmysql --user=genome --host=genome-mysql.cse.ucsc.edu -A -e /" << endl;
- cerr << "\t\"select chrom, size from hg19.chromInfo\" > hg19.genome" << endl << endl;
-
-
- // end the program here
- exit(1);
+
+ cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
+
+ cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
+
+ cerr << "Summary: Randomly permute the locations of a feature file among a genome." << endl << endl;
+
+ cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -i <bed/gff/vcf> -g <genome>" << endl << endl;
+
+ cerr << "Options: " << endl;
+ cerr << "\t-excl\t" << "A BED/GFF/VCF file of coordinates in which features in -i" << endl;
+ cerr << "\t\tshould not be placed (e.g. gaps.bed)." << endl << endl;
+
+ cerr << "\t-chrom\t" << "Keep features in -i on the same chromosome."<< endl;
+ cerr << "\t\t- By default, the chrom and position are randomly chosen." << endl << endl;
+
+ cerr << "\t-seed\t" << "Supply an integer seed for the shuffling." << endl;
+ cerr << "\t\t- By default, the seed is chosen automatically." << endl;
+ cerr << "\t\t- (INTEGER)" << endl << endl;
+
+
+ cerr << "Notes: " << endl;
+ cerr << "\t(1) The genome file should tab delimited and structured as follows:" << endl;
+ cerr << "\t <chromName><TAB><chromSize>" << endl << endl;
+ cerr << "\tFor example, Human (hg19):" << endl;
+ cerr << "\tchr1\t249250621" << endl;
+ cerr << "\tchr2\t243199373" << endl;
+ cerr << "\t..." << endl;
+ cerr << "\tchr18_gl000207_random\t4262" << endl << endl;
+
+
+ cerr << "Tips: " << endl;
+ cerr << "\tOne can use the UCSC Genome Browser's MySQL database to extract" << endl;
+ cerr << "\tchromosome sizes. For example, H. sapiens:" << endl << endl;
+ cerr << "\tmysql --user=genome --host=genome-mysql.cse.ucsc.edu -A -e /" << endl;
+ cerr << "\t\"select chrom, size from hg19.chromInfo\" > hg19.genome" << endl << endl;
+
+
+ // end the program here
+ exit(1);
}
diff --git a/src/slopBed/slopBed.cpp b/src/slopBed/slopBed.cpp
index 5d646cd135486fb82a11dd4310f3ad9712b81a24..0b4166ae952e67c8d01aa06d9ef3c7afceb1677f 100644
--- a/src/slopBed/slopBed.cpp
+++ b/src/slopBed/slopBed.cpp
@@ -15,17 +15,17 @@
BedSlop::BedSlop(string &bedFile, string &genomeFile, bool &forceStrand, int &leftSlop, int &rightSlop) {
- _bedFile = bedFile;
- _genomeFile = genomeFile;
- _forceStrand = forceStrand;
-
- _leftSlop = leftSlop;
- _rightSlop = rightSlop;
-
- _bed = new BedFile(bedFile);
- _genome = new GenomeFile(genomeFile);
-
- SlopBed();
+ _bedFile = bedFile;
+ _genomeFile = genomeFile;
+ _forceStrand = forceStrand;
+
+ _leftSlop = leftSlop;
+ _rightSlop = rightSlop;
+
+ _bed = new BedFile(bedFile);
+ _genome = new GenomeFile(genomeFile);
+
+ SlopBed();
}
@@ -35,49 +35,49 @@ BedSlop::~BedSlop(void) {
void BedSlop::SlopBed() {
-
- int lineNum = 0;
- BED bedEntry, nullBed; // used to store the current BED line from the BED file.
- BedLineStatus bedStatus;
-
- _bed->Open();
- bedStatus = _bed->GetNextBed(bedEntry, lineNum);
- while (bedStatus != BED_INVALID) {
- if (bedStatus == BED_VALID) {
- AddSlop(bedEntry);
- _bed->reportBedNewLine(bedEntry);
- bedEntry = nullBed;
- }
- bedStatus = _bed->GetNextBed(bedEntry, lineNum);
- }
- _bed->Close();
+
+ int lineNum = 0;
+ BED bedEntry, nullBed; // used to store the current BED line from the BED file.
+ BedLineStatus bedStatus;
+
+ _bed->Open();
+ bedStatus = _bed->GetNextBed(bedEntry, lineNum);
+ while (bedStatus != BED_INVALID) {
+ if (bedStatus == BED_VALID) {
+ AddSlop(bedEntry);
+ _bed->reportBedNewLine(bedEntry);
+ bedEntry = nullBed;
+ }
+ bedStatus = _bed->GetNextBed(bedEntry, lineNum);
+ }
+ _bed->Close();
}
void BedSlop::AddSlop(BED &bed) {
- // special handling if the BED entry is on the negative
- // strand and the user cares about strandedness.
- CHRPOS chromSize = _genome->getChromSize(bed.chrom);
-
- if ( (_forceStrand) && (bed.strand == "-") ) {
- // inspect the start
- if ( (static_cast<int>(bed.start) - _rightSlop) > 0 ) bed.start -= _rightSlop;
- else bed.start = 0;
-
- // inspect the start
- if ( (static_cast<int>(bed.end) + _leftSlop) <= static_cast<int>(chromSize)) bed.end += _leftSlop;
- else bed.end = chromSize;
- }
- else {
- // inspect the start
- if ( (static_cast<int>(bed.start) - _leftSlop) > 0) bed.start -= _leftSlop;
- else bed.start = 0;
-
- // inspect the end
- if ( (static_cast<int>(bed.end) + _rightSlop) <= static_cast<int>(chromSize)) bed.end += _rightSlop;
- else bed.end = chromSize;
- }
+ // special handling if the BED entry is on the negative
+ // strand and the user cares about strandedness.
+ CHRPOS chromSize = _genome->getChromSize(bed.chrom);
+
+ if ( (_forceStrand) && (bed.strand == "-") ) {
+ // inspect the start
+ if ( (static_cast<int>(bed.start) - _rightSlop) > 0 ) bed.start -= _rightSlop;
+ else bed.start = 0;
+
+ // inspect the start
+ if ( (static_cast<int>(bed.end) + _leftSlop) <= static_cast<int>(chromSize)) bed.end += _leftSlop;
+ else bed.end = chromSize;
+ }
+ else {
+ // inspect the start
+ if ( (static_cast<int>(bed.start) - _leftSlop) > 0) bed.start -= _leftSlop;
+ else bed.start = 0;
+
+ // inspect the end
+ if ( (static_cast<int>(bed.end) + _rightSlop) <= static_cast<int>(chromSize)) bed.end += _rightSlop;
+ else bed.end = chromSize;
+ }
}
diff --git a/src/slopBed/slopBed.h b/src/slopBed/slopBed.h
index 2e73f3969fd3b4bbb75f9b17174b4898f9674b32..48d36f4f87af8ccaa04a90f118588877a7f470eb 100644
--- a/src/slopBed/slopBed.h
+++ b/src/slopBed/slopBed.h
@@ -29,30 +29,30 @@ class BedSlop {
public:
- // constructor
- BedSlop(string &bedFile, string &genomeFile, bool &forceStrand, int &leftSlop, int &rightSlop) ;
+ // constructor
+ BedSlop(string &bedFile, string &genomeFile, bool &forceStrand, int &leftSlop, int &rightSlop) ;
+
+ // destructor
+ ~BedSlop(void);
- // destructor
- ~BedSlop(void);
-
private:
- string _bedFile;
- string _genomeFile;
-
- bool _forceStrand;
- int _leftSlop;
- int _rightSlop;
-
- BedFile *_bed;
- GenomeFile *_genome;
-
- // methods
-
- void SlopBed();
-
- // method to add requested "slop" to a single BED entry
- void AddSlop(BED &bed);
+ string _bedFile;
+ string _genomeFile;
+
+ bool _forceStrand;
+ int _leftSlop;
+ int _rightSlop;
+
+ BedFile *_bed;
+ GenomeFile *_genome;
+
+ // methods
+
+ void SlopBed();
+
+ // method to add requested "slop" to a single BED entry
+ void AddSlop(BED &bed);
};
diff --git a/src/slopBed/slopBedMain.cpp b/src/slopBed/slopBedMain.cpp
index 8319b47bf694b6213a61f2b578a111d3e4eb0384..3e490de07c0aebddc06a3ef6dba2dcc0995c9c97 100644
--- a/src/slopBed/slopBedMain.cpp
+++ b/src/slopBed/slopBedMain.cpp
@@ -26,157 +26,157 @@ void ShowHelp(void);
int main(int argc, char* argv[]) {
- // our configuration variables
- bool showHelp = false;
-
- // input files
- string bedFile = "stdin";
- string genomeFile;
-
- bool haveBed = true;
- bool haveGenome = false;
- bool haveLeft = false;
- bool haveRight = false;
- bool haveBoth = false;
-
- bool forceStrand = false;
- int leftSlop = 0;
- int rightSlop = 0;
-
- for(int i = 1; i < argc; i++) {
- int parameterLength = (int)strlen(argv[i]);
-
- if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
- (PARAMETER_CHECK("--help", 5, parameterLength))) {
- showHelp = true;
- }
- }
-
- if(showHelp) ShowHelp();
-
- // do some parsing (all of these parameters require 2 strings)
- for(int i = 1; i < argc; i++) {
-
- int parameterLength = (int)strlen(argv[i]);
-
- if(PARAMETER_CHECK("-i", 2, parameterLength)) {
- if ((i+1) < argc) {
- bedFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-g", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveGenome = true;
- genomeFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-l", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveLeft = true;
- leftSlop = atoi(argv[i + 1]);
- i++;
- }
- }
- else if(PARAMETER_CHECK("-r", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveRight = true;
- rightSlop = atoi(argv[i + 1]);
- i++;
- }
- }
- else if(PARAMETER_CHECK("-b", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveBoth = true;
- leftSlop = atoi(argv[i + 1]);
- rightSlop = atoi(argv[i + 1]);
- i++;
- }
- }
- else if(PARAMETER_CHECK("-s", 2, parameterLength)) {
- forceStrand = true;
- }
- else {
- cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
- showHelp = true;
- }
- }
-
- // make sure we have both input files
- if (!haveBed || !haveGenome) {
- cerr << endl << "*****" << endl << "*****ERROR: Need both a BED (-i) and a genome (-g) file. " << endl << "*****" << endl;
- showHelp = true;
- }
- if (!haveLeft && !haveRight && !haveBoth) {
- cerr << endl << "*****" << endl << "*****ERROR: Need -l and -r together or -b alone. " << endl << "*****" << endl;
- showHelp = true;
- }
- if ((!haveLeft && haveRight) || (haveLeft && !haveRight)) {
- cerr << endl << "*****" << endl << "*****ERROR: Need both -l and -r. " << endl << "*****" << endl;
- showHelp = true;
- }
- if (forceStrand && (!(haveLeft) || !(haveRight))) {
- cerr << endl << "*****" << endl << "*****ERROR: Must supply -l and -r with -s. " << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (!showHelp) {
- BedSlop *bc = new BedSlop(bedFile, genomeFile, forceStrand, leftSlop, rightSlop);
- delete bc;
-
- return 0;
- }
- else {
- ShowHelp();
- }
+ // our configuration variables
+ bool showHelp = false;
+
+ // input files
+ string bedFile = "stdin";
+ string genomeFile;
+
+ bool haveBed = true;
+ bool haveGenome = false;
+ bool haveLeft = false;
+ bool haveRight = false;
+ bool haveBoth = false;
+
+ bool forceStrand = false;
+ int leftSlop = 0;
+ int rightSlop = 0;
+
+ for(int i = 1; i < argc; i++) {
+ int parameterLength = (int)strlen(argv[i]);
+
+ if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
+ (PARAMETER_CHECK("--help", 5, parameterLength))) {
+ showHelp = true;
+ }
+ }
+
+ if(showHelp) ShowHelp();
+
+ // do some parsing (all of these parameters require 2 strings)
+ for(int i = 1; i < argc; i++) {
+
+ int parameterLength = (int)strlen(argv[i]);
+
+ if(PARAMETER_CHECK("-i", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ bedFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-g", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveGenome = true;
+ genomeFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-l", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveLeft = true;
+ leftSlop = atoi(argv[i + 1]);
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-r", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveRight = true;
+ rightSlop = atoi(argv[i + 1]);
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-b", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveBoth = true;
+ leftSlop = atoi(argv[i + 1]);
+ rightSlop = atoi(argv[i + 1]);
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-s", 2, parameterLength)) {
+ forceStrand = true;
+ }
+ else {
+ cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
+ showHelp = true;
+ }
+ }
+
+ // make sure we have both input files
+ if (!haveBed || !haveGenome) {
+ cerr << endl << "*****" << endl << "*****ERROR: Need both a BED (-i) and a genome (-g) file. " << endl << "*****" << endl;
+ showHelp = true;
+ }
+ if (!haveLeft && !haveRight && !haveBoth) {
+ cerr << endl << "*****" << endl << "*****ERROR: Need -l and -r together or -b alone. " << endl << "*****" << endl;
+ showHelp = true;
+ }
+ if ((!haveLeft && haveRight) || (haveLeft && !haveRight)) {
+ cerr << endl << "*****" << endl << "*****ERROR: Need both -l and -r. " << endl << "*****" << endl;
+ showHelp = true;
+ }
+ if (forceStrand && (!(haveLeft) || !(haveRight))) {
+ cerr << endl << "*****" << endl << "*****ERROR: Must supply -l and -r with -s. " << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (!showHelp) {
+ BedSlop *bc = new BedSlop(bedFile, genomeFile, forceStrand, leftSlop, rightSlop);
+ delete bc;
+
+ return 0;
+ }
+ else {
+ ShowHelp();
+ }
}
void ShowHelp(void) {
-
- cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
-
- cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
-
- cerr << "Summary: Add requested base pairs of \"slop\" to each feature." << endl << endl;
-
- cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -i <bed/gff/vcf> -g <genome> [-b <int> or (-l and -r)]" << endl << endl;
-
- cerr << "Options: " << endl;
- cerr << "\t-b\t" << "Increase the BED/GFF/VCF entry by -b base pairs in each direction." << endl;
- cerr << "\t\t- (Integer)" << endl;
-
- cerr << "\t-l\t" << "The number of base pairs to subtract from the start coordinate." << endl;
- cerr << "\t\t- (Integer)" << endl;
-
- cerr << "\t-r\t" << "The number of base pairs to add to the end coordinate." << endl;
- cerr << "\t\t- (Integer)" << endl;
-
- cerr << "\t-s\t" << "Define -l and -r based on strand." << endl;
- cerr << "\t\tE.g. if used, -l 500 for a negative-stranded feature, " << endl;
- cerr << "\t\tit will add 500 bp downstream. Default = false." << endl << endl;
-
- cerr << "Notes: " << endl;
- cerr << "\t(1) Starts will be set to 0 if options would force it below 0." << endl;
- cerr << "\t(2) Ends will be set to the chromosome length if requested slop would" << endl;
- cerr << "\tforce it above the max chrom length." << endl;
-
- cerr << "\t(3) The genome file should tab delimited and structured as follows:" << endl;
- cerr << "\n\t<chromName><TAB><chromSize>" << endl << endl;
- cerr << "\tFor example, Human (hg19):" << endl;
- cerr << "\tchr1\t249250621" << endl;
- cerr << "\tchr2\t243199373" << endl;
- cerr << "\t..." << endl;
- cerr << "\tchr18_gl000207_random\t4262" << endl << endl;
-
-
- cerr << "Tips: " << endl;
- cerr << "\tOne can use the UCSC Genome Browser's MySQL database to extract" << endl;
- cerr << "\tchromosome sizes. For example, H. sapiens:" << endl << endl;
- cerr << "\tmysql --user=genome --host=genome-mysql.cse.ucsc.edu -A -e /" << endl;
- cerr << "\t\"select chrom, size from hg19.chromInfo\" > hg19.genome" << endl << endl;
-
-
- // end the program here
- exit(1);
+
+ cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
+
+ cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
+
+ cerr << "Summary: Add requested base pairs of \"slop\" to each feature." << endl << endl;
+
+ cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -i <bed/gff/vcf> -g <genome> [-b <int> or (-l and -r)]" << endl << endl;
+
+ cerr << "Options: " << endl;
+ cerr << "\t-b\t" << "Increase the BED/GFF/VCF entry by -b base pairs in each direction." << endl;
+ cerr << "\t\t- (Integer)" << endl;
+
+ cerr << "\t-l\t" << "The number of base pairs to subtract from the start coordinate." << endl;
+ cerr << "\t\t- (Integer)" << endl;
+
+ cerr << "\t-r\t" << "The number of base pairs to add to the end coordinate." << endl;
+ cerr << "\t\t- (Integer)" << endl;
+
+ cerr << "\t-s\t" << "Define -l and -r based on strand." << endl;
+ cerr << "\t\tE.g. if used, -l 500 for a negative-stranded feature, " << endl;
+ cerr << "\t\tit will add 500 bp downstream. Default = false." << endl << endl;
+
+ cerr << "Notes: " << endl;
+ cerr << "\t(1) Starts will be set to 0 if options would force it below 0." << endl;
+ cerr << "\t(2) Ends will be set to the chromosome length if requested slop would" << endl;
+ cerr << "\tforce it above the max chrom length." << endl;
+
+ cerr << "\t(3) The genome file should tab delimited and structured as follows:" << endl;
+ cerr << "\n\t<chromName><TAB><chromSize>" << endl << endl;
+ cerr << "\tFor example, Human (hg19):" << endl;
+ cerr << "\tchr1\t249250621" << endl;
+ cerr << "\tchr2\t243199373" << endl;
+ cerr << "\t..." << endl;
+ cerr << "\tchr18_gl000207_random\t4262" << endl << endl;
+
+
+ cerr << "Tips: " << endl;
+ cerr << "\tOne can use the UCSC Genome Browser's MySQL database to extract" << endl;
+ cerr << "\tchromosome sizes. For example, H. sapiens:" << endl << endl;
+ cerr << "\tmysql --user=genome --host=genome-mysql.cse.ucsc.edu -A -e /" << endl;
+ cerr << "\t\"select chrom, size from hg19.chromInfo\" > hg19.genome" << endl << endl;
+
+
+ // end the program here
+ exit(1);
}
diff --git a/src/sortBed/sortBed.cpp b/src/sortBed/sortBed.cpp
index 89641be0d19a7fb4efd55b3079a63d991727e4b5..f76704642c7c0571c16596b66ae6a5e38154026e 100644
--- a/src/sortBed/sortBed.cpp
+++ b/src/sortBed/sortBed.cpp
@@ -16,8 +16,8 @@
// Constructor
//
BedSort::BedSort(string &bedFile) {
- _bedFile = bedFile;
- _bed = new BedFile(bedFile);
+ _bedFile = bedFile;
+ _bed = new BedFile(bedFile);
}
//
@@ -29,173 +29,173 @@ BedSort::~BedSort(void) {
void BedSort::SortBed() {
- // load the "B" bed file into a map so
- // that we can easily compare "A" to it for overlaps
- _bed->loadBedFileIntoMapNoBin();
+ // load the "B" bed file into a map so
+ // that we can easily compare "A" to it for overlaps
+ _bed->loadBedFileIntoMapNoBin();
- // loop through each chromosome and merge their BED entries
- for (masterBedMapNoBin::iterator m = _bed->bedMapNoBin.begin(); m != _bed->bedMapNoBin.end(); ++m) {
+ // loop through each chromosome and merge their BED entries
+ for (masterBedMapNoBin::iterator m = _bed->bedMapNoBin.begin(); m != _bed->bedMapNoBin.end(); ++m) {
- // bedList is already sorted by start position.
- vector<BED> bedList = m->second;
+ // bedList is already sorted by start position.
+ vector<BED> bedList = m->second;
- for (unsigned int i = 0; i < bedList.size(); ++i) {
- _bed->reportBedNewLine(bedList[i]);
- }
- }
+ for (unsigned int i = 0; i < bedList.size(); ++i) {
+ _bed->reportBedNewLine(bedList[i]);
+ }
+ }
}
void BedSort::SortBedBySizeAsc() {
- // load the "B" bed file into a map so
- // that we can easily compare "A" to it for overlaps
- _bed->loadBedFileIntoMapNoBin();
-
- vector<BED> masterList;
- masterList.reserve(1000000);
-
- // loop through each chromosome and merge their BED entries
- for (masterBedMapNoBin::iterator m = _bed->bedMapNoBin.begin(); m != _bed->bedMapNoBin.end(); ++m) {
-
- // bedList is already sorted by start position.
- vector<BED> bedList = m->second;
-
- // add the entries from this chromosome to the current list
- for (unsigned int i = 0; i < m->second.size(); ++i) {
- masterList.push_back(m->second[i]);
- }
- }
-
- // sort the master list by size (asc.)
- sort(masterList.begin(), masterList.end(), sortBySizeAsc);
-
- // report the entries in ascending order
- for (unsigned int i = 0; i < masterList.size(); ++i) {
- _bed->reportBedNewLine(masterList[i]);
- }
+ // load the "B" bed file into a map so
+ // that we can easily compare "A" to it for overlaps
+ _bed->loadBedFileIntoMapNoBin();
+
+ vector<BED> masterList;
+ masterList.reserve(1000000);
+
+ // loop through each chromosome and merge their BED entries
+ for (masterBedMapNoBin::iterator m = _bed->bedMapNoBin.begin(); m != _bed->bedMapNoBin.end(); ++m) {
+
+ // bedList is already sorted by start position.
+ vector<BED> bedList = m->second;
+
+ // add the entries from this chromosome to the current list
+ for (unsigned int i = 0; i < m->second.size(); ++i) {
+ masterList.push_back(m->second[i]);
+ }
+ }
+
+ // sort the master list by size (asc.)
+ sort(masterList.begin(), masterList.end(), sortBySizeAsc);
+
+ // report the entries in ascending order
+ for (unsigned int i = 0; i < masterList.size(); ++i) {
+ _bed->reportBedNewLine(masterList[i]);
+ }
}
void BedSort::SortBedBySizeDesc() {
- // load the "B" bed file into a map so
- // that we can easily compare "A" to it for overlaps
- _bed->loadBedFileIntoMapNoBin();
-
- vector<BED> masterList;
- masterList.reserve(1000000);
-
- // loop through each chromosome and merge their BED entries
- for (masterBedMapNoBin::iterator m = _bed->bedMapNoBin.begin(); m != _bed->bedMapNoBin.end(); ++m) {
-
- // bedList is already sorted by start position.
- vector<BED> bedList = m->second;
-
- // add the entries from this chromosome to the current list
- for (unsigned int i = 0; i < m->second.size(); ++i) {
- masterList.push_back(m->second[i]);
- }
- }
-
- // sort the master list by size (asc.)
- sort(masterList.begin(), masterList.end(), sortBySizeDesc);
-
- // report the entries in ascending order
- for (unsigned int i = 0; i < masterList.size(); ++i) {
- _bed->reportBedNewLine(masterList[i]);
- }
+ // load the "B" bed file into a map so
+ // that we can easily compare "A" to it for overlaps
+ _bed->loadBedFileIntoMapNoBin();
+
+ vector<BED> masterList;
+ masterList.reserve(1000000);
+
+ // loop through each chromosome and merge their BED entries
+ for (masterBedMapNoBin::iterator m = _bed->bedMapNoBin.begin(); m != _bed->bedMapNoBin.end(); ++m) {
+
+ // bedList is already sorted by start position.
+ vector<BED> bedList = m->second;
+
+ // add the entries from this chromosome to the current list
+ for (unsigned int i = 0; i < m->second.size(); ++i) {
+ masterList.push_back(m->second[i]);
+ }
+ }
+
+ // sort the master list by size (asc.)
+ sort(masterList.begin(), masterList.end(), sortBySizeDesc);
+
+ // report the entries in ascending order
+ for (unsigned int i = 0; i < masterList.size(); ++i) {
+ _bed->reportBedNewLine(masterList[i]);
+ }
}
void BedSort::SortBedByChromThenSizeAsc() {
- // load the "B" bed file into a map so
- // that we can easily compare "A" to it for overlaps
- _bed->loadBedFileIntoMapNoBin();
-
- // loop through each chromosome and merge their BED entries
- for (masterBedMapNoBin::iterator m = _bed->bedMapNoBin.begin(); m != _bed->bedMapNoBin.end(); ++m) {
-
- // bedList is already sorted by start position.
- vector<BED> bedList = m->second;
- sort(bedList.begin(), bedList.end(), sortBySizeAsc);
-
- for (unsigned int i = 0; i < bedList.size(); ++i) {
- _bed->reportBedNewLine(bedList[i]);
- }
- }
+ // load the "B" bed file into a map so
+ // that we can easily compare "A" to it for overlaps
+ _bed->loadBedFileIntoMapNoBin();
+
+ // loop through each chromosome and merge their BED entries
+ for (masterBedMapNoBin::iterator m = _bed->bedMapNoBin.begin(); m != _bed->bedMapNoBin.end(); ++m) {
+
+ // bedList is already sorted by start position.
+ vector<BED> bedList = m->second;
+ sort(bedList.begin(), bedList.end(), sortBySizeAsc);
+
+ for (unsigned int i = 0; i < bedList.size(); ++i) {
+ _bed->reportBedNewLine(bedList[i]);
+ }
+ }
}
void BedSort::SortBedByChromThenSizeDesc() {
- // load the "B" bed file into a map so
- // that we can easily compare "A" to it for overlaps
- _bed->loadBedFileIntoMapNoBin();
+ // load the "B" bed file into a map so
+ // that we can easily compare "A" to it for overlaps
+ _bed->loadBedFileIntoMapNoBin();
+
+ // loop through each chromosome and merge their BED entries
+ for (masterBedMapNoBin::iterator m = _bed->bedMapNoBin.begin(); m != _bed->bedMapNoBin.end(); ++m) {
- // loop through each chromosome and merge their BED entries
- for (masterBedMapNoBin::iterator m = _bed->bedMapNoBin.begin(); m != _bed->bedMapNoBin.end(); ++m) {
+ // bedList is already sorted by start position.
+ vector<BED> bedList = m->second;
- // bedList is already sorted by start position.
- vector<BED> bedList = m->second;
+ sort(bedList.begin(), bedList.end(), sortBySizeDesc);
- sort(bedList.begin(), bedList.end(), sortBySizeDesc);
-
- for (unsigned int i = 0; i < bedList.size(); ++i) {
- _bed->reportBedNewLine(bedList[i]);
- }
- }
+ for (unsigned int i = 0; i < bedList.size(); ++i) {
+ _bed->reportBedNewLine(bedList[i]);
+ }
+ }
}
void BedSort::SortBedByChromThenScoreAsc() {
- // load the "B" bed file into a map so
- // that we can easily compare "A" to it for overlaps
- _bed->loadBedFileIntoMapNoBin();
-
- if (_bed->bedType >= 5) {
- // loop through each chromosome and merge their BED entries
- for (masterBedMapNoBin::iterator m = _bed->bedMapNoBin.begin(); m != _bed->bedMapNoBin.end(); ++m) {
-
- // bedList is already sorted by start position.
- vector<BED> bedList = m->second;
- sort(bedList.begin(), bedList.end(), sortByScoreAsc);
-
- for (unsigned int i = 0; i < bedList.size(); ++i) {
- _bed->reportBedNewLine(bedList[i]);
- }
- }
- }
- else {
- cerr << "Error: Requested a sort by score, but your BED file does not appear to be in BED 5 format or greater. Exiting." << endl;
- exit(1);
- }
+ // load the "B" bed file into a map so
+ // that we can easily compare "A" to it for overlaps
+ _bed->loadBedFileIntoMapNoBin();
+
+ if (_bed->bedType >= 5) {
+ // loop through each chromosome and merge their BED entries
+ for (masterBedMapNoBin::iterator m = _bed->bedMapNoBin.begin(); m != _bed->bedMapNoBin.end(); ++m) {
+
+ // bedList is already sorted by start position.
+ vector<BED> bedList = m->second;
+ sort(bedList.begin(), bedList.end(), sortByScoreAsc);
+
+ for (unsigned int i = 0; i < bedList.size(); ++i) {
+ _bed->reportBedNewLine(bedList[i]);
+ }
+ }
+ }
+ else {
+ cerr << "Error: Requested a sort by score, but your BED file does not appear to be in BED 5 format or greater. Exiting." << endl;
+ exit(1);
+ }
}
void BedSort::SortBedByChromThenScoreDesc() {
- // load the "B" bed file into a map so
- // that we can easily compare "A" to it for overlaps
- _bed->loadBedFileIntoMapNoBin();
-
- if (_bed->bedType >= 5) {
- // loop through each chromosome and merge their BED entries
- for (masterBedMapNoBin::iterator m = _bed->bedMapNoBin.begin(); m != _bed->bedMapNoBin.end(); ++m) {
-
- // bedList is already sorted by start position.
- vector<BED> bedList = m->second;
- sort(bedList.begin(), bedList.end(), sortByScoreDesc);
-
- for (unsigned int i = 0; i < bedList.size(); ++i) {
- _bed->reportBedNewLine(bedList[i]);
- }
- }
- }
- else {
- cerr << "Error: Requested a sort by score, but your BED file does not appear to be in BED 5 format or greater. Exiting." << endl;
- exit(1);
- }
+ // load the "B" bed file into a map so
+ // that we can easily compare "A" to it for overlaps
+ _bed->loadBedFileIntoMapNoBin();
+
+ if (_bed->bedType >= 5) {
+ // loop through each chromosome and merge their BED entries
+ for (masterBedMapNoBin::iterator m = _bed->bedMapNoBin.begin(); m != _bed->bedMapNoBin.end(); ++m) {
+
+ // bedList is already sorted by start position.
+ vector<BED> bedList = m->second;
+ sort(bedList.begin(), bedList.end(), sortByScoreDesc);
+
+ for (unsigned int i = 0; i < bedList.size(); ++i) {
+ _bed->reportBedNewLine(bedList[i]);
+ }
+ }
+ }
+ else {
+ cerr << "Error: Requested a sort by score, but your BED file does not appear to be in BED 5 format or greater. Exiting." << endl;
+ exit(1);
+ }
}
diff --git a/src/sortBed/sortBed.h b/src/sortBed/sortBed.h
index 350c9ae376db2804c4354c0a9005639589ae46b1..11e7e90a5e0d32c582f7e48d9a946a05e7619522 100644
--- a/src/sortBed/sortBed.h
+++ b/src/sortBed/sortBed.h
@@ -25,26 +25,26 @@ class BedSort {
public:
- // constructor
- BedSort(string &);
-
- // destructor
- ~BedSort(void);
-
- void SortBed(); // the default. sorts by chrom (asc.) then by start (asc.)
- void SortBedBySizeAsc();
- void SortBedBySizeDesc();
- void SortBedByChromThenSizeAsc();
- void SortBedByChromThenSizeDesc();
- void SortBedByChromThenScoreAsc();
- void SortBedByChromThenScoreDesc();
-
-private:
- string _bedFile;
-
- // instance of a bed file class.
- BedFile *_bed;
-
- // methods
+ // constructor
+ BedSort(string &);
+
+ // destructor
+ ~BedSort(void);
+
+ void SortBed(); // the default. sorts by chrom (asc.) then by start (asc.)
+ void SortBedBySizeAsc();
+ void SortBedBySizeDesc();
+ void SortBedByChromThenSizeAsc();
+ void SortBedByChromThenSizeDesc();
+ void SortBedByChromThenScoreAsc();
+ void SortBedByChromThenScoreDesc();
+
+private:
+ string _bedFile;
+
+ // instance of a bed file class.
+ BedFile *_bed;
+
+ // methods
};
diff --git a/src/sortBed/sortMain.cpp b/src/sortBed/sortMain.cpp
index 304ec53040301d0508c5eb2a642120d37b3e1858..c5c19ab89d19dc1c5d106538961e2b062d0cc563 100644
--- a/src/sortBed/sortMain.cpp
+++ b/src/sortBed/sortMain.cpp
@@ -26,132 +26,132 @@ void ShowHelp(void);
int main(int argc, char* argv[]) {
- // our configuration variables
- bool showHelp = false;
-
- // input files
- string bedFile = "stdin";
- bool haveBed = true;
- int sortChoices = 0;
-
- bool sortBySizeAsc = false;
- bool sortBySizeDesc = false;
- bool sortByChromThenSizeAsc = false;
- bool sortByChromThenSizeDesc = false;
- bool sortByChromThenScoreAsc = false;
- bool sortByChromThenScoreDesc = false;
-
-
- for(int i = 1; i < argc; i++) {
- int parameterLength = (int)strlen(argv[i]);
-
- if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
- (PARAMETER_CHECK("--help", 5, parameterLength))) {
- showHelp = true;
- }
- }
-
- if(showHelp) ShowHelp();
-
- // do some parsing (all of these parameters require 2 strings)
- for(int i = 1; i < argc; i++) {
-
- int parameterLength = (int)strlen(argv[i]);
-
- if(PARAMETER_CHECK("-i", 2, parameterLength)) {
- if ((i+1) < argc) {
- bedFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-sizeA", 6, parameterLength)) {
- sortBySizeAsc = true;
- sortChoices++;
- }
- else if(PARAMETER_CHECK("-sizeD", 6, parameterLength)) {
- sortBySizeDesc = true;
- sortChoices++;
- }
- else if(PARAMETER_CHECK("-chrThenSizeA", 13, parameterLength)) {
- sortByChromThenSizeAsc = true;
- sortChoices++;
- }
- else if(PARAMETER_CHECK("-chrThenSizeD", 13, parameterLength)) {
- sortByChromThenSizeDesc = true;
- sortChoices++;
- }
- else if(PARAMETER_CHECK("-chrThenScoreA", 14, parameterLength)) {
- sortByChromThenScoreAsc = true;
- sortChoices++;
- }
- else if(PARAMETER_CHECK("-chrThenScoreD", 14, parameterLength)) {
- sortByChromThenScoreDesc = true;
- sortChoices++;
- }
- else {
- cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
- showHelp = true;
- }
- }
-
- // make sure we have both input files
- if (!haveBed) {
- cerr << endl << "*****" << endl << "*****ERROR: Need -i BED file. " << endl << "*****" << endl;
- showHelp = true;
- }
- if (sortChoices > 1) {
- cerr << endl << "*****" << endl << "*****ERROR: Sorting options are mutually exclusive. Please choose just one. " << endl << "*****" << endl;
- showHelp = true;
- }
-
-
- if (!showHelp) {
- BedSort *bm = new BedSort(bedFile);
-
- if (sortBySizeAsc) {
- bm->SortBedBySizeAsc();
- }
- else if (sortBySizeDesc) {
- bm->SortBedBySizeDesc();
- }
- else if (sortByChromThenSizeAsc) {
- bm->SortBedByChromThenSizeAsc();
- }
- else if (sortByChromThenSizeDesc) {
- bm->SortBedByChromThenSizeDesc();
- }
- else if (sortByChromThenScoreAsc) {
- bm->SortBedByChromThenScoreAsc();
- }
- else if (sortByChromThenScoreDesc) {
- bm->SortBedByChromThenScoreDesc();
- }
- else {
- bm->SortBed();
- }
- return 0;
- }
- else {
- ShowHelp();
- }
+ // our configuration variables
+ bool showHelp = false;
+
+ // input files
+ string bedFile = "stdin";
+ bool haveBed = true;
+ int sortChoices = 0;
+
+ bool sortBySizeAsc = false;
+ bool sortBySizeDesc = false;
+ bool sortByChromThenSizeAsc = false;
+ bool sortByChromThenSizeDesc = false;
+ bool sortByChromThenScoreAsc = false;
+ bool sortByChromThenScoreDesc = false;
+
+
+ for(int i = 1; i < argc; i++) {
+ int parameterLength = (int)strlen(argv[i]);
+
+ if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
+ (PARAMETER_CHECK("--help", 5, parameterLength))) {
+ showHelp = true;
+ }
+ }
+
+ if(showHelp) ShowHelp();
+
+ // do some parsing (all of these parameters require 2 strings)
+ for(int i = 1; i < argc; i++) {
+
+ int parameterLength = (int)strlen(argv[i]);
+
+ if(PARAMETER_CHECK("-i", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ bedFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-sizeA", 6, parameterLength)) {
+ sortBySizeAsc = true;
+ sortChoices++;
+ }
+ else if(PARAMETER_CHECK("-sizeD", 6, parameterLength)) {
+ sortBySizeDesc = true;
+ sortChoices++;
+ }
+ else if(PARAMETER_CHECK("-chrThenSizeA", 13, parameterLength)) {
+ sortByChromThenSizeAsc = true;
+ sortChoices++;
+ }
+ else if(PARAMETER_CHECK("-chrThenSizeD", 13, parameterLength)) {
+ sortByChromThenSizeDesc = true;
+ sortChoices++;
+ }
+ else if(PARAMETER_CHECK("-chrThenScoreA", 14, parameterLength)) {
+ sortByChromThenScoreAsc = true;
+ sortChoices++;
+ }
+ else if(PARAMETER_CHECK("-chrThenScoreD", 14, parameterLength)) {
+ sortByChromThenScoreDesc = true;
+ sortChoices++;
+ }
+ else {
+ cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
+ showHelp = true;
+ }
+ }
+
+ // make sure we have both input files
+ if (!haveBed) {
+ cerr << endl << "*****" << endl << "*****ERROR: Need -i BED file. " << endl << "*****" << endl;
+ showHelp = true;
+ }
+ if (sortChoices > 1) {
+ cerr << endl << "*****" << endl << "*****ERROR: Sorting options are mutually exclusive. Please choose just one. " << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+
+ if (!showHelp) {
+ BedSort *bm = new BedSort(bedFile);
+
+ if (sortBySizeAsc) {
+ bm->SortBedBySizeAsc();
+ }
+ else if (sortBySizeDesc) {
+ bm->SortBedBySizeDesc();
+ }
+ else if (sortByChromThenSizeAsc) {
+ bm->SortBedByChromThenSizeAsc();
+ }
+ else if (sortByChromThenSizeDesc) {
+ bm->SortBedByChromThenSizeDesc();
+ }
+ else if (sortByChromThenScoreAsc) {
+ bm->SortBedByChromThenScoreAsc();
+ }
+ else if (sortByChromThenScoreDesc) {
+ bm->SortBedByChromThenScoreDesc();
+ }
+ else {
+ bm->SortBed();
+ }
+ return 0;
+ }
+ else {
+ ShowHelp();
+ }
}
void ShowHelp(void) {
- cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
-
- cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
- cerr << "Summary: Sorts a feature file in various and useful ways." << endl << endl;
- cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -i <bed/gff/vcf>" << endl << endl;
-
- cerr << "Options: " << endl;
- cerr << "\t" << "-sizeA\t\t" << "Sort by feature size in ascending order." << endl;
- cerr << "\t" << "-sizeD\t\t" << "Sort by feature size in descending order." << endl;
- cerr << "\t" << "-chrThenSizeA\t" << "Sort by chrom (asc), then feature size (asc)." << endl;
- cerr << "\t" << "-chrThenSizeD\t" << "Sort by chrom (asc), then feature size (desc)." << endl;
- cerr << "\t" << "-chrThenScoreA\t" << "Sort by chrom (asc), then score (asc)." << endl;
- cerr << "\t" << "-chrThenScoreD\t" << "Sort by chrom (asc), then score (desc)." << endl << endl;
-
- exit(1);
+ cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
+
+ cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
+ cerr << "Summary: Sorts a feature file in various and useful ways." << endl << endl;
+ cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -i <bed/gff/vcf>" << endl << endl;
+
+ cerr << "Options: " << endl;
+ cerr << "\t" << "-sizeA\t\t" << "Sort by feature size in ascending order." << endl;
+ cerr << "\t" << "-sizeD\t\t" << "Sort by feature size in descending order." << endl;
+ cerr << "\t" << "-chrThenSizeA\t" << "Sort by chrom (asc), then feature size (asc)." << endl;
+ cerr << "\t" << "-chrThenSizeD\t" << "Sort by chrom (asc), then feature size (desc)." << endl;
+ cerr << "\t" << "-chrThenScoreA\t" << "Sort by chrom (asc), then score (asc)." << endl;
+ cerr << "\t" << "-chrThenScoreD\t" << "Sort by chrom (asc), then score (desc)." << endl << endl;
+
+ exit(1);
}
diff --git a/src/subtractBed/subtractBed.cpp b/src/subtractBed/subtractBed.cpp
index 5d71c9d53282e7d7c56b1ac81e6fcedd6e8bddbd..c5a8f0439b8b53f1318aed6c12d36a3df5ffd7de 100644
--- a/src/subtractBed/subtractBed.cpp
+++ b/src/subtractBed/subtractBed.cpp
@@ -14,163 +14,163 @@
/*
- Constructor
+ Constructor
*/
BedSubtract::BedSubtract(string &bedAFile, string &bedBFile, float &overlapFraction, bool &forceStrand) {
- _bedAFile = bedAFile;
- _bedBFile = bedBFile;
- _overlapFraction = overlapFraction;
- _forceStrand = forceStrand;
+ _bedAFile = bedAFile;
+ _bedBFile = bedBFile;
+ _overlapFraction = overlapFraction;
+ _forceStrand = forceStrand;
- _bedA = new BedFile(bedAFile);
- _bedB = new BedFile(bedBFile);
-
- SubtractBed();
+ _bedA = new BedFile(bedAFile);
+ _bedB = new BedFile(bedBFile);
+
+ SubtractBed();
}
/*
- Destructor
+ Destructor
*/
BedSubtract::~BedSubtract(void) {
}
void BedSubtract::FindAndSubtractOverlaps(BED &a, vector<BED> &hits) {
-
- // find all of the overlaps between a and B.
- _bedB->FindOverlapsPerBin(a.chrom, a.start, a.end, a.strand, hits, _forceStrand);
-
- // is A completely spanned by an entry in B?
- // if so, A should not be reported.
- int numConsumedByB = 0;
- int numOverlaps = 0;
- vector<BED> bOverlaps; // list of hits in B. Special processing if there are multiple.
-
- vector<BED>::const_iterator h = hits.begin();
- vector<BED>::const_iterator hitsEnd = hits.end();
- for (; h != hitsEnd; ++h) {
-
- int s = max(a.start, h->start);
- int e = min(a.end, h->end);
- int overlapBases = (e - s); // the number of overlapping bases b/w a and b
- int aLength = (a.end - a.start); // the length of a in b.p.
-
- if (s < e) {
-
- // is there enough overlap (default ~ 1bp)
- float overlap = ((float) overlapBases / (float) aLength);
-
- if (overlap >= 1.0) {
- numOverlaps++;
- numConsumedByB++;
- }
- else if ( overlap >= _overlapFraction ) {
- numOverlaps++;
- bOverlaps.push_back(*h);
- }
- }
- }
-
- if (numOverlaps == 0) {
- // no overlap found, so just report A as-is.
- _bedA->reportBedNewLine(a);
- }
- else if (numOverlaps == 1) {
- // one overlap found. only need to look at the single
- // entry in bOverlaps.
-
- // if A was not "consumed" by any entry in B
- if (numConsumedByB == 0) {
-
- BED theHit = bOverlaps[0];
-
- // A ++++++++++++
- // B ----
- // Res. ==== ====
- if ( (theHit.start > a.start) && (theHit.end < a.end) ) {
- _bedA->reportBedRangeNewLine(a,a.start,theHit.start);
- _bedA->reportBedRangeNewLine(a,theHit.end,a.end);
- }
- // A ++++++++++++
- // B ----------
- // Res. ==
- else if (theHit.start == a.start) {
- _bedA->reportBedRangeNewLine(a,theHit.end,a.end);
- }
- // A ++++++++++++
- // B ----------
- // Res. ====
- else if (theHit.start < a.start) {
- _bedA->reportBedRangeNewLine(a,theHit.end,a.end);
- }
- // A ++++++++++++
- // B ----------
- // Res. =======
- else if (theHit.start > a.start) {
- _bedA->reportBedRangeNewLine(a,a.start,theHit.start);
- }
- }
- }
- else if (numOverlaps > 1) {
- // multiple overlapz found. look at all the hits
- // and figure out which bases in A survived. then
- // report the contigous intervals that survived.
-
- vector<bool> aKeep(a.end - a.start, true);
-
- if (numConsumedByB == 0) {
- // track the number of hit starts and ends at each position in A
- for (vector<BED>::iterator h = bOverlaps.begin(); h != bOverlaps.end(); ++h) {
- int s = max(a.start, h->start);
- int e = min(a.end, h->end);
-
- for (int i = s+1; i <= e; ++i) {
- aKeep[i-a.start-1] = false;
- }
- }
- // report the remaining blocks.
- for (unsigned int i = 0; i < aKeep.size(); ++i) {
- if (aKeep[i] == true) {
- CHRPOS blockStart = i + a.start;
- while ((aKeep[i] == true) && (i < aKeep.size())) {
- i++;
- }
- CHRPOS blockEnd = i + a.start;
- blockEnd = min(a.end, blockEnd);
- _bedA->reportBedRangeNewLine(a,blockStart,blockEnd);
- }
- }
- }
- }
+
+ // find all of the overlaps between a and B.
+ _bedB->FindOverlapsPerBin(a.chrom, a.start, a.end, a.strand, hits, _forceStrand);
+
+ // is A completely spanned by an entry in B?
+ // if so, A should not be reported.
+ int numConsumedByB = 0;
+ int numOverlaps = 0;
+ vector<BED> bOverlaps; // list of hits in B. Special processing if there are multiple.
+
+ vector<BED>::const_iterator h = hits.begin();
+ vector<BED>::const_iterator hitsEnd = hits.end();
+ for (; h != hitsEnd; ++h) {
+
+ int s = max(a.start, h->start);
+ int e = min(a.end, h->end);
+ int overlapBases = (e - s); // the number of overlapping bases b/w a and b
+ int aLength = (a.end - a.start); // the length of a in b.p.
+
+ if (s < e) {
+
+ // is there enough overlap (default ~ 1bp)
+ float overlap = ((float) overlapBases / (float) aLength);
+
+ if (overlap >= 1.0) {
+ numOverlaps++;
+ numConsumedByB++;
+ }
+ else if ( overlap >= _overlapFraction ) {
+ numOverlaps++;
+ bOverlaps.push_back(*h);
+ }
+ }
+ }
+
+ if (numOverlaps == 0) {
+ // no overlap found, so just report A as-is.
+ _bedA->reportBedNewLine(a);
+ }
+ else if (numOverlaps == 1) {
+ // one overlap found. only need to look at the single
+ // entry in bOverlaps.
+
+ // if A was not "consumed" by any entry in B
+ if (numConsumedByB == 0) {
+
+ BED theHit = bOverlaps[0];
+
+ // A ++++++++++++
+ // B ----
+ // Res. ==== ====
+ if ( (theHit.start > a.start) && (theHit.end < a.end) ) {
+ _bedA->reportBedRangeNewLine(a,a.start,theHit.start);
+ _bedA->reportBedRangeNewLine(a,theHit.end,a.end);
+ }
+ // A ++++++++++++
+ // B ----------
+ // Res. ==
+ else if (theHit.start == a.start) {
+ _bedA->reportBedRangeNewLine(a,theHit.end,a.end);
+ }
+ // A ++++++++++++
+ // B ----------
+ // Res. ====
+ else if (theHit.start < a.start) {
+ _bedA->reportBedRangeNewLine(a,theHit.end,a.end);
+ }
+ // A ++++++++++++
+ // B ----------
+ // Res. =======
+ else if (theHit.start > a.start) {
+ _bedA->reportBedRangeNewLine(a,a.start,theHit.start);
+ }
+ }
+ }
+ else if (numOverlaps > 1) {
+ // multiple overlapz found. look at all the hits
+ // and figure out which bases in A survived. then
+ // report the contigous intervals that survived.
+
+ vector<bool> aKeep(a.end - a.start, true);
+
+ if (numConsumedByB == 0) {
+ // track the number of hit starts and ends at each position in A
+ for (vector<BED>::iterator h = bOverlaps.begin(); h != bOverlaps.end(); ++h) {
+ int s = max(a.start, h->start);
+ int e = min(a.end, h->end);
+
+ for (int i = s+1; i <= e; ++i) {
+ aKeep[i-a.start-1] = false;
+ }
+ }
+ // report the remaining blocks.
+ for (unsigned int i = 0; i < aKeep.size(); ++i) {
+ if (aKeep[i] == true) {
+ CHRPOS blockStart = i + a.start;
+ while ((aKeep[i] == true) && (i < aKeep.size())) {
+ i++;
+ }
+ CHRPOS blockEnd = i + a.start;
+ blockEnd = min(a.end, blockEnd);
+ _bedA->reportBedRangeNewLine(a,blockStart,blockEnd);
+ }
+ }
+ }
+ }
}
-
+
void BedSubtract::SubtractBed() {
- // load the "B" bed file into a map so
- // that we can easily compare "A" to it for overlaps
- _bedB->loadBedFileIntoMap();
-
- BED a, nullBed;
- BedLineStatus bedStatus;
- int lineNum = 0; // current input line number
- vector<BED> hits; // vector of potential hits
- // reserve some space
- hits.reserve(100);
-
- _bedA->Open();
- while ((bedStatus = _bedA->GetNextBed(a, lineNum)) != BED_INVALID) {
- if (bedStatus == BED_VALID) {
- FindAndSubtractOverlaps(a, hits);
- hits.clear();
- a = nullBed;
- }
- }
- _bedA->Close();
-
+ // load the "B" bed file into a map so
+ // that we can easily compare "A" to it for overlaps
+ _bedB->loadBedFileIntoMap();
+
+ BED a, nullBed;
+ BedLineStatus bedStatus;
+ int lineNum = 0; // current input line number
+ vector<BED> hits; // vector of potential hits
+ // reserve some space
+ hits.reserve(100);
+
+ _bedA->Open();
+ while ((bedStatus = _bedA->GetNextBed(a, lineNum)) != BED_INVALID) {
+ if (bedStatus == BED_VALID) {
+ FindAndSubtractOverlaps(a, hits);
+ hits.clear();
+ a = nullBed;
+ }
+ }
+ _bedA->Close();
+
}
// END Intersect
diff --git a/src/subtractBed/subtractBed.h b/src/subtractBed/subtractBed.h
index 23bba114b6d960f9134e0a9bcc4b994b2fdfe083..b613c21377e13e895ffb369e3406b2975608b4b2 100644
--- a/src/subtractBed/subtractBed.h
+++ b/src/subtractBed/subtractBed.h
@@ -26,27 +26,27 @@ class BedSubtract {
public:
- // constructor
- BedSubtract(string &bedAFile, string &bedBFile, float &overlapFraction, bool &forceStrand);
+ // constructor
+ BedSubtract(string &bedAFile, string &bedBFile, float &overlapFraction, bool &forceStrand);
- // destructor
- ~BedSubtract(void);
+ // destructor
+ ~BedSubtract(void);
private:
- // processing variables
- string _bedAFile;
- string _bedBFile;
- float _overlapFraction;
- bool _noHit;
- bool _forceStrand;
-
- // instances of bed file class.
- BedFile *_bedA, *_bedB;
-
- // methods
- void FindAndSubtractOverlaps(BED &a, vector<BED> &hits);
- void SubtractBed();
+ // processing variables
+ string _bedAFile;
+ string _bedBFile;
+ float _overlapFraction;
+ bool _noHit;
+ bool _forceStrand;
+
+ // instances of bed file class.
+ BedFile *_bedA, *_bedB;
+
+ // methods
+ void FindAndSubtractOverlaps(BED &a, vector<BED> &hits);
+ void SubtractBed();
};
#endif /* SUBTRACTBED_H */
diff --git a/src/subtractBed/subtractMain.cpp b/src/subtractBed/subtractMain.cpp
index 8986b386aef2830adf442e52d6c487ed7520b37f..9225d3ff249cfabba2d99df81483d5ab4d36373a 100644
--- a/src/subtractBed/subtractMain.cpp
+++ b/src/subtractBed/subtractMain.cpp
@@ -26,108 +26,108 @@ void ShowHelp(void);
int main(int argc, char* argv[]) {
- // our configuration variables
- bool showHelp = false;
-
- // input files
- string bedAFile;
- string bedBFile;
-
- // input arguments
- float overlapFraction = 1E-9;
-
- bool haveBedA = false;
- bool haveBedB = false;
- bool haveFraction = false;
- bool forceStrand = false;
-
- // check to see if we should print out some help
- if(argc <= 1) showHelp = true;
-
- for(int i = 1; i < argc; i++) {
- int parameterLength = (int)strlen(argv[i]);
-
- if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
- (PARAMETER_CHECK("--help", 5, parameterLength))) {
- showHelp = true;
- }
- }
-
- if(showHelp) ShowHelp();
-
- // do some parsing (all of these parameters require 2 strings)
- for(int i = 1; i < argc; i++) {
-
- int parameterLength = (int)strlen(argv[i]);
-
- if(PARAMETER_CHECK("-a", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveBedA = true;
- bedAFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-b", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveBedB = true;
- bedBFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-f", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveFraction = true;
- overlapFraction = atof(argv[i + 1]);
- i++;
- }
- }
- else if (PARAMETER_CHECK("-s", 2, parameterLength)) {
- forceStrand = true;
- }
- else {
- cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
- showHelp = true;
- }
- }
-
- // make sure we have both input files
- if (!haveBedA || !haveBedB) {
- cerr << endl << "*****" << endl << "*****ERROR: Need -a and -b files. " << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (!showHelp) {
-
- BedSubtract *bs = new BedSubtract(bedAFile, bedBFile, overlapFraction, forceStrand);
- delete bs;
- return 0;
- }
- else {
- ShowHelp();
- }
+ // our configuration variables
+ bool showHelp = false;
+
+ // input files
+ string bedAFile;
+ string bedBFile;
+
+ // input arguments
+ float overlapFraction = 1E-9;
+
+ bool haveBedA = false;
+ bool haveBedB = false;
+ bool haveFraction = false;
+ bool forceStrand = false;
+
+ // check to see if we should print out some help
+ if(argc <= 1) showHelp = true;
+
+ for(int i = 1; i < argc; i++) {
+ int parameterLength = (int)strlen(argv[i]);
+
+ if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
+ (PARAMETER_CHECK("--help", 5, parameterLength))) {
+ showHelp = true;
+ }
+ }
+
+ if(showHelp) ShowHelp();
+
+ // do some parsing (all of these parameters require 2 strings)
+ for(int i = 1; i < argc; i++) {
+
+ int parameterLength = (int)strlen(argv[i]);
+
+ if(PARAMETER_CHECK("-a", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveBedA = true;
+ bedAFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-b", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveBedB = true;
+ bedBFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-f", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveFraction = true;
+ overlapFraction = atof(argv[i + 1]);
+ i++;
+ }
+ }
+ else if (PARAMETER_CHECK("-s", 2, parameterLength)) {
+ forceStrand = true;
+ }
+ else {
+ cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
+ showHelp = true;
+ }
+ }
+
+ // make sure we have both input files
+ if (!haveBedA || !haveBedB) {
+ cerr << endl << "*****" << endl << "*****ERROR: Need -a and -b files. " << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (!showHelp) {
+
+ BedSubtract *bs = new BedSubtract(bedAFile, bedBFile, overlapFraction, forceStrand);
+ delete bs;
+ return 0;
+ }
+ else {
+ ShowHelp();
+ }
}
void ShowHelp(void) {
- cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
-
- cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
+ cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
- cerr << "Summary: Removes the portion(s) of an interval that is overlapped" << endl;
- cerr << "\t by another feature(s)." << endl << endl;
+ cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
- cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -a <bed/gff/vcf> -b <bed/gff/vcf>" << endl << endl;
+ cerr << "Summary: Removes the portion(s) of an interval that is overlapped" << endl;
+ cerr << "\t by another feature(s)." << endl << endl;
- cerr << "Options: " << endl;
- cerr << "\t-f\t" << "Minimum overlap required as a fraction of A." << endl;
- cerr << "\t\t- Default is 1E-9 (i.e., 1bp)." << endl;
- cerr << "\t\t- (FLOAT) (e.g. 0.50)" << endl << endl;
+ cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -a <bed/gff/vcf> -b <bed/gff/vcf>" << endl << endl;
- cerr << "\t-s\t" << "Force strandedness. That is, only report hits in B that" << endl;
- cerr << "\t\toverlap A on the same strand." << endl;
- cerr << "\t\t- By default, overlaps are reported without respect to strand." << endl << endl;
+ cerr << "Options: " << endl;
+ cerr << "\t-f\t" << "Minimum overlap required as a fraction of A." << endl;
+ cerr << "\t\t- Default is 1E-9 (i.e., 1bp)." << endl;
+ cerr << "\t\t- (FLOAT) (e.g. 0.50)" << endl << endl;
+ cerr << "\t-s\t" << "Force strandedness. That is, only report hits in B that" << endl;
+ cerr << "\t\toverlap A on the same strand." << endl;
+ cerr << "\t\t- By default, overlaps are reported without respect to strand." << endl << endl;
- // end the program here
- exit(1);
+
+ // end the program here
+ exit(1);
}
diff --git a/src/unionBedGraphs/intervalItem.h b/src/unionBedGraphs/intervalItem.h
index 00591b1e208c0ea08619f11dc6e7aaa150e7b737..ffec8c68719931039f7674d8abdb6ee8a38c86b7 100644
--- a/src/unionBedGraphs/intervalItem.h
+++ b/src/unionBedGraphs/intervalItem.h
@@ -16,8 +16,8 @@
#include <queue>
enum COORDINATE_TYPE {
- START,
- END
+ START,
+ END
};
/*
@@ -28,32 +28,32 @@ enum COORDINATE_TYPE {
class IntervalItem
{
private:
- IntervalItem();
+ IntervalItem();
public:
- int source_index; // which source BedGraph file this came from
- COORDINATE_TYPE coord_type; // is this the start or the end position?
- CHRPOS coord;
- std::string depth;
-
- IntervalItem(int _index, COORDINATE_TYPE _type, CHRPOS _coord, std::string _depth) :
- source_index(_index),
- coord_type(_type),
- coord(_coord),
- depth(_depth)
- {}
-
- IntervalItem(const IntervalItem &other) :
- source_index(other.source_index),
- coord_type(other.coord_type),
- coord(other.coord),
- depth(other.depth)
- {}
-
- bool operator< ( const IntervalItem& other ) const
- {
- return this->coord > other.coord;
- }
+ int source_index; // which source BedGraph file this came from
+ COORDINATE_TYPE coord_type; // is this the start or the end position?
+ CHRPOS coord;
+ std::string depth;
+
+ IntervalItem(int _index, COORDINATE_TYPE _type, CHRPOS _coord, std::string _depth) :
+ source_index(_index),
+ coord_type(_type),
+ coord(_coord),
+ depth(_depth)
+ {}
+
+ IntervalItem(const IntervalItem &other) :
+ source_index(other.source_index),
+ coord_type(other.coord_type),
+ coord(other.coord),
+ depth(other.depth)
+ {}
+
+ bool operator< ( const IntervalItem& other ) const
+ {
+ return this->coord > other.coord;
+ }
};
// our priority queue
diff --git a/src/unionBedGraphs/unionBedGraphs.cpp b/src/unionBedGraphs/unionBedGraphs.cpp
index 7eac9df02f11d7915fe85a128ffb9b372d4dcd16..998ca6beb5ea9e1c0501bd1831a93412bb2f26cc 100644
--- a/src/unionBedGraphs/unionBedGraphs.cpp
+++ b/src/unionBedGraphs/unionBedGraphs.cpp
@@ -23,233 +23,233 @@ using namespace std;
UnionBedGraphs::UnionBedGraphs(std::ostream& _output,
- const vector<string>& _filenames,
- const vector<string>& _titles,
- bool _print_empty_regions,
- const std::string& _genome_size_filename,
- const std::string& _no_coverage_value ) :
- filenames(_filenames),
- titles(_titles),
- output(_output),
- current_non_zero_inputs(0),
- print_empty_regions(_print_empty_regions),
- genome_sizes(NULL),
- no_coverage_value(_no_coverage_value)
+ const vector<string>& _filenames,
+ const vector<string>& _titles,
+ bool _print_empty_regions,
+ const std::string& _genome_size_filename,
+ const std::string& _no_coverage_value ) :
+ filenames(_filenames),
+ titles(_titles),
+ output(_output),
+ current_non_zero_inputs(0),
+ print_empty_regions(_print_empty_regions),
+ genome_sizes(NULL),
+ no_coverage_value(_no_coverage_value)
{
- if (print_empty_regions) {
- assert(!_genome_size_filename.empty());
+ if (print_empty_regions) {
+ assert(!_genome_size_filename.empty());
- genome_sizes = new GenomeFile(_genome_size_filename);
- }
+ genome_sizes = new GenomeFile(_genome_size_filename);
+ }
}
UnionBedGraphs::~UnionBedGraphs() {
- CloseBedgraphFiles();
- if (genome_sizes) {
- delete genome_sizes;
- genome_sizes = NULL ;
- }
+ CloseBedgraphFiles();
+ if (genome_sizes) {
+ delete genome_sizes;
+ genome_sizes = NULL ;
+ }
}
void UnionBedGraphs::Union() {
- OpenBedgraphFiles();
-
- // Add the first interval from each file
- for(size_t i=0;i<bedgraph_files.size();++i)
- LoadNextBedgraphItem(i);
-
- // Chromosome loop - once per chromosome
- do {
- // Find the first chromosome to use
- current_chrom = DetermineNextChrom();
-
- // Populate the queue with initial values from all files
- // (if they belong to the correct chromosome)
- for(size_t i=0;i<bedgraph_files.size();++i)
- AddInterval(i);
-
- CHRPOS current_start = ConsumeNextCoordinate();
-
- // User wanted empty regions, and the first coordinate is not 0 - print a dummy empty coverage
- if (print_empty_regions && current_start > 0)
- PrintEmptyCoverage(0,current_start);
-
- // Intervals loop - until all intervals (of current chromosome) from all files are used.
- do {
- CHRPOS current_end = queue.top().coord;
- PrintCoverage(current_start, current_end);
- current_start = ConsumeNextCoordinate();
- } while (!queue.empty());
-
- // User wanted empty regions, and the last coordinate is not the last coordinate of the chromosome
- // print a dummy empty coverage
- if (print_empty_regions) {
- CHRPOS chrom_size = genome_sizes->getChromSize(current_chrom);
- if (current_start < chrom_size)
- PrintEmptyCoverage(current_start, chrom_size);
- }
-
- } while (!AllFilesDone());
+ OpenBedgraphFiles();
+
+ // Add the first interval from each file
+ for(size_t i=0;i<bedgraph_files.size();++i)
+ LoadNextBedgraphItem(i);
+
+ // Chromosome loop - once per chromosome
+ do {
+ // Find the first chromosome to use
+ current_chrom = DetermineNextChrom();
+
+ // Populate the queue with initial values from all files
+ // (if they belong to the correct chromosome)
+ for(size_t i=0;i<bedgraph_files.size();++i)
+ AddInterval(i);
+
+ CHRPOS current_start = ConsumeNextCoordinate();
+
+ // User wanted empty regions, and the first coordinate is not 0 - print a dummy empty coverage
+ if (print_empty_regions && current_start > 0)
+ PrintEmptyCoverage(0,current_start);
+
+ // Intervals loop - until all intervals (of current chromosome) from all files are used.
+ do {
+ CHRPOS current_end = queue.top().coord;
+ PrintCoverage(current_start, current_end);
+ current_start = ConsumeNextCoordinate();
+ } while (!queue.empty());
+
+ // User wanted empty regions, and the last coordinate is not the last coordinate of the chromosome
+ // print a dummy empty coverage
+ if (print_empty_regions) {
+ CHRPOS chrom_size = genome_sizes->getChromSize(current_chrom);
+ if (current_start < chrom_size)
+ PrintEmptyCoverage(current_start, chrom_size);
+ }
+
+ } while (!AllFilesDone());
}
CHRPOS UnionBedGraphs::ConsumeNextCoordinate() {
- assert(!queue.empty());
+ assert(!queue.empty());
- CHRPOS new_position = queue.top().coord;
- do {
- IntervalItem item = queue.top();
- UpdateInformation(item);
- queue.pop();
- } while (!queue.empty() && queue.top().coord == new_position);
+ CHRPOS new_position = queue.top().coord;
+ do {
+ IntervalItem item = queue.top();
+ UpdateInformation(item);
+ queue.pop();
+ } while (!queue.empty() && queue.top().coord == new_position);
- return new_position;
+ return new_position;
}
void UnionBedGraphs::UpdateInformation(const IntervalItem &item) {
- // Update the depth coverage for this file
-
- // Which coordinate is it - start or end?
- switch (item.coord_type)
- {
- case START:
- current_depth[item.source_index] = item.depth;
- current_non_zero_inputs++;
- break;
- case END:
- //Read the next interval from this file
- AddInterval(item.source_index);
- current_depth[item.source_index] = no_coverage_value;
- current_non_zero_inputs--;
- break;
- default:
- assert(0);
- }
+ // Update the depth coverage for this file
+
+ // Which coordinate is it - start or end?
+ switch (item.coord_type)
+ {
+ case START:
+ current_depth[item.source_index] = item.depth;
+ current_non_zero_inputs++;
+ break;
+ case END:
+ //Read the next interval from this file
+ AddInterval(item.source_index);
+ current_depth[item.source_index] = no_coverage_value;
+ current_non_zero_inputs--;
+ break;
+ default:
+ assert(0);
+ }
}
void UnionBedGraphs::PrintHeader() {
- output << "chrom\tstart\tend" ;
- for (size_t i=0;i<titles.size();++i)
- output << "\t" <<titles[i];
- output << endl;
+ output << "chrom\tstart\tend" ;
+ for (size_t i=0;i<titles.size();++i)
+ output << "\t" <<titles[i];
+ output << endl;
}
void UnionBedGraphs::PrintCoverage(CHRPOS start, CHRPOS end) {
- if ( current_non_zero_inputs == 0 && ! print_empty_regions )
- return ;
+ if ( current_non_zero_inputs == 0 && ! print_empty_regions )
+ return ;
- output << current_chrom << "\t"
- << start << "\t"
- << end;
+ output << current_chrom << "\t"
+ << start << "\t"
+ << end;
- for (size_t i=0;i<current_depth.size();++i)
- output << "\t" << current_depth[i] ;
+ for (size_t i=0;i<current_depth.size();++i)
+ output << "\t" << current_depth[i] ;
- output << endl;
+ output << endl;
}
void UnionBedGraphs::PrintEmptyCoverage(CHRPOS start, CHRPOS end) {
- output << current_chrom << "\t"
- << start << "\t"
- << end;
+ output << current_chrom << "\t"
+ << start << "\t"
+ << end;
- for (size_t i=0;i<current_depth.size();++i)
- output << "\t" << no_coverage_value ;
+ for (size_t i=0;i<current_depth.size();++i)
+ output << "\t" << no_coverage_value ;
- output << endl;
+ output << endl;
}
void UnionBedGraphs::LoadNextBedgraphItem(int index) {
- assert(static_cast<unsigned int>(index) < bedgraph_files.size());
+ assert(static_cast<unsigned int>(index) < bedgraph_files.size());
- current_bedgraph_item[index].chrom="";
+ current_bedgraph_item[index].chrom="";
- BedGraphFile *file = bedgraph_files[index];
- BEDGRAPH_STR bg;
- int lineNum = 0;
- BedGraphLineStatus status;
+ BedGraphFile *file = bedgraph_files[index];
+ BEDGRAPH_STR bg;
+ int lineNum = 0;
+ BedGraphLineStatus status;
- while ( (status = file->GetNextBedGraph(bg, lineNum)) != BEDGRAPH_INVALID ) {
- if (status != BEDGRAPH_VALID)
- continue;
+ while ( (status = file->GetNextBedGraph(bg, lineNum)) != BEDGRAPH_INVALID ) {
+ if (status != BEDGRAPH_VALID)
+ continue;
- current_bedgraph_item[index] = bg ;
- break;
- }
+ current_bedgraph_item[index] = bg ;
+ break;
+ }
}
bool UnionBedGraphs::AllFilesDone() {
- for (size_t i=0;i<current_bedgraph_item.size();++i)
- if (!current_bedgraph_item[i].chrom.empty())
- return false;
- return true;
+ for (size_t i=0;i<current_bedgraph_item.size();++i)
+ if (!current_bedgraph_item[i].chrom.empty())
+ return false;
+ return true;
}
string UnionBedGraphs::DetermineNextChrom() {
- string next_chrom;
- for (size_t i=0;i<current_bedgraph_item.size();++i) {
- if (current_bedgraph_item[i].chrom.empty())
- continue;
-
- if (next_chrom.empty())
- next_chrom = current_bedgraph_item[i].chrom;
- else
- if (current_bedgraph_item[i].chrom < next_chrom)
- next_chrom = current_bedgraph_item[i].chrom ;
- }
- return next_chrom;
+ string next_chrom;
+ for (size_t i=0;i<current_bedgraph_item.size();++i) {
+ if (current_bedgraph_item[i].chrom.empty())
+ continue;
+
+ if (next_chrom.empty())
+ next_chrom = current_bedgraph_item[i].chrom;
+ else
+ if (current_bedgraph_item[i].chrom < next_chrom)
+ next_chrom = current_bedgraph_item[i].chrom ;
+ }
+ return next_chrom;
}
void UnionBedGraphs::AddInterval(int index) {
- assert(static_cast<unsigned int>(index) < bedgraph_files.size());
+ assert(static_cast<unsigned int>(index) < bedgraph_files.size());
- //This file has no more intervals
- if (current_bedgraph_item[index].chrom.empty())
- return ;
+ //This file has no more intervals
+ if (current_bedgraph_item[index].chrom.empty())
+ return ;
- //If the next interval belongs to a different chrom, don't add it
- if (current_bedgraph_item[index].chrom!=current_chrom)
- return ;
+ //If the next interval belongs to a different chrom, don't add it
+ if (current_bedgraph_item[index].chrom!=current_chrom)
+ return ;
- const BEDGRAPH_STR &bg(current_bedgraph_item[index]);
+ const BEDGRAPH_STR &bg(current_bedgraph_item[index]);
- IntervalItem start_item(index, START, bg.start, bg.depth);
- IntervalItem end_item(index, END, bg.end, bg.depth);
+ IntervalItem start_item(index, START, bg.start, bg.depth);
+ IntervalItem end_item(index, END, bg.end, bg.depth);
- queue.push(start_item);
- queue.push(end_item);
+ queue.push(start_item);
+ queue.push(end_item);
- LoadNextBedgraphItem(index);
+ LoadNextBedgraphItem(index);
}
void UnionBedGraphs::OpenBedgraphFiles() {
- for (size_t i=0;i<filenames.size();++i) {
- BedGraphFile *file = new BedGraphFile(filenames[i]);
- file->Open();
- bedgraph_files.push_back(file);
-
- current_depth.push_back(no_coverage_value);
- }
- current_bedgraph_item.resize(filenames.size());
+ for (size_t i=0;i<filenames.size();++i) {
+ BedGraphFile *file = new BedGraphFile(filenames[i]);
+ file->Open();
+ bedgraph_files.push_back(file);
+
+ current_depth.push_back(no_coverage_value);
+ }
+ current_bedgraph_item.resize(filenames.size());
}
void UnionBedGraphs::CloseBedgraphFiles() {
- for (size_t i=0;i<bedgraph_files.size();++i) {
- BedGraphFile *file = bedgraph_files[i];
- delete file;
- bedgraph_files[i] = NULL ;
- }
- bedgraph_files.clear();
+ for (size_t i=0;i<bedgraph_files.size();++i) {
+ BedGraphFile *file = bedgraph_files[i];
+ delete file;
+ bedgraph_files[i] = NULL ;
+ }
+ bedgraph_files.clear();
}
diff --git a/src/unionBedGraphs/unionBedGraphs.h b/src/unionBedGraphs/unionBedGraphs.h
index 852812a064dc3011baa2c056d245b7a60392d840..705e32f5f5c8f1d69456df5083bd84bc7a3b9f22 100644
--- a/src/unionBedGraphs/unionBedGraphs.h
+++ b/src/unionBedGraphs/unionBedGraphs.h
@@ -22,101 +22,101 @@
class UnionBedGraphs
{
private:
- typedef BEDGRAPH_STR BEDGRAPH_TYPE;
+ typedef BEDGRAPH_STR BEDGRAPH_TYPE;
- vector<string> filenames;
- vector<string> titles;
+ vector<string> filenames;
+ vector<string> titles;
- vector<BedGraphFile*> bedgraph_files;
- vector<BEDGRAPH_TYPE::DEPTH_TYPE> current_depth;
- vector<BEDGRAPH_TYPE> current_bedgraph_item;
+ vector<BedGraphFile*> bedgraph_files;
+ vector<BEDGRAPH_TYPE::DEPTH_TYPE> current_depth;
+ vector<BEDGRAPH_TYPE> current_bedgraph_item;
- std::ostream &output;
+ std::ostream &output;
- INTERVALS_PRIORITY_QUEUE queue;
- std::string current_chrom;
- int current_non_zero_inputs;
- bool print_empty_regions;
+ INTERVALS_PRIORITY_QUEUE queue;
+ std::string current_chrom;
+ int current_non_zero_inputs;
+ bool print_empty_regions;
- GenomeFile* genome_sizes;
+ GenomeFile* genome_sizes;
- std::string no_coverage_value;
+ std::string no_coverage_value;
public:
- UnionBedGraphs(std::ostream& _output,
- const vector<string>& _filenames,
- const vector<string>& _titles,
- bool _print_empty_regions,
- const std::string& _genomeFileName,
- const std::string& _no_coverage_value);
+ UnionBedGraphs(std::ostream& _output,
+ const vector<string>& _filenames,
+ const vector<string>& _titles,
+ bool _print_empty_regions,
+ const std::string& _genomeFileName,
+ const std::string& _no_coverage_value);
- virtual ~UnionBedGraphs();
+ virtual ~UnionBedGraphs();
- // Combines all bedgraph files
- void Union();
+ // Combines all bedgraph files
+ void Union();
- // Print the header line: chrom/start/end + name of each bedgraph file.
- void PrintHeader();
+ // Print the header line: chrom/start/end + name of each bedgraph file.
+ void PrintHeader();
private:
-
- // Open all BedGraph files, initialize "current_XXX" vectors
- void OpenBedgraphFiles();
+
+ // Open all BedGraph files, initialize "current_XXX" vectors
+ void OpenBedgraphFiles();
// Close the BedGraph files.
- void CloseBedgraphFiles();
-
- /*
- Add an interval from BedGraph file 'index' into the queue.
- will only be added if it belongs to the current chromosome.
-
- If the interval was added (=consumed), the next interval will be read from the file
- using 'LoadNextBedgraphItem'
- */
- void AddInterval(int index);
-
- /*
- Loads the next interval from BedGraph file 'index'.
- Stores it in 'current_bedgraph_item' vector.
- */
- void LoadNextBedgraphItem(int index);
-
- /*
- Scans the 'current_bedgraph_item' vector,
- find the 'first' chromosome to use (different BedGraph files can start with different chromosomes).
- */
- std::string DetermineNextChrom();
-
- /*
- Returns 'true' if ALL intervals from ALL BedGraph files were used
- */
- bool AllFilesDone();
-
- /*
- Extract the next coordinate from the queue, and updates the current coverage information.
- If multiple interval share the same coordinate values, all of them are handled.
- If an END coordinate is consumed, the next interval (from the corresponding file) is read.
- */
- CHRPOS ConsumeNextCoordinate();
-
- /*
- Updates the coverage information based on the given item.
- Item can be a START coordinate or an END coordiante.
- */
- void UpdateInformation(const IntervalItem &item);
-
- /*
- prints chrom/start/end and the current depth coverage values of all the files.
- */
- void PrintCoverage(CHRPOS start, CHRPOS end);
-
- /*
- prints chrom/start/end and the ZERO depth coverage values of all the files.
- */
- void PrintEmptyCoverage(CHRPOS start, CHRPOS end);
-
- void DebugPrintQueue();
+ void CloseBedgraphFiles();
+
+ /*
+ Add an interval from BedGraph file 'index' into the queue.
+ will only be added if it belongs to the current chromosome.
+
+ If the interval was added (=consumed), the next interval will be read from the file
+ using 'LoadNextBedgraphItem'
+ */
+ void AddInterval(int index);
+
+ /*
+ Loads the next interval from BedGraph file 'index'.
+ Stores it in 'current_bedgraph_item' vector.
+ */
+ void LoadNextBedgraphItem(int index);
+
+ /*
+ Scans the 'current_bedgraph_item' vector,
+ find the 'first' chromosome to use (different BedGraph files can start with different chromosomes).
+ */
+ std::string DetermineNextChrom();
+
+ /*
+ Returns 'true' if ALL intervals from ALL BedGraph files were used
+ */
+ bool AllFilesDone();
+
+ /*
+ Extract the next coordinate from the queue, and updates the current coverage information.
+ If multiple interval share the same coordinate values, all of them are handled.
+ If an END coordinate is consumed, the next interval (from the corresponding file) is read.
+ */
+ CHRPOS ConsumeNextCoordinate();
+
+ /*
+ Updates the coverage information based on the given item.
+ Item can be a START coordinate or an END coordiante.
+ */
+ void UpdateInformation(const IntervalItem &item);
+
+ /*
+ prints chrom/start/end and the current depth coverage values of all the files.
+ */
+ void PrintCoverage(CHRPOS start, CHRPOS end);
+
+ /*
+ prints chrom/start/end and the ZERO depth coverage values of all the files.
+ */
+ void PrintEmptyCoverage(CHRPOS start, CHRPOS end);
+
+ void DebugPrintQueue();
};
diff --git a/src/unionBedGraphs/unionBedGraphsMain.cpp b/src/unionBedGraphs/unionBedGraphsMain.cpp
index c36d4e314850252c03f957da98bdaa122fbaca4b..b140b013d84b74ce2d5a2c27337431072b07d21c 100644
--- a/src/unionBedGraphs/unionBedGraphsMain.cpp
+++ b/src/unionBedGraphs/unionBedGraphsMain.cpp
@@ -43,127 +43,127 @@ void ShowExamples(void);
int main(int argc, char* argv[])
{
- bool haveFiles = false;
- bool haveTitles = false;
+ bool haveFiles = false;
+ bool haveTitles = false;
bool haveGenome = false;
bool haveFiller = true;
- bool printHeader = false;
- bool printEmptyRegions = false;
+ bool printHeader = false;
+ bool printEmptyRegions = false;
bool showHelp = false;
- string genomeFile;
- string basePath;
- string noCoverageValue = "0";
- vector<string> inputFiles;
- vector<string> inputTitles;
-
- //Parse command line options
- if(argc <= 1)
- ShowHelp();
-
- for(int i = 1; i < argc; i++) {
- int parameterLength = (int)strlen(argv[i]);
-
- if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
- (PARAMETER_CHECK("--help", 5, parameterLength))) {
- showHelp = true;
- }
- }
-
- if(showHelp == true) {
- ShowHelp();
+ string genomeFile;
+ string basePath;
+ string noCoverageValue = "0";
+ vector<string> inputFiles;
+ vector<string> inputTitles;
+
+ //Parse command line options
+ if(argc <= 1)
+ ShowHelp();
+
+ for(int i = 1; i < argc; i++) {
+ int parameterLength = (int)strlen(argv[i]);
+
+ if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
+ (PARAMETER_CHECK("--help", 5, parameterLength))) {
+ showHelp = true;
+ }
+ }
+
+ if(showHelp == true) {
+ ShowHelp();
exit(1);
}
- // do some parsing (all of these parameters require 2 strings)
- for(int i = 1; i < argc; i++) {
+ // do some parsing (all of these parameters require 2 strings)
+ for(int i = 1; i < argc; i++) {
- int parameterLength = (int)strlen(argv[i]);
+ int parameterLength = (int)strlen(argv[i]);
- if(PARAMETER_CHECK("-i", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveFiles = true;
+ if(PARAMETER_CHECK("-i", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveFiles = true;
i = i+1;
string file = argv[i];
- while (file[0] != '-' && i < argc) {
+ while (file[0] != '-' && i < argc) {
inputFiles.push_back(file);
i++;
if (i < argc)
file = argv[i];
- }
+ }
i--;
- }
- }
- else if(PARAMETER_CHECK("-names", 6, parameterLength)) {
- if ((i+1) < argc) {
- haveTitles = true;
+ }
+ }
+ else if(PARAMETER_CHECK("-names", 6, parameterLength)) {
+ if ((i+1) < argc) {
+ haveTitles = true;
i = i+1;
string title = argv[i];
- while (title[0] != '-' && i < argc) {
+ while (title[0] != '-' && i < argc) {
inputTitles.push_back(title);
i++;
if (i < argc)
title = argv[i];
- }
+ }
i--;
- }
- }
- else if(PARAMETER_CHECK("-g", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveGenome = true;
- genomeFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-filler", 7, parameterLength)) {
- if ((i+1) < argc) {
- haveFiller = true;
- noCoverageValue = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-header", 7, parameterLength)) {
- printHeader = true;
- }
- else if(PARAMETER_CHECK("-empty", 6, parameterLength)) {
- printEmptyRegions = true;
- }
- else if(PARAMETER_CHECK("-examples", 9, parameterLength)) {
+ }
+ }
+ else if(PARAMETER_CHECK("-g", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveGenome = true;
+ genomeFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-filler", 7, parameterLength)) {
+ if ((i+1) < argc) {
+ haveFiller = true;
+ noCoverageValue = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-header", 7, parameterLength)) {
+ printHeader = true;
+ }
+ else if(PARAMETER_CHECK("-empty", 6, parameterLength)) {
+ printEmptyRegions = true;
+ }
+ else if(PARAMETER_CHECK("-examples", 9, parameterLength)) {
ShowHelp();
ShowExamples();
exit(1);
- }
- }
-
- //Sanity checks
- if (inputFiles.empty() == true) {
- cerr << "Error: missing BedGraph file names (-i) to combine." << endl;
- exit(1);
- }
- if (inputFiles.size() == 1) {
- cerr << "Error: Only a single BedGraph file was specified. Nothing to combine, exiting." << endl;
- exit(1);
- }
- if (printEmptyRegions && (genomeFile.empty() == true)) {
- cerr << "Error: when using -empty, the genome sizes file (-g) must be specified using '-g FILE'." << endl;
- exit(1);
- }
- if ((haveTitles == true) && (inputFiles.size() != inputTitles.size())) {
- cerr << "Error: The number of file titles (-names) does not match the number of files (-i)." << endl;
- exit(1);
- }
-
- UnionBedGraphs ubg(cout, inputFiles, inputTitles, printEmptyRegions, genomeFile, noCoverageValue);
- if (printHeader)
- ubg.PrintHeader();
- ubg.Union();
+ }
+ }
+
+ //Sanity checks
+ if (inputFiles.empty() == true) {
+ cerr << "Error: missing BedGraph file names (-i) to combine." << endl;
+ exit(1);
+ }
+ if (inputFiles.size() == 1) {
+ cerr << "Error: Only a single BedGraph file was specified. Nothing to combine, exiting." << endl;
+ exit(1);
+ }
+ if (printEmptyRegions && (genomeFile.empty() == true)) {
+ cerr << "Error: when using -empty, the genome sizes file (-g) must be specified using '-g FILE'." << endl;
+ exit(1);
+ }
+ if ((haveTitles == true) && (inputFiles.size() != inputTitles.size())) {
+ cerr << "Error: The number of file titles (-names) does not match the number of files (-i)." << endl;
+ exit(1);
+ }
+
+ UnionBedGraphs ubg(cout, inputFiles, inputTitles, printEmptyRegions, genomeFile, noCoverageValue);
+ if (printHeader)
+ ubg.PrintHeader();
+ ubg.Union();
}
void ShowHelp(void) {
-
- cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
-
- cerr << "Authors: Assaf Gordon, CSHL" << endl;
- cerr << " Aaron Quinlan (aaronquinlan@gmail.com)" << endl << endl;
+
+ cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
+
+ cerr << "Authors: Assaf Gordon, CSHL" << endl;
+ cerr << " Aaron Quinlan (aaronquinlan@gmail.com)" << endl << endl;
cerr << "Summary: Combines multiple BedGraph files into a single file," << endl;
cerr << "\t allowing coverage comparisons between them." << endl << endl;
@@ -172,123 +172,123 @@ void ShowHelp(void) {
cerr << "\t Assumes that each BedGraph file is sorted by chrom/start " << endl;
cerr << "\t and that the intervals in each are non-overlapping." << endl << endl;
- cerr << "Options: " << endl;
-
- cerr << "\t-header\t\t" << "Print a header line." << endl;
- cerr << "\t\t\t(chrom/start/end + names of each file)." << endl << endl;
-
- cerr << "\t-names\t\t" << "A list of names (one / file) to describe each file in -i." << endl;
- cerr << "\t\t\tThese names will be printed in the header line." << endl << endl;
-
- cerr << "\t-g\t\t" << "Use genome file to calculate empty regions." << endl;
- cerr << "\t\t\t- STRING." << endl << endl;
-
- cerr << "\t-empty\t\t" << "Report empty regions (i.e., start/end intervals w/o" << endl;
- cerr << "\t\t\tvalues in all files)." << endl;
- cerr << "\t\t\t- Requires the '-g FILE' parameter.\n" << endl;
-
- cerr << "\t-filler TEXT\t" << "Use TEXT when representing intervals having no value." << endl;
- cerr << "\t\t\t- Default is '0', but you can use 'N/A' or any other text." << endl << endl;
-
- cerr << "\t-examples\t" << "Show detailed usage examples." << endl << endl;
+ cerr << "Options: " << endl;
+
+ cerr << "\t-header\t\t" << "Print a header line." << endl;
+ cerr << "\t\t\t(chrom/start/end + names of each file)." << endl << endl;
+
+ cerr << "\t-names\t\t" << "A list of names (one / file) to describe each file in -i." << endl;
+ cerr << "\t\t\tThese names will be printed in the header line." << endl << endl;
+
+ cerr << "\t-g\t\t" << "Use genome file to calculate empty regions." << endl;
+ cerr << "\t\t\t- STRING." << endl << endl;
+
+ cerr << "\t-empty\t\t" << "Report empty regions (i.e., start/end intervals w/o" << endl;
+ cerr << "\t\t\tvalues in all files)." << endl;
+ cerr << "\t\t\t- Requires the '-g FILE' parameter.\n" << endl;
+
+ cerr << "\t-filler TEXT\t" << "Use TEXT when representing intervals having no value." << endl;
+ cerr << "\t\t\t- Default is '0', but you can use 'N/A' or any other text." << endl << endl;
+
+ cerr << "\t-examples\t" << "Show detailed usage examples." << endl << endl;
}
void ShowExamples()
{
- cerr << "Example usage:\n\n" \
+ cerr << "Example usage:\n\n" \
"== Input files: ==\n" \
"\n" \
" $ cat 1.bg\n" \
-" chr1 1000 1500 10\n" \
-" chr1 2000 2100 20\n" \
+" chr1 1000 1500 10\n" \
+" chr1 2000 2100 20\n" \
"\n" \
" $ cat 2.bg\n" \
-" chr1 900 1600 60\n" \
-" chr1 1700 2050 50\n" \
+" chr1 900 1600 60\n" \
+" chr1 1700 2050 50\n" \
"\n" \
" $ cat 3.bg\n" \
-" chr1 1980 2070 80\n" \
-" chr1 2090 2100 20\n" \
+" chr1 1980 2070 80\n" \
+" chr1 2090 2100 20\n" \
"\n" \
" $ cat sizes.txt\n" \
-" chr1 5000\n" \
+" chr1 5000\n" \
"\n" \
"== Union/combine the files: ==\n" \
"\n" \
" $ unionBedGraphs -i 1.bg 2.bg 3.bg\n" \
-" chr1 900 1000 0 60 0\n" \
-" chr1 1000 1500 10 60 0\n" \
-" chr1 1500 1600 0 60 0\n" \
-" chr1 1700 1980 0 50 0\n" \
-" chr1 1980 2000 0 50 80\n" \
-" chr1 2000 2050 20 50 80\n" \
-" chr1 2050 2070 20 0 80\n" \
-" chr1 2070 2090 20 0 0\n" \
-" chr1 2090 2100 20 0 20\n" \
+" chr1 900 1000 0 60 0\n" \
+" chr1 1000 1500 10 60 0\n" \
+" chr1 1500 1600 0 60 0\n" \
+" chr1 1700 1980 0 50 0\n" \
+" chr1 1980 2000 0 50 80\n" \
+" chr1 2000 2050 20 50 80\n" \
+" chr1 2050 2070 20 0 80\n" \
+" chr1 2070 2090 20 0 0\n" \
+" chr1 2090 2100 20 0 20\n" \
"\n" \
"== Union/combine the files, with a header line (titles are the file names): ==\n" \
"\n" \
" $ unionBedGraphs -header -i 1.bg 2.bg 3.bg\n" \
-" chrom start end 1 2 3\n" \
-" chr1 900 1000 0 60 0\n" \
-" chr1 1000 1500 10 60 0\n" \
-" chr1 1500 1600 0 60 0\n" \
-" chr1 1700 1980 0 50 0\n" \
-" chr1 1980 2000 0 50 80\n" \
-" chr1 2000 2050 20 50 80\n" \
-" chr1 2050 2070 20 0 80\n" \
-" chr1 2070 2090 20 0 0\n" \
-" chr1 2090 2100 20 0 20\n" \
+" chrom start end 1 2 3\n" \
+" chr1 900 1000 0 60 0\n" \
+" chr1 1000 1500 10 60 0\n" \
+" chr1 1500 1600 0 60 0\n" \
+" chr1 1700 1980 0 50 0\n" \
+" chr1 1980 2000 0 50 80\n" \
+" chr1 2000 2050 20 50 80\n" \
+" chr1 2050 2070 20 0 80\n" \
+" chr1 2070 2090 20 0 0\n" \
+" chr1 2090 2100 20 0 20\n" \
"\n" \
"== Union/combine the files, with a header line and custom names: ==\n" \
"\n" \
" $ unionBedGraphs -header -i 1.bg 2.bg 3.bg -names WT-1 WT-2 KO-1\n" \
-" chrom start end WT-1 WT-2 KO-1\n" \
-" chr1 900 1000 0 60 0\n" \
-" chr1 1000 1500 10 60 0\n" \
-" chr1 1500 1600 0 60 0\n" \
-" chr1 1700 1980 0 50 0\n" \
-" chr1 1980 2000 0 50 80\n" \
-" chr1 2000 2050 20 50 80\n" \
-" chr1 2050 2070 20 0 80\n" \
-" chr1 2070 2090 20 0 0\n" \
-" chr1 2090 2100 20 0 20\n" \
+" chrom start end WT-1 WT-2 KO-1\n" \
+" chr1 900 1000 0 60 0\n" \
+" chr1 1000 1500 10 60 0\n" \
+" chr1 1500 1600 0 60 0\n" \
+" chr1 1700 1980 0 50 0\n" \
+" chr1 1980 2000 0 50 80\n" \
+" chr1 2000 2050 20 50 80\n" \
+" chr1 2050 2070 20 0 80\n" \
+" chr1 2070 2090 20 0 0\n" \
+" chr1 2090 2100 20 0 20\n" \
"\n" \
"== Union/combine, showing empty regions (note, requires -g): ==\n" \
"\n" \
" $ unionBedGraphs -header -empty -g sizes.TXT -i 1.bg 2.bg 3.bg\n" \
-" chrom start end 1 2 3\n" \
-" chr1 0 900 0 0 0\n" \
-" chr1 900 1000 0 60 0\n" \
-" chr1 1000 1500 10 60 0\n" \
-" chr1 1500 1600 0 60 0\n" \
-" chr1 1600 1700 0 0 0\n" \
-" chr1 1700 1980 0 50 0\n" \
-" chr1 1980 2000 0 50 80\n" \
-" chr1 2000 2050 20 50 80\n" \
-" chr1 2050 2070 20 0 80\n" \
-" chr1 2070 2090 20 0 0\n" \
-" chr1 2090 2100 20 0 20\n" \
-" chr1 2100 5000 0 0 0\n" \
+" chrom start end 1 2 3\n" \
+" chr1 0 900 0 0 0\n" \
+" chr1 900 1000 0 60 0\n" \
+" chr1 1000 1500 10 60 0\n" \
+" chr1 1500 1600 0 60 0\n" \
+" chr1 1600 1700 0 0 0\n" \
+" chr1 1700 1980 0 50 0\n" \
+" chr1 1980 2000 0 50 80\n" \
+" chr1 2000 2050 20 50 80\n" \
+" chr1 2050 2070 20 0 80\n" \
+" chr1 2070 2090 20 0 0\n" \
+" chr1 2090 2100 20 0 20\n" \
+" chr1 2100 5000 0 0 0\n" \
"\n" \
;
}
std::string stl_basename(const std::string& path)
{
- string result;
+ string result;
- char* path_dup = strdup(path.c_str());
- char* basename_part = basename(path_dup);
- result = basename_part;
- free(path_dup);
+ char* path_dup = strdup(path.c_str());
+ char* basename_part = basename(path_dup);
+ result = basename_part;
+ free(path_dup);
- size_t pos = result.find_last_of('.');
- if (pos != string::npos )
- result = result.substr(0,pos);
+ size_t pos = result.find_last_of('.');
+ if (pos != string::npos )
+ result = result.substr(0,pos);
- return result;
+ return result;
}
diff --git a/src/utils/BamTools/BGZF.cpp b/src/utils/BamTools/BGZF.cpp
index 92afb96f83e058960aa4ebf0b2789de947944c0b..853d7b5194ee06e9e6a18b77369433b71337cc27 100644
--- a/src/utils/BamTools/BGZF.cpp
+++ b/src/utils/BamTools/BGZF.cpp
@@ -58,7 +58,7 @@ void BgzfData::Close(void) {
int blockLength = DeflateBlock();
fwrite(CompressedBlock, 1, blockLength, Stream);
}
-
+
// flush and close
fflush(Stream);
fclose(Stream);
@@ -84,14 +84,14 @@ int BgzfData::DeflateBlock(void) {
// set compression level
const int compressionLevel = ( IsWriteUncompressed ? 0 : Z_DEFAULT_COMPRESSION );
-
+
// loop to retry for blocks that do not compress enough
int inputLength = BlockOffset;
int compressedLength = 0;
unsigned int bufferSize = CompressedBlockSize;
while ( true ) {
-
+
// initialize zstream values
z_stream zs;
zs.zalloc = NULL;
@@ -182,7 +182,7 @@ void BgzfData::FlushBlock(void) {
printf("BGZF ERROR: expected to write %u bytes during flushing, but wrote %u bytes.\n", blockLength, numBytesWritten);
exit(1);
}
-
+
BlockAddress += blockLength;
}
}
@@ -227,25 +227,25 @@ bool BgzfData::Open(const string& filename, const char* mode, bool isWriteUncomp
// determine open mode
if ( strcmp(mode, "rb") == 0 )
IsWriteOnly = false;
- else if ( strcmp(mode, "wb") == 0)
+ else if ( strcmp(mode, "wb") == 0)
IsWriteOnly = true;
else {
printf("BGZF ERROR: unknown file mode: %s\n", mode);
- return false;
+ return false;
}
// ----------------------------------------------------------------
// open Stream to read to/write from file, stdin, or stdout
// stdin/stdout option contributed by Aaron Quinlan (2010-Jan-03)
-
+
// read/write BGZF data to/from a file
if ( (filename != "stdin") && (filename != "stdout") )
Stream = fopen(filename.c_str(), mode);
-
+
// read BGZF data from stdin
else if ( (filename == "stdin") && (strcmp(mode, "rb") == 0 ) )
Stream = freopen(NULL, mode, stdin);
-
+
// write BGZF data to stdout
else if ( (filename == "stdout") && (strcmp(mode, "wb") == 0) )
Stream = freopen(NULL, mode, stdout);
@@ -254,7 +254,7 @@ bool BgzfData::Open(const string& filename, const char* mode, bool isWriteUncomp
printf("BGZF ERROR: unable to open file %s\n", filename.c_str() );
return false;
}
-
+
// set flags, return success
IsOpen = true;
IsWriteUncompressed = isWriteUncompressed;
@@ -272,7 +272,7 @@ int BgzfData::Read(char* data, const unsigned int dataLength) {
int bytesAvailable = BlockLength - BlockOffset;
if ( bytesAvailable <= 0 ) {
- if ( !ReadBlock() ) return -1;
+ if ( !ReadBlock() ) return -1;
bytesAvailable = BlockLength - BlockOffset;
if ( bytesAvailable <= 0 ) break;
}
@@ -300,7 +300,7 @@ bool BgzfData::ReadBlock(void) {
char header[BLOCK_HEADER_LENGTH];
int64_t blockAddress = ftell64(Stream);
-
+
int count = fread(header, 1, sizeof(header), Stream);
if ( count == 0 ) {
BlockLength = 0;
@@ -329,7 +329,7 @@ bool BgzfData::ReadBlock(void) {
}
count = InflateBlock(blockLength);
- if ( count < 0 ) {
+ if ( count < 0 ) {
printf("BGZF ERROR: read block failed - could not decompress block data\n");
return false;
}
@@ -346,7 +346,7 @@ bool BgzfData::ReadBlock(void) {
bool BgzfData::Seek(int64_t position) {
if ( !IsOpen ) return false;
-
+
int blockOffset = (position & 0xFFFF);
int64_t blockAddress = (position >> 16) & 0xFFFFFFFFFFFFLL;
@@ -363,9 +363,9 @@ bool BgzfData::Seek(int64_t position) {
// get file position in BGZF file
int64_t BgzfData::Tell(void) {
- if ( !IsOpen )
+ if ( !IsOpen )
return false;
- else
+ else
return ( (BlockAddress << 16) | (BlockOffset & 0xFFFF) );
}
@@ -373,7 +373,7 @@ int64_t BgzfData::Tell(void) {
unsigned int BgzfData::Write(const char* data, const unsigned int dataLen) {
if ( !IsOpen || !IsWriteOnly ) return false;
-
+
// initialize
unsigned int numBytesWritten = 0;
const char* input = data;
@@ -381,7 +381,7 @@ unsigned int BgzfData::Write(const char* data, const unsigned int dataLen) {
// copy the data to the buffer
while ( numBytesWritten < dataLen ) {
-
+
unsigned int copyLength = min(blockLength - BlockOffset, dataLen - numBytesWritten);
char* buffer = UncompressedBlock;
memcpy(buffer + BlockOffset, input, copyLength);
diff --git a/src/utils/BamTools/BGZF.h b/src/utils/BamTools/BGZF.h
index 37bcff75bd2a3a93bb9665c21b250f2b69321246..8a709f4d3a2098b4f4550a4dbdcbad0ef8444f85 100644
--- a/src/utils/BamTools/BGZF.h
+++ b/src/utils/BamTools/BGZF.h
@@ -33,7 +33,7 @@
#define fseek64(a,b,c) _fseeki64(a,b,c)
#else
#define ftell64(a) ftello(a)
- #define fseek64(a,b,c) fseeko(a,b,c)
+ #define fseek64(a,b,c) fseeko(a,b,c)
#endif
#endif // BAMTOOLS_LFS
@@ -49,7 +49,7 @@
typedef unsigned int uint32_t;
typedef long long int64_t;
typedef unsigned long long uint64_t;
- #else
+ #else
#include <stdint.h>
#endif
#endif // BAMTOOLS_TYPES
@@ -97,7 +97,7 @@ struct BgzfData {
~BgzfData(void);
// main interface methods
- public:
+ public:
// closes BGZF file
void Close(void);
// opens the BGZF file (mode is either "rb" for reading, or "wb" for writing)
@@ -121,7 +121,7 @@ struct BgzfData {
int InflateBlock(const int& blockLength);
// reads a BGZF block
bool ReadBlock(void);
-
+
// static 'utility' methods
public:
// checks BGZF block header
diff --git a/src/utils/BamTools/BamAncillary.cpp b/src/utils/BamTools/BamAncillary.cpp
index d33eb159a7559cde10037692440ac33c978021c0..92b025580c9d754985555a993d72e3aa79ed499a 100644
--- a/src/utils/BamTools/BamAncillary.cpp
+++ b/src/utils/BamTools/BamAncillary.cpp
@@ -16,26 +16,26 @@ using namespace std;
// acccctttggacct---ataggga.................aaaa
// acccc---ggaccttttataggga.................aaaa
// 5M 3D 6M 2I 7M 20N 4M
-
+
namespace BamTools {
- void getBamBlocks(const BamAlignment &bam, const RefVector &refs,
+ void getBamBlocks(const BamAlignment &bam, const RefVector &refs,
vector<BED> &blocks, bool breakOnDeletionOps) {
-
- CHRPOS currPosition = bam.Position;
+
+ CHRPOS currPosition = bam.Position;
CHRPOS blockStart = bam.Position;
string chrom = refs.at(bam.RefID).RefName;
string name = bam.Name;
string strand = "+";
string score = ToString(bam.MapQuality);
- if (bam.IsReverseStrand()) strand = "-";
-
- vector<CigarOp>::const_iterator cigItr = bam.CigarData.begin();
- vector<CigarOp>::const_iterator cigEnd = bam.CigarData.end();
+ if (bam.IsReverseStrand()) strand = "-";
+
+ vector<CigarOp>::const_iterator cigItr = bam.CigarData.begin();
+ vector<CigarOp>::const_iterator cigEnd = bam.CigarData.end();
for ( ; cigItr != cigEnd; ++cigItr ) {
if (cigItr->Type == 'M') {
currPosition += cigItr->Length;
- blocks.push_back( BED(chrom, blockStart, currPosition, name, score, strand) );
- blockStart = currPosition;
+ blocks.push_back( BED(chrom, blockStart, currPosition, name, score, strand) );
+ blockStart = currPosition;
}
else if (cigItr->Type == 'D') {
if (breakOnDeletionOps == false)
@@ -53,9 +53,9 @@ namespace BamTools {
}
else {
cerr << "Input error: invalid CIGAR type (" << cigItr->Type
- << ") for: " << bam.Name << endl;
- exit(1);
+ << ") for: " << bam.Name << endl;
+ exit(1);
}
- }
+ }
}
}
diff --git a/src/utils/BamTools/BamAncillary.h b/src/utils/BamTools/BamAncillary.h
index 3f67825796aaa82644ab2f5e60626ec0ab1908bd..fcc04d7cde9b034c39e4573ac051f88291f496d4 100644
--- a/src/utils/BamTools/BamAncillary.h
+++ b/src/utils/BamTools/BamAncillary.h
@@ -14,6 +14,6 @@
#include "BamAux.h"
namespace BamTools {
- void getBamBlocks(const BamAlignment &bam, const RefVector &refs,
+ void getBamBlocks(const BamAlignment &bam, const RefVector &refs,
vector<BED> &blocks, bool includeDeletions = true);
}
diff --git a/src/utils/BamTools/BamAux.h b/src/utils/BamTools/BamAux.h
index 866ca15d13b9048c2ee4d0849c651c252dba6475..c3eb22c96cadc04a8b8f9c4fe363ead4a2c28a8e 100644
--- a/src/utils/BamTools/BamAux.h
+++ b/src/utils/BamTools/BamAux.h
@@ -56,7 +56,7 @@ const int BAM_CIGAR_SHIFT = 4;
const int BAM_CIGAR_MASK = ((1 << BAM_CIGAR_SHIFT) - 1);
// BAM index constants
-const int MAX_BIN = 37450; // =(8^6-1)/7+1
+const int MAX_BIN = 37450; // =(8^6-1)/7+1
const int BAM_MIN_CHUNK_GAP = 32768;
const int BAM_LIDX_SHIFT = 14;
@@ -74,38 +74,38 @@ struct BamAlignment {
~BamAlignment(void);
// Queries against alignment flags
- public:
- bool IsDuplicate(void) const; // Returns true if this read is a PCR duplicate
- bool IsFailedQC(void) const; // Returns true if this read failed quality control
- bool IsFirstMate(void) const; // Returns true if alignment is first mate on read
- bool IsMapped(void) const; // Returns true if alignment is mapped
- bool IsMateMapped(void) const; // Returns true if alignment's mate is mapped
- bool IsMateReverseStrand(void) const; // Returns true if alignment's mate mapped to reverse strand
- bool IsPaired(void) const; // Returns true if alignment part of paired-end read
- bool IsPrimaryAlignment(void) const; // Returns true if reported position is primary alignment
- bool IsProperPair(void) const; // Returns true if alignment is part of read that satisfied paired-end resolution
- bool IsReverseStrand(void) const; // Returns true if alignment mapped to reverse strand
- bool IsSecondMate(void) const; // Returns true if alignment is second mate on read
+ public:
+ bool IsDuplicate(void) const; // Returns true if this read is a PCR duplicate
+ bool IsFailedQC(void) const; // Returns true if this read failed quality control
+ bool IsFirstMate(void) const; // Returns true if alignment is first mate on read
+ bool IsMapped(void) const; // Returns true if alignment is mapped
+ bool IsMateMapped(void) const; // Returns true if alignment's mate is mapped
+ bool IsMateReverseStrand(void) const; // Returns true if alignment's mate mapped to reverse strand
+ bool IsPaired(void) const; // Returns true if alignment part of paired-end read
+ bool IsPrimaryAlignment(void) const; // Returns true if reported position is primary alignment
+ bool IsProperPair(void) const; // Returns true if alignment is part of read that satisfied paired-end resolution
+ bool IsReverseStrand(void) const; // Returns true if alignment mapped to reverse strand
+ bool IsSecondMate(void) const; // Returns true if alignment is second mate on read
// Manipulate alignment flags
- public:
- void SetIsDuplicate(bool ok); // Sets "PCR duplicate" flag
- void SetIsFailedQC(bool ok); // Sets "failed quality control" flag
- void SetIsFirstMate(bool ok); // Sets "alignment is first mate" flag
- void SetIsMateUnmapped(bool ok); // Sets "alignment's mate is mapped" flag
- void SetIsMateReverseStrand(bool ok); // Sets "alignment's mate mapped to reverse strand" flag
- void SetIsPaired(bool ok); // Sets "alignment part of paired-end read" flag
- void SetIsProperPair(bool ok); // Sets "alignment is part of read that satisfied paired-end resolution" flag
- void SetIsReverseStrand(bool ok); // Sets "alignment mapped to reverse strand" flag
- void SetIsSecondaryAlignment(bool ok); // Sets "position is primary alignment" flag
- void SetIsSecondMate(bool ok); // Sets "alignment is second mate on read" flag
- void SetIsUnmapped(bool ok); // Sets "alignment is mapped" flag
+ public:
+ void SetIsDuplicate(bool ok); // Sets "PCR duplicate" flag
+ void SetIsFailedQC(bool ok); // Sets "failed quality control" flag
+ void SetIsFirstMate(bool ok); // Sets "alignment is first mate" flag
+ void SetIsMateUnmapped(bool ok); // Sets "alignment's mate is mapped" flag
+ void SetIsMateReverseStrand(bool ok); // Sets "alignment's mate mapped to reverse strand" flag
+ void SetIsPaired(bool ok); // Sets "alignment part of paired-end read" flag
+ void SetIsProperPair(bool ok); // Sets "alignment is part of read that satisfied paired-end resolution" flag
+ void SetIsReverseStrand(bool ok); // Sets "alignment mapped to reverse strand" flag
+ void SetIsSecondaryAlignment(bool ok); // Sets "position is primary alignment" flag
+ void SetIsSecondMate(bool ok); // Sets "alignment is second mate on read" flag
+ void SetIsUnmapped(bool ok); // Sets "alignment is mapped" flag
// Tag data access methods
public:
// -------------------------------------------------------------------------------------
// N.B. - The following tag-modifying methods may not be used on BamAlignments fetched
- // using BamReader::GetNextAlignmentCore(). Attempting to use them will not result in
+ // using BamReader::GetNextAlignmentCore(). Attempting to use them will not result in
// error message (to keep output clean) but will ALWAYS return false. Only user-
// generated BamAlignments or those retrieved using BamReader::GetNextAlignment() are valid.
@@ -117,7 +117,7 @@ struct BamAlignment {
bool AddTag(const std::string& tag, const std::string& type, const uint32_t& value); // type must be A or i
bool AddTag(const std::string& tag, const std::string& type, const int32_t& value); // type must be A or i
bool AddTag(const std::string& tag, const std::string& type, const float& value); // type must be A, i, or f
-
+
// edit tag data (sets existing TAG with TYPE to VALUE or adds new TAG if not already present)
// TYPE is one of {A, i, f, Z, H} depending on VALUE - see SAM/BAM spec for details
// returns true if edit was successfaul, false if error
@@ -128,14 +128,14 @@ struct BamAlignment {
// specific tag data access methods - these only remain for legacy support
bool GetEditDistance(uint32_t& editDistance) const; // get "NM" tag data (implemented as GetTag("NM", editDistance))
- bool GetReadGroup(std::string& readGroup) const; // get "RG" tag data (implemented as GetTag("RG", readGroup))
-
- // generic tag data access methods
- bool GetTag(const std::string& tag, std::string& destination) const; // access variable-length char or hex strings
+ bool GetReadGroup(std::string& readGroup) const; // get "RG" tag data (implemented as GetTag("RG", readGroup))
+
+ // generic tag data access methods
+ bool GetTag(const std::string& tag, std::string& destination) const; // access variable-length char or hex strings
bool GetTag(const std::string& tag, uint32_t& destination) const; // access unsigned integer data
bool GetTag(const std::string& tag, int32_t& destination) const; // access signed integer data
bool GetTag(const std::string& tag, float& destination) const; // access floating point data
-
+
// remove tag data
// returns true if removal was successful, false if error
// N.B. - returns false if TAG does not exist (no removal can occur)
@@ -143,9 +143,9 @@ struct BamAlignment {
// Additional data access methods
public:
- int GetEndPosition(bool usePadded = false) const; // calculates alignment end position, based on starting position and CIGAR operations
+ int GetEndPosition(bool usePadded = false) const; // calculates alignment end position, based on starting position and CIGAR operations
- // 'internal' utility methods
+ // 'internal' utility methods
private:
static bool FindTag(const std::string& tag, char* &pTagData, const unsigned int& tagDataLength, unsigned int& numBytesParsed);
static bool SkipToNextTag(const char storageType, char* &pTagData, unsigned int& numBytesParsed);
@@ -162,16 +162,16 @@ struct BamAlignment {
int32_t Position; // Position (0-based) where alignment starts
uint16_t Bin; // Bin in BAM file where this alignment resides
uint16_t MapQuality; // Mapping quality score
- uint32_t AlignmentFlag; // Alignment bit-flag - see Is<something>() methods to query this value, SetIs<something>() methods to manipulate
+ uint32_t AlignmentFlag; // Alignment bit-flag - see Is<something>() methods to query this value, SetIs<something>() methods to manipulate
std::vector<CigarOp> CigarData; // CIGAR operations for this alignment
int32_t MateRefID; // ID number for reference sequence where alignment's mate was aligned
int32_t MatePosition; // Position (0-based) where alignment's mate starts
int32_t InsertSize; // Mate-pair insert size
-
+
// internal data
private:
struct BamAlignmentSupportData {
-
+
// data members
std::string AllCharData;
uint32_t BlockLength;
@@ -179,7 +179,7 @@ struct BamAlignment {
uint32_t QueryNameLength;
uint32_t QuerySequenceLength;
bool HasCoreOnly;
-
+
// constructor
BamAlignmentSupportData(void)
: BlockLength(0)
@@ -189,10 +189,10 @@ struct BamAlignment {
, HasCoreOnly(false)
{ }
};
-
+
// contains raw character data & lengths
- BamAlignmentSupportData SupportData;
-
+ BamAlignmentSupportData SupportData;
+
// allow these classes access to BamAlignment private members (SupportData)
// but client code should not need to touch this data
friend class BamReader;
@@ -211,7 +211,7 @@ struct BamAlignment {
, READ_2 = 128
, SECONDARY = 256
, QC_FAILED = 512
- , DUPLICATE = 1024
+ , DUPLICATE = 1024
};
};
@@ -219,28 +219,28 @@ struct BamAlignment {
// Auxiliary data structs & typedefs
struct CigarOp {
-
+
// data members
char Type; // Operation type (MIDNSHP)
uint32_t Length; // Operation length (number of bases)
-
+
// constructor
- CigarOp(const char type = '\0',
- const uint32_t length = 0)
+ CigarOp(const char type = '\0',
+ const uint32_t length = 0)
: Type(type)
- , Length(length)
+ , Length(length)
{ }
};
struct RefData {
-
+
// data members
std::string RefName; // Name of reference sequence
int32_t RefLength; // Length of reference sequence
bool RefHasAlignments; // True if BAM file contains alignments mapped to reference sequence
-
+
// constructor
- RefData(const int32_t& length = 0,
+ RefData(const int32_t& length = 0,
bool ok = false)
: RefLength(length)
, RefHasAlignments(ok)
@@ -251,15 +251,15 @@ typedef std::vector<RefData> RefVector;
typedef std::vector<BamAlignment> BamAlignmentVector;
struct BamRegion {
-
+
// data members
int LeftRefID;
int LeftPosition;
int RightRefID;
int RightPosition;
-
+
// constructor
- BamRegion(const int& leftID = -1,
+ BamRegion(const int& leftID = -1,
const int& leftPos = -1,
const int& rightID = -1,
const int& rightPos = -1)
@@ -292,24 +292,24 @@ inline void SwapEndian_16(uint16_t& x) {
// swaps endianness of 32-bit value 'in-place'
inline void SwapEndian_32(int32_t& x) {
- x = ( (x >> 24) |
- ((x << 8) & 0x00FF0000) |
- ((x >> 8) & 0x0000FF00) |
+ x = ( (x >> 24) |
+ ((x << 8) & 0x00FF0000) |
+ ((x >> 8) & 0x0000FF00) |
(x << 24)
);
}
inline void SwapEndian_32(uint32_t& x) {
- x = ( (x >> 24) |
- ((x << 8) & 0x00FF0000) |
- ((x >> 8) & 0x0000FF00) |
+ x = ( (x >> 24) |
+ ((x << 8) & 0x00FF0000) |
+ ((x >> 8) & 0x0000FF00) |
(x << 24)
);
}
// swaps endianness of 64-bit value 'in-place'
inline void SwapEndian_64(int64_t& x) {
- x = ( (x >> 56) |
+ x = ( (x >> 56) |
((x << 40) & 0x00FF000000000000ll) |
((x << 24) & 0x0000FF0000000000ll) |
((x << 8) & 0x000000FF00000000ll) |
@@ -321,7 +321,7 @@ inline void SwapEndian_64(int64_t& x) {
}
inline void SwapEndian_64(uint64_t& x) {
- x = ( (x >> 56) |
+ x = ( (x >> 56) |
((x << 40) & 0x00FF000000000000ll) |
((x << 24) & 0x0000FF0000000000ll) |
((x << 8) & 0x000000FF00000000ll) |
@@ -334,19 +334,19 @@ inline void SwapEndian_64(uint64_t& x) {
// swaps endianness of 'next 2 bytes' in a char buffer (in-place)
inline void SwapEndian_16p(char* data) {
- uint16_t& value = (uint16_t&)*data;
+ uint16_t& value = (uint16_t&)*data;
SwapEndian_16(value);
}
// swaps endianness of 'next 4 bytes' in a char buffer (in-place)
inline void SwapEndian_32p(char* data) {
- uint32_t& value = (uint32_t&)*data;
+ uint32_t& value = (uint32_t&)*data;
SwapEndian_32(value);
}
// swaps endianness of 'next 8 bytes' in a char buffer (in-place)
inline void SwapEndian_64p(char* data) {
- uint64_t& value = (uint64_t&)*data;
+ uint64_t& value = (uint64_t&)*data;
SwapEndian_64(value);
}
@@ -390,7 +390,7 @@ inline bool BamAlignment::IsProperPair(void) const { return ( (AlignmentF
inline bool BamAlignment::IsReverseStrand(void) const { return ( (AlignmentFlag & REVERSE) != 0 ); }
inline bool BamAlignment::IsSecondMate(void) const { return ( (AlignmentFlag & READ_2) != 0 ); }
-// Manipulate alignment flags
+// Manipulate alignment flags
inline void BamAlignment::SetIsDuplicate(bool ok) { if (ok) AlignmentFlag |= DUPLICATE; else AlignmentFlag &= ~DUPLICATE; }
inline void BamAlignment::SetIsFailedQC(bool ok) { if (ok) AlignmentFlag |= QC_FAILED; else AlignmentFlag &= ~QC_FAILED; }
inline void BamAlignment::SetIsFirstMate(bool ok) { if (ok) AlignmentFlag |= READ_1; else AlignmentFlag &= ~READ_1; }
@@ -404,7 +404,7 @@ inline void BamAlignment::SetIsSecondMate(bool ok) { if (ok) AlignmentFl
inline void BamAlignment::SetIsUnmapped(bool ok) { if (ok) AlignmentFlag |= UNMAPPED; else AlignmentFlag &= ~UNMAPPED; }
// calculates alignment end position, based on starting position and CIGAR operations
-inline
+inline
int BamAlignment::GetEndPosition(bool usePadded) const {
// initialize alignment end to starting position
@@ -414,10 +414,10 @@ int BamAlignment::GetEndPosition(bool usePadded) const {
std::vector<CigarOp>::const_iterator cigarIter = CigarData.begin();
std::vector<CigarOp>::const_iterator cigarEnd = CigarData.end();
for ( ; cigarIter != cigarEnd; ++cigarIter) {
- const char cigarType = (*cigarIter).Type;
- if ( cigarType == 'M' || cigarType == 'D' || cigarType == 'N' ) {
- alignEnd += (*cigarIter).Length;
- }
+ const char cigarType = (*cigarIter).Type;
+ if ( cigarType == 'M' || cigarType == 'D' || cigarType == 'N' ) {
+ alignEnd += (*cigarIter).Length;
+ }
else if ( usePadded && cigarType == 'I' ) {
alignEnd += (*cigarIter).Length;
}
@@ -427,53 +427,53 @@ int BamAlignment::GetEndPosition(bool usePadded) const {
inline
bool BamAlignment::AddTag(const std::string& tag, const std::string& type, const std::string& value) {
-
+
if ( SupportData.HasCoreOnly ) return false;
if ( tag.size() != 2 || type.size() != 1 ) return false;
if ( type != "Z" && type != "H" ) return false;
-
+
// localize the tag data
char* pTagData = (char*)TagData.data();
const unsigned int tagDataLength = TagData.size();
unsigned int numBytesParsed = 0;
-
+
// if tag already exists, return false
// use EditTag explicitly instead
if ( FindTag(tag, pTagData, tagDataLength, numBytesParsed) ) return false;
-
+
// otherwise, copy tag data to temp buffer
std::string newTag = tag + type + value;
const int newTagDataLength = tagDataLength + newTag.size() + 1; // leave room for null-term
char originalTagData[newTagDataLength];
memcpy(originalTagData, TagData.c_str(), tagDataLength + 1); // '+1' for TagData null-term
-
+
// append newTag
strcat(originalTagData + tagDataLength, newTag.data()); // removes original null-term, appends newTag + null-term
-
+
// store temp buffer back in TagData
const char* newTagData = (const char*)originalTagData;
TagData.assign(newTagData, newTagDataLength);
-
+
// return success
return true;
}
inline
bool BamAlignment::AddTag(const std::string& tag, const std::string& type, const uint32_t& value) {
-
+
if ( SupportData.HasCoreOnly ) return false;
if ( tag.size() != 2 || type.size() != 1 ) return false;
if ( type == "f" || type == "Z" || type == "H" ) return false;
-
+
// localize the tag data
char* pTagData = (char*)TagData.data();
const unsigned int tagDataLength = TagData.size();
unsigned int numBytesParsed = 0;
-
+
// if tag already exists, return false
// use EditTag explicitly instead
if ( FindTag(tag, pTagData, tagDataLength, numBytesParsed) ) return false;
-
+
// otherwise, convert value to string
union { unsigned int value; char valueBuffer[sizeof(unsigned int)]; } un;
un.value = value;
@@ -483,15 +483,15 @@ bool BamAlignment::AddTag(const std::string& tag, const std::string& type, const
const int newTagDataLength = tagDataLength + newTag.size() + 4; // leave room for new integer
char originalTagData[newTagDataLength];
memcpy(originalTagData, TagData.c_str(), tagDataLength + 1); // '+1' for TagData null-term
-
+
// append newTag
strcat(originalTagData + tagDataLength, newTag.data());
memcpy(originalTagData + tagDataLength + newTag.size(), un.valueBuffer, sizeof(unsigned int));
-
+
// store temp buffer back in TagData
const char* newTagData = (const char*)originalTagData;
TagData.assign(newTagData, newTagDataLength);
-
+
// return success
return true;
}
@@ -503,20 +503,20 @@ bool BamAlignment::AddTag(const std::string& tag, const std::string& type, const
inline
bool BamAlignment::AddTag(const std::string& tag, const std::string& type, const float& value) {
-
+
if ( SupportData.HasCoreOnly ) return false;
if ( tag.size() != 2 || type.size() != 1 ) return false;
if ( type == "Z" || type == "H" ) return false;
-
+
// localize the tag data
char* pTagData = (char*)TagData.data();
const unsigned int tagDataLength = TagData.size();
unsigned int numBytesParsed = 0;
-
+
// if tag already exists, return false
// use EditTag explicitly instead
if ( FindTag(tag, pTagData, tagDataLength, numBytesParsed) ) return false;
-
+
// otherwise, convert value to string
union { float value; char valueBuffer[sizeof(float)]; } un;
un.value = value;
@@ -526,120 +526,120 @@ bool BamAlignment::AddTag(const std::string& tag, const std::string& type, const
const int newTagDataLength = tagDataLength + newTag.size() + 4; // leave room for new float
char originalTagData[newTagDataLength];
memcpy(originalTagData, TagData.c_str(), tagDataLength + 1); // '+1' for TagData null-term
-
+
// append newTag
strcat(originalTagData + tagDataLength, newTag.data());
memcpy(originalTagData + tagDataLength + newTag.size(), un.valueBuffer, sizeof(float));
-
+
// store temp buffer back in TagData
const char* newTagData = (const char*)originalTagData;
TagData.assign(newTagData, newTagDataLength);
-
+
// return success
return true;
}
inline
bool BamAlignment::EditTag(const std::string& tag, const std::string& type, const std::string& value) {
-
+
if ( SupportData.HasCoreOnly ) return false;
if ( tag.size() != 2 || type.size() != 1 ) return false;
if ( type != "Z" && type != "H" ) return false;
-
+
// localize the tag data
char* pOriginalTagData = (char*)TagData.data();
char* pTagData = pOriginalTagData;
const unsigned int originalTagDataLength = TagData.size();
-
+
unsigned int newTagDataLength = 0;
unsigned int numBytesParsed = 0;
-
+
// if tag found, store data in readGroup, return success
if ( FindTag(tag, pTagData, originalTagDataLength, numBytesParsed) ) {
-
+
// make sure array is more than big enough
- char newTagData[originalTagDataLength + value.size()];
+ char newTagData[originalTagDataLength + value.size()];
// copy original tag data up til desired tag
const unsigned int beginningTagDataLength = numBytesParsed;
newTagDataLength += beginningTagDataLength;
memcpy(newTagData, pOriginalTagData, numBytesParsed);
-
+
// copy new VALUE in place of current tag data
const unsigned int dataLength = strlen(value.c_str());
memcpy(newTagData + beginningTagDataLength, (char*)value.c_str(), dataLength+1 );
-
- // skip to next tag (if tag for removal is last, return true)
+
+ // skip to next tag (if tag for removal is last, return true)
const char* pTagStorageType = pTagData - 1;
if ( !SkipToNextTag(*pTagStorageType, pTagData, numBytesParsed) ) return true;
-
+
// copy everything from current tag (the next one after tag for removal) to end
const unsigned int skippedDataLength = (numBytesParsed - beginningTagDataLength);
const unsigned int endTagOffset = beginningTagDataLength + dataLength + 1;
const unsigned int endTagDataLength = originalTagDataLength - beginningTagDataLength - skippedDataLength;
memcpy(newTagData + endTagOffset, pTagData, endTagDataLength);
-
+
// ensure null-terminator
newTagData[ endTagOffset + endTagDataLength + 1 ] = 0;
-
+
// save new tag data
TagData.assign(newTagData, endTagOffset + endTagDataLength);
return true;
}
-
+
// tag not found, attempt AddTag
else return AddTag(tag, type, value);
}
inline
bool BamAlignment::EditTag(const std::string& tag, const std::string& type, const uint32_t& value) {
-
+
if ( SupportData.HasCoreOnly ) return false;
if ( tag.size() != 2 || type.size() != 1 ) return false;
if ( type == "f" || type == "Z" || type == "H" ) return false;
-
+
// localize the tag data
char* pOriginalTagData = (char*)TagData.data();
char* pTagData = pOriginalTagData;
const unsigned int originalTagDataLength = TagData.size();
-
+
unsigned int newTagDataLength = 0;
unsigned int numBytesParsed = 0;
-
+
// if tag found, store data in readGroup, return success
if ( FindTag(tag, pTagData, originalTagDataLength, numBytesParsed) ) {
-
+
// make sure array is more than big enough
- char newTagData[originalTagDataLength + sizeof(value)];
+ char newTagData[originalTagDataLength + sizeof(value)];
// copy original tag data up til desired tag
const unsigned int beginningTagDataLength = numBytesParsed;
newTagDataLength += beginningTagDataLength;
memcpy(newTagData, pOriginalTagData, numBytesParsed);
-
+
// copy new VALUE in place of current tag data
union { unsigned int value; char valueBuffer[sizeof(unsigned int)]; } un;
un.value = value;
memcpy(newTagData + beginningTagDataLength, un.valueBuffer, sizeof(unsigned int));
-
- // skip to next tag (if tag for removal is last, return true)
+
+ // skip to next tag (if tag for removal is last, return true)
const char* pTagStorageType = pTagData - 1;
if ( !SkipToNextTag(*pTagStorageType, pTagData, numBytesParsed) ) return true;
-
+
// copy everything from current tag (the next one after tag for removal) to end
const unsigned int skippedDataLength = (numBytesParsed - beginningTagDataLength);
const unsigned int endTagOffset = beginningTagDataLength + sizeof(unsigned int);
const unsigned int endTagDataLength = originalTagDataLength - beginningTagDataLength - skippedDataLength;
memcpy(newTagData + endTagOffset, pTagData, endTagDataLength);
-
+
// ensure null-terminator
newTagData[ endTagOffset + endTagDataLength + 1 ] = 0;
-
+
// save new tag data
TagData.assign(newTagData, endTagOffset + endTagDataLength);
return true;
}
-
+
// tag not found, attempt AddTag
else return AddTag(tag, type, value);
}
@@ -651,67 +651,67 @@ bool BamAlignment::EditTag(const std::string& tag, const std::string& type, cons
inline
bool BamAlignment::EditTag(const std::string& tag, const std::string& type, const float& value) {
-
+
if ( SupportData.HasCoreOnly ) return false;
if ( tag.size() != 2 || type.size() != 1 ) return false;
if ( type == "Z" || type == "H" ) return false;
-
+
// localize the tag data
char* pOriginalTagData = (char*)TagData.data();
char* pTagData = pOriginalTagData;
const unsigned int originalTagDataLength = TagData.size();
-
+
unsigned int newTagDataLength = 0;
unsigned int numBytesParsed = 0;
-
+
// if tag found, store data in readGroup, return success
if ( FindTag(tag, pTagData, originalTagDataLength, numBytesParsed) ) {
-
+
// make sure array is more than big enough
- char newTagData[originalTagDataLength + sizeof(value)];
+ char newTagData[originalTagDataLength + sizeof(value)];
// copy original tag data up til desired tag
const unsigned int beginningTagDataLength = numBytesParsed;
newTagDataLength += beginningTagDataLength;
memcpy(newTagData, pOriginalTagData, numBytesParsed);
-
+
// copy new VALUE in place of current tag data
union { float value; char valueBuffer[sizeof(float)]; } un;
un.value = value;
memcpy(newTagData + beginningTagDataLength, un.valueBuffer, sizeof(float));
-
- // skip to next tag (if tag for removal is last, return true)
+
+ // skip to next tag (if tag for removal is last, return true)
const char* pTagStorageType = pTagData - 1;
if ( !SkipToNextTag(*pTagStorageType, pTagData, numBytesParsed) ) return true;
-
+
// copy everything from current tag (the next one after tag for removal) to end
const unsigned int skippedDataLength = (numBytesParsed - beginningTagDataLength);
const unsigned int endTagOffset = beginningTagDataLength + sizeof(float);
const unsigned int endTagDataLength = originalTagDataLength - beginningTagDataLength - skippedDataLength;
memcpy(newTagData + endTagOffset, pTagData, endTagDataLength);
-
+
// ensure null-terminator
newTagData[ endTagOffset + endTagDataLength + 1 ] = 0;
-
+
// save new tag data
TagData.assign(newTagData, endTagOffset + endTagDataLength);
return true;
}
-
+
// tag not found, attempt AddTag
else return AddTag(tag, type, value);
}
// get "NM" tag data - originally contributed by Aaron Quinlan
// stores data in 'editDistance', returns success/fail
-inline
-bool BamAlignment::GetEditDistance(uint32_t& editDistance) const {
+inline
+bool BamAlignment::GetEditDistance(uint32_t& editDistance) const {
return GetTag("NM", (uint32_t&)editDistance);
}
// get "RG" tag data
// stores data in 'readGroup', returns success/fail
-inline
+inline
bool BamAlignment::GetReadGroup(std::string& readGroup) const {
return GetTag("RG", readGroup);
}
@@ -720,14 +720,14 @@ inline
bool BamAlignment::GetTag(const std::string& tag, std::string& destination) const {
// make sure tag data exists
- if ( SupportData.HasCoreOnly || TagData.empty() )
+ if ( SupportData.HasCoreOnly || TagData.empty() )
return false;
// localize the tag data
char* pTagData = (char*)TagData.data();
const unsigned int tagDataLength = TagData.size();
unsigned int numBytesParsed = 0;
-
+
// if tag found, store data in readGroup, return success
if ( FindTag(tag, pTagData, tagDataLength, numBytesParsed) ) {
const unsigned int dataLength = strlen(pTagData);
@@ -736,26 +736,26 @@ bool BamAlignment::GetTag(const std::string& tag, std::string& destination) cons
memcpy( (char*)destination.data(), pTagData, dataLength );
return true;
}
-
+
// tag not found, return failure
return false;
}
inline
bool BamAlignment::GetTag(const std::string& tag, uint32_t& destination) const {
-
+
// make sure tag data exists
- if ( SupportData.HasCoreOnly || TagData.empty() )
+ if ( SupportData.HasCoreOnly || TagData.empty() )
return false;
// localize the tag data
char* pTagData = (char*)TagData.data();
const unsigned int tagDataLength = TagData.size();
unsigned int numBytesParsed = 0;
-
+
// if tag found, determine data byte-length, store data in readGroup, return success
if ( FindTag(tag, pTagData, tagDataLength, numBytesParsed) ) {
-
+
// determine data byte-length
const char type = *(pTagData - 1);
int destinationLength = 0;
@@ -791,13 +791,13 @@ bool BamAlignment::GetTag(const std::string& tag, uint32_t& destination) const {
printf("ERROR: Unknown tag storage class encountered: [%c]\n", type);
return false;
}
-
+
// store in destination
destination = 0;
memcpy(&destination, pTagData, destinationLength);
return true;
}
-
+
// tag not found, return failure
return false;
}
@@ -809,20 +809,20 @@ bool BamAlignment::GetTag(const std::string& tag, int32_t& destination) const {
inline
bool BamAlignment::GetTag(const std::string& tag, float& destination) const {
-
+
// make sure tag data exists
- if ( SupportData.HasCoreOnly || TagData.empty() )
+ if ( SupportData.HasCoreOnly || TagData.empty() )
return false;
// localize the tag data
char* pTagData = (char*)TagData.data();
const unsigned int tagDataLength = TagData.size();
unsigned int numBytesParsed = 0;
-
+
// if tag found, determine data byte-length, store data in readGroup, return success
if ( FindTag(tag, pTagData, tagDataLength, numBytesParsed) ) {
//pTagData += numBytesParsed;
-
+
// determine data byte-length
const char type = *(pTagData - 1);
int destinationLength = 0;
@@ -847,7 +847,7 @@ bool BamAlignment::GetTag(const std::string& tag, float& destination) const {
case 'I':
destinationLength = 4;
break;
-
+
// unsupported type (var-length strings)
case 'Z':
case 'H':
@@ -859,34 +859,34 @@ bool BamAlignment::GetTag(const std::string& tag, float& destination) const {
printf("ERROR: Unknown tag storage class encountered: [%c]\n", type);
return false;
}
-
+
// store in destination
destination = 0.0;
memcpy(&destination, pTagData, destinationLength);
return true;
}
-
+
// tag not found, return failure
return false;
}
inline
bool BamAlignment::RemoveTag(const std::string& tag) {
-
+
// BamAlignments fetched using BamReader::GetNextAlignmentCore() are not allowed
// also, return false if no data present to remove
if ( SupportData.HasCoreOnly || TagData.empty() ) return false;
-
+
// localize the tag data
char* pOriginalTagData = (char*)TagData.data();
char* pTagData = pOriginalTagData;
const unsigned int originalTagDataLength = TagData.size();
unsigned int newTagDataLength = 0;
unsigned int numBytesParsed = 0;
-
+
// if tag found, store data in readGroup, return success
if ( FindTag(tag, pTagData, originalTagDataLength, numBytesParsed) ) {
-
+
char newTagData[originalTagDataLength];
// copy original tag data up til desired tag
@@ -895,23 +895,23 @@ bool BamAlignment::RemoveTag(const std::string& tag) {
const unsigned int beginningTagDataLength = numBytesParsed;
newTagDataLength += beginningTagDataLength;
memcpy(newTagData, pOriginalTagData, numBytesParsed);
-
- // skip to next tag (if tag for removal is last, return true)
+
+ // skip to next tag (if tag for removal is last, return true)
const char* pTagStorageType = pTagData + 2;
pTagData += 3;
numBytesParsed += 3;
if ( !SkipToNextTag(*pTagStorageType, pTagData, numBytesParsed) ) return true;
-
+
// copy everything from current tag (the next one after tag for removal) to end
const unsigned int skippedDataLength = (numBytesParsed - beginningTagDataLength);
const unsigned int endTagDataLength = originalTagDataLength - beginningTagDataLength - skippedDataLength;
memcpy(newTagData + beginningTagDataLength, pTagData, endTagDataLength );
-
+
// save new tag data
TagData.assign(newTagData, beginningTagDataLength + endTagDataLength);
return true;
}
-
+
// tag not found, no removal - return failure
return false;
}
@@ -927,22 +927,22 @@ bool BamAlignment::FindTag(const std::string& tag, char* &pTagData, const unsign
numBytesParsed += 3;
// check the current tag, return true on match
- if ( std::strncmp(pTagType, tag.c_str(), 2) == 0 )
+ if ( std::strncmp(pTagType, tag.c_str(), 2) == 0 )
return true;
// get the storage class and find the next tag
- if ( *pTagStorageType == '\0' ) return false;
+ if ( *pTagStorageType == '\0' ) return false;
if ( !SkipToNextTag(*pTagStorageType, pTagData, numBytesParsed) ) return false;
if ( *pTagData == '\0' ) return false;
}
-
+
// checked all tags, none match
return false;
}
inline
bool BamAlignment::SkipToNextTag(const char storageType, char* &pTagData, unsigned int& numBytesParsed) {
-
+
switch(storageType) {
case 'A':
@@ -976,12 +976,12 @@ bool BamAlignment::SkipToNextTag(const char storageType, char* &pTagData, unsign
++pTagData;
break;
- default:
+ default:
// error case
printf("ERROR: Unknown tag storage class encountered: [%c]\n", storageType);
return false;
}
-
+
// return success
return true;
}
diff --git a/src/utils/BamTools/BamIndex.cpp b/src/utils/BamTools/BamIndex.cpp
index d74e751cd902c546760afa42e3ba7c5bbe90b0ca..a3fa09e9a11fb307e106fe965b1cbd346c8c2bc4 100644
--- a/src/utils/BamTools/BamIndex.cpp
+++ b/src/utils/BamTools/BamIndex.cpp
@@ -5,8 +5,8 @@
// ---------------------------------------------------------------------------
// Last modified: 17 August 2010 (DB)
// ---------------------------------------------------------------------------
-// Provides index functionality - both for the default (standardized) BAM
-// index format (.bai) as well as a BamTools-specific (nonstandard) index
+// Provides index functionality - both for the default (standardized) BAM
+// index format (.bai) as well as a BamTools-specific (nonstandard) index
// format (.bti).
// ***************************************************************************
@@ -24,21 +24,21 @@ using namespace BamTools;
// -------------------------------
// BamIndex implementation
-BamIndex::BamIndex(BamTools::BgzfData* bgzf, BamTools::BamReader* reader, bool isBigEndian)
+BamIndex::BamIndex(BamTools::BgzfData* bgzf, BamTools::BamReader* reader, bool isBigEndian)
: m_BGZF(bgzf)
, m_reader(reader)
, m_isBigEndian(isBigEndian)
-{
- if ( m_reader && m_reader->IsOpen() )
+{
+ if ( m_reader && m_reader->IsOpen() )
m_references = m_reader->GetReferenceData();
}
bool BamIndex::HasAlignments(const int& referenceID) {
-
+
// return false if invalid ID
- if ( (referenceID < 0) || (referenceID >= (int)m_references.size()) )
+ if ( (referenceID < 0) || (referenceID >= (int)m_references.size()) )
return false;
-
+
// else return status of reference (has alignments?)
else
return m_references.at(referenceID).RefHasAlignments;
@@ -48,9 +48,9 @@ bool BamIndex::HasAlignments(const int& referenceID) {
// #########################################################################################
// -------------------------------
-// BamDefaultIndex structs & typedefs
-
-namespace BamTools {
+// BamDefaultIndex structs & typedefs
+
+namespace BamTools {
// --------------------------------------------------
// BamDefaultIndex data structures & typedefs
@@ -61,7 +61,7 @@ struct Chunk {
uint64_t Stop;
// constructor
- Chunk(const uint64_t& start = 0,
+ Chunk(const uint64_t& start = 0,
const uint64_t& stop = 0)
: Start(start)
, Stop(stop)
@@ -77,11 +77,11 @@ typedef map<uint32_t, ChunkVector> BamBinMap;
typedef vector<uint64_t> LinearOffsetVector;
struct ReferenceIndex {
-
+
// data members
BamBinMap Bins;
LinearOffsetVector Offsets;
-
+
// constructor
ReferenceIndex(const BamBinMap& binMap = BamBinMap(),
const LinearOffsetVector& offsets = LinearOffsetVector())
@@ -93,27 +93,27 @@ struct ReferenceIndex {
typedef vector<ReferenceIndex> BamDefaultIndexData;
} // namespace BamTools
-
+
// -------------------------------
// BamDefaultIndex implementation
-
-struct BamDefaultIndex::BamDefaultIndexPrivate {
-
+
+struct BamDefaultIndex::BamDefaultIndexPrivate {
+
// -------------------------
// data members
-
+
BamDefaultIndexData m_indexData;
BamDefaultIndex* m_parent;
-
+
// -------------------------
// ctor & dtor
-
+
BamDefaultIndexPrivate(BamDefaultIndex* parent) : m_parent(parent) { }
~BamDefaultIndexPrivate(void) { }
-
+
// -------------------------
// internal methods
-
+
// calculate bins that overlap region
int BinsFromRegion(const BamTools::BamRegion& region, const bool isRightBoundSpecified, uint16_t bins[BamTools::MAX_BIN]);
// saves BAM bin entry for index
@@ -122,14 +122,14 @@ struct BamDefaultIndex::BamDefaultIndexPrivate {
void InsertLinearOffset(LinearOffsetVector& offsets, const BamAlignment& bAlignment, const uint64_t& lastOffset);
// simplifies index by merging 'chunks'
void MergeChunks(void);
-
+
};
-
+
BamDefaultIndex::BamDefaultIndex(BgzfData* bgzf, BamReader* reader, bool isBigEndian)
: BamIndex(bgzf, reader, isBigEndian)
{
d = new BamDefaultIndexPrivate(this);
-}
+}
BamDefaultIndex::~BamDefaultIndex(void) {
d->m_indexData.clear();
@@ -139,20 +139,20 @@ BamDefaultIndex::~BamDefaultIndex(void) {
// calculate bins that overlap region
int BamDefaultIndex::BamDefaultIndexPrivate::BinsFromRegion(const BamRegion& region, const bool isRightBoundSpecified, uint16_t bins[MAX_BIN]) {
-
+
// get region boundaries
uint32_t begin = (unsigned int)region.LeftPosition;
uint32_t end;
-
+
// if right bound specified AND left&right bounds are on same reference
// OK to use right bound position
if ( isRightBoundSpecified && ( region.LeftRefID == region.RightRefID ) )
end = (unsigned int)region.RightPosition;
-
+
// otherwise, use end of left bound reference as cutoff
else
end = (unsigned int)m_parent->m_references.at(region.LeftRefID).RefLength - 1;
-
+
// initialize list, bin '0' always a valid bin
int i = 0;
bins[i++] = 0;
@@ -169,10 +169,10 @@ int BamDefaultIndex::BamDefaultIndexPrivate::BinsFromRegion(const BamRegion& reg
return i;
}
-bool BamDefaultIndex::Build(void) {
-
+bool BamDefaultIndex::Build(void) {
+
// be sure reader & BGZF file are valid & open for reading
- if ( m_reader == 0 || m_BGZF == 0 || !m_BGZF->IsOpen )
+ if ( m_reader == 0 || m_BGZF == 0 || !m_BGZF->IsOpen )
return false;
// move file pointer to beginning of alignments
@@ -183,7 +183,7 @@ bool BamDefaultIndex::Build(void) {
for ( int i = 0; i < numReferences; ++i ) {
d->m_indexData.push_back(ReferenceIndex());
}
-
+
// sets default constant for bin, ID, offset, coordinate variables
const uint32_t defaultValue = 0xffffffffu;
@@ -276,7 +276,7 @@ bool BamDefaultIndex::Build(void) {
// simplify index by merging chunks
d->MergeChunks();
-
+
// iterate through references in index
// store whether reference has data &
// sort offsets in linear offset vector
@@ -300,8 +300,8 @@ bool BamDefaultIndex::Build(void) {
return m_reader->Rewind();
}
-bool BamDefaultIndex::GetOffsets(const BamRegion& region, const bool isRightBoundSpecified, vector<int64_t>& offsets) {
-
+bool BamDefaultIndex::GetOffsets(const BamRegion& region, const bool isRightBoundSpecified, vector<int64_t>& offsets) {
+
// calculate which bins overlap this region
uint16_t* bins = (uint16_t*)calloc(MAX_BIN, 2);
int numBins = d->BinsFromRegion(region, isRightBoundSpecified, bins);
@@ -316,7 +316,7 @@ bool BamDefaultIndex::GetOffsets(const BamRegion& region, const bool isRightBoun
// store all alignment 'chunk' starts (file offsets) for bins in this region
for ( int i = 0; i < numBins; ++i ) {
-
+
const uint16_t binKey = bins[i];
map<uint32_t, ChunkVector>::const_iterator binIter = binMap.find(binKey);
if ( (binIter != binMap.end()) && ((*binIter).first == binKey) ) {
@@ -325,7 +325,7 @@ bool BamDefaultIndex::GetOffsets(const BamRegion& region, const bool isRightBoun
std::vector<Chunk>::const_iterator chunksIter = chunks.begin();
std::vector<Chunk>::const_iterator chunksEnd = chunks.end();
for ( ; chunksIter != chunksEnd; ++chunksIter) {
-
+
// if valid chunk found, store its file offset
const Chunk& chunk = (*chunksIter);
if ( chunk.Stop > minOffset )
@@ -339,7 +339,7 @@ bool BamDefaultIndex::GetOffsets(const BamRegion& region, const bool isRightBoun
// sort the offsets before returning
sort(offsets.begin(), offsets.end());
-
+
// return whether any offsets were found
return ( offsets.size() != 0 );
}
@@ -387,13 +387,13 @@ void BamDefaultIndex::BamDefaultIndexPrivate::InsertLinearOffset(LinearOffsetVec
// store offset
for( int i = beginOffset + 1; i <= endOffset; ++i ) {
- if ( offsets[i] == 0 )
+ if ( offsets[i] == 0 )
offsets[i] = lastOffset;
}
-}
+}
+
+bool BamDefaultIndex::Load(const string& filename) {
-bool BamDefaultIndex::Load(const string& filename) {
-
// open index file, abort on error
FILE* indexStream = fopen(filename.c_str(), "rb");
if( !indexStream ) {
@@ -403,7 +403,7 @@ bool BamDefaultIndex::Load(const string& filename) {
// set placeholder to receive input byte count (suppresses compiler warnings)
size_t elementsRead = 0;
-
+
// see if index is valid BAM index
char magic[4];
elementsRead = fread(magic, 1, 4, indexStream);
@@ -417,7 +417,7 @@ bool BamDefaultIndex::Load(const string& filename) {
uint32_t numRefSeqs;
elementsRead = fread(&numRefSeqs, 4, 1, indexStream);
if ( m_isBigEndian ) { SwapEndian_32(numRefSeqs); }
-
+
// intialize space for BamDefaultIndexData data structure
d->m_indexData.reserve(numRefSeqs);
@@ -448,11 +448,11 @@ bool BamDefaultIndex::Load(const string& filename) {
uint32_t numChunks;
elementsRead = fread(&numChunks, 4, 1, indexStream);
- if ( m_isBigEndian ) {
+ if ( m_isBigEndian ) {
SwapEndian_32(binID);
SwapEndian_32(numChunks);
}
-
+
// intialize ChunkVector
ChunkVector regionChunks;
regionChunks.reserve(numChunks);
@@ -470,7 +470,7 @@ bool BamDefaultIndex::Load(const string& filename) {
SwapEndian_64(left);
SwapEndian_64(right);
}
-
+
// save ChunkPair
regionChunks.push_back( Chunk(left, right) );
}
@@ -571,9 +571,9 @@ void BamDefaultIndex::BamDefaultIndexPrivate::MergeChunks(void) {
}
}
-// writes in-memory index data out to file
+// writes in-memory index data out to file
// N.B. - (this is the original BAM filename, method will modify it to use applicable extension)
-bool BamDefaultIndex::Write(const std::string& bamFilename) {
+bool BamDefaultIndex::Write(const std::string& bamFilename) {
string indexFilename = bamFilename + ".bai";
FILE* indexStream = fopen(indexFilename.c_str(), "wb");
@@ -637,7 +637,7 @@ bool BamDefaultIndex::Write(const std::string& bamFilename) {
SwapEndian_64(start);
SwapEndian_64(stop);
}
-
+
// save chunk offsets
fwrite(&start, 8, 1, indexStream);
fwrite(&stop, 8, 1, indexStream);
@@ -674,14 +674,14 @@ bool BamDefaultIndex::Write(const std::string& bamFilename) {
// BamToolsIndex implementation
namespace BamTools {
-
+
struct BamToolsIndexEntry {
-
+
// data members
int64_t Offset;
int RefID;
int Position;
-
+
// ctor
BamToolsIndexEntry(const uint64_t& offset = 0,
const int& id = -1,
@@ -693,51 +693,51 @@ struct BamToolsIndexEntry {
};
typedef vector<BamToolsIndexEntry> BamToolsIndexData;
-
+
} // namespace BamTools
struct BamToolsIndex::BamToolsIndexPrivate {
-
+
// -------------------------
// data members
BamToolsIndexData m_indexData;
BamToolsIndex* m_parent;
int32_t m_blockSize;
-
+
// -------------------------
// ctor & dtor
-
- BamToolsIndexPrivate(BamToolsIndex* parent)
+
+ BamToolsIndexPrivate(BamToolsIndex* parent)
: m_parent(parent)
, m_blockSize(1000)
{ }
-
+
~BamToolsIndexPrivate(void) { }
-
+
// -------------------------
// internal methods
};
BamToolsIndex::BamToolsIndex(BgzfData* bgzf, BamReader* reader, bool isBigEndian)
: BamIndex(bgzf, reader, isBigEndian)
-{
+{
d = new BamToolsIndexPrivate(this);
-}
+}
-BamToolsIndex::~BamToolsIndex(void) {
+BamToolsIndex::~BamToolsIndex(void) {
delete d;
d = 0;
}
-bool BamToolsIndex::Build(void) {
-
+bool BamToolsIndex::Build(void) {
+
// be sure reader & BGZF file are valid & open for reading
- if ( m_reader == 0 || m_BGZF == 0 || !m_BGZF->IsOpen )
+ if ( m_reader == 0 || m_BGZF == 0 || !m_BGZF->IsOpen )
return false;
// move file pointer to beginning of alignments
m_reader->Rewind();
-
+
// plow through alignments, store block offsets
int32_t currentBlockCount = 0;
int64_t blockStartOffset = m_BGZF->Tell();
@@ -745,68 +745,68 @@ bool BamToolsIndex::Build(void) {
int blockStartPosition = -1;
BamAlignment al;
while ( m_reader->GetNextAlignmentCore(al) ) {
-
+
// set reference flag
m_references[al.RefID].RefHasAlignments = true;
-
+
// if beginning of block, save first alignment's refID & position
if ( currentBlockCount == 0 ) {
blockStartId = al.RefID;
blockStartPosition = al.Position;
}
-
+
// increment block counter
++currentBlockCount;
-
+
// if block is full, get offset for next block, reset currentBlockCount
if ( currentBlockCount == d->m_blockSize ) {
-
+
d->m_indexData.push_back( BamToolsIndexEntry(blockStartOffset, blockStartId, blockStartPosition) );
blockStartOffset = m_BGZF->Tell();
currentBlockCount = 0;
}
}
-
+
return m_reader->Rewind();
}
// N.B. - ignores isRightBoundSpecified
-bool BamToolsIndex::GetOffsets(const BamRegion& region, const bool isRightBoundSpecified, vector<int64_t>& offsets) {
-
- // return false if no index data present
+bool BamToolsIndex::GetOffsets(const BamRegion& region, const bool isRightBoundSpecified, vector<int64_t>& offsets) {
+
+ // return false if no index data present
if ( d->m_indexData.empty() ) return false;
-
+
// clear any prior data
offsets.clear();
-
+
// calculate nearest index to jump to
int64_t previousOffset = -1;
BamToolsIndexData::const_iterator indexIter = d->m_indexData.begin();
BamToolsIndexData::const_iterator indexEnd = d->m_indexData.end();
for ( ; indexIter != indexEnd; ++indexIter ) {
-
+
const BamToolsIndexEntry& entry = (*indexIter);
-
+
// check if we are 'past' beginning of desired region
// if so, we will break out & use previously stored offset
if ( entry.RefID > region.LeftRefID ) break;
if ( (entry.RefID == region.LeftRefID) && (entry.Position > region.LeftPosition) ) break;
-
+
// not past desired region, so store current entry offset in previousOffset
previousOffset = entry.Offset;
}
-
+
// no index was found
- if ( previousOffset == -1 )
+ if ( previousOffset == -1 )
return false;
-
+
// store offset & return success
offsets.push_back(previousOffset);
- return true;
+ return true;
}
-bool BamToolsIndex::Load(const string& filename) {
-
+bool BamToolsIndex::Load(const string& filename) {
+
// open index file, abort on error
FILE* indexStream = fopen(filename.c_str(), "rb");
if( !indexStream ) {
@@ -816,7 +816,7 @@ bool BamToolsIndex::Load(const string& filename) {
// set placeholder to receive input byte count (suppresses compiler warnings)
size_t elementsRead = 0;
-
+
// see if index is valid BAM index
char magic[4];
elementsRead = fread(magic, 1, 4, indexStream);
@@ -829,37 +829,37 @@ bool BamToolsIndex::Load(const string& filename) {
// read in block size
elementsRead = fread(&d->m_blockSize, sizeof(d->m_blockSize), 1, indexStream);
if ( m_isBigEndian ) { SwapEndian_32(d->m_blockSize); }
-
+
// read in number of offsets
uint32_t numOffsets;
elementsRead = fread(&numOffsets, sizeof(numOffsets), 1, indexStream);
if ( m_isBigEndian ) { SwapEndian_32(numOffsets); }
-
+
// reserve space for index data
d->m_indexData.reserve(numOffsets);
// iterate over index entries
for ( unsigned int i = 0; i < numOffsets; ++i ) {
-
+
uint64_t offset;
int id;
int position;
-
+
// read in data
elementsRead = fread(&offset, sizeof(offset), 1, indexStream);
elementsRead = fread(&id, sizeof(id), 1, indexStream);
elementsRead = fread(&position, sizeof(position), 1, indexStream);
-
+
// swap endian-ness if necessary
if ( m_isBigEndian ) {
SwapEndian_64(offset);
SwapEndian_32(id);
SwapEndian_32(position);
}
-
+
// save reference index entry
d->m_indexData.push_back( BamToolsIndexEntry(offset, id, position) );
-
+
// set reference flag
m_references[id].RefHasAlignments = true; // what about sparse references? wont be able to set flag?
}
@@ -869,10 +869,10 @@ bool BamToolsIndex::Load(const string& filename) {
return true;
}
-// writes in-memory index data out to file
+// writes in-memory index data out to file
// N.B. - (this is the original BAM filename, method will modify it to use applicable extension)
-bool BamToolsIndex::Write(const std::string& bamFilename) {
-
+bool BamToolsIndex::Write(const std::string& bamFilename) {
+
string indexFilename = bamFilename + ".bti";
FILE* indexStream = fopen(indexFilename.c_str(), "wb");
if ( indexStream == 0 ) {
@@ -887,12 +887,12 @@ bool BamToolsIndex::Write(const std::string& bamFilename) {
int32_t blockSize = d->m_blockSize;
if ( m_isBigEndian ) { SwapEndian_32(blockSize); }
fwrite(&blockSize, sizeof(blockSize), 1, indexStream);
-
+
// write number of offset entries
uint32_t numOffsets = d->m_indexData.size();
if ( m_isBigEndian ) { SwapEndian_32(numOffsets); }
fwrite(&numOffsets, sizeof(numOffsets), 1, indexStream);
-
+
// iterate over offset entries
BamToolsIndexData::const_iterator indexIter = d->m_indexData.begin();
BamToolsIndexData::const_iterator indexEnd = d->m_indexData.end();
@@ -900,19 +900,19 @@ bool BamToolsIndex::Write(const std::string& bamFilename) {
// get reference index data
const BamToolsIndexEntry& entry = (*indexIter);
-
+
// copy entry data
uint64_t offset = entry.Offset;
int id = entry.RefID;
int position = entry.Position;
-
+
// swap endian-ness if necessary
if ( m_isBigEndian ) {
SwapEndian_64(offset);
SwapEndian_32(id);
SwapEndian_32(position);
}
-
+
// write the reference index entry
fwrite(&offset, sizeof(offset), 1, indexStream);
fwrite(&id, sizeof(id), 1, indexStream);
diff --git a/src/utils/BamTools/BamIndex.h b/src/utils/BamTools/BamIndex.h
index b9ce7d03121b34f8fdb3c2640fe689c41b0954ec..ade11483b6da0f1948de97c9dda2fc277ddda060 100644
--- a/src/utils/BamTools/BamIndex.h
+++ b/src/utils/BamTools/BamIndex.h
@@ -5,8 +5,8 @@
// ---------------------------------------------------------------------------
// Last modified: 17 August 2010 (DB)
// ---------------------------------------------------------------------------
-// Provides index functionality - both for the default (standardized) BAM
-// index format (.bai) as well as a BamTools-specific (nonstandard) index
+// Provides index functionality - both for the default (standardized) BAM
+// index format (.bai) as well as a BamTools-specific (nonstandard) index
// format (.bti).
// ***************************************************************************
@@ -21,13 +21,13 @@ namespace BamTools {
class BamReader;
class BgzfData;
-
-// --------------------------------------------------
+
+// --------------------------------------------------
// BamIndex base class
class BamIndex {
public:
- BamIndex(BamTools::BgzfData* bgzf,
+ BamIndex(BamTools::BgzfData* bgzf,
BamTools::BamReader* reader,
bool isBigEndian);
virtual ~BamIndex(void) { }
@@ -40,11 +40,11 @@ class BamIndex {
// loads existing data from file into memory
virtual bool Load(const std::string& filename) =0;
// returns whether reference has alignments or no
- virtual bool HasAlignments(const int& referenceID);
- // writes in-memory index data out to file
+ virtual bool HasAlignments(const int& referenceID);
+ // writes in-memory index data out to file
// N.B. - (this is the original BAM filename, method will modify it to use applicable extension)
virtual bool Write(const std::string& bamFilename) =0;
-
+
protected:
BamTools::BgzfData* m_BGZF;
BamTools::BamReader* m_reader;
@@ -54,18 +54,18 @@ class BamIndex {
// --------------------------------------------------
// BamDefaultIndex class
-//
+//
// implements default (per SAM/BAM spec) index file ops
class BamDefaultIndex : public BamIndex {
-
+
// ctor & dtor
public:
- BamDefaultIndex(BamTools::BgzfData* bgzf,
+ BamDefaultIndex(BamTools::BgzfData* bgzf,
BamTools::BamReader* reader,
bool isBigEndian);
~BamDefaultIndex(void);
-
+
// interface (implements BamIndex virtual methods)
public:
// creates index data (in-memory) from current reader data
@@ -74,10 +74,10 @@ class BamDefaultIndex : public BamIndex {
bool GetOffsets(const BamTools::BamRegion& region, const bool isRightBoundSpecified, std::vector<int64_t>& offsets);
// loads existing data from file into memory
bool Load(const std::string& filename);
- // writes in-memory index data out to file
+ // writes in-memory index data out to file
// N.B. - (this is the original BAM filename, method will modify it to use applicable extension)
bool Write(const std::string& bamFilename);
-
+
// internal implementation
private:
struct BamDefaultIndexPrivate;
@@ -92,11 +92,11 @@ class BamToolsIndex : public BamIndex {
// ctor & dtor
public:
- BamToolsIndex(BamTools::BgzfData* bgzf,
+ BamToolsIndex(BamTools::BgzfData* bgzf,
BamTools::BamReader* reader,
bool isBigEndian);
~BamToolsIndex(void);
-
+
// interface (implements BamIndex virtual methods)
public:
// creates index data (in-memory) from current reader data
@@ -105,10 +105,10 @@ class BamToolsIndex : public BamIndex {
bool GetOffsets(const BamTools::BamRegion& region, const bool isRightBoundSpecified, std::vector<int64_t>& offsets);
// loads existing data from file into memory
bool Load(const std::string& filename);
- // writes in-memory index data out to file
+ // writes in-memory index data out to file
// N.B. - (this is the original BAM filename, method will modify it to use applicable extension)
bool Write(const std::string& bamFilename);
-
+
// internal implementation
private:
struct BamToolsIndexPrivate;
diff --git a/src/utils/BamTools/BamMultiReader.cpp b/src/utils/BamTools/BamMultiReader.cpp
index 005b0b0adc7c6c22c12f4317791785803a974bd6..11d48daff295b0d602b78edfb1c24104637614e3 100644
--- a/src/utils/BamTools/BamMultiReader.cpp
+++ b/src/utils/BamTools/BamMultiReader.cpp
@@ -137,7 +137,7 @@ bool BamMultiReader::GetNextAlignmentCore(BamAlignment& nextAlignment) {
// and add another entry if we can get another alignment from the reader
if (reader->GetNextAlignmentCore(*alignment)) {
- alignments.insert(make_pair(make_pair(alignment->RefID, alignment->Position),
+ alignments.insert(make_pair(make_pair(alignment->RefID, alignment->Position),
make_pair(reader, alignment)));
} else { // do nothing
//cerr << "reached end of file " << lowestReader->GetFilename() << endl;
@@ -201,7 +201,7 @@ void BamMultiReader::UpdateAlignments(void) {
BamReader* br = it->first;
BamAlignment* ba = it->second;
if (br->GetNextAlignment(*ba)) {
- alignments.insert(make_pair(make_pair(ba->RefID, ba->Position),
+ alignments.insert(make_pair(make_pair(ba->RefID, ba->Position),
make_pair(br, ba)));
} else {
// assume BamReader end of region / EOF
@@ -211,7 +211,7 @@ void BamMultiReader::UpdateAlignments(void) {
// opens BAM files
bool BamMultiReader::Open(const vector<string> filenames, bool openIndexes, bool coreMode, bool useDefaultIndex) {
-
+
// for filename in filenames
fileNames = filenames; // save filenames in our multireader
for (vector<string>::const_iterator it = filenames.begin(); it != filenames.end(); ++it) {
@@ -222,15 +222,15 @@ bool BamMultiReader::Open(const vector<string> filenames, bool openIndexes, bool
if (openIndexes) {
if (useDefaultIndex)
openedOK = reader->Open(filename, filename + ".bai");
- else
+ else
openedOK = reader->Open(filename, filename + ".bti");
} else {
openedOK = reader->Open(filename); // for merging, jumping is disallowed
}
-
+
// if file opened ok, check that it can be read
if ( openedOK ) {
-
+
bool fileOK = true;
BamAlignment* alignment = new BamAlignment;
if (coreMode) {
@@ -238,7 +238,7 @@ bool BamMultiReader::Open(const vector<string> filenames, bool openIndexes, bool
} else {
fileOK &= reader->GetNextAlignment(*alignment);
}
-
+
if (fileOK) {
readers.push_back(make_pair(reader, alignment)); // store pointers to our readers for cleanup
alignments.insert(make_pair(make_pair(alignment->RefID, alignment->Position),
@@ -248,11 +248,11 @@ bool BamMultiReader::Open(const vector<string> filenames, bool openIndexes, bool
// if only file available & could not be read, return failure
if ( filenames.size() == 1 ) return false;
}
-
- }
-
+
+ }
+
// TODO; any more error handling on openedOK ??
- else
+ else
return false;
}
@@ -277,7 +277,7 @@ void BamMultiReader::DumpAlignmentIndex(void) {
}
// returns BAM file pointers to beginning of alignment data
-bool BamMultiReader::Rewind(void) {
+bool BamMultiReader::Rewind(void) {
bool result = true;
for (vector<pair<BamReader*, BamAlignment*> >::iterator it = readers.begin(); it != readers.end(); ++it) {
BamReader* reader = it->first;
@@ -351,7 +351,7 @@ const string BamMultiReader::GetHeaderText(void) const {
// warn iff we are reading one file and discover duplicated @RG tags in the header
// otherwise, we emit no warning, as we might be merging multiple BAM files with identical @RG tags
if (currentFileReadGroups.find(readGroup) != currentFileReadGroups.end()) {
- cerr << "WARNING: duplicate @RG tag " << readGroup
+ cerr << "WARNING: duplicate @RG tag " << readGroup
<< " entry in header of " << reader->GetFilename() << endl;
}
}
@@ -377,7 +377,7 @@ void BamMultiReader::ValidateReaders(void) const {
BamTools::RefVector::const_iterator c = currentRefData.begin();
if (reader->GetReferenceCount() != firstRefCount || firstRefData.size() != currentRefData.size()) {
cerr << "ERROR: mismatched number of references in " << reader->GetFilename()
- << " expected " << firstRefCount
+ << " expected " << firstRefCount
<< " reference sequences but only found " << reader->GetReferenceCount() << endl;
exit(1);
}
@@ -415,6 +415,6 @@ const BamTools::RefVector BamMultiReader::GetReferenceData(void) const {
return readers.front().first->GetReferenceData();
}
-const int BamMultiReader::GetReferenceID(const string& refName) const {
+const int BamMultiReader::GetReferenceID(const string& refName) const {
return readers.front().first->GetReferenceID(refName);
}
diff --git a/src/utils/BamTools/BamReader.cpp b/src/utils/BamTools/BamReader.cpp
index b1b1b5de2ab79a76416bd5267f6dc5cc1ecccd02..d6355769144f5d2e7f628251942a04afc672205b 100644
--- a/src/utils/BamTools/BamReader.cpp
+++ b/src/utils/BamTools/BamReader.cpp
@@ -49,7 +49,7 @@ struct BamReader::BamReaderPrivate {
int64_t AlignmentsBeginOffset;
string Filename;
string IndexFilename;
-
+
// system data
bool IsBigEndian;
@@ -57,14 +57,14 @@ struct BamReader::BamReaderPrivate {
BamRegion Region;
bool IsLeftBoundSpecified;
bool IsRightBoundSpecified;
-
+
bool IsRegionSpecified;
int CurrentRefID;
int CurrentLeft;
// parent BamReader
BamReader* Parent;
-
+
// BAM character constants
const char* DNA_LOOKUP;
const char* CIGAR_LOOKUP;
@@ -138,12 +138,12 @@ BamReader::~BamReader(void) {
// file operations
void BamReader::Close(void) { d->Close(); }
bool BamReader::IsOpen(void) const { return d->mBGZF.IsOpen; }
-bool BamReader::Jump(int refID, int position) {
+bool BamReader::Jump(int refID, int position) {
d->Region.LeftRefID = refID;
d->Region.LeftPosition = position;
d->IsLeftBoundSpecified = true;
d->IsRightBoundSpecified = false;
- return d->Jump(refID, position);
+ return d->Jump(refID, position);
}
bool BamReader::Open(const string& filename, const string& indexFilename) { return d->Open(filename, indexFilename); }
bool BamReader::Rewind(void) { return d->Rewind(); }
@@ -183,7 +183,7 @@ BamReader::BamReaderPrivate::BamReaderPrivate(BamReader* parent)
, Parent(parent)
, DNA_LOOKUP("=ACMGRSVTWYHKDBN")
, CIGAR_LOOKUP("MIDNSHP")
-{
+{
IsBigEndian = SystemIsBigEndian();
}
@@ -193,7 +193,7 @@ BamReader::BamReaderPrivate::~BamReaderPrivate(void) {
}
bool BamReader::BamReaderPrivate::BuildCharData(BamAlignment& bAlignment) {
-
+
// calculate character lengths/offsets
const unsigned int dataLength = bAlignment.SupportData.BlockLength - BAM_CORE_SIZE;
const unsigned int cigarDataOffset = bAlignment.SupportData.QueryNameLength;
@@ -201,18 +201,18 @@ bool BamReader::BamReaderPrivate::BuildCharData(BamAlignment& bAlignment) {
const unsigned int qualDataOffset = seqDataOffset + (bAlignment.SupportData.QuerySequenceLength+1)/2;
const unsigned int tagDataOffset = qualDataOffset + bAlignment.SupportData.QuerySequenceLength;
const unsigned int tagDataLength = dataLength - tagDataOffset;
-
+
// set up char buffers
const char* allCharData = bAlignment.SupportData.AllCharData.data();
uint32_t* cigarData = (uint32_t*)(allCharData + cigarDataOffset);
const char* seqData = ((const char*)allCharData) + seqDataOffset;
const char* qualData = ((const char*)allCharData) + qualDataOffset;
char* tagData = ((char*)allCharData) + tagDataOffset;
-
+
// store alignment name (depends on null char as terminator)
- bAlignment.Name.assign((const char*)(allCharData));
-
- // save CigarOps
+ bAlignment.Name.assign((const char*)(allCharData));
+
+ // save CigarOps
CigarOp op;
bAlignment.CigarData.clear();
bAlignment.CigarData.reserve(bAlignment.SupportData.NumCigarOperations);
@@ -220,7 +220,7 @@ bool BamReader::BamReaderPrivate::BuildCharData(BamAlignment& bAlignment) {
// swap if necessary
if ( IsBigEndian ) { SwapEndian_32(cigarData[i]); }
-
+
// build CigarOp structure
op.Length = (cigarData[i] >> BAM_CIGAR_SHIFT);
op.Type = CIGAR_LOOKUP[ (cigarData[i] & BAM_CIGAR_MASK) ];
@@ -228,8 +228,8 @@ bool BamReader::BamReaderPrivate::BuildCharData(BamAlignment& bAlignment) {
// save CigarOp
bAlignment.CigarData.push_back(op);
}
-
-
+
+
// save query sequence
bAlignment.QueryBases.clear();
bAlignment.QueryBases.reserve(bAlignment.SupportData.QuerySequenceLength);
@@ -237,7 +237,7 @@ bool BamReader::BamReaderPrivate::BuildCharData(BamAlignment& bAlignment) {
char singleBase = DNA_LOOKUP[ ( ( seqData[(i/2)] >> (4*(1-(i%2)))) & 0xf ) ];
bAlignment.QueryBases.append(1, singleBase);
}
-
+
// save qualities, converting from numeric QV to 'FASTQ-style' ASCII character
bAlignment.Qualities.clear();
bAlignment.Qualities.reserve(bAlignment.SupportData.QuerySequenceLength);
@@ -245,58 +245,58 @@ bool BamReader::BamReaderPrivate::BuildCharData(BamAlignment& bAlignment) {
char singleQuality = (char)(qualData[i]+33);
bAlignment.Qualities.append(1, singleQuality);
}
-
+
// if QueryBases is empty (and this is a allowed case)
- if ( bAlignment.QueryBases.empty() )
+ if ( bAlignment.QueryBases.empty() )
bAlignment.AlignedBases = bAlignment.QueryBases;
-
+
// if QueryBases contains data, then build AlignedBases using CIGAR data
else {
-
+
// resize AlignedBases
bAlignment.AlignedBases.clear();
bAlignment.AlignedBases.reserve(bAlignment.SupportData.QuerySequenceLength);
-
+
// iterate over CigarOps
int k = 0;
vector<CigarOp>::const_iterator cigarIter = bAlignment.CigarData.begin();
vector<CigarOp>::const_iterator cigarEnd = bAlignment.CigarData.end();
for ( ; cigarIter != cigarEnd; ++cigarIter ) {
-
+
const CigarOp& op = (*cigarIter);
switch(op.Type) {
-
+
case ('M') :
case ('I') :
bAlignment.AlignedBases.append(bAlignment.QueryBases.substr(k, op.Length)); // for 'M', 'I' - write bases
// fall through
-
+
case ('S') :
k += op.Length; // for 'S' - soft clip, skip over query bases
break;
-
+
case ('D') :
bAlignment.AlignedBases.append(op.Length, '-'); // for 'D' - write gap character
break;
-
+
case ('P') :
bAlignment.AlignedBases.append( op.Length, '*' ); // for 'P' - write padding character
break;
-
+
case ('N') :
bAlignment.AlignedBases.append( op.Length, 'N' ); // for 'N' - write N's, skip bases in original query sequence
break;
-
+
case ('H') :
break; // for 'H' - hard clip, do nothing to AlignedBases, move to next op
-
+
default:
printf("ERROR: Invalid Cigar op type\n"); // shouldn't get here
exit(1);
}
}
}
-
+
// -----------------------
// Added: 3-25-2010 DB
// Fixed: endian-correctness for tag data
@@ -304,55 +304,55 @@ bool BamReader::BamReaderPrivate::BuildCharData(BamAlignment& bAlignment) {
if ( IsBigEndian ) {
int i = 0;
while ( (unsigned int)i < tagDataLength ) {
-
+
i += 2; // skip tag type (e.g. "RG", "NM", etc)
- uint8_t type = toupper(tagData[i]); // lower & upper case letters have same meaning
+ uint8_t type = toupper(tagData[i]); // lower & upper case letters have same meaning
++i; // skip value type
-
+
switch (type) {
-
+
case('A') :
- case('C') :
+ case('C') :
++i;
break;
- case('S') :
- SwapEndian_16p(&tagData[i]);
+ case('S') :
+ SwapEndian_16p(&tagData[i]);
i += sizeof(uint16_t);
break;
-
+
case('F') :
- case('I') :
+ case('I') :
SwapEndian_32p(&tagData[i]);
i += sizeof(uint32_t);
break;
-
- case('D') :
+
+ case('D') :
SwapEndian_64p(&tagData[i]);
i += sizeof(uint64_t);
break;
-
+
case('H') :
- case('Z') :
+ case('Z') :
while (tagData[i]) { ++i; }
++i; // increment one more for null terminator
break;
-
- default :
+
+ default :
printf("ERROR: Invalid tag value type\n"); // shouldn't get here
exit(1);
}
}
}
-
+
// store TagData
bAlignment.TagData.clear();
bAlignment.TagData.resize(tagDataLength);
memcpy((char*)bAlignment.TagData.data(), tagData, tagDataLength);
-
+
// clear the core-only flag
bAlignment.SupportData.HasCoreOnly = false;
-
+
// return success
return true;
}
@@ -365,16 +365,16 @@ void BamReader::BamReaderPrivate::ClearIndex(void) {
// closes the BAM file
void BamReader::BamReaderPrivate::Close(void) {
-
+
// close BGZF file stream
mBGZF.Close();
-
+
// clear out index data
ClearIndex();
-
+
// clear out header data
HeaderText.clear();
-
+
// clear out region flags
IsLeftBoundSpecified = false;
IsRightBoundSpecified = false;
@@ -386,18 +386,18 @@ bool BamReader::BamReaderPrivate::CreateIndex(bool useDefaultIndex) {
// clear out prior index data
ClearIndex();
-
+
// create default index
if ( useDefaultIndex )
NewIndex = new BamDefaultIndex(&mBGZF, Parent, IsBigEndian);
// create BamTools 'custom' index
else
NewIndex = new BamToolsIndex(&mBGZF, Parent, IsBigEndian);
-
+
bool ok = true;
ok &= NewIndex->Build();
- ok &= NewIndex->Write(Filename);
-
+ ok &= NewIndex->Write(Filename);
+
// return success/fail
return ok;
}
@@ -408,7 +408,7 @@ bool BamReader::BamReaderPrivate::GetNextAlignment(BamAlignment& bAlignment) {
// if valid alignment found, attempt to parse char data, and return success/failure
if ( GetNextAlignmentCore(bAlignment) )
return BuildCharData(bAlignment);
-
+
// no valid alignment found
else
return false;
@@ -416,7 +416,7 @@ bool BamReader::BamReaderPrivate::GetNextAlignment(BamAlignment& bAlignment) {
// retrieves next available alignment core data (returns success/fail)
// ** DOES NOT parse any character data (read name, bases, qualities, tag data)
-// these can be accessed, if necessary, from the supportData
+// these can be accessed, if necessary, from the supportData
// useful for operations requiring ONLY positional or other alignment-related information
bool BamReader::BamReaderPrivate::GetNextAlignmentCore(BamAlignment& bAlignment) {
@@ -425,15 +425,15 @@ bool BamReader::BamReaderPrivate::GetNextAlignmentCore(BamAlignment& bAlignment)
// set core-only flag
bAlignment.SupportData.HasCoreOnly = true;
-
+
// if region not specified, return success
if ( !IsLeftBoundSpecified ) return true;
// determine region state (before, within, after)
BamReader::BamReaderPrivate::RegionState state = IsOverlap(bAlignment);
-
+
// if alignment lies after region, return false
- if ( state == AFTER_REGION )
+ if ( state == AFTER_REGION )
return false;
while ( state != WITHIN_REGION ) {
@@ -442,7 +442,7 @@ bool BamReader::BamReaderPrivate::GetNextAlignmentCore(BamAlignment& bAlignment)
// if alignment lies after region, return false (no available read within region)
state = IsOverlap(bAlignment);
if ( state == AFTER_REGION) return false;
-
+
}
// return success (alignment found that overlaps region)
@@ -472,30 +472,30 @@ int BamReader::BamReaderPrivate::GetReferenceID(const string& refName) const {
// returns region state - whether alignment ends before, overlaps, or starts after currently specified region
// this *internal* method should ONLY called when (at least) IsLeftBoundSpecified == true
BamReader::BamReaderPrivate::RegionState BamReader::BamReaderPrivate::IsOverlap(BamAlignment& bAlignment) {
-
+
// --------------------------------------------------
// check alignment start against right bound cutoff
-
+
// if full region of interest was given
if ( IsRightBoundSpecified ) {
-
+
// read starts on right bound reference, but AFTER right bound position
if ( bAlignment.RefID == Region.RightRefID && bAlignment.Position > Region.RightPosition )
return AFTER_REGION;
-
+
// if read starts on reference AFTER right bound, return false
- if ( bAlignment.RefID > Region.RightRefID )
+ if ( bAlignment.RefID > Region.RightRefID )
return AFTER_REGION;
}
-
+
// --------------------------------------------------------
// no right bound given OR read starts before right bound
- // so, check if it overlaps left bound
-
+ // so, check if it overlaps left bound
+
// if read starts on left bound reference AND after left boundary, return success
if ( bAlignment.RefID == Region.LeftRefID && bAlignment.Position >= Region.LeftPosition)
return WITHIN_REGION;
-
+
// if read is on any reference sequence before left bound, return false
if ( bAlignment.RefID < Region.LeftRefID )
return BEFORE_REGION;
@@ -515,29 +515,29 @@ BamReader::BamReaderPrivate::RegionState BamReader::BamReaderPrivate::IsOverlap(
bool BamReader::BamReaderPrivate::Jump(int refID, int position) {
// -----------------------------------------------------------------------
- // check for existing index
- if ( NewIndex == 0 ) return false;
+ // check for existing index
+ if ( NewIndex == 0 ) return false;
// see if reference has alignments
- if ( !NewIndex->HasAlignments(refID) ) return false;
+ if ( !NewIndex->HasAlignments(refID) ) return false;
// make sure position is valid
if ( position > References.at(refID).RefLength ) return false;
-
+
// determine possible offsets
vector<int64_t> offsets;
if ( !NewIndex->GetOffsets(Region, IsRightBoundSpecified, offsets) ) {
printf("ERROR: Could not jump: unable to calculate offset for specified region.\n");
return false;
}
-
+
// iterate through offsets
BamAlignment bAlignment;
bool result = true;
for ( vector<int64_t>::const_iterator o = offsets.begin(); o != offsets.end(); ++o) {
-
+
// attempt seek & load first available alignment
result &= mBGZF.Seek(*o);
LoadNextAlignment(bAlignment);
-
+
// if this alignment corresponds to desired position
// return success of seeking back to 'current offset'
if ( (bAlignment.RefID == refID && bAlignment.Position + bAlignment.Length > position) || (bAlignment.RefID > refID) ) {
@@ -545,7 +545,7 @@ bool BamReader::BamReaderPrivate::Jump(int refID, int position) {
return mBGZF.Seek(*o);
}
}
-
+
return result;
}
@@ -568,7 +568,7 @@ void BamReader::BamReaderPrivate::LoadHeaderData(void) {
mBGZF.Read(buffer, 4);
unsigned int headerTextLength = BgzfData::UnpackUnsignedInt(buffer);
if ( IsBigEndian ) { SwapEndian_32(headerTextLength); }
-
+
// get BAM header text
char* headerText = (char*)calloc(headerTextLength + 1, 1);
mBGZF.Read(headerText, headerTextLength);
@@ -591,21 +591,21 @@ bool BamReader::BamReaderPrivate::LoadIndex(void) {
// check supplied filename for index type
size_t defaultExtensionFound = IndexFilename.find(".bai");
size_t customExtensionFound = IndexFilename.find(".bti");
-
+
// if SAM/BAM default (".bai")
if ( defaultExtensionFound != string::npos )
NewIndex = new BamDefaultIndex(&mBGZF, Parent, IsBigEndian);
-
+
// if BamTools custom index (".bti")
else if ( customExtensionFound != string::npos )
NewIndex = new BamToolsIndex(&mBGZF, Parent, IsBigEndian);
-
+
// else unknown
else {
printf("ERROR: Unknown index file extension.\n");
return false;
}
-
+
// return success of loading index data
return NewIndex->Load(IndexFilename);
}
@@ -625,15 +625,15 @@ bool BamReader::BamReaderPrivate::LoadNextAlignment(BamAlignment& bAlignment) {
if ( mBGZF.Read(x, BAM_CORE_SIZE) != BAM_CORE_SIZE ) { return false; }
if ( IsBigEndian ) {
- for ( int i = 0; i < BAM_CORE_SIZE; i+=sizeof(uint32_t) ) {
- SwapEndian_32p(&x[i]);
+ for ( int i = 0; i < BAM_CORE_SIZE; i+=sizeof(uint32_t) ) {
+ SwapEndian_32p(&x[i]);
}
}
-
+
// set BamAlignment 'core' and 'support' data
- bAlignment.RefID = BgzfData::UnpackSignedInt(&x[0]);
+ bAlignment.RefID = BgzfData::UnpackSignedInt(&x[0]);
bAlignment.Position = BgzfData::UnpackSignedInt(&x[4]);
-
+
unsigned int tempValue = BgzfData::UnpackUnsignedInt(&x[8]);
bAlignment.Bin = tempValue >> 16;
bAlignment.MapQuality = tempValue >> 8 & 0xff;
@@ -647,20 +647,20 @@ bool BamReader::BamReaderPrivate::LoadNextAlignment(BamAlignment& bAlignment) {
bAlignment.MateRefID = BgzfData::UnpackSignedInt(&x[20]);
bAlignment.MatePosition = BgzfData::UnpackSignedInt(&x[24]);
bAlignment.InsertSize = BgzfData::UnpackSignedInt(&x[28]);
-
+
// set BamAlignment length
bAlignment.Length = bAlignment.SupportData.QuerySequenceLength;
-
+
// read in character data - make sure proper data size was read
bool readCharDataOK = false;
const unsigned int dataLength = bAlignment.SupportData.BlockLength - BAM_CORE_SIZE;
char* allCharData = (char*)calloc(sizeof(char), dataLength);
-
- if ( mBGZF.Read(allCharData, dataLength) == (signed int)dataLength) {
-
+
+ if ( mBGZF.Read(allCharData, dataLength) == (signed int)dataLength) {
+
// store 'allCharData' in supportData structure
bAlignment.SupportData.AllCharData.assign((const char*)allCharData, dataLength);
-
+
// set success flag
readCharDataOK = true;
}
@@ -713,9 +713,9 @@ bool BamReader::BamReaderPrivate::Open(const string& filename, const string& ind
IndexFilename = indexFilename;
// open the BGZF file for reading, return false on failure
- if ( !mBGZF.Open(filename, "rb") )
+ if ( !mBGZF.Open(filename, "rb") )
return false;
-
+
// retrieve header text & reference data
LoadHeaderData();
LoadReferenceData();
@@ -726,28 +726,28 @@ bool BamReader::BamReaderPrivate::Open(const string& filename, const string& ind
// open index file & load index data (if exists)
if ( !IndexFilename.empty() )
LoadIndex();
-
+
// return success
return true;
}
// returns BAM file pointer to beginning of alignment data
bool BamReader::BamReaderPrivate::Rewind(void) {
-
+
// rewind to first alignment
if ( !mBGZF.Seek(AlignmentsBeginOffset) ) return false;
-
+
// retrieve first alignment data
BamAlignment al;
if ( !LoadNextAlignment(al) ) return false;
-
+
// reset default region info using first alignment in file
Region.LeftRefID = al.RefID;
Region.LeftPosition = al.Position;
Region.RightRefID = -1;
Region.RightPosition = -1;
IsLeftBoundSpecified = false;
- IsRightBoundSpecified = false;
+ IsRightBoundSpecified = false;
// rewind back to before first alignment
// return success/fail of seek
@@ -758,16 +758,16 @@ bool BamReader::BamReaderPrivate::Rewind(void) {
// attempts a Jump() to left bound as well
// returns success/failure of Jump()
bool BamReader::BamReaderPrivate::SetRegion(const BamRegion& region) {
-
+
// save region of interest
Region = region;
-
+
// set flags
- if ( region.LeftRefID >= 0 && region.LeftPosition >= 0 )
+ if ( region.LeftRefID >= 0 && region.LeftPosition >= 0 )
IsLeftBoundSpecified = true;
- if ( region.RightRefID >= 0 && region.RightPosition >= 0 )
+ if ( region.RightRefID >= 0 && region.RightPosition >= 0 )
IsRightBoundSpecified = true;
-
+
// attempt jump to beginning of region, return success/fail of Jump()
return Jump( Region.LeftRefID, Region.LeftPosition );
}
diff --git a/src/utils/BamTools/BamReader.h b/src/utils/BamTools/BamReader.h
index c93987b1a41bfbe41b7f0a10bd9d826a3514e681..a56316efcafd41e7ab33ab07b71316d12d49b158 100644
--- a/src/utils/BamTools/BamReader.h
+++ b/src/utils/BamTools/BamReader.h
@@ -21,7 +21,7 @@
#include "BamAux.h"
namespace BamTools {
-
+
class BamReader {
// constructor / destructor
@@ -58,10 +58,10 @@ class BamReader {
// retrieves next available alignment (returns success/fail)
bool GetNextAlignment(BamAlignment& bAlignment);
-
+
// retrieves next available alignment core data (returns success/fail)
// ** DOES NOT parse any character data (read name, bases, qualities, tag data)
- // these can be accessed, if necessary, from the supportData
+ // these can be accessed, if necessary, from the supportData
// useful for operations requiring ONLY positional or other alignment-related information
bool GetNextAlignmentCore(BamAlignment& bAlignment);
@@ -86,7 +86,7 @@ class BamReader {
// creates index for BAM file, saves to file (default = bamFilename + ".bai")
bool CreateIndex(bool useDefaultIndex = true);
-
+
// private implementation
private:
struct BamReaderPrivate;
diff --git a/src/utils/BamTools/BamWriter.cpp b/src/utils/BamTools/BamWriter.cpp
index f83ff1c3046ed46876c655b5b11f0535d634bda0..49e223b29e45e6e370fd058794c20bdbc0f630f9 100644
--- a/src/utils/BamTools/BamWriter.cpp
+++ b/src/utils/BamTools/BamWriter.cpp
@@ -23,12 +23,12 @@ struct BamWriter::BamWriterPrivate {
// data members
BgzfData mBGZF;
bool IsBigEndian;
-
+
// constructor / destructor
- BamWriterPrivate(void) {
- IsBigEndian = SystemIsBigEndian();
+ BamWriterPrivate(void) {
+ IsBigEndian = SystemIsBigEndian();
}
-
+
~BamWriterPrivate(void) {
mBGZF.Close();
}
@@ -60,8 +60,8 @@ BamWriter::~BamWriter(void) {
}
// closes the alignment archive
-void BamWriter::Close(void) {
- d->Close();
+void BamWriter::Close(void) {
+ d->Close();
}
// opens the alignment archive
@@ -70,7 +70,7 @@ bool BamWriter::Open(const string& filename, const string& samHeader, const RefV
}
// saves the alignment to the alignment archive
-void BamWriter::SaveAlignment(const BamAlignment& al) {
+void BamWriter::SaveAlignment(const BamAlignment& al) {
d->SaveAlignment(al);
}
@@ -84,7 +84,7 @@ void BamWriter::BamWriterPrivate::Close(void) {
}
// calculates minimum bin for a BAM alignment interval
-const unsigned int BamWriter::BamWriterPrivate::CalculateMinimumBin(const int begin, int end) const {
+const unsigned int BamWriter::BamWriterPrivate::CalculateMinimumBin(const int begin, int end) const {
--end;
if( (begin >> 14) == (end >> 14) ) return 4681 + (begin >> 14);
if( (begin >> 17) == (end >> 17) ) return 585 + (begin >> 17);
@@ -156,31 +156,31 @@ void BamWriter::BamWriterPrivate::EncodeQuerySequence(const string& query, strin
while(*pQuery) {
switch(*pQuery) {
-
+
case '=':
nucleotideCode = 0;
break;
-
+
case 'A':
nucleotideCode = 1;
break;
-
+
case 'C':
nucleotideCode = 2;
break;
-
+
case 'G':
nucleotideCode = 4;
break;
-
+
case 'T':
nucleotideCode = 8;
break;
-
+
case 'N':
nucleotideCode = 15;
break;
-
+
default:
printf("ERROR: Only the following bases are supported in the BAM format: {=, A, C, G, T, N}. Found [%c]\n", *pQuery);
exit(1);
@@ -223,7 +223,7 @@ bool BamWriter::BamWriterPrivate::Open(const string& filename, const string& sam
mBGZF.Write((char*)&samHeaderLen, BT_SIZEOF_INT);
// write the SAM header text
- if(samHeaderLen > 0)
+ if(samHeaderLen > 0)
mBGZF.Write(samHeader.data(), samHeaderLen);
// write the number of reference sequences
@@ -251,7 +251,7 @@ bool BamWriter::BamWriterPrivate::Open(const string& filename, const string& sam
if (IsBigEndian) SwapEndian_32(referenceLength);
mBGZF.Write((char*)&referenceLength, BT_SIZEOF_INT);
}
-
+
// return success
return true;
}
@@ -262,7 +262,7 @@ void BamWriter::BamWriterPrivate::SaveAlignment(const BamAlignment& al) {
// if BamAlignment contains only the core data and a raw char data buffer
// (as a result of BamReader::GetNextAlignmentCore())
if ( al.SupportData.HasCoreOnly ) {
-
+
// write the block size
unsigned int blockSize = al.SupportData.BlockLength;
if (IsBigEndian) SwapEndian_32(blockSize);
@@ -278,35 +278,35 @@ void BamWriter::BamWriterPrivate::SaveAlignment(const BamAlignment& al) {
buffer[5] = al.MateRefID;
buffer[6] = al.MatePosition;
buffer[7] = al.InsertSize;
-
+
// swap BAM core endian-ness, if necessary
- if ( IsBigEndian ) {
+ if ( IsBigEndian ) {
for ( int i = 0; i < 8; ++i )
- SwapEndian_32(buffer[i]);
+ SwapEndian_32(buffer[i]);
}
-
+
// write the BAM core
mBGZF.Write((char*)&buffer, BAM_CORE_SIZE);
-
+
// write the raw char data
- mBGZF.Write((char*)al.SupportData.AllCharData.data(), al.SupportData.BlockLength-BAM_CORE_SIZE);
+ mBGZF.Write((char*)al.SupportData.AllCharData.data(), al.SupportData.BlockLength-BAM_CORE_SIZE);
}
-
+
// otherwise, BamAlignment should contain character in the standard fields: Name, QueryBases, etc
// ( resulting from BamReader::GetNextAlignment() *OR* being generated directly by client code )
else {
-
+
// calculate char lengths
const unsigned int nameLength = al.Name.size() + 1;
const unsigned int numCigarOperations = al.CigarData.size();
const unsigned int queryLength = al.QueryBases.size();
const unsigned int tagDataLength = al.TagData.size();
-
+
// no way to tell if BamAlignment.Bin is already defined (no default, invalid value)
// force calculation of Bin before storing
const int endPosition = al.GetEndPosition();
const unsigned int alignmentBin = CalculateMinimumBin(al.Position, endPosition);
-
+
// create our packed cigar string
string packedCigar;
CreatePackedCigar(al.CigarData, packedCigar);
@@ -315,8 +315,8 @@ void BamWriter::BamWriterPrivate::SaveAlignment(const BamAlignment& al) {
// encode the query
string encodedQuery;
EncodeQuerySequence(al.QueryBases, encodedQuery);
- const unsigned int encodedQueryLength = encodedQuery.size();
-
+ const unsigned int encodedQueryLength = encodedQuery.size();
+
// write the block size
const unsigned int dataBlockSize = nameLength + packedCigarLength + encodedQueryLength + queryLength + tagDataLength;
unsigned int blockSize = BAM_CORE_SIZE + dataBlockSize;
@@ -333,34 +333,34 @@ void BamWriter::BamWriterPrivate::SaveAlignment(const BamAlignment& al) {
buffer[5] = al.MateRefID;
buffer[6] = al.MatePosition;
buffer[7] = al.InsertSize;
-
+
// swap BAM core endian-ness, if necessary
- if ( IsBigEndian ) {
+ if ( IsBigEndian ) {
for ( int i = 0; i < 8; ++i )
- SwapEndian_32(buffer[i]);
+ SwapEndian_32(buffer[i]);
}
-
+
// write the BAM core
mBGZF.Write((char*)&buffer, BAM_CORE_SIZE);
-
+
// write the query name
mBGZF.Write(al.Name.c_str(), nameLength);
// write the packed cigar
if ( IsBigEndian ) {
-
+
char* cigarData = (char*)calloc(sizeof(char), packedCigarLength);
memcpy(cigarData, packedCigar.data(), packedCigarLength);
-
+
for (unsigned int i = 0; i < packedCigarLength; ++i) {
if ( IsBigEndian )
- SwapEndian_32p(&cigarData[i]);
+ SwapEndian_32p(&cigarData[i]);
}
-
+
mBGZF.Write(cigarData, packedCigarLength);
- free(cigarData);
- }
- else
+ free(cigarData);
+ }
+ else
mBGZF.Write(packedCigar.data(), packedCigarLength);
// write the encoded query sequence
@@ -369,64 +369,64 @@ void BamWriter::BamWriterPrivate::SaveAlignment(const BamAlignment& al) {
// write the base qualities
string baseQualities(al.Qualities);
char* pBaseQualities = (char*)al.Qualities.data();
- for(unsigned int i = 0; i < queryLength; i++) {
- pBaseQualities[i] -= 33;
+ for(unsigned int i = 0; i < queryLength; i++) {
+ pBaseQualities[i] -= 33;
}
mBGZF.Write(pBaseQualities, queryLength);
// write the read group tag
if ( IsBigEndian ) {
-
+
char* tagData = (char*)calloc(sizeof(char), tagDataLength);
memcpy(tagData, al.TagData.data(), tagDataLength);
-
+
int i = 0;
while ( (unsigned int)i < tagDataLength ) {
-
+
i += 2; // skip tag type (e.g. "RG", "NM", etc)
- uint8_t type = toupper(tagData[i]); // lower & upper case letters have same meaning
+ uint8_t type = toupper(tagData[i]); // lower & upper case letters have same meaning
++i; // skip value type
-
+
switch (type) {
-
+
case('A') :
- case('C') :
+ case('C') :
++i;
break;
-
- case('S') :
- SwapEndian_16p(&tagData[i]);
+
+ case('S') :
+ SwapEndian_16p(&tagData[i]);
i+=2; // sizeof(uint16_t)
break;
-
+
case('F') :
- case('I') :
+ case('I') :
SwapEndian_32p(&tagData[i]);
i+=4; // sizeof(uint32_t)
break;
-
- case('D') :
+
+ case('D') :
SwapEndian_64p(&tagData[i]);
i+=8; // sizeof(uint64_t)
break;
-
+
case('H') :
- case('Z') :
+ case('Z') :
while (tagData[i]) { ++i; }
++i; // increment one more for null terminator
break;
-
- default :
+
+ default :
printf("ERROR: Invalid tag value type\n"); // shouldn't get here
free(tagData);
- exit(1);
+ exit(1);
}
}
-
+
mBGZF.Write(tagData, tagDataLength);
free(tagData);
- }
- else
- mBGZF.Write(al.TagData.data(), tagDataLength);
+ }
+ else
+ mBGZF.Write(al.TagData.data(), tagDataLength);
}
}
diff --git a/src/utils/BamTools/BamWriter.h b/src/utils/BamTools/BamWriter.h
index b0cb6ceba3457cc58f3f3670522148a394a39a96..20e3ffc2750d266609b3be0d3464bcfa61886a5d 100644
--- a/src/utils/BamTools/BamWriter.h
+++ b/src/utils/BamTools/BamWriter.h
@@ -34,9 +34,9 @@ class BamWriter {
// closes the alignment archive
void Close(void);
// opens the alignment archive
- bool Open(const std::string& filename,
- const std::string& samHeader,
- const BamTools::RefVector& referenceSequences,
+ bool Open(const std::string& filename,
+ const std::string& samHeader,
+ const BamTools::RefVector& referenceSequences,
bool writeUncompressed = false);
// saves the alignment to the alignment archive
void SaveAlignment(const BamTools::BamAlignment& al);
diff --git a/src/utils/bedFile/bedFile.cpp b/src/utils/bedFile/bedFile.cpp
index 8b11f46bea5276f44c32bd88b72f84a0cbb10cef..9f243dc3f1d0169321a9b2f36b2de8724c03aeaf 100644
--- a/src/utils/bedFile/bedFile.cpp
+++ b/src/utils/bedFile/bedFile.cpp
@@ -17,43 +17,43 @@ Helper functions
*************************************************/
void splitBedIntoBlocks(const BED &bed, int lineNum, bedVector &bedBlocks) {
- if (bed.otherFields.size() < 6) {
- cerr << "Input error: Cannot split into blocks. Found interval with fewer than 12 columns on line " << lineNum << "." << endl;
- exit(1);
- }
-
- int blockCount = atoi(bed.otherFields[3].c_str());
- if ( blockCount <= 0 ) {
- cerr << "Input error: found interval having <= 0 blocks on line " << lineNum << "." << endl;
- exit(1);
- }
- else if ( blockCount == 1 ) {
- //take a short-cut for single blocks
- bedBlocks.push_back(bed);
- }
- else {
- // get the comma-delimited strings for the BED12 block starts and block ends.
- string blockSizes(bed.otherFields[4]);
- string blockStarts(bed.otherFields[5]);
-
- vector<int> sizes;
- vector<int> starts;
- Tokenize(blockSizes, sizes, ",");
- Tokenize(blockStarts, starts, ",");
-
- if ( sizes.size() != (size_t) blockCount || starts.size() != (size_t) blockCount ) {
- cerr << "Input error: found interval with block-counts not matching starts/sizes on line " << lineNum << "." << endl;
- exit(1);
- }
+ if (bed.otherFields.size() < 6) {
+ cerr << "Input error: Cannot split into blocks. Found interval with fewer than 12 columns on line " << lineNum << "." << endl;
+ exit(1);
+ }
+
+ int blockCount = atoi(bed.otherFields[3].c_str());
+ if ( blockCount <= 0 ) {
+ cerr << "Input error: found interval having <= 0 blocks on line " << lineNum << "." << endl;
+ exit(1);
+ }
+ else if ( blockCount == 1 ) {
+ //take a short-cut for single blocks
+ bedBlocks.push_back(bed);
+ }
+ else {
+ // get the comma-delimited strings for the BED12 block starts and block ends.
+ string blockSizes(bed.otherFields[4]);
+ string blockStarts(bed.otherFields[5]);
+
+ vector<int> sizes;
+ vector<int> starts;
+ Tokenize(blockSizes, sizes, ",");
+ Tokenize(blockStarts, starts, ",");
+
+ if ( sizes.size() != (size_t) blockCount || starts.size() != (size_t) blockCount ) {
+ cerr << "Input error: found interval with block-counts not matching starts/sizes on line " << lineNum << "." << endl;
+ exit(1);
+ }
// add each BED block to the bedBlocks vector
- for (UINT i = 0; i < (UINT) blockCount; ++i) {
+ for (UINT i = 0; i < (UINT) blockCount; ++i) {
CHRPOS blockStart = bed.start + starts[i];
CHRPOS blockEnd = bed.start + starts[i] + sizes[i];
BED currBedBlock(bed.chrom, blockStart, blockEnd, bed.name, bed.score, bed.strand, bed.otherFields);
bedBlocks.push_back(currBedBlock);
- }
- }
+ }
+ }
}
@@ -61,52 +61,52 @@ void splitBedIntoBlocks(const BED &bed, int lineNum, bedVector &bedBlocks) {
Sorting comparison functions
************************************************/
bool sortByChrom(BED const &a, BED const &b) {
- if (a.chrom < b.chrom) return true;
- else return false;
+ if (a.chrom < b.chrom) return true;
+ else return false;
};
bool sortByStart(const BED &a, const BED &b) {
- if (a.start < b.start) return true;
- else return false;
+ if (a.start < b.start) return true;
+ else return false;
};
bool sortBySizeAsc(const BED &a, const BED &b) {
-
- CHRPOS aLen = a.end - a.start;
- CHRPOS bLen = b.end - b.start;
-
- if (aLen < bLen) return true;
- else return false;
+
+ CHRPOS aLen = a.end - a.start;
+ CHRPOS bLen = b.end - b.start;
+
+ if (aLen < bLen) return true;
+ else return false;
};
bool sortBySizeDesc(const BED &a, const BED &b) {
-
- CHRPOS aLen = a.end - a.start;
- CHRPOS bLen = b.end - b.start;
-
- if (aLen > bLen) return true;
- else return false;
+
+ CHRPOS aLen = a.end - a.start;
+ CHRPOS bLen = b.end - b.start;
+
+ if (aLen > bLen) return true;
+ else return false;
};
bool sortByScoreAsc(const BED &a, const BED &b) {
- if (a.score < b.score) return true;
- else return false;
+ if (a.score < b.score) return true;
+ else return false;
};
bool sortByScoreDesc(const BED &a, const BED &b) {
- if (a.score > b.score) return true;
- else return false;
+ if (a.score > b.score) return true;
+ else return false;
};
bool byChromThenStart(BED const &a, BED const &b) {
- if (a.chrom < b.chrom) return true;
- else if (a.chrom > b.chrom) return false;
+ if (a.chrom < b.chrom) return true;
+ else if (a.chrom > b.chrom) return false;
- if (a.start < b.start) return true;
- else if (a.start >= b.start) return false;
+ if (a.start < b.start) return true;
+ else if (a.start >= b.start) return false;
- return false;
+ return false;
};
@@ -126,14 +126,14 @@ BedFile::~BedFile(void) {
void BedFile::Open(void) {
- if (bedFile == "stdin") {
- _bedStream = &cin;
- }
- // New method thanks to Assaf Gordon
- else if ((isGzipFile(bedFile) == false) && (isRegularFile(bedFile) == true)) {
+ if (bedFile == "stdin") {
+ _bedStream = &cin;
+ }
+ // New method thanks to Assaf Gordon
+ else if ((isGzipFile(bedFile) == false) && (isRegularFile(bedFile) == true)) {
// open an ifstream
ifstream beds(bedFile.c_str(), ios::in);
-
+
// can we open the file?
if ( !beds ) {
cerr << "Error: The requested bed file (" << bedFile << ") could not be opened. Exiting!" << endl;
@@ -141,23 +141,23 @@ void BedFile::Open(void) {
}
else {
// if so, close it (this was just a test)
- beds.close();
+ beds.close();
// now set a pointer to the stream so that we
_bedStream = new ifstream(bedFile.c_str(), ios::in);
}
- }
- else if ((isGzipFile(bedFile) == true) && (isRegularFile(bedFile) == true)) {
- igzstream beds(bedFile.c_str(), ios::in);
- if ( !beds ) {
- cerr << "Error: The requested bed file (" << bedFile << ") could not be opened. Exiting!" << endl;
- exit (1);
- }
- else {
- // if so, close it (this was just a test)
- beds.close();
- // now set a pointer to the stream so that we
- _bedStream = new igzstream(bedFile.c_str(), ios::in);
- }
+ }
+ else if ((isGzipFile(bedFile) == true) && (isRegularFile(bedFile) == true)) {
+ igzstream beds(bedFile.c_str(), ios::in);
+ if ( !beds ) {
+ cerr << "Error: The requested bed file (" << bedFile << ") could not be opened. Exiting!" << endl;
+ exit (1);
+ }
+ else {
+ // if so, close it (this was just a test)
+ beds.close();
+ // now set a pointer to the stream so that we
+ _bedStream = new igzstream(bedFile.c_str(), ios::in);
+ }
}
else {
cerr << "Error: Unexpected file type (" << bedFile << "). Exiting!" << endl;
@@ -168,55 +168,55 @@ void BedFile::Open(void) {
// Close the BED file
void BedFile::Close(void) {
- if (bedFile != "stdin") delete _bedStream;
+ if (bedFile != "stdin") delete _bedStream;
}
BedLineStatus BedFile::GetNextBed(BED &bed, int &lineNum) {
- // make sure there are still lines to process.
- // if so, tokenize, validate and return the BED entry.
- if (_bedStream->good()) {
- string bedLine;
- vector<string> bedFields;
- bedFields.reserve(12);
-
- // parse the bedStream pointer
- getline(*_bedStream, bedLine);
- lineNum++;
-
- // split into a string vector.
- Tokenize(bedLine,bedFields);
-
- // load the BED struct as long as it's a valid BED entry.
- return parseLine(bed, bedFields, lineNum);
- }
-
- // default if file is closed or EOF
- return BED_INVALID;
+ // make sure there are still lines to process.
+ // if so, tokenize, validate and return the BED entry.
+ if (_bedStream->good()) {
+ string bedLine;
+ vector<string> bedFields;
+ bedFields.reserve(12);
+
+ // parse the bedStream pointer
+ getline(*_bedStream, bedLine);
+ lineNum++;
+
+ // split into a string vector.
+ Tokenize(bedLine,bedFields);
+
+ // load the BED struct as long as it's a valid BED entry.
+ return parseLine(bed, bedFields, lineNum);
+ }
+
+ // default if file is closed or EOF
+ return BED_INVALID;
}
-void BedFile::FindOverlapsPerBin(string chrom, CHRPOS start, CHRPOS end,
+void BedFile::FindOverlapsPerBin(string chrom, CHRPOS start, CHRPOS end,
string strand, vector<BED> &hits, bool forceStrand) {
- BIN startBin, endBin;
- startBin = (start >> _binFirstShift);
- endBin = ((end-1) >> _binFirstShift);
-
- // loop through each bin "level" in the binning hierarchy
- for (BINLEVEL i = 0; i < _binLevels; ++i) {
-
- // loop through each bin at this level of the hierarchy
- BIN offset = _binOffsetsExtended[i];
- for (BIN j = (startBin+offset); j <= (endBin+offset); ++j) {
-
+ BIN startBin, endBin;
+ startBin = (start >> _binFirstShift);
+ endBin = ((end-1) >> _binFirstShift);
+
+ // loop through each bin "level" in the binning hierarchy
+ for (BINLEVEL i = 0; i < _binLevels; ++i) {
+
+ // loop through each bin at this level of the hierarchy
+ BIN offset = _binOffsetsExtended[i];
+ for (BIN j = (startBin+offset); j <= (endBin+offset); ++j) {
+
// loop through each feature in this chrom/bin and see if it overlaps
- // with the feature that was passed in. if so, add the feature to
+ // with the feature that was passed in. if so, add the feature to
// the list of hits.
vector<BED>::const_iterator bedItr = bedMap[chrom][j].begin();
vector<BED>::const_iterator bedEnd = bedMap[chrom][j].end();
-
+
for (; bedItr != bedEnd; ++bedItr) {
// do we have sufficient overlap?
if (overlaps(bedItr->start, bedItr->end, start, end) > 0) {
@@ -227,103 +227,103 @@ void BedFile::FindOverlapsPerBin(string chrom, CHRPOS start, CHRPOS end,
}
}
}
- }
- startBin >>= _binNextShift;
- endBin >>= _binNextShift;
- }
+ }
+ startBin >>= _binNextShift;
+ endBin >>= _binNextShift;
+ }
}
-bool BedFile::FindOneOrMoreOverlapsPerBin(string chrom, CHRPOS start, CHRPOS end, string strand,
- bool forceStrand, float overlapFraction) {
-
- BIN startBin, endBin;
- startBin = (start >> _binFirstShift);
- endBin = ((end-1) >> _binFirstShift);
-
- CHRPOS aLength = (end - start);
-
- // loop through each bin "level" in the binning hierarchy
- for (BINLEVEL i = 0; i < _binLevels; ++i) {
-
- // loop through each bin at this level of the hierarchy
- BIN offset = _binOffsetsExtended[i];
- for (BIN j = (startBin+offset); j <= (endBin+offset); ++j) {
-
- // loop through each feature in this chrom/bin and see if it overlaps
- // with the feature that was passed in. if so, add the feature to
- // the list of hits.
- vector<BED>::const_iterator bedItr = bedMap[chrom][j].begin();
- vector<BED>::const_iterator bedEnd = bedMap[chrom][j].end();
- for (; bedItr != bedEnd; ++bedItr) {
-
- CHRPOS s = max(start, bedItr->start);
- CHRPOS e = min(end, bedItr->end);
- // the number of overlapping bases b/w a and b
- int overlapBases = (e - s);
-
- // do we have sufficient overlap?
- if ( (float) overlapBases / (float) aLength >= overlapFraction) {
- // skip the hit if not on the same strand (and we care)
- if (forceStrand == false) return true;
- else if ( (forceStrand == true) && (strand == bedItr->strand)) {
- return true;
- }
- }
- }
- }
- startBin >>= _binNextShift;
- endBin >>= _binNextShift;
- }
- return false;
+bool BedFile::FindOneOrMoreOverlapsPerBin(string chrom, CHRPOS start, CHRPOS end, string strand,
+ bool forceStrand, float overlapFraction) {
+
+ BIN startBin, endBin;
+ startBin = (start >> _binFirstShift);
+ endBin = ((end-1) >> _binFirstShift);
+
+ CHRPOS aLength = (end - start);
+
+ // loop through each bin "level" in the binning hierarchy
+ for (BINLEVEL i = 0; i < _binLevels; ++i) {
+
+ // loop through each bin at this level of the hierarchy
+ BIN offset = _binOffsetsExtended[i];
+ for (BIN j = (startBin+offset); j <= (endBin+offset); ++j) {
+
+ // loop through each feature in this chrom/bin and see if it overlaps
+ // with the feature that was passed in. if so, add the feature to
+ // the list of hits.
+ vector<BED>::const_iterator bedItr = bedMap[chrom][j].begin();
+ vector<BED>::const_iterator bedEnd = bedMap[chrom][j].end();
+ for (; bedItr != bedEnd; ++bedItr) {
+
+ CHRPOS s = max(start, bedItr->start);
+ CHRPOS e = min(end, bedItr->end);
+ // the number of overlapping bases b/w a and b
+ int overlapBases = (e - s);
+
+ // do we have sufficient overlap?
+ if ( (float) overlapBases / (float) aLength >= overlapFraction) {
+ // skip the hit if not on the same strand (and we care)
+ if (forceStrand == false) return true;
+ else if ( (forceStrand == true) && (strand == bedItr->strand)) {
+ return true;
+ }
+ }
+ }
+ }
+ startBin >>= _binNextShift;
+ endBin >>= _binNextShift;
+ }
+ return false;
}
-bool BedFile::FindOneOrMoreReciprocalOverlapsPerBin(string chrom, CHRPOS start, CHRPOS end, string strand,
- bool forceStrand, float overlapFraction) {
-
- BIN startBin, endBin;
- startBin = (start >> _binFirstShift);
- endBin = ((end-1) >> _binFirstShift);
-
- CHRPOS aLength = (end - start);
-
- // loop through each bin "level" in the binning hierarchy
- for (BINLEVEL i = 0; i < _binLevels; ++i) {
-
- // loop through each bin at this level of the hierarchy
- BIN offset = _binOffsetsExtended[i];
- for (BIN j = (startBin+offset); j <= (endBin+offset); ++j) {
-
- // loop through each feature in this chrom/bin and see if it overlaps
- // with the feature that was passed in. if so, add the feature to
- // the list of hits.
- vector<BED>::const_iterator bedItr = bedMap[chrom][j].begin();
- vector<BED>::const_iterator bedEnd = bedMap[chrom][j].end();
- for (; bedItr != bedEnd; ++bedItr) {
- CHRPOS s = max(start, bedItr->start);
- CHRPOS e = min(end, bedItr->end);
-
- // the number of overlapping bases b/w a and b
- int overlapBases = (e - s);
-
- // do we have sufficient overlap?
- if ( (float) overlapBases / (float) aLength >= overlapFraction) {
- CHRPOS bLength = (bedItr->end - bedItr->start);
- float bOverlap = ( (float) overlapBases / (float) bLength );
- if ((forceStrand == false) && (bOverlap >= overlapFraction)) {
- return true;
- }
- else if ( (forceStrand == true) && (strand == bedItr->strand) && (bOverlap >= overlapFraction)) {
- return true;
- }
- }
- }
- }
- startBin >>= _binNextShift;
- endBin >>= _binNextShift;
- }
- return false;
+bool BedFile::FindOneOrMoreReciprocalOverlapsPerBin(string chrom, CHRPOS start, CHRPOS end, string strand,
+ bool forceStrand, float overlapFraction) {
+
+ BIN startBin, endBin;
+ startBin = (start >> _binFirstShift);
+ endBin = ((end-1) >> _binFirstShift);
+
+ CHRPOS aLength = (end - start);
+
+ // loop through each bin "level" in the binning hierarchy
+ for (BINLEVEL i = 0; i < _binLevels; ++i) {
+
+ // loop through each bin at this level of the hierarchy
+ BIN offset = _binOffsetsExtended[i];
+ for (BIN j = (startBin+offset); j <= (endBin+offset); ++j) {
+
+ // loop through each feature in this chrom/bin and see if it overlaps
+ // with the feature that was passed in. if so, add the feature to
+ // the list of hits.
+ vector<BED>::const_iterator bedItr = bedMap[chrom][j].begin();
+ vector<BED>::const_iterator bedEnd = bedMap[chrom][j].end();
+ for (; bedItr != bedEnd; ++bedItr) {
+ CHRPOS s = max(start, bedItr->start);
+ CHRPOS e = min(end, bedItr->end);
+
+ // the number of overlapping bases b/w a and b
+ int overlapBases = (e - s);
+
+ // do we have sufficient overlap?
+ if ( (float) overlapBases / (float) aLength >= overlapFraction) {
+ CHRPOS bLength = (bedItr->end - bedItr->start);
+ float bOverlap = ( (float) overlapBases / (float) bLength );
+ if ((forceStrand == false) && (bOverlap >= overlapFraction)) {
+ return true;
+ }
+ else if ( (forceStrand == true) && (strand == bedItr->strand) && (bOverlap >= overlapFraction)) {
+ return true;
+ }
+ }
+ }
+ }
+ startBin >>= _binNextShift;
+ endBin >>= _binNextShift;
+ }
+ return false;
}
@@ -333,18 +333,18 @@ void BedFile::countHits(const BED &a, bool forceStrand) {
startBin = (a.start >> _binFirstShift);
endBin = ((a.end-1) >> _binFirstShift);
- // loop through each bin "level" in the binning hierarchy
+ // loop through each bin "level" in the binning hierarchy
for (BINLEVEL i = 0; i < _binLevels; ++i) {
- // loop through each bin at this level of the hierarchy
+ // loop through each bin at this level of the hierarchy
BIN offset = _binOffsetsExtended[i];
for (BIN j = (startBin+offset); j <= (endBin+offset); ++j) {
// loop through each feature in this chrom/bin and see if it overlaps
- // with the feature that was passed in. if so, add the feature to
+ // with the feature that was passed in. if so, add the feature to
// the list of hits.
vector<BEDCOV>::iterator bedItr = bedCovMap[a.chrom][j].begin();
- vector<BEDCOV>::iterator bedEnd = bedCovMap[a.chrom][j].end();
+ vector<BEDCOV>::iterator bedEnd = bedCovMap[a.chrom][j].end();
for (; bedItr != bedEnd; ++bedItr) {
// skip the hit if not on the same strand (and we care)
@@ -359,7 +359,7 @@ void BedFile::countHits(const BED &a, bool forceStrand) {
if (a.start < bedItr->minOverlapStart) {
bedItr->minOverlapStart = a.start;
- }
+ }
}
}
}
@@ -373,29 +373,29 @@ void BedFile::countSplitHits(const vector<BED> &bedBlocks, bool forceStrand) {
// set to track the distinct B features that had coverage.
// we'll update the counts of coverage for these features by one
- // at the end of this function to avoid over-counting.
+ // at the end of this function to avoid over-counting.
set< vector<BEDCOV>::iterator > validHits;
-
+
vector<BED>::const_iterator blockItr = bedBlocks.begin();
- vector<BED>::const_iterator blockEnd = bedBlocks.end();
- for (; blockItr != blockEnd; ++blockItr) {
-
+ vector<BED>::const_iterator blockEnd = bedBlocks.end();
+ for (; blockItr != blockEnd; ++blockItr) {
+
BIN startBin, endBin;
startBin = (blockItr->start >> _binFirstShift);
endBin = ((blockItr->end-1) >> _binFirstShift);
-
- // loop through each bin "level" in the binning hierarchy
+
+ // loop through each bin "level" in the binning hierarchy
for (BINLEVEL i = 0; i < _binLevels; ++i) {
- // loop through each bin at this level of the hierarchy
+ // loop through each bin at this level of the hierarchy
BIN offset = _binOffsetsExtended[i];
for (BIN j = (startBin+offset); j <= (endBin+offset); ++j) {
// loop through each feature in this chrom/bin and see if it overlaps
- // with the feature that was passed in. if so, add the feature to
+ // with the feature that was passed in. if so, add the feature to
// the list of hits.
vector<BEDCOV>::iterator bedItr = bedCovMap[blockItr->chrom][j].begin();
- vector<BEDCOV>::iterator bedEnd = bedCovMap[blockItr->chrom][j].end();
+ vector<BEDCOV>::iterator bedEnd = bedCovMap[blockItr->chrom][j].end();
for (; bedItr != bedEnd; ++bedItr) {
// skip the hit if not on the same strand (and we care)
@@ -407,7 +407,7 @@ void BedFile::countSplitHits(const vector<BED> &bedBlocks, bool forceStrand) {
bedItr->depthMap[blockItr->end].ends++;
validHits.insert(bedItr);
if (blockItr->start < bedItr->minOverlapStart)
- bedItr->minOverlapStart = blockItr->start;
+ bedItr->minOverlapStart = blockItr->start;
}
}
}
@@ -433,18 +433,18 @@ void BedFile::countListHits(const BED &a, int index, bool forceStrand) {
startBin = (a.start >> _binFirstShift);
endBin = ((a.end-1) >> _binFirstShift);
- // loop through each bin "level" in the binning hierarchy
+ // loop through each bin "level" in the binning hierarchy
for (BINLEVEL i = 0; i < _binLevels; ++i) {
- // loop through each bin at this level of the hierarchy
+ // loop through each bin at this level of the hierarchy
BIN offset = _binOffsetsExtended[i];
for (BIN j = (startBin+offset); j <= (endBin+offset); ++j) {
// loop through each feature in this chrom/bin and see if it overlaps
- // with the feature that was passed in. if so, add the feature to
+ // with the feature that was passed in. if so, add the feature to
// the list of hits.
vector<BEDCOVLIST>::iterator bedItr = bedCovListMap[a.chrom][j].begin();
- vector<BEDCOVLIST>::iterator bedEnd = bedCovListMap[a.chrom][j].end();
+ vector<BEDCOVLIST>::iterator bedEnd = bedCovListMap[a.chrom][j].end();
for (; bedItr != bedEnd; ++bedItr) {
if (forceStrand && (a.strand != bedItr->strand)) {
@@ -457,7 +457,7 @@ void BedFile::countListHits(const BED &a, int index, bool forceStrand) {
if (a.start < bedItr->minOverlapStarts[index]) {
bedItr->minOverlapStarts[index] = a.start;
- }
+ }
}
}
}
@@ -468,14 +468,14 @@ void BedFile::countListHits(const BED &a, int index, bool forceStrand) {
void BedFile::setGff (bool gff) {
- if (gff == true) this->_isGff = true;
- else this->_isGff = false;
+ if (gff == true) this->_isGff = true;
+ else this->_isGff = false;
}
void BedFile::setVcf (bool vcf) {
- if (vcf == true) this->_isVcf = true;
- else this->_isVcf = false;
+ if (vcf == true) this->_isVcf = true;
+ else this->_isVcf = false;
}
@@ -492,33 +492,33 @@ void BedFile::setBedType (int colNums) {
void BedFile::loadBedFileIntoMap() {
- BED bedEntry, nullBed;
- int lineNum = 0;
- BedLineStatus bedStatus;
-
- Open();
- while ((bedStatus = GetNextBed(bedEntry, lineNum)) != BED_INVALID) {
- if (bedStatus == BED_VALID) {
- BIN bin = getBin(bedEntry.start, bedEntry.end);
- bedMap[bedEntry.chrom][bin].push_back(bedEntry);
- bedEntry = nullBed;
- }
- }
- Close();
+ BED bedEntry, nullBed;
+ int lineNum = 0;
+ BedLineStatus bedStatus;
+
+ Open();
+ while ((bedStatus = GetNextBed(bedEntry, lineNum)) != BED_INVALID) {
+ if (bedStatus == BED_VALID) {
+ BIN bin = getBin(bedEntry.start, bedEntry.end);
+ bedMap[bedEntry.chrom][bin].push_back(bedEntry);
+ bedEntry = nullBed;
+ }
+ }
+ Close();
}
void BedFile::loadBedCovFileIntoMap() {
- BED bedEntry, nullBed;
- int lineNum = 0;
- BedLineStatus bedStatus;
-
- Open();
- while ((bedStatus = GetNextBed(bedEntry, lineNum)) != BED_INVALID) {
- if (bedStatus == BED_VALID) {
- BIN bin = getBin(bedEntry.start, bedEntry.end);
-
+ BED bedEntry, nullBed;
+ int lineNum = 0;
+ BedLineStatus bedStatus;
+
+ Open();
+ while ((bedStatus = GetNextBed(bedEntry, lineNum)) != BED_INVALID) {
+ if (bedStatus == BED_VALID) {
+ BIN bin = getBin(bedEntry.start, bedEntry.end);
+
BEDCOV bedCov;
bedCov.chrom = bedEntry.chrom;
bedCov.start = bedEntry.start;
@@ -527,27 +527,27 @@ void BedFile::loadBedCovFileIntoMap() {
bedCov.score = bedEntry.score;
bedCov.strand = bedEntry.strand;
bedCov.otherFields = bedEntry.otherFields;
- bedCov.count = 0;
- bedCov.minOverlapStart = INT_MAX;
-
- bedCovMap[bedEntry.chrom][bin].push_back(bedCov);
- bedEntry = nullBed;
- }
- }
- Close();
+ bedCov.count = 0;
+ bedCov.minOverlapStart = INT_MAX;
+
+ bedCovMap[bedEntry.chrom][bin].push_back(bedCov);
+ bedEntry = nullBed;
+ }
+ }
+ Close();
}
void BedFile::loadBedCovListFileIntoMap() {
- BED bedEntry, nullBed;
- int lineNum = 0;
- BedLineStatus bedStatus;
+ BED bedEntry, nullBed;
+ int lineNum = 0;
+ BedLineStatus bedStatus;
+
+ Open();
+ while ((bedStatus = GetNextBed(bedEntry, lineNum)) != BED_INVALID) {
+ if (bedStatus == BED_VALID) {
+ BIN bin = getBin(bedEntry.start, bedEntry.end);
- Open();
- while ((bedStatus = GetNextBed(bedEntry, lineNum)) != BED_INVALID) {
- if (bedStatus == BED_VALID) {
- BIN bin = getBin(bedEntry.start, bedEntry.end);
-
BEDCOVLIST bedCovList;
bedCovList.chrom = bedEntry.chrom;
bedCovList.start = bedEntry.start;
@@ -557,32 +557,32 @@ void BedFile::loadBedCovListFileIntoMap() {
bedCovList.strand = bedEntry.strand;
bedCovList.otherFields = bedEntry.otherFields;
- bedCovListMap[bedEntry.chrom][bin].push_back(bedCovList);
- bedEntry = nullBed;
- }
- }
- Close();
+ bedCovListMap[bedEntry.chrom][bin].push_back(bedCovList);
+ bedEntry = nullBed;
+ }
+ }
+ Close();
}
void BedFile::loadBedFileIntoMapNoBin() {
-
- BED bedEntry, nullBed;
- int lineNum = 0;
- BedLineStatus bedStatus;
-
- Open();
- while ((bedStatus = this->GetNextBed(bedEntry, lineNum)) != BED_INVALID) {
- if (bedStatus == BED_VALID) {
- bedMapNoBin[bedEntry.chrom].push_back(bedEntry);
- bedEntry = nullBed;
- }
- }
- Close();
-
- // sort the BED entries for each chromosome
- // in ascending order of start position
- for (masterBedMapNoBin::iterator m = this->bedMapNoBin.begin(); m != this->bedMapNoBin.end(); ++m) {
- sort(m->second.begin(), m->second.end(), sortByStart);
- }
+
+ BED bedEntry, nullBed;
+ int lineNum = 0;
+ BedLineStatus bedStatus;
+
+ Open();
+ while ((bedStatus = this->GetNextBed(bedEntry, lineNum)) != BED_INVALID) {
+ if (bedStatus == BED_VALID) {
+ bedMapNoBin[bedEntry.chrom].push_back(bedEntry);
+ bedEntry = nullBed;
+ }
+ }
+ Close();
+
+ // sort the BED entries for each chromosome
+ // in ascending order of start position
+ for (masterBedMapNoBin::iterator m = this->bedMapNoBin.begin(); m != this->bedMapNoBin.end(); ++m) {
+ sort(m->second.begin(), m->second.end(), sortByStart);
+ }
}
diff --git a/src/utils/bedFile/bedFile.h b/src/utils/bedFile/bedFile.h
index 2d5d8886eb7946ed0d9f60135fe928ddca1819ad..ddf29d3d457ff5585a7955588770ab02f39d6338 100644
--- a/src/utils/bedFile/bedFile.h
+++ b/src/utils/bedFile/bedFile.h
@@ -50,7 +50,7 @@ typedef uint32_t UINT;
const BIN _numBins = 37450;
const BINLEVEL _binLevels = 7;
-// bins range in size from 16kb to 512Mb
+// bins range in size from 16kb to 512Mb
// Bin 0 spans 512Mbp, # Level 1
// Bins 1-8 span 64Mbp, # Level 2
// Bins 9-72 span 8Mbp, # Level 3
@@ -59,9 +59,9 @@ const BINLEVEL _binLevels = 7;
// Bins 4681-37449 span 16Kbp # Level 6
const BIN _binOffsetsExtended[] = {32678+4096+512+64+8+1, 4096+512+64+8+1, 512+64+8+1, 64+8+1, 8+1, 1, 0};
//const BIN _binOffsetsExtended[] = {4096+512+64+8+1, 4096+512+64+8+1, 512+64+8+1, 64+8+1, 8+1, 1, 0};
-
-const USHORT _binFirstShift = 14; /* How much to shift to get to finest bin. */
-const USHORT _binNextShift = 3; /* How much to shift to get to next larger bin. */
+
+const USHORT _binFirstShift = 14; /* How much to shift to get to finest bin. */
+const USHORT _binNextShift = 3; /* How much to shift to get to next larger bin. */
//*************************************************
@@ -69,39 +69,39 @@ const USHORT _binNextShift = 3; /* How much to shift to get to next larger bin
//*************************************************
struct DEPTH {
- UINT starts;
- UINT ends;
+ UINT starts;
+ UINT ends;
};
/*
- Structure for regular BED records
+ Structure for regular BED records
*/
struct BED {
- // Regular BED fields
- string chrom;
- CHRPOS start;
- CHRPOS end;
- string name;
- string score;
- string strand;
-
- // Add'l fields for BED12 and/or custom BED annotations
- vector<string> otherFields;
-
- // experimental fields for the FJOIN approach.
- bool added;
- bool finished;
- // list of hits from another file.
+ // Regular BED fields
+ string chrom;
+ CHRPOS start;
+ CHRPOS end;
+ string name;
+ string score;
+ string strand;
+
+ // Add'l fields for BED12 and/or custom BED annotations
+ vector<string> otherFields;
+
+ // experimental fields for the FJOIN approach.
+ bool added;
+ bool finished;
+ // list of hits from another file.
vector<BED> overlaps;
-
+
public:
// constructors
// Null
- BED()
- : chrom(""),
+ BED()
+ : chrom(""),
start(0),
end(0),
name(""),
@@ -109,40 +109,40 @@ public:
strand(""),
otherFields(),
added(false),
- finished(false),
+ finished(false),
overlaps()
{}
-
+
// BED3
- BED(string chrom, CHRPOS start, CHRPOS end)
- : chrom(chrom),
+ BED(string chrom, CHRPOS start, CHRPOS end)
+ : chrom(chrom),
start(start),
end(end)
{}
// BED4
- BED(string chrom, CHRPOS start, CHRPOS end, string strand)
- : chrom(chrom),
+ BED(string chrom, CHRPOS start, CHRPOS end, string strand)
+ : chrom(chrom),
start(start),
end(end),
strand(strand)
{}
// BED6
- BED(string chrom, CHRPOS start, CHRPOS end, string name,
- string score, string strand)
- : chrom(chrom),
+ BED(string chrom, CHRPOS start, CHRPOS end, string name,
+ string score, string strand)
+ : chrom(chrom),
start(start),
end(end),
name(name),
score(score),
strand(strand)
{}
-
+
// BEDALL
- BED(string chrom, CHRPOS start, CHRPOS end, string name,
- string score, string strand, vector<string> otherFields)
- : chrom(chrom),
+ BED(string chrom, CHRPOS start, CHRPOS end, string name,
+ string score, string strand, vector<string> otherFields)
+ : chrom(chrom),
start(start),
end(end),
name(name),
@@ -150,13 +150,13 @@ public:
strand(strand),
otherFields(otherFields)
{}
-
+
}; // BED
/*
- Structure for each end of a paired BED record
- mate points to the other end.
+ Structure for each end of a paired BED record
+ mate points to the other end.
*/
struct MATE {
BED bed;
@@ -166,21 +166,21 @@ struct MATE {
/*
- Structure for regular BED COVERAGE records
+ Structure for regular BED COVERAGE records
*/
struct BEDCOV {
- // Regular BED fields
- CHRPOS start;
- CHRPOS end;
-
- string chrom;
- string name;
- string score;
- string strand;
+ // Regular BED fields
+ CHRPOS start;
+ CHRPOS end;
+
+ string chrom;
+ string name;
+ string score;
+ string strand;
- // Add'l fields for BED12 and/or custom BED annotations
- vector<string> otherFields;
+ // Add'l fields for BED12 and/or custom BED annotations
+ vector<string> otherFields;
// Additional fields specific to computing coverage
map<unsigned int, DEPTH> depthMap;
@@ -190,22 +190,22 @@ struct BEDCOV {
/*
- Structure for BED COVERAGE records having lists of
- multiple coverages
+ Structure for BED COVERAGE records having lists of
+ multiple coverages
*/
struct BEDCOVLIST {
- // Regular BED fields
- CHRPOS start;
- CHRPOS end;
-
- string chrom;
- string name;
- string score;
- string strand;
+ // Regular BED fields
+ CHRPOS start;
+ CHRPOS end;
- // Add'l fields for BED12 and/or custom BED annotations
- vector<string> otherFields;
+ string chrom;
+ string name;
+ string score;
+ string strand;
+
+ // Add'l fields for BED12 and/or custom BED annotations
+ vector<string> otherFields;
// Additional fields specific to computing coverage
vector< map<unsigned int, DEPTH> > depthMapList;
@@ -216,7 +216,7 @@ struct BEDCOVLIST {
// enum to flag the state of a given line in a BED file.
enum BedLineStatus
-{
+{
BED_INVALID = -1,
BED_HEADER = 0,
BED_BLANK = 1,
@@ -225,7 +225,7 @@ enum BedLineStatus
// enum to indicate the type of file we are dealing with
enum FileType
-{
+{
BED_FILETYPE,
GFF_FILETYPE,
VCF_FILETYPE
@@ -254,10 +254,10 @@ typedef map<string, bedVector, std::less<string> > masterBedMapNoBin;
// EXPERIMENTAL - wait for TR1
// typedef vector<BED> bedVector;
// typedef vector<BEDCOV> bedCovVector;
-//
+//
// typedef tr1::unordered_map<BIN, bedVector> binsToBeds;
// typedef tr1::unordered_map<BIN, bedCovVector> binsToBedCovs;
-//
+//
// typedef tr1::unordered_map<string, binsToBeds> masterBedMap;
// typedef tr1::unordered_map<string, binsToBedCovs> masterBedCovMap;
// typedef tr1::unordered_map<string, bedVector> masterBedMapNoBin;
@@ -270,7 +270,7 @@ BIN getBin(CHRPOS start, CHRPOS end) {
--end;
start >>= _binFirstShift;
end >>= _binFirstShift;
-
+
for (register short i = 0; i < _binLevels; ++i) {
if (start == end) return _binOffsetsExtended[i] + start;
start >>= _binNextShift;
@@ -287,16 +287,16 @@ inline bool isInteger(const std::string& s) {
int len = s.length();
for (int i = 0; i < len; i++) {
if (!std::isdigit(s[i])) return false;
- }
+ }
return true;
}
-// return the amount of overlap between two features. Negative if none and the the
+// return the amount of overlap between two features. Negative if none and the the
// number of negative bases is the distance between the two.
-inline
+inline
int overlaps(CHRPOS aS, CHRPOS aE, CHRPOS bS, CHRPOS bE) {
- return min(aE, bE) - max(aS, bS);
+ return min(aE, bE) - max(aS, bS);
}
@@ -304,8 +304,8 @@ int overlaps(CHRPOS aS, CHRPOS aE, CHRPOS bS, CHRPOS bE) {
void splitBedIntoBlocks(const BED &bed, int lineNum, bedVector &bedBlocks);
-// BED Sorting Methods
-bool sortByChrom(const BED &a, const BED &b);
+// BED Sorting Methods
+bool sortByChrom(const BED &a, const BED &b);
bool sortByStart(const BED &a, const BED &b);
bool sortBySizeAsc(const BED &a, const BED &b);
bool sortBySizeDesc(const BED &a, const BED &b);
@@ -322,89 +322,89 @@ class BedFile {
public:
- // Constructor
- BedFile(string &);
-
- // Destructor
- ~BedFile(void);
-
- // Open a BED file for reading (creates an istream pointer)
- void Open(void);
-
- // Close an opened BED file.
- void Close(void);
-
- // Get the next BED entry in an opened BED file.
- BedLineStatus GetNextBed (BED &bed, int &lineNum);
-
- // load a BED file into a map keyed by chrom, then bin. value is vector of BEDs
- void loadBedFileIntoMap();
-
- // load a BED file into a map keyed by chrom, then bin. value is vector of BEDCOVs
- void loadBedCovFileIntoMap();
-
- // load a BED file into a map keyed by chrom, then bin. value is vector of BEDCOVLISTs
- void loadBedCovListFileIntoMap();
-
- // load a BED file into a map keyed by chrom. value is vector of BEDs
- void loadBedFileIntoMapNoBin();
-
- // Given a chrom, start, end and strand for a single feature,
- // search for all overlapping features in another BED file.
- // Searches through each relevant genome bin on the same chromosome
- // as the single feature. Note: Adapted from kent source "binKeeperFind"
- void FindOverlapsPerBin(string chrom, CHRPOS start, CHRPOS end, string strand, vector<BED> &hits, bool forceStrand);
-
- // return true if at least one overlap was found. otherwise, return false.
- bool FindOneOrMoreOverlapsPerBin(string chrom, CHRPOS start, CHRPOS end, string strand,
- bool forceStrand, float overlapFraction = 0.0);
-
- // return true if at least one __reciprocal__ overlap was found. otherwise, return false.
- bool FindOneOrMoreReciprocalOverlapsPerBin(string chrom, CHRPOS start, CHRPOS end, string strand,
- bool forceStrand, float overlapFraction = 0.0);
-
- // Given a chrom, start, end and strand for a single feature,
- // increment a the number of hits for each feature in B file
- // that the feature overlaps
- void countHits(const BED &a, bool forceStrand);
-
- // same as above, but has special logic that processes a set of
- // BED "blocks" from a single entry so as to avoid over-counting
- // each "block" of a single BAM/BED12 as distinct coverage. That is,
- // if one read has four block, we only want to count the coverage as
- // coming from one read, not four.
+ // Constructor
+ BedFile(string &);
+
+ // Destructor
+ ~BedFile(void);
+
+ // Open a BED file for reading (creates an istream pointer)
+ void Open(void);
+
+ // Close an opened BED file.
+ void Close(void);
+
+ // Get the next BED entry in an opened BED file.
+ BedLineStatus GetNextBed (BED &bed, int &lineNum);
+
+ // load a BED file into a map keyed by chrom, then bin. value is vector of BEDs
+ void loadBedFileIntoMap();
+
+ // load a BED file into a map keyed by chrom, then bin. value is vector of BEDCOVs
+ void loadBedCovFileIntoMap();
+
+ // load a BED file into a map keyed by chrom, then bin. value is vector of BEDCOVLISTs
+ void loadBedCovListFileIntoMap();
+
+ // load a BED file into a map keyed by chrom. value is vector of BEDs
+ void loadBedFileIntoMapNoBin();
+
+ // Given a chrom, start, end and strand for a single feature,
+ // search for all overlapping features in another BED file.
+ // Searches through each relevant genome bin on the same chromosome
+ // as the single feature. Note: Adapted from kent source "binKeeperFind"
+ void FindOverlapsPerBin(string chrom, CHRPOS start, CHRPOS end, string strand, vector<BED> &hits, bool forceStrand);
+
+ // return true if at least one overlap was found. otherwise, return false.
+ bool FindOneOrMoreOverlapsPerBin(string chrom, CHRPOS start, CHRPOS end, string strand,
+ bool forceStrand, float overlapFraction = 0.0);
+
+ // return true if at least one __reciprocal__ overlap was found. otherwise, return false.
+ bool FindOneOrMoreReciprocalOverlapsPerBin(string chrom, CHRPOS start, CHRPOS end, string strand,
+ bool forceStrand, float overlapFraction = 0.0);
+
+ // Given a chrom, start, end and strand for a single feature,
+ // increment a the number of hits for each feature in B file
+ // that the feature overlaps
+ void countHits(const BED &a, bool forceStrand);
+
+ // same as above, but has special logic that processes a set of
+ // BED "blocks" from a single entry so as to avoid over-counting
+ // each "block" of a single BAM/BED12 as distinct coverage. That is,
+ // if one read has four block, we only want to count the coverage as
+ // coming from one read, not four.
void countSplitHits(const vector<BED> &bedBlock, bool forceStrand);
- // Given a chrom, start, end and strand for a single feature,
- // increment a the number of hits for each feature in B file
- // that the feature overlaps
+ // Given a chrom, start, end and strand for a single feature,
+ // increment a the number of hits for each feature in B file
+ // that the feature overlaps
void countListHits(const BED &a, int index, bool forceStrand);
-
- // the bedfile with which this instance is associated
- string bedFile;
- unsigned int bedType; // 3-6, 12 for BED
- // 9 for GFF
-
- // Main data structires used by BEDTools
+
+ // the bedfile with which this instance is associated
+ string bedFile;
+ unsigned int bedType; // 3-6, 12 for BED
+ // 9 for GFF
+
+ // Main data structires used by BEDTools
masterBedCovMap bedCovMap;
masterBedCovListMap bedCovListMap;
- masterBedMap bedMap;
- masterBedMapNoBin bedMapNoBin;
-
+ masterBedMap bedMap;
+ masterBedMapNoBin bedMapNoBin;
+
private:
-
- // data
- bool _isGff;
- bool _isVcf;
+
+ // data
+ bool _isGff;
+ bool _isVcf;
bool _typeIsKnown; // do we know the type? (i.e., BED, GFF, VCF)
- FileType _fileType; // what is the file type? (BED? GFF? VCF?)
- istream *_bedStream;
+ FileType _fileType; // what is the file type? (BED? GFF? VCF?)
+ istream *_bedStream;
void setGff (bool isGff);
void setVcf (bool isVcf);
void setFileType (FileType type);
void setBedType (int colNums);
-
+
/******************************************************
Private definitions to circumvent linker issues with
templated member functions.
@@ -416,19 +416,19 @@ private:
template <typename T>
inline BedLineStatus parseLine (T &bed, const vector<string> &lineVector, int &lineNum) {
- //char *p2End, *p3End, *p4End, *p5End;
- //long l2, l3, l4, l5;
+ //char *p2End, *p3End, *p4End, *p5End;
+ //long l2, l3, l4, l5;
unsigned int numFields = lineVector.size();
-
- // bail out if we have a blank line
- if (numFields == 0) {
- return BED_BLANK;
- }
- if ((lineVector[0].find("track") == string::npos) && (lineVector[0].find("browser") == string::npos) && (lineVector[0].find("#") == string::npos) ) {
+ // bail out if we have a blank line
+ if (numFields == 0) {
+ return BED_BLANK;
+ }
- if (numFields >= 3) {
- // line parsing for all lines after the first non-header line
+ if ((lineVector[0].find("track") == string::npos) && (lineVector[0].find("browser") == string::npos) && (lineVector[0].find("#") == string::npos) ) {
+
+ if (numFields >= 3) {
+ // line parsing for all lines after the first non-header line
if (_typeIsKnown == true) {
switch(_fileType) {
case BED_FILETYPE:
@@ -442,48 +442,48 @@ private:
exit(1);
}
}
- // line parsing for first non-header line: figure out file contents
+ // line parsing for first non-header line: figure out file contents
else {
- // it's BED format if columns 2 and 3 are integers
- if (isInteger(lineVector[1]) && isInteger(lineVector[2])) {
- setGff(false);
- setFileType(BED_FILETYPE);
+ // it's BED format if columns 2 and 3 are integers
+ if (isInteger(lineVector[1]) && isInteger(lineVector[2])) {
+ setGff(false);
+ setFileType(BED_FILETYPE);
setBedType(numFields); // we now expect numFields columns in each line
- if (parseBedLine(bed, lineVector, lineNum, numFields) == true) return BED_VALID;
- }
- // it's VCF, assuming the second column is numeric and there are at least 8 fields.
- else if (isInteger(lineVector[1]) && numFields >= 8) {
+ if (parseBedLine(bed, lineVector, lineNum, numFields) == true) return BED_VALID;
+ }
+ // it's VCF, assuming the second column is numeric and there are at least 8 fields.
+ else if (isInteger(lineVector[1]) && numFields >= 8) {
setGff(false);
setVcf(true);
setFileType(VCF_FILETYPE);
setBedType(numFields); // we now expect numFields columns in each line
if (parseVcfLine(bed, lineVector, lineNum, numFields) == true) return BED_VALID;
- }
- // it's GFF, assuming columns columns 4 and 5 are numeric and we have 9 fields total.
- else if ((numFields == 9) && isInteger(lineVector[3]) && isInteger(lineVector[4])) {
- setGff(true);
- setFileType(GFF_FILETYPE);
- setBedType(numFields); // we now expect numFields columns in each line
- if (parseGffLine(bed, lineVector, lineNum, numFields) == true) return BED_VALID;
- }
- else {
- cerr << "Unexpected file format. Please use tab-delimited BED, GFF, or VCF. " <<
- "Perhaps you have non-integer starts or ends at line " << lineNum << "?" << endl;
- exit(1);
- }
- }
- }
- else {
- cerr << "It looks as though you have less than 3 columns at line: " << lineNum << ". Are you sure your files are tab-delimited?" << endl;
- exit(1);
- }
- }
- else {
- lineNum--;
- return BED_HEADER;
- }
- // default
- return BED_INVALID;
+ }
+ // it's GFF, assuming columns columns 4 and 5 are numeric and we have 9 fields total.
+ else if ((numFields == 9) && isInteger(lineVector[3]) && isInteger(lineVector[4])) {
+ setGff(true);
+ setFileType(GFF_FILETYPE);
+ setBedType(numFields); // we now expect numFields columns in each line
+ if (parseGffLine(bed, lineVector, lineNum, numFields) == true) return BED_VALID;
+ }
+ else {
+ cerr << "Unexpected file format. Please use tab-delimited BED, GFF, or VCF. " <<
+ "Perhaps you have non-integer starts or ends at line " << lineNum << "?" << endl;
+ exit(1);
+ }
+ }
+ }
+ else {
+ cerr << "It looks as though you have less than 3 columns at line: " << lineNum << ". Are you sure your files are tab-delimited?" << endl;
+ exit(1);
+ }
+ }
+ else {
+ lineNum--;
+ return BED_HEADER;
+ }
+ // default
+ return BED_INVALID;
}
@@ -493,13 +493,13 @@ private:
template <typename T>
inline bool parseBedLine (T &bed, const vector<string> &lineVector, int lineNum, unsigned int numFields) {
- // process as long as the number of fields in this
+ // process as long as the number of fields in this
// line matches what we expect for this file.
- if (numFields == this->bedType) {
+ if (numFields == this->bedType) {
bed.chrom = lineVector[0];
bed.start = atoi(lineVector[1].c_str());
bed.end = atoi(lineVector[2].c_str());
-
+
if (this->bedType == 4) {
bed.name = lineVector[3];
}
@@ -515,23 +515,23 @@ private:
else if (this->bedType > 6) {
bed.name = lineVector[3];
bed.score = lineVector[4];
- bed.strand = lineVector[5];
+ bed.strand = lineVector[5];
for (unsigned int i = 6; i < lineVector.size(); ++i) {
- bed.otherFields.push_back(lineVector[i]);
+ bed.otherFields.push_back(lineVector[i]);
}
}
else if (this->bedType != 3) {
- cerr << "Error: unexpected number of fields at line: " << lineNum
- << ". Verify that your files are TAB-delimited. Exiting..." << endl;
+ cerr << "Error: unexpected number of fields at line: " << lineNum
+ << ". Verify that your files are TAB-delimited. Exiting..." << endl;
exit(1);
}
-
+
// sanity checks.
if ((bed.start <= bed.end) && (bed.start >= 0) && (bed.end >= 0)) {
return true;
}
else if (bed.start > bed.end) {
- cerr << "Error: malformed BED entry at line " << lineNum << ". Start was greater than end. Exiting." << endl;
+ cerr << "Error: malformed BED entry at line " << lineNum << ". Start was greater than end. Exiting." << endl;
exit(1);
}
else if ( (bed.start < 0) || (bed.end < 0) ) {
@@ -539,19 +539,19 @@ private:
exit(1);
}
}
- else if (numFields == 1) {
- cerr << "Only one BED field detected: " << lineNum << ". Verify that your files are TAB-delimited. Exiting..." << endl;
- exit(1);
- }
- else if ((numFields != this->bedType) && (numFields != 0)) {
- cerr << "Differing number of BED fields encountered at line: " << lineNum << ". Exiting..." << endl;
- exit(1);
- }
- else if ((numFields < 3) && (numFields != 0)) {
- cerr << "TAB delimited BED file with at least 3 fields (chrom, start, end) is required at line: "<< lineNum << ". Exiting..." << endl;
- exit(1);
- }
- return false;
+ else if (numFields == 1) {
+ cerr << "Only one BED field detected: " << lineNum << ". Verify that your files are TAB-delimited. Exiting..." << endl;
+ exit(1);
+ }
+ else if ((numFields != this->bedType) && (numFields != 0)) {
+ cerr << "Differing number of BED fields encountered at line: " << lineNum << ". Exiting..." << endl;
+ exit(1);
+ }
+ else if ((numFields < 3) && (numFields != 0)) {
+ cerr << "TAB delimited BED file with at least 3 fields (chrom, start, end) is required at line: "<< lineNum << ". Exiting..." << endl;
+ exit(1);
+ }
+ return false;
}
@@ -560,48 +560,48 @@ private:
*/
template <typename T>
inline bool parseVcfLine (T &bed, const vector<string> &lineVector, int lineNum, unsigned int numFields) {
- if (numFields == this->bedType) {
- bed.chrom = lineVector[0];
- bed.start = atoi(lineVector[1].c_str()) - 1; // VCF is one-based
+ if (numFields == this->bedType) {
+ bed.chrom = lineVector[0];
+ bed.start = atoi(lineVector[1].c_str()) - 1; // VCF is one-based
bed.end = bed.start + lineVector[3].size(); // VCF 4.0 stores the size of the affected REF allele.
bed.strand = "+";
- // construct the name from the ref and alt alleles.
+ // construct the name from the ref and alt alleles.
// if it's an annotated variant, add the rsId as well.
bed.name = lineVector[3] + "/" + lineVector[4];
if (lineVector[2] != ".") {
bed.name += "_" + lineVector[2];
}
- if (this->bedType > 2) {
- for (unsigned int i = 2; i < numFields; ++i)
- bed.otherFields.push_back(lineVector[i]);
- }
+ if (this->bedType > 2) {
+ for (unsigned int i = 2; i < numFields; ++i)
+ bed.otherFields.push_back(lineVector[i]);
+ }
- if ((bed.start <= bed.end) && (bed.start > 0) && (bed.end > 0)) {
+ if ((bed.start <= bed.end) && (bed.start > 0) && (bed.end > 0)) {
return true;
- }
- else if (bed.start > bed.end) {
- cerr << "Error: malformed VCF entry at line " << lineNum << ". Start was greater than end. Exiting." << endl;
- exit(1);
- }
- else if ( (bed.start < 0) || (bed.end < 0) ) {
- cerr << "Error: malformed VCF entry at line " << lineNum << ". Coordinate detected that is < 0. Exiting." << endl;
- exit(1);
- }
- }
- else if (numFields == 1) {
- cerr << "Only one VCF field detected: " << lineNum << ". Verify that your files are TAB-delimited. Exiting..." << endl;
- exit(1);
- }
- else if ((numFields != this->bedType) && (numFields != 0)) {
- cerr << "Differing number of VCF fields encountered at line: " << lineNum << ". Exiting..." << endl;
- exit(1);
- }
- else if ((numFields < 2) && (numFields != 0)) {
- cerr << "TAB delimited VCF file with at least 2 fields (chrom, pos) is required at line: "<< lineNum << ". Exiting..." << endl;
+ }
+ else if (bed.start > bed.end) {
+ cerr << "Error: malformed VCF entry at line " << lineNum << ". Start was greater than end. Exiting." << endl;
+ exit(1);
+ }
+ else if ( (bed.start < 0) || (bed.end < 0) ) {
+ cerr << "Error: malformed VCF entry at line " << lineNum << ". Coordinate detected that is < 0. Exiting." << endl;
+ exit(1);
+ }
+ }
+ else if (numFields == 1) {
+ cerr << "Only one VCF field detected: " << lineNum << ". Verify that your files are TAB-delimited. Exiting..." << endl;
+ exit(1);
+ }
+ else if ((numFields != this->bedType) && (numFields != 0)) {
+ cerr << "Differing number of VCF fields encountered at line: " << lineNum << ". Exiting..." << endl;
exit(1);
- }
- return false;
+ }
+ else if ((numFields < 2) && (numFields != 0)) {
+ cerr << "TAB delimited VCF file with at least 2 fields (chrom, pos) is required at line: "<< lineNum << ". Exiting..." << endl;
+ exit(1);
+ }
+ return false;
}
@@ -611,348 +611,348 @@ private:
*/
template <typename T>
inline bool parseGffLine (T &bed, const vector<string> &lineVector, int lineNum, unsigned int numFields) {
- if (numFields == this->bedType) {
- if (this->bedType == 9 && _isGff) {
- bed.chrom = lineVector[0];
- // substract 1 to force the start to be BED-style
- bed.start = atoi(lineVector[3].c_str()) - 1;
- bed.end = atoi(lineVector[4].c_str());
- bed.name = lineVector[2];
- bed.score = lineVector[5];
- bed.strand = lineVector[6].c_str();
- bed.otherFields.push_back(lineVector[1]); // add GFF "source". unused in BED
- bed.otherFields.push_back(lineVector[7]); // add GFF "fname". unused in BED
- bed.otherFields.push_back(lineVector[8]); // add GFF "group". unused in BED
- }
- else {
- cerr << "Error: unexpected number of fields at line: " << lineNum <<
- ". Verify that your files are TAB-delimited and that your GFF file has 9 fields. Exiting..." << endl;
- exit(1);
- }
- if (bed.start > bed.end) {
- cerr << "Error: malformed GFF entry at line " << lineNum << ". Start was greater than end. Exiting." << endl;
- exit(1);
- }
- else if ( (bed.start < 0) || (bed.end < 0) ) {
- cerr << "Error: malformed GFF entry at line " << lineNum << ". Coordinate detected that is < 1. Exiting." << endl;
- exit(1);
- }
- else return true;
- }
- else if (numFields == 1) {
- cerr << "Only one GFF field detected: " << lineNum << ". Verify that your files are TAB-delimited. Exiting..." << endl;
- exit(1);
- }
- else if ((numFields != this->bedType) && (numFields != 0)) {
- cerr << "Differing number of GFF fields encountered at line: " << lineNum << ". Exiting..." << endl;
- exit(1);
- }
- else if ((numFields < 9) && (numFields != 0)) {
- cerr << "TAB delimited GFF file with 9 fields is required at line: "<< lineNum << ". Exiting..." << endl;
- exit(1);
- }
- return false;
+ if (numFields == this->bedType) {
+ if (this->bedType == 9 && _isGff) {
+ bed.chrom = lineVector[0];
+ // substract 1 to force the start to be BED-style
+ bed.start = atoi(lineVector[3].c_str()) - 1;
+ bed.end = atoi(lineVector[4].c_str());
+ bed.name = lineVector[2];
+ bed.score = lineVector[5];
+ bed.strand = lineVector[6].c_str();
+ bed.otherFields.push_back(lineVector[1]); // add GFF "source". unused in BED
+ bed.otherFields.push_back(lineVector[7]); // add GFF "fname". unused in BED
+ bed.otherFields.push_back(lineVector[8]); // add GFF "group". unused in BED
+ }
+ else {
+ cerr << "Error: unexpected number of fields at line: " << lineNum <<
+ ". Verify that your files are TAB-delimited and that your GFF file has 9 fields. Exiting..." << endl;
+ exit(1);
+ }
+ if (bed.start > bed.end) {
+ cerr << "Error: malformed GFF entry at line " << lineNum << ". Start was greater than end. Exiting." << endl;
+ exit(1);
+ }
+ else if ( (bed.start < 0) || (bed.end < 0) ) {
+ cerr << "Error: malformed GFF entry at line " << lineNum << ". Coordinate detected that is < 1. Exiting." << endl;
+ exit(1);
+ }
+ else return true;
+ }
+ else if (numFields == 1) {
+ cerr << "Only one GFF field detected: " << lineNum << ". Verify that your files are TAB-delimited. Exiting..." << endl;
+ exit(1);
+ }
+ else if ((numFields != this->bedType) && (numFields != 0)) {
+ cerr << "Differing number of GFF fields encountered at line: " << lineNum << ". Exiting..." << endl;
+ exit(1);
+ }
+ else if ((numFields < 9) && (numFields != 0)) {
+ cerr << "TAB delimited GFF file with 9 fields is required at line: "<< lineNum << ". Exiting..." << endl;
+ exit(1);
+ }
+ return false;
}
-
-
+
+
public:
-
+
/*
- reportBedTab
+ reportBedTab
- Writes the _original_ BED entry with a TAB
- at the end of the line.
- Works for BED3 - BED6.
+ Writes the _original_ BED entry with a TAB
+ at the end of the line.
+ Works for BED3 - BED6.
*/
template <typename T>
inline void reportBedTab(const T &bed) {
// BED
- if (_isGff == false && _isVcf == false) {
- if (this->bedType == 3) {
- printf ("%s\t%d\t%d\t", bed.chrom.c_str(), bed.start, bed.end);
- }
- else if (this->bedType == 4) {
- printf ("%s\t%d\t%d\t%s\t", bed.chrom.c_str(), bed.start, bed.end, bed.name.c_str());
- }
- else if (this->bedType == 5) {
- printf ("%s\t%d\t%d\t%s\t%s\t", bed.chrom.c_str(), bed.start, bed.end, bed.name.c_str(),
- bed.score.c_str());
- }
- else if (this->bedType == 6) {
- printf ("%s\t%d\t%d\t%s\t%s\t%s\t", bed.chrom.c_str(), bed.start, bed.end, bed.name.c_str(),
- bed.score.c_str(), bed.strand.c_str());
- }
- else if (this->bedType > 6) {
- printf ("%s\t%d\t%d\t%s\t%s\t%s\t", bed.chrom.c_str(), bed.start, bed.end, bed.name.c_str(),
- bed.score.c_str(), bed.strand.c_str());
-
- vector<string>::const_iterator othIt = bed.otherFields.begin();
- vector<string>::const_iterator othEnd = bed.otherFields.end();
- for ( ; othIt != othEnd; ++othIt) {
- printf("%s\t", othIt->c_str());
- }
- }
- }
- // VCF
- else if (_isGff == false && _isVcf == true) {
- printf ("%s\t%d\t", bed.chrom.c_str(), bed.start+1);
-
- vector<string>::const_iterator othIt = bed.otherFields.begin();
- vector<string>::const_iterator othEnd = bed.otherFields.end();
- for ( ; othIt != othEnd; ++othIt) {
- printf("%s\t", othIt->c_str());
- }
- }
- // GFF
- else if (this->bedType == 9) {
- printf ("%s\t%s\t%s\t%d\t%d\t%s\t%s\t%s\t%s\t", bed.chrom.c_str(), bed.otherFields[0].c_str(),
- bed.name.c_str(), bed.start+1, bed.end,
- bed.score.c_str(), bed.strand.c_str(),
- bed.otherFields[1].c_str(), bed.otherFields[2].c_str());
- }
+ if (_isGff == false && _isVcf == false) {
+ if (this->bedType == 3) {
+ printf ("%s\t%d\t%d\t", bed.chrom.c_str(), bed.start, bed.end);
+ }
+ else if (this->bedType == 4) {
+ printf ("%s\t%d\t%d\t%s\t", bed.chrom.c_str(), bed.start, bed.end, bed.name.c_str());
+ }
+ else if (this->bedType == 5) {
+ printf ("%s\t%d\t%d\t%s\t%s\t", bed.chrom.c_str(), bed.start, bed.end, bed.name.c_str(),
+ bed.score.c_str());
+ }
+ else if (this->bedType == 6) {
+ printf ("%s\t%d\t%d\t%s\t%s\t%s\t", bed.chrom.c_str(), bed.start, bed.end, bed.name.c_str(),
+ bed.score.c_str(), bed.strand.c_str());
+ }
+ else if (this->bedType > 6) {
+ printf ("%s\t%d\t%d\t%s\t%s\t%s\t", bed.chrom.c_str(), bed.start, bed.end, bed.name.c_str(),
+ bed.score.c_str(), bed.strand.c_str());
+
+ vector<string>::const_iterator othIt = bed.otherFields.begin();
+ vector<string>::const_iterator othEnd = bed.otherFields.end();
+ for ( ; othIt != othEnd; ++othIt) {
+ printf("%s\t", othIt->c_str());
+ }
+ }
+ }
+ // VCF
+ else if (_isGff == false && _isVcf == true) {
+ printf ("%s\t%d\t", bed.chrom.c_str(), bed.start+1);
+
+ vector<string>::const_iterator othIt = bed.otherFields.begin();
+ vector<string>::const_iterator othEnd = bed.otherFields.end();
+ for ( ; othIt != othEnd; ++othIt) {
+ printf("%s\t", othIt->c_str());
+ }
+ }
+ // GFF
+ else if (this->bedType == 9) {
+ printf ("%s\t%s\t%s\t%d\t%d\t%s\t%s\t%s\t%s\t", bed.chrom.c_str(), bed.otherFields[0].c_str(),
+ bed.name.c_str(), bed.start+1, bed.end,
+ bed.score.c_str(), bed.strand.c_str(),
+ bed.otherFields[1].c_str(), bed.otherFields[2].c_str());
+ }
}
/*
- reportBedNewLine
+ reportBedNewLine
- Writes the _original_ BED entry with a NEWLINE
- at the end of the line.
- Works for BED3 - BED6.
+ Writes the _original_ BED entry with a NEWLINE
+ at the end of the line.
+ Works for BED3 - BED6.
*/
template <typename T>
inline void reportBedNewLine(const T &bed) {
//BED
- if (_isGff == false && _isVcf == false) {
- if (this->bedType == 3) {
- printf ("%s\t%d\t%d\n", bed.chrom.c_str(), bed.start, bed.end);
- }
- else if (this->bedType == 4) {
- printf ("%s\t%d\t%d\t%s\n", bed.chrom.c_str(), bed.start, bed.end, bed.name.c_str());
- }
- else if (this->bedType == 5) {
- printf ("%s\t%d\t%d\t%s\t%s\n", bed.chrom.c_str(), bed.start, bed.end, bed.name.c_str(),
- bed.score.c_str());
- }
- else if (this->bedType == 6) {
- printf ("%s\t%d\t%d\t%s\t%s\t%s\n", bed.chrom.c_str(), bed.start, bed.end, bed.name.c_str(),
- bed.score.c_str(), bed.strand.c_str());
- }
- else if (this->bedType > 6) {
- printf ("%s\t%d\t%d\t%s\t%s\t%s", bed.chrom.c_str(), bed.start, bed.end, bed.name.c_str(),
- bed.score.c_str(), bed.strand.c_str());
-
- vector<string>::const_iterator othIt = bed.otherFields.begin();
- vector<string>::const_iterator othEnd = bed.otherFields.end();
- for ( ; othIt != othEnd; ++othIt) {
- printf("\t%s", othIt->c_str());
- }
- printf("\n");
- }
- }
- // VCF
- else if (_isGff == false && _isVcf == true) {
- printf ("%s\t%d\t", bed.chrom.c_str(), bed.start+1);
-
- vector<string>::const_iterator othIt = bed.otherFields.begin();
- vector<string>::const_iterator othEnd = bed.otherFields.end();
- for ( ; othIt != othEnd; ++othIt) {
- printf("%s\t", othIt->c_str());
- }
- printf("\n");
- }
- //GFF
- else if (this->bedType == 9) {
- printf ("%s\t%s\t%s\t%d\t%d\t%s\t%s\t%s\t%s\n", bed.chrom.c_str(), bed.otherFields[0].c_str(),
- bed.name.c_str(), bed.start+1, bed.end,
- bed.score.c_str(), bed.strand.c_str(),
- bed.otherFields[1].c_str(), bed.otherFields[2].c_str());
- }
+ if (_isGff == false && _isVcf == false) {
+ if (this->bedType == 3) {
+ printf ("%s\t%d\t%d\n", bed.chrom.c_str(), bed.start, bed.end);
+ }
+ else if (this->bedType == 4) {
+ printf ("%s\t%d\t%d\t%s\n", bed.chrom.c_str(), bed.start, bed.end, bed.name.c_str());
+ }
+ else if (this->bedType == 5) {
+ printf ("%s\t%d\t%d\t%s\t%s\n", bed.chrom.c_str(), bed.start, bed.end, bed.name.c_str(),
+ bed.score.c_str());
+ }
+ else if (this->bedType == 6) {
+ printf ("%s\t%d\t%d\t%s\t%s\t%s\n", bed.chrom.c_str(), bed.start, bed.end, bed.name.c_str(),
+ bed.score.c_str(), bed.strand.c_str());
+ }
+ else if (this->bedType > 6) {
+ printf ("%s\t%d\t%d\t%s\t%s\t%s", bed.chrom.c_str(), bed.start, bed.end, bed.name.c_str(),
+ bed.score.c_str(), bed.strand.c_str());
+
+ vector<string>::const_iterator othIt = bed.otherFields.begin();
+ vector<string>::const_iterator othEnd = bed.otherFields.end();
+ for ( ; othIt != othEnd; ++othIt) {
+ printf("\t%s", othIt->c_str());
+ }
+ printf("\n");
+ }
+ }
+ // VCF
+ else if (_isGff == false && _isVcf == true) {
+ printf ("%s\t%d\t", bed.chrom.c_str(), bed.start+1);
+
+ vector<string>::const_iterator othIt = bed.otherFields.begin();
+ vector<string>::const_iterator othEnd = bed.otherFields.end();
+ for ( ; othIt != othEnd; ++othIt) {
+ printf("%s\t", othIt->c_str());
+ }
+ printf("\n");
+ }
+ //GFF
+ else if (this->bedType == 9) {
+ printf ("%s\t%s\t%s\t%d\t%d\t%s\t%s\t%s\t%s\n", bed.chrom.c_str(), bed.otherFields[0].c_str(),
+ bed.name.c_str(), bed.start+1, bed.end,
+ bed.score.c_str(), bed.strand.c_str(),
+ bed.otherFields[1].c_str(), bed.otherFields[2].c_str());
+ }
}
/*
- reportBedRangeNewLine
+ reportBedRangeNewLine
- Writes a custom start->end for a BED entry
- with a NEWLINE at the end of the line.
+ Writes a custom start->end for a BED entry
+ with a NEWLINE at the end of the line.
- Works for BED3 - BED6.
+ Works for BED3 - BED6.
*/
template <typename T>
inline void reportBedRangeTab(const T &bed, CHRPOS start, CHRPOS end) {
// BED
- if (_isGff == false && _isVcf == false) {
- if (this->bedType == 3) {
- printf ("%s\t%d\t%d\t", bed.chrom.c_str(), start, end);
- }
- else if (this->bedType == 4) {
- printf ("%s\t%d\t%d\t%s\t", bed.chrom.c_str(), start, end, bed.name.c_str());
- }
- else if (this->bedType == 5) {
- printf ("%s\t%d\t%d\t%s\t%s\t", bed.chrom.c_str(), start, end, bed.name.c_str(),
- bed.score.c_str());
- }
- else if (this->bedType == 6) {
- printf ("%s\t%d\t%d\t%s\t%s\t%s\t", bed.chrom.c_str(), start, end, bed.name.c_str(),
- bed.score.c_str(), bed.strand.c_str());
- }
- else if (this->bedType > 6) {
- printf ("%s\t%d\t%d\t%s\t%s\t%s\t", bed.chrom.c_str(), start, end, bed.name.c_str(),
- bed.score.c_str(), bed.strand.c_str());
-
- vector<string>::const_iterator othIt = bed.otherFields.begin();
- vector<string>::const_iterator othEnd = bed.otherFields.end();
- for ( ; othIt != othEnd; ++othIt) {
- printf("%s\t", othIt->c_str());
- }
- }
- }
- // VCF
- else if (_isGff == false && _isVcf == true) {
- printf ("%s\t%d\t", bed.chrom.c_str(), bed.start+1);
-
- vector<string>::const_iterator othIt = bed.otherFields.begin();
- vector<string>::const_iterator othEnd = bed.otherFields.end();
- for ( ; othIt != othEnd; ++othIt) {
- printf("%s\t", othIt->c_str());
- }
- }
- // GFF
- else if (this->bedType == 9) {
- printf ("%s\t%s\t%s\t%d\t%d\t%s\t%s\t%s\t%s\t", bed.chrom.c_str(), bed.otherFields[0].c_str(),
- bed.name.c_str(), start+1, end,
- bed.score.c_str(), bed.strand.c_str(),
- bed.otherFields[1].c_str(), bed.otherFields[2].c_str());
- }
+ if (_isGff == false && _isVcf == false) {
+ if (this->bedType == 3) {
+ printf ("%s\t%d\t%d\t", bed.chrom.c_str(), start, end);
+ }
+ else if (this->bedType == 4) {
+ printf ("%s\t%d\t%d\t%s\t", bed.chrom.c_str(), start, end, bed.name.c_str());
+ }
+ else if (this->bedType == 5) {
+ printf ("%s\t%d\t%d\t%s\t%s\t", bed.chrom.c_str(), start, end, bed.name.c_str(),
+ bed.score.c_str());
+ }
+ else if (this->bedType == 6) {
+ printf ("%s\t%d\t%d\t%s\t%s\t%s\t", bed.chrom.c_str(), start, end, bed.name.c_str(),
+ bed.score.c_str(), bed.strand.c_str());
+ }
+ else if (this->bedType > 6) {
+ printf ("%s\t%d\t%d\t%s\t%s\t%s\t", bed.chrom.c_str(), start, end, bed.name.c_str(),
+ bed.score.c_str(), bed.strand.c_str());
+
+ vector<string>::const_iterator othIt = bed.otherFields.begin();
+ vector<string>::const_iterator othEnd = bed.otherFields.end();
+ for ( ; othIt != othEnd; ++othIt) {
+ printf("%s\t", othIt->c_str());
+ }
+ }
+ }
+ // VCF
+ else if (_isGff == false && _isVcf == true) {
+ printf ("%s\t%d\t", bed.chrom.c_str(), bed.start+1);
+
+ vector<string>::const_iterator othIt = bed.otherFields.begin();
+ vector<string>::const_iterator othEnd = bed.otherFields.end();
+ for ( ; othIt != othEnd; ++othIt) {
+ printf("%s\t", othIt->c_str());
+ }
+ }
+ // GFF
+ else if (this->bedType == 9) {
+ printf ("%s\t%s\t%s\t%d\t%d\t%s\t%s\t%s\t%s\t", bed.chrom.c_str(), bed.otherFields[0].c_str(),
+ bed.name.c_str(), start+1, end,
+ bed.score.c_str(), bed.strand.c_str(),
+ bed.otherFields[1].c_str(), bed.otherFields[2].c_str());
+ }
}
/*
- reportBedRangeTab
+ reportBedRangeTab
- Writes a custom start->end for a BED entry
- with a TAB at the end of the line.
+ Writes a custom start->end for a BED entry
+ with a TAB at the end of the line.
- Works for BED3 - BED6.
+ Works for BED3 - BED6.
*/
template <typename T>
inline void reportBedRangeNewLine(const T &bed, CHRPOS start, CHRPOS end) {
// BED
- if (_isGff == false && _isVcf == false) {
- if (this->bedType == 3) {
- printf ("%s\t%d\t%d\n", bed.chrom.c_str(), start, end);
- }
- else if (this->bedType == 4) {
- printf ("%s\t%d\t%d\t%s\n", bed.chrom.c_str(), start, end, bed.name.c_str());
- }
- else if (this->bedType == 5) {
- printf ("%s\t%d\t%d\t%s\t%s\n", bed.chrom.c_str(), start, end, bed.name.c_str(),
- bed.score.c_str());
- }
- else if (this->bedType == 6) {
- printf ("%s\t%d\t%d\t%s\t%s\t%s\n", bed.chrom.c_str(), start, end, bed.name.c_str(),
- bed.score.c_str(), bed.strand.c_str());
- }
- else if (this->bedType > 6) {
- printf ("%s\t%d\t%d\t%s\t%s\t%s", bed.chrom.c_str(), start, end, bed.name.c_str(),
- bed.score.c_str(), bed.strand.c_str());
-
- vector<string>::const_iterator othIt = bed.otherFields.begin();
- vector<string>::const_iterator othEnd = bed.otherFields.end();
- for ( ; othIt != othEnd; ++othIt) {
- printf("\t%s", othIt->c_str());
- }
- printf("\n");
- }
- }
- // VCF
- else if (_isGff == false && _isVcf == true) {
- printf ("%s\t%d\t", bed.chrom.c_str(), bed.start+1);
-
- vector<string>::const_iterator othIt = bed.otherFields.begin();
- vector<string>::const_iterator othEnd = bed.otherFields.end();
- for ( ; othIt != othEnd; ++othIt) {
- printf("%s\t", othIt->c_str());
- }
+ if (_isGff == false && _isVcf == false) {
+ if (this->bedType == 3) {
+ printf ("%s\t%d\t%d\n", bed.chrom.c_str(), start, end);
+ }
+ else if (this->bedType == 4) {
+ printf ("%s\t%d\t%d\t%s\n", bed.chrom.c_str(), start, end, bed.name.c_str());
+ }
+ else if (this->bedType == 5) {
+ printf ("%s\t%d\t%d\t%s\t%s\n", bed.chrom.c_str(), start, end, bed.name.c_str(),
+ bed.score.c_str());
+ }
+ else if (this->bedType == 6) {
+ printf ("%s\t%d\t%d\t%s\t%s\t%s\n", bed.chrom.c_str(), start, end, bed.name.c_str(),
+ bed.score.c_str(), bed.strand.c_str());
+ }
+ else if (this->bedType > 6) {
+ printf ("%s\t%d\t%d\t%s\t%s\t%s", bed.chrom.c_str(), start, end, bed.name.c_str(),
+ bed.score.c_str(), bed.strand.c_str());
+
+ vector<string>::const_iterator othIt = bed.otherFields.begin();
+ vector<string>::const_iterator othEnd = bed.otherFields.end();
+ for ( ; othIt != othEnd; ++othIt) {
+ printf("\t%s", othIt->c_str());
+ }
+ printf("\n");
+ }
+ }
+ // VCF
+ else if (_isGff == false && _isVcf == true) {
+ printf ("%s\t%d\t", bed.chrom.c_str(), bed.start+1);
+
+ vector<string>::const_iterator othIt = bed.otherFields.begin();
+ vector<string>::const_iterator othEnd = bed.otherFields.end();
+ for ( ; othIt != othEnd; ++othIt) {
+ printf("%s\t", othIt->c_str());
+ }
printf("\n");
- }
- // GFF
- else if (this->bedType == 9) { // add 1 to the start for GFF
- printf ("%s\t%s\t%s\t%d\t%d\t%s\t%s\t%s\t%s\n", bed.chrom.c_str(), bed.otherFields[0].c_str(),
- bed.name.c_str(), start+1, end,
- bed.score.c_str(), bed.strand.c_str(),
- bed.otherFields[1].c_str(), bed.otherFields[2].c_str());
- }
+ }
+ // GFF
+ else if (this->bedType == 9) { // add 1 to the start for GFF
+ printf ("%s\t%s\t%s\t%d\t%d\t%s\t%s\t%s\t%s\n", bed.chrom.c_str(), bed.otherFields[0].c_str(),
+ bed.name.c_str(), start+1, end,
+ bed.score.c_str(), bed.strand.c_str(),
+ bed.otherFields[1].c_str(), bed.otherFields[2].c_str());
+ }
}
/*
- reportNullBedTab
+ reportNullBedTab
*/
void reportNullBedTab() {
- if (_isGff == false) {
- if (this->bedType == 3) {
- printf (".\t-1\t-1\t");
- }
- else if (this->bedType == 4) {
- printf (".\t-1\t-1\t.\t");
- }
- else if (this->bedType == 5) {
- printf (".\t-1\t-1\t.\t-1\t");
- }
- else if (this->bedType == 6) {
- printf (".\t-1\t-1\t.\t-1\t.\t");
- }
- else if (this->bedType > 6) {
- printf (".\t-1\t-1\t.\t-1\t.\t");
- for (unsigned int i = 6; i < this->bedType; ++i) {
- printf(".\t");
- }
- }
- }
- else if (this->bedType == 9) {
- printf (".\t.\t.\t-1\t-1\t-1\t.\t.\t.\t");
- }
+ if (_isGff == false) {
+ if (this->bedType == 3) {
+ printf (".\t-1\t-1\t");
+ }
+ else if (this->bedType == 4) {
+ printf (".\t-1\t-1\t.\t");
+ }
+ else if (this->bedType == 5) {
+ printf (".\t-1\t-1\t.\t-1\t");
+ }
+ else if (this->bedType == 6) {
+ printf (".\t-1\t-1\t.\t-1\t.\t");
+ }
+ else if (this->bedType > 6) {
+ printf (".\t-1\t-1\t.\t-1\t.\t");
+ for (unsigned int i = 6; i < this->bedType; ++i) {
+ printf(".\t");
+ }
+ }
+ }
+ else if (this->bedType == 9) {
+ printf (".\t.\t.\t-1\t-1\t-1\t.\t.\t.\t");
+ }
}
/*
- reportNullBedTab
+ reportNullBedTab
*/
void reportNullBedNewLine() {
- if (_isGff == false) {
- if (this->bedType == 3) {
- printf (".\t-1\t-1\n");
- }
- else if (this->bedType == 4) {
- printf (".\t-1\t-1\t.\n");
- }
- else if (this->bedType == 5) {
- printf (".\t-1\t-1\t.\t-1\n");
- }
- else if (this->bedType == 6) {
- printf (".\t-1\t-1\t.\t-1\t.\n");
- }
- else if (this->bedType > 6) {
- printf (".\t-1\t-1\t.\t-1\t.");
- for (unsigned int i = 6; i < this->bedType; ++i) {
- printf("\t.");
- }
- printf("\n");
- }
- }
- else if (this->bedType == 9) {
- printf (".\t.\t.\t-1\t-1\t-1\t.\t.\t.\n");
- }
+ if (_isGff == false) {
+ if (this->bedType == 3) {
+ printf (".\t-1\t-1\n");
+ }
+ else if (this->bedType == 4) {
+ printf (".\t-1\t-1\t.\n");
+ }
+ else if (this->bedType == 5) {
+ printf (".\t-1\t-1\t.\t-1\n");
+ }
+ else if (this->bedType == 6) {
+ printf (".\t-1\t-1\t.\t-1\t.\n");
+ }
+ else if (this->bedType > 6) {
+ printf (".\t-1\t-1\t.\t-1\t.");
+ for (unsigned int i = 6; i < this->bedType; ++i) {
+ printf("\t.");
+ }
+ printf("\n");
+ }
+ }
+ else if (this->bedType == 9) {
+ printf (".\t.\t.\t-1\t-1\t-1\t.\t.\t.\n");
+ }
}
-
+
};
#endif /* BEDFILE_H */
diff --git a/src/utils/bedFilePE/bedFilePE.cpp b/src/utils/bedFilePE/bedFilePE.cpp
index 98d3a200c9bf865086f199393765f420be3fca70..f9cd5d2220aad0e9f208aaa582461ad985895e67 100644
--- a/src/utils/bedFilePE/bedFilePE.cpp
+++ b/src/utils/bedFilePE/bedFilePE.cpp
@@ -1,7 +1,7 @@
-//
+//
// bedFilePE.cpp
// BEDTools
-//
+//
// Created by Aaron Quinlan Spring 2009.
// Copyright 2009 Aaron Quinlan. All rights reserved.
//
@@ -9,7 +9,7 @@
//
// Acknowledgments: Much of the code herein is taken from Jim Kent's
// BED processing code. I am grateful for his elegant
-// genome binning algorithm and therefore use it extensively.
+// genome binning algorithm and therefore use it extensively.
#include "bedFilePE.h"
@@ -17,7 +17,7 @@
// Constructor
BedFilePE::BedFilePE(string &bedFile) {
- this->bedFile = bedFile;
+ this->bedFile = bedFile;
}
// Destructor
@@ -25,512 +25,528 @@ BedFilePE::~BedFilePE(void) {
}
void BedFilePE::Open(void) {
- if (bedFile == "stdin") {
- _bedStream = &cin;
- }
- else {
- size_t foundPos;
- foundPos = bedFile.find_last_of(".gz");
- // is this a GZIPPED BED file?
- if (foundPos == bedFile.size() - 1) {
- igzstream beds(bedFile.c_str(), ios::in);
- if ( !beds ) {
- cerr << "Error: The requested bedpe file (" << bedFile << ") could not be opened. Exiting!" << endl;
- exit (1);
- }
- else {
- // if so, close it (this was just a test)
- beds.close();
- // now set a pointer to the stream so that we
- // can read the file later on.
- // Thank God for Josuttis, p. 631!
- _bedStream = new igzstream(bedFile.c_str(), ios::in);
- }
- }
- // not GZIPPED.
- else {
-
- ifstream beds(bedFile.c_str(), ios::in);
- // can we open the file?
- if ( !beds ) {
- cerr << "Error: The requested bed file (" << bedFile << ") could not be opened. Exiting!" << endl;
- exit (1);
- }
- else {
- // if so, close it (this was just a test)
- beds.close();
- // now set a pointer to the stream so that we
- // can read the file later on.
- // Thank God for Josuttis, p. 631!
- _bedStream = new ifstream(bedFile.c_str(), ios::in);
- }
- }
- }
+ if (bedFile == "stdin") {
+ _bedStream = &cin;
+ }
+ else {
+ size_t foundPos;
+ foundPos = bedFile.find_last_of(".gz");
+ // is this a GZIPPED BED file?
+ if (foundPos == bedFile.size() - 1) {
+ igzstream beds(bedFile.c_str(), ios::in);
+ if ( !beds ) {
+ cerr << "Error: The requested bedpe file (" << bedFile << ") could not be opened. Exiting!" << endl;
+ exit (1);
+ }
+ else {
+ // if so, close it (this was just a test)
+ beds.close();
+ // now set a pointer to the stream so that we
+ // can read the file later on.
+ // Thank God for Josuttis, p. 631!
+ _bedStream = new igzstream(bedFile.c_str(), ios::in);
+ }
+ }
+ // not GZIPPED.
+ else {
+
+ ifstream beds(bedFile.c_str(), ios::in);
+ // can we open the file?
+ if ( !beds ) {
+ cerr << "Error: The requested bed file (" << bedFile << ") could not be opened. Exiting!" << endl;
+ exit (1);
+ }
+ else {
+ // if so, close it (this was just a test)
+ beds.close();
+ // now set a pointer to the stream so that we
+ // can read the file later on.
+ // Thank God for Josuttis, p. 631!
+ _bedStream = new ifstream(bedFile.c_str(), ios::in);
+ }
+ }
+ }
}
// Close the BEDPE file
void BedFilePE::Close(void) {
- if (bedFile != "stdin") delete _bedStream;
+ if (bedFile != "stdin") delete _bedStream;
}
BedLineStatus BedFilePE::GetNextBedPE (BEDPE &bedpe, int &lineNum) {
- // make sure there are still lines to process.
- // if so, tokenize, validate and return the BEDPE entry.
- if (_bedStream->good()) {
- string bedPELine;
- vector<string> bedPEFields;
- bedPEFields.reserve(10);
-
- // parse the bedStream pointer
- getline(*_bedStream, bedPELine);
- lineNum++;
-
- // split into a string vector.
- Tokenize(bedPELine,bedPEFields);
-
- // load the BEDPE struct as long as it's a valid BEDPE entry.
- return parseLine(bedpe, bedPEFields, lineNum);
- }
- // default if file is closed or EOF
- return BED_INVALID;
+ // make sure there are still lines to process.
+ // if so, tokenize, validate and return the BEDPE entry.
+ if (_bedStream->good()) {
+ string bedPELine;
+ vector<string> bedPEFields;
+ bedPEFields.reserve(10);
+
+ // parse the bedStream pointer
+ getline(*_bedStream, bedPELine);
+ lineNum++;
+
+ // split into a string vector.
+ Tokenize(bedPELine,bedPEFields);
+
+ // load the BEDPE struct as long as it's a valid BEDPE entry.
+ return parseLine(bedpe, bedPEFields, lineNum);
+ }
+ // default if file is closed or EOF
+ return BED_INVALID;
}
/*
- reportBedPETab
-
- Writes the _original_ BED entry for A.
- Works for BEDPE only.
+ reportBedPETab
+
+ Writes the _original_ BED entry for A.
+ Works for BEDPE only.
*/
void BedFilePE::reportBedPETab(const BEDPE &a) {
- if (this->bedType == 6) {
- printf("%s\t%d\t%d\t%s\t%d\t%d\t", a.chrom1.c_str(), a.start1, a.end1,
- a.chrom2.c_str(), a.start2, a.end2);
- }
- else if (this->bedType == 7) {
- printf("%s\t%d\t%d\t%s\t%d\t%d\t%s\t", a.chrom1.c_str(), a.start1, a.end1,
- a.chrom2.c_str(), a.start2, a.end2,
- a.name.c_str());
- }
- else if (this->bedType == 8) {
- printf("%s\t%d\t%d\t%s\t%d\t%d\t%s\t%s\t", a.chrom1.c_str(), a.start1, a.end1,
- a.chrom2.c_str(), a.start2, a.end2,
- a.name.c_str(), a.score.c_str());
- }
- else if (this->bedType == 10) {
- printf("%s\t%d\t%d\t%s\t%d\t%d\t%s\t%s\t%s\t%s\t", a.chrom1.c_str(), a.start1, a.end1,
- a.chrom2.c_str(), a.start2, a.end2,
- a.name.c_str(), a.score.c_str(), a.strand1.c_str(), a.strand2.c_str());
- }
- else if (this->bedType > 10) {
- printf("%s\t%d\t%d\t%s\t%d\t%d\t%s\t%s\t%s\t%s", a.chrom1.c_str(), a.start1, a.end1,
- a.chrom2.c_str(), a.start2, a.end2,
- a.name.c_str(), a.score.c_str(), a.strand1.c_str(), a.strand2.c_str());
-
- vector<string>::const_iterator othIt = a.otherFields.begin();
- vector<string>::const_iterator othEnd = a.otherFields.end();
- for ( ; othIt != othEnd; ++othIt) {
- printf("\t%s", othIt->c_str());
- }
- printf("\t");
- }
+ if (this->bedType == 6) {
+ printf("%s\t%d\t%d\t%s\t%d\t%d\t", a.chrom1.c_str(), a.start1, a.end1,
+ a.chrom2.c_str(), a.start2, a.end2);
+ }
+ else if (this->bedType == 7) {
+ printf("%s\t%d\t%d\t%s\t%d\t%d\t%s\t", a.chrom1.c_str(), a.start1, a.end1,
+ a.chrom2.c_str(), a.start2, a.end2,
+ a.name.c_str());
+ }
+ else if (this->bedType == 8) {
+ printf("%s\t%d\t%d\t%s\t%d\t%d\t%s\t%s\t", a.chrom1.c_str(), a.start1, a.end1,
+ a.chrom2.c_str(), a.start2, a.end2,
+ a.name.c_str(), a.score.c_str());
+ }
+ else if (this->bedType == 10) {
+ printf("%s\t%d\t%d\t%s\t%d\t%d\t%s\t%s\t%s\t%s\t", a.chrom1.c_str(), a.start1, a.end1,
+ a.chrom2.c_str(), a.start2, a.end2,
+ a.name.c_str(), a.score.c_str(), a.strand1.c_str(), a.strand2.c_str());
+ }
+ else if (this->bedType > 10) {
+ printf("%s\t%d\t%d\t%s\t%d\t%d\t%s\t%s\t%s\t%s", a.chrom1.c_str(), a.start1, a.end1,
+ a.chrom2.c_str(), a.start2, a.end2,
+ a.name.c_str(), a.score.c_str(), a.strand1.c_str(), a.strand2.c_str());
+
+ vector<string>::const_iterator othIt = a.otherFields.begin();
+ vector<string>::const_iterator othEnd = a.otherFields.end();
+ for ( ; othIt != othEnd; ++othIt) {
+ printf("\t%s", othIt->c_str());
+ }
+ printf("\t");
+ }
}
/*
- reportBedPENewLine
-
- Writes the _original_ BED entry for A.
- Works for BEDPE only.
+ reportBedPENewLine
+
+ Writes the _original_ BED entry for A.
+ Works for BEDPE only.
*/
void BedFilePE::reportBedPENewLine(const BEDPE &a) {
- if (this->bedType == 6) {
- printf("%s\t%d\t%d\t%s\t%d\t%d\n", a.chrom1.c_str(), a.start1, a.end1,
- a.chrom2.c_str(), a.start2, a.end2);
- }
- else if (this->bedType == 7) {
- printf("%s\t%d\t%d\t%s\t%d\t%d\t%s\n", a.chrom1.c_str(), a.start1, a.end1,
- a.chrom2.c_str(), a.start2, a.end2,
- a.name.c_str());
- }
- else if (this->bedType == 8) {
- printf("%s\t%d\t%d\t%s\t%d\t%d\t%s\t%s\n", a.chrom1.c_str(), a.start1, a.end1,
- a.chrom2.c_str(), a.start2, a.end2,
- a.name.c_str(), a.score.c_str());
- }
- else if (this->bedType == 10) {
- printf("%s\t%d\t%d\t%s\t%d\t%d\t%s\t%s\t%s\t%s\n", a.chrom1.c_str(), a.start1, a.end1,
- a.chrom2.c_str(), a.start2, a.end2,
- a.name.c_str(), a.score.c_str(), a.strand1.c_str(), a.strand2.c_str());
- }
- else if (this->bedType > 10) {
- printf("%s\t%d\t%d\t%s\t%d\t%d\t%s\t%s\t%s\t%s", a.chrom1.c_str(), a.start1, a.end1,
- a.chrom2.c_str(), a.start2, a.end2,
- a.name.c_str(), a.score.c_str(), a.strand1.c_str(), a.strand2.c_str());
-
- vector<string>::const_iterator othIt = a.otherFields.begin();
- vector<string>::const_iterator othEnd = a.otherFields.end();
- for ( ; othIt != othEnd; ++othIt) {
- printf("\t%s", othIt->c_str());
- }
- printf("\n");
- }
+ if (this->bedType == 6) {
+ printf("%s\t%d\t%d\t%s\t%d\t%d\n", a.chrom1.c_str(), a.start1, a.end1,
+ a.chrom2.c_str(), a.start2, a.end2);
+ }
+ else if (this->bedType == 7) {
+ printf("%s\t%d\t%d\t%s\t%d\t%d\t%s\n", a.chrom1.c_str(), a.start1, a.end1,
+ a.chrom2.c_str(), a.start2, a.end2,
+ a.name.c_str());
+ }
+ else if (this->bedType == 8) {
+ printf("%s\t%d\t%d\t%s\t%d\t%d\t%s\t%s\n", a.chrom1.c_str(), a.start1, a.end1,
+ a.chrom2.c_str(), a.start2, a.end2,
+ a.name.c_str(), a.score.c_str());
+ }
+ else if (this->bedType == 10) {
+ printf("%s\t%d\t%d\t%s\t%d\t%d\t%s\t%s\t%s\t%s\n", a.chrom1.c_str(), a.start1, a.end1,
+ a.chrom2.c_str(), a.start2, a.end2,
+ a.name.c_str(), a.score.c_str(), a.strand1.c_str(), a.strand2.c_str());
+ }
+ else if (this->bedType > 10) {
+ printf("%s\t%d\t%d\t%s\t%d\t%d\t%s\t%s\t%s\t%s", a.chrom1.c_str(), a.start1, a.end1,
+ a.chrom2.c_str(), a.start2, a.end2,
+ a.name.c_str(), a.score.c_str(), a.strand1.c_str(), a.strand2.c_str());
+
+ vector<string>::const_iterator othIt = a.otherFields.begin();
+ vector<string>::const_iterator othEnd = a.otherFields.end();
+ for ( ; othIt != othEnd; ++othIt) {
+ printf("\t%s", othIt->c_str());
+ }
+ printf("\n");
+ }
}
BedLineStatus BedFilePE::parseLine (BEDPE &bedpe, const vector<string> &lineVector, int &lineNum) {
- // bail out if we have a blank line
- if (lineVector.empty())
- return BED_BLANK;
-
- if ((lineVector[0].find("track") == string::npos) && (lineVector[0].find("browser") == string::npos) && (lineVector[0].find("#") == string::npos) ) {
- // we need at least 6 columns
- if (lineVector.size() >= 6) {
- if (parseBedPELine(bedpe, lineVector, lineNum) == true)
- return BED_VALID;
- else return BED_INVALID;
- }
- else {
- cerr << "It looks as though you have less than 6 columns. Are you sure your files are tab-delimited?" << endl;
- exit(1);
- }
- }
- else {
- lineNum--;
- return BED_HEADER;
- }
-
- // default
- return BED_INVALID;
+ // bail out if we have a blank line
+ if (lineVector.empty())
+ return BED_BLANK;
+
+ if ((lineVector[0].find("track") == string::npos) && (lineVector[0].find("browser") == string::npos) && (lineVector[0].find("#") == string::npos) ) {
+ // we need at least 6 columns
+ if (lineVector.size() >= 6) {
+ if (parseBedPELine(bedpe, lineVector, lineNum) == true)
+ return BED_VALID;
+ else return BED_INVALID;
+ }
+ else {
+ cerr << "It looks as though you have less than 6 columns. Are you sure your files are tab-delimited?" << endl;
+ exit(1);
+ }
+ }
+ else {
+ lineNum--;
+ return BED_HEADER;
+ }
+
+ // default
+ return BED_INVALID;
}
bool BedFilePE::parseBedPELine (BEDPE &bed, const vector<string> &lineVector, const int &lineNum) {
- if ((lineNum == 1) && (lineVector.size() >= 6)) {
-
- this->bedType = lineVector.size();
-
- if (this->bedType == 6) {
- bed.chrom1 = lineVector[0];
- bed.start1 = atoi(lineVector[1].c_str());
- bed.end1 = atoi(lineVector[2].c_str());
-
- bed.chrom2 = lineVector[3];
- bed.start2 = atoi(lineVector[4].c_str());
- bed.end2 = atoi(lineVector[5].c_str());
-
- return true;
- }
- else if (this->bedType == 7) {
- bed.chrom1 = lineVector[0];
- bed.start1 = atoi(lineVector[1].c_str());
- bed.end1 = atoi(lineVector[2].c_str());
-
- bed.chrom2 = lineVector[3];
- bed.start2 = atoi(lineVector[4].c_str());
- bed.end2 = atoi(lineVector[5].c_str());
-
- bed.name = lineVector[6];
- return true;
- }
- else if (this->bedType == 8) {
- bed.chrom1 = lineVector[0];
- bed.start1 = atoi(lineVector[1].c_str());
- bed.end1 = atoi(lineVector[2].c_str());
-
- bed.chrom2 = lineVector[3];
- bed.start2 = atoi(lineVector[4].c_str());
- bed.end2 = atoi(lineVector[5].c_str());
-
- bed.name = lineVector[6];
- bed.score = lineVector[7].c_str();
- return true;
- }
- else if (this->bedType == 10) {
- bed.chrom1 = lineVector[0];
- bed.start1 = atoi(lineVector[1].c_str());
- bed.end1 = atoi(lineVector[2].c_str());
-
- bed.chrom2 = lineVector[3];
- bed.start2 = atoi(lineVector[4].c_str());
- bed.end2 = atoi(lineVector[5].c_str());
-
- bed.name = lineVector[6];
- bed.score = lineVector[7].c_str();
-
- bed.strand1 = lineVector[8];
- bed.strand2 = lineVector[9];
-
- return true;
- }
- else if (this->bedType > 10) {
- bed.chrom1 = lineVector[0];
- bed.start1 = atoi(lineVector[1].c_str());
- bed.end1 = atoi(lineVector[2].c_str());
-
- bed.chrom2 = lineVector[3];
- bed.start2 = atoi(lineVector[4].c_str());
- bed.end2 = atoi(lineVector[5].c_str());
-
- bed.name = lineVector[6];
- bed.score = lineVector[7].c_str();
-
- bed.strand1 = lineVector[8];
- bed.strand2 = lineVector[9];
-
- for (unsigned int i = 10; i < lineVector.size(); ++i) {
- bed.otherFields.push_back(lineVector[i]);
- }
- return true;
- }
- else {
- cerr << "Unexpected number of fields: " << lineNum << ". Verify that your files are TAB-delimited and that your BEDPE file has 6,7,8 or 10 fields. Exiting..." << endl;
- exit(1);
- }
-
- if (bed.start1 > bed.end1) {
- cerr << "Error: malformed BEDPE entry at line " << lineNum << ". Start1 was greater than End1. Ignoring it and moving on." << endl;
- return false;
- }
- else if (bed.start2 > bed.end2) {
- cerr << "Error: malformed BEDPE entry at line " << lineNum << ". Start2 was greater than End2. Ignoring it and moving on." << endl;
- return false;
- }
- else if ( (bed.start1 < 0) || (bed.end1 < 0) || (bed.start2 < 0) || (bed.end2 < 0) ) {
- cerr << "Error: malformed BEDPE entry at line " << lineNum << ". Coordinate <= 0. Ignoring it and moving on." << endl;
- return false;
- }
- }
- else if ( (lineNum > 1) && (lineVector.size() == this->bedType)) {
-
- if (this->bedType == 6) {
- bed.chrom1 = lineVector[0];
- bed.start1 = atoi(lineVector[1].c_str());
- bed.end1 = atoi(lineVector[2].c_str());
-
- bed.chrom2 = lineVector[3];
- bed.start2 = atoi(lineVector[4].c_str());
- bed.end2 = atoi(lineVector[5].c_str());
-
- return true;
- }
- else if (this->bedType == 7) {
- bed.chrom1 = lineVector[0];
- bed.start1 = atoi(lineVector[1].c_str());
- bed.end1 = atoi(lineVector[2].c_str());
-
- bed.chrom2 = lineVector[3];
- bed.start2 = atoi(lineVector[4].c_str());
- bed.end2 = atoi(lineVector[5].c_str());
-
- bed.name = lineVector[6];
- return true;
- }
- else if (this->bedType == 8) {
- bed.chrom1 = lineVector[0];
- bed.start1 = atoi(lineVector[1].c_str());
- bed.end1 = atoi(lineVector[2].c_str());
-
- bed.chrom2 = lineVector[3];
- bed.start2 = atoi(lineVector[4].c_str());
- bed.end2 = atoi(lineVector[5].c_str());
-
- bed.name = lineVector[6];
- bed.score = lineVector[7].c_str();
- return true;
- }
- else if (this->bedType == 10) {
- bed.chrom1 = lineVector[0];
- bed.start1 = atoi(lineVector[1].c_str());
- bed.end1 = atoi(lineVector[2].c_str());
-
- bed.chrom2 = lineVector[3];
- bed.start2 = atoi(lineVector[4].c_str());
- bed.end2 = atoi(lineVector[5].c_str());
-
- bed.name = lineVector[6];
- bed.score = lineVector[7].c_str();
-
- bed.strand1 = lineVector[8];
- bed.strand2 = lineVector[9];
-
- return true;
- }
- else if (this->bedType > 10) {
- bed.chrom1 = lineVector[0];
- bed.start1 = atoi(lineVector[1].c_str());
- bed.end1 = atoi(lineVector[2].c_str());
-
- bed.chrom2 = lineVector[3];
- bed.start2 = atoi(lineVector[4].c_str());
- bed.end2 = atoi(lineVector[5].c_str());
-
- bed.name = lineVector[6];
- bed.score = lineVector[7].c_str();
-
- bed.strand1 = lineVector[8];
- bed.strand2 = lineVector[9];
-
- for (unsigned int i = 10; i < lineVector.size(); ++i) {
- bed.otherFields.push_back(lineVector[i]);
- }
- return true;
- }
- else {
- cerr << "Unexpected number of fields: " << lineNum << ". Verify that your files are TAB-delimited and that your BEDPE file has 6,7,8 or 10 fields. Exiting..." << endl;
- exit(1);
- }
-
- if (bed.start1 > bed.end1) {
- cerr << "Error: malformed BED entry at line " << lineNum << ". Start1 was greater than End1. Ignoring it and moving on." << endl;
- return false;
- }
- else if (bed.start2 > bed.end2) {
- cerr << "Error: malformed BED entry at line " << lineNum << ". Start2 was greater than End2. Ignoring it and moving on." << endl;
- return false;
- }
- else if ( (bed.start1 < 0) || (bed.end1 < 0) || (bed.start2 < 0) || (bed.end2 < 0) ) {
- cerr << "Error: malformed BED entry at line " << lineNum << ". Coordinate <= 0. Ignoring it and moving on." << endl;
- return false;
- }
- }
- else if (lineVector.size() == 1) {
- cerr << "Only one BED field detected: " << lineNum << ". Verify that your files are TAB-delimited. Exiting..." << endl;
- exit(1);
- }
- else if ((lineVector.size() != this->bedType) && (lineVector.size() != 0)) {
- cerr << "Differing number of BEDPE fields encountered at line: " << lineNum << ". Exiting..." << endl;
- exit(1);
- }
- else if ((lineVector.size() < 6) && (lineVector.size() != 0)) {
- cerr << "TAB delimited BEDPE file with at least 6 fields (chrom1, start1, end1, chrom2, start2, end2) is required at line: "<< lineNum << ". Exiting..." << endl;
- exit(1);
- }
- return false;
+ if ((lineNum == 1) && (lineVector.size() >= 6)) {
+
+ this->bedType = lineVector.size();
+
+ if (this->bedType == 6) {
+ bed.chrom1 = lineVector[0];
+ bed.start1 = atoi(lineVector[1].c_str());
+ bed.end1 = atoi(lineVector[2].c_str());
+
+ bed.chrom2 = lineVector[3];
+ bed.start2 = atoi(lineVector[4].c_str());
+ bed.end2 = atoi(lineVector[5].c_str());
+
+ return true;
+ }
+ else if (this->bedType == 7) {
+ bed.chrom1 = lineVector[0];
+ bed.start1 = atoi(lineVector[1].c_str());
+ bed.end1 = atoi(lineVector[2].c_str());
+
+ bed.chrom2 = lineVector[3];
+ bed.start2 = atoi(lineVector[4].c_str());
+ bed.end2 = atoi(lineVector[5].c_str());
+
+ bed.name = lineVector[6];
+ return true;
+ }
+ else if (this->bedType == 8) {
+ bed.chrom1 = lineVector[0];
+ bed.start1 = atoi(lineVector[1].c_str());
+ bed.end1 = atoi(lineVector[2].c_str());
+
+ bed.chrom2 = lineVector[3];
+ bed.start2 = atoi(lineVector[4].c_str());
+ bed.end2 = atoi(lineVector[5].c_str());
+
+ bed.name = lineVector[6];
+ bed.score = lineVector[7].c_str();
+ return true;
+ }
+ else if (this->bedType == 10) {
+ bed.chrom1 = lineVector[0];
+ bed.start1 = atoi(lineVector[1].c_str());
+ bed.end1 = atoi(lineVector[2].c_str());
+
+ bed.chrom2 = lineVector[3];
+ bed.start2 = atoi(lineVector[4].c_str());
+ bed.end2 = atoi(lineVector[5].c_str());
+
+ bed.name = lineVector[6];
+ bed.score = lineVector[7].c_str();
+
+ bed.strand1 = lineVector[8];
+ bed.strand2 = lineVector[9];
+
+ return true;
+ }
+ else if (this->bedType > 10) {
+ bed.chrom1 = lineVector[0];
+ bed.start1 = atoi(lineVector[1].c_str());
+ bed.end1 = atoi(lineVector[2].c_str());
+
+ bed.chrom2 = lineVector[3];
+ bed.start2 = atoi(lineVector[4].c_str());
+ bed.end2 = atoi(lineVector[5].c_str());
+
+ bed.name = lineVector[6];
+ bed.score = lineVector[7].c_str();
+
+ bed.strand1 = lineVector[8];
+ bed.strand2 = lineVector[9];
+
+ for (unsigned int i = 10; i < lineVector.size(); ++i) {
+ bed.otherFields.push_back(lineVector[i]);
+ }
+ return true;
+ }
+ else {
+ cerr << "Unexpected number of fields: " << lineNum << ". Verify that your files are TAB-delimited and that your BEDPE file has 6,7,8 or 10 fields. Exiting..." << endl;
+ exit(1);
+ }
+
+ if (bed.start1 > bed.end1) {
+ cerr << "Error: malformed BEDPE entry at line " << lineNum << ". Start1 was greater than End1. Ignoring it and moving on." << endl;
+ return false;
+ }
+ else if (bed.start2 > bed.end2) {
+ cerr << "Error: malformed BEDPE entry at line " << lineNum << ". Start2 was greater than End2. Ignoring it and moving on." << endl;
+ return false;
+ }
+ else if ( (bed.start1 < 0) || (bed.end1 < 0) || (bed.start2 < 0) || (bed.end2 < 0) ) {
+ cerr << "Error: malformed BEDPE entry at line " << lineNum << ". Coordinate <= 0. Ignoring it and moving on." << endl;
+ return false;
+ }
+ }
+ else if ( (lineNum > 1) && (lineVector.size() == this->bedType)) {
+
+ if (this->bedType == 6) {
+ bed.chrom1 = lineVector[0];
+ bed.start1 = atoi(lineVector[1].c_str());
+ bed.end1 = atoi(lineVector[2].c_str());
+
+ bed.chrom2 = lineVector[3];
+ bed.start2 = atoi(lineVector[4].c_str());
+ bed.end2 = atoi(lineVector[5].c_str());
+
+ return true;
+ }
+ else if (this->bedType == 7) {
+ bed.chrom1 = lineVector[0];
+ bed.start1 = atoi(lineVector[1].c_str());
+ bed.end1 = atoi(lineVector[2].c_str());
+
+ bed.chrom2 = lineVector[3];
+ bed.start2 = atoi(lineVector[4].c_str());
+ bed.end2 = atoi(lineVector[5].c_str());
+
+ bed.name = lineVector[6];
+ return true;
+ }
+ else if (this->bedType == 8) {
+ bed.chrom1 = lineVector[0];
+ bed.start1 = atoi(lineVector[1].c_str());
+ bed.end1 = atoi(lineVector[2].c_str());
+
+ bed.chrom2 = lineVector[3];
+ bed.start2 = atoi(lineVector[4].c_str());
+ bed.end2 = atoi(lineVector[5].c_str());
+
+ bed.name = lineVector[6];
+ bed.score = lineVector[7].c_str();
+ return true;
+ }
+ else if (this->bedType == 10) {
+ bed.chrom1 = lineVector[0];
+ bed.start1 = atoi(lineVector[1].c_str());
+ bed.end1 = atoi(lineVector[2].c_str());
+
+ bed.chrom2 = lineVector[3];
+ bed.start2 = atoi(lineVector[4].c_str());
+ bed.end2 = atoi(lineVector[5].c_str());
+
+ bed.name = lineVector[6];
+ bed.score = lineVector[7].c_str();
+
+ bed.strand1 = lineVector[8];
+ bed.strand2 = lineVector[9];
+
+ return true;
+ }
+ else if (this->bedType > 10) {
+ bed.chrom1 = lineVector[0];
+ bed.start1 = atoi(lineVector[1].c_str());
+ bed.end1 = atoi(lineVector[2].c_str());
+
+ bed.chrom2 = lineVector[3];
+ bed.start2 = atoi(lineVector[4].c_str());
+ bed.end2 = atoi(lineVector[5].c_str());
+
+ bed.name = lineVector[6];
+ bed.score = lineVector[7].c_str();
+
+ bed.strand1 = lineVector[8];
+ bed.strand2 = lineVector[9];
+
+ for (unsigned int i = 10; i < lineVector.size(); ++i) {
+ bed.otherFields.push_back(lineVector[i]);
+ }
+ return true;
+ }
+ else {
+ cerr << "Unexpected number of fields: " << lineNum << ". Verify that your files are TAB-delimited and that your BEDPE file has 6,7,8 or 10 fields. Exiting..." << endl;
+ exit(1);
+ }
+
+ if (bed.start1 > bed.end1) {
+ cerr << "Error: malformed BED entry at line " << lineNum << ". Start1 was greater than End1. Ignoring it and moving on." << endl;
+ return false;
+ }
+ else if (bed.start2 > bed.end2) {
+ cerr << "Error: malformed BED entry at line " << lineNum << ". Start2 was greater than End2. Ignoring it and moving on." << endl;
+ return false;
+ }
+ else if ( (bed.start1 < 0) || (bed.end1 < 0) || (bed.start2 < 0) || (bed.end2 < 0) ) {
+ cerr << "Error: malformed BED entry at line " << lineNum << ". Coordinate <= 0. Ignoring it and moving on." << endl;
+ return false;
+ }
+ }
+ else if (lineVector.size() == 1) {
+ cerr << "Only one BED field detected: " << lineNum << ". Verify that your files are TAB-delimited. Exiting..." << endl;
+ exit(1);
+ }
+ else if ((lineVector.size() != this->bedType) && (lineVector.size() != 0)) {
+ cerr << "Differing number of BEDPE fields encountered at line: " << lineNum << ". Exiting..." << endl;
+ exit(1);
+ }
+ else if ((lineVector.size() < 6) && (lineVector.size() != 0)) {
+ cerr << "TAB delimited BEDPE file with at least 6 fields (chrom1, start1, end1, chrom2, start2, end2) is required at line: "<< lineNum << ". Exiting..." << endl;
+ exit(1);
+ }
+ return false;
}
/*
- Adapted from kent source "binKeeperFind"
+ Adapted from kent source "binKeeperFind"
*/
-void BedFilePE::FindOverlapsPerBin(int bEnd, string chrom, CHRPOS start, CHRPOS end, string strand, vector<MATE> &hits, bool forceStrand) {
-
- int startBin, endBin;
- startBin = (start >> _binFirstShift);
- endBin = ((end-1) >> _binFirstShift);
-
- // loop through each bin "level" in the binning hierarchy
- for (int i = 0; i < _binLevels; ++i) {
-
- // loop through each bin at this level of the hierarchy
- int offset = _binOffsetsExtended[i];
- for (int j = (startBin+offset); j <= (endBin+offset); ++j) {
-
- // loop through each feature in this chrom/bin and see if it overlaps
- // with the feature that was passed in. if so, add the feature to
- // the list of hits.
- vector<MATE>::const_iterator bedItr;
- vector<MATE>::const_iterator bedEnd;
- if (bEnd == 1) {
- bedItr = bedMapEnd1[chrom][j].begin();
- bedEnd = bedMapEnd1[chrom][j].end();
- }
- else if (bEnd == 2) {
- bedItr = bedMapEnd2[chrom][j].begin();
- bedEnd = bedMapEnd2[chrom][j].end();
- }
- else {
- cerr << "Unexpected end of B requested" << endl;
- }
- for (; bedItr != bedEnd; ++bedItr) {
-
- // skip the hit if not on the same strand (and we care)
- if (forceStrand && (strand != bedItr->bed.strand)) {
- continue;
- }
- else if (overlaps(bedItr->bed.start, bedItr->bed.end, start, end) > 0) {
- hits.push_back(*bedItr); // it's a hit, add it.
- }
-
- }
- }
- startBin >>= _binNextShift;
- endBin >>= _binNextShift;
- }
+void BedFilePE::FindOverlapsPerBin(int bEnd, string chrom, CHRPOS start, CHRPOS end, string name, string strand,
+ vector<MATE> &hits, float overlapFraction, bool forceStrand, bool enforceDiffNames) {
+
+ int startBin, endBin;
+ startBin = (start >> _binFirstShift);
+ endBin = ((end-1) >> _binFirstShift);
+
+ // loop through each bin "level" in the binning hierarchy
+ for (int i = 0; i < _binLevels; ++i) {
+
+ // loop through each bin at this level of the hierarchy
+ int offset = _binOffsetsExtended[i];
+ for (int j = (startBin+offset); j <= (endBin+offset); ++j) {
+
+ // loop through each feature in this chrom/bin and see if it overlaps
+ // with the feature that was passed in. if so, add the feature to
+ // the list of hits.
+ vector<MATE>::const_iterator bedItr;
+ vector<MATE>::const_iterator bedEnd;
+ if (bEnd == 1) {
+ bedItr = bedMapEnd1[chrom][j].begin();
+ bedEnd = bedMapEnd1[chrom][j].end();
+ }
+ else if (bEnd == 2) {
+ bedItr = bedMapEnd2[chrom][j].begin();
+ bedEnd = bedMapEnd2[chrom][j].end();
+ }
+ else {
+ cerr << "Unexpected end of B requested" << endl;
+ }
+ for (; bedItr != bedEnd; ++bedItr) {
+ float overlap = overlaps(bedItr->bed.start, bedItr->bed.end, start, end);
+ float size = end - start;
+
+ if ( (overlap / size) >= overlapFraction ) {
+
+ // skip the hit if not on the same strand (and we care)
+ if ((forceStrand == false) && (enforceDiffNames == false)) {
+ hits.push_back(*bedItr); // it's a hit, add it.
+ }
+ else if ((forceStrand == true) && (enforceDiffNames == false)) {
+ if (strand == bedItr->bed.strand)
+ hits.push_back(*bedItr); // it's a hit, add it.
+ }
+ else if ((forceStrand == true) && (enforceDiffNames == true)) {
+ if ((strand == bedItr->bed.strand) && (name != bedItr->bed.name))
+ hits.push_back(*bedItr); // it's a hit, add it.
+ }
+ else if ((forceStrand == false) && (enforceDiffNames == true)) {
+ if (name != bedItr->bed.name)
+ hits.push_back(*bedItr); // it's a hit, add it.
+ }
+ }
+
+ }
+ }
+ startBin >>= _binNextShift;
+ endBin >>= _binNextShift;
+ }
}
void BedFilePE::loadBedPEFileIntoMap() {
- int lineNum = 0;
- int bin1, bin2;
- BedLineStatus bedStatus;
- BEDPE bedpeEntry, nullBedPE;
+ int lineNum = 0;
+ int bin1, bin2;
+ BedLineStatus bedStatus;
+ BEDPE bedpeEntry, nullBedPE;
- Open();
- bedStatus = this->GetNextBedPE(bedpeEntry, lineNum);
- while (bedStatus != BED_INVALID) {
-
- if (bedStatus == BED_VALID) {
+ Open();
+ bedStatus = this->GetNextBedPE(bedpeEntry, lineNum);
+ while (bedStatus != BED_INVALID) {
+
+ if (bedStatus == BED_VALID) {
MATE *bedEntry1 = new MATE();
MATE *bedEntry2 = new MATE();
- // separate the BEDPE entry into separate
- // BED entries
- splitBedPEIntoBeds(bedpeEntry, lineNum, bedEntry1, bedEntry2);
-
- // load end1 into a UCSC bin map
- bin1 = getBin(bedEntry1->bed.start, bedEntry1->bed.end);
- this->bedMapEnd1[bedEntry1->bed.chrom][bin1].push_back(*bedEntry1);
-
- // load end2 into a UCSC bin map
- bin2 = getBin(bedEntry2->bed.start, bedEntry2->bed.end);
- this->bedMapEnd2[bedEntry2->bed.chrom][bin2].push_back(*bedEntry2);
-
- bedpeEntry = nullBedPE;
- }
- bedStatus = this->GetNextBedPE(bedpeEntry, lineNum);
- }
- Close();
+ // separate the BEDPE entry into separate
+ // BED entries
+ splitBedPEIntoBeds(bedpeEntry, lineNum, bedEntry1, bedEntry2);
+
+ // load end1 into a UCSC bin map
+ bin1 = getBin(bedEntry1->bed.start, bedEntry1->bed.end);
+ this->bedMapEnd1[bedEntry1->bed.chrom][bin1].push_back(*bedEntry1);
+
+ // load end2 into a UCSC bin map
+ bin2 = getBin(bedEntry2->bed.start, bedEntry2->bed.end);
+ this->bedMapEnd2[bedEntry2->bed.chrom][bin2].push_back(*bedEntry2);
+
+ bedpeEntry = nullBedPE;
+ }
+ bedStatus = this->GetNextBedPE(bedpeEntry, lineNum);
+ }
+ Close();
}
void BedFilePE::splitBedPEIntoBeds(const BEDPE &bedpeEntry, const int &lineNum, MATE *bedEntry1, MATE *bedEntry2) {
-
- /*
- Split the BEDPE entry into separate BED entries
-
- NOTE: I am using a trick here where I store
- the lineNum of the BEDPE from the original file
- in the "count" column. This allows me to later
- resolve whether the hits found on both ends of BEDPE A
- came from the same entry in BEDPE B. Tracking by "name"
- alone with fail when there are multiple mappings for a given
- read-pair.
- */
-
- bedEntry1->bed.chrom = bedpeEntry.chrom1;
- bedEntry1->bed.start = bedpeEntry.start1;
- bedEntry1->bed.end = bedpeEntry.end1;
- bedEntry1->bed.name = bedpeEntry.name; // only store the name in end1 to save memory
- bedEntry1->bed.score = bedpeEntry.score; // only store the score in end1 to save memory
- bedEntry1->bed.strand = bedpeEntry.strand1;
- bedEntry1->bed.otherFields = bedpeEntry.otherFields; // only store the otherFields in end1 to save memory
- bedEntry1->lineNum = lineNum;
+
+ /*
+ Split the BEDPE entry into separate BED entries
+
+ NOTE: I am using a trick here where I store
+ the lineNum of the BEDPE from the original file
+ in the "count" column. This allows me to later
+ resolve whether the hits found on both ends of BEDPE A
+ came from the same entry in BEDPE B. Tracking by "name"
+ alone with fail when there are multiple mappings for a given
+ read-pair.
+ */
+
+ bedEntry1->bed.chrom = bedpeEntry.chrom1;
+ bedEntry1->bed.start = bedpeEntry.start1;
+ bedEntry1->bed.end = bedpeEntry.end1;
+ bedEntry1->bed.name = bedpeEntry.name;
+ bedEntry1->bed.score = bedpeEntry.score; // only store the score in end1 to save memory
+ bedEntry1->bed.strand = bedpeEntry.strand1;
+ bedEntry1->bed.otherFields = bedpeEntry.otherFields; // only store the otherFields in end1 to save memory
+ bedEntry1->lineNum = lineNum;
bedEntry1->mate = bedEntry2; // keep a pointer to end2
-
- bedEntry2->bed.chrom = bedpeEntry.chrom2;
- bedEntry2->bed.start = bedpeEntry.start2;
- bedEntry2->bed.end = bedpeEntry.end2;
- bedEntry2->bed.strand = bedpeEntry.strand2;
- bedEntry2->lineNum = lineNum;
+
+ bedEntry2->bed.chrom = bedpeEntry.chrom2;
+ bedEntry2->bed.start = bedpeEntry.start2;
+ bedEntry2->bed.end = bedpeEntry.end2;
+ bedEntry2->bed.name = bedpeEntry.name;
+ bedEntry2->bed.strand = bedpeEntry.strand2;
+ bedEntry2->lineNum = lineNum;
bedEntry2->mate = bedEntry1; // keep a pointer to end1
}
diff --git a/src/utils/bedFilePE/bedFilePE.h b/src/utils/bedFilePE/bedFilePE.h
index e6e43ed06b7fe719f31545d6b269c79790e436cd..00dedbefcdc6ea6f51a0ddd2f20add356fd4f0c5 100644
--- a/src/utils/bedFilePE/bedFilePE.h
+++ b/src/utils/bedFilePE/bedFilePE.h
@@ -16,26 +16,26 @@ using namespace std;
/*
- Structure for paired-end records
+ Structure for paired-end records
*/
struct BEDPE {
- // UCSC BED fields
- string chrom1;
- CHRPOS start1;
- CHRPOS end1;
-
- string chrom2;
- CHRPOS start2;
- CHRPOS end2;
-
- string name;
- string score;
-
- string strand1;
- string strand2;
-
- vector<string> otherFields;
+ // UCSC BED fields
+ string chrom1;
+ CHRPOS start1;
+ CHRPOS end1;
+
+ string chrom2;
+ CHRPOS start2;
+ CHRPOS end2;
+
+ string name;
+ string score;
+
+ string strand1;
+ string strand2;
+
+ vector<string> otherFields;
};
@@ -48,46 +48,46 @@ class BedFilePE {
public:
- // Constructor
- BedFilePE(string &);
-
- // Destructor
- ~BedFilePE(void);
-
- // Open a BEDPE file for reading (creates an istream pointer)
- void Open(void);
-
- // Close an opened BEDPE file.
- void Close(void);
-
- // Get the next BED entry in an opened BED file.
- BedLineStatus GetNextBedPE (BEDPE &bedpe, int &lineNum);
-
-
- // Methods
-
- void reportBedPETab(const BEDPE &a);
- void reportBedPENewLine(const BEDPE &a);
- void loadBedPEFileIntoMap();
- void splitBedPEIntoBeds(const BEDPE &a, const int &lineNum, MATE *bedEntry1, MATE *bedEntry2);
-
-
- void FindOverlapsPerBin(int bEnd, string chrom, CHRPOS start, CHRPOS end, string strand,
- vector<MATE> &hits, bool forceStrand);
-
-
- string bedFile;
- unsigned int bedType;
-
- masterMateMap bedMapEnd1;
- masterMateMap bedMapEnd2;
-
+ // Constructor
+ BedFilePE(string &);
+
+ // Destructor
+ ~BedFilePE(void);
+
+ // Open a BEDPE file for reading (creates an istream pointer)
+ void Open(void);
+
+ // Close an opened BEDPE file.
+ void Close(void);
+
+ // Get the next BED entry in an opened BED file.
+ BedLineStatus GetNextBedPE (BEDPE &bedpe, int &lineNum);
+
+
+ // Methods
+
+ void reportBedPETab(const BEDPE &a);
+ void reportBedPENewLine(const BEDPE &a);
+ void loadBedPEFileIntoMap();
+ void splitBedPEIntoBeds(const BEDPE &a, const int &lineNum, MATE *bedEntry1, MATE *bedEntry2);
+
+
+ void FindOverlapsPerBin(int bEnd, string chrom, CHRPOS start, CHRPOS end, string name, string strand,
+ vector<MATE> &hits, float overlapFraction, bool forceStrand, bool enforceDiffNames);
+
+
+ string bedFile;
+ unsigned int bedType;
+
+ masterMateMap bedMapEnd1;
+ masterMateMap bedMapEnd2;
+
private:
- istream *_bedStream;
-
- // methods
- BedLineStatus parseLine (BEDPE &bedpe, const vector<string> &lineVector, int &lineNum);
- bool parseBedPELine (BEDPE &bed, const vector<string> &lineVector, const int &lineNum);
+ istream *_bedStream;
+
+ // methods
+ BedLineStatus parseLine (BEDPE &bedpe, const vector<string> &lineVector, int &lineNum);
+ bool parseBedPELine (BEDPE &bed, const vector<string> &lineVector, const int &lineNum);
};
#endif /* BEDFILEPE_H */
diff --git a/src/utils/bedGraphFile/bedGraphFile.cpp b/src/utils/bedGraphFile/bedGraphFile.cpp
index 3ad8aa4abf99cfa627d005b86ea6cedc06a8cbd2..44b87bf9f635b8e64e0b9ef05f4170b082078ae4 100644
--- a/src/utils/bedGraphFile/bedGraphFile.cpp
+++ b/src/utils/bedGraphFile/bedGraphFile.cpp
@@ -14,26 +14,26 @@
// Constructor
BedGraphFile::BedGraphFile(string &_file) :
- bedGraphFile(_file),
- _bedGraphStream(NULL)
+ bedGraphFile(_file),
+ _bedGraphStream(NULL)
{}
// Destructor
BedGraphFile::~BedGraphFile() {
- Close();
+ Close();
}
// Open the BEDGRAPH file
void BedGraphFile::Open() {
- if (bedGraphFile == "stdin") {
- _bedGraphStream = &cin;
- return;
- }
- // unzipped, regular
+ if (bedGraphFile == "stdin") {
+ _bedGraphStream = &cin;
+ return;
+ }
+ // unzipped, regular
else if ((isGzipFile(bedGraphFile) == false) && (isRegularFile(bedGraphFile) == true)) {
- _bedGraphStream = new ifstream(bedGraphFile.c_str(), ios::in);
+ _bedGraphStream = new ifstream(bedGraphFile.c_str(), ios::in);
// open an ifstream
ifstream bedg(bedGraphFile.c_str(), ios::in);
@@ -45,24 +45,24 @@ void BedGraphFile::Open() {
}
else {
// if so, close it (this was just a test)
- bedg.close();
+ bedg.close();
// now set a pointer to the stream so that we
_bedGraphStream = new ifstream(bedGraphFile.c_str(), ios::in);
}
}
- else if ((isGzipFile(bedGraphFile) == true) && (isRegularFile(bedGraphFile) == true)) {
-
+ else if ((isGzipFile(bedGraphFile) == true) && (isRegularFile(bedGraphFile) == true)) {
+
igzstream bedg(bedGraphFile.c_str(), ios::in);
- if ( !bedg ) {
- cerr << "Error: The requested bedgraph file (" << bedGraphFile << ") could not be opened. Exiting!" << endl;
- exit (1);
- }
- else {
- // if so, close it (this was just a test)
- bedg.close();
- // now set a pointer to the stream so that we
- _bedGraphStream = new igzstream(bedGraphFile.c_str(), ios::in);
- }
+ if ( !bedg ) {
+ cerr << "Error: The requested bedgraph file (" << bedGraphFile << ") could not be opened. Exiting!" << endl;
+ exit (1);
+ }
+ else {
+ // if so, close it (this was just a test)
+ bedg.close();
+ // now set a pointer to the stream so that we
+ _bedGraphStream = new igzstream(bedGraphFile.c_str(), ios::in);
+ }
}
else {
cerr << "Error: Unexpected file type (" << bedGraphFile << "). Exiting!" << endl;
@@ -73,11 +73,11 @@ void BedGraphFile::Open() {
// Close the BEDGRAPH file
void BedGraphFile::Close() {
- if (bedGraphFile != "stdin") {
- if (_bedGraphStream) {
- delete _bedGraphStream;
- _bedGraphStream = NULL ;
- }
- }
+ if (bedGraphFile != "stdin") {
+ if (_bedGraphStream) {
+ delete _bedGraphStream;
+ _bedGraphStream = NULL ;
+ }
+ }
}
diff --git a/src/utils/bedGraphFile/bedGraphFile.h b/src/utils/bedGraphFile/bedGraphFile.h
index f37db126f51b75683596902c8c1266e9c88a18a4..41e860de562c015e7dfd1bd27a211dd3b1d09c74 100644
--- a/src/utils/bedGraphFile/bedGraphFile.h
+++ b/src/utils/bedGraphFile/bedGraphFile.h
@@ -48,29 +48,29 @@ template <typename T>
class BEDGRAPH
{
public:
- std::string chrom;
- CHRPOS start;
- CHRPOS end;
- T depth;
+ std::string chrom;
+ CHRPOS start;
+ CHRPOS end;
+ T depth;
public:
- typedef T DEPTH_TYPE;
- // constructors
-
- // Null
- BEDGRAPH() :
- start(0),
- end(0),
- depth(T())
- {}
-
- // BEDGraph
- BEDGRAPH(string _chrom, CHRPOS _start, CHRPOS _end, T _depth) :
- chrom(_chrom),
- start(_start),
- end(_end),
- depth(_depth)
- {}
+ typedef T DEPTH_TYPE;
+ // constructors
+
+ // Null
+ BEDGRAPH() :
+ start(0),
+ end(0),
+ depth(T())
+ {}
+
+ // BEDGraph
+ BEDGRAPH(string _chrom, CHRPOS _start, CHRPOS _end, T _depth) :
+ chrom(_chrom),
+ start(_start),
+ end(_end),
+ depth(_depth)
+ {}
}; // BEDGraph
typedef BEDGRAPH<int32_t> BEDGRAPH_INT;
@@ -80,11 +80,11 @@ typedef BEDGRAPH<double> BEDGRAPH_FLOAT;
template <typename T>
std::ostream& operator<< (std::ostream& strm, const BEDGRAPH<T>& bg)
{
- strm << bg.chrom << "\t"
- << bg.start << "\t"
- << bg.end << "\t"
- << bg.depth;
- return strm;
+ strm << bg.chrom << "\t"
+ << bg.start << "\t"
+ << bg.end << "\t"
+ << bg.depth;
+ return strm;
}
// enum to flag the state of a given line in a BEDGraph file.
@@ -104,96 +104,96 @@ class BedGraphFile {
public:
- // Constructor
- BedGraphFile(string &);
-
- // Destructor
- ~BedGraphFile(void);
-
- // Open a BEDGraph file for reading (creates an istream pointer)
- void Open(void);
-
- // Close an opened BED file.
- void Close(void);
-
- // Get the next BED entry in an opened BED file.
- template <typename T>
- BedGraphLineStatus GetNextBedGraph (BEDGRAPH<T> &bedgraph, int &lineNum)
- {
- // make sure there are still lines to process.
- // if so, tokenize, validate and return the BED entry.
- if (_bedGraphStream->good()) {
- string bedGraphLine;
- vector<string> bedGraphFields;
-
- // parse the bedStream pointer
- getline(*_bedGraphStream, bedGraphLine);
- if (_bedGraphStream->eof())
- return BEDGRAPH_INVALID;
- if (_bedGraphStream->bad()) {
- cerr << "Error while reading file '" << bedGraphFile << "' : "
- << strerror(errno) << endl;
- exit(1);
- }
- lineNum++;
-
- // split into a string vector.
- Tokenize(bedGraphLine,bedGraphFields);
-
- // load the BED struct as long as it's a valid BED entry.
- return parseLine(bedgraph, bedGraphFields, lineNum);
- }
-
- // default if file is closed or EOF
- return BEDGRAPH_INVALID;
- }
-
- // the bedfile with which this instance is associated
- string bedGraphFile;
+ // Constructor
+ BedGraphFile(string &);
+
+ // Destructor
+ ~BedGraphFile(void);
+
+ // Open a BEDGraph file for reading (creates an istream pointer)
+ void Open(void);
+
+ // Close an opened BED file.
+ void Close(void);
+
+ // Get the next BED entry in an opened BED file.
+ template <typename T>
+ BedGraphLineStatus GetNextBedGraph (BEDGRAPH<T> &bedgraph, int &lineNum)
+ {
+ // make sure there are still lines to process.
+ // if so, tokenize, validate and return the BED entry.
+ if (_bedGraphStream->good()) {
+ string bedGraphLine;
+ vector<string> bedGraphFields;
+
+ // parse the bedStream pointer
+ getline(*_bedGraphStream, bedGraphLine);
+ if (_bedGraphStream->eof())
+ return BEDGRAPH_INVALID;
+ if (_bedGraphStream->bad()) {
+ cerr << "Error while reading file '" << bedGraphFile << "' : "
+ << strerror(errno) << endl;
+ exit(1);
+ }
+ lineNum++;
+
+ // split into a string vector.
+ Tokenize(bedGraphLine,bedGraphFields);
+
+ // load the BED struct as long as it's a valid BED entry.
+ return parseLine(bedgraph, bedGraphFields, lineNum);
+ }
+
+ // default if file is closed or EOF
+ return BEDGRAPH_INVALID;
+ }
+
+ // the bedfile with which this instance is associated
+ string bedGraphFile;
private:
- // data
- istream *_bedGraphStream;
-
- template <typename T>
- BedGraphLineStatus parseLine (BEDGRAPH<T> &bg, const vector<string> &lineVector, int &lineNum)
- {
- if (lineVector.size() == 0)
- return BEDGRAPH_BLANK;
-
- if (lineVector[0].find("track") != string::npos ||
- lineVector[0].find("browser") != string::npos ||
- lineVector[0].find("#") != string::npos)
- return BEDGRAPH_HEADER;
-
- if (lineVector.size() != 4)
- return BEDGRAPH_INVALID;
-
- bg.chrom = lineVector[0];
-
- stringstream str_start(lineVector[1]);
- if (! (str_start >> bg.start) ) {
- cerr << "Input error, failed to extract start value from '" << lineVector[1]
- << "' (column 2) in " << bedGraphFile << " line " << lineNum << endl;
- exit(1);
- }
-
- stringstream str_end(lineVector[2]);
- if (! (str_end >> bg.end) ) {
- cerr << "Input error, failed to extract end value from '" << lineVector[2]
- << "' (column 3) in " << bedGraphFile << " line " << lineNum << endl;
- exit(1);
- }
-
- stringstream str_depth(lineVector[3]);
- if (! (str_depth >> bg.depth) ) {
- cerr << "Input error, failed to extract depth value from '" << lineVector[3]
- << "' (column 4) in " << bedGraphFile << " line " << lineNum << endl;
- exit(1);
- }
-
- return BEDGRAPH_VALID;
- }
+ // data
+ istream *_bedGraphStream;
+
+ template <typename T>
+ BedGraphLineStatus parseLine (BEDGRAPH<T> &bg, const vector<string> &lineVector, int &lineNum)
+ {
+ if (lineVector.size() == 0)
+ return BEDGRAPH_BLANK;
+
+ if (lineVector[0].find("track") != string::npos ||
+ lineVector[0].find("browser") != string::npos ||
+ lineVector[0].find("#") != string::npos)
+ return BEDGRAPH_HEADER;
+
+ if (lineVector.size() != 4)
+ return BEDGRAPH_INVALID;
+
+ bg.chrom = lineVector[0];
+
+ stringstream str_start(lineVector[1]);
+ if (! (str_start >> bg.start) ) {
+ cerr << "Input error, failed to extract start value from '" << lineVector[1]
+ << "' (column 2) in " << bedGraphFile << " line " << lineNum << endl;
+ exit(1);
+ }
+
+ stringstream str_end(lineVector[2]);
+ if (! (str_end >> bg.end) ) {
+ cerr << "Input error, failed to extract end value from '" << lineVector[2]
+ << "' (column 3) in " << bedGraphFile << " line " << lineNum << endl;
+ exit(1);
+ }
+
+ stringstream str_depth(lineVector[3]);
+ if (! (str_depth >> bg.depth) ) {
+ cerr << "Input error, failed to extract depth value from '" << lineVector[3]
+ << "' (column 4) in " << bedGraphFile << " line " << lineNum << endl;
+ exit(1);
+ }
+
+ return BEDGRAPH_VALID;
+ }
};
#endif /* BEDFILE_H */
diff --git a/src/utils/curl/Makefile.am b/src/utils/curl/Makefile.am
deleted file mode 100644
index a3b4443865af9ea14812ee0dfe3dc85d34c34f77..0000000000000000000000000000000000000000
--- a/src/utils/curl/Makefile.am
+++ /dev/null
@@ -1,25 +0,0 @@
-pkginclude_HEADERS = \
- curl.h curlver.h easy.h mprintf.h stdcheaders.h types.h multi.h \
- typecheck-gcc.h curlbuild.h curlrules.h
-
-pkgincludedir= $(includedir)/curl
-
-# curlbuild.h does not exist in the git tree. When the original libcurl
-# source code distribution archive file is created, curlbuild.h.dist is
-# renamed to curlbuild.h and included in the tarball so that it can be
-# used directly on non-configure systems.
-#
-# The distributed curlbuild.h will be overwritten on configure systems
-# when the configure script runs, with one that is suitable and specific
-# to the library being configured and built.
-#
-# curlbuild.h.in is the distributed template file from which the configure
-# script creates curlbuild.h at library configuration time, overwiting the
-# one included in the distribution archive.
-#
-# curlbuild.h.dist is not included in the source code distribution archive.
-
-EXTRA_DIST = curlbuild.h.in
-
-DISTCLEANFILES = curlbuild.h
-
diff --git a/src/utils/curl/Makefile.in b/src/utils/curl/Makefile.in
deleted file mode 100644
index 58eb07b969168c8cc123e2b696837fce24808eea..0000000000000000000000000000000000000000
--- a/src/utils/curl/Makefile.in
+++ /dev/null
@@ -1,511 +0,0 @@
-# Makefile.in generated by automake 1.9.6 from Makefile.am.
-# @configure_input@
-
-# Copyright (C) 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002,
-# 2003, 2004, 2005 Free Software Foundation, Inc.
-# This Makefile.in is free software; the Free Software Foundation
-# gives unlimited permission to copy and/or distribute it,
-# with or without modifications, as long as this notice is preserved.
-
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY, to the extent permitted by law; without
-# even the implied warranty of MERCHANTABILITY or FITNESS FOR A
-# PARTICULAR PURPOSE.
-
-@SET_MAKE@
-
-srcdir = @srcdir@
-top_srcdir = @top_srcdir@
-VPATH = @srcdir@
-pkgdatadir = $(datadir)/@PACKAGE@
-pkglibdir = $(libdir)/@PACKAGE@
-top_builddir = ../..
-am__cd = CDPATH="$${ZSH_VERSION+.}$(PATH_SEPARATOR)" && cd
-INSTALL = @INSTALL@
-install_sh_DATA = $(install_sh) -c -m 644
-install_sh_PROGRAM = $(install_sh) -c
-install_sh_SCRIPT = $(install_sh) -c
-INSTALL_HEADER = $(INSTALL_DATA)
-transform = $(program_transform_name)
-NORMAL_INSTALL = :
-PRE_INSTALL = :
-POST_INSTALL = :
-NORMAL_UNINSTALL = :
-PRE_UNINSTALL = :
-POST_UNINSTALL = :
-build_triplet = @build@
-host_triplet = @host@
-subdir = include/curl
-DIST_COMMON = $(pkginclude_HEADERS) $(srcdir)/Makefile.am \
- $(srcdir)/Makefile.in $(srcdir)/curlbuild.h.in
-ACLOCAL_M4 = $(top_srcdir)/aclocal.m4
-am__aclocal_m4_deps = $(top_srcdir)/m4/curl-compilers.m4 \
- $(top_srcdir)/m4/curl-confopts.m4 \
- $(top_srcdir)/m4/curl-functions.m4 \
- $(top_srcdir)/m4/curl-override.m4 \
- $(top_srcdir)/m4/curl-reentrant.m4 \
- $(top_srcdir)/m4/curl-system.m4 $(top_srcdir)/m4/libtool.m4 \
- $(top_srcdir)/m4/ltoptions.m4 $(top_srcdir)/m4/ltsugar.m4 \
- $(top_srcdir)/m4/ltversion.m4 $(top_srcdir)/m4/lt~obsolete.m4 \
- $(top_srcdir)/acinclude.m4 $(top_srcdir)/configure.ac
-am__configure_deps = $(am__aclocal_m4_deps) $(CONFIGURE_DEPENDENCIES) \
- $(ACLOCAL_M4)
-mkinstalldirs = $(SHELL) $(top_srcdir)/mkinstalldirs
-CONFIG_HEADER = $(top_builddir)/lib/curl_config.h \
- $(top_builddir)/src/curl_config.h curlbuild.h
-CONFIG_CLEAN_FILES =
-SOURCES =
-DIST_SOURCES =
-am__vpath_adj_setup = srcdirstrip=`echo "$(srcdir)" | sed 's|.|.|g'`;
-am__vpath_adj = case $$p in \
- $(srcdir)/*) f=`echo "$$p" | sed "s|^$$srcdirstrip/||"`;; \
- *) f=$$p;; \
- esac;
-am__strip_dir = `echo $$p | sed -e 's|^.*/||'`;
-am__installdirs = "$(DESTDIR)$(pkgincludedir)"
-pkgincludeHEADERS_INSTALL = $(INSTALL_HEADER)
-HEADERS = $(pkginclude_HEADERS)
-ETAGS = etags
-CTAGS = ctags
-DISTFILES = $(DIST_COMMON) $(DIST_SOURCES) $(TEXINFOS) $(EXTRA_DIST)
-pkgincludedir = $(includedir)/curl
-ACLOCAL = @ACLOCAL@
-AMDEP_FALSE = @AMDEP_FALSE@
-AMDEP_TRUE = @AMDEP_TRUE@
-AMTAR = @AMTAR@
-AR = @AR@
-AS = @AS@
-AUTOCONF = @AUTOCONF@
-AUTOHEADER = @AUTOHEADER@
-AUTOMAKE = @AUTOMAKE@
-AWK = @AWK@
-CC = @CC@
-CCDEPMODE = @CCDEPMODE@
-CFLAGS = @CFLAGS@
-CONFIGURE_OPTIONS = @CONFIGURE_OPTIONS@
-CPP = @CPP@
-CPPFLAGS = @CPPFLAGS@
-CROSSCOMPILING_FALSE = @CROSSCOMPILING_FALSE@
-CROSSCOMPILING_TRUE = @CROSSCOMPILING_TRUE@
-CURLDEBUG_FALSE = @CURLDEBUG_FALSE@
-CURLDEBUG_TRUE = @CURLDEBUG_TRUE@
-CURL_CA_BUNDLE = @CURL_CA_BUNDLE@
-CURL_DISABLE_DICT = @CURL_DISABLE_DICT@
-CURL_DISABLE_FILE = @CURL_DISABLE_FILE@
-CURL_DISABLE_FTP = @CURL_DISABLE_FTP@
-CURL_DISABLE_HTTP = @CURL_DISABLE_HTTP@
-CURL_DISABLE_IMAP = @CURL_DISABLE_IMAP@
-CURL_DISABLE_LDAP = @CURL_DISABLE_LDAP@
-CURL_DISABLE_LDAPS = @CURL_DISABLE_LDAPS@
-CURL_DISABLE_POP3 = @CURL_DISABLE_POP3@
-CURL_DISABLE_PROXY = @CURL_DISABLE_PROXY@
-CURL_DISABLE_RTSP = @CURL_DISABLE_RTSP@
-CURL_DISABLE_SMTP = @CURL_DISABLE_SMTP@
-CURL_DISABLE_TELNET = @CURL_DISABLE_TELNET@
-CURL_DISABLE_TFTP = @CURL_DISABLE_TFTP@
-CURL_LIBS = @CURL_LIBS@
-CYGPATH_W = @CYGPATH_W@
-DEFS = @DEFS@
-DEPDIR = @DEPDIR@
-DLLTOOL = @DLLTOOL@
-DSYMUTIL = @DSYMUTIL@
-DUMPBIN = @DUMPBIN@
-ECHO_C = @ECHO_C@
-ECHO_N = @ECHO_N@
-ECHO_T = @ECHO_T@
-EGREP = @EGREP@
-EXEEXT = @EXEEXT@
-FGREP = @FGREP@
-GREP = @GREP@
-HAVE_LIBZ = @HAVE_LIBZ@
-HAVE_LIBZ_FALSE = @HAVE_LIBZ_FALSE@
-HAVE_LIBZ_TRUE = @HAVE_LIBZ_TRUE@
-HAVE_PK11_CREATEGENERICOBJECT = @HAVE_PK11_CREATEGENERICOBJECT@
-IDN_ENABLED = @IDN_ENABLED@
-INSTALL_DATA = @INSTALL_DATA@
-INSTALL_PROGRAM = @INSTALL_PROGRAM@
-INSTALL_SCRIPT = @INSTALL_SCRIPT@
-INSTALL_STRIP_PROGRAM = @INSTALL_STRIP_PROGRAM@
-IPV6_ENABLED = @IPV6_ENABLED@
-KRB4_ENABLED = @KRB4_ENABLED@
-LD = @LD@
-LDFLAGS = @LDFLAGS@
-LIBCURL_LIBS = @LIBCURL_LIBS@
-LIBOBJS = @LIBOBJS@
-LIBS = @LIBS@
-LIBTOOL = @LIBTOOL@
-LIPO = @LIPO@
-LN_S = @LN_S@
-LTLIBOBJS = @LTLIBOBJS@
-MAINT = @MAINT@
-MAINTAINER_MODE_FALSE = @MAINTAINER_MODE_FALSE@
-MAINTAINER_MODE_TRUE = @MAINTAINER_MODE_TRUE@
-MAKEINFO = @MAKEINFO@
-MANOPT = @MANOPT@
-MIMPURE_FALSE = @MIMPURE_FALSE@
-MIMPURE_TRUE = @MIMPURE_TRUE@
-NM = @NM@
-NMEDIT = @NMEDIT@
-NO_UNDEFINED_FALSE = @NO_UNDEFINED_FALSE@
-NO_UNDEFINED_TRUE = @NO_UNDEFINED_TRUE@
-NROFF = @NROFF@
-OBJDUMP = @OBJDUMP@
-OBJEXT = @OBJEXT@
-OTOOL = @OTOOL@
-OTOOL64 = @OTOOL64@
-PACKAGE = @PACKAGE@
-PACKAGE_BUGREPORT = @PACKAGE_BUGREPORT@
-PACKAGE_NAME = @PACKAGE_NAME@
-PACKAGE_STRING = @PACKAGE_STRING@
-PACKAGE_TARNAME = @PACKAGE_TARNAME@
-PACKAGE_URL = @PACKAGE_URL@
-PACKAGE_VERSION = @PACKAGE_VERSION@
-PATH = @PATH@
-PATH_SEPARATOR = @PATH_SEPARATOR@
-PERL = @PERL@
-PKGADD_NAME = @PKGADD_NAME@
-PKGADD_PKG = @PKGADD_PKG@
-PKGADD_VENDOR = @PKGADD_VENDOR@
-PKGCONFIG = @PKGCONFIG@
-RANDOM_FILE = @RANDOM_FILE@
-RANLIB = @RANLIB@
-REQUIRE_LIB_DEPS = @REQUIRE_LIB_DEPS@
-SED = @SED@
-SET_MAKE = @SET_MAKE@
-SHELL = @SHELL@
-SONAME_BUMP_FALSE = @SONAME_BUMP_FALSE@
-SONAME_BUMP_TRUE = @SONAME_BUMP_TRUE@
-SSL_ENABLED = @SSL_ENABLED@
-STATICLIB_FALSE = @STATICLIB_FALSE@
-STATICLIB_TRUE = @STATICLIB_TRUE@
-STRIP = @STRIP@
-SUPPORT_FEATURES = @SUPPORT_FEATURES@
-SUPPORT_PROTOCOLS = @SUPPORT_PROTOCOLS@
-TEST_SERVER_LIBS = @TEST_SERVER_LIBS@
-USE_ARES = @USE_ARES@
-USE_EMBEDDED_ARES_FALSE = @USE_EMBEDDED_ARES_FALSE@
-USE_EMBEDDED_ARES_TRUE = @USE_EMBEDDED_ARES_TRUE@
-USE_GNUTLS = @USE_GNUTLS@
-USE_LIBSSH2 = @USE_LIBSSH2@
-USE_MANUAL_FALSE = @USE_MANUAL_FALSE@
-USE_MANUAL_TRUE = @USE_MANUAL_TRUE@
-USE_NSS = @USE_NSS@
-USE_SSLEAY = @USE_SSLEAY@
-USE_WINDOWS_SSPI = @USE_WINDOWS_SSPI@
-VERSION = @VERSION@
-VERSIONNUM = @VERSIONNUM@
-ac_ct_CC = @ac_ct_CC@
-ac_ct_DUMPBIN = @ac_ct_DUMPBIN@
-am__fastdepCC_FALSE = @am__fastdepCC_FALSE@
-am__fastdepCC_TRUE = @am__fastdepCC_TRUE@
-am__include = @am__include@
-am__leading_dot = @am__leading_dot@
-am__quote = @am__quote@
-am__tar = @am__tar@
-am__untar = @am__untar@
-bindir = @bindir@
-build = @build@
-build_alias = @build_alias@
-build_cpu = @build_cpu@
-build_os = @build_os@
-build_vendor = @build_vendor@
-datadir = @datadir@
-datarootdir = @datarootdir@
-docdir = @docdir@
-dvidir = @dvidir@
-exec_prefix = @exec_prefix@
-host = @host@
-host_alias = @host_alias@
-host_cpu = @host_cpu@
-host_os = @host_os@
-host_vendor = @host_vendor@
-htmldir = @htmldir@
-includedir = @includedir@
-infodir = @infodir@
-install_sh = @install_sh@
-libdir = @libdir@
-libexecdir = @libexecdir@
-libext = @libext@
-localedir = @localedir@
-localstatedir = @localstatedir@
-lt_ECHO = @lt_ECHO@
-mandir = @mandir@
-mkdir_p = @mkdir_p@
-oldincludedir = @oldincludedir@
-pdfdir = @pdfdir@
-prefix = @prefix@
-program_transform_name = @program_transform_name@
-psdir = @psdir@
-sbindir = @sbindir@
-sharedstatedir = @sharedstatedir@
-subdirs = @subdirs@
-sysconfdir = @sysconfdir@
-target_alias = @target_alias@
-pkginclude_HEADERS = \
- curl.h curlver.h easy.h mprintf.h stdcheaders.h types.h multi.h \
- typecheck-gcc.h curlbuild.h curlrules.h
-
-
-# curlbuild.h does not exist in the git tree. When the original libcurl
-# source code distribution archive file is created, curlbuild.h.dist is
-# renamed to curlbuild.h and included in the tarball so that it can be
-# used directly on non-configure systems.
-#
-# The distributed curlbuild.h will be overwritten on configure systems
-# when the configure script runs, with one that is suitable and specific
-# to the library being configured and built.
-#
-# curlbuild.h.in is the distributed template file from which the configure
-# script creates curlbuild.h at library configuration time, overwiting the
-# one included in the distribution archive.
-#
-# curlbuild.h.dist is not included in the source code distribution archive.
-EXTRA_DIST = curlbuild.h.in
-DISTCLEANFILES = curlbuild.h
-all: curlbuild.h
- $(MAKE) $(AM_MAKEFLAGS) all-am
-
-.SUFFIXES:
-$(srcdir)/Makefile.in: @MAINTAINER_MODE_TRUE@ $(srcdir)/Makefile.am $(am__configure_deps)
- @for dep in $?; do \
- case '$(am__configure_deps)' in \
- *$$dep*) \
- cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh \
- && exit 0; \
- exit 1;; \
- esac; \
- done; \
- echo ' cd $(top_srcdir) && $(AUTOMAKE) --foreign include/curl/Makefile'; \
- cd $(top_srcdir) && \
- $(AUTOMAKE) --foreign include/curl/Makefile
-.PRECIOUS: Makefile
-Makefile: $(srcdir)/Makefile.in $(top_builddir)/config.status
- @case '$?' in \
- *config.status*) \
- cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh;; \
- *) \
- echo ' cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__depfiles_maybe)'; \
- cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__depfiles_maybe);; \
- esac;
-
-$(top_builddir)/config.status: $(top_srcdir)/configure $(CONFIG_STATUS_DEPENDENCIES)
- cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh
-
-$(top_srcdir)/configure: @MAINTAINER_MODE_TRUE@ $(am__configure_deps)
- cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh
-$(ACLOCAL_M4): @MAINTAINER_MODE_TRUE@ $(am__aclocal_m4_deps)
- cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh
-
-curlbuild.h: stamp-h3
- @if test ! -f $@; then \
- rm -f stamp-h3; \
- $(MAKE) stamp-h3; \
- else :; fi
-
-stamp-h3: $(srcdir)/curlbuild.h.in $(top_builddir)/config.status
- @rm -f stamp-h3
- cd $(top_builddir) && $(SHELL) ./config.status include/curl/curlbuild.h
-$(srcdir)/curlbuild.h.in: @MAINTAINER_MODE_TRUE@ $(am__configure_deps)
- cd $(top_srcdir) && $(AUTOHEADER)
- rm -f stamp-h3
- touch $@
-
-distclean-hdr:
- -rm -f curlbuild.h stamp-h3
-
-mostlyclean-libtool:
- -rm -f *.lo
-
-clean-libtool:
- -rm -rf .libs _libs
-
-distclean-libtool:
- -rm -f libtool
-uninstall-info-am:
-install-pkgincludeHEADERS: $(pkginclude_HEADERS)
- @$(NORMAL_INSTALL)
- test -z "$(pkgincludedir)" || $(mkdir_p) "$(DESTDIR)$(pkgincludedir)"
- @list='$(pkginclude_HEADERS)'; for p in $$list; do \
- if test -f "$$p"; then d=; else d="$(srcdir)/"; fi; \
- f=$(am__strip_dir) \
- echo " $(pkgincludeHEADERS_INSTALL) '$$d$$p' '$(DESTDIR)$(pkgincludedir)/$$f'"; \
- $(pkgincludeHEADERS_INSTALL) "$$d$$p" "$(DESTDIR)$(pkgincludedir)/$$f"; \
- done
-
-uninstall-pkgincludeHEADERS:
- @$(NORMAL_UNINSTALL)
- @list='$(pkginclude_HEADERS)'; for p in $$list; do \
- f=$(am__strip_dir) \
- echo " rm -f '$(DESTDIR)$(pkgincludedir)/$$f'"; \
- rm -f "$(DESTDIR)$(pkgincludedir)/$$f"; \
- done
-
-ID: $(HEADERS) $(SOURCES) $(LISP) $(TAGS_FILES)
- list='$(SOURCES) $(HEADERS) $(LISP) $(TAGS_FILES)'; \
- unique=`for i in $$list; do \
- if test -f "$$i"; then echo $$i; else echo $(srcdir)/$$i; fi; \
- done | \
- $(AWK) ' { files[$$0] = 1; } \
- END { for (i in files) print i; }'`; \
- mkid -fID $$unique
-tags: TAGS
-
-TAGS: $(HEADERS) $(SOURCES) curlbuild.h.in $(TAGS_DEPENDENCIES) \
- $(TAGS_FILES) $(LISP)
- tags=; \
- here=`pwd`; \
- list='$(SOURCES) $(HEADERS) curlbuild.h.in $(LISP) $(TAGS_FILES)'; \
- unique=`for i in $$list; do \
- if test -f "$$i"; then echo $$i; else echo $(srcdir)/$$i; fi; \
- done | \
- $(AWK) ' { files[$$0] = 1; } \
- END { for (i in files) print i; }'`; \
- if test -z "$(ETAGS_ARGS)$$tags$$unique"; then :; else \
- test -n "$$unique" || unique=$$empty_fix; \
- $(ETAGS) $(ETAGSFLAGS) $(AM_ETAGSFLAGS) $(ETAGS_ARGS) \
- $$tags $$unique; \
- fi
-ctags: CTAGS
-CTAGS: $(HEADERS) $(SOURCES) curlbuild.h.in $(TAGS_DEPENDENCIES) \
- $(TAGS_FILES) $(LISP)
- tags=; \
- here=`pwd`; \
- list='$(SOURCES) $(HEADERS) curlbuild.h.in $(LISP) $(TAGS_FILES)'; \
- unique=`for i in $$list; do \
- if test -f "$$i"; then echo $$i; else echo $(srcdir)/$$i; fi; \
- done | \
- $(AWK) ' { files[$$0] = 1; } \
- END { for (i in files) print i; }'`; \
- test -z "$(CTAGS_ARGS)$$tags$$unique" \
- || $(CTAGS) $(CTAGSFLAGS) $(AM_CTAGSFLAGS) $(CTAGS_ARGS) \
- $$tags $$unique
-
-GTAGS:
- here=`$(am__cd) $(top_builddir) && pwd` \
- && cd $(top_srcdir) \
- && gtags -i $(GTAGS_ARGS) $$here
-
-distclean-tags:
- -rm -f TAGS ID GTAGS GRTAGS GSYMS GPATH tags
-
-distdir: $(DISTFILES)
- @srcdirstrip=`echo "$(srcdir)" | sed 's|.|.|g'`; \
- topsrcdirstrip=`echo "$(top_srcdir)" | sed 's|.|.|g'`; \
- list='$(DISTFILES)'; for file in $$list; do \
- case $$file in \
- $(srcdir)/*) file=`echo "$$file" | sed "s|^$$srcdirstrip/||"`;; \
- $(top_srcdir)/*) file=`echo "$$file" | sed "s|^$$topsrcdirstrip/|$(top_builddir)/|"`;; \
- esac; \
- if test -f $$file || test -d $$file; then d=.; else d=$(srcdir); fi; \
- dir=`echo "$$file" | sed -e 's,/[^/]*$$,,'`; \
- if test "$$dir" != "$$file" && test "$$dir" != "."; then \
- dir="/$$dir"; \
- $(mkdir_p) "$(distdir)$$dir"; \
- else \
- dir=''; \
- fi; \
- if test -d $$d/$$file; then \
- if test -d $(srcdir)/$$file && test $$d != $(srcdir); then \
- cp -pR $(srcdir)/$$file $(distdir)$$dir || exit 1; \
- fi; \
- cp -pR $$d/$$file $(distdir)$$dir || exit 1; \
- else \
- test -f $(distdir)/$$file \
- || cp -p $$d/$$file $(distdir)/$$file \
- || exit 1; \
- fi; \
- done
-check-am: all-am
-check: check-am
-all-am: Makefile $(HEADERS) curlbuild.h
-installdirs:
- for dir in "$(DESTDIR)$(pkgincludedir)"; do \
- test -z "$$dir" || $(mkdir_p) "$$dir"; \
- done
-install: install-am
-install-exec: install-exec-am
-install-data: install-data-am
-uninstall: uninstall-am
-
-install-am: all-am
- @$(MAKE) $(AM_MAKEFLAGS) install-exec-am install-data-am
-
-installcheck: installcheck-am
-install-strip:
- $(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \
- install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \
- `test -z '$(STRIP)' || \
- echo "INSTALL_PROGRAM_ENV=STRIPPROG='$(STRIP)'"` install
-mostlyclean-generic:
-
-clean-generic:
-
-distclean-generic:
- -test -z "$(CONFIG_CLEAN_FILES)" || rm -f $(CONFIG_CLEAN_FILES)
- -test -z "$(DISTCLEANFILES)" || rm -f $(DISTCLEANFILES)
-
-maintainer-clean-generic:
- @echo "This command is intended for maintainers to use"
- @echo "it deletes files that may require special tools to rebuild."
-clean: clean-am
-
-clean-am: clean-generic clean-libtool mostlyclean-am
-
-distclean: distclean-am
- -rm -f Makefile
-distclean-am: clean-am distclean-generic distclean-hdr \
- distclean-libtool distclean-tags
-
-dvi: dvi-am
-
-dvi-am:
-
-html: html-am
-
-info: info-am
-
-info-am:
-
-install-data-am: install-pkgincludeHEADERS
-
-install-exec-am:
-
-install-info: install-info-am
-
-install-man:
-
-installcheck-am:
-
-maintainer-clean: maintainer-clean-am
- -rm -f Makefile
-maintainer-clean-am: distclean-am maintainer-clean-generic
-
-mostlyclean: mostlyclean-am
-
-mostlyclean-am: mostlyclean-generic mostlyclean-libtool
-
-pdf: pdf-am
-
-pdf-am:
-
-ps: ps-am
-
-ps-am:
-
-uninstall-am: uninstall-info-am uninstall-pkgincludeHEADERS
-
-.PHONY: CTAGS GTAGS all all-am check check-am clean clean-generic \
- clean-libtool ctags distclean distclean-generic distclean-hdr \
- distclean-libtool distclean-tags distdir dvi dvi-am html \
- html-am info info-am install install-am install-data \
- install-data-am install-exec install-exec-am install-info \
- install-info-am install-man install-pkgincludeHEADERS \
- install-strip installcheck installcheck-am installdirs \
- maintainer-clean maintainer-clean-generic mostlyclean \
- mostlyclean-generic mostlyclean-libtool pdf pdf-am ps ps-am \
- tags uninstall uninstall-am uninstall-info-am \
- uninstall-pkgincludeHEADERS
-
-# Tell versions [3.59,3.63) of GNU make to not export all variables.
-# Otherwise a system limit (for SysV at least) may be exceeded.
-.NOEXPORT:
diff --git a/src/utils/curl/curl.h b/src/utils/curl/curl.h
deleted file mode 100644
index e63596828a4b1cae4c9d3bee1a02aad1a18af347..0000000000000000000000000000000000000000
--- a/src/utils/curl/curl.h
+++ /dev/null
@@ -1,1996 +0,0 @@
-#ifndef __CURL_CURL_H
-#define __CURL_CURL_H
-/***************************************************************************
- * _ _ ____ _
- * Project ___| | | | _ \| |
- * / __| | | | |_) | |
- * | (__| |_| | _ <| |___
- * \___|\___/|_| \_\_____|
- *
- * Copyright (C) 1998 - 2010, Daniel Stenberg, <daniel@haxx.se>, et al.
- *
- * This software is licensed as described in the file COPYING, which
- * you should have received as part of this distribution. The terms
- * are also available at http://curl.haxx.se/docs/copyright.html.
- *
- * You may opt to use, copy, modify, merge, publish, distribute and/or sell
- * copies of the Software, and permit persons to whom the Software is
- * furnished to do so, under the terms of the COPYING file.
- *
- * This software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY
- * KIND, either express or implied.
- *
- ***************************************************************************/
-
-/*
- * If you have libcurl problems, all docs and details are found here:
- * http://curl.haxx.se/libcurl/
- *
- * curl-library mailing list subscription and unsubscription web interface:
- * http://cool.haxx.se/mailman/listinfo/curl-library/
- */
-
-#include "curlver.h" /* libcurl version defines */
-#include "curlbuild.h" /* libcurl build definitions */
-#include "curlrules.h" /* libcurl rules enforcement */
-
-/*
- * Define WIN32 when build target is Win32 API
- */
-
-#if (defined(_WIN32) || defined(__WIN32__)) && \
- !defined(WIN32) && !defined(__SYMBIAN32__)
-#define WIN32
-#endif
-
-#include <stdio.h>
-#include <limits.h>
-
-#if defined(__FreeBSD__) && (__FreeBSD__ >= 2)
-/* Needed for __FreeBSD_version symbol definition */
-#include <osreldate.h>
-#endif
-
-/* The include stuff here below is mainly for time_t! */
-#include <sys/types.h>
-#include <time.h>
-
-#if defined(WIN32) && !defined(_WIN32_WCE) && !defined(__GNUC__) && \
- !defined(__CYGWIN__) || defined(__MINGW32__)
-#if !(defined(_WINSOCKAPI_) || defined(_WINSOCK_H))
-/* The check above prevents the winsock2 inclusion if winsock.h already was
- included, since they can't co-exist without problems */
-#include <winsock2.h>
-#include <ws2tcpip.h>
-#endif
-#else
-
-/* HP-UX systems version 9, 10 and 11 lack sys/select.h and so does oldish
- libc5-based Linux systems. Only include it on system that are known to
- require it! */
-#if defined(_AIX) || defined(__NOVELL_LIBC__) || defined(__NetBSD__) || \
- defined(__minix) || defined(__SYMBIAN32__) || defined(__INTEGRITY) || \
- defined(ANDROID) || \
- (defined(__FreeBSD_version) && (__FreeBSD_version < 800000))
-#include <sys/select.h>
-#endif
-
-#ifndef _WIN32_WCE
-#include <sys/socket.h>
-#endif
-#if !defined(WIN32) && !defined(__WATCOMC__) && !defined(__VXWORKS__)
-#include <sys/time.h>
-#endif
-#include <sys/types.h>
-#endif
-
-#ifdef __BEOS__
-#include <support/SupportDefs.h>
-#endif
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-typedef void CURL;
-
-/*
- * Decorate exportable functions for Win32 and Symbian OS DLL linking.
- * This avoids using a .def file for building libcurl.dll.
- */
-#if (defined(WIN32) || defined(_WIN32) || defined(__SYMBIAN32__)) && \
- !defined(CURL_STATICLIB)
-#if defined(BUILDING_LIBCURL)
-#define CURL_EXTERN __declspec(dllexport)
-#else
-#define CURL_EXTERN __declspec(dllimport)
-#endif
-#else
-
-#ifdef CURL_HIDDEN_SYMBOLS
-/*
- * This definition is used to make external definitions visible in the
- * shared library when symbols are hidden by default. It makes no
- * difference when compiling applications whether this is set or not,
- * only when compiling the library.
- */
-#define CURL_EXTERN CURL_EXTERN_SYMBOL
-#else
-#define CURL_EXTERN
-#endif
-#endif
-
-#ifndef curl_socket_typedef
-/* socket typedef */
-#ifdef WIN32
-typedef SOCKET curl_socket_t;
-#define CURL_SOCKET_BAD INVALID_SOCKET
-#else
-typedef int curl_socket_t;
-#define CURL_SOCKET_BAD -1
-#endif
-#define curl_socket_typedef
-#endif /* curl_socket_typedef */
-
-struct curl_httppost {
- struct curl_httppost *next; /* next entry in the list */
- char *name; /* pointer to allocated name */
- long namelength; /* length of name length */
- char *contents; /* pointer to allocated data contents */
- long contentslength; /* length of contents field */
- char *buffer; /* pointer to allocated buffer contents */
- long bufferlength; /* length of buffer field */
- char *contenttype; /* Content-Type */
- struct curl_slist* contentheader; /* list of extra headers for this form */
- struct curl_httppost *more; /* if one field name has more than one
- file, this link should link to following
- files */
- long flags; /* as defined below */
-#define HTTPPOST_FILENAME (1<<0) /* specified content is a file name */
-#define HTTPPOST_READFILE (1<<1) /* specified content is a file name */
-#define HTTPPOST_PTRNAME (1<<2) /* name is only stored pointer
- do not free in formfree */
-#define HTTPPOST_PTRCONTENTS (1<<3) /* contents is only stored pointer
- do not free in formfree */
-#define HTTPPOST_BUFFER (1<<4) /* upload file from buffer */
-#define HTTPPOST_PTRBUFFER (1<<5) /* upload file from pointer contents */
-#define HTTPPOST_CALLBACK (1<<6) /* upload file contents by using the
- regular read callback to get the data
- and pass the given pointer as custom
- pointer */
-
- char *showfilename; /* The file name to show. If not set, the
- actual file name will be used (if this
- is a file part) */
- void *userp; /* custom pointer used for
- HTTPPOST_CALLBACK posts */
-};
-
-typedef int (*curl_progress_callback)(void *clientp,
- double dltotal,
- double dlnow,
- double ultotal,
- double ulnow);
-
-#ifndef CURL_MAX_WRITE_SIZE
- /* Tests have proven that 20K is a very bad buffer size for uploads on
- Windows, while 16K for some odd reason performed a lot better.
- We do the ifndef check to allow this value to easier be changed at build
- time for those who feel adventurous. The practical minimum is about
- 400 bytes since libcurl uses a buffer of this size as a scratch area
- (unrelated to network send operations). */
-#define CURL_MAX_WRITE_SIZE 16384
-#endif
-
-#ifndef CURL_MAX_HTTP_HEADER
-/* The only reason to have a max limit for this is to avoid the risk of a bad
- server feeding libcurl with a never-ending header that will cause reallocs
- infinitely */
-#define CURL_MAX_HTTP_HEADER (100*1024)
-#endif
-
-
-/* This is a magic return code for the write callback that, when returned,
- will signal libcurl to pause receiving on the current transfer. */
-#define CURL_WRITEFUNC_PAUSE 0x10000001
-typedef size_t (*curl_write_callback)(char *buffer,
- size_t size,
- size_t nitems,
- void *outstream);
-
-/* These are the return codes for the seek callbacks */
-#define CURL_SEEKFUNC_OK 0
-#define CURL_SEEKFUNC_FAIL 1 /* fail the entire transfer */
-#define CURL_SEEKFUNC_CANTSEEK 2 /* tell libcurl seeking can't be done, so
- libcurl might try other means instead */
-typedef int (*curl_seek_callback)(void *instream,
- curl_off_t offset,
- int origin); /* 'whence' */
-
-/* This is a return code for the read callback that, when returned, will
- signal libcurl to immediately abort the current transfer. */
-#define CURL_READFUNC_ABORT 0x10000000
-/* This is a return code for the read callback that, when returned, will
- signal libcurl to pause sending data on the current transfer. */
-#define CURL_READFUNC_PAUSE 0x10000001
-
-typedef size_t (*curl_read_callback)(char *buffer,
- size_t size,
- size_t nitems,
- void *instream);
-
-typedef enum {
- CURLSOCKTYPE_IPCXN, /* socket created for a specific IP connection */
- CURLSOCKTYPE_LAST /* never use */
-} curlsocktype;
-
-typedef int (*curl_sockopt_callback)(void *clientp,
- curl_socket_t curlfd,
- curlsocktype purpose);
-
-struct curl_sockaddr {
- int family;
- int socktype;
- int protocol;
- unsigned int addrlen; /* addrlen was a socklen_t type before 7.18.0 but it
- turned really ugly and painful on the systems that
- lack this type */
- struct sockaddr addr;
-};
-
-typedef curl_socket_t
-(*curl_opensocket_callback)(void *clientp,
- curlsocktype purpose,
- struct curl_sockaddr *address);
-
-typedef enum {
- CURLIOE_OK, /* I/O operation successful */
- CURLIOE_UNKNOWNCMD, /* command was unknown to callback */
- CURLIOE_FAILRESTART, /* failed to restart the read */
- CURLIOE_LAST /* never use */
-} curlioerr;
-
-typedef enum {
- CURLIOCMD_NOP, /* no operation */
- CURLIOCMD_RESTARTREAD, /* restart the read stream from start */
- CURLIOCMD_LAST /* never use */
-} curliocmd;
-
-typedef curlioerr (*curl_ioctl_callback)(CURL *handle,
- int cmd,
- void *clientp);
-
-/*
- * The following typedef's are signatures of malloc, free, realloc, strdup and
- * calloc respectively. Function pointers of these types can be passed to the
- * curl_global_init_mem() function to set user defined memory management
- * callback routines.
- */
-typedef void *(*curl_malloc_callback)(size_t size);
-typedef void (*curl_free_callback)(void *ptr);
-typedef void *(*curl_realloc_callback)(void *ptr, size_t size);
-typedef char *(*curl_strdup_callback)(const char *str);
-typedef void *(*curl_calloc_callback)(size_t nmemb, size_t size);
-
-/* the kind of data that is passed to information_callback*/
-typedef enum {
- CURLINFO_TEXT = 0,
- CURLINFO_HEADER_IN, /* 1 */
- CURLINFO_HEADER_OUT, /* 2 */
- CURLINFO_DATA_IN, /* 3 */
- CURLINFO_DATA_OUT, /* 4 */
- CURLINFO_SSL_DATA_IN, /* 5 */
- CURLINFO_SSL_DATA_OUT, /* 6 */
- CURLINFO_END
-} curl_infotype;
-
-typedef int (*curl_debug_callback)
- (CURL *handle, /* the handle/transfer this concerns */
- curl_infotype type, /* what kind of data */
- char *data, /* points to the data */
- size_t size, /* size of the data pointed to */
- void *userptr); /* whatever the user please */
-
-/* All possible error codes from all sorts of curl functions. Future versions
- may return other values, stay prepared.
-
- Always add new return codes last. Never *EVER* remove any. The return
- codes must remain the same!
- */
-
-typedef enum {
- CURLE_OK = 0,
- CURLE_UNSUPPORTED_PROTOCOL, /* 1 */
- CURLE_FAILED_INIT, /* 2 */
- CURLE_URL_MALFORMAT, /* 3 */
- CURLE_OBSOLETE4, /* 4 - NOT USED */
- CURLE_COULDNT_RESOLVE_PROXY, /* 5 */
- CURLE_COULDNT_RESOLVE_HOST, /* 6 */
- CURLE_COULDNT_CONNECT, /* 7 */
- CURLE_FTP_WEIRD_SERVER_REPLY, /* 8 */
- CURLE_REMOTE_ACCESS_DENIED, /* 9 a service was denied by the server
- due to lack of access - when login fails
- this is not returned. */
- CURLE_OBSOLETE10, /* 10 - NOT USED */
- CURLE_FTP_WEIRD_PASS_REPLY, /* 11 */
- CURLE_OBSOLETE12, /* 12 - NOT USED */
- CURLE_FTP_WEIRD_PASV_REPLY, /* 13 */
- CURLE_FTP_WEIRD_227_FORMAT, /* 14 */
- CURLE_FTP_CANT_GET_HOST, /* 15 */
- CURLE_OBSOLETE16, /* 16 - NOT USED */
- CURLE_FTP_COULDNT_SET_TYPE, /* 17 */
- CURLE_PARTIAL_FILE, /* 18 */
- CURLE_FTP_COULDNT_RETR_FILE, /* 19 */
- CURLE_OBSOLETE20, /* 20 - NOT USED */
- CURLE_QUOTE_ERROR, /* 21 - quote command failure */
- CURLE_HTTP_RETURNED_ERROR, /* 22 */
- CURLE_WRITE_ERROR, /* 23 */
- CURLE_OBSOLETE24, /* 24 - NOT USED */
- CURLE_UPLOAD_FAILED, /* 25 - failed upload "command" */
- CURLE_READ_ERROR, /* 26 - couldn't open/read from file */
- CURLE_OUT_OF_MEMORY, /* 27 */
- /* Note: CURLE_OUT_OF_MEMORY may sometimes indicate a conversion error
- instead of a memory allocation error if CURL_DOES_CONVERSIONS
- is defined
- */
- CURLE_OPERATION_TIMEDOUT, /* 28 - the timeout time was reached */
- CURLE_OBSOLETE29, /* 29 - NOT USED */
- CURLE_FTP_PORT_FAILED, /* 30 - FTP PORT operation failed */
- CURLE_FTP_COULDNT_USE_REST, /* 31 - the REST command failed */
- CURLE_OBSOLETE32, /* 32 - NOT USED */
- CURLE_RANGE_ERROR, /* 33 - RANGE "command" didn't work */
- CURLE_HTTP_POST_ERROR, /* 34 */
- CURLE_SSL_CONNECT_ERROR, /* 35 - wrong when connecting with SSL */
- CURLE_BAD_DOWNLOAD_RESUME, /* 36 - couldn't resume download */
- CURLE_FILE_COULDNT_READ_FILE, /* 37 */
- CURLE_LDAP_CANNOT_BIND, /* 38 */
- CURLE_LDAP_SEARCH_FAILED, /* 39 */
- CURLE_OBSOLETE40, /* 40 - NOT USED */
- CURLE_FUNCTION_NOT_FOUND, /* 41 */
- CURLE_ABORTED_BY_CALLBACK, /* 42 */
- CURLE_BAD_FUNCTION_ARGUMENT, /* 43 */
- CURLE_OBSOLETE44, /* 44 - NOT USED */
- CURLE_INTERFACE_FAILED, /* 45 - CURLOPT_INTERFACE failed */
- CURLE_OBSOLETE46, /* 46 - NOT USED */
- CURLE_TOO_MANY_REDIRECTS , /* 47 - catch endless re-direct loops */
- CURLE_UNKNOWN_TELNET_OPTION, /* 48 - User specified an unknown option */
- CURLE_TELNET_OPTION_SYNTAX , /* 49 - Malformed telnet option */
- CURLE_OBSOLETE50, /* 50 - NOT USED */
- CURLE_PEER_FAILED_VERIFICATION, /* 51 - peer's certificate or fingerprint
- wasn't verified fine */
- CURLE_GOT_NOTHING, /* 52 - when this is a specific error */
- CURLE_SSL_ENGINE_NOTFOUND, /* 53 - SSL crypto engine not found */
- CURLE_SSL_ENGINE_SETFAILED, /* 54 - can not set SSL crypto engine as
- default */
- CURLE_SEND_ERROR, /* 55 - failed sending network data */
- CURLE_RECV_ERROR, /* 56 - failure in receiving network data */
- CURLE_OBSOLETE57, /* 57 - NOT IN USE */
- CURLE_SSL_CERTPROBLEM, /* 58 - problem with the local certificate */
- CURLE_SSL_CIPHER, /* 59 - couldn't use specified cipher */
- CURLE_SSL_CACERT, /* 60 - problem with the CA cert (path?) */
- CURLE_BAD_CONTENT_ENCODING, /* 61 - Unrecognized transfer encoding */
- CURLE_LDAP_INVALID_URL, /* 62 - Invalid LDAP URL */
- CURLE_FILESIZE_EXCEEDED, /* 63 - Maximum file size exceeded */
- CURLE_USE_SSL_FAILED, /* 64 - Requested FTP SSL level failed */
- CURLE_SEND_FAIL_REWIND, /* 65 - Sending the data requires a rewind
- that failed */
- CURLE_SSL_ENGINE_INITFAILED, /* 66 - failed to initialise ENGINE */
- CURLE_LOGIN_DENIED, /* 67 - user, password or similar was not
- accepted and we failed to login */
- CURLE_TFTP_NOTFOUND, /* 68 - file not found on server */
- CURLE_TFTP_PERM, /* 69 - permission problem on server */
- CURLE_REMOTE_DISK_FULL, /* 70 - out of disk space on server */
- CURLE_TFTP_ILLEGAL, /* 71 - Illegal TFTP operation */
- CURLE_TFTP_UNKNOWNID, /* 72 - Unknown transfer ID */
- CURLE_REMOTE_FILE_EXISTS, /* 73 - File already exists */
- CURLE_TFTP_NOSUCHUSER, /* 74 - No such user */
- CURLE_CONV_FAILED, /* 75 - conversion failed */
- CURLE_CONV_REQD, /* 76 - caller must register conversion
- callbacks using curl_easy_setopt options
- CURLOPT_CONV_FROM_NETWORK_FUNCTION,
- CURLOPT_CONV_TO_NETWORK_FUNCTION, and
- CURLOPT_CONV_FROM_UTF8_FUNCTION */
- CURLE_SSL_CACERT_BADFILE, /* 77 - could not load CACERT file, missing
- or wrong format */
- CURLE_REMOTE_FILE_NOT_FOUND, /* 78 - remote file not found */
- CURLE_SSH, /* 79 - error from the SSH layer, somewhat
- generic so the error message will be of
- interest when this has happened */
-
- CURLE_SSL_SHUTDOWN_FAILED, /* 80 - Failed to shut down the SSL
- connection */
- CURLE_AGAIN, /* 81 - socket is not ready for send/recv,
- wait till it's ready and try again (Added
- in 7.18.2) */
- CURLE_SSL_CRL_BADFILE, /* 82 - could not load CRL file, missing or
- wrong format (Added in 7.19.0) */
- CURLE_SSL_ISSUER_ERROR, /* 83 - Issuer check failed. (Added in
- 7.19.0) */
- CURLE_FTP_PRET_FAILED, /* 84 - a PRET command failed */
- CURLE_RTSP_CSEQ_ERROR, /* 85 - mismatch of RTSP CSeq numbers */
- CURLE_RTSP_SESSION_ERROR, /* 86 - mismatch of RTSP Session Identifiers */
-
- CURL_LAST /* never use! */
-} CURLcode;
-
-#ifndef CURL_NO_OLDIES /* define this to test if your app builds with all
- the obsolete stuff removed! */
-
-/* Backwards compatibility with older names */
-
-/* The following were added in 7.17.1 */
-/* These are scheduled to disappear by 2009 */
-#define CURLE_SSL_PEER_CERTIFICATE CURLE_PEER_FAILED_VERIFICATION
-
-/* The following were added in 7.17.0 */
-/* These are scheduled to disappear by 2009 */
-#define CURLE_OBSOLETE CURLE_OBSOLETE50 /* noone should be using this! */
-#define CURLE_BAD_PASSWORD_ENTERED CURLE_OBSOLETE46
-#define CURLE_BAD_CALLING_ORDER CURLE_OBSOLETE44
-#define CURLE_FTP_USER_PASSWORD_INCORRECT CURLE_OBSOLETE10
-#define CURLE_FTP_CANT_RECONNECT CURLE_OBSOLETE16
-#define CURLE_FTP_COULDNT_GET_SIZE CURLE_OBSOLETE32
-#define CURLE_FTP_COULDNT_SET_ASCII CURLE_OBSOLETE29
-#define CURLE_FTP_WEIRD_USER_REPLY CURLE_OBSOLETE12
-#define CURLE_FTP_WRITE_ERROR CURLE_OBSOLETE20
-#define CURLE_LIBRARY_NOT_FOUND CURLE_OBSOLETE40
-#define CURLE_MALFORMAT_USER CURLE_OBSOLETE24
-#define CURLE_SHARE_IN_USE CURLE_OBSOLETE57
-#define CURLE_URL_MALFORMAT_USER CURLE_OBSOLETE4
-
-#define CURLE_FTP_ACCESS_DENIED CURLE_REMOTE_ACCESS_DENIED
-#define CURLE_FTP_COULDNT_SET_BINARY CURLE_FTP_COULDNT_SET_TYPE
-#define CURLE_FTP_QUOTE_ERROR CURLE_QUOTE_ERROR
-#define CURLE_TFTP_DISKFULL CURLE_REMOTE_DISK_FULL
-#define CURLE_TFTP_EXISTS CURLE_REMOTE_FILE_EXISTS
-#define CURLE_HTTP_RANGE_ERROR CURLE_RANGE_ERROR
-#define CURLE_FTP_SSL_FAILED CURLE_USE_SSL_FAILED
-
-/* The following were added earlier */
-
-#define CURLE_OPERATION_TIMEOUTED CURLE_OPERATION_TIMEDOUT
-
-#define CURLE_HTTP_NOT_FOUND CURLE_HTTP_RETURNED_ERROR
-#define CURLE_HTTP_PORT_FAILED CURLE_INTERFACE_FAILED
-#define CURLE_FTP_COULDNT_STOR_FILE CURLE_UPLOAD_FAILED
-
-#define CURLE_FTP_PARTIAL_FILE CURLE_PARTIAL_FILE
-#define CURLE_FTP_BAD_DOWNLOAD_RESUME CURLE_BAD_DOWNLOAD_RESUME
-
-/* This was the error code 50 in 7.7.3 and a few earlier versions, this
- is no longer used by libcurl but is instead #defined here only to not
- make programs break */
-#define CURLE_ALREADY_COMPLETE 99999
-
-#endif /*!CURL_NO_OLDIES*/
-
-/* This prototype applies to all conversion callbacks */
-typedef CURLcode (*curl_conv_callback)(char *buffer, size_t length);
-
-typedef CURLcode (*curl_ssl_ctx_callback)(CURL *curl, /* easy handle */
- void *ssl_ctx, /* actually an
- OpenSSL SSL_CTX */
- void *userptr);
-
-typedef enum {
- CURLPROXY_HTTP = 0, /* added in 7.10, new in 7.19.4 default is to use
- CONNECT HTTP/1.1 */
- CURLPROXY_HTTP_1_0 = 1, /* added in 7.19.4, force to use CONNECT
- HTTP/1.0 */
- CURLPROXY_SOCKS4 = 4, /* support added in 7.15.2, enum existed already
- in 7.10 */
- CURLPROXY_SOCKS5 = 5, /* added in 7.10 */
- CURLPROXY_SOCKS4A = 6, /* added in 7.18.0 */
- CURLPROXY_SOCKS5_HOSTNAME = 7 /* Use the SOCKS5 protocol but pass along the
- host name rather than the IP address. added
- in 7.18.0 */
-} curl_proxytype; /* this enum was added in 7.10 */
-
-#define CURLAUTH_NONE 0 /* nothing */
-#define CURLAUTH_BASIC (1<<0) /* Basic (default) */
-#define CURLAUTH_DIGEST (1<<1) /* Digest */
-#define CURLAUTH_GSSNEGOTIATE (1<<2) /* GSS-Negotiate */
-#define CURLAUTH_NTLM (1<<3) /* NTLM */
-#define CURLAUTH_DIGEST_IE (1<<4) /* Digest with IE flavour */
-#define CURLAUTH_ANY (~CURLAUTH_DIGEST_IE) /* all fine types set */
-#define CURLAUTH_ANYSAFE (~(CURLAUTH_BASIC|CURLAUTH_DIGEST_IE))
-
-#define CURLSSH_AUTH_ANY ~0 /* all types supported by the server */
-#define CURLSSH_AUTH_NONE 0 /* none allowed, silly but complete */
-#define CURLSSH_AUTH_PUBLICKEY (1<<0) /* public/private key files */
-#define CURLSSH_AUTH_PASSWORD (1<<1) /* password */
-#define CURLSSH_AUTH_HOST (1<<2) /* host key files */
-#define CURLSSH_AUTH_KEYBOARD (1<<3) /* keyboard interactive */
-#define CURLSSH_AUTH_DEFAULT CURLSSH_AUTH_ANY
-
-#define CURL_ERROR_SIZE 256
-
-struct curl_khkey {
- const char *key; /* points to a zero-terminated string encoded with base64
- if len is zero, otherwise to the "raw" data */
- size_t len;
- enum type {
- CURLKHTYPE_UNKNOWN,
- CURLKHTYPE_RSA1,
- CURLKHTYPE_RSA,
- CURLKHTYPE_DSS
- } keytype;
-};
-
-/* this is the set of return values expected from the curl_sshkeycallback
- callback */
-enum curl_khstat {
- CURLKHSTAT_FINE_ADD_TO_FILE,
- CURLKHSTAT_FINE,
- CURLKHSTAT_REJECT, /* reject the connection, return an error */
- CURLKHSTAT_DEFER, /* do not accept it, but we can't answer right now so
- this causes a CURLE_DEFER error but otherwise the
- connection will be left intact etc */
- CURLKHSTAT_LAST /* not for use, only a marker for last-in-list */
-};
-
-/* this is the set of status codes pass in to the callback */
-enum curl_khmatch {
- CURLKHMATCH_OK, /* match */
- CURLKHMATCH_MISMATCH, /* host found, key mismatch! */
- CURLKHMATCH_MISSING, /* no matching host/key found */
- CURLKHMATCH_LAST /* not for use, only a marker for last-in-list */
-};
-
-typedef int
- (*curl_sshkeycallback) (CURL *easy, /* easy handle */
- const struct curl_khkey *knownkey, /* known */
- const struct curl_khkey *foundkey, /* found */
- enum curl_khmatch, /* libcurl's view on the keys */
- void *clientp); /* custom pointer passed from app */
-
-/* parameter for the CURLOPT_USE_SSL option */
-typedef enum {
- CURLUSESSL_NONE, /* do not attempt to use SSL */
- CURLUSESSL_TRY, /* try using SSL, proceed anyway otherwise */
- CURLUSESSL_CONTROL, /* SSL for the control connection or fail */
- CURLUSESSL_ALL, /* SSL for all communication or fail */
- CURLUSESSL_LAST /* not an option, never use */
-} curl_usessl;
-
-#ifndef CURL_NO_OLDIES /* define this to test if your app builds with all
- the obsolete stuff removed! */
-
-/* Backwards compatibility with older names */
-/* These are scheduled to disappear by 2009 */
-
-#define CURLFTPSSL_NONE CURLUSESSL_NONE
-#define CURLFTPSSL_TRY CURLUSESSL_TRY
-#define CURLFTPSSL_CONTROL CURLUSESSL_CONTROL
-#define CURLFTPSSL_ALL CURLUSESSL_ALL
-#define CURLFTPSSL_LAST CURLUSESSL_LAST
-#define curl_ftpssl curl_usessl
-#endif /*!CURL_NO_OLDIES*/
-
-/* parameter for the CURLOPT_FTP_SSL_CCC option */
-typedef enum {
- CURLFTPSSL_CCC_NONE, /* do not send CCC */
- CURLFTPSSL_CCC_PASSIVE, /* Let the server initiate the shutdown */
- CURLFTPSSL_CCC_ACTIVE, /* Initiate the shutdown */
- CURLFTPSSL_CCC_LAST /* not an option, never use */
-} curl_ftpccc;
-
-/* parameter for the CURLOPT_FTPSSLAUTH option */
-typedef enum {
- CURLFTPAUTH_DEFAULT, /* let libcurl decide */
- CURLFTPAUTH_SSL, /* use "AUTH SSL" */
- CURLFTPAUTH_TLS, /* use "AUTH TLS" */
- CURLFTPAUTH_LAST /* not an option, never use */
-} curl_ftpauth;
-
-/* parameter for the CURLOPT_FTP_CREATE_MISSING_DIRS option */
-typedef enum {
- CURLFTP_CREATE_DIR_NONE, /* do NOT create missing dirs! */
- CURLFTP_CREATE_DIR, /* (FTP/SFTP) if CWD fails, try MKD and then CWD
- again if MKD succeeded, for SFTP this does
- similar magic */
- CURLFTP_CREATE_DIR_RETRY, /* (FTP only) if CWD fails, try MKD and then CWD
- again even if MKD failed! */
- CURLFTP_CREATE_DIR_LAST /* not an option, never use */
-} curl_ftpcreatedir;
-
-/* parameter for the CURLOPT_FTP_FILEMETHOD option */
-typedef enum {
- CURLFTPMETHOD_DEFAULT, /* let libcurl pick */
- CURLFTPMETHOD_MULTICWD, /* single CWD operation for each path part */
- CURLFTPMETHOD_NOCWD, /* no CWD at all */
- CURLFTPMETHOD_SINGLECWD, /* one CWD to full dir, then work on file */
- CURLFTPMETHOD_LAST /* not an option, never use */
-} curl_ftpmethod;
-
-/* CURLPROTO_ defines are for the CURLOPT_*PROTOCOLS options */
-#define CURLPROTO_HTTP (1<<0)
-#define CURLPROTO_HTTPS (1<<1)
-#define CURLPROTO_FTP (1<<2)
-#define CURLPROTO_FTPS (1<<3)
-#define CURLPROTO_SCP (1<<4)
-#define CURLPROTO_SFTP (1<<5)
-#define CURLPROTO_TELNET (1<<6)
-#define CURLPROTO_LDAP (1<<7)
-#define CURLPROTO_LDAPS (1<<8)
-#define CURLPROTO_DICT (1<<9)
-#define CURLPROTO_FILE (1<<10)
-#define CURLPROTO_TFTP (1<<11)
-#define CURLPROTO_IMAP (1<<12)
-#define CURLPROTO_IMAPS (1<<13)
-#define CURLPROTO_POP3 (1<<14)
-#define CURLPROTO_POP3S (1<<15)
-#define CURLPROTO_SMTP (1<<16)
-#define CURLPROTO_SMTPS (1<<17)
-#define CURLPROTO_RTSP (1<<18)
-#define CURLPROTO_ALL (~0) /* enable everything */
-
-/* long may be 32 or 64 bits, but we should never depend on anything else
- but 32 */
-#define CURLOPTTYPE_LONG 0
-#define CURLOPTTYPE_OBJECTPOINT 10000
-#define CURLOPTTYPE_FUNCTIONPOINT 20000
-#define CURLOPTTYPE_OFF_T 30000
-
-/* name is uppercase CURLOPT_<name>,
- type is one of the defined CURLOPTTYPE_<type>
- number is unique identifier */
-#ifdef CINIT
-#undef CINIT
-#endif
-
-#ifdef CURL_ISOCPP
-#define CINIT(name,type,number) CURLOPT_ ## name = CURLOPTTYPE_ ## type + number
-#else
-/* The macro "##" is ISO C, we assume pre-ISO C doesn't support it. */
-#define LONG CURLOPTTYPE_LONG
-#define OBJECTPOINT CURLOPTTYPE_OBJECTPOINT
-#define FUNCTIONPOINT CURLOPTTYPE_FUNCTIONPOINT
-#define OFF_T CURLOPTTYPE_OFF_T
-#define CINIT(name,type,number) CURLOPT_/**/name = type + number
-#endif
-
-/*
- * This macro-mania below setups the CURLOPT_[what] enum, to be used with
- * curl_easy_setopt(). The first argument in the CINIT() macro is the [what]
- * word.
- */
-
-typedef enum {
- /* This is the FILE * or void * the regular output should be written to. */
- CINIT(FILE, OBJECTPOINT, 1),
-
- /* The full URL to get/put */
- CINIT(URL, OBJECTPOINT, 2),
-
- /* Port number to connect to, if other than default. */
- CINIT(PORT, LONG, 3),
-
- /* Name of proxy to use. */
- CINIT(PROXY, OBJECTPOINT, 4),
-
- /* "name:password" to use when fetching. */
- CINIT(USERPWD, OBJECTPOINT, 5),
-
- /* "name:password" to use with proxy. */
- CINIT(PROXYUSERPWD, OBJECTPOINT, 6),
-
- /* Range to get, specified as an ASCII string. */
- CINIT(RANGE, OBJECTPOINT, 7),
-
- /* not used */
-
- /* Specified file stream to upload from (use as input): */
- CINIT(INFILE, OBJECTPOINT, 9),
-
- /* Buffer to receive error messages in, must be at least CURL_ERROR_SIZE
- * bytes big. If this is not used, error messages go to stderr instead: */
- CINIT(ERRORBUFFER, OBJECTPOINT, 10),
-
- /* Function that will be called to store the output (instead of fwrite). The
- * parameters will use fwrite() syntax, make sure to follow them. */
- CINIT(WRITEFUNCTION, FUNCTIONPOINT, 11),
-
- /* Function that will be called to read the input (instead of fread). The
- * parameters will use fread() syntax, make sure to follow them. */
- CINIT(READFUNCTION, FUNCTIONPOINT, 12),
-
- /* Time-out the read operation after this amount of seconds */
- CINIT(TIMEOUT, LONG, 13),
-
- /* If the CURLOPT_INFILE is used, this can be used to inform libcurl about
- * how large the file being sent really is. That allows better error
- * checking and better verifies that the upload was successful. -1 means
- * unknown size.
- *
- * For large file support, there is also a _LARGE version of the key
- * which takes an off_t type, allowing platforms with larger off_t
- * sizes to handle larger files. See below for INFILESIZE_LARGE.
- */
- CINIT(INFILESIZE, LONG, 14),
-
- /* POST static input fields. */
- CINIT(POSTFIELDS, OBJECTPOINT, 15),
-
- /* Set the referrer page (needed by some CGIs) */
- CINIT(REFERER, OBJECTPOINT, 16),
-
- /* Set the FTP PORT string (interface name, named or numerical IP address)
- Use i.e '-' to use default address. */
- CINIT(FTPPORT, OBJECTPOINT, 17),
-
- /* Set the User-Agent string (examined by some CGIs) */
- CINIT(USERAGENT, OBJECTPOINT, 18),
-
- /* If the download receives less than "low speed limit" bytes/second
- * during "low speed time" seconds, the operations is aborted.
- * You could i.e if you have a pretty high speed connection, abort if
- * it is less than 2000 bytes/sec during 20 seconds.
- */
-
- /* Set the "low speed limit" */
- CINIT(LOW_SPEED_LIMIT, LONG, 19),
-
- /* Set the "low speed time" */
- CINIT(LOW_SPEED_TIME, LONG, 20),
-
- /* Set the continuation offset.
- *
- * Note there is also a _LARGE version of this key which uses
- * off_t types, allowing for large file offsets on platforms which
- * use larger-than-32-bit off_t's. Look below for RESUME_FROM_LARGE.
- */
- CINIT(RESUME_FROM, LONG, 21),
-
- /* Set cookie in request: */
- CINIT(COOKIE, OBJECTPOINT, 22),
-
- /* This points to a linked list of headers, struct curl_slist kind */
- CINIT(HTTPHEADER, OBJECTPOINT, 23),
-
- /* This points to a linked list of post entries, struct curl_httppost */
- CINIT(HTTPPOST, OBJECTPOINT, 24),
-
- /* name of the file keeping your private SSL-certificate */
- CINIT(SSLCERT, OBJECTPOINT, 25),
-
- /* password for the SSL or SSH private key */
- CINIT(KEYPASSWD, OBJECTPOINT, 26),
-
- /* send TYPE parameter? */
- CINIT(CRLF, LONG, 27),
-
- /* send linked-list of QUOTE commands */
- CINIT(QUOTE, OBJECTPOINT, 28),
-
- /* send FILE * or void * to store headers to, if you use a callback it
- is simply passed to the callback unmodified */
- CINIT(WRITEHEADER, OBJECTPOINT, 29),
-
- /* point to a file to read the initial cookies from, also enables
- "cookie awareness" */
- CINIT(COOKIEFILE, OBJECTPOINT, 31),
-
- /* What version to specifically try to use.
- See CURL_SSLVERSION defines below. */
- CINIT(SSLVERSION, LONG, 32),
-
- /* What kind of HTTP time condition to use, see defines */
- CINIT(TIMECONDITION, LONG, 33),
-
- /* Time to use with the above condition. Specified in number of seconds
- since 1 Jan 1970 */
- CINIT(TIMEVALUE, LONG, 34),
-
- /* 35 = OBSOLETE */
-
- /* Custom request, for customizing the get command like
- HTTP: DELETE, TRACE and others
- FTP: to use a different list command
- */
- CINIT(CUSTOMREQUEST, OBJECTPOINT, 36),
-
- /* HTTP request, for odd commands like DELETE, TRACE and others */
- CINIT(STDERR, OBJECTPOINT, 37),
-
- /* 38 is not used */
-
- /* send linked-list of post-transfer QUOTE commands */
- CINIT(POSTQUOTE, OBJECTPOINT, 39),
-
- /* Pass a pointer to string of the output using full variable-replacement
- as described elsewhere. */
- CINIT(WRITEINFO, OBJECTPOINT, 40),
-
- CINIT(VERBOSE, LONG, 41), /* talk a lot */
- CINIT(HEADER, LONG, 42), /* throw the header out too */
- CINIT(NOPROGRESS, LONG, 43), /* shut off the progress meter */
- CINIT(NOBODY, LONG, 44), /* use HEAD to get http document */
- CINIT(FAILONERROR, LONG, 45), /* no output on http error codes >= 300 */
- CINIT(UPLOAD, LONG, 46), /* this is an upload */
- CINIT(POST, LONG, 47), /* HTTP POST method */
- CINIT(DIRLISTONLY, LONG, 48), /* return bare names when listing directories */
-
- CINIT(APPEND, LONG, 50), /* Append instead of overwrite on upload! */
-
- /* Specify whether to read the user+password from the .netrc or the URL.
- * This must be one of the CURL_NETRC_* enums below. */
- CINIT(NETRC, LONG, 51),
-
- CINIT(FOLLOWLOCATION, LONG, 52), /* use Location: Luke! */
-
- CINIT(TRANSFERTEXT, LONG, 53), /* transfer data in text/ASCII format */
- CINIT(PUT, LONG, 54), /* HTTP PUT */
-
- /* 55 = OBSOLETE */
-
- /* Function that will be called instead of the internal progress display
- * function. This function should be defined as the curl_progress_callback
- * prototype defines. */
- CINIT(PROGRESSFUNCTION, FUNCTIONPOINT, 56),
-
- /* Data passed to the progress callback */
- CINIT(PROGRESSDATA, OBJECTPOINT, 57),
-
- /* We want the referrer field set automatically when following locations */
- CINIT(AUTOREFERER, LONG, 58),
-
- /* Port of the proxy, can be set in the proxy string as well with:
- "[host]:[port]" */
- CINIT(PROXYPORT, LONG, 59),
-
- /* size of the POST input data, if strlen() is not good to use */
- CINIT(POSTFIELDSIZE, LONG, 60),
-
- /* tunnel non-http operations through a HTTP proxy */
- CINIT(HTTPPROXYTUNNEL, LONG, 61),
-
- /* Set the interface string to use as outgoing network interface */
- CINIT(INTERFACE, OBJECTPOINT, 62),
-
- /* Set the krb4/5 security level, this also enables krb4/5 awareness. This
- * is a string, 'clear', 'safe', 'confidential' or 'private'. If the string
- * is set but doesn't match one of these, 'private' will be used. */
- CINIT(KRBLEVEL, OBJECTPOINT, 63),
-
- /* Set if we should verify the peer in ssl handshake, set 1 to verify. */
- CINIT(SSL_VERIFYPEER, LONG, 64),
-
- /* The CApath or CAfile used to validate the peer certificate
- this option is used only if SSL_VERIFYPEER is true */
- CINIT(CAINFO, OBJECTPOINT, 65),
-
- /* 66 = OBSOLETE */
- /* 67 = OBSOLETE */
-
- /* Maximum number of http redirects to follow */
- CINIT(MAXREDIRS, LONG, 68),
-
- /* Pass a long set to 1 to get the date of the requested document (if
- possible)! Pass a zero to shut it off. */
- CINIT(FILETIME, LONG, 69),
-
- /* This points to a linked list of telnet options */
- CINIT(TELNETOPTIONS, OBJECTPOINT, 70),
-
- /* Max amount of cached alive connections */
- CINIT(MAXCONNECTS, LONG, 71),
-
- /* What policy to use when closing connections when the cache is filled
- up */
- CINIT(CLOSEPOLICY, LONG, 72),
-
- /* 73 = OBSOLETE */
-
- /* Set to explicitly use a new connection for the upcoming transfer.
- Do not use this unless you're absolutely sure of this, as it makes the
- operation slower and is less friendly for the network. */
- CINIT(FRESH_CONNECT, LONG, 74),
-
- /* Set to explicitly forbid the upcoming transfer's connection to be re-used
- when done. Do not use this unless you're absolutely sure of this, as it
- makes the operation slower and is less friendly for the network. */
- CINIT(FORBID_REUSE, LONG, 75),
-
- /* Set to a file name that contains random data for libcurl to use to
- seed the random engine when doing SSL connects. */
- CINIT(RANDOM_FILE, OBJECTPOINT, 76),
-
- /* Set to the Entropy Gathering Daemon socket pathname */
- CINIT(EGDSOCKET, OBJECTPOINT, 77),
-
- /* Time-out connect operations after this amount of seconds, if connects
- are OK within this time, then fine... This only aborts the connect
- phase. [Only works on unix-style/SIGALRM operating systems] */
- CINIT(CONNECTTIMEOUT, LONG, 78),
-
- /* Function that will be called to store headers (instead of fwrite). The
- * parameters will use fwrite() syntax, make sure to follow them. */
- CINIT(HEADERFUNCTION, FUNCTIONPOINT, 79),
-
- /* Set this to force the HTTP request to get back to GET. Only really usable
- if POST, PUT or a custom request have been used first.
- */
- CINIT(HTTPGET, LONG, 80),
-
- /* Set if we should verify the Common name from the peer certificate in ssl
- * handshake, set 1 to check existence, 2 to ensure that it matches the
- * provided hostname. */
- CINIT(SSL_VERIFYHOST, LONG, 81),
-
- /* Specify which file name to write all known cookies in after completed
- operation. Set file name to "-" (dash) to make it go to stdout. */
- CINIT(COOKIEJAR, OBJECTPOINT, 82),
-
- /* Specify which SSL ciphers to use */
- CINIT(SSL_CIPHER_LIST, OBJECTPOINT, 83),
-
- /* Specify which HTTP version to use! This must be set to one of the
- CURL_HTTP_VERSION* enums set below. */
- CINIT(HTTP_VERSION, LONG, 84),
-
- /* Specifically switch on or off the FTP engine's use of the EPSV command. By
- default, that one will always be attempted before the more traditional
- PASV command. */
- CINIT(FTP_USE_EPSV, LONG, 85),
-
- /* type of the file keeping your SSL-certificate ("DER", "PEM", "ENG") */
- CINIT(SSLCERTTYPE, OBJECTPOINT, 86),
-
- /* name of the file keeping your private SSL-key */
- CINIT(SSLKEY, OBJECTPOINT, 87),
-
- /* type of the file keeping your private SSL-key ("DER", "PEM", "ENG") */
- CINIT(SSLKEYTYPE, OBJECTPOINT, 88),
-
- /* crypto engine for the SSL-sub system */
- CINIT(SSLENGINE, OBJECTPOINT, 89),
-
- /* set the crypto engine for the SSL-sub system as default
- the param has no meaning...
- */
- CINIT(SSLENGINE_DEFAULT, LONG, 90),
-
- /* Non-zero value means to use the global dns cache */
- CINIT(DNS_USE_GLOBAL_CACHE, LONG, 91), /* To become OBSOLETE soon */
-
- /* DNS cache timeout */
- CINIT(DNS_CACHE_TIMEOUT, LONG, 92),
-
- /* send linked-list of pre-transfer QUOTE commands */
- CINIT(PREQUOTE, OBJECTPOINT, 93),
-
- /* set the debug function */
- CINIT(DEBUGFUNCTION, FUNCTIONPOINT, 94),
-
- /* set the data for the debug function */
- CINIT(DEBUGDATA, OBJECTPOINT, 95),
-
- /* mark this as start of a cookie session */
- CINIT(COOKIESESSION, LONG, 96),
-
- /* The CApath directory used to validate the peer certificate
- this option is used only if SSL_VERIFYPEER is true */
- CINIT(CAPATH, OBJECTPOINT, 97),
-
- /* Instruct libcurl to use a smaller receive buffer */
- CINIT(BUFFERSIZE, LONG, 98),
-
- /* Instruct libcurl to not use any signal/alarm handlers, even when using
- timeouts. This option is useful for multi-threaded applications.
- See libcurl-the-guide for more background information. */
- CINIT(NOSIGNAL, LONG, 99),
-
- /* Provide a CURLShare for mutexing non-ts data */
- CINIT(SHARE, OBJECTPOINT, 100),
-
- /* indicates type of proxy. accepted values are CURLPROXY_HTTP (default),
- CURLPROXY_SOCKS4, CURLPROXY_SOCKS4A and CURLPROXY_SOCKS5. */
- CINIT(PROXYTYPE, LONG, 101),
-
- /* Set the Accept-Encoding string. Use this to tell a server you would like
- the response to be compressed. */
- CINIT(ENCODING, OBJECTPOINT, 102),
-
- /* Set pointer to private data */
- CINIT(PRIVATE, OBJECTPOINT, 103),
-
- /* Set aliases for HTTP 200 in the HTTP Response header */
- CINIT(HTTP200ALIASES, OBJECTPOINT, 104),
-
- /* Continue to send authentication (user+password) when following locations,
- even when hostname changed. This can potentially send off the name
- and password to whatever host the server decides. */
- CINIT(UNRESTRICTED_AUTH, LONG, 105),
-
- /* Specifically switch on or off the FTP engine's use of the EPRT command ( it
- also disables the LPRT attempt). By default, those ones will always be
- attempted before the good old traditional PORT command. */
- CINIT(FTP_USE_EPRT, LONG, 106),
-
- /* Set this to a bitmask value to enable the particular authentications
- methods you like. Use this in combination with CURLOPT_USERPWD.
- Note that setting multiple bits may cause extra network round-trips. */
- CINIT(HTTPAUTH, LONG, 107),
-
- /* Set the ssl context callback function, currently only for OpenSSL ssl_ctx
- in second argument. The function must be matching the
- curl_ssl_ctx_callback proto. */
- CINIT(SSL_CTX_FUNCTION, FUNCTIONPOINT, 108),
-
- /* Set the userdata for the ssl context callback function's third
- argument */
- CINIT(SSL_CTX_DATA, OBJECTPOINT, 109),
-
- /* FTP Option that causes missing dirs to be created on the remote server.
- In 7.19.4 we introduced the convenience enums for this option using the
- CURLFTP_CREATE_DIR prefix.
- */
- CINIT(FTP_CREATE_MISSING_DIRS, LONG, 110),
-
- /* Set this to a bitmask value to enable the particular authentications
- methods you like. Use this in combination with CURLOPT_PROXYUSERPWD.
- Note that setting multiple bits may cause extra network round-trips. */
- CINIT(PROXYAUTH, LONG, 111),
-
- /* FTP option that changes the timeout, in seconds, associated with
- getting a response. This is different from transfer timeout time and
- essentially places a demand on the FTP server to acknowledge commands
- in a timely manner. */
- CINIT(FTP_RESPONSE_TIMEOUT, LONG, 112),
-#define CURLOPT_SERVER_RESPONSE_TIMEOUT CURLOPT_FTP_RESPONSE_TIMEOUT
-
- /* Set this option to one of the CURL_IPRESOLVE_* defines (see below) to
- tell libcurl to resolve names to those IP versions only. This only has
- affect on systems with support for more than one, i.e IPv4 _and_ IPv6. */
- CINIT(IPRESOLVE, LONG, 113),
-
- /* Set this option to limit the size of a file that will be downloaded from
- an HTTP or FTP server.
-
- Note there is also _LARGE version which adds large file support for
- platforms which have larger off_t sizes. See MAXFILESIZE_LARGE below. */
- CINIT(MAXFILESIZE, LONG, 114),
-
- /* See the comment for INFILESIZE above, but in short, specifies
- * the size of the file being uploaded. -1 means unknown.
- */
- CINIT(INFILESIZE_LARGE, OFF_T, 115),
-
- /* Sets the continuation offset. There is also a LONG version of this;
- * look above for RESUME_FROM.
- */
- CINIT(RESUME_FROM_LARGE, OFF_T, 116),
-
- /* Sets the maximum size of data that will be downloaded from
- * an HTTP or FTP server. See MAXFILESIZE above for the LONG version.
- */
- CINIT(MAXFILESIZE_LARGE, OFF_T, 117),
-
- /* Set this option to the file name of your .netrc file you want libcurl
- to parse (using the CURLOPT_NETRC option). If not set, libcurl will do
- a poor attempt to find the user's home directory and check for a .netrc
- file in there. */
- CINIT(NETRC_FILE, OBJECTPOINT, 118),
-
- /* Enable SSL/TLS for FTP, pick one of:
- CURLFTPSSL_TRY - try using SSL, proceed anyway otherwise
- CURLFTPSSL_CONTROL - SSL for the control connection or fail
- CURLFTPSSL_ALL - SSL for all communication or fail
- */
- CINIT(USE_SSL, LONG, 119),
-
- /* The _LARGE version of the standard POSTFIELDSIZE option */
- CINIT(POSTFIELDSIZE_LARGE, OFF_T, 120),
-
- /* Enable/disable the TCP Nagle algorithm */
- CINIT(TCP_NODELAY, LONG, 121),
-
- /* 122 OBSOLETE, used in 7.12.3. Gone in 7.13.0 */
- /* 123 OBSOLETE. Gone in 7.16.0 */
- /* 124 OBSOLETE, used in 7.12.3. Gone in 7.13.0 */
- /* 125 OBSOLETE, used in 7.12.3. Gone in 7.13.0 */
- /* 126 OBSOLETE, used in 7.12.3. Gone in 7.13.0 */
- /* 127 OBSOLETE. Gone in 7.16.0 */
- /* 128 OBSOLETE. Gone in 7.16.0 */
-
- /* When FTP over SSL/TLS is selected (with CURLOPT_USE_SSL), this option
- can be used to change libcurl's default action which is to first try
- "AUTH SSL" and then "AUTH TLS" in this order, and proceed when a OK
- response has been received.
-
- Available parameters are:
- CURLFTPAUTH_DEFAULT - let libcurl decide
- CURLFTPAUTH_SSL - try "AUTH SSL" first, then TLS
- CURLFTPAUTH_TLS - try "AUTH TLS" first, then SSL
- */
- CINIT(FTPSSLAUTH, LONG, 129),
-
- CINIT(IOCTLFUNCTION, FUNCTIONPOINT, 130),
- CINIT(IOCTLDATA, OBJECTPOINT, 131),
-
- /* 132 OBSOLETE. Gone in 7.16.0 */
- /* 133 OBSOLETE. Gone in 7.16.0 */
-
- /* zero terminated string for pass on to the FTP server when asked for
- "account" info */
- CINIT(FTP_ACCOUNT, OBJECTPOINT, 134),
-
- /* feed cookies into cookie engine */
- CINIT(COOKIELIST, OBJECTPOINT, 135),
-
- /* ignore Content-Length */
- CINIT(IGNORE_CONTENT_LENGTH, LONG, 136),
-
- /* Set to non-zero to skip the IP address received in a 227 PASV FTP server
- response. Typically used for FTP-SSL purposes but is not restricted to
- that. libcurl will then instead use the same IP address it used for the
- control connection. */
- CINIT(FTP_SKIP_PASV_IP, LONG, 137),
-
- /* Select "file method" to use when doing FTP, see the curl_ftpmethod
- above. */
- CINIT(FTP_FILEMETHOD, LONG, 138),
-
- /* Local port number to bind the socket to */
- CINIT(LOCALPORT, LONG, 139),
-
- /* Number of ports to try, including the first one set with LOCALPORT.
- Thus, setting it to 1 will make no additional attempts but the first.
- */
- CINIT(LOCALPORTRANGE, LONG, 140),
-
- /* no transfer, set up connection and let application use the socket by
- extracting it with CURLINFO_LASTSOCKET */
- CINIT(CONNECT_ONLY, LONG, 141),
-
- /* Function that will be called to convert from the
- network encoding (instead of using the iconv calls in libcurl) */
- CINIT(CONV_FROM_NETWORK_FUNCTION, FUNCTIONPOINT, 142),
-
- /* Function that will be called to convert to the
- network encoding (instead of using the iconv calls in libcurl) */
- CINIT(CONV_TO_NETWORK_FUNCTION, FUNCTIONPOINT, 143),
-
- /* Function that will be called to convert from UTF8
- (instead of using the iconv calls in libcurl)
- Note that this is used only for SSL certificate processing */
- CINIT(CONV_FROM_UTF8_FUNCTION, FUNCTIONPOINT, 144),
-
- /* if the connection proceeds too quickly then need to slow it down */
- /* limit-rate: maximum number of bytes per second to send or receive */
- CINIT(MAX_SEND_SPEED_LARGE, OFF_T, 145),
- CINIT(MAX_RECV_SPEED_LARGE, OFF_T, 146),
-
- /* Pointer to command string to send if USER/PASS fails. */
- CINIT(FTP_ALTERNATIVE_TO_USER, OBJECTPOINT, 147),
-
- /* callback function for setting socket options */
- CINIT(SOCKOPTFUNCTION, FUNCTIONPOINT, 148),
- CINIT(SOCKOPTDATA, OBJECTPOINT, 149),
-
- /* set to 0 to disable session ID re-use for this transfer, default is
- enabled (== 1) */
- CINIT(SSL_SESSIONID_CACHE, LONG, 150),
-
- /* allowed SSH authentication methods */
- CINIT(SSH_AUTH_TYPES, LONG, 151),
-
- /* Used by scp/sftp to do public/private key authentication */
- CINIT(SSH_PUBLIC_KEYFILE, OBJECTPOINT, 152),
- CINIT(SSH_PRIVATE_KEYFILE, OBJECTPOINT, 153),
-
- /* Send CCC (Clear Command Channel) after authentication */
- CINIT(FTP_SSL_CCC, LONG, 154),
-
- /* Same as TIMEOUT and CONNECTTIMEOUT, but with ms resolution */
- CINIT(TIMEOUT_MS, LONG, 155),
- CINIT(CONNECTTIMEOUT_MS, LONG, 156),
-
- /* set to zero to disable the libcurl's decoding and thus pass the raw body
- data to the application even when it is encoded/compressed */
- CINIT(HTTP_TRANSFER_DECODING, LONG, 157),
- CINIT(HTTP_CONTENT_DECODING, LONG, 158),
-
- /* Permission used when creating new files and directories on the remote
- server for protocols that support it, SFTP/SCP/FILE */
- CINIT(NEW_FILE_PERMS, LONG, 159),
- CINIT(NEW_DIRECTORY_PERMS, LONG, 160),
-
- /* Set the behaviour of POST when redirecting. Values must be set to one
- of CURL_REDIR* defines below. This used to be called CURLOPT_POST301 */
- CINIT(POSTREDIR, LONG, 161),
-
- /* used by scp/sftp to verify the host's public key */
- CINIT(SSH_HOST_PUBLIC_KEY_MD5, OBJECTPOINT, 162),
-
- /* Callback function for opening socket (instead of socket(2)). Optionally,
- callback is able change the address or refuse to connect returning
- CURL_SOCKET_BAD. The callback should have type
- curl_opensocket_callback */
- CINIT(OPENSOCKETFUNCTION, FUNCTIONPOINT, 163),
- CINIT(OPENSOCKETDATA, OBJECTPOINT, 164),
-
- /* POST volatile input fields. */
- CINIT(COPYPOSTFIELDS, OBJECTPOINT, 165),
-
- /* set transfer mode (;type=<a|i>) when doing FTP via an HTTP proxy */
- CINIT(PROXY_TRANSFER_MODE, LONG, 166),
-
- /* Callback function for seeking in the input stream */
- CINIT(SEEKFUNCTION, FUNCTIONPOINT, 167),
- CINIT(SEEKDATA, OBJECTPOINT, 168),
-
- /* CRL file */
- CINIT(CRLFILE, OBJECTPOINT, 169),
-
- /* Issuer certificate */
- CINIT(ISSUERCERT, OBJECTPOINT, 170),
-
- /* (IPv6) Address scope */
- CINIT(ADDRESS_SCOPE, LONG, 171),
-
- /* Collect certificate chain info and allow it to get retrievable with
- CURLINFO_CERTINFO after the transfer is complete. (Unfortunately) only
- working with OpenSSL-powered builds. */
- CINIT(CERTINFO, LONG, 172),
-
- /* "name" and "pwd" to use when fetching. */
- CINIT(USERNAME, OBJECTPOINT, 173),
- CINIT(PASSWORD, OBJECTPOINT, 174),
-
- /* "name" and "pwd" to use with Proxy when fetching. */
- CINIT(PROXYUSERNAME, OBJECTPOINT, 175),
- CINIT(PROXYPASSWORD, OBJECTPOINT, 176),
-
- /* Comma separated list of hostnames defining no-proxy zones. These should
- match both hostnames directly, and hostnames within a domain. For
- example, local.com will match local.com and www.local.com, but NOT
- notlocal.com or www.notlocal.com. For compatibility with other
- implementations of this, .local.com will be considered to be the same as
- local.com. A single * is the only valid wildcard, and effectively
- disables the use of proxy. */
- CINIT(NOPROXY, OBJECTPOINT, 177),
-
- /* block size for TFTP transfers */
- CINIT(TFTP_BLKSIZE, LONG, 178),
-
- /* Socks Service */
- CINIT(SOCKS5_GSSAPI_SERVICE, OBJECTPOINT, 179),
-
- /* Socks Service */
- CINIT(SOCKS5_GSSAPI_NEC, LONG, 180),
-
- /* set the bitmask for the protocols that are allowed to be used for the
- transfer, which thus helps the app which takes URLs from users or other
- external inputs and want to restrict what protocol(s) to deal
- with. Defaults to CURLPROTO_ALL. */
- CINIT(PROTOCOLS, LONG, 181),
-
- /* set the bitmask for the protocols that libcurl is allowed to follow to,
- as a subset of the CURLOPT_PROTOCOLS ones. That means the protocol needs
- to be set in both bitmasks to be allowed to get redirected to. Defaults
- to all protocols except FILE and SCP. */
- CINIT(REDIR_PROTOCOLS, LONG, 182),
-
- /* set the SSH knownhost file name to use */
- CINIT(SSH_KNOWNHOSTS, OBJECTPOINT, 183),
-
- /* set the SSH host key callback, must point to a curl_sshkeycallback
- function */
- CINIT(SSH_KEYFUNCTION, FUNCTIONPOINT, 184),
-
- /* set the SSH host key callback custom pointer */
- CINIT(SSH_KEYDATA, OBJECTPOINT, 185),
-
- /* set the SMTP mail originator */
- CINIT(MAIL_FROM, OBJECTPOINT, 186),
-
- /* set the SMTP mail receiver(s) */
- CINIT(MAIL_RCPT, OBJECTPOINT, 187),
-
- /* FTP: send PRET before PASV */
- CINIT(FTP_USE_PRET, LONG, 188),
-
- /* RTSP request method (OPTIONS, SETUP, PLAY, etc...) */
- CINIT(RTSP_REQUEST, LONG, 189),
-
- /* The RTSP session identifier */
- CINIT(RTSP_SESSION_ID, OBJECTPOINT, 190),
-
- /* The RTSP stream URI */
- CINIT(RTSP_STREAM_URI, OBJECTPOINT, 191),
-
- /* The Transport: header to use in RTSP requests */
- CINIT(RTSP_TRANSPORT, OBJECTPOINT, 192),
-
- /* Manually initialize the client RTSP CSeq for this handle */
- CINIT(RTSP_CLIENT_CSEQ, LONG, 193),
-
- /* Manually initialize the server RTSP CSeq for this handle */
- CINIT(RTSP_SERVER_CSEQ, LONG, 194),
-
- /* The stream to pass to INTERLEAVEFUNCTION. */
- CINIT(INTERLEAVEDATA, OBJECTPOINT, 195),
-
- /* Let the application define a custom write method for RTP data */
- CINIT(INTERLEAVEFUNCTION, FUNCTIONPOINT, 196),
-
- CURLOPT_LASTENTRY /* the last unused */
-} CURLoption;
-
-#ifndef CURL_NO_OLDIES /* define this to test if your app builds with all
- the obsolete stuff removed! */
-
-/* Backwards compatibility with older names */
-/* These are scheduled to disappear by 2011 */
-
-/* This was added in version 7.19.1 */
-#define CURLOPT_POST301 CURLOPT_POSTREDIR
-
-/* These are scheduled to disappear by 2009 */
-
-/* The following were added in 7.17.0 */
-#define CURLOPT_SSLKEYPASSWD CURLOPT_KEYPASSWD
-#define CURLOPT_FTPAPPEND CURLOPT_APPEND
-#define CURLOPT_FTPLISTONLY CURLOPT_DIRLISTONLY
-#define CURLOPT_FTP_SSL CURLOPT_USE_SSL
-
-/* The following were added earlier */
-
-#define CURLOPT_SSLCERTPASSWD CURLOPT_KEYPASSWD
-#define CURLOPT_KRB4LEVEL CURLOPT_KRBLEVEL
-
-#else
-/* This is set if CURL_NO_OLDIES is defined at compile-time */
-#undef CURLOPT_DNS_USE_GLOBAL_CACHE /* soon obsolete */
-#endif
-
-
- /* Below here follows defines for the CURLOPT_IPRESOLVE option. If a host
- name resolves addresses using more than one IP protocol version, this
- option might be handy to force libcurl to use a specific IP version. */
-#define CURL_IPRESOLVE_WHATEVER 0 /* default, resolves addresses to all IP
- versions that your system allows */
-#define CURL_IPRESOLVE_V4 1 /* resolve to ipv4 addresses */
-#define CURL_IPRESOLVE_V6 2 /* resolve to ipv6 addresses */
-
- /* three convenient "aliases" that follow the name scheme better */
-#define CURLOPT_WRITEDATA CURLOPT_FILE
-#define CURLOPT_READDATA CURLOPT_INFILE
-#define CURLOPT_HEADERDATA CURLOPT_WRITEHEADER
-#define CURLOPT_RTSPHEADER CURLOPT_HTTPHEADER
-
- /* These enums are for use with the CURLOPT_HTTP_VERSION option. */
-enum {
- CURL_HTTP_VERSION_NONE, /* setting this means we don't care, and that we'd
- like the library to choose the best possible
- for us! */
- CURL_HTTP_VERSION_1_0, /* please use HTTP 1.0 in the request */
- CURL_HTTP_VERSION_1_1, /* please use HTTP 1.1 in the request */
-
- CURL_HTTP_VERSION_LAST /* *ILLEGAL* http version */
-};
-
-/*
- * Public API enums for RTSP requests
- */
-enum {
- CURL_RTSPREQ_NONE, /* first in list */
- CURL_RTSPREQ_OPTIONS,
- CURL_RTSPREQ_DESCRIBE,
- CURL_RTSPREQ_ANNOUNCE,
- CURL_RTSPREQ_SETUP,
- CURL_RTSPREQ_PLAY,
- CURL_RTSPREQ_PAUSE,
- CURL_RTSPREQ_TEARDOWN,
- CURL_RTSPREQ_GET_PARAMETER,
- CURL_RTSPREQ_SET_PARAMETER,
- CURL_RTSPREQ_RECORD,
- CURL_RTSPREQ_RECEIVE,
- CURL_RTSPREQ_LAST /* last in list */
-};
-
- /* These enums are for use with the CURLOPT_NETRC option. */
-enum CURL_NETRC_OPTION {
- CURL_NETRC_IGNORED, /* The .netrc will never be read.
- * This is the default. */
- CURL_NETRC_OPTIONAL, /* A user:password in the URL will be preferred
- * to one in the .netrc. */
- CURL_NETRC_REQUIRED, /* A user:password in the URL will be ignored.
- * Unless one is set programmatically, the .netrc
- * will be queried. */
- CURL_NETRC_LAST
-};
-
-enum {
- CURL_SSLVERSION_DEFAULT,
- CURL_SSLVERSION_TLSv1,
- CURL_SSLVERSION_SSLv2,
- CURL_SSLVERSION_SSLv3,
-
- CURL_SSLVERSION_LAST /* never use, keep last */
-};
-
-/* symbols to use with CURLOPT_POSTREDIR.
- CURL_REDIR_POST_301 and CURL_REDIR_POST_302 can be bitwise ORed so that
- CURL_REDIR_POST_301 | CURL_REDIR_POST_302 == CURL_REDIR_POST_ALL */
-
-#define CURL_REDIR_GET_ALL 0
-#define CURL_REDIR_POST_301 1
-#define CURL_REDIR_POST_302 2
-#define CURL_REDIR_POST_ALL (CURL_REDIR_POST_301|CURL_REDIR_POST_302)
-
-typedef enum {
- CURL_TIMECOND_NONE,
-
- CURL_TIMECOND_IFMODSINCE,
- CURL_TIMECOND_IFUNMODSINCE,
- CURL_TIMECOND_LASTMOD,
-
- CURL_TIMECOND_LAST
-} curl_TimeCond;
-
-
-/* curl_strequal() and curl_strnequal() are subject for removal in a future
- libcurl, see lib/README.curlx for details */
-CURL_EXTERN int (curl_strequal)(const char *s1, const char *s2);
-CURL_EXTERN int (curl_strnequal)(const char *s1, const char *s2, size_t n);
-
-/* name is uppercase CURLFORM_<name> */
-#ifdef CFINIT
-#undef CFINIT
-#endif
-
-#ifdef CURL_ISOCPP
-#define CFINIT(name) CURLFORM_ ## name
-#else
-/* The macro "##" is ISO C, we assume pre-ISO C doesn't support it. */
-#define CFINIT(name) CURLFORM_/**/name
-#endif
-
-typedef enum {
- CFINIT(NOTHING), /********* the first one is unused ************/
-
- /* */
- CFINIT(COPYNAME),
- CFINIT(PTRNAME),
- CFINIT(NAMELENGTH),
- CFINIT(COPYCONTENTS),
- CFINIT(PTRCONTENTS),
- CFINIT(CONTENTSLENGTH),
- CFINIT(FILECONTENT),
- CFINIT(ARRAY),
- CFINIT(OBSOLETE),
- CFINIT(FILE),
-
- CFINIT(BUFFER),
- CFINIT(BUFFERPTR),
- CFINIT(BUFFERLENGTH),
-
- CFINIT(CONTENTTYPE),
- CFINIT(CONTENTHEADER),
- CFINIT(FILENAME),
- CFINIT(END),
- CFINIT(OBSOLETE2),
-
- CFINIT(STREAM),
-
- CURLFORM_LASTENTRY /* the last unused */
-} CURLformoption;
-
-#undef CFINIT /* done */
-
-/* structure to be used as parameter for CURLFORM_ARRAY */
-struct curl_forms {
- CURLformoption option;
- const char *value;
-};
-
-/* use this for multipart formpost building */
-/* Returns code for curl_formadd()
- *
- * Returns:
- * CURL_FORMADD_OK on success
- * CURL_FORMADD_MEMORY if the FormInfo allocation fails
- * CURL_FORMADD_OPTION_TWICE if one option is given twice for one Form
- * CURL_FORMADD_NULL if a null pointer was given for a char
- * CURL_FORMADD_MEMORY if the allocation of a FormInfo struct failed
- * CURL_FORMADD_UNKNOWN_OPTION if an unknown option was used
- * CURL_FORMADD_INCOMPLETE if the some FormInfo is not complete (or error)
- * CURL_FORMADD_MEMORY if a curl_httppost struct cannot be allocated
- * CURL_FORMADD_MEMORY if some allocation for string copying failed.
- * CURL_FORMADD_ILLEGAL_ARRAY if an illegal option is used in an array
- *
- ***************************************************************************/
-typedef enum {
- CURL_FORMADD_OK, /* first, no error */
-
- CURL_FORMADD_MEMORY,
- CURL_FORMADD_OPTION_TWICE,
- CURL_FORMADD_NULL,
- CURL_FORMADD_UNKNOWN_OPTION,
- CURL_FORMADD_INCOMPLETE,
- CURL_FORMADD_ILLEGAL_ARRAY,
- CURL_FORMADD_DISABLED, /* libcurl was built with this disabled */
-
- CURL_FORMADD_LAST /* last */
-} CURLFORMcode;
-
-/*
- * NAME curl_formadd()
- *
- * DESCRIPTION
- *
- * Pretty advanced function for building multi-part formposts. Each invoke
- * adds one part that together construct a full post. Then use
- * CURLOPT_HTTPPOST to send it off to libcurl.
- */
-CURL_EXTERN CURLFORMcode curl_formadd(struct curl_httppost **httppost,
- struct curl_httppost **last_post,
- ...);
-
-/*
- * callback function for curl_formget()
- * The void *arg pointer will be the one passed as second argument to
- * curl_formget().
- * The character buffer passed to it must not be freed.
- * Should return the buffer length passed to it as the argument "len" on
- * success.
- */
-typedef size_t (*curl_formget_callback)(void *arg, const char *buf, size_t len);
-
-/*
- * NAME curl_formget()
- *
- * DESCRIPTION
- *
- * Serialize a curl_httppost struct built with curl_formadd().
- * Accepts a void pointer as second argument which will be passed to
- * the curl_formget_callback function.
- * Returns 0 on success.
- */
-CURL_EXTERN int curl_formget(struct curl_httppost *form, void *arg,
- curl_formget_callback append);
-/*
- * NAME curl_formfree()
- *
- * DESCRIPTION
- *
- * Free a multipart formpost previously built with curl_formadd().
- */
-CURL_EXTERN void curl_formfree(struct curl_httppost *form);
-
-/*
- * NAME curl_getenv()
- *
- * DESCRIPTION
- *
- * Returns a malloc()'ed string that MUST be curl_free()ed after usage is
- * complete. DEPRECATED - see lib/README.curlx
- */
-CURL_EXTERN char *curl_getenv(const char *variable);
-
-/*
- * NAME curl_version()
- *
- * DESCRIPTION
- *
- * Returns a static ascii string of the libcurl version.
- */
-CURL_EXTERN char *curl_version(void);
-
-/*
- * NAME curl_easy_escape()
- *
- * DESCRIPTION
- *
- * Escapes URL strings (converts all letters consider illegal in URLs to their
- * %XX versions). This function returns a new allocated string or NULL if an
- * error occurred.
- */
-CURL_EXTERN char *curl_easy_escape(CURL *handle,
- const char *string,
- int length);
-
-/* the previous version: */
-CURL_EXTERN char *curl_escape(const char *string,
- int length);
-
-
-/*
- * NAME curl_easy_unescape()
- *
- * DESCRIPTION
- *
- * Unescapes URL encoding in strings (converts all %XX codes to their 8bit
- * versions). This function returns a new allocated string or NULL if an error
- * occurred.
- * Conversion Note: On non-ASCII platforms the ASCII %XX codes are
- * converted into the host encoding.
- */
-CURL_EXTERN char *curl_easy_unescape(CURL *handle,
- const char *string,
- int length,
- int *outlength);
-
-/* the previous version */
-CURL_EXTERN char *curl_unescape(const char *string,
- int length);
-
-/*
- * NAME curl_free()
- *
- * DESCRIPTION
- *
- * Provided for de-allocation in the same translation unit that did the
- * allocation. Added in libcurl 7.10
- */
-CURL_EXTERN void curl_free(void *p);
-
-/*
- * NAME curl_global_init()
- *
- * DESCRIPTION
- *
- * curl_global_init() should be invoked exactly once for each application that
- * uses libcurl and before any call of other libcurl functions.
- *
- * This function is not thread-safe!
- */
-CURL_EXTERN CURLcode curl_global_init(long flags);
-
-/*
- * NAME curl_global_init_mem()
- *
- * DESCRIPTION
- *
- * curl_global_init() or curl_global_init_mem() should be invoked exactly once
- * for each application that uses libcurl. This function can be used to
- * initialize libcurl and set user defined memory management callback
- * functions. Users can implement memory management routines to check for
- * memory leaks, check for mis-use of the curl library etc. User registered
- * callback routines with be invoked by this library instead of the system
- * memory management routines like malloc, free etc.
- */
-CURL_EXTERN CURLcode curl_global_init_mem(long flags,
- curl_malloc_callback m,
- curl_free_callback f,
- curl_realloc_callback r,
- curl_strdup_callback s,
- curl_calloc_callback c);
-
-/*
- * NAME curl_global_cleanup()
- *
- * DESCRIPTION
- *
- * curl_global_cleanup() should be invoked exactly once for each application
- * that uses libcurl
- */
-CURL_EXTERN void curl_global_cleanup(void);
-
-/* linked-list structure for the CURLOPT_QUOTE option (and other) */
-struct curl_slist {
- char *data;
- struct curl_slist *next;
-};
-
-/*
- * NAME curl_slist_append()
- *
- * DESCRIPTION
- *
- * Appends a string to a linked list. If no list exists, it will be created
- * first. Returns the new list, after appending.
- */
-CURL_EXTERN struct curl_slist *curl_slist_append(struct curl_slist *,
- const char *);
-
-/*
- * NAME curl_slist_free_all()
- *
- * DESCRIPTION
- *
- * free a previously built curl_slist.
- */
-CURL_EXTERN void curl_slist_free_all(struct curl_slist *);
-
-/*
- * NAME curl_getdate()
- *
- * DESCRIPTION
- *
- * Returns the time, in seconds since 1 Jan 1970 of the time string given in
- * the first argument. The time argument in the second parameter is unused
- * and should be set to NULL.
- */
-CURL_EXTERN time_t curl_getdate(const char *p, const time_t *unused);
-
-/* info about the certificate chain, only for OpenSSL builds. Asked
- for with CURLOPT_CERTINFO / CURLINFO_CERTINFO */
-struct curl_certinfo {
- int num_of_certs; /* number of certificates with information */
- struct curl_slist **certinfo; /* for each index in this array, there's a
- linked list with textual information in the
- format "name: value" */
-};
-
-#define CURLINFO_STRING 0x100000
-#define CURLINFO_LONG 0x200000
-#define CURLINFO_DOUBLE 0x300000
-#define CURLINFO_SLIST 0x400000
-#define CURLINFO_MASK 0x0fffff
-#define CURLINFO_TYPEMASK 0xf00000
-
-typedef enum {
- CURLINFO_NONE, /* first, never use this */
- CURLINFO_EFFECTIVE_URL = CURLINFO_STRING + 1,
- CURLINFO_RESPONSE_CODE = CURLINFO_LONG + 2,
- CURLINFO_TOTAL_TIME = CURLINFO_DOUBLE + 3,
- CURLINFO_NAMELOOKUP_TIME = CURLINFO_DOUBLE + 4,
- CURLINFO_CONNECT_TIME = CURLINFO_DOUBLE + 5,
- CURLINFO_PRETRANSFER_TIME = CURLINFO_DOUBLE + 6,
- CURLINFO_SIZE_UPLOAD = CURLINFO_DOUBLE + 7,
- CURLINFO_SIZE_DOWNLOAD = CURLINFO_DOUBLE + 8,
- CURLINFO_SPEED_DOWNLOAD = CURLINFO_DOUBLE + 9,
- CURLINFO_SPEED_UPLOAD = CURLINFO_DOUBLE + 10,
- CURLINFO_HEADER_SIZE = CURLINFO_LONG + 11,
- CURLINFO_REQUEST_SIZE = CURLINFO_LONG + 12,
- CURLINFO_SSL_VERIFYRESULT = CURLINFO_LONG + 13,
- CURLINFO_FILETIME = CURLINFO_LONG + 14,
- CURLINFO_CONTENT_LENGTH_DOWNLOAD = CURLINFO_DOUBLE + 15,
- CURLINFO_CONTENT_LENGTH_UPLOAD = CURLINFO_DOUBLE + 16,
- CURLINFO_STARTTRANSFER_TIME = CURLINFO_DOUBLE + 17,
- CURLINFO_CONTENT_TYPE = CURLINFO_STRING + 18,
- CURLINFO_REDIRECT_TIME = CURLINFO_DOUBLE + 19,
- CURLINFO_REDIRECT_COUNT = CURLINFO_LONG + 20,
- CURLINFO_PRIVATE = CURLINFO_STRING + 21,
- CURLINFO_HTTP_CONNECTCODE = CURLINFO_LONG + 22,
- CURLINFO_HTTPAUTH_AVAIL = CURLINFO_LONG + 23,
- CURLINFO_PROXYAUTH_AVAIL = CURLINFO_LONG + 24,
- CURLINFO_OS_ERRNO = CURLINFO_LONG + 25,
- CURLINFO_NUM_CONNECTS = CURLINFO_LONG + 26,
- CURLINFO_SSL_ENGINES = CURLINFO_SLIST + 27,
- CURLINFO_COOKIELIST = CURLINFO_SLIST + 28,
- CURLINFO_LASTSOCKET = CURLINFO_LONG + 29,
- CURLINFO_FTP_ENTRY_PATH = CURLINFO_STRING + 30,
- CURLINFO_REDIRECT_URL = CURLINFO_STRING + 31,
- CURLINFO_PRIMARY_IP = CURLINFO_STRING + 32,
- CURLINFO_APPCONNECT_TIME = CURLINFO_DOUBLE + 33,
- CURLINFO_CERTINFO = CURLINFO_SLIST + 34,
- CURLINFO_CONDITION_UNMET = CURLINFO_LONG + 35,
- CURLINFO_RTSP_SESSION_ID = CURLINFO_STRING + 36,
- CURLINFO_RTSP_CLIENT_CSEQ = CURLINFO_LONG + 37,
- CURLINFO_RTSP_SERVER_CSEQ = CURLINFO_LONG + 38,
- CURLINFO_RTSP_CSEQ_RECV = CURLINFO_LONG + 39,
- /* Fill in new entries below here! */
-
- CURLINFO_LASTONE = 39
-} CURLINFO;
-
-/* CURLINFO_RESPONSE_CODE is the new name for the option previously known as
- CURLINFO_HTTP_CODE */
-#define CURLINFO_HTTP_CODE CURLINFO_RESPONSE_CODE
-
-typedef enum {
- CURLCLOSEPOLICY_NONE, /* first, never use this */
-
- CURLCLOSEPOLICY_OLDEST,
- CURLCLOSEPOLICY_LEAST_RECENTLY_USED,
- CURLCLOSEPOLICY_LEAST_TRAFFIC,
- CURLCLOSEPOLICY_SLOWEST,
- CURLCLOSEPOLICY_CALLBACK,
-
- CURLCLOSEPOLICY_LAST /* last, never use this */
-} curl_closepolicy;
-
-#define CURL_GLOBAL_SSL (1<<0)
-#define CURL_GLOBAL_WIN32 (1<<1)
-#define CURL_GLOBAL_ALL (CURL_GLOBAL_SSL|CURL_GLOBAL_WIN32)
-#define CURL_GLOBAL_NOTHING 0
-#define CURL_GLOBAL_DEFAULT CURL_GLOBAL_ALL
-
-
-/*****************************************************************************
- * Setup defines, protos etc for the sharing stuff.
- */
-
-/* Different data locks for a single share */
-typedef enum {
- CURL_LOCK_DATA_NONE = 0,
- /* CURL_LOCK_DATA_SHARE is used internally to say that
- * the locking is just made to change the internal state of the share
- * itself.
- */
- CURL_LOCK_DATA_SHARE,
- CURL_LOCK_DATA_COOKIE,
- CURL_LOCK_DATA_DNS,
- CURL_LOCK_DATA_SSL_SESSION,
- CURL_LOCK_DATA_CONNECT,
- CURL_LOCK_DATA_LAST
-} curl_lock_data;
-
-/* Different lock access types */
-typedef enum {
- CURL_LOCK_ACCESS_NONE = 0, /* unspecified action */
- CURL_LOCK_ACCESS_SHARED = 1, /* for read perhaps */
- CURL_LOCK_ACCESS_SINGLE = 2, /* for write perhaps */
- CURL_LOCK_ACCESS_LAST /* never use */
-} curl_lock_access;
-
-typedef void (*curl_lock_function)(CURL *handle,
- curl_lock_data data,
- curl_lock_access locktype,
- void *userptr);
-typedef void (*curl_unlock_function)(CURL *handle,
- curl_lock_data data,
- void *userptr);
-
-typedef void CURLSH;
-
-typedef enum {
- CURLSHE_OK, /* all is fine */
- CURLSHE_BAD_OPTION, /* 1 */
- CURLSHE_IN_USE, /* 2 */
- CURLSHE_INVALID, /* 3 */
- CURLSHE_NOMEM, /* out of memory */
- CURLSHE_LAST /* never use */
-} CURLSHcode;
-
-typedef enum {
- CURLSHOPT_NONE, /* don't use */
- CURLSHOPT_SHARE, /* specify a data type to share */
- CURLSHOPT_UNSHARE, /* specify which data type to stop sharing */
- CURLSHOPT_LOCKFUNC, /* pass in a 'curl_lock_function' pointer */
- CURLSHOPT_UNLOCKFUNC, /* pass in a 'curl_unlock_function' pointer */
- CURLSHOPT_USERDATA, /* pass in a user data pointer used in the lock/unlock
- callback functions */
- CURLSHOPT_LAST /* never use */
-} CURLSHoption;
-
-CURL_EXTERN CURLSH *curl_share_init(void);
-CURL_EXTERN CURLSHcode curl_share_setopt(CURLSH *, CURLSHoption option, ...);
-CURL_EXTERN CURLSHcode curl_share_cleanup(CURLSH *);
-
-/****************************************************************************
- * Structures for querying information about the curl library at runtime.
- */
-
-typedef enum {
- CURLVERSION_FIRST,
- CURLVERSION_SECOND,
- CURLVERSION_THIRD,
- CURLVERSION_FOURTH,
- CURLVERSION_LAST /* never actually use this */
-} CURLversion;
-
-/* The 'CURLVERSION_NOW' is the symbolic name meant to be used by
- basically all programs ever that want to get version information. It is
- meant to be a built-in version number for what kind of struct the caller
- expects. If the struct ever changes, we redefine the NOW to another enum
- from above. */
-#define CURLVERSION_NOW CURLVERSION_FOURTH
-
-typedef struct {
- CURLversion age; /* age of the returned struct */
- const char *version; /* LIBCURL_VERSION */
- unsigned int version_num; /* LIBCURL_VERSION_NUM */
- const char *host; /* OS/host/cpu/machine when configured */
- int features; /* bitmask, see defines below */
- const char *ssl_version; /* human readable string */
- long ssl_version_num; /* not used anymore, always 0 */
- const char *libz_version; /* human readable string */
- /* protocols is terminated by an entry with a NULL protoname */
- const char * const *protocols;
-
- /* The fields below this were added in CURLVERSION_SECOND */
- const char *ares;
- int ares_num;
-
- /* This field was added in CURLVERSION_THIRD */
- const char *libidn;
-
- /* These field were added in CURLVERSION_FOURTH */
-
- /* Same as '_libiconv_version' if built with HAVE_ICONV */
- int iconv_ver_num;
-
- const char *libssh_version; /* human readable string */
-
-} curl_version_info_data;
-
-#define CURL_VERSION_IPV6 (1<<0) /* IPv6-enabled */
-#define CURL_VERSION_KERBEROS4 (1<<1) /* kerberos auth is supported */
-#define CURL_VERSION_SSL (1<<2) /* SSL options are present */
-#define CURL_VERSION_LIBZ (1<<3) /* libz features are present */
-#define CURL_VERSION_NTLM (1<<4) /* NTLM auth is supported */
-#define CURL_VERSION_GSSNEGOTIATE (1<<5) /* Negotiate auth support */
-#define CURL_VERSION_DEBUG (1<<6) /* built with debug capabilities */
-#define CURL_VERSION_ASYNCHDNS (1<<7) /* asynchronous dns resolves */
-#define CURL_VERSION_SPNEGO (1<<8) /* SPNEGO auth */
-#define CURL_VERSION_LARGEFILE (1<<9) /* supports files bigger than 2GB */
-#define CURL_VERSION_IDN (1<<10) /* International Domain Names support */
-#define CURL_VERSION_SSPI (1<<11) /* SSPI is supported */
-#define CURL_VERSION_CONV (1<<12) /* character conversions supported */
-#define CURL_VERSION_CURLDEBUG (1<<13) /* debug memory tracking supported */
-
-/*
- * NAME curl_version_info()
- *
- * DESCRIPTION
- *
- * This function returns a pointer to a static copy of the version info
- * struct. See above.
- */
-CURL_EXTERN curl_version_info_data *curl_version_info(CURLversion);
-
-/*
- * NAME curl_easy_strerror()
- *
- * DESCRIPTION
- *
- * The curl_easy_strerror function may be used to turn a CURLcode value
- * into the equivalent human readable error string. This is useful
- * for printing meaningful error messages.
- */
-CURL_EXTERN const char *curl_easy_strerror(CURLcode);
-
-/*
- * NAME curl_share_strerror()
- *
- * DESCRIPTION
- *
- * The curl_share_strerror function may be used to turn a CURLSHcode value
- * into the equivalent human readable error string. This is useful
- * for printing meaningful error messages.
- */
-CURL_EXTERN const char *curl_share_strerror(CURLSHcode);
-
-/*
- * NAME curl_easy_pause()
- *
- * DESCRIPTION
- *
- * The curl_easy_pause function pauses or unpauses transfers. Select the new
- * state by setting the bitmask, use the convenience defines below.
- *
- */
-CURL_EXTERN CURLcode curl_easy_pause(CURL *handle, int bitmask);
-
-#define CURLPAUSE_RECV (1<<0)
-#define CURLPAUSE_RECV_CONT (0)
-
-#define CURLPAUSE_SEND (1<<2)
-#define CURLPAUSE_SEND_CONT (0)
-
-#define CURLPAUSE_ALL (CURLPAUSE_RECV|CURLPAUSE_SEND)
-#define CURLPAUSE_CONT (CURLPAUSE_RECV_CONT|CURLPAUSE_SEND_CONT)
-
-#ifdef __cplusplus
-}
-#endif
-
-/* unfortunately, the easy.h and multi.h include files need options and info
- stuff before they can be included! */
-#include "easy.h" /* nothing in curl is fun without the easy stuff */
-#include "multi.h"
-
-/* the typechecker doesn't work in C++ (yet) */
-#if defined(__GNUC__) && defined(__GNUC_MINOR__) && \
- ((__GNUC__ > 4) || (__GNUC__ == 4 && __GNUC_MINOR__ >= 3)) && \
- !defined(__cplusplus) && !defined(CURL_DISABLE_TYPECHECK)
-#include "typecheck-gcc.h"
-#else
-#if defined(__STDC__) && (__STDC__ >= 1)
-/* This preprocessor magic that replaces a call with the exact same call is
- only done to make sure application authors pass exactly three arguments
- to these functions. */
-#define curl_easy_setopt(handle,opt,param) curl_easy_setopt(handle,opt,param)
-#define curl_easy_getinfo(handle,info,arg) curl_easy_getinfo(handle,info,arg)
-#define curl_share_setopt(share,opt,param) curl_share_setopt(share,opt,param)
-#define curl_multi_setopt(handle,opt,param) curl_multi_setopt(handle,opt,param)
-#endif /* __STDC__ >= 1 */
-#endif /* gcc >= 4.3 && !__cplusplus */
-
-#endif /* __CURL_CURL_H */
diff --git a/src/utils/curl/curlbuild.h b/src/utils/curl/curlbuild.h
deleted file mode 100644
index d0b32acbec47fb148136d2368b0d0d783b5212e7..0000000000000000000000000000000000000000
--- a/src/utils/curl/curlbuild.h
+++ /dev/null
@@ -1,583 +0,0 @@
-#ifndef __CURL_CURLBUILD_H
-#define __CURL_CURLBUILD_H
-/***************************************************************************
- * _ _ ____ _
- * Project ___| | | | _ \| |
- * / __| | | | |_) | |
- * | (__| |_| | _ <| |___
- * \___|\___/|_| \_\_____|
- *
- * Copyright (C) 1998 - 2010, Daniel Stenberg, <daniel@haxx.se>, et al.
- *
- * This software is licensed as described in the file COPYING, which
- * you should have received as part of this distribution. The terms
- * are also available at http://curl.haxx.se/docs/copyright.html.
- *
- * You may opt to use, copy, modify, merge, publish, distribute and/or sell
- * copies of the Software, and permit persons to whom the Software is
- * furnished to do so, under the terms of the COPYING file.
- *
- * This software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY
- * KIND, either express or implied.
- *
- ***************************************************************************/
-
-/* ================================================================ */
-/* NOTES FOR CONFIGURE CAPABLE SYSTEMS */
-/* ================================================================ */
-
-/*
- * NOTE 1:
- * -------
- *
- * See file include/curl/curlbuild.h.in, run configure, and forget
- * that this file exists it is only used for non-configure systems.
- * But you can keep reading if you want ;-)
- *
- */
-
-/* ================================================================ */
-/* NOTES FOR NON-CONFIGURE SYSTEMS */
-/* ================================================================ */
-
-/*
- * NOTE 1:
- * -------
- *
- * Nothing in this file is intended to be modified or adjusted by the
- * curl library user nor by the curl library builder.
- *
- * If you think that something actually needs to be changed, adjusted
- * or fixed in this file, then, report it on the libcurl development
- * mailing list: http://cool.haxx.se/mailman/listinfo/curl-library/
- *
- * Try to keep one section per platform, compiler and architecture,
- * otherwise, if an existing section is reused for a different one and
- * later on the original is adjusted, probably the piggybacking one can
- * be adversely changed.
- *
- * In order to differentiate between platforms/compilers/architectures
- * use only compiler built in predefined preprocessor symbols.
- *
- * This header file shall only export symbols which are 'curl' or 'CURL'
- * prefixed, otherwise public name space would be polluted.
- *
- * NOTE 2:
- * -------
- *
- * For any given platform/compiler curl_off_t must be typedef'ed to a
- * 64-bit wide signed integral data type. The width of this data type
- * must remain constant and independent of any possible large file
- * support settings.
- *
- * As an exception to the above, curl_off_t shall be typedef'ed to a
- * 32-bit wide signed integral data type if there is no 64-bit type.
- *
- * As a general rule, curl_off_t shall not be mapped to off_t. This
- * rule shall only be violated if off_t is the only 64-bit data type
- * available and the size of off_t is independent of large file support
- * settings. Keep your build on the safe side avoiding an off_t gating.
- * If you have a 64-bit off_t then take for sure that another 64-bit
- * data type exists, dig deeper and you will find it.
- *
- * NOTE 3:
- * -------
- *
- * Right now you might be staring at file include/curl/curlbuild.h.dist or
- * at file include/curl/curlbuild.h, this is due to the following reason:
- * file include/curl/curlbuild.h.dist is renamed to include/curl/curlbuild.h
- * when the libcurl source code distribution archive file is created.
- *
- * File include/curl/curlbuild.h.dist is not included in the distribution
- * archive. File include/curl/curlbuild.h is not present in the git tree.
- *
- * The distributed include/curl/curlbuild.h file is only intended to be used
- * on systems which can not run the also distributed configure script.
- *
- * On systems capable of running the configure script, the configure process
- * will overwrite the distributed include/curl/curlbuild.h file with one that
- * is suitable and specific to the library being configured and built, which
- * is generated from the include/curl/curlbuild.h.in template file.
- *
- * If you check out from git on a non-configure platform, you must run the
- * appropriate buildconf* script to set up curlbuild.h and other local files.
- *
- */
-
-/* ================================================================ */
-/* DEFINITION OF THESE SYMBOLS SHALL NOT TAKE PLACE ANYWHERE ELSE */
-/* ================================================================ */
-
-#ifdef CURL_SIZEOF_LONG
-# error "CURL_SIZEOF_LONG shall not be defined except in curlbuild.h"
- Error Compilation_aborted_CURL_SIZEOF_LONG_already_defined
-#endif
-
-#ifdef CURL_TYPEOF_CURL_SOCKLEN_T
-# error "CURL_TYPEOF_CURL_SOCKLEN_T shall not be defined except in curlbuild.h"
- Error Compilation_aborted_CURL_TYPEOF_CURL_SOCKLEN_T_already_defined
-#endif
-
-#ifdef CURL_SIZEOF_CURL_SOCKLEN_T
-# error "CURL_SIZEOF_CURL_SOCKLEN_T shall not be defined except in curlbuild.h"
- Error Compilation_aborted_CURL_SIZEOF_CURL_SOCKLEN_T_already_defined
-#endif
-
-#ifdef CURL_TYPEOF_CURL_OFF_T
-# error "CURL_TYPEOF_CURL_OFF_T shall not be defined except in curlbuild.h"
- Error Compilation_aborted_CURL_TYPEOF_CURL_OFF_T_already_defined
-#endif
-
-#ifdef CURL_FORMAT_CURL_OFF_T
-# error "CURL_FORMAT_CURL_OFF_T shall not be defined except in curlbuild.h"
- Error Compilation_aborted_CURL_FORMAT_CURL_OFF_T_already_defined
-#endif
-
-#ifdef CURL_FORMAT_CURL_OFF_TU
-# error "CURL_FORMAT_CURL_OFF_TU shall not be defined except in curlbuild.h"
- Error Compilation_aborted_CURL_FORMAT_CURL_OFF_TU_already_defined
-#endif
-
-#ifdef CURL_FORMAT_OFF_T
-# error "CURL_FORMAT_OFF_T shall not be defined except in curlbuild.h"
- Error Compilation_aborted_CURL_FORMAT_OFF_T_already_defined
-#endif
-
-#ifdef CURL_SIZEOF_CURL_OFF_T
-# error "CURL_SIZEOF_CURL_OFF_T shall not be defined except in curlbuild.h"
- Error Compilation_aborted_CURL_SIZEOF_CURL_OFF_T_already_defined
-#endif
-
-#ifdef CURL_SUFFIX_CURL_OFF_T
-# error "CURL_SUFFIX_CURL_OFF_T shall not be defined except in curlbuild.h"
- Error Compilation_aborted_CURL_SUFFIX_CURL_OFF_T_already_defined
-#endif
-
-#ifdef CURL_SUFFIX_CURL_OFF_TU
-# error "CURL_SUFFIX_CURL_OFF_TU shall not be defined except in curlbuild.h"
- Error Compilation_aborted_CURL_SUFFIX_CURL_OFF_TU_already_defined
-#endif
-
-/* ================================================================ */
-/* EXTERNAL INTERFACE SETTINGS FOR NON-CONFIGURE SYSTEMS ONLY */
-/* ================================================================ */
-
-#if defined(__DJGPP__) || defined(__GO32__)
-# if defined(__DJGPP__) && (__DJGPP__ > 1)
-# define CURL_SIZEOF_LONG 4
-# define CURL_TYPEOF_CURL_OFF_T long long
-# define CURL_FORMAT_CURL_OFF_T "lld"
-# define CURL_FORMAT_CURL_OFF_TU "llu"
-# define CURL_FORMAT_OFF_T "%lld"
-# define CURL_SIZEOF_CURL_OFF_T 8
-# define CURL_SUFFIX_CURL_OFF_T LL
-# define CURL_SUFFIX_CURL_OFF_TU ULL
-# else
-# define CURL_SIZEOF_LONG 4
-# define CURL_TYPEOF_CURL_OFF_T long
-# define CURL_FORMAT_CURL_OFF_T "ld"
-# define CURL_FORMAT_CURL_OFF_TU "lu"
-# define CURL_FORMAT_OFF_T "%ld"
-# define CURL_SIZEOF_CURL_OFF_T 4
-# define CURL_SUFFIX_CURL_OFF_T L
-# define CURL_SUFFIX_CURL_OFF_TU UL
-# endif
-# define CURL_TYPEOF_CURL_SOCKLEN_T int
-# define CURL_SIZEOF_CURL_SOCKLEN_T 4
-
-#elif defined(__SALFORDC__)
-# define CURL_SIZEOF_LONG 4
-# define CURL_TYPEOF_CURL_OFF_T long
-# define CURL_FORMAT_CURL_OFF_T "ld"
-# define CURL_FORMAT_CURL_OFF_TU "lu"
-# define CURL_FORMAT_OFF_T "%ld"
-# define CURL_SIZEOF_CURL_OFF_T 4
-# define CURL_SUFFIX_CURL_OFF_T L
-# define CURL_SUFFIX_CURL_OFF_TU UL
-# define CURL_TYPEOF_CURL_SOCKLEN_T int
-# define CURL_SIZEOF_CURL_SOCKLEN_T 4
-
-#elif defined(__BORLANDC__)
-# if (__BORLANDC__ < 0x520)
-# define CURL_SIZEOF_LONG 4
-# define CURL_TYPEOF_CURL_OFF_T long
-# define CURL_FORMAT_CURL_OFF_T "ld"
-# define CURL_FORMAT_CURL_OFF_TU "lu"
-# define CURL_FORMAT_OFF_T "%ld"
-# define CURL_SIZEOF_CURL_OFF_T 4
-# define CURL_SUFFIX_CURL_OFF_T L
-# define CURL_SUFFIX_CURL_OFF_TU UL
-# else
-# define CURL_SIZEOF_LONG 4
-# define CURL_TYPEOF_CURL_OFF_T __int64
-# define CURL_FORMAT_CURL_OFF_T "I64d"
-# define CURL_FORMAT_CURL_OFF_TU "I64u"
-# define CURL_FORMAT_OFF_T "%I64d"
-# define CURL_SIZEOF_CURL_OFF_T 8
-# define CURL_SUFFIX_CURL_OFF_T i64
-# define CURL_SUFFIX_CURL_OFF_TU ui64
-# endif
-# define CURL_TYPEOF_CURL_SOCKLEN_T int
-# define CURL_SIZEOF_CURL_SOCKLEN_T 4
-
-#elif defined(__TURBOC__)
-# define CURL_SIZEOF_LONG 4
-# define CURL_TYPEOF_CURL_OFF_T long
-# define CURL_FORMAT_CURL_OFF_T "ld"
-# define CURL_FORMAT_CURL_OFF_TU "lu"
-# define CURL_FORMAT_OFF_T "%ld"
-# define CURL_SIZEOF_CURL_OFF_T 4
-# define CURL_SUFFIX_CURL_OFF_T L
-# define CURL_SUFFIX_CURL_OFF_TU UL
-# define CURL_TYPEOF_CURL_SOCKLEN_T int
-# define CURL_SIZEOF_CURL_SOCKLEN_T 4
-
-#elif defined(__WATCOMC__)
-# if defined(__386__)
-# define CURL_SIZEOF_LONG 4
-# define CURL_TYPEOF_CURL_OFF_T __int64
-# define CURL_FORMAT_CURL_OFF_T "I64d"
-# define CURL_FORMAT_CURL_OFF_TU "I64u"
-# define CURL_FORMAT_OFF_T "%I64d"
-# define CURL_SIZEOF_CURL_OFF_T 8
-# define CURL_SUFFIX_CURL_OFF_T i64
-# define CURL_SUFFIX_CURL_OFF_TU ui64
-# else
-# define CURL_SIZEOF_LONG 4
-# define CURL_TYPEOF_CURL_OFF_T long
-# define CURL_FORMAT_CURL_OFF_T "ld"
-# define CURL_FORMAT_CURL_OFF_TU "lu"
-# define CURL_FORMAT_OFF_T "%ld"
-# define CURL_SIZEOF_CURL_OFF_T 4
-# define CURL_SUFFIX_CURL_OFF_T L
-# define CURL_SUFFIX_CURL_OFF_TU UL
-# endif
-# define CURL_TYPEOF_CURL_SOCKLEN_T int
-# define CURL_SIZEOF_CURL_SOCKLEN_T 4
-
-#elif defined(__POCC__)
-# if (__POCC__ < 280)
-# define CURL_SIZEOF_LONG 4
-# define CURL_TYPEOF_CURL_OFF_T long
-# define CURL_FORMAT_CURL_OFF_T "ld"
-# define CURL_FORMAT_CURL_OFF_TU "lu"
-# define CURL_FORMAT_OFF_T "%ld"
-# define CURL_SIZEOF_CURL_OFF_T 4
-# define CURL_SUFFIX_CURL_OFF_T L
-# define CURL_SUFFIX_CURL_OFF_TU UL
-# elif defined(_MSC_VER)
-# define CURL_SIZEOF_LONG 4
-# define CURL_TYPEOF_CURL_OFF_T __int64
-# define CURL_FORMAT_CURL_OFF_T "I64d"
-# define CURL_FORMAT_CURL_OFF_TU "I64u"
-# define CURL_FORMAT_OFF_T "%I64d"
-# define CURL_SIZEOF_CURL_OFF_T 8
-# define CURL_SUFFIX_CURL_OFF_T i64
-# define CURL_SUFFIX_CURL_OFF_TU ui64
-# else
-# define CURL_SIZEOF_LONG 4
-# define CURL_TYPEOF_CURL_OFF_T long long
-# define CURL_FORMAT_CURL_OFF_T "lld"
-# define CURL_FORMAT_CURL_OFF_TU "llu"
-# define CURL_FORMAT_OFF_T "%lld"
-# define CURL_SIZEOF_CURL_OFF_T 8
-# define CURL_SUFFIX_CURL_OFF_T LL
-# define CURL_SUFFIX_CURL_OFF_TU ULL
-# endif
-# define CURL_TYPEOF_CURL_SOCKLEN_T int
-# define CURL_SIZEOF_CURL_SOCKLEN_T 4
-
-#elif defined(__LCC__)
-# define CURL_SIZEOF_LONG 4
-# define CURL_TYPEOF_CURL_OFF_T long
-# define CURL_FORMAT_CURL_OFF_T "ld"
-# define CURL_FORMAT_CURL_OFF_TU "lu"
-# define CURL_FORMAT_OFF_T "%ld"
-# define CURL_SIZEOF_CURL_OFF_T 4
-# define CURL_SUFFIX_CURL_OFF_T L
-# define CURL_SUFFIX_CURL_OFF_TU UL
-# define CURL_TYPEOF_CURL_SOCKLEN_T int
-# define CURL_SIZEOF_CURL_SOCKLEN_T 4
-
-#elif defined(__SYMBIAN32__)
-# if defined(__EABI__) /* Treat all ARM compilers equally */
-# define CURL_SIZEOF_LONG 4
-# define CURL_TYPEOF_CURL_OFF_T long long
-# define CURL_FORMAT_CURL_OFF_T "lld"
-# define CURL_FORMAT_CURL_OFF_TU "llu"
-# define CURL_FORMAT_OFF_T "%lld"
-# define CURL_SIZEOF_CURL_OFF_T 8
-# define CURL_SUFFIX_CURL_OFF_T LL
-# define CURL_SUFFIX_CURL_OFF_TU ULL
-# elif defined(__CW32__)
-# pragma longlong on
-# define CURL_SIZEOF_LONG 4
-# define CURL_TYPEOF_CURL_OFF_T long long
-# define CURL_FORMAT_CURL_OFF_T "lld"
-# define CURL_FORMAT_CURL_OFF_TU "llu"
-# define CURL_FORMAT_OFF_T "%lld"
-# define CURL_SIZEOF_CURL_OFF_T 8
-# define CURL_SUFFIX_CURL_OFF_T LL
-# define CURL_SUFFIX_CURL_OFF_TU ULL
-# elif defined(__VC32__)
-# define CURL_SIZEOF_LONG 4
-# define CURL_TYPEOF_CURL_OFF_T __int64
-# define CURL_FORMAT_CURL_OFF_T "lld"
-# define CURL_FORMAT_CURL_OFF_TU "llu"
-# define CURL_FORMAT_OFF_T "%lld"
-# define CURL_SIZEOF_CURL_OFF_T 8
-# define CURL_SUFFIX_CURL_OFF_T LL
-# define CURL_SUFFIX_CURL_OFF_TU ULL
-# endif
-# define CURL_TYPEOF_CURL_SOCKLEN_T unsigned int
-# define CURL_SIZEOF_CURL_SOCKLEN_T 4
-
-#elif defined(__MWERKS__)
-# define CURL_SIZEOF_LONG 4
-# define CURL_TYPEOF_CURL_OFF_T long long
-# define CURL_FORMAT_CURL_OFF_T "lld"
-# define CURL_FORMAT_CURL_OFF_TU "llu"
-# define CURL_FORMAT_OFF_T "%lld"
-# define CURL_SIZEOF_CURL_OFF_T 8
-# define CURL_SUFFIX_CURL_OFF_T LL
-# define CURL_SUFFIX_CURL_OFF_TU ULL
-# define CURL_TYPEOF_CURL_SOCKLEN_T int
-# define CURL_SIZEOF_CURL_SOCKLEN_T 4
-
-#elif defined(_WIN32_WCE)
-# define CURL_SIZEOF_LONG 4
-# define CURL_TYPEOF_CURL_OFF_T __int64
-# define CURL_FORMAT_CURL_OFF_T "I64d"
-# define CURL_FORMAT_CURL_OFF_TU "I64u"
-# define CURL_FORMAT_OFF_T "%I64d"
-# define CURL_SIZEOF_CURL_OFF_T 8
-# define CURL_SUFFIX_CURL_OFF_T i64
-# define CURL_SUFFIX_CURL_OFF_TU ui64
-# define CURL_TYPEOF_CURL_SOCKLEN_T int
-# define CURL_SIZEOF_CURL_SOCKLEN_T 4
-
-#elif defined(__MINGW32__)
-# define CURL_SIZEOF_LONG 4
-# define CURL_TYPEOF_CURL_OFF_T long long
-# define CURL_FORMAT_CURL_OFF_T "I64d"
-# define CURL_FORMAT_CURL_OFF_TU "I64u"
-# define CURL_FORMAT_OFF_T "%I64d"
-# define CURL_SIZEOF_CURL_OFF_T 8
-# define CURL_SUFFIX_CURL_OFF_T LL
-# define CURL_SUFFIX_CURL_OFF_TU ULL
-# define CURL_TYPEOF_CURL_SOCKLEN_T int
-# define CURL_SIZEOF_CURL_SOCKLEN_T 4
-
-#elif defined(__VMS)
-# if defined(__VAX)
-# define CURL_SIZEOF_LONG 4
-# define CURL_TYPEOF_CURL_OFF_T long
-# define CURL_FORMAT_CURL_OFF_T "ld"
-# define CURL_FORMAT_CURL_OFF_TU "lu"
-# define CURL_FORMAT_OFF_T "%ld"
-# define CURL_SIZEOF_CURL_OFF_T 4
-# define CURL_SUFFIX_CURL_OFF_T L
-# define CURL_SUFFIX_CURL_OFF_TU UL
-# else
-# define CURL_SIZEOF_LONG 4
-# define CURL_TYPEOF_CURL_OFF_T long long
-# define CURL_FORMAT_CURL_OFF_T "lld"
-# define CURL_FORMAT_CURL_OFF_TU "llu"
-# define CURL_FORMAT_OFF_T "%lld"
-# define CURL_SIZEOF_CURL_OFF_T 8
-# define CURL_SUFFIX_CURL_OFF_T LL
-# define CURL_SUFFIX_CURL_OFF_TU ULL
-# endif
-# define CURL_TYPEOF_CURL_SOCKLEN_T unsigned int
-# define CURL_SIZEOF_CURL_SOCKLEN_T 4
-
-#elif defined(__OS400__)
-# if defined(__ILEC400__)
-# define CURL_SIZEOF_LONG 4
-# define CURL_TYPEOF_CURL_OFF_T long long
-# define CURL_FORMAT_CURL_OFF_T "lld"
-# define CURL_FORMAT_CURL_OFF_TU "llu"
-# define CURL_FORMAT_OFF_T "%lld"
-# define CURL_SIZEOF_CURL_OFF_T 8
-# define CURL_SUFFIX_CURL_OFF_T LL
-# define CURL_SUFFIX_CURL_OFF_TU ULL
-# define CURL_TYPEOF_CURL_SOCKLEN_T socklen_t
-# define CURL_SIZEOF_CURL_SOCKLEN_T 4
-# define CURL_PULL_SYS_TYPES_H 1
-# define CURL_PULL_SYS_SOCKET_H 1
-# endif
-
-#elif defined(__MVS__)
-# if defined(__IBMC__) || defined(__IBMCPP__)
-# if defined(_ILP32)
-# define CURL_SIZEOF_LONG 4
-# elif defined(_LP64)
-# define CURL_SIZEOF_LONG 8
-# endif
-# if defined(_LONG_LONG)
-# define CURL_TYPEOF_CURL_OFF_T long long
-# define CURL_FORMAT_CURL_OFF_T "lld"
-# define CURL_FORMAT_CURL_OFF_TU "llu"
-# define CURL_FORMAT_OFF_T "%lld"
-# define CURL_SIZEOF_CURL_OFF_T 8
-# define CURL_SUFFIX_CURL_OFF_T LL
-# define CURL_SUFFIX_CURL_OFF_TU ULL
-# elif defined(_LP64)
-# define CURL_TYPEOF_CURL_OFF_T long
-# define CURL_FORMAT_CURL_OFF_T "ld"
-# define CURL_FORMAT_CURL_OFF_TU "lu"
-# define CURL_FORMAT_OFF_T "%ld"
-# define CURL_SIZEOF_CURL_OFF_T 8
-# define CURL_SUFFIX_CURL_OFF_T L
-# define CURL_SUFFIX_CURL_OFF_TU UL
-# else
-# define CURL_TYPEOF_CURL_OFF_T long
-# define CURL_FORMAT_CURL_OFF_T "ld"
-# define CURL_FORMAT_CURL_OFF_TU "lu"
-# define CURL_FORMAT_OFF_T "%ld"
-# define CURL_SIZEOF_CURL_OFF_T 4
-# define CURL_SUFFIX_CURL_OFF_T L
-# define CURL_SUFFIX_CURL_OFF_TU UL
-# endif
-# define CURL_TYPEOF_CURL_SOCKLEN_T socklen_t
-# define CURL_SIZEOF_CURL_SOCKLEN_T 4
-# define CURL_PULL_SYS_TYPES_H 1
-# define CURL_PULL_SYS_SOCKET_H 1
-# endif
-
-#elif defined(__370__)
-# if defined(__IBMC__) || defined(__IBMCPP__)
-# if defined(_ILP32)
-# define CURL_SIZEOF_LONG 4
-# elif defined(_LP64)
-# define CURL_SIZEOF_LONG 8
-# endif
-# if defined(_LONG_LONG)
-# define CURL_TYPEOF_CURL_OFF_T long long
-# define CURL_FORMAT_CURL_OFF_T "lld"
-# define CURL_FORMAT_CURL_OFF_TU "llu"
-# define CURL_FORMAT_OFF_T "%lld"
-# define CURL_SIZEOF_CURL_OFF_T 8
-# define CURL_SUFFIX_CURL_OFF_T LL
-# define CURL_SUFFIX_CURL_OFF_TU ULL
-# elif defined(_LP64)
-# define CURL_TYPEOF_CURL_OFF_T long
-# define CURL_FORMAT_CURL_OFF_T "ld"
-# define CURL_FORMAT_CURL_OFF_TU "lu"
-# define CURL_FORMAT_OFF_T "%ld"
-# define CURL_SIZEOF_CURL_OFF_T 8
-# define CURL_SUFFIX_CURL_OFF_T L
-# define CURL_SUFFIX_CURL_OFF_TU UL
-# else
-# define CURL_TYPEOF_CURL_OFF_T long
-# define CURL_FORMAT_CURL_OFF_T "ld"
-# define CURL_FORMAT_CURL_OFF_TU "lu"
-# define CURL_FORMAT_OFF_T "%ld"
-# define CURL_SIZEOF_CURL_OFF_T 4
-# define CURL_SUFFIX_CURL_OFF_T L
-# define CURL_SUFFIX_CURL_OFF_TU UL
-# endif
-# define CURL_TYPEOF_CURL_SOCKLEN_T socklen_t
-# define CURL_SIZEOF_CURL_SOCKLEN_T 4
-# define CURL_PULL_SYS_TYPES_H 1
-# define CURL_PULL_SYS_SOCKET_H 1
-# endif
-
-#elif defined(TPF)
-# define CURL_SIZEOF_LONG 8
-# define CURL_TYPEOF_CURL_OFF_T long
-# define CURL_FORMAT_CURL_OFF_T "ld"
-# define CURL_FORMAT_CURL_OFF_TU "lu"
-# define CURL_FORMAT_OFF_T "%ld"
-# define CURL_SIZEOF_CURL_OFF_T 8
-# define CURL_SUFFIX_CURL_OFF_T L
-# define CURL_SUFFIX_CURL_OFF_TU UL
-# define CURL_TYPEOF_CURL_SOCKLEN_T int
-# define CURL_SIZEOF_CURL_SOCKLEN_T 4
-
-/* ===================================== */
-/* KEEP MSVC THE PENULTIMATE ENTRY */
-/* ===================================== */
-
-#elif defined(_MSC_VER)
-# if (_MSC_VER >= 900) && (_INTEGRAL_MAX_BITS >= 64)
-# define CURL_SIZEOF_LONG 4
-# define CURL_TYPEOF_CURL_OFF_T __int64
-# define CURL_FORMAT_CURL_OFF_T "I64d"
-# define CURL_FORMAT_CURL_OFF_TU "I64u"
-# define CURL_FORMAT_OFF_T "%I64d"
-# define CURL_SIZEOF_CURL_OFF_T 8
-# define CURL_SUFFIX_CURL_OFF_T i64
-# define CURL_SUFFIX_CURL_OFF_TU ui64
-# else
-# define CURL_SIZEOF_LONG 4
-# define CURL_TYPEOF_CURL_OFF_T long
-# define CURL_FORMAT_CURL_OFF_T "ld"
-# define CURL_FORMAT_CURL_OFF_TU "lu"
-# define CURL_FORMAT_OFF_T "%ld"
-# define CURL_SIZEOF_CURL_OFF_T 4
-# define CURL_SUFFIX_CURL_OFF_T L
-# define CURL_SUFFIX_CURL_OFF_TU UL
-# endif
-# define CURL_TYPEOF_CURL_SOCKLEN_T int
-# define CURL_SIZEOF_CURL_SOCKLEN_T 4
-
-/* ===================================== */
-/* KEEP GENERIC GCC THE LAST ENTRY */
-/* ===================================== */
-
-#elif defined(__GNUC__)
-# if defined(__i386__) || defined(__ppc__)
-# define CURL_SIZEOF_LONG 4
-# define CURL_TYPEOF_CURL_OFF_T long long
-# define CURL_FORMAT_CURL_OFF_T "lld"
-# define CURL_FORMAT_CURL_OFF_TU "llu"
-# define CURL_FORMAT_OFF_T "%lld"
-# define CURL_SIZEOF_CURL_OFF_T 8
-# define CURL_SUFFIX_CURL_OFF_T LL
-# define CURL_SUFFIX_CURL_OFF_TU ULL
-# elif defined(__x86_64__) || defined(__ppc64__)
-# define CURL_SIZEOF_LONG 8
-# define CURL_TYPEOF_CURL_OFF_T long
-# define CURL_FORMAT_CURL_OFF_T "ld"
-# define CURL_FORMAT_CURL_OFF_TU "lu"
-# define CURL_FORMAT_OFF_T "%ld"
-# define CURL_SIZEOF_CURL_OFF_T 8
-# define CURL_SUFFIX_CURL_OFF_T L
-# define CURL_SUFFIX_CURL_OFF_TU UL
-# endif
-# define CURL_TYPEOF_CURL_SOCKLEN_T socklen_t
-# define CURL_SIZEOF_CURL_SOCKLEN_T 4
-# define CURL_PULL_SYS_TYPES_H 1
-# define CURL_PULL_SYS_SOCKET_H 1
-
-#else
-# error "Unknown non-configure build target!"
- Error Compilation_aborted_Unknown_non_configure_build_target
-#endif
-
-/* CURL_PULL_SYS_TYPES_H is defined above when inclusion of header file */
-/* sys/types.h is required here to properly make type definitions below. */
-#ifdef CURL_PULL_SYS_TYPES_H
-# include <sys/types.h>
-#endif
-
-/* CURL_PULL_SYS_SOCKET_H is defined above when inclusion of header file */
-/* sys/socket.h is required here to properly make type definitions below. */
-#ifdef CURL_PULL_SYS_SOCKET_H
-# include <sys/socket.h>
-#endif
-
-/* Data type definition of curl_socklen_t. */
-
-#ifdef CURL_TYPEOF_CURL_SOCKLEN_T
- typedef CURL_TYPEOF_CURL_SOCKLEN_T curl_socklen_t;
-#endif
-
-/* Data type definition of curl_off_t. */
-
-#ifdef CURL_TYPEOF_CURL_OFF_T
- typedef CURL_TYPEOF_CURL_OFF_T curl_off_t;
-#endif
-
-#endif /* __CURL_CURLBUILD_H */
diff --git a/src/utils/curl/curlbuild.h.cmake b/src/utils/curl/curlbuild.h.cmake
deleted file mode 100644
index 3aa772fc4715dc853ee1c4752f55eaa900d1d2b3..0000000000000000000000000000000000000000
--- a/src/utils/curl/curlbuild.h.cmake
+++ /dev/null
@@ -1,180 +0,0 @@
-#ifndef __CURL_CURLBUILD_H
-#define __CURL_CURLBUILD_H
-/***************************************************************************
- * _ _ ____ _
- * Project ___| | | | _ \| |
- * / __| | | | |_) | |
- * | (__| |_| | _ <| |___
- * \___|\___/|_| \_\_____|
- *
- * Copyright (C) 1998 - 2008, Daniel Stenberg, <daniel@haxx.se>, et al.
- *
- * This software is licensed as described in the file COPYING, which
- * you should have received as part of this distribution. The terms
- * are also available at http://curl.haxx.se/docs/copyright.html.
- *
- * You may opt to use, copy, modify, merge, publish, distribute and/or sell
- * copies of the Software, and permit persons to whom the Software is
- * furnished to do so, under the terms of the COPYING file.
- *
- * This software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY
- * KIND, either express or implied.
- *
- ***************************************************************************/
-
-/* ================================================================ */
-/* NOTES FOR CONFIGURE CAPABLE SYSTEMS */
-/* ================================================================ */
-
-/*
- * NOTE 1:
- * -------
- *
- * Nothing in this file is intended to be modified or adjusted by the
- * curl library user nor by the curl library builder.
- *
- * If you think that something actually needs to be changed, adjusted
- * or fixed in this file, then, report it on the libcurl development
- * mailing list: http://cool.haxx.se/mailman/listinfo/curl-library/
- *
- * This header file shall only export symbols which are 'curl' or 'CURL'
- * prefixed, otherwise public name space would be polluted.
- *
- * NOTE 2:
- * -------
- *
- * Right now you might be staring at file include/curl/curlbuild.h.in or
- * at file include/curl/curlbuild.h, this is due to the following reason:
- *
- * On systems capable of running the configure script, the configure process
- * will overwrite the distributed include/curl/curlbuild.h file with one that
- * is suitable and specific to the library being configured and built, which
- * is generated from the include/curl/curlbuild.h.in template file.
- *
- */
-
-/* ================================================================ */
-/* DEFINITION OF THESE SYMBOLS SHALL NOT TAKE PLACE ANYWHERE ELSE */
-/* ================================================================ */
-
-#ifdef CURL_SIZEOF_LONG
-# error "CURL_SIZEOF_LONG shall not be defined except in curlbuild.h"
- Error Compilation_aborted_CURL_SIZEOF_LONG_already_defined
-#endif
-
-#ifdef CURL_TYPEOF_CURL_SOCKLEN_T
-# error "CURL_TYPEOF_CURL_SOCKLEN_T shall not be defined except in curlbuild.h"
- Error Compilation_aborted_CURL_TYPEOF_CURL_SOCKLEN_T_already_defined
-#endif
-
-#ifdef CURL_SIZEOF_CURL_SOCKLEN_T
-# error "CURL_SIZEOF_CURL_SOCKLEN_T shall not be defined except in curlbuild.h"
- Error Compilation_aborted_CURL_SIZEOF_CURL_SOCKLEN_T_already_defined
-#endif
-#ifdef CURL_TYPEOF_CURL_OFF_T
-# error "CURL_TYPEOF_CURL_OFF_T shall not be defined except in curlbuild.h"
- Error Compilation_aborted_CURL_TYPEOF_CURL_OFF_T_already_defined
-#endif
-
-#ifdef CURL_FORMAT_CURL_OFF_T
-# error "CURL_FORMAT_CURL_OFF_T shall not be defined except in curlbuild.h"
- Error Compilation_aborted_CURL_FORMAT_CURL_OFF_T_already_defined
-#endif
-
-#ifdef CURL_FORMAT_CURL_OFF_TU
-# error "CURL_FORMAT_CURL_OFF_TU shall not be defined except in curlbuild.h"
- Error Compilation_aborted_CURL_FORMAT_CURL_OFF_TU_already_defined
-#endif
-
-#ifdef CURL_FORMAT_OFF_T
-# error "CURL_FORMAT_OFF_T shall not be defined except in curlbuild.h"
- Error Compilation_aborted_CURL_FORMAT_OFF_T_already_defined
-#endif
-
-#ifdef CURL_SIZEOF_CURL_OFF_T
-# error "CURL_SIZEOF_CURL_OFF_T shall not be defined except in curlbuild.h"
- Error Compilation_aborted_CURL_SIZEOF_CURL_OFF_T_already_defined
-#endif
-
-#ifdef CURL_SUFFIX_CURL_OFF_T
-# error "CURL_SUFFIX_CURL_OFF_T shall not be defined except in curlbuild.h"
- Error Compilation_aborted_CURL_SUFFIX_CURL_OFF_T_already_defined
-#endif
-
-#ifdef CURL_SUFFIX_CURL_OFF_TU
-# error "CURL_SUFFIX_CURL_OFF_TU shall not be defined except in curlbuild.h"
- Error Compilation_aborted_CURL_SUFFIX_CURL_OFF_TU_already_defined
-#endif
-
-/* ================================================================ */
-/* EXTERNAL INTERFACE SETTINGS FOR CONFIGURE CAPABLE SYSTEMS ONLY */
-/* ================================================================ */
-
-/* Configure process defines this to 1 when it finds out that system */
-/* header file sys/types.h must be included by the external interface. */
-#cmakedefine CURL_PULL_SYS_TYPES_H ${CURL_PULL_SYS_TYPES_H}
-#ifdef CURL_PULL_SYS_TYPES_H
-# include <sys/types.h>
-#endif
-
-/* Configure process defines this to 1 when it finds out that system */
-/* header file stdint.h must be included by the external interface. */
-#cmakedefine CURL_PULL_STDINT_H ${CURL_PULL_STDINT_H}
-#ifdef CURL_PULL_STDINT_H
-# include <stdint.h>
-#endif
-
-/* Configure process defines this to 1 when it finds out that system */
-/* header file inttypes.h must be included by the external interface. */
-#cmakedefine CURL_PULL_INTTYPES_H ${CURL_PULL_INTTYPES_H}
-#ifdef CURL_PULL_INTTYPES_H
-# include <inttypes.h>
-#endif
-
-/* The size of `long', as computed by sizeof. */
-#cmakedefine CURL_SIZEOF_LONG ${CURL_SIZEOF_LONG}
-
-/* Integral data type used for curl_socklen_t. */
-#cmakedefine CURL_TYPEOF_CURL_SOCKLEN_T ${CURL_TYPEOF_CURL_SOCKLEN_T}
-
-/* on windows socklen_t is in here */
-#ifdef _WIN32
-# include <winsock2.h>
-# include <ws2tcpip.h>
-#endif
-
-#ifdef HAVE_SYS_SOCKET_H
-# include <sys/socket.h>
-#endif
-
-/* Data type definition of curl_socklen_t. */
-typedef CURL_TYPEOF_CURL_SOCKLEN_T curl_socklen_t;
-
-/* The size of `curl_socklen_t', as computed by sizeof. */
-#cmakedefine CURL_SIZEOF_CURL_SOCKLEN_T ${CURL_SIZEOF_CURL_SOCKLEN_T}
-
-/* Signed integral data type used for curl_off_t. */
-#cmakedefine CURL_TYPEOF_CURL_OFF_T ${CURL_TYPEOF_CURL_OFF_T}
-
-/* Data type definition of curl_off_t. */
-typedef CURL_TYPEOF_CURL_OFF_T curl_off_t;
-
-/* curl_off_t formatting string directive without "%" conversion specifier. */
-#cmakedefine CURL_FORMAT_CURL_OFF_T "${CURL_FORMAT_CURL_OFF_T}"
-
-/* unsigned curl_off_t formatting string without "%" conversion specifier. */
-#cmakedefine CURL_FORMAT_CURL_OFF_TU "${CURL_FORMAT_CURL_OFF_TU}"
-
-/* curl_off_t formatting string directive with "%" conversion specifier. */
-#cmakedefine CURL_FORMAT_OFF_T "${CURL_FORMAT_OFF_T}"
-
-/* The size of `curl_off_t', as computed by sizeof. */
-#cmakedefine CURL_SIZEOF_CURL_OFF_T ${CURL_SIZEOF_CURL_OFF_T}
-
-/* curl_off_t constant suffix. */
-#cmakedefine CURL_SUFFIX_CURL_OFF_T ${CURL_SUFFIX_CURL_OFF_T}
-
-/* unsigned curl_off_t constant suffix. */
-#cmakedefine CURL_SUFFIX_CURL_OFF_TU ${CURL_SUFFIX_CURL_OFF_TU}
-
-#endif /* __CURL_CURLBUILD_H */
diff --git a/src/utils/curl/curlbuild.h.in b/src/utils/curl/curlbuild.h.in
deleted file mode 100644
index cb1de80a03e6ec7f4c1c3ed410ccfb3d76e1f17e..0000000000000000000000000000000000000000
--- a/src/utils/curl/curlbuild.h.in
+++ /dev/null
@@ -1,190 +0,0 @@
-#ifndef __CURL_CURLBUILD_H
-#define __CURL_CURLBUILD_H
-/***************************************************************************
- * _ _ ____ _
- * Project ___| | | | _ \| |
- * / __| | | | |_) | |
- * | (__| |_| | _ <| |___
- * \___|\___/|_| \_\_____|
- *
- * Copyright (C) 1998 - 2009, Daniel Stenberg, <daniel@haxx.se>, et al.
- *
- * This software is licensed as described in the file COPYING, which
- * you should have received as part of this distribution. The terms
- * are also available at http://curl.haxx.se/docs/copyright.html.
- *
- * You may opt to use, copy, modify, merge, publish, distribute and/or sell
- * copies of the Software, and permit persons to whom the Software is
- * furnished to do so, under the terms of the COPYING file.
- *
- * This software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY
- * KIND, either express or implied.
- *
- ***************************************************************************/
-
-/* ================================================================ */
-/* NOTES FOR CONFIGURE CAPABLE SYSTEMS */
-/* ================================================================ */
-
-/*
- * NOTE 1:
- * -------
- *
- * Nothing in this file is intended to be modified or adjusted by the
- * curl library user nor by the curl library builder.
- *
- * If you think that something actually needs to be changed, adjusted
- * or fixed in this file, then, report it on the libcurl development
- * mailing list: http://cool.haxx.se/mailman/listinfo/curl-library/
- *
- * This header file shall only export symbols which are 'curl' or 'CURL'
- * prefixed, otherwise public name space would be polluted.
- *
- * NOTE 2:
- * -------
- *
- * Right now you might be staring at file include/curl/curlbuild.h.in or
- * at file include/curl/curlbuild.h, this is due to the following reason:
- *
- * On systems capable of running the configure script, the configure process
- * will overwrite the distributed include/curl/curlbuild.h file with one that
- * is suitable and specific to the library being configured and built, which
- * is generated from the include/curl/curlbuild.h.in template file.
- *
- */
-
-/* ================================================================ */
-/* DEFINITION OF THESE SYMBOLS SHALL NOT TAKE PLACE ANYWHERE ELSE */
-/* ================================================================ */
-
-#ifdef CURL_SIZEOF_LONG
-# error "CURL_SIZEOF_LONG shall not be defined except in curlbuild.h"
- Error Compilation_aborted_CURL_SIZEOF_LONG_already_defined
-#endif
-
-#ifdef CURL_TYPEOF_CURL_SOCKLEN_T
-# error "CURL_TYPEOF_CURL_SOCKLEN_T shall not be defined except in curlbuild.h"
- Error Compilation_aborted_CURL_TYPEOF_CURL_SOCKLEN_T_already_defined
-#endif
-
-#ifdef CURL_SIZEOF_CURL_SOCKLEN_T
-# error "CURL_SIZEOF_CURL_SOCKLEN_T shall not be defined except in curlbuild.h"
- Error Compilation_aborted_CURL_SIZEOF_CURL_SOCKLEN_T_already_defined
-#endif
-
-#ifdef CURL_TYPEOF_CURL_OFF_T
-# error "CURL_TYPEOF_CURL_OFF_T shall not be defined except in curlbuild.h"
- Error Compilation_aborted_CURL_TYPEOF_CURL_OFF_T_already_defined
-#endif
-
-#ifdef CURL_FORMAT_CURL_OFF_T
-# error "CURL_FORMAT_CURL_OFF_T shall not be defined except in curlbuild.h"
- Error Compilation_aborted_CURL_FORMAT_CURL_OFF_T_already_defined
-#endif
-
-#ifdef CURL_FORMAT_CURL_OFF_TU
-# error "CURL_FORMAT_CURL_OFF_TU shall not be defined except in curlbuild.h"
- Error Compilation_aborted_CURL_FORMAT_CURL_OFF_TU_already_defined
-#endif
-
-#ifdef CURL_FORMAT_OFF_T
-# error "CURL_FORMAT_OFF_T shall not be defined except in curlbuild.h"
- Error Compilation_aborted_CURL_FORMAT_OFF_T_already_defined
-#endif
-
-#ifdef CURL_SIZEOF_CURL_OFF_T
-# error "CURL_SIZEOF_CURL_OFF_T shall not be defined except in curlbuild.h"
- Error Compilation_aborted_CURL_SIZEOF_CURL_OFF_T_already_defined
-#endif
-
-#ifdef CURL_SUFFIX_CURL_OFF_T
-# error "CURL_SUFFIX_CURL_OFF_T shall not be defined except in curlbuild.h"
- Error Compilation_aborted_CURL_SUFFIX_CURL_OFF_T_already_defined
-#endif
-
-#ifdef CURL_SUFFIX_CURL_OFF_TU
-# error "CURL_SUFFIX_CURL_OFF_TU shall not be defined except in curlbuild.h"
- Error Compilation_aborted_CURL_SUFFIX_CURL_OFF_TU_already_defined
-#endif
-
-/* ================================================================ */
-/* EXTERNAL INTERFACE SETTINGS FOR CONFIGURE CAPABLE SYSTEMS ONLY */
-/* ================================================================ */
-
-/* Configure process defines this to 1 when it finds out that system */
-/* header file ws2tcpip.h must be included by the external interface. */
-#undef CURL_PULL_WS2TCPIP_H
-#ifdef CURL_PULL_WS2TCPIP_H
-# ifndef WIN32_LEAN_AND_MEAN
-# define WIN32_LEAN_AND_MEAN
-# endif
-# include <windows.h>
-# include <winsock2.h>
-# include <ws2tcpip.h>
-#endif
-
-/* Configure process defines this to 1 when it finds out that system */
-/* header file sys/types.h must be included by the external interface. */
-#undef CURL_PULL_SYS_TYPES_H
-#ifdef CURL_PULL_SYS_TYPES_H
-# include <sys/types.h>
-#endif
-
-/* Configure process defines this to 1 when it finds out that system */
-/* header file stdint.h must be included by the external interface. */
-#undef CURL_PULL_STDINT_H
-#ifdef CURL_PULL_STDINT_H
-# include <stdint.h>
-#endif
-
-/* Configure process defines this to 1 when it finds out that system */
-/* header file inttypes.h must be included by the external interface. */
-#undef CURL_PULL_INTTYPES_H
-#ifdef CURL_PULL_INTTYPES_H
-# include <inttypes.h>
-#endif
-
-/* Configure process defines this to 1 when it finds out that system */
-/* header file sys/socket.h must be included by the external interface. */
-#undef CURL_PULL_SYS_SOCKET_H
-#ifdef CURL_PULL_SYS_SOCKET_H
-# include <sys/socket.h>
-#endif
-
-/* The size of `long', as computed by sizeof. */
-#undef CURL_SIZEOF_LONG
-
-/* Integral data type used for curl_socklen_t. */
-#undef CURL_TYPEOF_CURL_SOCKLEN_T
-
-/* The size of `curl_socklen_t', as computed by sizeof. */
-#undef CURL_SIZEOF_CURL_SOCKLEN_T
-
-/* Data type definition of curl_socklen_t. */
-typedef CURL_TYPEOF_CURL_SOCKLEN_T curl_socklen_t;
-
-/* Signed integral data type used for curl_off_t. */
-#undef CURL_TYPEOF_CURL_OFF_T
-
-/* Data type definition of curl_off_t. */
-typedef CURL_TYPEOF_CURL_OFF_T curl_off_t;
-
-/* curl_off_t formatting string directive without "%" conversion specifier. */
-#undef CURL_FORMAT_CURL_OFF_T
-
-/* unsigned curl_off_t formatting string without "%" conversion specifier. */
-#undef CURL_FORMAT_CURL_OFF_TU
-
-/* curl_off_t formatting string directive with "%" conversion specifier. */
-#undef CURL_FORMAT_OFF_T
-
-/* The size of `curl_off_t', as computed by sizeof. */
-#undef CURL_SIZEOF_CURL_OFF_T
-
-/* curl_off_t constant suffix. */
-#undef CURL_SUFFIX_CURL_OFF_T
-
-/* unsigned curl_off_t constant suffix. */
-#undef CURL_SUFFIX_CURL_OFF_TU
-
-#endif /* __CURL_CURLBUILD_H */
diff --git a/src/utils/curl/curlrules.h b/src/utils/curl/curlrules.h
deleted file mode 100644
index 8aad1df678c0d827ca792c16137d17d86963fc3d..0000000000000000000000000000000000000000
--- a/src/utils/curl/curlrules.h
+++ /dev/null
@@ -1,252 +0,0 @@
-#ifndef __CURL_CURLRULES_H
-#define __CURL_CURLRULES_H
-/***************************************************************************
- * _ _ ____ _
- * Project ___| | | | _ \| |
- * / __| | | | |_) | |
- * | (__| |_| | _ <| |___
- * \___|\___/|_| \_\_____|
- *
- * Copyright (C) 1998 - 2010, Daniel Stenberg, <daniel@haxx.se>, et al.
- *
- * This software is licensed as described in the file COPYING, which
- * you should have received as part of this distribution. The terms
- * are also available at http://curl.haxx.se/docs/copyright.html.
- *
- * You may opt to use, copy, modify, merge, publish, distribute and/or sell
- * copies of the Software, and permit persons to whom the Software is
- * furnished to do so, under the terms of the COPYING file.
- *
- * This software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY
- * KIND, either express or implied.
- *
- ***************************************************************************/
-
-/* ================================================================ */
-/* COMPILE TIME SANITY CHECKS */
-/* ================================================================ */
-
-/*
- * NOTE 1:
- * -------
- *
- * All checks done in this file are intentionally placed in a public
- * header file which is pulled by curl/curl.h when an application is
- * being built using an already built libcurl library. Additionally
- * this file is also included and used when building the library.
- *
- * If compilation fails on this file it is certainly sure that the
- * problem is elsewhere. It could be a problem in the curlbuild.h
- * header file, or simply that you are using different compilation
- * settings than those used to build the library.
- *
- * Nothing in this file is intended to be modified or adjusted by the
- * curl library user nor by the curl library builder.
- *
- * Do not deactivate any check, these are done to make sure that the
- * library is properly built and used.
- *
- * You can find further help on the libcurl development mailing list:
- * http://cool.haxx.se/mailman/listinfo/curl-library/
- *
- * NOTE 2
- * ------
- *
- * Some of the following compile time checks are based on the fact
- * that the dimension of a constant array can not be a negative one.
- * In this way if the compile time verification fails, the compilation
- * will fail issuing an error. The error description wording is compiler
- * dependent but it will be quite similar to one of the following:
- *
- * "negative subscript or subscript is too large"
- * "array must have at least one element"
- * "-1 is an illegal array size"
- * "size of array is negative"
- *
- * If you are building an application which tries to use an already
- * built libcurl library and you are getting this kind of errors on
- * this file, it is a clear indication that there is a mismatch between
- * how the library was built and how you are trying to use it for your
- * application. Your already compiled or binary library provider is the
- * only one who can give you the details you need to properly use it.
- */
-
-/*
- * Verify that some macros are actually defined.
- */
-
-#ifndef CURL_SIZEOF_LONG
-# error "CURL_SIZEOF_LONG definition is missing!"
- Error Compilation_aborted_CURL_SIZEOF_LONG_is_missing
-#endif
-
-#ifndef CURL_TYPEOF_CURL_SOCKLEN_T
-# error "CURL_TYPEOF_CURL_SOCKLEN_T definition is missing!"
- Error Compilation_aborted_CURL_TYPEOF_CURL_SOCKLEN_T_is_missing
-#endif
-
-#ifndef CURL_SIZEOF_CURL_SOCKLEN_T
-# error "CURL_SIZEOF_CURL_SOCKLEN_T definition is missing!"
- Error Compilation_aborted_CURL_SIZEOF_CURL_SOCKLEN_T_is_missing
-#endif
-
-#ifndef CURL_TYPEOF_CURL_OFF_T
-# error "CURL_TYPEOF_CURL_OFF_T definition is missing!"
- Error Compilation_aborted_CURL_TYPEOF_CURL_OFF_T_is_missing
-#endif
-
-#ifndef CURL_FORMAT_CURL_OFF_T
-# error "CURL_FORMAT_CURL_OFF_T definition is missing!"
- Error Compilation_aborted_CURL_FORMAT_CURL_OFF_T_is_missing
-#endif
-
-#ifndef CURL_FORMAT_CURL_OFF_TU
-# error "CURL_FORMAT_CURL_OFF_TU definition is missing!"
- Error Compilation_aborted_CURL_FORMAT_CURL_OFF_TU_is_missing
-#endif
-
-#ifndef CURL_FORMAT_OFF_T
-# error "CURL_FORMAT_OFF_T definition is missing!"
- Error Compilation_aborted_CURL_FORMAT_OFF_T_is_missing
-#endif
-
-#ifndef CURL_SIZEOF_CURL_OFF_T
-# error "CURL_SIZEOF_CURL_OFF_T definition is missing!"
- Error Compilation_aborted_CURL_SIZEOF_CURL_OFF_T_is_missing
-#endif
-
-#ifndef CURL_SUFFIX_CURL_OFF_T
-# error "CURL_SUFFIX_CURL_OFF_T definition is missing!"
- Error Compilation_aborted_CURL_SUFFIX_CURL_OFF_T_is_missing
-#endif
-
-#ifndef CURL_SUFFIX_CURL_OFF_TU
-# error "CURL_SUFFIX_CURL_OFF_TU definition is missing!"
- Error Compilation_aborted_CURL_SUFFIX_CURL_OFF_TU_is_missing
-#endif
-
-/*
- * Macros private to this header file.
- */
-
-#define CurlchkszEQ(t, s) sizeof(t) == s ? 1 : -1
-
-#define CurlchkszGE(t1, t2) sizeof(t1) >= sizeof(t2) ? 1 : -1
-
-/*
- * Verify that the size previously defined and expected for long
- * is the same as the one reported by sizeof() at compile time.
- */
-
-typedef char
- __curl_rule_01__
- [CurlchkszEQ(long, CURL_SIZEOF_LONG)];
-
-/*
- * Verify that the size previously defined and expected for
- * curl_off_t is actually the the same as the one reported
- * by sizeof() at compile time.
- */
-
-typedef char
- __curl_rule_02__
- [CurlchkszEQ(curl_off_t, CURL_SIZEOF_CURL_OFF_T)];
-
-/*
- * Verify at compile time that the size of curl_off_t as reported
- * by sizeof() is greater or equal than the one reported for long
- * for the current compilation.
- */
-
-typedef char
- __curl_rule_03__
- [CurlchkszGE(curl_off_t, long)];
-
-/*
- * Verify that the size previously defined and expected for
- * curl_socklen_t is actually the the same as the one reported
- * by sizeof() at compile time.
- */
-
-typedef char
- __curl_rule_04__
- [CurlchkszEQ(curl_socklen_t, CURL_SIZEOF_CURL_SOCKLEN_T)];
-
-/*
- * Verify at compile time that the size of curl_socklen_t as reported
- * by sizeof() is greater or equal than the one reported for int for
- * the current compilation.
- */
-
-typedef char
- __curl_rule_05__
- [CurlchkszGE(curl_socklen_t, int)];
-
-/* ================================================================ */
-/* EXTERNALLY AND INTERNALLY VISIBLE DEFINITIONS */
-/* ================================================================ */
-
-/*
- * CURL_ISOCPP and CURL_OFF_T_C definitions are done here in order to allow
- * these to be visible and exported by the external libcurl interface API,
- * while also making them visible to the library internals, simply including
- * setup.h, without actually needing to include curl.h internally.
- * If some day this section would grow big enough, all this should be moved
- * to its own header file.
- */
-
-/*
- * Figure out if we can use the ## preprocessor operator, which is supported
- * by ISO/ANSI C and C++. Some compilers support it without setting __STDC__
- * or __cplusplus so we need to carefully check for them too.
- */
-
-#if defined(__STDC__) || defined(_MSC_VER) || defined(__cplusplus) || \
- defined(__HP_aCC) || defined(__BORLANDC__) || defined(__LCC__) || \
- defined(__POCC__) || defined(__SALFORDC__) || defined(__HIGHC__) || \
- defined(__ILEC400__)
- /* This compiler is believed to have an ISO compatible preprocessor */
-#define CURL_ISOCPP
-#else
- /* This compiler is believed NOT to have an ISO compatible preprocessor */
-#undef CURL_ISOCPP
-#endif
-
-/*
- * Macros for minimum-width signed and unsigned curl_off_t integer constants.
- */
-
-#ifdef CURL_ISOCPP
-# define __CURL_OFF_T_C_HELPER2(Val,Suffix) Val ## Suffix
-#else
-# define __CURL_OFF_T_C_HELPER2(Val,Suffix) Val/**/Suffix
-#endif
-#define __CURL_OFF_T_C_HELPER1(Val,Suffix) __CURL_OFF_T_C_HELPER2(Val,Suffix)
-#define CURL_OFF_T_C(Val) __CURL_OFF_T_C_HELPER1(Val,CURL_SUFFIX_CURL_OFF_T)
-#define CURL_OFF_TU_C(Val) __CURL_OFF_T_C_HELPER1(Val,CURL_SUFFIX_CURL_OFF_TU)
-
-/*
- * Get rid of macros private to this header file.
- */
-
-#undef CurlchkszEQ
-#undef CurlchkszGE
-
-/*
- * Get rid of macros not intended to exist beyond this point.
- */
-
-#undef CURL_PULL_WS2TCPIP_H
-#undef CURL_PULL_SYS_TYPES_H
-#undef CURL_PULL_SYS_SOCKET_H
-#undef CURL_PULL_STDINT_H
-#undef CURL_PULL_INTTYPES_H
-
-#undef CURL_TYPEOF_CURL_SOCKLEN_T
-#undef CURL_TYPEOF_CURL_OFF_T
-
-#ifdef CURL_NO_OLDIES
-#undef CURL_FORMAT_OFF_T /* not required since 7.19.0 - obsoleted in 7.20.0 */
-#endif
-
-#endif /* __CURL_CURLRULES_H */
diff --git a/src/utils/curl/curlver.h b/src/utils/curl/curlver.h
deleted file mode 100644
index 35ca9a8d57e071d8200705e548a17e708d09a0cc..0000000000000000000000000000000000000000
--- a/src/utils/curl/curlver.h
+++ /dev/null
@@ -1,69 +0,0 @@
-#ifndef __CURL_CURLVER_H
-#define __CURL_CURLVER_H
-/***************************************************************************
- * _ _ ____ _
- * Project ___| | | | _ \| |
- * / __| | | | |_) | |
- * | (__| |_| | _ <| |___
- * \___|\___/|_| \_\_____|
- *
- * Copyright (C) 1998 - 2010, Daniel Stenberg, <daniel@haxx.se>, et al.
- *
- * This software is licensed as described in the file COPYING, which
- * you should have received as part of this distribution. The terms
- * are also available at http://curl.haxx.se/docs/copyright.html.
- *
- * You may opt to use, copy, modify, merge, publish, distribute and/or sell
- * copies of the Software, and permit persons to whom the Software is
- * furnished to do so, under the terms of the COPYING file.
- *
- * This software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY
- * KIND, either express or implied.
- *
- ***************************************************************************/
-
-/* This header file contains nothing but libcurl version info, generated by
- a script at release-time. This was made its own header file in 7.11.2 */
-
-/* This is the global package copyright */
-#define LIBCURL_COPYRIGHT "1996 - 2010 Daniel Stenberg, <daniel@haxx.se>."
-
-/* This is the version number of the libcurl package from which this header
- file origins: */
-#define LIBCURL_VERSION "7.20.1"
-
-/* The numeric version number is also available "in parts" by using these
- defines: */
-#define LIBCURL_VERSION_MAJOR 7
-#define LIBCURL_VERSION_MINOR 20
-#define LIBCURL_VERSION_PATCH 1
-
-/* This is the numeric version of the libcurl version number, meant for easier
- parsing and comparions by programs. The LIBCURL_VERSION_NUM define will
- always follow this syntax:
-
- 0xXXYYZZ
-
- Where XX, YY and ZZ are the main version, release and patch numbers in
- hexadecimal (using 8 bits each). All three numbers are always represented
- using two digits. 1.2 would appear as "0x010200" while version 9.11.7
- appears as "0x090b07".
-
- This 6-digit (24 bits) hexadecimal number does not show pre-release number,
- and it is always a greater number in a more recent release. It makes
- comparisons with greater than and less than work.
-*/
-#define LIBCURL_VERSION_NUM 0x071401
-
-/*
- * This is the date and time when the full source package was created. The
- * timestamp is not stored in git, as the timestamp is properly set in the
- * tarballs by the maketgz script.
- *
- * The format of the date should follow this template:
- *
- * "Mon Feb 12 11:35:33 UTC 2007"
- */
-#define LIBCURL_TIMESTAMP "Wed Apr 14 14:55:20 UTC 2010"
-
-#endif /* __CURL_CURLVER_H */
diff --git a/src/utils/curl/easy.h b/src/utils/curl/easy.h
deleted file mode 100644
index 1ddb4fe5a2cb476f1a1278b83c7b576135bd5aa9..0000000000000000000000000000000000000000
--- a/src/utils/curl/easy.h
+++ /dev/null
@@ -1,102 +0,0 @@
-#ifndef __CURL_EASY_H
-#define __CURL_EASY_H
-/***************************************************************************
- * _ _ ____ _
- * Project ___| | | | _ \| |
- * / __| | | | |_) | |
- * | (__| |_| | _ <| |___
- * \___|\___/|_| \_\_____|
- *
- * Copyright (C) 1998 - 2008, Daniel Stenberg, <daniel@haxx.se>, et al.
- *
- * This software is licensed as described in the file COPYING, which
- * you should have received as part of this distribution. The terms
- * are also available at http://curl.haxx.se/docs/copyright.html.
- *
- * You may opt to use, copy, modify, merge, publish, distribute and/or sell
- * copies of the Software, and permit persons to whom the Software is
- * furnished to do so, under the terms of the COPYING file.
- *
- * This software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY
- * KIND, either express or implied.
- *
- ***************************************************************************/
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-CURL_EXTERN CURL *curl_easy_init(void);
-CURL_EXTERN CURLcode curl_easy_setopt(CURL *curl, CURLoption option, ...);
-CURL_EXTERN CURLcode curl_easy_perform(CURL *curl);
-CURL_EXTERN void curl_easy_cleanup(CURL *curl);
-
-/*
- * NAME curl_easy_getinfo()
- *
- * DESCRIPTION
- *
- * Request internal information from the curl session with this function. The
- * third argument MUST be a pointer to a long, a pointer to a char * or a
- * pointer to a double (as the documentation describes elsewhere). The data
- * pointed to will be filled in accordingly and can be relied upon only if the
- * function returns CURLE_OK. This function is intended to get used *AFTER* a
- * performed transfer, all results from this function are undefined until the
- * transfer is completed.
- */
-CURL_EXTERN CURLcode curl_easy_getinfo(CURL *curl, CURLINFO info, ...);
-
-
-/*
- * NAME curl_easy_duphandle()
- *
- * DESCRIPTION
- *
- * Creates a new curl session handle with the same options set for the handle
- * passed in. Duplicating a handle could only be a matter of cloning data and
- * options, internal state info and things like persistant connections cannot
- * be transfered. It is useful in multithreaded applications when you can run
- * curl_easy_duphandle() for each new thread to avoid a series of identical
- * curl_easy_setopt() invokes in every thread.
- */
-CURL_EXTERN CURL* curl_easy_duphandle(CURL *curl);
-
-/*
- * NAME curl_easy_reset()
- *
- * DESCRIPTION
- *
- * Re-initializes a CURL handle to the default values. This puts back the
- * handle to the same state as it was in when it was just created.
- *
- * It does keep: live connections, the Session ID cache, the DNS cache and the
- * cookies.
- */
-CURL_EXTERN void curl_easy_reset(CURL *curl);
-
-/*
- * NAME curl_easy_recv()
- *
- * DESCRIPTION
- *
- * Receives data from the connected socket. Use after successful
- * curl_easy_perform() with CURLOPT_CONNECT_ONLY option.
- */
-CURL_EXTERN CURLcode curl_easy_recv(CURL *curl, void *buffer, size_t buflen,
- size_t *n);
-
-/*
- * NAME curl_easy_send()
- *
- * DESCRIPTION
- *
- * Sends data over the connected socket. Use after successful
- * curl_easy_perform() with CURLOPT_CONNECT_ONLY option.
- */
-CURL_EXTERN CURLcode curl_easy_send(CURL *curl, const void *buffer,
- size_t buflen, size_t *n);
-
-#ifdef __cplusplus
-}
-#endif
-
-#endif
diff --git a/src/utils/curl/mprintf.h b/src/utils/curl/mprintf.h
deleted file mode 100644
index de7dd2f3c360e327e6280372e8a10f335fcf3504..0000000000000000000000000000000000000000
--- a/src/utils/curl/mprintf.h
+++ /dev/null
@@ -1,81 +0,0 @@
-#ifndef __CURL_MPRINTF_H
-#define __CURL_MPRINTF_H
-/***************************************************************************
- * _ _ ____ _
- * Project ___| | | | _ \| |
- * / __| | | | |_) | |
- * | (__| |_| | _ <| |___
- * \___|\___/|_| \_\_____|
- *
- * Copyright (C) 1998 - 2006, Daniel Stenberg, <daniel@haxx.se>, et al.
- *
- * This software is licensed as described in the file COPYING, which
- * you should have received as part of this distribution. The terms
- * are also available at http://curl.haxx.se/docs/copyright.html.
- *
- * You may opt to use, copy, modify, merge, publish, distribute and/or sell
- * copies of the Software, and permit persons to whom the Software is
- * furnished to do so, under the terms of the COPYING file.
- *
- * This software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY
- * KIND, either express or implied.
- *
- ***************************************************************************/
-
-#include <stdarg.h>
-#include <stdio.h> /* needed for FILE */
-
-#include "curl.h"
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-CURL_EXTERN int curl_mprintf(const char *format, ...);
-CURL_EXTERN int curl_mfprintf(FILE *fd, const char *format, ...);
-CURL_EXTERN int curl_msprintf(char *buffer, const char *format, ...);
-CURL_EXTERN int curl_msnprintf(char *buffer, size_t maxlength,
- const char *format, ...);
-CURL_EXTERN int curl_mvprintf(const char *format, va_list args);
-CURL_EXTERN int curl_mvfprintf(FILE *fd, const char *format, va_list args);
-CURL_EXTERN int curl_mvsprintf(char *buffer, const char *format, va_list args);
-CURL_EXTERN int curl_mvsnprintf(char *buffer, size_t maxlength,
- const char *format, va_list args);
-CURL_EXTERN char *curl_maprintf(const char *format, ...);
-CURL_EXTERN char *curl_mvaprintf(const char *format, va_list args);
-
-#ifdef _MPRINTF_REPLACE
-# undef printf
-# undef fprintf
-# undef sprintf
-# undef vsprintf
-# undef snprintf
-# undef vprintf
-# undef vfprintf
-# undef vsnprintf
-# undef aprintf
-# undef vaprintf
-# define printf curl_mprintf
-# define fprintf curl_mfprintf
-#ifdef CURLDEBUG
-/* When built with CURLDEBUG we define away the sprintf() functions since we
- don't want internal code to be using them */
-# define sprintf sprintf_was_used
-# define vsprintf vsprintf_was_used
-#else
-# define sprintf curl_msprintf
-# define vsprintf curl_mvsprintf
-#endif
-# define snprintf curl_msnprintf
-# define vprintf curl_mvprintf
-# define vfprintf curl_mvfprintf
-# define vsnprintf curl_mvsnprintf
-# define aprintf curl_maprintf
-# define vaprintf curl_mvaprintf
-#endif
-
-#ifdef __cplusplus
-}
-#endif
-
-#endif /* __CURL_MPRINTF_H */
diff --git a/src/utils/curl/multi.h b/src/utils/curl/multi.h
deleted file mode 100644
index f96566669c6771fbbf2e1735f826d8cb3a1fce11..0000000000000000000000000000000000000000
--- a/src/utils/curl/multi.h
+++ /dev/null
@@ -1,345 +0,0 @@
-#ifndef __CURL_MULTI_H
-#define __CURL_MULTI_H
-/***************************************************************************
- * _ _ ____ _
- * Project ___| | | | _ \| |
- * / __| | | | |_) | |
- * | (__| |_| | _ <| |___
- * \___|\___/|_| \_\_____|
- *
- * Copyright (C) 1998 - 2007, Daniel Stenberg, <daniel@haxx.se>, et al.
- *
- * This software is licensed as described in the file COPYING, which
- * you should have received as part of this distribution. The terms
- * are also available at http://curl.haxx.se/docs/copyright.html.
- *
- * You may opt to use, copy, modify, merge, publish, distribute and/or sell
- * copies of the Software, and permit persons to whom the Software is
- * furnished to do so, under the terms of the COPYING file.
- *
- * This software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY
- * KIND, either express or implied.
- *
- ***************************************************************************/
-/*
- This is an "external" header file. Don't give away any internals here!
-
- GOALS
-
- o Enable a "pull" interface. The application that uses libcurl decides where
- and when to ask libcurl to get/send data.
-
- o Enable multiple simultaneous transfers in the same thread without making it
- complicated for the application.
-
- o Enable the application to select() on its own file descriptors and curl's
- file descriptors simultaneous easily.
-
-*/
-
-/*
- * This header file should not really need to include "curl.h" since curl.h
- * itself includes this file and we expect user applications to do #include
- * <curl/curl.h> without the need for especially including multi.h.
- *
- * For some reason we added this include here at one point, and rather than to
- * break existing (wrongly written) libcurl applications, we leave it as-is
- * but with this warning attached.
- */
-#include "curl.h"
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-typedef void CURLM;
-
-typedef enum {
- CURLM_CALL_MULTI_PERFORM = -1, /* please call curl_multi_perform() or
- curl_multi_socket*() soon */
- CURLM_OK,
- CURLM_BAD_HANDLE, /* the passed-in handle is not a valid CURLM handle */
- CURLM_BAD_EASY_HANDLE, /* an easy handle was not good/valid */
- CURLM_OUT_OF_MEMORY, /* if you ever get this, you're in deep sh*t */
- CURLM_INTERNAL_ERROR, /* this is a libcurl bug */
- CURLM_BAD_SOCKET, /* the passed in socket argument did not match */
- CURLM_UNKNOWN_OPTION, /* curl_multi_setopt() with unsupported option */
- CURLM_LAST
-} CURLMcode;
-
-/* just to make code nicer when using curl_multi_socket() you can now check
- for CURLM_CALL_MULTI_SOCKET too in the same style it works for
- curl_multi_perform() and CURLM_CALL_MULTI_PERFORM */
-#define CURLM_CALL_MULTI_SOCKET CURLM_CALL_MULTI_PERFORM
-
-typedef enum {
- CURLMSG_NONE, /* first, not used */
- CURLMSG_DONE, /* This easy handle has completed. 'result' contains
- the CURLcode of the transfer */
- CURLMSG_LAST /* last, not used */
-} CURLMSG;
-
-struct CURLMsg {
- CURLMSG msg; /* what this message means */
- CURL *easy_handle; /* the handle it concerns */
- union {
- void *whatever; /* message-specific data */
- CURLcode result; /* return code for transfer */
- } data;
-};
-typedef struct CURLMsg CURLMsg;
-
-/*
- * Name: curl_multi_init()
- *
- * Desc: inititalize multi-style curl usage
- *
- * Returns: a new CURLM handle to use in all 'curl_multi' functions.
- */
-CURL_EXTERN CURLM *curl_multi_init(void);
-
-/*
- * Name: curl_multi_add_handle()
- *
- * Desc: add a standard curl handle to the multi stack
- *
- * Returns: CURLMcode type, general multi error code.
- */
-CURL_EXTERN CURLMcode curl_multi_add_handle(CURLM *multi_handle,
- CURL *curl_handle);
-
- /*
- * Name: curl_multi_remove_handle()
- *
- * Desc: removes a curl handle from the multi stack again
- *
- * Returns: CURLMcode type, general multi error code.
- */
-CURL_EXTERN CURLMcode curl_multi_remove_handle(CURLM *multi_handle,
- CURL *curl_handle);
-
- /*
- * Name: curl_multi_fdset()
- *
- * Desc: Ask curl for its fd_set sets. The app can use these to select() or
- * poll() on. We want curl_multi_perform() called as soon as one of
- * them are ready.
- *
- * Returns: CURLMcode type, general multi error code.
- */
-CURL_EXTERN CURLMcode curl_multi_fdset(CURLM *multi_handle,
- fd_set *read_fd_set,
- fd_set *write_fd_set,
- fd_set *exc_fd_set,
- int *max_fd);
-
- /*
- * Name: curl_multi_perform()
- *
- * Desc: When the app thinks there's data available for curl it calls this
- * function to read/write whatever there is right now. This returns
- * as soon as the reads and writes are done. This function does not
- * require that there actually is data available for reading or that
- * data can be written, it can be called just in case. It returns
- * the number of handles that still transfer data in the second
- * argument's integer-pointer.
- *
- * Returns: CURLMcode type, general multi error code. *NOTE* that this only
- * returns errors etc regarding the whole multi stack. There might
- * still have occurred problems on invidual transfers even when this
- * returns OK.
- */
-CURL_EXTERN CURLMcode curl_multi_perform(CURLM *multi_handle,
- int *running_handles);
-
- /*
- * Name: curl_multi_cleanup()
- *
- * Desc: Cleans up and removes a whole multi stack. It does not free or
- * touch any individual easy handles in any way. We need to define
- * in what state those handles will be if this function is called
- * in the middle of a transfer.
- *
- * Returns: CURLMcode type, general multi error code.
- */
-CURL_EXTERN CURLMcode curl_multi_cleanup(CURLM *multi_handle);
-
-/*
- * Name: curl_multi_info_read()
- *
- * Desc: Ask the multi handle if there's any messages/informationals from
- * the individual transfers. Messages include informationals such as
- * error code from the transfer or just the fact that a transfer is
- * completed. More details on these should be written down as well.
- *
- * Repeated calls to this function will return a new struct each
- * time, until a special "end of msgs" struct is returned as a signal
- * that there is no more to get at this point.
- *
- * The data the returned pointer points to will not survive calling
- * curl_multi_cleanup().
- *
- * The 'CURLMsg' struct is meant to be very simple and only contain
- * very basic informations. If more involved information is wanted,
- * we will provide the particular "transfer handle" in that struct
- * and that should/could/would be used in subsequent
- * curl_easy_getinfo() calls (or similar). The point being that we
- * must never expose complex structs to applications, as then we'll
- * undoubtably get backwards compatibility problems in the future.
- *
- * Returns: A pointer to a filled-in struct, or NULL if it failed or ran out
- * of structs. It also writes the number of messages left in the
- * queue (after this read) in the integer the second argument points
- * to.
- */
-CURL_EXTERN CURLMsg *curl_multi_info_read(CURLM *multi_handle,
- int *msgs_in_queue);
-
-/*
- * Name: curl_multi_strerror()
- *
- * Desc: The curl_multi_strerror function may be used to turn a CURLMcode
- * value into the equivalent human readable error string. This is
- * useful for printing meaningful error messages.
- *
- * Returns: A pointer to a zero-terminated error message.
- */
-CURL_EXTERN const char *curl_multi_strerror(CURLMcode);
-
-/*
- * Name: curl_multi_socket() and
- * curl_multi_socket_all()
- *
- * Desc: An alternative version of curl_multi_perform() that allows the
- * application to pass in one of the file descriptors that have been
- * detected to have "action" on them and let libcurl perform.
- * See man page for details.
- */
-#define CURL_POLL_NONE 0
-#define CURL_POLL_IN 1
-#define CURL_POLL_OUT 2
-#define CURL_POLL_INOUT 3
-#define CURL_POLL_REMOVE 4
-
-#define CURL_SOCKET_TIMEOUT CURL_SOCKET_BAD
-
-#define CURL_CSELECT_IN 0x01
-#define CURL_CSELECT_OUT 0x02
-#define CURL_CSELECT_ERR 0x04
-
-typedef int (*curl_socket_callback)(CURL *easy, /* easy handle */
- curl_socket_t s, /* socket */
- int what, /* see above */
- void *userp, /* private callback
- pointer */
- void *socketp); /* private socket
- pointer */
-/*
- * Name: curl_multi_timer_callback
- *
- * Desc: Called by libcurl whenever the library detects a change in the
- * maximum number of milliseconds the app is allowed to wait before
- * curl_multi_socket() or curl_multi_perform() must be called
- * (to allow libcurl's timed events to take place).
- *
- * Returns: The callback should return zero.
- */
-typedef int (*curl_multi_timer_callback)(CURLM *multi, /* multi handle */
- long timeout_ms, /* see above */
- void *userp); /* private callback
- pointer */
-
-CURL_EXTERN CURLMcode curl_multi_socket(CURLM *multi_handle, curl_socket_t s,
- int *running_handles);
-
-CURL_EXTERN CURLMcode curl_multi_socket_action(CURLM *multi_handle,
- curl_socket_t s,
- int ev_bitmask,
- int *running_handles);
-
-CURL_EXTERN CURLMcode curl_multi_socket_all(CURLM *multi_handle,
- int *running_handles);
-
-#ifndef CURL_ALLOW_OLD_MULTI_SOCKET
-/* This macro below was added in 7.16.3 to push users who recompile to use
- the new curl_multi_socket_action() instead of the old curl_multi_socket()
-*/
-#define curl_multi_socket(x,y,z) curl_multi_socket_action(x,y,0,z)
-#endif
-
-/*
- * Name: curl_multi_timeout()
- *
- * Desc: Returns the maximum number of milliseconds the app is allowed to
- * wait before curl_multi_socket() or curl_multi_perform() must be
- * called (to allow libcurl's timed events to take place).
- *
- * Returns: CURLM error code.
- */
-CURL_EXTERN CURLMcode curl_multi_timeout(CURLM *multi_handle,
- long *milliseconds);
-
-#undef CINIT /* re-using the same name as in curl.h */
-
-#ifdef CURL_ISOCPP
-#define CINIT(name,type,num) CURLMOPT_ ## name = CURLOPTTYPE_ ## type + num
-#else
-/* The macro "##" is ISO C, we assume pre-ISO C doesn't support it. */
-#define LONG CURLOPTTYPE_LONG
-#define OBJECTPOINT CURLOPTTYPE_OBJECTPOINT
-#define FUNCTIONPOINT CURLOPTTYPE_FUNCTIONPOINT
-#define OFF_T CURLOPTTYPE_OFF_T
-#define CINIT(name,type,number) CURLMOPT_/**/name = type + number
-#endif
-
-typedef enum {
- /* This is the socket callback function pointer */
- CINIT(SOCKETFUNCTION, FUNCTIONPOINT, 1),
-
- /* This is the argument passed to the socket callback */
- CINIT(SOCKETDATA, OBJECTPOINT, 2),
-
- /* set to 1 to enable pipelining for this multi handle */
- CINIT(PIPELINING, LONG, 3),
-
- /* This is the timer callback function pointer */
- CINIT(TIMERFUNCTION, FUNCTIONPOINT, 4),
-
- /* This is the argument passed to the timer callback */
- CINIT(TIMERDATA, OBJECTPOINT, 5),
-
- /* maximum number of entries in the connection cache */
- CINIT(MAXCONNECTS, LONG, 6),
-
- CURLMOPT_LASTENTRY /* the last unused */
-} CURLMoption;
-
-
-/*
- * Name: curl_multi_setopt()
- *
- * Desc: Sets options for the multi handle.
- *
- * Returns: CURLM error code.
- */
-CURL_EXTERN CURLMcode curl_multi_setopt(CURLM *multi_handle,
- CURLMoption option, ...);
-
-
-/*
- * Name: curl_multi_assign()
- *
- * Desc: This function sets an association in the multi handle between the
- * given socket and a private pointer of the application. This is
- * (only) useful for curl_multi_socket uses.
- *
- * Returns: CURLM error code.
- */
-CURL_EXTERN CURLMcode curl_multi_assign(CURLM *multi_handle,
- curl_socket_t sockfd, void *sockp);
-
-#ifdef __cplusplus
-} /* end of extern "C" */
-#endif
-
-#endif
diff --git a/src/utils/curl/stdcheaders.h b/src/utils/curl/stdcheaders.h
deleted file mode 100644
index ad82ef6335d6167aecf8b9e49d68c462ea028bfd..0000000000000000000000000000000000000000
--- a/src/utils/curl/stdcheaders.h
+++ /dev/null
@@ -1,33 +0,0 @@
-#ifndef __STDC_HEADERS_H
-#define __STDC_HEADERS_H
-/***************************************************************************
- * _ _ ____ _
- * Project ___| | | | _ \| |
- * / __| | | | |_) | |
- * | (__| |_| | _ <| |___
- * \___|\___/|_| \_\_____|
- *
- * Copyright (C) 1998 - 2010, Daniel Stenberg, <daniel@haxx.se>, et al.
- *
- * This software is licensed as described in the file COPYING, which
- * you should have received as part of this distribution. The terms
- * are also available at http://curl.haxx.se/docs/copyright.html.
- *
- * You may opt to use, copy, modify, merge, publish, distribute and/or sell
- * copies of the Software, and permit persons to whom the Software is
- * furnished to do so, under the terms of the COPYING file.
- *
- * This software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY
- * KIND, either express or implied.
- *
- ***************************************************************************/
-
-#include <sys/types.h>
-
-size_t fread (void *, size_t, size_t, FILE *);
-size_t fwrite (const void *, size_t, size_t, FILE *);
-
-int strcasecmp(const char *, const char *);
-int strncasecmp(const char *, const char *, size_t);
-
-#endif /* __STDC_HEADERS_H */
diff --git a/src/utils/curl/typecheck-gcc.h b/src/utils/curl/typecheck-gcc.h
deleted file mode 100644
index c4fad516dd4e232983852213c51983e247b8e525..0000000000000000000000000000000000000000
--- a/src/utils/curl/typecheck-gcc.h
+++ /dev/null
@@ -1,550 +0,0 @@
-#ifndef __CURL_TYPECHECK_GCC_H
-#define __CURL_TYPECHECK_GCC_H
-/***************************************************************************
- * _ _ ____ _
- * Project ___| | | | _ \| |
- * / __| | | | |_) | |
- * | (__| |_| | _ <| |___
- * \___|\___/|_| \_\_____|
- *
- * Copyright (C) 1998 - 2009, Daniel Stenberg, <daniel@haxx.se>, et al.
- *
- * This software is licensed as described in the file COPYING, which
- * you should have received as part of this distribution. The terms
- * are also available at http://curl.haxx.se/docs/copyright.html.
- *
- * You may opt to use, copy, modify, merge, publish, distribute and/or sell
- * copies of the Software, and permit persons to whom the Software is
- * furnished to do so, under the terms of the COPYING file.
- *
- * This software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY
- * KIND, either express or implied.
- *
- ***************************************************************************/
-
-/* wraps curl_easy_setopt() with typechecking */
-
-/* To add a new kind of warning, add an
- * if(_curl_is_sometype_option(_curl_opt) && ! _curl_is_sometype(value))
- * _curl_easy_setopt_err_sometype();
- * block and define _curl_is_sometype_option, _curl_is_sometype and
- * _curl_easy_setopt_err_sometype below
- *
- * To add an option that uses the same type as an existing option, you'll just
- * need to extend the appropriate _curl_*_option macro
- */
-#define curl_easy_setopt(handle, option, value) \
-__extension__ ({ \
- __typeof__ (option) _curl_opt = option; \
- if (__builtin_constant_p(_curl_opt)) { \
- if (_curl_is_long_option(_curl_opt) && !_curl_is_long(value)) \
- _curl_easy_setopt_err_long(); \
- if (_curl_is_off_t_option(_curl_opt) && !_curl_is_off_t(value)) \
- _curl_easy_setopt_err_curl_off_t(); \
- if (_curl_is_string_option(_curl_opt) && !_curl_is_string(value)) \
- _curl_easy_setopt_err_string(); \
- if (_curl_is_write_cb_option(_curl_opt) && !_curl_is_write_cb(value)) \
- _curl_easy_setopt_err_write_callback(); \
- if ((_curl_opt) == CURLOPT_READFUNCTION && !_curl_is_read_cb(value)) \
- _curl_easy_setopt_err_read_cb(); \
- if ((_curl_opt) == CURLOPT_IOCTLFUNCTION && !_curl_is_ioctl_cb(value)) \
- _curl_easy_setopt_err_ioctl_cb(); \
- if ((_curl_opt) == CURLOPT_SOCKOPTFUNCTION && !_curl_is_sockopt_cb(value))\
- _curl_easy_setopt_err_sockopt_cb(); \
- if ((_curl_opt) == CURLOPT_OPENSOCKETFUNCTION && \
- !_curl_is_opensocket_cb(value)) \
- _curl_easy_setopt_err_opensocket_cb(); \
- if ((_curl_opt) == CURLOPT_PROGRESSFUNCTION && \
- !_curl_is_progress_cb(value)) \
- _curl_easy_setopt_err_progress_cb(); \
- if ((_curl_opt) == CURLOPT_DEBUGFUNCTION && !_curl_is_debug_cb(value)) \
- _curl_easy_setopt_err_debug_cb(); \
- if ((_curl_opt) == CURLOPT_SSL_CTX_FUNCTION && \
- !_curl_is_ssl_ctx_cb(value)) \
- _curl_easy_setopt_err_ssl_ctx_cb(); \
- if (_curl_is_conv_cb_option(_curl_opt) && !_curl_is_conv_cb(value)) \
- _curl_easy_setopt_err_conv_cb(); \
- if ((_curl_opt) == CURLOPT_SEEKFUNCTION && !_curl_is_seek_cb(value)) \
- _curl_easy_setopt_err_seek_cb(); \
- if (_curl_is_cb_data_option(_curl_opt) && !_curl_is_cb_data(value)) \
- _curl_easy_setopt_err_cb_data(); \
- if ((_curl_opt) == CURLOPT_ERRORBUFFER && !_curl_is_error_buffer(value)) \
- _curl_easy_setopt_err_error_buffer(); \
- if ((_curl_opt) == CURLOPT_STDERR && !_curl_is_FILE(value)) \
- _curl_easy_setopt_err_FILE(); \
- if (_curl_is_postfields_option(_curl_opt) && !_curl_is_postfields(value)) \
- _curl_easy_setopt_err_postfields(); \
- if ((_curl_opt) == CURLOPT_HTTPPOST && \
- !_curl_is_arr((value), struct curl_httppost)) \
- _curl_easy_setopt_err_curl_httpost(); \
- if (_curl_is_slist_option(_curl_opt) && \
- !_curl_is_arr((value), struct curl_slist)) \
- _curl_easy_setopt_err_curl_slist(); \
- if ((_curl_opt) == CURLOPT_SHARE && !_curl_is_ptr((value), CURLSH)) \
- _curl_easy_setopt_err_CURLSH(); \
- } \
- curl_easy_setopt(handle, _curl_opt, value); \
-})
-
-/* wraps curl_easy_getinfo() with typechecking */
-/* FIXME: don't allow const pointers */
-#define curl_easy_getinfo(handle, info, arg) \
-__extension__ ({ \
- __typeof__ (info) _curl_info = info; \
- if (__builtin_constant_p(_curl_info)) { \
- if (_curl_is_string_info(_curl_info) && !_curl_is_arr((arg), char *)) \
- _curl_easy_getinfo_err_string(); \
- if (_curl_is_long_info(_curl_info) && !_curl_is_arr((arg), long)) \
- _curl_easy_getinfo_err_long(); \
- if (_curl_is_double_info(_curl_info) && !_curl_is_arr((arg), double)) \
- _curl_easy_getinfo_err_double(); \
- if (_curl_is_slist_info(_curl_info) && \
- !_curl_is_arr((arg), struct curl_slist *)) \
- _curl_easy_getinfo_err_curl_slist(); \
- } \
- curl_easy_getinfo(handle, _curl_info, arg); \
-})
-
-/* TODO: typechecking for curl_share_setopt() and curl_multi_setopt(),
- * for now just make sure that the functions are called with three
- * arguments
- */
-#define curl_share_setopt(share,opt,param) curl_share_setopt(share,opt,param)
-#define curl_multi_setopt(handle,opt,param) curl_multi_setopt(handle,opt,param)
-
-
-/* the actual warnings, triggered by calling the _curl_easy_setopt_err*
- * functions */
-
-/* To define a new warning, use _CURL_WARNING(identifier, "message") */
-#define _CURL_WARNING(id, message) \
- static void __attribute__((warning(message))) __attribute__((unused)) \
- __attribute__((noinline)) id(void) { __asm__(""); }
-
-_CURL_WARNING(_curl_easy_setopt_err_long,
- "curl_easy_setopt expects a long argument for this option")
-_CURL_WARNING(_curl_easy_setopt_err_curl_off_t,
- "curl_easy_setopt expects a curl_off_t argument for this option")
-_CURL_WARNING(_curl_easy_setopt_err_string,
- "curl_easy_setopt expects a string (char* or char[]) argument for this option"
- )
-_CURL_WARNING(_curl_easy_setopt_err_write_callback,
- "curl_easy_setopt expects a curl_write_callback argument for this option")
-_CURL_WARNING(_curl_easy_setopt_err_read_cb,
- "curl_easy_setopt expects a curl_read_callback argument for this option")
-_CURL_WARNING(_curl_easy_setopt_err_ioctl_cb,
- "curl_easy_setopt expects a curl_ioctl_callback argument for this option")
-_CURL_WARNING(_curl_easy_setopt_err_sockopt_cb,
- "curl_easy_setopt expects a curl_sockopt_callback argument for this option")
-_CURL_WARNING(_curl_easy_setopt_err_opensocket_cb,
- "curl_easy_setopt expects a curl_opensocket_callback argument for this option"
- )
-_CURL_WARNING(_curl_easy_setopt_err_progress_cb,
- "curl_easy_setopt expects a curl_progress_callback argument for this option")
-_CURL_WARNING(_curl_easy_setopt_err_debug_cb,
- "curl_easy_setopt expects a curl_debug_callback argument for this option")
-_CURL_WARNING(_curl_easy_setopt_err_ssl_ctx_cb,
- "curl_easy_setopt expects a curl_ssl_ctx_callback argument for this option")
-_CURL_WARNING(_curl_easy_setopt_err_conv_cb,
- "curl_easy_setopt expects a curl_conv_callback argument for this option")
-_CURL_WARNING(_curl_easy_setopt_err_seek_cb,
- "curl_easy_setopt expects a curl_seek_callback argument for this option")
-_CURL_WARNING(_curl_easy_setopt_err_cb_data,
- "curl_easy_setopt expects a private data pointer as argument for this option")
-_CURL_WARNING(_curl_easy_setopt_err_error_buffer,
- "curl_easy_setopt expects a char buffer of CURL_ERROR_SIZE as argument for this option")
-_CURL_WARNING(_curl_easy_setopt_err_FILE,
- "curl_easy_setopt expects a FILE* argument for this option")
-_CURL_WARNING(_curl_easy_setopt_err_postfields,
- "curl_easy_setopt expects a void* or char* argument for this option")
-_CURL_WARNING(_curl_easy_setopt_err_curl_httpost,
- "curl_easy_setopt expects a struct curl_httppost* argument for this option")
-_CURL_WARNING(_curl_easy_setopt_err_curl_slist,
- "curl_easy_setopt expects a struct curl_slist* argument for this option")
-_CURL_WARNING(_curl_easy_setopt_err_CURLSH,
- "curl_easy_setopt expects a CURLSH* argument for this option")
-
-_CURL_WARNING(_curl_easy_getinfo_err_string,
- "curl_easy_getinfo expects a pointer to char * for this info")
-_CURL_WARNING(_curl_easy_getinfo_err_long,
- "curl_easy_getinfo expects a pointer to long for this info")
-_CURL_WARNING(_curl_easy_getinfo_err_double,
- "curl_easy_getinfo expects a pointer to double for this info")
-_CURL_WARNING(_curl_easy_getinfo_err_curl_slist,
- "curl_easy_getinfo expects a pointer to struct curl_slist * for this info")
-
-/* groups of curl_easy_setops options that take the same type of argument */
-
-/* To add a new option to one of the groups, just add
- * (option) == CURLOPT_SOMETHING
- * to the or-expression. If the option takes a long or curl_off_t, you don't
- * have to do anything
- */
-
-/* evaluates to true if option takes a long argument */
-#define _curl_is_long_option(option) \
- (0 < (option) && (option) < CURLOPTTYPE_OBJECTPOINT)
-
-#define _curl_is_off_t_option(option) \
- ((option) > CURLOPTTYPE_OFF_T)
-
-/* evaluates to true if option takes a char* argument */
-#define _curl_is_string_option(option) \
- ((option) == CURLOPT_URL || \
- (option) == CURLOPT_PROXY || \
- (option) == CURLOPT_INTERFACE || \
- (option) == CURLOPT_NETRC_FILE || \
- (option) == CURLOPT_USERPWD || \
- (option) == CURLOPT_USERNAME || \
- (option) == CURLOPT_PASSWORD || \
- (option) == CURLOPT_PROXYUSERPWD || \
- (option) == CURLOPT_PROXYUSERNAME || \
- (option) == CURLOPT_PROXYPASSWORD || \
- (option) == CURLOPT_NOPROXY || \
- (option) == CURLOPT_ENCODING || \
- (option) == CURLOPT_REFERER || \
- (option) == CURLOPT_USERAGENT || \
- (option) == CURLOPT_COOKIE || \
- (option) == CURLOPT_COOKIEFILE || \
- (option) == CURLOPT_COOKIEJAR || \
- (option) == CURLOPT_COOKIELIST || \
- (option) == CURLOPT_FTPPORT || \
- (option) == CURLOPT_FTP_ALTERNATIVE_TO_USER || \
- (option) == CURLOPT_FTP_ACCOUNT || \
- (option) == CURLOPT_RANGE || \
- (option) == CURLOPT_CUSTOMREQUEST || \
- (option) == CURLOPT_SSLCERT || \
- (option) == CURLOPT_SSLCERTTYPE || \
- (option) == CURLOPT_SSLKEY || \
- (option) == CURLOPT_SSLKEYTYPE || \
- (option) == CURLOPT_KEYPASSWD || \
- (option) == CURLOPT_SSLENGINE || \
- (option) == CURLOPT_CAINFO || \
- (option) == CURLOPT_CAPATH || \
- (option) == CURLOPT_RANDOM_FILE || \
- (option) == CURLOPT_EGDSOCKET || \
- (option) == CURLOPT_SSL_CIPHER_LIST || \
- (option) == CURLOPT_KRBLEVEL || \
- (option) == CURLOPT_SSH_HOST_PUBLIC_KEY_MD5 || \
- (option) == CURLOPT_SSH_PUBLIC_KEYFILE || \
- (option) == CURLOPT_SSH_PRIVATE_KEYFILE || \
- (option) == CURLOPT_CRLFILE || \
- (option) == CURLOPT_ISSUERCERT || \
- 0)
-
-/* evaluates to true if option takes a curl_write_callback argument */
-#define _curl_is_write_cb_option(option) \
- ((option) == CURLOPT_HEADERFUNCTION || \
- (option) == CURLOPT_WRITEFUNCTION)
-
-/* evaluates to true if option takes a curl_conv_callback argument */
-#define _curl_is_conv_cb_option(option) \
- ((option) == CURLOPT_CONV_TO_NETWORK_FUNCTION || \
- (option) == CURLOPT_CONV_FROM_NETWORK_FUNCTION || \
- (option) == CURLOPT_CONV_FROM_UTF8_FUNCTION)
-
-/* evaluates to true if option takes a data argument to pass to a callback */
-#define _curl_is_cb_data_option(option) \
- ((option) == CURLOPT_WRITEDATA || \
- (option) == CURLOPT_READDATA || \
- (option) == CURLOPT_IOCTLDATA || \
- (option) == CURLOPT_SOCKOPTDATA || \
- (option) == CURLOPT_OPENSOCKETDATA || \
- (option) == CURLOPT_PROGRESSDATA || \
- (option) == CURLOPT_WRITEHEADER || \
- (option) == CURLOPT_DEBUGDATA || \
- (option) == CURLOPT_SSL_CTX_DATA || \
- (option) == CURLOPT_SEEKDATA || \
- (option) == CURLOPT_PRIVATE || \
- 0)
-
-/* evaluates to true if option takes a POST data argument (void* or char*) */
-#define _curl_is_postfields_option(option) \
- ((option) == CURLOPT_POSTFIELDS || \
- (option) == CURLOPT_COPYPOSTFIELDS || \
- 0)
-
-/* evaluates to true if option takes a struct curl_slist * argument */
-#define _curl_is_slist_option(option) \
- ((option) == CURLOPT_HTTPHEADER || \
- (option) == CURLOPT_HTTP200ALIASES || \
- (option) == CURLOPT_QUOTE || \
- (option) == CURLOPT_POSTQUOTE || \
- (option) == CURLOPT_PREQUOTE || \
- (option) == CURLOPT_TELNETOPTIONS || \
- 0)
-
-/* groups of curl_easy_getinfo infos that take the same type of argument */
-
-/* evaluates to true if info expects a pointer to char * argument */
-#define _curl_is_string_info(info) \
- (CURLINFO_STRING < (info) && (info) < CURLINFO_LONG)
-
-/* evaluates to true if info expects a pointer to long argument */
-#define _curl_is_long_info(info) \
- (CURLINFO_LONG < (info) && (info) < CURLINFO_DOUBLE)
-
-/* evaluates to true if info expects a pointer to double argument */
-#define _curl_is_double_info(info) \
- (CURLINFO_DOUBLE < (info) && (info) < CURLINFO_SLIST)
-
-/* true if info expects a pointer to struct curl_slist * argument */
-#define _curl_is_slist_info(info) \
- (CURLINFO_SLIST < (info))
-
-
-/* typecheck helpers -- check whether given expression has requested type*/
-
-/* For pointers, you can use the _curl_is_ptr/_curl_is_arr macros,
- * otherwise define a new macro. Search for __builtin_types_compatible_p
- * in the GCC manual.
- * NOTE: these macros MUST NOT EVALUATE their arguments! The argument is
- * the actual expression passed to the curl_easy_setopt macro. This
- * means that you can only apply the sizeof and __typeof__ operators, no
- * == or whatsoever.
- */
-
-/* XXX: should evaluate to true iff expr is a pointer */
-#define _curl_is_any_ptr(expr) \
- (sizeof(expr) == sizeof(void*))
-
-/* evaluates to true if expr is NULL */
-/* XXX: must not evaluate expr, so this check is not accurate */
-#define _curl_is_NULL(expr) \
- (__builtin_types_compatible_p(__typeof__(expr), __typeof__(NULL)))
-
-/* evaluates to true if expr is type*, const type* or NULL */
-#define _curl_is_ptr(expr, type) \
- (_curl_is_NULL(expr) || \
- __builtin_types_compatible_p(__typeof__(expr), type *) || \
- __builtin_types_compatible_p(__typeof__(expr), const type *))
-
-/* evaluates to true if expr is one of type[], type*, NULL or const type* */
-#define _curl_is_arr(expr, type) \
- (_curl_is_ptr((expr), type) || \
- __builtin_types_compatible_p(__typeof__(expr), type []))
-
-/* evaluates to true if expr is a string */
-#define _curl_is_string(expr) \
- (_curl_is_arr((expr), char) || \
- _curl_is_arr((expr), signed char) || \
- _curl_is_arr((expr), unsigned char))
-
-/* evaluates to true if expr is a long (no matter the signedness)
- * XXX: for now, int is also accepted (and therefore short and char, which
- * are promoted to int when passed to a variadic function) */
-#define _curl_is_long(expr) \
- (__builtin_types_compatible_p(__typeof__(expr), long) || \
- __builtin_types_compatible_p(__typeof__(expr), signed long) || \
- __builtin_types_compatible_p(__typeof__(expr), unsigned long) || \
- __builtin_types_compatible_p(__typeof__(expr), int) || \
- __builtin_types_compatible_p(__typeof__(expr), signed int) || \
- __builtin_types_compatible_p(__typeof__(expr), unsigned int) || \
- __builtin_types_compatible_p(__typeof__(expr), short) || \
- __builtin_types_compatible_p(__typeof__(expr), signed short) || \
- __builtin_types_compatible_p(__typeof__(expr), unsigned short) || \
- __builtin_types_compatible_p(__typeof__(expr), char) || \
- __builtin_types_compatible_p(__typeof__(expr), signed char) || \
- __builtin_types_compatible_p(__typeof__(expr), unsigned char))
-
-/* evaluates to true if expr is of type curl_off_t */
-#define _curl_is_off_t(expr) \
- (__builtin_types_compatible_p(__typeof__(expr), curl_off_t))
-
-/* evaluates to true if expr is abuffer suitable for CURLOPT_ERRORBUFFER */
-/* XXX: also check size of an char[] array? */
-#define _curl_is_error_buffer(expr) \
- (__builtin_types_compatible_p(__typeof__(expr), char *) || \
- __builtin_types_compatible_p(__typeof__(expr), char[]))
-
-/* evaluates to true if expr is of type (const) void* or (const) FILE* */
-#if 0
-#define _curl_is_cb_data(expr) \
- (_curl_is_ptr((expr), void) || \
- _curl_is_ptr((expr), FILE))
-#else /* be less strict */
-#define _curl_is_cb_data(expr) \
- _curl_is_any_ptr(expr)
-#endif
-
-/* evaluates to true if expr is of type FILE* */
-#define _curl_is_FILE(expr) \
- (__builtin_types_compatible_p(__typeof__(expr), FILE *))
-
-/* evaluates to true if expr can be passed as POST data (void* or char*) */
-#define _curl_is_postfields(expr) \
- (_curl_is_ptr((expr), void) || \
- _curl_is_arr((expr), char))
-
-/* FIXME: the whole callback checking is messy...
- * The idea is to tolerate char vs. void and const vs. not const
- * pointers in arguments at least
- */
-/* helper: __builtin_types_compatible_p distinguishes between functions and
- * function pointers, hide it */
-#define _curl_callback_compatible(func, type) \
- (__builtin_types_compatible_p(__typeof__(func), type) || \
- __builtin_types_compatible_p(__typeof__(func), type*))
-
-/* evaluates to true if expr is of type curl_read_callback or "similar" */
-#define _curl_is_read_cb(expr) \
- (_curl_is_NULL(expr) || \
- __builtin_types_compatible_p(__typeof__(expr), __typeof__(fread)) || \
- __builtin_types_compatible_p(__typeof__(expr), curl_read_callback) || \
- _curl_callback_compatible((expr), _curl_read_callback1) || \
- _curl_callback_compatible((expr), _curl_read_callback2) || \
- _curl_callback_compatible((expr), _curl_read_callback3) || \
- _curl_callback_compatible((expr), _curl_read_callback4) || \
- _curl_callback_compatible((expr), _curl_read_callback5) || \
- _curl_callback_compatible((expr), _curl_read_callback6))
-typedef size_t (_curl_read_callback1)(char *, size_t, size_t, void*);
-typedef size_t (_curl_read_callback2)(char *, size_t, size_t, const void*);
-typedef size_t (_curl_read_callback3)(char *, size_t, size_t, FILE*);
-typedef size_t (_curl_read_callback4)(void *, size_t, size_t, void*);
-typedef size_t (_curl_read_callback5)(void *, size_t, size_t, const void*);
-typedef size_t (_curl_read_callback6)(void *, size_t, size_t, FILE*);
-
-/* evaluates to true if expr is of type curl_write_callback or "similar" */
-#define _curl_is_write_cb(expr) \
- (_curl_is_read_cb(expr) || \
- __builtin_types_compatible_p(__typeof__(expr), __typeof__(fwrite)) || \
- __builtin_types_compatible_p(__typeof__(expr), curl_write_callback) || \
- _curl_callback_compatible((expr), _curl_write_callback1) || \
- _curl_callback_compatible((expr), _curl_write_callback2) || \
- _curl_callback_compatible((expr), _curl_write_callback3) || \
- _curl_callback_compatible((expr), _curl_write_callback4) || \
- _curl_callback_compatible((expr), _curl_write_callback5) || \
- _curl_callback_compatible((expr), _curl_write_callback6))
-typedef size_t (_curl_write_callback1)(const char *, size_t, size_t, void*);
-typedef size_t (_curl_write_callback2)(const char *, size_t, size_t,
- const void*);
-typedef size_t (_curl_write_callback3)(const char *, size_t, size_t, FILE*);
-typedef size_t (_curl_write_callback4)(const void *, size_t, size_t, void*);
-typedef size_t (_curl_write_callback5)(const void *, size_t, size_t,
- const void*);
-typedef size_t (_curl_write_callback6)(const void *, size_t, size_t, FILE*);
-
-/* evaluates to true if expr is of type curl_ioctl_callback or "similar" */
-#define _curl_is_ioctl_cb(expr) \
- (_curl_is_NULL(expr) || \
- __builtin_types_compatible_p(__typeof__(expr), curl_ioctl_callback) || \
- _curl_callback_compatible((expr), _curl_ioctl_callback1) || \
- _curl_callback_compatible((expr), _curl_ioctl_callback2) || \
- _curl_callback_compatible((expr), _curl_ioctl_callback3) || \
- _curl_callback_compatible((expr), _curl_ioctl_callback4))
-typedef curlioerr (_curl_ioctl_callback1)(CURL *, int, void*);
-typedef curlioerr (_curl_ioctl_callback2)(CURL *, int, const void*);
-typedef curlioerr (_curl_ioctl_callback3)(CURL *, curliocmd, void*);
-typedef curlioerr (_curl_ioctl_callback4)(CURL *, curliocmd, const void*);
-
-/* evaluates to true if expr is of type curl_sockopt_callback or "similar" */
-#define _curl_is_sockopt_cb(expr) \
- (_curl_is_NULL(expr) || \
- __builtin_types_compatible_p(__typeof__(expr), curl_sockopt_callback) || \
- _curl_callback_compatible((expr), _curl_sockopt_callback1) || \
- _curl_callback_compatible((expr), _curl_sockopt_callback2))
-typedef int (_curl_sockopt_callback1)(void *, curl_socket_t, curlsocktype);
-typedef int (_curl_sockopt_callback2)(const void *, curl_socket_t,
- curlsocktype);
-
-/* evaluates to true if expr is of type curl_opensocket_callback or "similar" */
-#define _curl_is_opensocket_cb(expr) \
- (_curl_is_NULL(expr) || \
- __builtin_types_compatible_p(__typeof__(expr), curl_opensocket_callback) ||\
- _curl_callback_compatible((expr), _curl_opensocket_callback1) || \
- _curl_callback_compatible((expr), _curl_opensocket_callback2) || \
- _curl_callback_compatible((expr), _curl_opensocket_callback3) || \
- _curl_callback_compatible((expr), _curl_opensocket_callback4))
-typedef curl_socket_t (_curl_opensocket_callback1)
- (void *, curlsocktype, struct curl_sockaddr *);
-typedef curl_socket_t (_curl_opensocket_callback2)
- (void *, curlsocktype, const struct curl_sockaddr *);
-typedef curl_socket_t (_curl_opensocket_callback3)
- (const void *, curlsocktype, struct curl_sockaddr *);
-typedef curl_socket_t (_curl_opensocket_callback4)
- (const void *, curlsocktype, const struct curl_sockaddr *);
-
-/* evaluates to true if expr is of type curl_progress_callback or "similar" */
-#define _curl_is_progress_cb(expr) \
- (_curl_is_NULL(expr) || \
- __builtin_types_compatible_p(__typeof__(expr), curl_progress_callback) || \
- _curl_callback_compatible((expr), _curl_progress_callback1) || \
- _curl_callback_compatible((expr), _curl_progress_callback2))
-typedef int (_curl_progress_callback1)(void *,
- double, double, double, double);
-typedef int (_curl_progress_callback2)(const void *,
- double, double, double, double);
-
-/* evaluates to true if expr is of type curl_debug_callback or "similar" */
-#define _curl_is_debug_cb(expr) \
- (_curl_is_NULL(expr) || \
- __builtin_types_compatible_p(__typeof__(expr), curl_debug_callback) || \
- _curl_callback_compatible((expr), _curl_debug_callback1) || \
- _curl_callback_compatible((expr), _curl_debug_callback2) || \
- _curl_callback_compatible((expr), _curl_debug_callback3) || \
- _curl_callback_compatible((expr), _curl_debug_callback4))
-typedef int (_curl_debug_callback1) (CURL *,
- curl_infotype, char *, size_t, void *);
-typedef int (_curl_debug_callback2) (CURL *,
- curl_infotype, char *, size_t, const void *);
-typedef int (_curl_debug_callback3) (CURL *,
- curl_infotype, const char *, size_t, void *);
-typedef int (_curl_debug_callback4) (CURL *,
- curl_infotype, const char *, size_t, const void *);
-
-/* evaluates to true if expr is of type curl_ssl_ctx_callback or "similar" */
-/* this is getting even messier... */
-#define _curl_is_ssl_ctx_cb(expr) \
- (_curl_is_NULL(expr) || \
- __builtin_types_compatible_p(__typeof__(expr), curl_ssl_ctx_callback) || \
- _curl_callback_compatible((expr), _curl_ssl_ctx_callback1) || \
- _curl_callback_compatible((expr), _curl_ssl_ctx_callback2) || \
- _curl_callback_compatible((expr), _curl_ssl_ctx_callback3) || \
- _curl_callback_compatible((expr), _curl_ssl_ctx_callback4) || \
- _curl_callback_compatible((expr), _curl_ssl_ctx_callback5) || \
- _curl_callback_compatible((expr), _curl_ssl_ctx_callback6) || \
- _curl_callback_compatible((expr), _curl_ssl_ctx_callback7) || \
- _curl_callback_compatible((expr), _curl_ssl_ctx_callback8))
-typedef CURLcode (_curl_ssl_ctx_callback1)(CURL *, void *, void *);
-typedef CURLcode (_curl_ssl_ctx_callback2)(CURL *, void *, const void *);
-typedef CURLcode (_curl_ssl_ctx_callback3)(CURL *, const void *, void *);
-typedef CURLcode (_curl_ssl_ctx_callback4)(CURL *, const void *, const void *);
-#ifdef HEADER_SSL_H
-/* hack: if we included OpenSSL's ssl.h, we know about SSL_CTX
- * this will of course break if we're included before OpenSSL headers...
- */
-typedef CURLcode (_curl_ssl_ctx_callback5)(CURL *, SSL_CTX, void *);
-typedef CURLcode (_curl_ssl_ctx_callback6)(CURL *, SSL_CTX, const void *);
-typedef CURLcode (_curl_ssl_ctx_callback7)(CURL *, const SSL_CTX, void *);
-typedef CURLcode (_curl_ssl_ctx_callback8)(CURL *, const SSL_CTX, const void *);
-#else
-typedef _curl_ssl_ctx_callback1 _curl_ssl_ctx_callback5;
-typedef _curl_ssl_ctx_callback1 _curl_ssl_ctx_callback6;
-typedef _curl_ssl_ctx_callback1 _curl_ssl_ctx_callback7;
-typedef _curl_ssl_ctx_callback1 _curl_ssl_ctx_callback8;
-#endif
-
-/* evaluates to true if expr is of type curl_conv_callback or "similar" */
-#define _curl_is_conv_cb(expr) \
- (_curl_is_NULL(expr) || \
- __builtin_types_compatible_p(__typeof__(expr), curl_conv_callback) || \
- _curl_callback_compatible((expr), _curl_conv_callback1) || \
- _curl_callback_compatible((expr), _curl_conv_callback2) || \
- _curl_callback_compatible((expr), _curl_conv_callback3) || \
- _curl_callback_compatible((expr), _curl_conv_callback4))
-typedef CURLcode (*_curl_conv_callback1)(char *, size_t length);
-typedef CURLcode (*_curl_conv_callback2)(const char *, size_t length);
-typedef CURLcode (*_curl_conv_callback3)(void *, size_t length);
-typedef CURLcode (*_curl_conv_callback4)(const void *, size_t length);
-
-/* evaluates to true if expr is of type curl_seek_callback or "similar" */
-#define _curl_is_seek_cb(expr) \
- (_curl_is_NULL(expr) || \
- __builtin_types_compatible_p(__typeof__(expr), curl_seek_callback) || \
- _curl_callback_compatible((expr), _curl_seek_callback1) || \
- _curl_callback_compatible((expr), _curl_seek_callback2))
-typedef CURLcode (*_curl_seek_callback1)(void *, curl_off_t, int);
-typedef CURLcode (*_curl_seek_callback2)(const void *, curl_off_t, int);
-
-
-#endif /* __CURL_TYPECHECK_GCC_H */
diff --git a/src/utils/curl/types.h b/src/utils/curl/types.h
deleted file mode 100644
index d37d6ae9e11e48d3f8aaba1957015a03f7f12c63..0000000000000000000000000000000000000000
--- a/src/utils/curl/types.h
+++ /dev/null
@@ -1 +0,0 @@
-/* not used */
diff --git a/src/utils/fileType/fileType.h b/src/utils/fileType/fileType.h
index 3642a4ba3e830cb1f8cdececd6b622f6505fb10e..adf2d6215fd1e277375dbc0d20b74baf4f08a679 100644
--- a/src/utils/fileType/fileType.h
+++ b/src/utils/fileType/fileType.h
@@ -26,9 +26,9 @@
using namespace std;
/*****************************************************************************
- Convenience functions to detect whether a given file is
+ Convenience functions to detect whether a given file is
"regular" and/or "gzipped".
-
+
Kindly contributed by Assaf Gordon.
******************************************************************************/
string string_error(int errnum);
diff --git a/src/utils/genomeFile/genomeFile.cpp b/src/utils/genomeFile/genomeFile.cpp
index 5a69736078383240bdebf10d97a6310b9766b1dc..67a280ea1b681c7caf286e9159db413f9288478a 100644
--- a/src/utils/genomeFile/genomeFile.cpp
+++ b/src/utils/genomeFile/genomeFile.cpp
@@ -14,8 +14,8 @@
GenomeFile::GenomeFile(const string &genomeFile) {
- _genomeFile = genomeFile;
- loadGenomeFileIntoMap();
+ _genomeFile = genomeFile;
+ loadGenomeFileIntoMap();
}
// Destructor
@@ -25,69 +25,69 @@ GenomeFile::~GenomeFile(void) {
void GenomeFile::loadGenomeFileIntoMap() {
- string genomeLine;
- int lineNum = 0;
- vector<string> genomeFields; // vector for a GENOME entry
-
- // open the GENOME file for reading
- ifstream genome(_genomeFile.c_str(), ios::in);
- if ( !genome ) {
- cerr << "Error: The requested genome file (" << _genomeFile << ") could not be opened. Exiting!" << endl;
- exit (1);
- }
-
- while (getline(genome, genomeLine)) {
-
- Tokenize(genomeLine,genomeFields); // load the fields into the vector
- lineNum++;
-
- // ignore a blank line
- if (genomeFields.size() > 0) {
- if (genomeFields[0].find("#") == string::npos) {
-
- // we need at least 2 columns
- if (genomeFields.size() >= 2) {
- char *p2End;
- long c2;
- // make sure the second column is numeric.
- c2 = strtol(genomeFields[1].c_str(), &p2End, 10);
-
- // strtol will set p2End to the start of the string if non-integral, base 10
- if (p2End != genomeFields[1].c_str()) {
- string chrom = genomeFields[0];
- int size = atoi(genomeFields[1].c_str());
- _chromSizes[chrom] = size;
- _chromList.push_back(chrom);
- }
- }
- else {
- cerr << "Less than the req'd two fields were encountered in the genome file (" << _genomeFile << ")";
- cerr << " at line " << lineNum << ". Exiting." << endl;
- exit (1);
- }
- }
- }
- genomeFields.clear();
- }
+ string genomeLine;
+ int lineNum = 0;
+ vector<string> genomeFields; // vector for a GENOME entry
+
+ // open the GENOME file for reading
+ ifstream genome(_genomeFile.c_str(), ios::in);
+ if ( !genome ) {
+ cerr << "Error: The requested genome file (" << _genomeFile << ") could not be opened. Exiting!" << endl;
+ exit (1);
+ }
+
+ while (getline(genome, genomeLine)) {
+
+ Tokenize(genomeLine,genomeFields); // load the fields into the vector
+ lineNum++;
+
+ // ignore a blank line
+ if (genomeFields.size() > 0) {
+ if (genomeFields[0].find("#") == string::npos) {
+
+ // we need at least 2 columns
+ if (genomeFields.size() >= 2) {
+ char *p2End;
+ long c2;
+ // make sure the second column is numeric.
+ c2 = strtol(genomeFields[1].c_str(), &p2End, 10);
+
+ // strtol will set p2End to the start of the string if non-integral, base 10
+ if (p2End != genomeFields[1].c_str()) {
+ string chrom = genomeFields[0];
+ int size = atoi(genomeFields[1].c_str());
+ _chromSizes[chrom] = size;
+ _chromList.push_back(chrom);
+ }
+ }
+ else {
+ cerr << "Less than the req'd two fields were encountered in the genome file (" << _genomeFile << ")";
+ cerr << " at line " << lineNum << ". Exiting." << endl;
+ exit (1);
+ }
+ }
+ }
+ genomeFields.clear();
+ }
}
int GenomeFile::getChromSize(const string &chrom) {
- chromToSizes::const_iterator chromIt = _chromSizes.find(chrom);
- if (chromIt != _chromSizes.end())
- return _chromSizes[chrom];
- else
- return -1; // chrom not found.
+ chromToSizes::const_iterator chromIt = _chromSizes.find(chrom);
+ if (chromIt != _chromSizes.end())
+ return _chromSizes[chrom];
+ else
+ return -1; // chrom not found.
}
vector<string> GenomeFile::getChromList() {
- return _chromList;
+ return _chromList;
}
int GenomeFile::getNumberOfChroms() {
- return _chromList.size();
+ return _chromList.size();
}
string GenomeFile::getGenomeFileName() {
- return _genomeFile;
+ return _genomeFile;
}
diff --git a/src/utils/genomeFile/genomeFile.h b/src/utils/genomeFile/genomeFile.h
index 9f88f67024635e150fc7b26d8a9f88d04cbe3e85..5da8d6b968c046e046dfca0b46619d18699dcf92 100644
--- a/src/utils/genomeFile/genomeFile.h
+++ b/src/utils/genomeFile/genomeFile.h
@@ -31,26 +31,26 @@ class GenomeFile {
public:
- // Constructor
- GenomeFile(const string &genomeFile);
+ // Constructor
+ GenomeFile(const string &genomeFile);
- // Destructor
- ~GenomeFile(void);
+ // Destructor
+ ~GenomeFile(void);
- // load a GENOME file into a map keyed by chrom. value is size of chrom.
- void loadGenomeFileIntoMap();
+ // load a GENOME file into a map keyed by chrom. value is size of chrom.
+ void loadGenomeFileIntoMap();
+
+ int getChromSize(const string &chrom); // return the size of a chromosome
+ vector<string> getChromList(); // return a list of chrom names
+ int getNumberOfChroms(); // return the number of chroms
+ string getGenomeFileName(); // return the name of the genome file
- int getChromSize(const string &chrom); // return the size of a chromosome
- vector<string> getChromList(); // return a list of chrom names
- int getNumberOfChroms(); // return the number of chroms
- string getGenomeFileName(); // return the name of the genome file
-
private:
- string _genomeFile;
- chromToSizes _chromSizes;
- vector<string> _chromList;
+ string _genomeFile;
+ chromToSizes _chromSizes;
+ vector<string> _chromList;
};
#endif /* GENOMEFILE_H */
diff --git a/src/utils/gzstream/gzstream.C b/src/utils/gzstream/gzstream.C
index 8cb4590e1fb704dd0a3087448b8ee2c8d44c3297..4633c0e928cdcadb16397498081a5d393b3b0897 100644
--- a/src/utils/gzstream/gzstream.C
+++ b/src/utils/gzstream/gzstream.C
@@ -21,8 +21,8 @@
// Revision : $Revision: 1.7 $
// Revision_date : $Date: 2003/01/08 14:41:27 $
// Author(s) : Deepak Bandyopadhyay, Lutz Kettner
-//
-// Standard streambuf implementation following Nicolai Josuttis, "The
+//
+// Standard streambuf implementation following Nicolai Josuttis, "The
// Standard C++ Library".
// ============================================================================
@@ -97,7 +97,7 @@ int gzstreambuf::underflow() { // used for input buffer only
buffer + 4 + num); // end of buffer
// return next character
- return * reinterpret_cast<unsigned char *>( gptr());
+ return * reinterpret_cast<unsigned char *>( gptr());
}
int gzstreambuf::flush_buffer() {
diff --git a/src/utils/gzstream/gzstream.h b/src/utils/gzstream/gzstream.h
index 861653f4810f244e60ec1e049ec60bc903a573ce..85910712151bc6fdd16ab8ca2eb7430a9f0a3155 100644
--- a/src/utils/gzstream/gzstream.h
+++ b/src/utils/gzstream/gzstream.h
@@ -21,8 +21,8 @@
// Revision : $Revision: 1.5 $
// Revision_date : $Date: 2002/04/26 23:30:15 $
// Author(s) : Deepak Bandyopadhyay, Lutz Kettner
-//
-// Standard streambuf implementation following Nicolai Josuttis, "The
+//
+// Standard streambuf implementation following Nicolai Josuttis, "The
// Standard C++ Library".
// ============================================================================
@@ -58,14 +58,14 @@ public:
setp( buffer, buffer + (bufferSize-1));
setg( buffer + 4, // beginning of putback area
buffer + 4, // read position
- buffer + 4); // end position
+ buffer + 4); // end position
// ASSERT: both input & output capabilities will not be used together
}
int is_open() { return opened; }
gzstreambuf* open( const char* name, int open_mode);
gzstreambuf* close();
~gzstreambuf() { close(); }
-
+
virtual int overflow( int c = EOF);
virtual int underflow();
virtual int sync();
@@ -85,15 +85,15 @@ public:
// ----------------------------------------------------------------------------
// User classes. Use igzstream and ogzstream analogously to ifstream and
-// ofstream respectively. They read and write files based on the gz*
+// ofstream respectively. They read and write files based on the gz*
// function interface of the zlib. Files are compatible with gzip compression.
// ----------------------------------------------------------------------------
class igzstream : public gzstreambase, public std::istream {
public:
- igzstream() : std::istream( &buf) {}
+ igzstream() : std::istream( &buf) {}
igzstream( const char* name, int open_mode = std::ios::in)
- : gzstreambase( name, open_mode), std::istream( &buf) {}
+ : gzstreambase( name, open_mode), std::istream( &buf) {}
gzstreambuf* rdbuf() { return gzstreambase::rdbuf(); }
void open( const char* name, int open_mode = std::ios::in) {
gzstreambase::open( name, open_mode);
@@ -104,7 +104,7 @@ class ogzstream : public gzstreambase, public std::ostream {
public:
ogzstream() : std::ostream( &buf) {}
ogzstream( const char* name, int mode = std::ios::out)
- : gzstreambase( name, mode), std::ostream( &buf) {}
+ : gzstreambase( name, mode), std::ostream( &buf) {}
gzstreambuf* rdbuf() { return gzstreambase::rdbuf(); }
void open( const char* name, int open_mode = std::ios::out) {
gzstreambase::open( name, open_mode);
diff --git a/src/utils/lineFileUtilities/lineFileUtilities.cpp b/src/utils/lineFileUtilities/lineFileUtilities.cpp
index 3c80fef6296dda942e94d78d0582cbbcbeec92db..81cb6595f23cb964d2b9e953ac47a84c0903889d 100644
--- a/src/utils/lineFileUtilities/lineFileUtilities.cpp
+++ b/src/utils/lineFileUtilities/lineFileUtilities.cpp
@@ -1,7 +1,7 @@
-//
+//
// lineFileUtilities.cpp
// BEDTools
-//
+//
// Created by Aaron Quinlan Spring 2009.
// Copyright 2009 Aaron Quinlan. All rights reserved.
//
@@ -12,7 +12,7 @@
#include "lineFileUtilities.h"
//***********************************************
// lineFileUtilities:
-// Common Functions
+// Common Functions
//***********************************************
// void Tokenize(const string &str, vector<string> &tokens, const string &delimiter) {
@@ -20,7 +20,7 @@
// string::size_type lastPos = str.find_first_not_of(delimiter, 0);
// // Find first "non-delimiter".
// string::size_type pos = str.find_first_of(delimiter, lastPos);
-//
+//
// while (string::npos != pos || string::npos != lastPos) {
// // Found a token, add it to the vector.
// tokens.push_back(str.substr(lastPos, pos - lastPos));
@@ -30,13 +30,13 @@
// pos = str.find_first_of(delimiter, lastPos);
// }
// }
-//
+//
// void Tokenize(const string &str, vector<int> &tokens, const string &delimiter) {
// // Skip delimiters at beginning.
// string::size_type lastPos = str.find_first_not_of(delimiter, 0);
// // Find first "non-delimiter".
// string::size_type pos = str.find_first_of(delimiter, lastPos);
-//
+//
// while (string::npos != pos || string::npos != lastPos) {
// // Found a token, add it to the vector.
// tokens.push_back(atoi(str.substr(lastPos, pos - lastPos).c_str()));
diff --git a/src/utils/lineFileUtilities/lineFileUtilities.h b/src/utils/lineFileUtilities/lineFileUtilities.h
index f1aac59ea1903aad3ca873fe1e203fb7560dcf8b..97d3a5209453fc168054699c46d29963728dbc84 100644
--- a/src/utils/lineFileUtilities/lineFileUtilities.h
+++ b/src/utils/lineFileUtilities/lineFileUtilities.h
@@ -16,26 +16,26 @@ using namespace std;
template <typename T>
inline
std::string ToString(const T & value) {
- std::stringstream ss;
- ss << value;
- return ss.str();
+ std::stringstream ss;
+ ss << value;
+ return ss.str();
}
inline
void Tokenize(const string &str, vector<string> &tokens, const string &delimiter = "\t") {
- // Skip delimiters at beginning.
- string::size_type lastPos = str.find_first_not_of(delimiter, 0);
- // Find first "non-delimiter".
- string::size_type pos = str.find_first_of(delimiter, lastPos);
-
- while (string::npos != pos || string::npos != lastPos) {
- // Found a token, add it to the vector.
- tokens.push_back(str.substr(lastPos, pos - lastPos));
- // Skip delimiters. Note the "not_of"
- lastPos = str.find_first_not_of(delimiter, pos);
- // Find next "non-delimiter"
- pos = str.find_first_of(delimiter, lastPos);
- }
+ // Skip delimiters at beginning.
+ string::size_type lastPos = str.find_first_not_of(delimiter, 0);
+ // Find first "non-delimiter".
+ string::size_type pos = str.find_first_of(delimiter, lastPos);
+
+ while (string::npos != pos || string::npos != lastPos) {
+ // Found a token, add it to the vector.
+ tokens.push_back(str.substr(lastPos, pos - lastPos));
+ // Skip delimiters. Note the "not_of"
+ lastPos = str.find_first_not_of(delimiter, pos);
+ // Find next "non-delimiter"
+ pos = str.find_first_of(delimiter, lastPos);
+ }
}
inline
diff --git a/src/utils/sequenceUtilities/sequenceUtils.cpp b/src/utils/sequenceUtilities/sequenceUtils.cpp
index e43b57c3dd8d648089bad7943e1427f493f99c4a..1995c119cc9c28feb5d75e47d2235ea92c1ae9b0 100644
--- a/src/utils/sequenceUtilities/sequenceUtils.cpp
+++ b/src/utils/sequenceUtilities/sequenceUtils.cpp
@@ -1,7 +1,7 @@
-//
+//
// sequenceUtils.cpp
// BEDTools
-//
+//
// Created by Aaron Quinlan Spring 2009.
// Copyright 2009 Aaron Quinlan. All rights reserved.
//
@@ -14,72 +14,72 @@
// Performs an in-place sequence reversal
void reverseSequence(string &sequence) {
- std::reverse(sequence.begin(), sequence.end());
+ std::reverse(sequence.begin(), sequence.end());
}
// Performs an in-place reverse complement conversion
void reverseComplement(string &sequence) {
- // reverse the sequence
- reverseSequence(sequence);
+ // reverse the sequence
+ reverseSequence(sequence);
- // swap the bases
- for(unsigned int i = 0; i < sequence.length(); i++) {
- switch(sequence[i]) {
- case 'A':
- sequence[i] = 'T';
- break;
- case 'C':
- sequence[i] = 'G';
- break;
- case 'G':
- sequence[i] = 'C';
- break;
- case 'T':
- sequence[i] = 'A';
- break;
- case 'a':
- sequence[i] = 't';
- break;
- case 'c':
- sequence[i] = 'g';
- break;
- case 'g':
- sequence[i] = 'c';
- break;
- case 't':
- sequence[i] = 'a';
- break;
- default:
- break;
- }
- }
+ // swap the bases
+ for(unsigned int i = 0; i < sequence.length(); i++) {
+ switch(sequence[i]) {
+ case 'A':
+ sequence[i] = 'T';
+ break;
+ case 'C':
+ sequence[i] = 'G';
+ break;
+ case 'G':
+ sequence[i] = 'C';
+ break;
+ case 'T':
+ sequence[i] = 'A';
+ break;
+ case 'a':
+ sequence[i] = 't';
+ break;
+ case 'c':
+ sequence[i] = 'g';
+ break;
+ case 'g':
+ sequence[i] = 'c';
+ break;
+ case 't':
+ sequence[i] = 'a';
+ break;
+ default:
+ break;
+ }
+ }
}
void toLowerCase(std::string &str)
{
-
- const int length = str.length();
- for(int i=0; i < length; ++i)
- {
- str[i] = std::tolower(str[i]);
- }
-
- // alternate, C++ style.
- //transform(str.start(), str.end(), str.start(), std::tolower);
+
+ const int length = str.length();
+ for(int i=0; i < length; ++i)
+ {
+ str[i] = std::tolower(str[i]);
+ }
+
+ // alternate, C++ style.
+ //transform(str.start(), str.end(), str.start(), std::tolower);
}
void toUpperCase(std::string &str)
{
-
- const int length = str.length();
- for(int i=0; i < length; ++i)
- {
- str[i] = std::toupper(str[i]);
- }
-
- // alternate, C++ style.
- //transform(str.start(), str.end(), str.start(), std::toupper);
+
+ const int length = str.length();
+ for(int i=0; i < length; ++i)
+ {
+ str[i] = std::toupper(str[i]);
+ }
+
+ // alternate, C++ style.
+ //transform(str.start(), str.end(), str.start(), std::toupper);
}
diff --git a/src/utils/sequenceUtilities/sequenceUtils.h b/src/utils/sequenceUtilities/sequenceUtils.h
index d71383f9035fd45035f5515bbf076e520d7f8592..206e0fc8d371ce0114c53dcefc3232ad3a9a717b 100644
--- a/src/utils/sequenceUtilities/sequenceUtils.h
+++ b/src/utils/sequenceUtilities/sequenceUtils.h
@@ -19,4 +19,4 @@ void toLowerCase(string &);
// Converts every character in a string to uppercase
void toUpperCase(string &);
-#endif
+#endif
diff --git a/src/utils/tabFile/tabFile.cpp b/src/utils/tabFile/tabFile.cpp
index c14b12d692bc97a9e47cc50c19623bb365ceece0..7e444426982605268971856039b62f649e3b4b59 100644
--- a/src/utils/tabFile/tabFile.cpp
+++ b/src/utils/tabFile/tabFile.cpp
@@ -27,73 +27,73 @@ TabFile::~TabFile(void) {
void TabFile::Open(void) {
- if (_tabFile == "stdin") {
- _tabStream = &cin;
- }
- else {
- size_t foundPos;
- foundPos = _tabFile.find_last_of(".gz");
- // is this a GZIPPED TAB file?
- if (foundPos == _tabFile.size() - 1) {
- igzstream tabs(_tabFile.c_str(), ios::in);
- if ( !tabs ) {
- cerr << "Error: The requested file (" << _tabFile << ") could not be opened. Exiting!" << endl;
- exit (1);
- }
- else {
- // if so, close it (this was just a test)
- tabs.close();
- // now set a pointer to the stream so that we
- // can read the file later on.
- _tabStream = new igzstream(_tabFile.c_str(), ios::in);
- }
- }
- // not GZIPPED.
- else {
-
- ifstream tabs(_tabFile.c_str(), ios::in);
- // can we open the file?
- if ( !tabs ) {
- cerr << "Error: The requested file (" << _tabFile << ") could not be opened. Exiting!" << endl;
- exit (1);
- }
- else {
- // if so, close it (this was just a test)
- tabs.close();
- // now set a pointer to the stream so that we
- // can read the file later on.
- _tabStream = new ifstream(_tabFile.c_str(), ios::in);
- }
- }
- }
+ if (_tabFile == "stdin") {
+ _tabStream = &cin;
+ }
+ else {
+ size_t foundPos;
+ foundPos = _tabFile.find_last_of(".gz");
+ // is this a GZIPPED TAB file?
+ if (foundPos == _tabFile.size() - 1) {
+ igzstream tabs(_tabFile.c_str(), ios::in);
+ if ( !tabs ) {
+ cerr << "Error: The requested file (" << _tabFile << ") could not be opened. Exiting!" << endl;
+ exit (1);
+ }
+ else {
+ // if so, close it (this was just a test)
+ tabs.close();
+ // now set a pointer to the stream so that we
+ // can read the file later on.
+ _tabStream = new igzstream(_tabFile.c_str(), ios::in);
+ }
+ }
+ // not GZIPPED.
+ else {
+
+ ifstream tabs(_tabFile.c_str(), ios::in);
+ // can we open the file?
+ if ( !tabs ) {
+ cerr << "Error: The requested file (" << _tabFile << ") could not be opened. Exiting!" << endl;
+ exit (1);
+ }
+ else {
+ // if so, close it (this was just a test)
+ tabs.close();
+ // now set a pointer to the stream so that we
+ // can read the file later on.
+ _tabStream = new ifstream(_tabFile.c_str(), ios::in);
+ }
+ }
+ }
}
// Close the TAB file
void TabFile::Close(void) {
- if (_tabFile != "stdin") delete _tabStream;
+ if (_tabFile != "stdin") delete _tabStream;
}
TabLineStatus TabFile::GetNextTabLine(TAB_FIELDS &tabFields, int &lineNum) {
- // make sure there are still lines to process.
- // if so, tokenize, return the TAB_FIELDS.
- if (_tabStream->good() == true) {
- string tabLine;
- tabFields.reserve(20);
-
- // parse the tabStream pointer
- getline(*_tabStream, tabLine);
- lineNum++;
+ // make sure there are still lines to process.
+ // if so, tokenize, return the TAB_FIELDS.
+ if (_tabStream->good() == true) {
+ string tabLine;
+ tabFields.reserve(20);
+
+ // parse the tabStream pointer
+ getline(*_tabStream, tabLine);
+ lineNum++;
- // split into a string vector.
- Tokenize(tabLine, tabFields);
+ // split into a string vector.
+ Tokenize(tabLine, tabFields);
// parse the line and validate it
- return parseTabLine(tabFields, lineNum);
- }
-
- // default if file is closed or EOF
- return TAB_INVALID;
+ return parseTabLine(tabFields, lineNum);
+ }
+
+ // default if file is closed or EOF
+ return TAB_INVALID;
}
diff --git a/src/utils/tabFile/tabFile.h b/src/utils/tabFile/tabFile.h
index a4e87706a6fc42e491c12821d2766ae119107f02..4674ee9bd842c729d80f8bf58684a7546b276392 100644
--- a/src/utils/tabFile/tabFile.h
+++ b/src/utils/tabFile/tabFile.h
@@ -21,7 +21,7 @@ using namespace std;
// enum to flag the state of a given line in a TAB file.
enum TabLineStatus
-{
+{
TAB_INVALID = -1,
TAB_HEADER = 0,
TAB_BLANK = 1,
@@ -37,43 +37,43 @@ class TabFile {
public:
- // Constructor
- TabFile(const string &tabFile);
-
- // Destructor
- ~TabFile(void);
-
- // Open a TAB file for reading (creates an istream pointer)
- void Open(void);
-
- // Close an opened TAB file.
- void Close(void);
-
- // Get the next TAB entry in an opened TAB file.
- TabLineStatus GetNextTabLine (TAB_FIELDS &tab, int &lineNum);
-
+ // Constructor
+ TabFile(const string &tabFile);
+
+ // Destructor
+ ~TabFile(void);
+
+ // Open a TAB file for reading (creates an istream pointer)
+ void Open(void);
+
+ // Close an opened TAB file.
+ void Close(void);
+
+ // Get the next TAB entry in an opened TAB file.
+ TabLineStatus GetNextTabLine (TAB_FIELDS &tab, int &lineNum);
+
private:
-
- // data
- istream *_tabStream;
+
+ // data
+ istream *_tabStream;
string _tabFile;
-
- // methods
- inline TabLineStatus parseTabLine (const vector<string> &lineVector, int &lineNum) {
- // bail out if we have a blank line
- if (lineVector.size() == 0)
- return TAB_BLANK;
+
+ // methods
+ inline TabLineStatus parseTabLine (const vector<string> &lineVector, int &lineNum) {
+ // bail out if we have a blank line
+ if (lineVector.size() == 0)
+ return TAB_BLANK;
// real line with data
- if (lineVector[0][0] != '#') {
+ if (lineVector[0][0] != '#') {
return TAB_VALID;
}
// comment or header line
- else {
- lineNum--;
- return TAB_HEADER;
- }
- // default
- return TAB_INVALID;
+ else {
+ lineNum--;
+ return TAB_HEADER;
+ }
+ // default
+ return TAB_INVALID;
}
};
diff --git a/src/utils/version/version.h b/src/utils/version/version.h
index 978739666a4e005c607bf6acca9f266b64acdcaf..5338638800443224fc09c5d105bdacefdef93586 100644
--- a/src/utils/version/version.h
+++ b/src/utils/version/version.h
@@ -1,7 +1,7 @@
#ifndef VERSION_H
#define VERSION_H
-// define the version. All tools in the
+// define the version. All tools in the
// suite carry the same version number.
#define VERSION "2.10.2"
diff --git a/src/windowBed/windowBed.cpp b/src/windowBed/windowBed.cpp
index a5dc1a96be7a2dd7911258906918bedb179f2a60..4723e3b087b5d57aeef5be7df04633496e9cc92f 100644
--- a/src/windowBed/windowBed.cpp
+++ b/src/windowBed/windowBed.cpp
@@ -14,40 +14,40 @@
/*
- Constructor
+ Constructor
*/
-BedWindow::BedWindow(string bedAFile, string bedBFile, int leftSlop, int rightSlop,
- bool anyHit, bool noHit, bool writeCount, bool strandWindows,
+BedWindow::BedWindow(string bedAFile, string bedBFile, int leftSlop, int rightSlop,
+ bool anyHit, bool noHit, bool writeCount, bool strandWindows,
bool matchOnStrand, bool bamInput, bool bamOutput, bool isUncompressedBam) {
- _bedAFile = bedAFile;
- _bedBFile = bedBFile;
+ _bedAFile = bedAFile;
+ _bedBFile = bedBFile;
- _leftSlop = leftSlop;
- _rightSlop = rightSlop;
+ _leftSlop = leftSlop;
+ _rightSlop = rightSlop;
- _anyHit = anyHit;
- _noHit = noHit;
- _writeCount = writeCount;
- _strandWindows = strandWindows;
- _matchOnStrand = matchOnStrand;
- _bamInput = bamInput;
- _bamOutput = bamOutput;
+ _anyHit = anyHit;
+ _noHit = noHit;
+ _writeCount = writeCount;
+ _strandWindows = strandWindows;
+ _matchOnStrand = matchOnStrand;
+ _bamInput = bamInput;
+ _bamOutput = bamOutput;
_isUncompressedBam = isUncompressedBam;
-
- _bedA = new BedFile(bedAFile);
- _bedB = new BedFile(bedBFile);
-
- if (_bamInput == false)
- WindowIntersectBed();
- else
- WindowIntersectBam(_bedAFile);
+
+ _bedA = new BedFile(bedAFile);
+ _bedB = new BedFile(bedBFile);
+
+ if (_bamInput == false)
+ WindowIntersectBed();
+ else
+ WindowIntersectBam(_bedAFile);
}
/*
- Destructor
+ Destructor
*/
BedWindow::~BedWindow(void) {
}
@@ -55,187 +55,187 @@ BedWindow::~BedWindow(void) {
void BedWindow::FindWindowOverlaps(const BED &a, vector<BED> &hits) {
-
- /*
- Adjust the start and end of a based on the requested window
- */
-
- // update the current feature's start and end
- // according to the slop requested (slop = 0 by default)
- CHRPOS aFudgeStart = 0;
- CHRPOS aFudgeEnd;
- AddWindow(a, aFudgeStart, aFudgeEnd);
-
- /*
- Now report the hits (if any) based on the window around a.
- */
- // get the hits in B for the A feature
- _bedB->FindOverlapsPerBin(a.chrom, aFudgeStart, aFudgeEnd, a.strand, hits, _matchOnStrand);
-
- int numOverlaps = 0;
-
- // loop through the hits and report those that meet the user's criteria
- vector<BED>::const_iterator h = hits.begin();
- vector<BED>::const_iterator hitsEnd = hits.end();
- for (; h != hitsEnd; ++h) {
-
- int s = max(aFudgeStart, h->start);
- int e = min(aFudgeEnd, h->end);
- int overlapBases = (e - s); // the number of overlapping bases b/w a and b
- int aLength = (a.end - a.start); // the length of a in b.p.
-
- if (s < e) {
- // is there enough overlap (default ~ 1bp)
- if ( ((float) overlapBases / (float) aLength) > 0 ) {
- numOverlaps++;
- if (_anyHit == false && _noHit == false && _writeCount == false) {
- _bedA->reportBedTab(a);
- _bedB->reportBedNewLine(*h);
- }
- }
- }
- }
- if (_anyHit == true && (numOverlaps >= 1)) {
- _bedA->reportBedNewLine(a); }
- else if (_writeCount == true) {
- _bedA->reportBedTab(a); printf("\t%d\n", numOverlaps);
- }
- else if (_noHit == true && (numOverlaps == 0)) {
- _bedA->reportBedNewLine(a);
- }
+
+ /*
+ Adjust the start and end of a based on the requested window
+ */
+
+ // update the current feature's start and end
+ // according to the slop requested (slop = 0 by default)
+ CHRPOS aFudgeStart = 0;
+ CHRPOS aFudgeEnd;
+ AddWindow(a, aFudgeStart, aFudgeEnd);
+
+ /*
+ Now report the hits (if any) based on the window around a.
+ */
+ // get the hits in B for the A feature
+ _bedB->FindOverlapsPerBin(a.chrom, aFudgeStart, aFudgeEnd, a.strand, hits, _matchOnStrand);
+
+ int numOverlaps = 0;
+
+ // loop through the hits and report those that meet the user's criteria
+ vector<BED>::const_iterator h = hits.begin();
+ vector<BED>::const_iterator hitsEnd = hits.end();
+ for (; h != hitsEnd; ++h) {
+
+ int s = max(aFudgeStart, h->start);
+ int e = min(aFudgeEnd, h->end);
+ int overlapBases = (e - s); // the number of overlapping bases b/w a and b
+ int aLength = (a.end - a.start); // the length of a in b.p.
+
+ if (s < e) {
+ // is there enough overlap (default ~ 1bp)
+ if ( ((float) overlapBases / (float) aLength) > 0 ) {
+ numOverlaps++;
+ if (_anyHit == false && _noHit == false && _writeCount == false) {
+ _bedA->reportBedTab(a);
+ _bedB->reportBedNewLine(*h);
+ }
+ }
+ }
+ }
+ if (_anyHit == true && (numOverlaps >= 1)) {
+ _bedA->reportBedNewLine(a); }
+ else if (_writeCount == true) {
+ _bedA->reportBedTab(a); printf("\t%d\n", numOverlaps);
+ }
+ else if (_noHit == true && (numOverlaps == 0)) {
+ _bedA->reportBedNewLine(a);
+ }
}
bool BedWindow::FindOneOrMoreWindowOverlaps(const BED &a) {
-
- // update the current feature's start and end
- // according to the slop requested (slop = 0 by default)
- CHRPOS aFudgeStart = 0;
- CHRPOS aFudgeEnd;
- AddWindow(a, aFudgeStart, aFudgeEnd);
-
- bool overlapsFound = _bedB->FindOneOrMoreOverlapsPerBin(a.chrom, a.start, a.end, a.strand, _matchOnStrand);
- return overlapsFound;
+
+ // update the current feature's start and end
+ // according to the slop requested (slop = 0 by default)
+ CHRPOS aFudgeStart = 0;
+ CHRPOS aFudgeEnd;
+ AddWindow(a, aFudgeStart, aFudgeEnd);
+
+ bool overlapsFound = _bedB->FindOneOrMoreOverlapsPerBin(a.chrom, a.start, a.end, a.strand, _matchOnStrand);
+ return overlapsFound;
}
-
+
void BedWindow::WindowIntersectBed() {
- // load the "B" bed file into a map so
- // that we can easily compare "A" to it for overlaps
- _bedB->loadBedFileIntoMap();
-
- BED a, nullBed;
- int lineNum = 0; // current input line number
- BedLineStatus bedStatus;
- vector<BED> hits; // vector of potential hits
- hits.reserve(100);
-
- _bedA->Open();
- while ((bedStatus = _bedA->GetNextBed(a, lineNum)) != BED_INVALID) {
- if (bedStatus == BED_VALID) {
- FindWindowOverlaps(a, hits);
- hits.clear();
- a = nullBed;
- }
- }
- _bedA->Close();
+ // load the "B" bed file into a map so
+ // that we can easily compare "A" to it for overlaps
+ _bedB->loadBedFileIntoMap();
+
+ BED a, nullBed;
+ int lineNum = 0; // current input line number
+ BedLineStatus bedStatus;
+ vector<BED> hits; // vector of potential hits
+ hits.reserve(100);
+
+ _bedA->Open();
+ while ((bedStatus = _bedA->GetNextBed(a, lineNum)) != BED_INVALID) {
+ if (bedStatus == BED_VALID) {
+ FindWindowOverlaps(a, hits);
+ hits.clear();
+ a = nullBed;
+ }
+ }
+ _bedA->Close();
}
void BedWindow::WindowIntersectBam(string bamFile) {
- // load the "B" bed file into a map so
- // that we can easily compare "A" to it for overlaps
- _bedB->loadBedFileIntoMap();
-
- // open the BAM file
- BamReader reader;
- BamWriter writer;
- reader.Open(bamFile);
-
- // get header & reference information
- string header = reader.GetHeaderText();
- RefVector refs = reader.GetReferenceData();
-
- // open a BAM output to stdout if we are writing BAM
- if (_bamOutput == true) {
- // open our BAM writer
- writer.Open("stdout", header, refs, _isUncompressedBam);
- }
-
- vector<BED> hits; // vector of potential hits
- // reserve some space
- hits.reserve(100);
-
- _bedA->bedType = 6;
- BamAlignment bam;
- bool overlapsFound;
- // get each set of alignments for each pair.
- while (reader.GetNextAlignment(bam)) {
-
- if (bam.IsMapped()) {
- BED a;
- a.chrom = refs.at(bam.RefID).RefName;
- a.start = bam.Position;
- a.end = bam.GetEndPosition(false);
-
- // build the name field from the BAM alignment.
- a.name = bam.Name;
- if (bam.IsFirstMate()) a.name += "/1";
- if (bam.IsSecondMate()) a.name += "/2";
-
- a.score = ToString(bam.MapQuality);
- a.strand = "+"; if (bam.IsReverseStrand()) a.strand = "-";
-
- if (_bamOutput == true) {
- overlapsFound = FindOneOrMoreWindowOverlaps(a);
- if (overlapsFound == true) {
- if (_noHit == false)
- writer.SaveAlignment(bam);
- }
- else {
- if (_noHit == true)
- writer.SaveAlignment(bam);
- }
- }
- else {
- FindWindowOverlaps(a, hits);
- hits.clear();
- }
- }
- }
-
- // close the relevant BAM files.
- reader.Close();
- if (_bamOutput == true) {
- writer.Close();
- }
+ // load the "B" bed file into a map so
+ // that we can easily compare "A" to it for overlaps
+ _bedB->loadBedFileIntoMap();
+
+ // open the BAM file
+ BamReader reader;
+ BamWriter writer;
+ reader.Open(bamFile);
+
+ // get header & reference information
+ string header = reader.GetHeaderText();
+ RefVector refs = reader.GetReferenceData();
+
+ // open a BAM output to stdout if we are writing BAM
+ if (_bamOutput == true) {
+ // open our BAM writer
+ writer.Open("stdout", header, refs, _isUncompressedBam);
+ }
+
+ vector<BED> hits; // vector of potential hits
+ // reserve some space
+ hits.reserve(100);
+
+ _bedA->bedType = 6;
+ BamAlignment bam;
+ bool overlapsFound;
+ // get each set of alignments for each pair.
+ while (reader.GetNextAlignment(bam)) {
+
+ if (bam.IsMapped()) {
+ BED a;
+ a.chrom = refs.at(bam.RefID).RefName;
+ a.start = bam.Position;
+ a.end = bam.GetEndPosition(false);
+
+ // build the name field from the BAM alignment.
+ a.name = bam.Name;
+ if (bam.IsFirstMate()) a.name += "/1";
+ if (bam.IsSecondMate()) a.name += "/2";
+
+ a.score = ToString(bam.MapQuality);
+ a.strand = "+"; if (bam.IsReverseStrand()) a.strand = "-";
+
+ if (_bamOutput == true) {
+ overlapsFound = FindOneOrMoreWindowOverlaps(a);
+ if (overlapsFound == true) {
+ if (_noHit == false)
+ writer.SaveAlignment(bam);
+ }
+ else {
+ if (_noHit == true)
+ writer.SaveAlignment(bam);
+ }
+ }
+ else {
+ FindWindowOverlaps(a, hits);
+ hits.clear();
+ }
+ }
+ }
+
+ // close the relevant BAM files.
+ reader.Close();
+ if (_bamOutput == true) {
+ writer.Close();
+ }
}
void BedWindow::AddWindow(const BED &a, CHRPOS &fudgeStart, CHRPOS &fudgeEnd) {
- // Does the user want to treat the windows based on strand?
- // If so,
- // if "+", then left is left and right is right
- // if "-", the left is right and right is left.
- if (_strandWindows) {
- if (a.strand == "+") {
- if ((a.start - _leftSlop) > 0) fudgeStart = a.start - _leftSlop;
- else fudgeStart = 0;
- fudgeEnd = a.end + _rightSlop;
- }
- else {
- if ((a.start - _rightSlop) > 0) fudgeStart = a.start - _rightSlop;
- else fudgeStart = 0;
- fudgeEnd = a.end + _leftSlop;
- }
- }
- // If not, add the windows irrespective of strand
- else {
- if ((a.start - _leftSlop) > 0) fudgeStart = a.start - _leftSlop;
- else fudgeStart = 0;
- fudgeEnd = a.end + _rightSlop;
- }
+ // Does the user want to treat the windows based on strand?
+ // If so,
+ // if "+", then left is left and right is right
+ // if "-", the left is right and right is left.
+ if (_strandWindows) {
+ if (a.strand == "+") {
+ if ((a.start - _leftSlop) > 0) fudgeStart = a.start - _leftSlop;
+ else fudgeStart = 0;
+ fudgeEnd = a.end + _rightSlop;
+ }
+ else {
+ if ((a.start - _rightSlop) > 0) fudgeStart = a.start - _rightSlop;
+ else fudgeStart = 0;
+ fudgeEnd = a.end + _leftSlop;
+ }
+ }
+ // If not, add the windows irrespective of strand
+ else {
+ if ((a.start - _leftSlop) > 0) fudgeStart = a.start - _leftSlop;
+ else fudgeStart = 0;
+ fudgeEnd = a.end + _rightSlop;
+ }
}
diff --git a/src/windowBed/windowBed.h b/src/windowBed/windowBed.h
index 229b74adeb4f5f70b349e001513c80dc398a38f9..d2af1849698c99bf1f109a5cf33a97a69982e2f6 100644
--- a/src/windowBed/windowBed.h
+++ b/src/windowBed/windowBed.h
@@ -31,38 +31,38 @@ class BedWindow {
public:
- // constructor
- BedWindow(string bedAFile, string bedBFile, int leftSlop, int rightSlop,
- bool anyHit, bool noHit, bool writeCount, bool strandWindows,
- bool matchOnStrand, bool bamInput, bool bamOutput, bool isUncompressedBam);
+ // constructor
+ BedWindow(string bedAFile, string bedBFile, int leftSlop, int rightSlop,
+ bool anyHit, bool noHit, bool writeCount, bool strandWindows,
+ bool matchOnStrand, bool bamInput, bool bamOutput, bool isUncompressedBam);
+
+ // destructor
+ ~BedWindow(void);
- // destructor
- ~BedWindow(void);
-
private:
- string _bedAFile;
- string _bedBFile;
- bool _anyHit;
- bool _writeCount;
- int _leftSlop;
- int _rightSlop;
- bool _noHit;
- bool _strandWindows;
- bool _matchOnStrand;
- bool _bamInput;
- bool _bamOutput;
- bool _isUncompressedBam;
+ string _bedAFile;
+ string _bedBFile;
+ bool _anyHit;
+ bool _writeCount;
+ int _leftSlop;
+ int _rightSlop;
+ bool _noHit;
+ bool _strandWindows;
+ bool _matchOnStrand;
+ bool _bamInput;
+ bool _bamOutput;
+ bool _isUncompressedBam;
+
+ // instance of a bed file class.
+ BedFile *_bedA, *_bedB;
- // instance of a bed file class.
- BedFile *_bedA, *_bedB;
-
- // methods
- void WindowIntersectBed();
- void WindowIntersectBam(string bamFile);
- void FindWindowOverlaps(const BED &a, vector<BED> &hits);
- bool FindOneOrMoreWindowOverlaps(const BED &a);
- void AddWindow(const BED &a, CHRPOS &fudgeStart, CHRPOS &fudgeEnd);
+ // methods
+ void WindowIntersectBed();
+ void WindowIntersectBam(string bamFile);
+ void FindWindowOverlaps(const BED &a, vector<BED> &hits);
+ bool FindOneOrMoreWindowOverlaps(const BED &a);
+ void AddWindow(const BED &a, CHRPOS &fudgeStart, CHRPOS &fudgeEnd);
};
#endif /* WINDOWBED_H */
diff --git a/src/windowBed/windowMain.cpp b/src/windowBed/windowMain.cpp
index e3a20411e0d29e8fb760733ddf03547e8db98210..b15854f2e1d099d77e853378734a6cf8a31f9f47 100644
--- a/src/windowBed/windowMain.cpp
+++ b/src/windowBed/windowMain.cpp
@@ -26,226 +26,226 @@ void ShowHelp(void);
int main(int argc, char* argv[]) {
- // our configuration variables
- bool showHelp = false;
-
- // input files
- string bedAFile;
- string bedBFile;
-
- // input arguments
- int leftSlop = 1000;
- int rightSlop = 1000;
-
- bool haveBedA = false;
- bool haveBedB = false;
- bool noHit = false;
- bool anyHit = false;
- bool writeCount = false;
- bool haveSlop = false;
- bool haveLeft = false;
- bool haveRight = false;
- bool strandWindows = false;
- bool matchOnStrand = false;
- bool inputIsBam = false;
- bool outputIsBam = true;
+ // our configuration variables
+ bool showHelp = false;
+
+ // input files
+ string bedAFile;
+ string bedBFile;
+
+ // input arguments
+ int leftSlop = 1000;
+ int rightSlop = 1000;
+
+ bool haveBedA = false;
+ bool haveBedB = false;
+ bool noHit = false;
+ bool anyHit = false;
+ bool writeCount = false;
+ bool haveSlop = false;
+ bool haveLeft = false;
+ bool haveRight = false;
+ bool strandWindows = false;
+ bool matchOnStrand = false;
+ bool inputIsBam = false;
+ bool outputIsBam = true;
bool uncompressedBam = false;
- // check to see if we should print out some help
- if(argc <= 1) showHelp = true;
-
- for(int i = 1; i < argc; i++) {
- int parameterLength = (int)strlen(argv[i]);
-
- if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
- (PARAMETER_CHECK("--help", 5, parameterLength))) {
- showHelp = true;
- }
- }
-
- if(showHelp) ShowHelp();
-
- // do some parsing (all of these parameters require 2 strings)
- for(int i = 1; i < argc; i++) {
-
- int parameterLength = (int)strlen(argv[i]);
-
- if(PARAMETER_CHECK("-a", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveBedA = true;
- bedAFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-abam", 5, parameterLength)) {
- if ((i+1) < argc) {
- haveBedA = true;
- inputIsBam = true;
- bedAFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-b", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveBedB = true;
- bedBFile = argv[i + 1];
- i++;
- }
- }
- else if(PARAMETER_CHECK("-bed", 4, parameterLength)) {
- outputIsBam = false;
- }
- else if(PARAMETER_CHECK("-u", 2, parameterLength)) {
- anyHit = true;
- }
- else if(PARAMETER_CHECK("-c", 2, parameterLength)) {
- writeCount = true;
- }
- else if (PARAMETER_CHECK("-v", 2, parameterLength)) {
- noHit = true;
- }
- else if (PARAMETER_CHECK("-sw", 3, parameterLength)) {
- strandWindows = true;
- }
- else if (PARAMETER_CHECK("-sm", 3, parameterLength)) {
- matchOnStrand = true;
- }
- else if (PARAMETER_CHECK("-w", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveSlop = true;
- leftSlop = atoi(argv[i + 1]);
- rightSlop = leftSlop;
- i++;
- }
- }
- else if (PARAMETER_CHECK("-l", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveLeft = true;
- leftSlop = atoi(argv[i + 1]);
- i++;
- }
- }
- else if (PARAMETER_CHECK("-r", 2, parameterLength)) {
- if ((i+1) < argc) {
- haveRight = true;
- rightSlop = atoi(argv[i + 1]);
- i++;
- }
- }
- else if(PARAMETER_CHECK("-ubam", 5, parameterLength)) {
+ // check to see if we should print out some help
+ if(argc <= 1) showHelp = true;
+
+ for(int i = 1; i < argc; i++) {
+ int parameterLength = (int)strlen(argv[i]);
+
+ if((PARAMETER_CHECK("-h", 2, parameterLength)) ||
+ (PARAMETER_CHECK("--help", 5, parameterLength))) {
+ showHelp = true;
+ }
+ }
+
+ if(showHelp) ShowHelp();
+
+ // do some parsing (all of these parameters require 2 strings)
+ for(int i = 1; i < argc; i++) {
+
+ int parameterLength = (int)strlen(argv[i]);
+
+ if(PARAMETER_CHECK("-a", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveBedA = true;
+ bedAFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-abam", 5, parameterLength)) {
+ if ((i+1) < argc) {
+ haveBedA = true;
+ inputIsBam = true;
+ bedAFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-b", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveBedB = true;
+ bedBFile = argv[i + 1];
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-bed", 4, parameterLength)) {
+ outputIsBam = false;
+ }
+ else if(PARAMETER_CHECK("-u", 2, parameterLength)) {
+ anyHit = true;
+ }
+ else if(PARAMETER_CHECK("-c", 2, parameterLength)) {
+ writeCount = true;
+ }
+ else if (PARAMETER_CHECK("-v", 2, parameterLength)) {
+ noHit = true;
+ }
+ else if (PARAMETER_CHECK("-sw", 3, parameterLength)) {
+ strandWindows = true;
+ }
+ else if (PARAMETER_CHECK("-sm", 3, parameterLength)) {
+ matchOnStrand = true;
+ }
+ else if (PARAMETER_CHECK("-w", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveSlop = true;
+ leftSlop = atoi(argv[i + 1]);
+ rightSlop = leftSlop;
+ i++;
+ }
+ }
+ else if (PARAMETER_CHECK("-l", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveLeft = true;
+ leftSlop = atoi(argv[i + 1]);
+ i++;
+ }
+ }
+ else if (PARAMETER_CHECK("-r", 2, parameterLength)) {
+ if ((i+1) < argc) {
+ haveRight = true;
+ rightSlop = atoi(argv[i + 1]);
+ i++;
+ }
+ }
+ else if(PARAMETER_CHECK("-ubam", 5, parameterLength)) {
uncompressedBam = true;
- }
- else {
- cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
- showHelp = true;
- }
- }
-
- // make sure we have both input files
- if (!haveBedA || !haveBedB) {
- cerr << endl << "*****" << endl << "*****ERROR: Need -a and -b files. " << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (anyHit && noHit) {
- cerr << endl << "*****" << endl << "*****ERROR: Request either -u OR -v, not both." << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (anyHit && writeCount) {
- cerr << endl << "*****" << endl << "*****ERROR: Request either -u OR -c, not both." << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (haveLeft && (leftSlop < 0)) {
- cerr << endl << "*****" << endl << "*****ERROR: Upstream window (-l) must be positive." << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (haveRight && (rightSlop < 0)) {
- cerr << endl << "*****" << endl << "*****ERROR: Downstream window (-r) must be positive." << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (haveSlop && (haveLeft || haveRight)) {
- cerr << endl << "*****" << endl << "*****ERROR: Cannot choose -w with -l or -r. Either specify -l and -r or specify solely -w" << endl << "*****" << endl;
- showHelp = true;
- }
-
- if ((haveLeft && !haveRight) || (haveRight && !haveLeft)) {
- cerr << endl << "*****" << endl << "*****ERROR: Please specify both -l and -r." << endl << "*****" << endl;
- showHelp = true;
- }
-
- if (!showHelp) {
- BedWindow *bi = new BedWindow(bedAFile, bedBFile, leftSlop, rightSlop, anyHit,
- noHit, writeCount, strandWindows, matchOnStrand,
- inputIsBam, outputIsBam, uncompressedBam);
- delete bi;
- return 0;
- }
- else {
- ShowHelp();
- }
+ }
+ else {
+ cerr << endl << "*****ERROR: Unrecognized parameter: " << argv[i] << " *****" << endl << endl;
+ showHelp = true;
+ }
+ }
+
+ // make sure we have both input files
+ if (!haveBedA || !haveBedB) {
+ cerr << endl << "*****" << endl << "*****ERROR: Need -a and -b files. " << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (anyHit && noHit) {
+ cerr << endl << "*****" << endl << "*****ERROR: Request either -u OR -v, not both." << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (anyHit && writeCount) {
+ cerr << endl << "*****" << endl << "*****ERROR: Request either -u OR -c, not both." << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (haveLeft && (leftSlop < 0)) {
+ cerr << endl << "*****" << endl << "*****ERROR: Upstream window (-l) must be positive." << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (haveRight && (rightSlop < 0)) {
+ cerr << endl << "*****" << endl << "*****ERROR: Downstream window (-r) must be positive." << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (haveSlop && (haveLeft || haveRight)) {
+ cerr << endl << "*****" << endl << "*****ERROR: Cannot choose -w with -l or -r. Either specify -l and -r or specify solely -w" << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if ((haveLeft && !haveRight) || (haveRight && !haveLeft)) {
+ cerr << endl << "*****" << endl << "*****ERROR: Please specify both -l and -r." << endl << "*****" << endl;
+ showHelp = true;
+ }
+
+ if (!showHelp) {
+ BedWindow *bi = new BedWindow(bedAFile, bedBFile, leftSlop, rightSlop, anyHit,
+ noHit, writeCount, strandWindows, matchOnStrand,
+ inputIsBam, outputIsBam, uncompressedBam);
+ delete bi;
+ return 0;
+ }
+ else {
+ ShowHelp();
+ }
}
void ShowHelp(void) {
- cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
-
- cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
-
- cerr << "Summary: Examines a \"window\" around each feature in A and" << endl;
- cerr << "\t reports all features in B that overlap the window. For each" << endl;
- cerr << "\t overlap the entire entry in A and B are reported." << endl << endl;
-
- cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -a <bed/gff/vcf> -b <bed/gff/vcf>" << endl << endl;
-
- cerr << "Options: " << endl;
-
- cerr << "\t-abam\t" << "The A input file is in BAM format. Output will be BAM as well." << endl << endl;
-
- cerr << "\t-ubam\t" << "Write uncompressed BAM output. Default is to write compressed BAM." << endl << endl;
-
- cerr << "\t-bed\t" << "When using BAM input (-abam), write output as BED. The default" << endl;
- cerr << "\t\tis to write output in BAM when using -abam." << endl << endl;
-
- cerr << "\t-w\t" << "Base pairs added upstream and downstream of each entry" << endl;
- cerr << "\t\tin A when searching for overlaps in B." << endl;
- cerr << "\t\t- Creates symterical \"windows\" around A." << endl;
- cerr << "\t\t- Default is 1000 bp." << endl;
- cerr << "\t\t- (INTEGER)" << endl << endl;
-
- cerr << "\t-l\t" << "Base pairs added upstream (left of) of each entry" << endl;
- cerr << "\t\tin A when searching for overlaps in B." << endl;
- cerr << "\t\t- Allows one to define assymterical \"windows\"." << endl;
- cerr << "\t\t- Default is 1000 bp." << endl;
- cerr << "\t\t- (INTEGER)" << endl << endl;
-
- cerr << "\t-r\t" << "Base pairs added downstream (right of) of each entry" << endl;
- cerr << "\t\tin A when searching for overlaps in B." << endl;
- cerr << "\t\t- Allows one to define assymterical \"windows\"." << endl;
- cerr << "\t\t- Default is 1000 bp." << endl;
- cerr << "\t\t- (INTEGER)" << endl << endl;
-
- cerr << "\t-sw\t" << "Define -l and -r based on strand. For example if used, -l 500" << endl;
- cerr << "\t\tfor a negative-stranded feature will add 500 bp downstream." << endl;
- cerr << "\t\t- Default = disabled." << endl << endl;
-
- cerr << "\t-sm\t" << "Only report hits in B that overlap A on the same strand." << endl;
- cerr << "\t\t- By default, overlaps are reported without respect to strand." << endl << endl;
-
- cerr << "\t-u\t" << "Write the original A entry _once_ if _any_ overlaps found in B." << endl;
- cerr << "\t\t- In other words, just report the fact >=1 hit was found." << endl << endl;
-
- cerr << "\t-c\t" << "For each entry in A, report the number of overlaps with B." << endl;
- cerr << "\t\t- Reports 0 for A entries that have no overlap with B." << endl;
- cerr << "\t\t- Overlaps restricted by -f." << endl << endl;
-
- cerr << "\t-v\t" << "Only report those entries in A that have _no overlaps_ with B." << endl;
- cerr << "\t\t- Similar to \"grep -v.\"" << endl << endl;
-
- // end the program here
- exit(1);
+ cerr << endl << "Program: " << PROGRAM_NAME << " (v" << VERSION << ")" << endl;
+
+ cerr << "Author: Aaron Quinlan (aaronquinlan@gmail.com)" << endl;
+
+ cerr << "Summary: Examines a \"window\" around each feature in A and" << endl;
+ cerr << "\t reports all features in B that overlap the window. For each" << endl;
+ cerr << "\t overlap the entire entry in A and B are reported." << endl << endl;
+
+ cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -a <bed/gff/vcf> -b <bed/gff/vcf>" << endl << endl;
+
+ cerr << "Options: " << endl;
+
+ cerr << "\t-abam\t" << "The A input file is in BAM format. Output will be BAM as well." << endl << endl;
+
+ cerr << "\t-ubam\t" << "Write uncompressed BAM output. Default is to write compressed BAM." << endl << endl;
+
+ cerr << "\t-bed\t" << "When using BAM input (-abam), write output as BED. The default" << endl;
+ cerr << "\t\tis to write output in BAM when using -abam." << endl << endl;
+
+ cerr << "\t-w\t" << "Base pairs added upstream and downstream of each entry" << endl;
+ cerr << "\t\tin A when searching for overlaps in B." << endl;
+ cerr << "\t\t- Creates symterical \"windows\" around A." << endl;
+ cerr << "\t\t- Default is 1000 bp." << endl;
+ cerr << "\t\t- (INTEGER)" << endl << endl;
+
+ cerr << "\t-l\t" << "Base pairs added upstream (left of) of each entry" << endl;
+ cerr << "\t\tin A when searching for overlaps in B." << endl;
+ cerr << "\t\t- Allows one to define assymterical \"windows\"." << endl;
+ cerr << "\t\t- Default is 1000 bp." << endl;
+ cerr << "\t\t- (INTEGER)" << endl << endl;
+
+ cerr << "\t-r\t" << "Base pairs added downstream (right of) of each entry" << endl;
+ cerr << "\t\tin A when searching for overlaps in B." << endl;
+ cerr << "\t\t- Allows one to define assymterical \"windows\"." << endl;
+ cerr << "\t\t- Default is 1000 bp." << endl;
+ cerr << "\t\t- (INTEGER)" << endl << endl;
+
+ cerr << "\t-sw\t" << "Define -l and -r based on strand. For example if used, -l 500" << endl;
+ cerr << "\t\tfor a negative-stranded feature will add 500 bp downstream." << endl;
+ cerr << "\t\t- Default = disabled." << endl << endl;
+
+ cerr << "\t-sm\t" << "Only report hits in B that overlap A on the same strand." << endl;
+ cerr << "\t\t- By default, overlaps are reported without respect to strand." << endl << endl;
+
+ cerr << "\t-u\t" << "Write the original A entry _once_ if _any_ overlaps found in B." << endl;
+ cerr << "\t\t- In other words, just report the fact >=1 hit was found." << endl << endl;
+
+ cerr << "\t-c\t" << "For each entry in A, report the number of overlaps with B." << endl;
+ cerr << "\t\t- Reports 0 for A entries that have no overlap with B." << endl;
+ cerr << "\t\t- Overlaps restricted by -f." << endl << endl;
+
+ cerr << "\t-v\t" << "Only report those entries in A that have _no overlaps_ with B." << endl;
+ cerr << "\t\t- Similar to \"grep -v.\"" << endl << endl;
+
+ // end the program here
+ exit(1);
}