From d245bbc9fda885d9dac1341b7c83b21c9399e893 Mon Sep 17 00:00:00 2001
From: Aaron <aaronquinlan@gmail.com>
Date: Wed, 14 Apr 2010 23:04:35 -0400
Subject: [PATCH] Updated most of the code to use _ notation and the
Open,GetNext,Close functionality.
---
src/closestBed/closestBed.cpp | 97 +++-----
src/closestBed/closestBed.h | 29 +--
src/closestBed/closestMain.cpp | 1 -
src/complementBed/complementBed.cpp | 17 +-
src/complementBed/complementBed.h | 12 +-
src/coverageBed/coverageBed.cpp | 95 ++++----
src/coverageBed/coverageBed.h | 22 +-
src/coverageBed/coverageMain.cpp | 3 +-
src/fastaFromBed/fastaFromBed.cpp | 54 ++---
src/fastaFromBed/fastaFromBed.h | 14 +-
src/fastaFromBed/fastaFromBedMain.cpp | 3 +-
src/genomeCoverageBed/genomeCoverageBed.cpp | 174 +++++++-------
src/genomeCoverageBed/genomeCoverageBed.h | 39 ++--
src/genomeCoverageBed/genomeCoverageMain.cpp | 3 +-
src/intersectBed/intersectBed.cpp | 40 ++--
src/intersectBed/intersectBed.h | 1 -
src/intersectBed/intersectMain.cpp | 2 +-
src/linksBed/linksBed.cpp | 66 ++----
src/linksBed/linksBed.h | 18 +-
src/linksBed/linksMain.cpp | 2 +-
src/maskFastaFromBed/maskFastaFromBed.cpp | 33 +--
src/maskFastaFromBed/maskFastaFromBed.h | 19 +-
src/maskFastaFromBed/maskFastaFromBedMain.cpp | 2 +-
src/mergeBed/mergeBed.cpp | 65 +++---
src/mergeBed/mergeBed.h | 14 +-
src/mergeBed/mergeMain.cpp | 8 +-
src/pairToBed/pairToBed.cpp | 148 ++++++------
src/pairToBed/pairToBed.h | 21 +-
src/shuffleBed/shuffleBed.cpp | 217 ++++++++----------
src/shuffleBed/shuffleBed.h | 37 ++-
src/shuffleBed/shuffleBedMain.cpp | 4 +-
src/slopBed/slopBed.cpp | 64 ++----
src/slopBed/slopBed.h | 30 +--
src/slopBed/slopBedMain.cpp | 2 +-
src/sortBed/sortBed.cpp | 52 +++--
src/sortBed/sortBed.h | 9 +-
36 files changed, 636 insertions(+), 781 deletions(-)
diff --git a/src/closestBed/closestBed.cpp b/src/closestBed/closestBed.cpp
index 07aeaa87..f339eec5 100755
--- a/src/closestBed/closestBed.cpp
+++ b/src/closestBed/closestBed.cpp
@@ -23,14 +23,15 @@ const int SLOPGROWTH = 2048000;
*/
BedClosest::BedClosest(string &bedAFile, string &bedBFile, bool &forceStrand, string &tieMode) {
- this->bedAFile = bedAFile;
- this->bedBFile = bedBFile;
- this->forceStrand = forceStrand;
- this->tieMode = tieMode;
+ _bedAFile = bedAFile;
+ _bedBFile = bedBFile;
+ _forceStrand = forceStrand;
+ _tieMode = tieMode;
- this->bedA = new BedFile(bedAFile);
- this->bedB = new BedFile(bedBFile);
+ _bedA = new BedFile(bedAFile);
+ _bedB = new BedFile(bedBFile);
+ FindClosestBed();
}
/*
@@ -47,16 +48,16 @@ BedClosest::~BedClosest(void) {
Works for BED3 - BED6.
*/
void BedClosest::reportNullB() {
- if (bedB->bedType == 3) {
+ if (_bedB->bedType == 3) {
printf("none\t-1\t-1\n");
}
- else if (bedB->bedType == 4) {
+ else if (_bedB->bedType == 4) {
printf("none\t-1\t-1\t-1\n");
}
- else if (bedB->bedType == 5) {
+ else if (_bedB->bedType == 5) {
printf("none\t-1\t-1\t-1\t-1\n");
}
- else if (bedB->bedType == 6) {
+ else if (_bedB->bedType == 6) {
printf("none\t-1\t-1\t-1\t-1\t-1\n");
}
}
@@ -79,7 +80,7 @@ void BedClosest::FindWindowOverlaps(BED &a, vector<BED> &hits) {
int minDistance = 999999999;
- if(bedB->bedMap.find(a.chrom) != bedB->bedMap.end()) {
+ if(_bedB->bedMap.find(a.chrom) != _bedB->bedMap.end()) {
while ((numOverlaps == 0) && (slop <= MAXSLOP)) {
@@ -91,7 +92,7 @@ void BedClosest::FindWindowOverlaps(BED &a, vector<BED> &hits) {
if ((a.start + slop) < 2 * MAXSLOP) aFudgeEnd = a.end + slop;
else aFudgeEnd = 2 * MAXSLOP;
- bedB->FindOverlapsPerBin(a.chrom, aFudgeStart, aFudgeEnd, a.strand, hits, this->forceStrand);
+ _bedB->FindOverlapsPerBin(a.chrom, aFudgeStart, aFudgeEnd, a.strand, hits, _forceStrand);
vector<BED>::const_iterator h = hits.begin();
vector<BED>::const_iterator hitsEnd = hits.end();
@@ -141,82 +142,54 @@ void BedClosest::FindWindowOverlaps(BED &a, vector<BED> &hits) {
}
}
else {
- bedA->reportBedTab(a);
+ _bedA->reportBedTab(a);
reportNullB();
}
if (numOverlaps > 0) {
if (closestB.size() == 1) {
- bedA->reportBedTab(a);
- bedB->reportBedNewLine(closestB[0]);
+ _bedA->reportBedTab(a);
+ _bedB->reportBedNewLine(closestB[0]);
}
else {
- if (this->tieMode == "all") {
+ if (_tieMode == "all") {
for (vector<BED>::iterator b = closestB.begin(); b != closestB.end(); ++b) {
- bedA->reportBedTab(a);
- bedB->reportBedNewLine(*b);
+ _bedA->reportBedTab(a);
+ _bedB->reportBedNewLine(*b);
}
}
- else if (this->tieMode == "first") {
- bedA->reportBedTab(a);
- bedB->reportBedNewLine(closestB[0]);
+ else if (_tieMode == "first") {
+ _bedA->reportBedTab(a);
+ _bedB->reportBedNewLine(closestB[0]);
}
- else if (this->tieMode == "last") {
- bedA->reportBedTab(a);
- bedB->reportBedNewLine(closestB[closestB.size()-1]);
+ else if (_tieMode == "last") {
+ _bedA->reportBedTab(a);
+ _bedB->reportBedNewLine(closestB[closestB.size()-1]);
}
}
}
}
-void BedClosest::ClosestBed(istream &bedInput) {
+void BedClosest::FindClosestBed() {
// load the "B" bed file into a map so
// that we can easily compare "A" to it for overlaps
- bedB->loadBedFileIntoMap();
-
- string bedLine;
+ _bedB->loadBedFileIntoMap();
+
+ BED a;
int lineNum = 0; // current input line number
vector<BED> hits; // vector of potential hits
- vector<string> bedFields; // vector for a BED entry
-
- // reserve some space
hits.reserve(100);
- bedFields.reserve(12);
-
- // process each entry in A
- while (getline(bedInput, bedLine)) {
- lineNum++;
- Tokenize(bedLine,bedFields);
- BED a;
-
- // find the overlaps with B if it's a valid BED entry.
- if (bedA->parseLine(a, bedFields, lineNum)) {
- FindWindowOverlaps(a, hits);
- hits.clear();
- }
- // reset for the next input line
- bedFields.clear();
+ _bedA->Open();
+ // process each entry in A in search of the closest feature in B
+ while (_bedA->GetNextBed(a, lineNum)) {
+ FindWindowOverlaps(a, hits);
+ hits.clear();
}
+ _bedA->Close();
}
// END ClosestBed
-
-
-void BedClosest::DetermineBedInput() {
- if (bedA->bedFile != "stdin") { // process a file
- ifstream beds(bedA->bedFile.c_str(), ios::in);
- if ( !beds ) {
- cerr << "Error: The requested bed file (" << bedA->bedFile << ") could not be opened. Exiting!" << endl;
- exit (1);
- }
- ClosestBed(beds);
- }
- else { // process stdin
- ClosestBed(cin);
- }
-}
-
diff --git a/src/closestBed/closestBed.h b/src/closestBed/closestBed.h
index 0e3804bc..41c43cd6 100755
--- a/src/closestBed/closestBed.h
+++ b/src/closestBed/closestBed.h
@@ -27,28 +27,29 @@ class BedClosest {
public:
// constructor
- BedClosest(string &, string &, bool &, string &);
+ BedClosest(string &bedAFile, string &bedAFile, bool &forceStrand, string &tieMode);
// destructor
~BedClosest(void);
+
+ // find the closest feature in B to A
+ void FindClosestBed();
+private:
+
+ // data
+ string _bedAFile;
+ string _bedBFile;
+ string _tieMode;
+ bool _forceStrand;
+
+ BedFile *_bedA, *_bedB;
+
+ // methods
void reportA(const BED &);
void reportB(const BED &);
void reportNullB();
-
- void ClosestBed(istream &bedInput);
void FindWindowOverlaps(BED &, vector<BED> &);
- void DetermineBedInput();
-
-private:
-
- string bedAFile;
- string bedBFile;
- string tieMode;
- bool forceStrand;
-
- // instance of a bed file class.
- BedFile *bedA, *bedB;
};
#endif /* CLOSEST_H */
diff --git a/src/closestBed/closestMain.cpp b/src/closestBed/closestMain.cpp
index d72fa759..6cafec77 100755
--- a/src/closestBed/closestMain.cpp
+++ b/src/closestBed/closestMain.cpp
@@ -98,7 +98,6 @@ int main(int argc, char* argv[]) {
if (!showHelp) {
BedClosest *bc = new BedClosest(bedAFile, bedBFile, forceStrand, tieMode);
- bc->DetermineBedInput();
return 0;
}
else {
diff --git a/src/complementBed/complementBed.cpp b/src/complementBed/complementBed.cpp
index 0ef9ab99..275455b3 100755
--- a/src/complementBed/complementBed.cpp
+++ b/src/complementBed/complementBed.cpp
@@ -14,11 +14,12 @@
BedComplement::BedComplement(string &bedFile, string &genomeFile) {
- this->bedFile = bedFile;
- this->genomeFile = genomeFile;
+ _bedFile = bedFile;
+ _genomeFile = genomeFile;
- this->bed = new BedFile(bedFile);
- this->genome = new GenomeFile(genomeFile);
+ _bed = new BedFile(bedFile);
+ _genome = new GenomeFile(genomeFile);
+
}
@@ -33,16 +34,16 @@ void BedComplement::ComplementBed() {
// load the "B" bed file into a map so
// that we can easily compare "A" to it for overlaps
- bed->loadBedFileIntoMapNoBin();
+ _bed->loadBedFileIntoMapNoBin();
vector<short> chromMasks;
string currChrom;
// loop through each chromosome and merge their BED entries
- for (masterBedMapNoBin::iterator m = bed->bedMapNoBin.begin(); m != bed->bedMapNoBin.end(); ++m) {
+ for (masterBedMapNoBin::iterator m = _bed->bedMapNoBin.begin(); m != _bed->bedMapNoBin.end(); ++m) {
currChrom = m->first;
- int currChromSize = genome->getChromSize(currChrom);
+ int currChromSize = _genome->getChromSize(currChrom);
// bedList is already sorted by start position.
vector<BED> bedList = m->second;
@@ -57,7 +58,7 @@ void BedComplement::ComplementBed() {
// 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);
+ _bed->reportBedNewLine(*bIt);
exit(1);
}
diff --git a/src/complementBed/complementBed.h b/src/complementBed/complementBed.h
index dcdec407..7d3a94ab 100755
--- a/src/complementBed/complementBed.h
+++ b/src/complementBed/complementBed.h
@@ -30,7 +30,7 @@ class BedComplement {
public:
// constructor
- BedComplement(string &, string &);
+ BedComplement(string &bedFile, string &genomeFile);
// destructor
~BedComplement(void);
@@ -39,10 +39,8 @@ public:
private:
- string bedFile;
- string genomeFile;
-
- // instance of a bed file class.
- BedFile *bed;
- GenomeFile *genome;
+ string _bedFile;
+ string _genomeFile;
+ BedFile *_bed;
+ GenomeFile *_genome;
};
diff --git a/src/coverageBed/coverageBed.cpp b/src/coverageBed/coverageBed.cpp
index d07e7261..13f61939 100755
--- a/src/coverageBed/coverageBed.cpp
+++ b/src/coverageBed/coverageBed.cpp
@@ -15,48 +15,52 @@
// build
BedCoverage::BedCoverage(string &bedAFile, string &bedBFile, bool &forceStrand, bool &writeHistogram, bool &bamInput) {
- this->bedAFile = bedAFile;
- this->bedBFile = bedBFile;
+ _bedAFile = bedAFile;
+ _bedBFile = bedBFile;
- this->bedA = new BedFile(bedAFile);
- this->bedB = new BedFile(bedBFile);
+ _bedA = new BedFile(bedAFile);
+ _bedB = new BedFile(bedBFile);
- this->forceStrand = forceStrand;
- this->writeHistogram = writeHistogram;
- this->bamInput = bamInput;
+ _forceStrand = forceStrand;
+ _writeHistogram = writeHistogram;
+ _bamInput = bamInput;
+
+ if (_bedA->bedFile != "stdin") { // process a file
+ if (_bamInput == false) { //bed/gff
+ CollectCoverageBed();
+ }
+ else {
+ CollectCoverageBam(_bedA->bedFile);
+ }
+ }
+ else { // process stdin
+ if (_bamInput == false)
+ CollectCoverageBed();
+ else {
+ CollectCoverageBam("stdin");
+ }
+ }
}
// destroy
BedCoverage::~BedCoverage(void) {
- delete this->bedA;
- delete this->bedB;
+ delete _bedA;
+ delete _bedB;
}
-void BedCoverage::CollectCoverageBed(istream &bedInput) {
+void BedCoverage::CollectCoverageBed() {
// load the "B" bed file into a map so
// that we can easily compare "A" to it for overlaps
- bedB->loadBedFileIntoMap();
+ _bedB->loadBedFileIntoMap();
- string bedLine;
int lineNum = 0; // current input line number
- vector<string> bedFields; // vector for a BED entry
- bedFields.reserve(12);
-
+ BED a;
// process each entry in A
- while (getline(bedInput, bedLine)) {
-
- lineNum++;
- Tokenize(bedLine,bedFields);
- BED a;
-
- if (bedA->parseLine(a, bedFields, lineNum)) {
- // count a as a hit with all the relevant features in B
- bedB->countHits(a, this->forceStrand);
- }
- // reset for the next input line
- bedFields.clear();
+ while (_bedA->GetNextBed(a, lineNum)) {
+ // count a as a hit with all the relevant features in B
+ _bedB->countHits(a, _forceStrand);
}
// report the coverage (summary or histogram) for BED B.
@@ -68,7 +72,7 @@ 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->loadBedFileIntoMap();
+ _bedB->loadBedFileIntoMap();
// open the BAM file
BamReader reader;
@@ -92,7 +96,7 @@ void BedCoverage::CollectCoverageBam(string bamFile) {
a.end = bam.Position + bam.AlignedBases.size();
a.strand = "+"; if (bam.IsReverseStrand()) a.strand = "-";
- bedB->countHits(a, this->forceStrand);
+ _bedB->countHits(a, _forceStrand);
}
}
// report the coverage (summary or histogram) for BED B.
@@ -107,8 +111,8 @@ void BedCoverage::ReportCoverage() {
map<unsigned int, unsigned int> allDepthHist;
unsigned int totalLength = 0;
- masterBedMap::const_iterator chromItr = bedB->bedMap.begin();
- masterBedMap::const_iterator chromEnd = bedB->bedMap.end();
+ masterBedMap::const_iterator chromItr = _bedB->bedMap.begin();
+ masterBedMap::const_iterator chromEnd = _bedB->bedMap.end();
for (; chromItr != chromEnd; ++chromItr) {
binsToBeds::const_iterator binItr = chromItr->second.begin();
@@ -157,8 +161,8 @@ void BedCoverage::ReportCoverage() {
int nonZeroBases = (length - zeroDepthCount);
float fractCovered = (float) nonZeroBases / length;
- if (this->writeHistogram == false) {
- bedB->reportBedTab(*bedItr);
+ if (_writeHistogram == false) {
+ _bedB->reportBedTab(*bedItr);
printf("%d\t%d\t%d\t%0.7f\n", bedItr->count, nonZeroBases, length, fractCovered);
}
else {
@@ -166,14 +170,14 @@ void BedCoverage::ReportCoverage() {
map<unsigned int, unsigned int>::const_iterator histEnd = depthHist.end();
for (; histItr != histEnd; ++histItr) {
float fractAtThisDepth = (float) histItr->second / length;
- bedB->reportBedTab(*bedItr);
+ _bedB->reportBedTab(*bedItr);
printf("%d\t%d\t%d\t%0.7f\n", histItr->first, histItr->second, length, fractAtThisDepth);
}
}
}
}
}
- if (this->writeHistogram == true) {
+ 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) {
@@ -184,24 +188,3 @@ void BedCoverage::ReportCoverage() {
}
-void BedCoverage::DetermineBedInput() {
- if (bedA->bedFile != "stdin") { // process a file
- if (this->bamInput == false) { //bed/gff
- ifstream beds(bedA->bedFile.c_str(), ios::in);
- if ( !beds ) {
- cerr << "Error: The requested bed file (" << bedA->bedFile << ") could not be opened. Exiting!" << endl;
- exit (1);
- }
- CollectCoverageBed(beds);
- }
- else
- CollectCoverageBam(bedA->bedFile);
- }
- else { // process stdin
- if (this->bamInput == false)
- CollectCoverageBed(cin);
- else
- CollectCoverageBam("stdin");
- }
-}
-
diff --git a/src/coverageBed/coverageBed.h b/src/coverageBed/coverageBed.h
index a4aa2fc6..60ea56c2 100755
--- a/src/coverageBed/coverageBed.h
+++ b/src/coverageBed/coverageBed.h
@@ -40,31 +40,29 @@ public:
// destructor
~BedCoverage(void);
- void CollectCoverageBed(istream &bedInput);
-
- void CollectCoverageBam(string bamFile);
-
- void DetermineBedInput();
-
private:
// input files.
- string bedAFile;
- string bedBFile;
+ string _bedAFile;
+ string _bedBFile;
// instance of a bed file class.
- BedFile *bedA, *bedB;
+ BedFile *_bedA, *_bedB;
// do we care about strandedness when counting coverage?
- bool forceStrand;
+ bool _forceStrand;
// should we write a histogram for each feature in B?
- bool writeHistogram;
+ bool _writeHistogram;
// are we dealing with BAM input for "A"?
- bool bamInput;
+ bool _bamInput;
// 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 804a997f..df618ebb 100755
--- a/src/coverageBed/coverageMain.cpp
+++ b/src/coverageBed/coverageMain.cpp
@@ -99,9 +99,8 @@ int main(int argc, char* argv[]) {
}
if (!showHelp) {
-
BedCoverage *bg = new BedCoverage(bedAFile, bedBFile, forceStrand, writeHistogram, bamInput);
- bg->DetermineBedInput();
+ delete bg;
return 0;
}
else {
diff --git a/src/fastaFromBed/fastaFromBed.cpp b/src/fastaFromBed/fastaFromBed.cpp
index 931ebb86..c69736bd 100755
--- a/src/fastaFromBed/fastaFromBed.cpp
+++ b/src/fastaFromBed/fastaFromBed.cpp
@@ -16,16 +16,18 @@ Bed2Fa::Bed2Fa(bool &useName, string &dbFile, string &bedFile, string &fastaOutF
bool &useFasta, bool &useStrand) {
if (useName) {
- this->useName = true;
+ _useName = true;
}
- this->dbFile = dbFile;
- this->bedFile = bedFile;
- this->fastaOutFile = fastaOutFile;
- this->useFasta = useFasta;
- this->useStrand = useStrand;
+ _dbFile = dbFile;
+ _bedFile = bedFile;
+ _fastaOutFile = fastaOutFile;
+ _useFasta = useFasta;
+ _useStrand = useStrand;
- this->bed = new BedFile(this->bedFile);
+ _bed = new BedFile(_bedFile);
+
+ ExtractDNA();
}
@@ -41,21 +43,21 @@ void Bed2Fa::ExtractDNA() {
/* Make sure that we can oen all of the files successfully*/
// open the fasta database for reading
- ifstream faDb(this->dbFile.c_str(), ios::in);
+ ifstream faDb(_dbFile.c_str(), ios::in);
if ( !faDb ) {
- cerr << "Error: The requested fasta database file (" << this->dbFile << ") could not be opened. Exiting!" << endl;
+ cerr << "Error: The requested fasta database file (" << _dbFile << ") could not be opened. Exiting!" << endl;
exit (1);
}
// open the fasta database for reading
- ofstream faOut(this->fastaOutFile.c_str(), ios::out);
+ ofstream faOut(_fastaOutFile.c_str(), ios::out);
if ( !faOut ) {
- cerr << "Error: The requested fasta output file (" << this->fastaOutFile << ") could not be opened. Exiting!" << endl;
+ cerr << "Error: The requested fasta output file (" << _fastaOutFile << ") could not be opened. Exiting!" << endl;
exit (1);
}
// load the BED file into an unbinned map.
- bed->loadBedFileIntoMapNoBin();
+ _bed->loadBedFileIntoMapNoBin();
//Read the fastaDb chromosome by chromosome
string fastaDbLine;
@@ -71,7 +73,7 @@ void Bed2Fa::ExtractDNA() {
else {
if (currDNA.size() > 0) {
- vector<BED> bedList = bed->bedMapNoBin[currChrom];
+ vector<BED> bedList = _bed->bedMapNoBin[currChrom];
// loop through each BED entry for this chrom and
// print the sequence
@@ -84,13 +86,13 @@ void Bed2Fa::ExtractDNA() {
string dna = currDNA.substr(bedList[i].start, ((bedList[i].end - bedList[i].start)));
// revcomp if necessary. Thanks to Thomas Doktor.
- if ((this->useStrand == true) && (bedList[i].strand == "-")) {
+ if ((_useStrand == true) && (bedList[i].strand == "-")) {
reverseComplement(dna);
}
- if (!(this->useName)) {
- if (this->useFasta == true) {
- if (this->useStrand == true) {
+ if (!(_useName)) {
+ if (_useFasta == true) {
+ if (_useStrand == true) {
faOut << ">" << currChrom << ":" << bedList[i].start << "-"
<< bedList[i].end << "(" << bedList[i].strand << ")" << endl << dna << endl;
}
@@ -100,7 +102,7 @@ void Bed2Fa::ExtractDNA() {
}
}
else {
- if (this->useStrand == true) {
+ if (_useStrand == true) {
faOut << currChrom << ":" << bedList[i].start << "-"
<< bedList[i].end << "(" << bedList[i].strand << ")"
<< "\t" << dna << endl;
@@ -112,7 +114,7 @@ void Bed2Fa::ExtractDNA() {
}
}
else {
- if (this->useFasta == true) {
+ if (_useFasta == true) {
faOut << ">" << bedList[i].name << endl << dna << endl;
}
else {
@@ -132,7 +134,7 @@ void Bed2Fa::ExtractDNA() {
// process the last chromosome in the fasta file.
if (currDNA.size() > 0) {
- vector<BED> bedList = bed->bedMapNoBin[currChrom];
+ vector<BED> bedList = _bed->bedMapNoBin[currChrom];
// loop through each BED entry for this chrom and
// print the sequence.
@@ -145,13 +147,13 @@ void Bed2Fa::ExtractDNA() {
string dna = currDNA.substr(bedList[i].start, ((bedList[i].end - bedList[i].start)));
// revcomp if necessary. Thanks to Thomas Doktor.
- if ((this->useStrand == true) && (bedList[i].strand == "-")) {
+ if ((_useStrand == true) && (bedList[i].strand == "-")) {
reverseComplement(dna);
}
- if (!(this->useName)) {
- if (this->useFasta == true) {
- if (this->useStrand == true) {
+ if (!(_useName)) {
+ if (_useFasta == true) {
+ if (_useStrand == true) {
faOut << ">" << currChrom << ":" << bedList[i].start << "-"
<< bedList[i].end << "(" << bedList[i].strand << ")" << endl << dna << endl;
}
@@ -161,7 +163,7 @@ void Bed2Fa::ExtractDNA() {
}
}
else {
- if (this->useStrand == true) {
+ if (_useStrand == true) {
faOut << currChrom << ":" << bedList[i].start << "-"
<< bedList[i].end << "(" << bedList[i].strand << ")"
<< "\t" << dna << endl;
@@ -173,7 +175,7 @@ void Bed2Fa::ExtractDNA() {
}
}
else {
- if (this->useFasta == true) {
+ if (_useFasta == true) {
faOut << ">" << bedList[i].name << endl << dna << endl;
}
else {
diff --git a/src/fastaFromBed/fastaFromBed.h b/src/fastaFromBed/fastaFromBed.h
index 1b62f367..17b12215 100755
--- a/src/fastaFromBed/fastaFromBed.h
+++ b/src/fastaFromBed/fastaFromBed.h
@@ -38,15 +38,15 @@ public:
private:
- bool useName;
- string dbFile;
- string bedFile;
- string fastaOutFile;
- bool useFasta;
- bool useStrand;
+ bool _useName;
+ string _dbFile;
+ string _bedFile;
+ string _fastaOutFile;
+ bool _useFasta;
+ bool _useStrand;
// instance of a bed file class.
- BedFile *bed;
+ BedFile *_bed;
};
diff --git a/src/fastaFromBed/fastaFromBedMain.cpp b/src/fastaFromBed/fastaFromBedMain.cpp
index 1a3e0eb3..e2028815 100755
--- a/src/fastaFromBed/fastaFromBedMain.cpp
+++ b/src/fastaFromBed/fastaFromBedMain.cpp
@@ -106,7 +106,8 @@ int main(int argc, char* argv[]) {
if (!showHelp) {
Bed2Fa *b2f = new Bed2Fa(useNameOnly, fastaDbFile, bedFile, fastaOutFile, useFasta, useStrand);
- b2f->ExtractDNA();
+ delete b2f;
+
return 0;
}
else {
diff --git a/src/genomeCoverageBed/genomeCoverageBed.cpp b/src/genomeCoverageBed/genomeCoverageBed.cpp
index 0c25590a..1d845c80 100755
--- a/src/genomeCoverageBed/genomeCoverageBed.cpp
+++ b/src/genomeCoverageBed/genomeCoverageBed.cpp
@@ -16,25 +16,38 @@
BedGenomeCoverage::BedGenomeCoverage(string &bedFile, string &genomeFile, bool &eachBase,
bool &startSites, bool &bedGraph, int &max, bool &bamInput) {
- this->bedFile = bedFile;
- this->genomeFile = genomeFile;
- this->eachBase = eachBase;
- this->startSites = startSites;
- this->bedGraph = bedGraph;
- this->max = max;
- this->bamInput = bamInput;
+ _bedFile = bedFile;
+ _genomeFile = genomeFile;
+ _eachBase = eachBase;
+ _startSites = startSites;
+ _bedGraph = bedGraph;
+ _max = max;
+ _bamInput = bamInput;
- this->bed = new BedFile(bedFile);
- this->genome = new GenomeFile(genomeFile);
+ _bed = new BedFile(bedFile);
+ _genome = new GenomeFile(genomeFile);
+
+ if (_bed->bedFile != "stdin") { // process a file
+ if (_bamInput == false)
+ CoverageBed();
+ else
+ CoverageBam(_bed->bedFile);
+ }
+ else { // process stdin
+ if (_bamInput == false)
+ CoverageBed();
+ else
+ CoverageBam("stdin");
+ }
}
BedGenomeCoverage::~BedGenomeCoverage(void) {
- delete this->bed;
+ delete _bed;
}
-void BedGenomeCoverage::CoverageBed(istream &bedInput) {
+void BedGenomeCoverage::CoverageBed() {
chromHistMap chromDepthHist;
@@ -45,71 +58,64 @@ void BedGenomeCoverage::CoverageBed(istream &bedInput) {
int currChromSize = 0;
int start, end;
- string bedLine;
+ BED a;
int lineNum = 0; // current input line number
- vector<string> bedFields; // vector for a BED entry
- bedFields.reserve(12);
- while (getline(bedInput, bedLine)) {
-
- Tokenize(bedLine,bedFields);
- lineNum++;
- BED bedEntry; // used to store the current BED line from the BED file.
-
- if (bed->parseLine(bedEntry, bedFields, lineNum)) {
+ _bed->Open();
+ while (_bed->GetNextBed(a, lineNum)) {
- currChrom = bedEntry.chrom;
- start = bedEntry.start;
- end = bedEntry.end - 1;
-
- if (currChrom != prevChrom) {
- // If we've moved beyond the first encountered chromosomes,
- // process the results of the previous chromosome.
- if (prevChrom.length() > 0) {
- ReportChromCoverage(chromCov, prevChromSize, prevChrom, chromDepthHist);
- }
+ currChrom = a.chrom;
+ start = a.start;
+ end = a.end - 1;
- // empty the previous chromosome and reserve new
- std::vector<DEPTH>().swap(chromCov);
-
- // get the current chrom size and allocate space
- currChromSize = genome->getChromSize(currChrom);
- chromCov.resize(currChromSize);
-
- // process the first line for this chromosome.
- // make sure the coordinates fit within the chrom
- if (start < currChromSize) {
- chromCov[start].starts++;
- }
- if (end < currChromSize) {
- chromCov[end].ends++;
- }
- else {
- chromCov[currChromSize-1].ends++;
- }
+ if (currChrom != prevChrom) {
+ // If we've moved beyond the first encountered chromosomes,
+ // process the results of the previous chromosome.
+ if (prevChrom.length() > 0) {
+ ReportChromCoverage(chromCov, prevChromSize, prevChrom, chromDepthHist);
+ }
+
+ // empty the previous chromosome and reserve new
+ std::vector<DEPTH>().swap(chromCov);
+
+ // get the current chrom size and allocate space
+ currChromSize = _genome->getChromSize(currChrom);
+ chromCov.resize(currChromSize);
+
+ // process the first line for this chromosome.
+ // make sure the coordinates fit within the chrom
+ if (start < currChromSize) {
+ chromCov[start].starts++;
+ }
+ if (end < currChromSize) {
+ chromCov[end].ends++;
}
else {
- // process the other lines for this chromosome.
- // make sure the coordinates fit within the chrom
- if (start < currChromSize) {
- chromCov[start].starts++;
- }
- if (end < currChromSize) {
- chromCov[end].ends++;
- }
- else {
- chromCov[currChromSize-1].ends++;
- }
+ chromCov[currChromSize-1].ends++;
}
- prevChrom = currChrom;
- prevChromSize = currChromSize;
}
- bedFields.clear();
+ else {
+ // process the other lines for this chromosome.
+ // make sure the coordinates fit within the chrom
+ if (start < currChromSize) {
+ chromCov[start].starts++;
+ }
+ if (end < currChromSize) {
+ chromCov[end].ends++;
+ }
+ else {
+ chromCov[currChromSize-1].ends++;
+ }
+ }
+ prevChrom = currChrom;
+ prevChromSize = currChromSize;
}
+ _bed->Close();
+
// process the results of the last chromosome.
ReportChromCoverage(chromCov, currChromSize, currChrom, chromDepthHist);
- if (this->eachBase == false && this->bedGraph == false) {
+ if (_eachBase == false && _bedGraph == false) {
ReportGenomeCoverage(chromDepthHist);
}
}
@@ -156,7 +162,7 @@ void BedGenomeCoverage::CoverageBam(string bamFile) {
std::vector<DEPTH>().swap(chromCov);
// get the current chrom size and allocate space
- currChromSize = genome->getChromSize(currChrom);
+ currChromSize = _genome->getChromSize(currChrom);
chromCov.resize(currChromSize);
// process the first line for this chromosome.
@@ -191,7 +197,7 @@ void BedGenomeCoverage::CoverageBam(string bamFile) {
// process the results of the last chromosome.
ReportChromCoverage(chromCov, currChromSize, currChrom, chromDepthHist);
- if (this->eachBase == false && this->bedGraph == false) {
+ if (_eachBase == false && _bedGraph == false) {
ReportGenomeCoverage(chromDepthHist);
}
@@ -202,7 +208,7 @@ void BedGenomeCoverage::CoverageBam(string bamFile) {
void BedGenomeCoverage::ReportChromCoverage(const vector<DEPTH> &chromCov, int &chromSize, string &chrom, chromHistMap &chromDepthHist) {
- if (this->eachBase) {
+ if (_eachBase) {
int depth = 0; // initialize the depth
for (int pos = 0; pos < chromSize; pos++) {
@@ -212,7 +218,7 @@ void BedGenomeCoverage::ReportChromCoverage(const vector<DEPTH> &chromCov, int &
depth = depth - chromCov[pos].ends;
}
}
- else if (this->bedGraph) {
+ else if (_bedGraph) {
ReportChromCoverageBedGraph(chromCov, chromSize, chrom);
}
else {
@@ -226,8 +232,8 @@ void BedGenomeCoverage::ReportChromCoverage(const vector<DEPTH> &chromCov, int &
// 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 >= this->max) {
- chromDepthHist[chrom][this->max]++;
+ if (depth >= _max) {
+ chromDepthHist[chrom][_max]++;
}
else {
chromDepthHist[chrom][depth]++;
@@ -250,18 +256,18 @@ void BedGenomeCoverage::ReportChromCoverage(const vector<DEPTH> &chromCov, int &
void BedGenomeCoverage::ReportGenomeCoverage(chromHistMap &chromDepthHist) {
// get the list of chromosome names in the genome
- vector<string> chromList = genome->getChromList();
+ 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);
+ 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);
+ chromDepthHist[chrom][0] += _genome->getChromSize(chrom);
}
}
@@ -328,25 +334,3 @@ void BedGenomeCoverage::ReportChromCoverageBedGraph(const vector<DEPTH> &chromCo
cout << chrom << "\t" << lastStart << "\t" << chromSize << "\t" << lastDepth << endl;
}
}
-
-
-void BedGenomeCoverage::DetermineBedInput() {
- if (bed->bedFile != "stdin") { // process a file
- if (this->bamInput == false) { //bed/gff
- ifstream beds(bed->bedFile.c_str(), ios::in);
- if ( !beds ) {
- cerr << "Error: The requested bed file (" << bed->bedFile << ") could not be opened. Exiting!" << endl;
- exit (1);
- }
- CoverageBed(beds);
- }
- else
- CoverageBam(bed->bedFile);
- }
- else { // process stdin
- if (this->bamInput == false)
- CoverageBed(cin);
- else
- CoverageBam("stdin");
- }
-}
diff --git a/src/genomeCoverageBed/genomeCoverageBed.h b/src/genomeCoverageBed/genomeCoverageBed.h
index a08e03bc..e598181e 100755
--- a/src/genomeCoverageBed/genomeCoverageBed.h
+++ b/src/genomeCoverageBed/genomeCoverageBed.h
@@ -45,31 +45,28 @@ public:
// destructor
~BedGenomeCoverage(void);
- void CoverageBed(istream &bedInput);
+private:
- void CoverageBam(string bamFile);
+ // data
+ string _bedFile;
+ string _genomeFile;
+ bool _bamInput;
+ bool _eachBase;
+ bool _startSites;
+ bool _bedGraph;
+ int _max;
+ // The BED file from which to compute coverage.
+ BedFile *_bed;
+ GenomeFile *_genome;
+
+ chromDepthMap _chromCov;
+
+ // methods
+ void CoverageBed();
+ void CoverageBam(string bamFile);
void ReportChromCoverage(const vector<DEPTH> &, int &chromSize, string &chrom, chromHistMap&);
-
void ReportGenomeCoverage(chromHistMap &chromDepthHist);
-
void ReportChromCoverageBedGraph(const vector<DEPTH> &chromCov, int &chromSize, string &chrom);
-
- void DetermineBedInput();
-
-private:
-
- string bedFile;
- string genomeFile;
- bool bamInput;
- bool eachBase;
- bool startSites;
- bool bedGraph;
- int max;
-
- // The BED file from which to compute coverage.
- BedFile *bed;
- GenomeFile *genome;
- chromDepthMap chromCov;
};
diff --git a/src/genomeCoverageBed/genomeCoverageMain.cpp b/src/genomeCoverageBed/genomeCoverageMain.cpp
index 731f2b07..3dcf152b 100755
--- a/src/genomeCoverageBed/genomeCoverageMain.cpp
+++ b/src/genomeCoverageBed/genomeCoverageMain.cpp
@@ -114,8 +114,7 @@ int main(int argc, char* argv[]) {
BedGenomeCoverage *bc = new BedGenomeCoverage(bedFile, genomeFile, eachBase,
startSites, bedGraph, max, bamInput);
-
- bc->DetermineBedInput();
+ delete bc;
return 0;
}
diff --git a/src/intersectBed/intersectBed.cpp b/src/intersectBed/intersectBed.cpp
index 1b8359bf..15491a6f 100755
--- a/src/intersectBed/intersectBed.cpp
+++ b/src/intersectBed/intersectBed.cpp
@@ -39,6 +39,21 @@ BedIntersect::BedIntersect(string bedAFile, string bedBFile, bool anyHit,
// create new BED file objects for A and B
_bedA = new BedFile(bedAFile);
_bedB = new BedFile(bedBFile);
+
+ // dealing with a proper file
+ if (_bedA->bedFile != "stdin") {
+ if (_bamInput == false)
+ IntersectBed();
+ else
+ IntersectBam(_bedA->bedFile);
+ }
+ // reading from stdin
+ else {
+ if (_bamInput == false)
+ IntersectBed();
+ else
+ IntersectBam("stdin");
+ }
}
@@ -262,28 +277,3 @@ void BedIntersect::IntersectBam(string bamFile) {
}
}
-
-void BedIntersect::DetermineBedInput() {
-
- // dealing with a proper file
- if (_bedA->bedFile != "stdin") {
- // it's BED or GFF
- if (_bamInput == false) {
- IntersectBed();
- }
- else {
- IntersectBam(_bedA->bedFile);
- }
- }
- // reading from stdin
- else {
- // it's BED or GFF
- if (_bamInput == false) {
- IntersectBed();
- }
- // it's BAM
- else {
- IntersectBam("stdin");
- }
- }
-}
diff --git a/src/intersectBed/intersectBed.h b/src/intersectBed/intersectBed.h
index e49f9fa1..9b4a05e4 100755
--- a/src/intersectBed/intersectBed.h
+++ b/src/intersectBed/intersectBed.h
@@ -39,7 +39,6 @@ public:
// destructor
~BedIntersect(void);
- void DetermineBedInput();
private:
diff --git a/src/intersectBed/intersectMain.cpp b/src/intersectBed/intersectMain.cpp
index 086cf603..a57df8d4 100755
--- a/src/intersectBed/intersectMain.cpp
+++ b/src/intersectBed/intersectMain.cpp
@@ -194,7 +194,7 @@ int main(int argc, char* argv[]) {
BedIntersect *bi = new BedIntersect(bedAFile, bedBFile, anyHit, writeA, writeB, writeOverlap,
writeAllOverlap, overlapFraction, noHit, writeCount, forceStrand,
reciprocalFraction, inputIsBam, outputIsBam);
- bi->DetermineBedInput();
+ delete bi;
return 0;
}
else {
diff --git a/src/linksBed/linksBed.cpp b/src/linksBed/linksBed.cpp
index d0594992..25097157 100755
--- a/src/linksBed/linksBed.cpp
+++ b/src/linksBed/linksBed.cpp
@@ -16,12 +16,14 @@
// Constructor
//
BedLinks::BedLinks(string &bedFile, string &base, string &org, string &db) {
- this->bedFile = bedFile;
- this->bed = new BedFile(bedFile);
+ _bedFile = bedFile;
+ _bed = new BedFile(bedFile);
- this->base = base;
- this->org = org;
- this->db = db;
+ _base = base;
+ _org = org;
+ _db = db;
+
+ CreateLinks();
}
//
@@ -45,12 +47,12 @@ void BedLinks::WriteURL(BED &bed, string &base) {
cout << "</a>" << endl;
cout << "\t</td>" << endl;
- if (this->bed->bedType == 4) {
+ if (_bed->bedType == 4) {
cout << "\t<td>" << endl;
cout << bed.name << endl;
cout << "\t</td>" << endl;
}
- else if (this->bed->bedType == 5) {
+ else if (_bed->bedType == 5) {
cout << "\t<td>" << endl;
cout << bed.name << endl;
cout << "\t</td>" << endl;
@@ -59,7 +61,7 @@ void BedLinks::WriteURL(BED &bed, string &base) {
cout << bed.score << endl;
cout << "\t</td>" << endl;
}
- else if ((this->bed->bedType == 6) || (this->bed->bedType == 9) || (this->bed->bedType == 12)) {
+ else if ((_bed->bedType == 6) || (_bed->bedType == 9) || (_bed->bedType == 12)) {
cout << "\t<td>" << endl;
cout << bed.name << endl;
cout << "\t</td>" << endl;
@@ -76,13 +78,13 @@ void BedLinks::WriteURL(BED &bed, string &base) {
}
-void BedLinks::LinksBed(istream &bedInput) {
+void BedLinks::CreateLinks() {
// construct the html base.
- string org = this->org;
- string db = this->db;
- string base = this->base;
+ string org = _org;
+ string db = _db;
+ string base = _base;
base.append("/cgi-bin/hgTracks?org=");
base.append(org);
base.append("&db=");
@@ -91,49 +93,27 @@ void BedLinks::LinksBed(istream &bedInput) {
// create the HTML header
cout << "<html>" << endl <<"\t<body>" << endl;
- cout << "<title>" << this->bedFile << "</title>" << 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;
- string bedLine;
int lineNum = 0;
- vector<string> bedFields;
- bedFields.reserve(12);
-
- cout << "<h3>BED Entries from: stdin </h3>" << endl;
-
- while (getline(bedInput, bedLine)) {
+ BED bedEntry;
- Tokenize(bedLine,bedFields);
- lineNum++;
- BED bedEntry;
-
- if (this->bed->parseLine(bedEntry, bedFields, lineNum)) {
- bedEntry.count = 0;
- WriteURL(bedEntry, base);
- }
- bedFields.clear();
+ _bed->Open();
+ while (_bed->GetNextBed(bedEntry, lineNum)) {
+ bedEntry.count = 0;
+ WriteURL(bedEntry, base);
}
+ _bed->Close();
+
cout << "</table>" << endl;
cout << "</p>" << endl;
cout << "\t</body>" << endl <<"</html>" << endl;
}
-void BedLinks::DetermineBedInput() {
-
- if (this->bedFile != "stdin") { // process a file
- ifstream beds(this->bedFile.c_str(), ios::in);
- if ( !beds ) {
- cerr << "Error: The requested bed file (" << this->bedFile << ") could not be opened. Exiting!" << endl;
- exit (1);
- }
- LinksBed(beds);
- }
- else { // process stdin
- LinksBed(cin);
- }
-}
diff --git a/src/linksBed/linksBed.h b/src/linksBed/linksBed.h
index 06e8b851..01b768ac 100755
--- a/src/linksBed/linksBed.h
+++ b/src/linksBed/linksBed.h
@@ -25,22 +25,20 @@ class BedLinks {
public:
// constructor
- BedLinks(string &, string &, string &, string &);
+ BedLinks(string &bedFile, string &base, string &org, string &db);
// destructor
~BedLinks(void);
-
- void WriteURL(BED &, string &);
- void LinksBed(istream &bedInput); // the default. sorts by chrom (asc.) then by start (asc.)
- void DetermineBedInput();
private:
- string bedFile;
- string base;
- string org;
- string db;
+ string _bedFile;
+ string _base;
+ string _org;
+ string _db;
// instance of a bed file class.
- BedFile *bed;
+ 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 f5b8ea2a..a03e300e 100755
--- a/src/linksBed/linksMain.cpp
+++ b/src/linksBed/linksMain.cpp
@@ -95,7 +95,7 @@ int main(int argc, char* argv[]) {
if (!showHelp) {
BedLinks *bl = new BedLinks(bedFile, base, org, db);
- bl->DetermineBedInput();
+ delete bl;
return 0;
}
else {
diff --git a/src/maskFastaFromBed/maskFastaFromBed.cpp b/src/maskFastaFromBed/maskFastaFromBed.cpp
index ab283ce7..f2629f83 100755
--- a/src/maskFastaFromBed/maskFastaFromBed.cpp
+++ b/src/maskFastaFromBed/maskFastaFromBed.cpp
@@ -15,19 +15,20 @@
MaskFastaFromBed::MaskFastaFromBed(string &fastaInFile, string &bedFile, string &fastaOutFile, bool &softMask) {
- this->softMask = false;
+ _softMask = false;
if (softMask) {
- this->softMask = true;
+ _softMask = true;
}
- this->fastaInFile = fastaInFile;
- this->bedFile = bedFile;
- this->fastaOutFile = fastaOutFile;
+ _fastaInFile = fastaInFile;
+ _bedFile = bedFile;
+ _fastaOutFile = fastaOutFile;
- this->bed = new BedFile(this->bedFile);
+ _bed = new BedFile(_bedFile);
+
+ _bed->loadBedFileIntoMapNoBin();
- //
- bed->loadBedFileIntoMapNoBin();
+ MaskFasta();
}
@@ -43,16 +44,16 @@ void MaskFastaFromBed::MaskFasta() {
/* Make sure that we can open all of the files successfully*/
// open the fasta database for reading
- ifstream fa(this->fastaInFile.c_str(), ios::in);
+ ifstream fa(_fastaInFile.c_str(), ios::in);
if ( !fa ) {
- cerr << "Error: The requested fasta file (" << this->fastaInFile << ") could not be opened. Exiting!" << endl;
+ cerr << "Error: The requested fasta file (" << _fastaInFile << ") could not be opened. Exiting!" << endl;
exit (1);
}
// open the fasta database for reading
- ofstream faOut(this->fastaOutFile.c_str(), ios::out);
+ ofstream faOut(_fastaOutFile.c_str(), ios::out);
if ( !faOut ) {
- cerr << "Error: The requested fasta output file (" << this->fastaOutFile << ") could not be opened. Exiting!" << endl;
+ cerr << "Error: The requested fasta output file (" << _fastaOutFile << ") could not be opened. Exiting!" << endl;
exit (1);
}
@@ -79,7 +80,7 @@ void MaskFastaFromBed::MaskFasta() {
else {
if (currDNA.size() > 0) {
- vector<BED> bedList = bed->bedMapNoBin[currChrom];
+ vector<BED> bedList = _bed->bedMapNoBin[currChrom];
/*
loop through each BED entry for this chrom and
@@ -95,7 +96,7 @@ void MaskFastaFromBed::MaskFasta() {
then put it back
(2) otherwise replace with Ns
*/
- if (this->softMask) {
+ if (_softMask) {
replacement = currDNA.substr(start, length);
toLowerCase(replacement);
currDNA.replace(start, length, replacement);
@@ -119,14 +120,14 @@ void MaskFastaFromBed::MaskFasta() {
// exact same logic as in the main loop.
if (currDNA.size() > 0) {
- vector<BED> bedList = bed->bedMapNoBin[currChrom];
+ 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 (this->softMask) {
+ if (_softMask) {
replacement = currDNA.substr(start, length);
toLowerCase(replacement);
currDNA.replace(start, length, replacement);
diff --git a/src/maskFastaFromBed/maskFastaFromBed.h b/src/maskFastaFromBed/maskFastaFromBed.h
index 6550a7bf..e9fec55a 100755
--- a/src/maskFastaFromBed/maskFastaFromBed.h
+++ b/src/maskFastaFromBed/maskFastaFromBed.h
@@ -28,25 +28,26 @@ class MaskFastaFromBed {
public:
// constructor
- MaskFastaFromBed(string &, string &, string &, bool &);
+ MaskFastaFromBed(string &fastaInFile, string &bedFile, string &fastaOutFile, bool &softMask);
// destructor
~MaskFastaFromBed(void);
- void MaskFasta();
-
- void PrettyPrintChrom(ofstream &, string , const string &, int);
private:
- bool softMask;
+ bool _softMask;
- string fastaInFile;
- string bedFile;
- string fastaOutFile;
+ string _fastaInFile;
+ string _bedFile;
+ string _fastaOutFile;
// instance of a bed file class.
- BedFile *bed;
+ 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 00add002..720070f5 100755
--- a/src/maskFastaFromBed/maskFastaFromBedMain.cpp
+++ b/src/maskFastaFromBed/maskFastaFromBedMain.cpp
@@ -98,7 +98,7 @@ int main(int argc, char* argv[]) {
if (!showHelp) {
MaskFastaFromBed *maskFasta = new MaskFastaFromBed(fastaInFile, bedFile, fastaOutFile, softMask);
- maskFasta->MaskFasta();
+ delete maskFasta;
return 0;
}
else {
diff --git a/src/mergeBed/mergeBed.cpp b/src/mergeBed/mergeBed.cpp
index b577e466..6720bf14 100755
--- a/src/mergeBed/mergeBed.cpp
+++ b/src/mergeBed/mergeBed.cpp
@@ -29,13 +29,18 @@ void ReportMergedNames(const map<string, bool> &names) {
// ===============
BedMerge::BedMerge(string &bedFile, bool &numEntries, int &maxDistance, bool &forceStrand, bool &reportNames) {
- this->bedFile = bedFile;
- this->numEntries = numEntries;
- this->maxDistance = -1 * maxDistance;
- this->forceStrand = forceStrand;
- this->reportNames = reportNames;
+ _bedFile = bedFile;
+ _numEntries = numEntries;
+ _maxDistance = -1 * maxDistance;
+ _forceStrand = forceStrand;
+ _reportNames = reportNames;
- this->bed = new BedFile(bedFile);
+ _bed = new BedFile(bedFile);
+
+ if (_forceStrand == false)
+ MergeBed();
+ else
+ MergeBedStranded();
}
@@ -53,10 +58,10 @@ void BedMerge::MergeBed() {
// load the "B" bed file into a map so
// that we can easily compare "A" to it for overlaps
- bed->loadBedFileIntoMapNoBin();
+ _bed->loadBedFileIntoMapNoBin();
// loop through each chromosome and merge their BED entries
- for (masterBedMapNoBin::iterator m = bed->bedMapNoBin.begin(); m != bed->bedMapNoBin.end(); ++m) {
+ for (masterBedMapNoBin::iterator m = _bed->bedMapNoBin.begin(); m != _bed->bedMapNoBin.end(); ++m) {
// bedList is already sorted by start position.
vector<BED> bedList = m->second;
@@ -81,7 +86,7 @@ void BedMerge::MergeBed() {
// Is there an overlap between the current and previous entries?
if ( overlaps(bedList[prev].start, bedList[prev].end,
- bedList[curr].start, bedList[curr].end) >= this->maxDistance) {
+ bedList[curr].start, bedList[curr].end) >= _maxDistance) {
OIP = true;
mergeCount++;
minStart = min(bedList[prev].start, min(minStart, bedList[curr].start));
@@ -91,7 +96,7 @@ void BedMerge::MergeBed() {
names[bedList[curr].name] = true;
}
else if ( overlaps(minStart, maxEnd,
- bedList[curr].start, bedList[curr].end) >= this->maxDistance) {
+ bedList[curr].start, bedList[curr].end) >= _maxDistance) {
mergeCount++;
minStart = min(minStart, bedList[curr].start);
maxEnd = max(maxEnd, bedList[curr].end);
@@ -100,10 +105,10 @@ void BedMerge::MergeBed() {
else {
// was there an overlap befor the current entry broke it?
if (OIP) {
- if (this->numEntries) {
+ if (_numEntries) {
cout << bedList[prev].chrom << "\t" << minStart << "\t" << maxEnd << "\t" << mergeCount << endl;
}
- else if (this->reportNames) {
+ else if (_reportNames) {
cout << bedList[prev].chrom << "\t" << minStart << "\t" << maxEnd << "\t";
ReportMergedNames(names);
cout << endl;
@@ -113,10 +118,10 @@ void BedMerge::MergeBed() {
}
}
else {
- if (this->numEntries) {
+ if (_numEntries) {
cout << bedList[prev].chrom << "\t" << bedList[prev].start << "\t" << bedList[prev].end << "\t" << mergeCount << endl;
}
- else if (this->reportNames) {
+ else if (_reportNames) {
cout << bedList[prev].chrom << "\t" << bedList[prev].start << "\t" << bedList[prev].end << "\t" << bedList[prev].name << endl;
}
else {
@@ -138,10 +143,10 @@ void BedMerge::MergeBed() {
// clean up based on the last entry for the current chromosome
if (OIP) {
- if (this->numEntries) {
+ if (_numEntries) {
cout << bedList[prev].chrom << "\t" << minStart << "\t" << maxEnd << "\t" << mergeCount << endl;
}
- else if (this->reportNames) {
+ else if (_reportNames) {
cout << bedList[prev].chrom << "\t" << minStart << "\t" << maxEnd << "\t";
ReportMergedNames(names);
cout << endl;
@@ -151,10 +156,10 @@ void BedMerge::MergeBed() {
}
}
else {
- if (this->numEntries) {
+ if (_numEntries) {
cout << bedList[prev].chrom << "\t" << bedList[prev].start << "\t" << bedList[prev].end << "\t" << mergeCount << endl;
}
- else if (this->reportNames) {
+ else if (_reportNames) {
cout << bedList[prev].chrom << "\t" << bedList[prev].start << "\t" << bedList[prev].end << "\t" << bedList[prev].name << endl;
}
else {
@@ -172,10 +177,10 @@ void BedMerge::MergeBedStranded() {
// load the "B" bed file into a map so
// that we can easily compare "A" to it for overlaps
- bed->loadBedFileIntoMapNoBin();
+ _bed->loadBedFileIntoMapNoBin();
// loop through each chromosome and merge their BED entries
- for (masterBedMapNoBin::iterator m = bed->bedMapNoBin.begin(); m != bed->bedMapNoBin.end(); ++m) {
+ for (masterBedMapNoBin::iterator m = _bed->bedMapNoBin.begin(); m != _bed->bedMapNoBin.end(); ++m) {
// bedList is already sorted by start position.
vector<BED> bedList = m->second;
@@ -221,7 +226,7 @@ void BedMerge::MergeBedStranded() {
}
if ( overlaps(bedList[prev].start, bedList[prev].end,
- bedList[curr].start, bedList[curr].end) >= this->maxDistance) {
+ bedList[curr].start, bedList[curr].end) >= _maxDistance) {
OIP = true;
mergeCount++;
minStart = min(bedList[prev].start, min(minStart, bedList[curr].start));
@@ -231,7 +236,7 @@ void BedMerge::MergeBedStranded() {
names[bedList[curr].name] = true;
}
else if ( overlaps(minStart, maxEnd,
- bedList[curr].start, bedList[curr].end) >= this->maxDistance) {
+ bedList[curr].start, bedList[curr].end) >= _maxDistance) {
mergeCount++;
minStart = min(minStart, bedList[curr].start);
maxEnd = max(maxEnd, bedList[curr].end);
@@ -241,10 +246,10 @@ void BedMerge::MergeBedStranded() {
// was there an overlap before the current entry broke it?
if (OIP) {
- if (this->numEntries) {
+ if (_numEntries) {
cout << bedList[prev].chrom << "\t" << minStart << "\t" << maxEnd << "\t" << mergeCount << "\t" << strands[s] << endl;
}
- else if (this->reportNames) {
+ else if (_reportNames) {
cout << bedList[prev].chrom << "\t" << minStart << "\t" << maxEnd << "\t";
ReportMergedNames(names);
cout << "\t" << strands[s] << endl;
@@ -254,10 +259,10 @@ void BedMerge::MergeBedStranded() {
}
}
else {
- if ((this->numEntries) && (numOnStrand > 0)) {
+ if ((_numEntries) && (numOnStrand > 0)) {
cout << bedList[prev].chrom << "\t" << bedList[prev].start << "\t" << bedList[prev].end << "\t" << mergeCount << "\t" << strands[s] << endl;
}
- else if (this->reportNames) {
+ 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) {
@@ -280,10 +285,10 @@ void BedMerge::MergeBedStranded() {
// clean up based on the last entry for the current chromosome
if (OIP) {
- if (this->numEntries) {
+ if (_numEntries) {
cout << bedList[prev].chrom << "\t" << minStart << "\t" << maxEnd << "\t" << mergeCount << "\t" << strands[s] << endl;
}
- else if (this->reportNames) {
+ else if (_reportNames) {
cout << bedList[prev].chrom << "\t" << minStart << "\t" << maxEnd << "\t";
ReportMergedNames(names);
cout << "\t" << strands[s] << endl;
@@ -293,10 +298,10 @@ void BedMerge::MergeBedStranded() {
}
}
else {
- if ((this->numEntries) && (numOnStrand > 0)) {
+ if ((_numEntries) && (numOnStrand > 0)) {
cout << bedList[prev].chrom << "\t" << bedList[prev].start << "\t" << bedList[prev].end << "\t" << mergeCount << "\t" << strands[s] << endl;
}
- else if ((this->reportNames) && (numOnStrand > 0)) {
+ 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) {
diff --git a/src/mergeBed/mergeBed.h b/src/mergeBed/mergeBed.h
index 336c5d55..b6023801 100755
--- a/src/mergeBed/mergeBed.h
+++ b/src/mergeBed/mergeBed.h
@@ -29,7 +29,7 @@ class BedMerge {
public:
// constructor
- BedMerge(string &, bool &, int&, bool &, bool &);
+ BedMerge(string &bedFile, bool &numEntries, int &maxDistance, bool &forceStrand, bool &reportNames);
// destructor
~BedMerge(void);
@@ -39,12 +39,12 @@ public:
private:
- string bedFile;
- bool numEntries;
- bool forceStrand;
- bool reportNames;
- int maxDistance;
+ string _bedFile;
+ bool _numEntries;
+ bool _forceStrand;
+ bool _reportNames;
+ int _maxDistance;
// instance of a bed file class.
- BedFile *bed;
+ BedFile *_bed;
};
diff --git a/src/mergeBed/mergeMain.cpp b/src/mergeBed/mergeMain.cpp
index 82e3dde4..43f3f653 100755
--- a/src/mergeBed/mergeMain.cpp
+++ b/src/mergeBed/mergeMain.cpp
@@ -100,13 +100,7 @@ int main(int argc, char* argv[]) {
if (!showHelp) {
BedMerge *bm = new BedMerge(bedFile, numEntries, maxDistance, forceStrand, reportNames);
-
- if (!forceStrand) {
- bm->MergeBed();
- }
- else {
- bm->MergeBedStranded();
- }
+ delete bm;
return 0;
}
else {
diff --git a/src/pairToBed/pairToBed.cpp b/src/pairToBed/pairToBed.cpp
index f7423189..3a52aa8c 100755
--- a/src/pairToBed/pairToBed.cpp
+++ b/src/pairToBed/pairToBed.cpp
@@ -35,16 +35,16 @@ bool IsCorrectMappingForBEDPE (const BamAlignment &bam) {
BedIntersectPE::BedIntersectPE(string bedAFilePE, string bedBFile, float overlapFraction,
string searchType, bool forceStrand, bool bamInput, bool bamOutput) {
- this->bedAFilePE = bedAFilePE;
- this->bedBFile = bedBFile;
- this->overlapFraction = overlapFraction;
- this->forceStrand = forceStrand;
- this->searchType = searchType;
- this->bamInput = bamInput;
- this->bamOutput = bamOutput;
+ _bedAFilePE = bedAFilePE;
+ _bedBFile = bedBFile;
+ _overlapFraction = overlapFraction;
+ _forceStrand = forceStrand;
+ _searchType = searchType;
+ _bamInput = bamInput;
+ _bamOutput = bamOutput;
- this->bedA = new BedFilePE(bedAFilePE);
- this->bedB = new BedFile(bedBFile);
+ _bedA = new BedFilePE(bedAFilePE);
+ _bedB = new BedFile(bedBFile);
}
@@ -72,7 +72,7 @@ void BedIntersectPE::FindOverlaps(const BEDPE &a, vector<BED> &hits1, vector<BED
// 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, this->forceStrand);
+ _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();
@@ -84,12 +84,12 @@ void BedIntersectPE::FindOverlaps(const BEDPE &a, vector<BED> &hits1, vector<BED
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 ) >= this->overlapFraction ) {
+ if ( ( (float) overlapBases / (float) aLength ) >= _overlapFraction ) {
numOverlapsEnd1++;
if (type == "either") {
- bedA->reportBedPETab(a);
- bedB->reportBedNewLine(*h);
+ _bedA->reportBedPETab(a);
+ _bedB->reportBedNewLine(*h);
}
else {
qualityHits1.push_back(*h);
@@ -102,7 +102,7 @@ void BedIntersectPE::FindOverlaps(const BEDPE &a, vector<BED> &hits1, vector<BED
// 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, this->forceStrand);
+ _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();
@@ -114,12 +114,12 @@ void BedIntersectPE::FindOverlaps(const BEDPE &a, vector<BED> &hits1, vector<BED
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 ) >= this->overlapFraction ) {
+ if ( ( (float) overlapBases / (float) aLength ) >= _overlapFraction ) {
numOverlapsEnd2++;
if (type == "either") {
- bedA->reportBedPETab(a);
- bedB->reportBedNewLine(*h);
+ _bedA->reportBedPETab(a);
+ _bedB->reportBedNewLine(*h);
}
else {
qualityHits2.push_back(*h);
@@ -131,49 +131,49 @@ void BedIntersectPE::FindOverlaps(const BEDPE &a, vector<BED> &hits1, vector<BED
// Now report the hits depending on what the user has requested.
if (type == "neither") {
if ( (numOverlapsEnd1 == 0) && (numOverlapsEnd2 == 0) ) {
- bedA->reportBedPENewLine(a);
+ _bedA->reportBedPENewLine(a);
}
}
else if (type == "notboth") {
if ( (numOverlapsEnd1 == 0) && (numOverlapsEnd2 == 0) ) {
- bedA->reportBedPENewLine(a);
+ _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);
+ _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);
+ _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);
+ _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);
+ _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);
+ _bedA->reportBedPETab(a);
+ _bedB->reportBedNewLine(*q);
}
for (vector<BED>::iterator q = qualityHits2.begin(); q != qualityHits2.end(); ++q) {
- bedA->reportBedPETab(a);
- bedB->reportBedNewLine(*q);
+ _bedA->reportBedPETab(a);
+ _bedB->reportBedNewLine(*q);
}
}
}
@@ -189,8 +189,8 @@ bool BedIntersectPE::FindOneOrMoreOverlaps(const BEDPE &a, const string &type) {
// 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,
- this->forceStrand, this->overlapFraction);
+ 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;
@@ -201,8 +201,8 @@ bool BedIntersectPE::FindOneOrMoreOverlaps(const BEDPE &a, const string &type) {
// 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,
- this->forceStrand, this->overlapFraction);
+ 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;
@@ -263,7 +263,7 @@ void BedIntersectPE::FindSpanningOverlaps(const BEDPE &a, vector<BED> &hits, con
spanLength = spanEnd - spanStart;
// get the hits for the span
- bedB->FindOverlapsPerBin(a.chrom1, spanStart, spanEnd, a.strand1, hits, this->forceStrand);
+ _bedB->FindOverlapsPerBin(a.chrom1, spanStart, spanEnd, a.strand1, hits, _forceStrand);
vector<BED>::const_iterator h = hits.begin();
vector<BED>::const_iterator hitsEnd = hits.end();
@@ -275,17 +275,17 @@ void BedIntersectPE::FindSpanningOverlaps(const BEDPE &a, vector<BED> &hits, con
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 ) >= this->overlapFraction ) {
+ if ( ( (float) overlapBases / (float) spanLength ) >= _overlapFraction ) {
numOverlaps++;
if ((type == "ispan") || (type == "ospan")) {
- bedA->reportBedPETab(a);
- bedB->reportBedNewLine(*h);
+ _bedA->reportBedPETab(a);
+ _bedB->reportBedNewLine(*h);
}
}
}
if ( ( (type == "notispan") || (type == "notospan") ) && numOverlaps == 0 ) {
- bedA->reportBedPENewLine(a);
+ _bedA->reportBedPENewLine(a);
}
}
@@ -315,8 +315,8 @@ bool BedIntersectPE::FindOneOrMoreSpanningOverlaps(const BEDPE &a, const string
}
spanLength = spanEnd - spanStart;
- overlapFound = bedB->FindOneOrMoreOverlapsPerBin(a.chrom1, spanStart, spanEnd, a.strand1,
- this->forceStrand, this->overlapFraction);
+ overlapFound = _bedB->FindOneOrMoreOverlapsPerBin(a.chrom1, spanStart, spanEnd, a.strand1,
+ _forceStrand, _overlapFraction);
return overlapFound;
}
@@ -327,7 +327,7 @@ void BedIntersectPE::IntersectBedPE(istream &bedInput) {
// load the "B" bed file into a map so
// that we can easily compare "A" to it for overlaps
- bedB->loadBedFileIntoMap();
+ _bedB->loadBedFileIntoMap();
string bedLine;
int lineNum = 0; // current input line number
@@ -348,16 +348,16 @@ void BedIntersectPE::IntersectBedPE(istream &bedInput) {
BEDPE a;
// find the overlaps with B if it's a valid BED entry.
- if (bedA->parseBedPELine(a, bedFields, lineNum)) {
- if ( (this->searchType == "ispan") || (this->searchType == "ospan") ||
- (this->searchType == "notispan") || (this->searchType == "notospan") ) {
+ if (_bedA->parseBedPELine(a, bedFields, lineNum)) {
+ if ( (_searchType == "ispan") || (_searchType == "ospan") ||
+ (_searchType == "notispan") || (_searchType == "notospan") ) {
if (a.chrom1 == a.chrom2) {
- FindSpanningOverlaps(a, hits, this->searchType);
+ FindSpanningOverlaps(a, hits, _searchType);
hits.clear();
}
}
else {
- FindOverlaps(a, hits1, hits2, this->searchType);
+ FindOverlaps(a, hits1, hits2, _searchType);
hits1.clear();
hits2.clear();
}
@@ -373,7 +373,7 @@ 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();
+ _bedB->loadBedFileIntoMap();
// open the BAM file
BamReader reader;
@@ -385,7 +385,7 @@ void BedIntersectPE::IntersectBamPE(string bamFile) {
RefVector refs = reader.GetReferenceData();
// open a BAM output to stdout if we are writing BAM
- if (this->bamOutput == true) {
+ if (_bamOutput == true) {
// open our BAM writer
writer.Open("stdout", header, refs);
}
@@ -396,7 +396,7 @@ void BedIntersectPE::IntersectBamPE(string bamFile) {
hits1.reserve(1000);
hits2.reserve(1000);
- bedA->bedType = 10; // it's a full BEDPE given it's BAM
+ _bedA->bedType = 10; // it's a full BEDPE given it's BAM
BamAlignment bam;
bool overlapsFound;
@@ -409,72 +409,72 @@ void BedIntersectPE::IntersectBamPE(string bamFile) {
cerr << "Encountered an unpaired alignment. Are you sure this is a paired BAM file? Exiting." << endl;
exit(1);
}
- else if ((this->searchType == "ispan") || (this->searchType == "ospan")) {
+ else if ((_searchType == "ispan") || (_searchType == "ospan")) {
// only look for ispan and ospan when both ends are mapped.
if (bam.IsMapped() && bam.IsMateMapped()) {
// only do an inspan or outspan check if the alignment is intrachromosomal
if (bam.RefID == bam.MateRefID) {
- if (this->bamOutput == true) { // BAM output
+ if (_bamOutput == true) { // BAM output
BEDPE a; ConvertBamToBedPE(bam, refs, a);
// look for overlaps, and write to BAM if >=1 were found
- overlapsFound = FindOneOrMoreSpanningOverlaps(a, this->searchType);
+ overlapsFound = FindOneOrMoreSpanningOverlaps(a, _searchType);
if (overlapsFound == true) writer.SaveAlignment(bam);
}
else if ( IsCorrectMappingForBEDPE(bam) ) { // BEDPE output
BEDPE a;
ConvertBamToBedPE(bam, refs, a);
- FindSpanningOverlaps(a, hits, this->searchType);
+ FindSpanningOverlaps(a, hits, _searchType);
}
}
}
}
- else if ((this->searchType == "notispan") || (this->searchType == "notospan")) {
+ else if ((_searchType == "notispan") || (_searchType == "notospan")) {
// only look for notispan and notospan when both ends are mapped.
if (bam.IsMapped() && bam.IsMateMapped()) {
// only do an inspan or outspan if the alignment is intrachromosomal
if (bam.RefID == bam.MateRefID) {
- if (this->bamOutput == true) { // BAM output
+ if (_bamOutput == true) { // BAM output
BEDPE a; ConvertBamToBedPE(bam, refs, a);
// write to BAM if there were no overlaps
- overlapsFound = FindOneOrMoreSpanningOverlaps(a, this->searchType);
+ overlapsFound = FindOneOrMoreSpanningOverlaps(a, _searchType);
if (overlapsFound == false) writer.SaveAlignment(bam);
}
else if ( IsCorrectMappingForBEDPE(bam) ) { // BEDPE output
BEDPE a;
ConvertBamToBedPE(bam, refs, a);
- FindSpanningOverlaps(a, hits, this->searchType);
+ FindSpanningOverlaps(a, hits, _searchType);
}
}
// if inter-chromosomal or orphaned, we know it's not ispan and not ospan
- else if (this->bamOutput == true) writer.SaveAlignment(bam);
+ else if (_bamOutput == true) writer.SaveAlignment(bam);
}
// if both ends aren't mapped, we know that it's notispan and not ospan
- else if (this->bamOutput == true) writer.SaveAlignment(bam);
+ else if (_bamOutput == true) writer.SaveAlignment(bam);
}
- else if ( (this->searchType == "either") || (this->searchType == "xor") ||
- (this->searchType == "both") || (this->searchType == "notboth") ||
- (this->searchType == "neither") ) {
+ else if ( (_searchType == "either") || (_searchType == "xor") ||
+ (_searchType == "both") || (_searchType == "notboth") ||
+ (_searchType == "neither") ) {
- if (this->bamOutput == true) { // BAM output
+ if (_bamOutput == true) { // BAM output
BEDPE a; ConvertBamToBedPE(bam, refs, a);
// write to BAM if correct hits found
- overlapsFound = FindOneOrMoreOverlaps(a, this->searchType);
+ overlapsFound = FindOneOrMoreOverlaps(a, _searchType);
if (overlapsFound == true) writer.SaveAlignment(bam);
}
else if ( IsCorrectMappingForBEDPE(bam) ) { // BEDPE output
BEDPE a;
ConvertBamToBedPE(bam, refs, a);
- FindOverlaps(a, hits1, hits2, this->searchType);
+ FindOverlaps(a, hits1, hits2, _searchType);
hits1.clear();
hits2.clear();
}
}
}
reader.Close();
- if (this->bamOutput == true) {
+ if (_bamOutput == true) {
writer.Close();
}
}
@@ -482,21 +482,21 @@ void BedIntersectPE::IntersectBamPE(string bamFile) {
void BedIntersectPE::DetermineBedPEInput() {
- if (bedA->bedFile != "stdin") { // process a file
- if (this->bamInput == false) { // BEDPE
- ifstream beds(bedA->bedFile.c_str(), ios::in);
+ if (_bedA->bedFile != "stdin") { // process a file
+ if (_bamInput == false) { // BEDPE
+ ifstream beds(_bedA->bedFile.c_str(), ios::in);
if ( !beds ) {
- cerr << "Error: The requested bed file (" << bedA->bedFile << ") could not be opened. Exiting!" << endl;
+ cerr << "Error: The requested bed file (" << _bedA->bedFile << ") could not be opened. Exiting!" << endl;
exit (1);
}
IntersectBedPE(beds);
}
else { // bam
- IntersectBamPE(bedA->bedFile);
+ IntersectBamPE(_bedA->bedFile);
}
}
else { // process stdin
- if (this->bamInput == false) { // BEDPE
+ if (_bamInput == false) { // BEDPE
IntersectBedPE(cin);
}
else {
diff --git a/src/pairToBed/pairToBed.h b/src/pairToBed/pairToBed.h
index bc938f9d..565827ad 100755
--- a/src/pairToBed/pairToBed.h
+++ b/src/pairToBed/pairToBed.h
@@ -62,21 +62,22 @@ public:
private:
- string bedAFilePE;
- string bedBFile;
- float overlapFraction;
- string searchType;
- bool forceStrand;
- bool bamInput;
- bool bamOutput;
+ string _bedAFilePE;
+ string _bedBFile;
+ float _overlapFraction;
+ string _searchType;
+ bool _forceStrand;
+ bool _bamInput;
+ bool _bamOutput;
// instance of a paired-end bed file class.
- BedFilePE *bedA;
+ BedFilePE *_bedA;
// instance of a bed file class.
- BedFile *bedB;
+ BedFile *_bedB;
- inline void ConvertBamToBedPE(const BamAlignment &bam, const RefVector &refs, BEDPE &a) {
+ inline
+ void ConvertBamToBedPE(const BamAlignment &bam, const RefVector &refs, BEDPE &a) {
a.start1 = a.start2 = a.end1 = a.end2 = -1;
a.chrom1 = a.chrom2 = a.strand1 = a.strand2 = ".";
diff --git a/src/shuffleBed/shuffleBed.cpp b/src/shuffleBed/shuffleBed.cpp
index cdcfa2f5..faa62d1e 100755
--- a/src/shuffleBed/shuffleBed.cpp
+++ b/src/shuffleBed/shuffleBed.cpp
@@ -15,33 +15,46 @@
BedShuffle::BedShuffle(string &bedFile, string &genomeFile, string &excludeFile, bool &haveSeed, bool &haveExclude, bool &sameChrom, int &seed) {
- this->bedFile = bedFile;
- this->genomeFile = genomeFile;
- this->excludeFile = excludeFile;
- this->sameChrom = sameChrom;
- this->haveExclude = haveExclude;
- this->haveSeed = haveSeed;
+ _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 (this->haveSeed) {
- this->seed = seed;
+ if (_haveSeed) {
+ _seed = seed;
srand(seed);
}
else {
srand((unsigned)time(0));
}
- this->bed = new BedFile(bedFile);
- this->genome = new GenomeFile(genomeFile);
- this->chroms = genome->getChromList();
- this->numChroms = genome->getNumberOfChroms();
+ _bed = new BedFile(bedFile);
+ _genome = new GenomeFile(genomeFile);
+ _chroms = _genome->getChromList();
+ _numChroms = _genome->getNumberOfChroms();
- if (this->haveExclude) {
- this->exclude = new BedFile(excludeFile);
- this->exclude->loadBedFileIntoMap();
+ 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();
}
}
@@ -51,55 +64,68 @@ BedShuffle::~BedShuffle(void) {
}
-void BedShuffle::Shuffle(istream &bedInput) {
+void BedShuffle::Shuffle() {
int lineNum = 0;
- string bedLine; // used to store the current (unparsed) line from the BED file.
- vector<string> bedFields;
- bedFields.reserve(12);
-
- while (getline(bedInput, bedLine)) {
-
- Tokenize(bedLine,bedFields);
- lineNum++;
- BED bedEntry; // used to store the current BED line from the BED file.
-
- if (bed->parseLine(bedEntry, bedFields, lineNum)) {
- // choose a new locus for this feat
- ChooseLocus(bedEntry);
- bed->reportBedNewLine(bedEntry);
- }
- bedFields.clear();
+ BED bedEntry; // used to store the current BED line from the BED file.
+
+ _bed->Open();
+ while (_bed->GetNextBed(bedEntry, lineNum)) {
+ ChooseLocus(bedEntry);
+ _bed->reportBedNewLine(bedEntry);
}
+ _bed->Close();
}
-void BedShuffle::ShuffleWithExclusions(istream &bedInput) {
+void BedShuffle::ShuffleWithExclusions() {
int lineNum = 0;
- string bedLine; // used to store the current (unparsed) line from the BED file.
- vector<string> bedFields;
- bedFields.reserve(12);
+ BED bedEntry; // used to store the current BED line from the BED file.
vector<BED> hits;
hits.reserve(100);
- while (getline(bedInput, bedLine)) {
+ _bed->Open();
+ while (_bed->GetNextBed(bedEntry, lineNum)) {
+
+ // choose a random locus
+ ChooseLocus(bedEntry);
- Tokenize(bedLine,bedFields);
- lineNum++;
- BED bedEntry; // used to store the current BED line from the BED file.
+ // 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) {
- if (bed->parseLine(bedEntry, bedFields, lineNum)) {
-
- // 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;
+ 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) {
@@ -109,49 +135,18 @@ void BedShuffle::ShuffleWithExclusions(istream &bedInput) {
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*/
- }
+ 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);
}
+ 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);
}
- bedFields.clear();
}
}
@@ -168,16 +163,16 @@ void BedShuffle::ChooseLocus(BED &bedEntry) {
int randomStart;
int chromSize;
- if (!this->sameChrom) {
- randomChrom = chroms[rand() % this->numChroms];
- chromSize = genome->getChromSize(randomChrom);
+ 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);
+ chromSize = _genome->getChromSize(chrom);
randomStart = rand() % chromSize;
bedEntry.start = randomStart;
bedEntry.end = randomStart + length;
@@ -187,16 +182,16 @@ void BedShuffle::ChooseLocus(BED &bedEntry) {
// the length of the chromosome. if so, keep looking
// for a new spot.
while (bedEntry.end > chromSize) {
- if (!this->sameChrom) {
- randomChrom = chroms[rand() % this->numChroms];
- chromSize = genome->getChromSize(randomChrom);
+ 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);
+ chromSize = _genome->getChromSize(chrom);
randomStart = rand() % chromSize;
bedEntry.start = randomStart;
bedEntry.end = randomStart + length;
@@ -204,29 +199,3 @@ void BedShuffle::ChooseLocus(BED &bedEntry) {
}
}
-
-void BedShuffle::DetermineBedInput() {
- if (bed->bedFile != "stdin") { // process a file
- ifstream beds(bed->bedFile.c_str(), ios::in);
- if ( !beds ) {
- cerr << "Error: The requested bed file (" << bed->bedFile << ") could not be opened. Exiting!" << endl;
- exit (1);
- }
- if (this->haveExclude) {
- ShuffleWithExclusions(beds);
- }
- else {
- Shuffle(beds);
- }
- }
- else {
- // process stdin
- if (this->haveExclude) {
- ShuffleWithExclusions(cin);
- }
- else {
- Shuffle(cin);
- }
- }
-}
-
diff --git a/src/shuffleBed/shuffleBed.h b/src/shuffleBed/shuffleBed.h
index 5bfad33d..3c015f7c 100755
--- a/src/shuffleBed/shuffleBed.h
+++ b/src/shuffleBed/shuffleBed.h
@@ -37,30 +37,29 @@ public:
// destructor
~BedShuffle(void);
- void Shuffle(istream &bedInput);
- void ShuffleWithExclusions(istream &bedInput);
-
- void ChooseLocus(BED &);
-
- void DetermineBedInput();
-
private:
- string bedFile;
- string genomeFile;
- string excludeFile;
- int seed;
- bool sameChrom;
- bool haveExclude;
- bool haveSeed;
+ 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;
+ BedFile *_bed;
+ BedFile *_exclude;
- GenomeFile *genome;
+ GenomeFile *_genome;
- vector<string> chroms;
- int numChroms;
+ 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 b4ae12d8..2d51bb2d 100755
--- a/src/shuffleBed/shuffleBedMain.cpp
+++ b/src/shuffleBed/shuffleBedMain.cpp
@@ -105,9 +105,7 @@ int main(int argc, char* argv[]) {
if (!showHelp) {
BedShuffle *bc = new BedShuffle(bedFile, genomeFile, excludeFile, haveSeed, haveExclude, sameChrom, seed);
-
- bc->DetermineBedInput();
-
+ delete bc;
return 0;
}
else {
diff --git a/src/slopBed/slopBed.cpp b/src/slopBed/slopBed.cpp
index 590bf2bc..118eb758 100755
--- a/src/slopBed/slopBed.cpp
+++ b/src/slopBed/slopBed.cpp
@@ -15,15 +15,17 @@
BedSlop::BedSlop(string &bedFile, string &genomeFile, bool &forceStrand, int &leftSlop, int &rightSlop) {
- this->bedFile = bedFile;
- this->genomeFile = genomeFile;
- this->forceStrand = forceStrand;
+ _bedFile = bedFile;
+ _genomeFile = genomeFile;
+ _forceStrand = forceStrand;
- this->leftSlop = leftSlop;
- this->rightSlop = rightSlop;
+ _leftSlop = leftSlop;
+ _rightSlop = rightSlop;
- this->bed = new BedFile(bedFile);
- this->genome = new GenomeFile(genomeFile);
+ _bed = new BedFile(bedFile);
+ _genome = new GenomeFile(genomeFile);
+
+ SlopBed();
}
@@ -32,23 +34,17 @@ BedSlop::~BedSlop(void) {
}
-void BedSlop::SlopBed(istream &bedInput) {
+void BedSlop::SlopBed() {
int lineNum = 0;
- string bedLine; // used to store the current (unparsed) line from the BED file.
-
- while (getline(bedInput, bedLine)) {
-
- vector<string> bedFields;
- Tokenize(bedLine,bedFields);
- lineNum++;
-
- BED bedEntry; // used to store the current BED line from the BED file.
- if (this->bed->parseLine(bedEntry, bedFields, lineNum)) {
- AddSlop(bedEntry);
- bed->reportBedNewLine(bedEntry);
- }
+ BED bedEntry; // used to store the current BED line from the BED file.
+
+ _bed->Open();
+ while (_bed->GetNextBed(bedEntry, lineNum)) {
+ AddSlop(bedEntry);
+ _bed->reportBedNewLine(bedEntry);
}
+ _bed->Close();
}
@@ -56,40 +52,26 @@ void BedSlop::AddSlop(BED &bed) {
// special handling if the BED entry is on the negative
// strand and the user cares about strandedness.
- int chromSize = genome->getChromSize(bed.chrom);
+ int chromSize = _genome->getChromSize(bed.chrom);
- if ( (this->forceStrand) && (bed.strand == "-") ) {
+ if ( (_forceStrand) && (bed.strand == "-") ) {
// inspect the start
- if ((bed.start - rightSlop) > 0) bed.start -= rightSlop;
+ if ((bed.start - _rightSlop) > 0) bed.start -= _rightSlop;
else bed.start = 0;
// inspect the start
- if ((bed.end + leftSlop) <= chromSize) bed.end += leftSlop;
+ if ((bed.end + _leftSlop) <= chromSize) bed.end += _leftSlop;
else bed.end = chromSize;
}
else {
// inspect the start
- if ((bed.start - leftSlop) > 0) bed.start -= leftSlop;
+ if ((bed.start - _leftSlop) > 0) bed.start -= _leftSlop;
else bed.start = 0;
// inspect the end
- if ((bed.end + rightSlop) <= chromSize) bed.end += rightSlop;
+ if ((bed.end + _rightSlop) <= chromSize) bed.end += _rightSlop;
else bed.end = chromSize;
}
}
-void BedSlop::DetermineBedInput() {
-
- if (this->bedFile != "stdin") { // process a file
- ifstream beds(this->bedFile.c_str(), ios::in);
- if ( !beds ) {
- cerr << "Error: The requested bed file (" << this->bedFile << ") could not be opened. Exiting!" << endl;
- exit (1);
- }
- SlopBed(beds);
- }
- else { // process stdin
- SlopBed(cin);
- }
-}
diff --git a/src/slopBed/slopBed.h b/src/slopBed/slopBed.h
index e6dbce0e..9e4baf17 100755
--- a/src/slopBed/slopBed.h
+++ b/src/slopBed/slopBed.h
@@ -30,27 +30,29 @@ class BedSlop {
public:
// constructor
- BedSlop(string &, string &, bool &, int &, int &);
+ BedSlop(string &bedFile, string &genomeFile, bool &forceStrand, int &leftSlop, int &rightSlop) ;
// destructor
~BedSlop(void);
- void SlopBed(istream &bedInput);
-
- // method to add requested "slop" to a single BED entry
- void AddSlop(BED &bed);
-
- void DetermineBedInput();
+
private:
- string bedFile;
- string genomeFile;
+ string _bedFile;
+ string _genomeFile;
- bool forceStrand;
- int leftSlop;
- int rightSlop;
+ bool _forceStrand;
+ int _leftSlop;
+ int _rightSlop;
- BedFile *bed;
- GenomeFile *genome;
+ 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 e4f35fed..0b4af157 100755
--- a/src/slopBed/slopBedMain.cpp
+++ b/src/slopBed/slopBedMain.cpp
@@ -127,7 +127,7 @@ int main(int argc, char* argv[]) {
if (!showHelp) {
BedSlop *bc = new BedSlop(bedFile, genomeFile, forceStrand, leftSlop, rightSlop);
- bc->DetermineBedInput();
+ delete bc;
return 0;
}
diff --git a/src/sortBed/sortBed.cpp b/src/sortBed/sortBed.cpp
index f61b322d..dc79612d 100755
--- a/src/sortBed/sortBed.cpp
+++ b/src/sortBed/sortBed.cpp
@@ -16,8 +16,10 @@
// Constructor
//
BedSort::BedSort(string &bedFile) {
- this->bedFile = bedFile;
- this->bed = new BedFile(bedFile);
+ _bedFile = bedFile;
+ _bed = new BedFile(bedFile);
+
+ SortBed();
}
//
@@ -31,16 +33,16 @@ void BedSort::SortBed() {
// load the "B" bed file into a map so
// that we can easily compare "A" to it for overlaps
- bed->loadBedFileIntoMapNoBin();
+ _bed->loadBedFileIntoMapNoBin();
// loop through each chromosome and merge their BED entries
- for (masterBedMapNoBin::iterator m = bed->bedMapNoBin.begin(); m != bed->bedMapNoBin.end(); ++m) {
+ for (masterBedMapNoBin::iterator m = _bed->bedMapNoBin.begin(); m != _bed->bedMapNoBin.end(); ++m) {
// 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]);
+ _bed->reportBedNewLine(bedList[i]);
}
}
}
@@ -50,13 +52,13 @@ void BedSort::SortBedBySizeAsc() {
// load the "B" bed file into a map so
// that we can easily compare "A" to it for overlaps
- bed->loadBedFileIntoMapNoBin();
+ _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) {
+ for (masterBedMapNoBin::iterator m = _bed->bedMapNoBin.begin(); m != _bed->bedMapNoBin.end(); ++m) {
// bedList is already sorted by start position.
vector<BED> bedList = m->second;
@@ -72,7 +74,7 @@ void BedSort::SortBedBySizeAsc() {
// report the entries in ascending order
for (unsigned int i = 0; i < masterList.size(); ++i) {
- bed->reportBedNewLine(masterList[i]);
+ _bed->reportBedNewLine(masterList[i]);
}
}
@@ -81,13 +83,13 @@ void BedSort::SortBedBySizeDesc() {
// load the "B" bed file into a map so
// that we can easily compare "A" to it for overlaps
- bed->loadBedFileIntoMapNoBin();
+ _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) {
+ for (masterBedMapNoBin::iterator m = _bed->bedMapNoBin.begin(); m != _bed->bedMapNoBin.end(); ++m) {
// bedList is already sorted by start position.
vector<BED> bedList = m->second;
@@ -103,7 +105,7 @@ void BedSort::SortBedBySizeDesc() {
// report the entries in ascending order
for (unsigned int i = 0; i < masterList.size(); ++i) {
- bed->reportBedNewLine(masterList[i]);
+ _bed->reportBedNewLine(masterList[i]);
}
}
@@ -111,17 +113,17 @@ void BedSort::SortBedByChromThenSizeAsc() {
// load the "B" bed file into a map so
// that we can easily compare "A" to it for overlaps
- bed->loadBedFileIntoMapNoBin();
+ _bed->loadBedFileIntoMapNoBin();
// loop through each chromosome and merge their BED entries
- for (masterBedMapNoBin::iterator m = bed->bedMapNoBin.begin(); m != bed->bedMapNoBin.end(); ++m) {
+ 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]);
+ _bed->reportBedNewLine(bedList[i]);
}
}
}
@@ -131,10 +133,10 @@ void BedSort::SortBedByChromThenSizeDesc() {
// load the "B" bed file into a map so
// that we can easily compare "A" to it for overlaps
- bed->loadBedFileIntoMapNoBin();
+ _bed->loadBedFileIntoMapNoBin();
// loop through each chromosome and merge their BED entries
- for (masterBedMapNoBin::iterator m = bed->bedMapNoBin.begin(); m != bed->bedMapNoBin.end(); ++m) {
+ for (masterBedMapNoBin::iterator m = _bed->bedMapNoBin.begin(); m != _bed->bedMapNoBin.end(); ++m) {
// bedList is already sorted by start position.
vector<BED> bedList = m->second;
@@ -142,7 +144,7 @@ void BedSort::SortBedByChromThenSizeDesc() {
sort(bedList.begin(), bedList.end(), sortBySizeDesc);
for (unsigned int i = 0; i < bedList.size(); ++i) {
- bed->reportBedNewLine(bedList[i]);
+ _bed->reportBedNewLine(bedList[i]);
}
}
}
@@ -152,18 +154,18 @@ void BedSort::SortBedByChromThenScoreAsc() {
// load the "B" bed file into a map so
// that we can easily compare "A" to it for overlaps
- bed->loadBedFileIntoMapNoBin();
+ _bed->loadBedFileIntoMapNoBin();
- if (bed->bedType >= 5) {
+ 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) {
+ 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]);
+ _bed->reportBedNewLine(bedList[i]);
}
}
}
@@ -178,18 +180,18 @@ void BedSort::SortBedByChromThenScoreDesc() {
// load the "B" bed file into a map so
// that we can easily compare "A" to it for overlaps
- bed->loadBedFileIntoMapNoBin();
+ _bed->loadBedFileIntoMapNoBin();
- if (bed->bedType >= 5) {
+ 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) {
+ 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]);
+ _bed->reportBedNewLine(bedList[i]);
}
}
}
diff --git a/src/sortBed/sortBed.h b/src/sortBed/sortBed.h
index 48125995..4d9dd256 100755
--- a/src/sortBed/sortBed.h
+++ b/src/sortBed/sortBed.h
@@ -31,9 +31,6 @@ public:
// destructor
~BedSort(void);
- // write BED to stdout
- void reportBed(const BED &);
-
void SortBed(); // the default. sorts by chrom (asc.) then by start (asc.)
void SortBedBySizeAsc();
void SortBedBySizeDesc();
@@ -43,9 +40,11 @@ public:
void SortBedByChromThenScoreDesc();
private:
- string bedFile;
+ string _bedFile;
// instance of a bed file class.
- BedFile *bed;
+ BedFile *_bed;
+
+ // methods
};
--
GitLab