diff --git a/Makefile b/Makefile index 91cbbd5..80c5656 100644 --- a/Makefile +++ b/Makefile @@ -18,7 +18,7 @@ export SRC_DIR = src export UTIL_DIR = src/utils export CXX = g++ ifeq ($(DEBUG),1) -export CXXFLAGS = -Wall -O0 -g -fno-inline -fkeep-inline-functions -D_FILE_OFFSET_BITS=64 -fPIC -DDEBUG -D_DEBUG +export CXXFLAGS = -Wall -Wextra -DDEBUG -D_DEBUG -g -O0 -D_FILE_OFFSET_BITS=64 -fPIC $(INCLUDES) else export CXXFLAGS = -Wall -O2 -D_FILE_OFFSET_BITS=64 -fPIC $(INCLUDES) endif diff --git a/docs/content/history.rst b/docs/content/history.rst index c59e84e..ac04a02 100644 --- a/docs/content/history.rst +++ b/docs/content/history.rst @@ -4,23 +4,24 @@ Release History Version 2.26.0 (7-July-2016) ============================ -1. Fixed a major memory leak when using ``-sorted``. Thanks to Emily Tsang and Steohen Montgomery. +1. Fixed a major memory leak when using ``-sorted``. Thanks to Emily Tsang and Stephen Montgomery. 2. Fixed a bug for BED files containing a single record with no newline. Thanks to @jmarshall. -3. The ``getfasta`` tool includes name, chromosome and position in fasta headers when the ``-name`` option is used. Thanks to @rishavray. -4. Fixed a bug that now forces the ``coverage`` tool to process every record in the ``-a`` file. -5. Fixed a bug preventing proper processing of BED files with consecutive tabs. -6. VCF files containing structural variants now infer SV length from either the SVLEN or END INFO fields. Thanks to Zev Kronenberg. -7. Resolve off by one bugs when intersecting GFF or VCF files with BED files. -8. The ``shuffle`` tool now uses roulette wheel sampling to shuffle to ``-incl`` regions based upon the size of the interval. Thanks to Zev Kronenberg and Michael Imbeault. -9. Fixed a bug in ``coverage`` that prevented correct calculation of depth when using the ``-split`` option. -10. The ``shuffle`` tool warns when an interval exceeds the maximum chromosome length. -11. The ``complement`` tool better checks intervals against the chromosome lengths. -12. Fixes for ``stddev``, ``min``, and ``max`` operations. Thanks to @jmarshall. -13. Enabled ``stdev``, ``sstdev``, ``freqasc``, and ``freqdesc`` options for ``groupby``. -14. Allow ``-s`` and ``-w`` to be used in any order for ``makewindows``. -15. Added new ``-bedOut`` option to ``getfasta``. -16. The ``-r`` option forces the ``-F`` value for ``intersect``. -17. Add ``-pc`` option to the ``genomecov`` tool, allowing coverage to be calculated based upon paired-end fragments. +3. Fixed a bug in the contigency table values for thr ``fisher`` tool. +4. The ``getfasta`` tool includes name, chromosome and position in fasta headers when the ``-name`` option is used. Thanks to @rishavray. +5. Fixed a bug that now forces the ``coverage`` tool to process every record in the ``-a`` file. +6. Fixed a bug preventing proper processing of BED files with consecutive tabs. +7. VCF files containing structural variants now infer SV length from either the SVLEN or END INFO fields. Thanks to Zev Kronenberg. +8. Resolve off by one bugs when intersecting GFF or VCF files with BED files. +9. The ``shuffle`` tool now uses roulette wheel sampling to shuffle to ``-incl`` regions based upon the size of the interval. Thanks to Zev Kronenberg and Michael Imbeault. +10. Fixed a bug in ``coverage`` that prevented correct calculation of depth when using the ``-split`` option. +11. The ``shuffle`` tool warns when an interval exceeds the maximum chromosome length. +12. The ``complement`` tool better checks intervals against the chromosome lengths. +13. Fixes for ``stddev``, ``min``, and ``max`` operations. Thanks to @jmarshall. +14. Enabled ``stdev``, ``sstdev``, ``freqasc``, and ``freqdesc`` options for ``groupby``. +15. Allow ``-s`` and ``-w`` to be used in any order for ``makewindows``. +16. Added new ``-bedOut`` option to ``getfasta``. +17. The ``-r`` option forces the ``-F`` value for ``intersect``. +18. Add ``-pc`` option to the ``genomecov`` tool, allowing coverage to be calculated based upon paired-end fragments. Version 2.25.0 (3-Sept-2015) diff --git a/docs/index.rst b/docs/index.rst index 2d67581..67cdd91 100755 --- a/docs/index.rst +++ b/docs/index.rst @@ -11,6 +11,7 @@ genomic file formats such as BAM, BED, GFF/GTF, VCF. While each individual tool *intersect* two interval files), quite sophisticated analyses can be conducted by combining multiple bedtools operations on the UNIX command line. +**bedtools** is developed in the `Quinlan laboratory `_ at the `University of Utah `_ and benefits from fantastic contributions made by scientists worldwide. ========================== Tutorial diff --git a/docs/templates/sidebar-intro.html b/docs/templates/sidebar-intro.html index 262da46..dc430e7 100644 --- a/docs/templates/sidebar-intro.html +++ b/docs/templates/sidebar-intro.html @@ -8,7 +8,7 @@
  • Old Releases @ Google Code
  • Mailing list @ Google Groups
  • Queries @ Biostar
    • -
  • Quinlan lab @ UVa
    • +
  • Quinlan lab @ UU
    • diff --git a/src/annotateBed/annotateBed.cpp b/src/annotateBed/annotateBed.cpp index 23c775a..d462944 100644 --- a/src/annotateBed/annotateBed.cpp +++ b/src/annotateBed/annotateBed.cpp @@ -57,13 +57,13 @@ void BedAnnotate::PrintHeader() { // 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) + for (size_t i = 0; i < _bed->bedType -1; ++i) printf("\t"); // now print the label for each file. if (_reportBoth == false) { for (size_t i = 0; i < _annoTitles.size(); ++i) - printf("%s\t", _annoTitles[i].c_str()); + printf("\t%s", _annoTitles[i].c_str()); printf("\n"); } else { diff --git a/src/bedtools.cpp b/src/bedtools.cpp index 088ea70..b03b072 100644 --- a/src/bedtools.cpp +++ b/src/bedtools.cpp @@ -34,8 +34,8 @@ using namespace std; // define our parameter checking macro #define PARAMETER_CHECK(param, paramLen, actualLen) (strncmp(argv[i], param, min(actualLen, paramLen))== 0) && (actualLen == paramLen) -bool sub_main(const QuickString &subCmd); -void showHelp(const QuickString &subCmd); +bool sub_main(const string &subCmd); +void showHelp(const string &subCmd); int annotate_main(int argc, char* argv[]);// int bamtobed_main(int argc, char* argv[]);// @@ -92,7 +92,7 @@ int main(int argc, char *argv[]) // make sure the user at least entered a sub_command if (argc < 2) return bedtools_help(); - QuickString subCmd(argv[1]); + string subCmd(argv[1]); BedtoolsDriver btDriver; if (btDriver.supports(subCmd)) { @@ -190,8 +190,13 @@ int main(int argc, char *argv[]) int bedtools_help(void) { - cout << PROGRAM_NAME << ": flexible tools for genome arithmetic and DNA sequence analysis.\n"; - cout << "usage: bedtools [options]" << endl << endl; + cout << PROGRAM_NAME << " is a powerful toolset for genome arithmetic." << endl << endl; + cout << "Version: " << VERSION << endl; + cout << "About: developed in the quinlanlab.org and by many contributors worldwide." << endl; + cout << "Docs: http://bedtools.readthedocs.io/" << endl; + cout << "Code: https://github.com/arq5x/bedtools2" << endl; + cout << "Mail: https://groups.google.com/forum/#!forum/bedtools-discuss" << endl << endl; + cout << "Usage: bedtools [options]" << endl << endl; cout << "The bedtools sub-commands include:" << endl; @@ -287,7 +292,7 @@ int bedtools_faq(void) return 0; } -void showHelp(const QuickString &subCmd) { +void showHelp(const string &subCmd) { if (subCmd == "intersect") { intersect_help(); } else if (subCmd == "map") { diff --git a/src/complementFile/complementFile.cpp b/src/complementFile/complementFile.cpp index 803b7c5..5d3b384 100644 --- a/src/complementFile/complementFile.cpp +++ b/src/complementFile/complementFile.cpp @@ -38,7 +38,7 @@ void ComplementFile::processHits(RecordOutputMgr *outputMgr, RecordKeyVector &hi const Record *rec = hits.getKey(); //test for chrom change. - const QuickString &newChrom = rec->getChrName(); + const string &newChrom = rec->getChrName(); if (_currChrom != newChrom) { outPutLastRecordInPrevChrom(); @@ -95,7 +95,7 @@ void ComplementFile::giveFinalReport(RecordOutputMgr *outputMgr) { void ComplementFile::outPutLastRecordInPrevChrom() { - const QuickString &chrom = _outRecord.getChrName(); + const string &chrom = _outRecord.getChrName(); //do nothing if triggered by first record in DB. At this point, //there was no prev chrom, so nothing is stored in the output Record yet. @@ -106,7 +106,7 @@ void ComplementFile::outPutLastRecordInPrevChrom() printRecord(maxChromSize); } -bool ComplementFile::fastForward(const QuickString &newChrom) { +bool ComplementFile::fastForward(const string &newChrom) { if (!newChrom.empty() && !_genomeFile->hasChrom(newChrom)) return false; int i= _currPosInGenomeList +1; @@ -133,14 +133,14 @@ bool ComplementFile::fastForward(const QuickString &newChrom) { void ComplementFile::printRecord(int endPos) { _outRecord.setStartPos(_currStartPos); - QuickString startStr; - startStr.append(_currStartPos); - _outRecord.setStartPosStr(startStr); + stringstream startStr; + startStr << _currStartPos; + _outRecord.setStartPosStr(startStr.str()); _outRecord.setEndPos(endPos); - QuickString endStr; - endStr.append(endPos); - _outRecord.setEndPosStr(endStr); + stringstream endStr; + endStr << endPos; + _outRecord.setEndPosStr(endStr.str()); _outputMgr->printRecord(&_outRecord); _outputMgr->newline(); diff --git a/src/complementFile/complementFile.h b/src/complementFile/complementFile.h index 3382dbd..a90b6c2 100644 --- a/src/complementFile/complementFile.h +++ b/src/complementFile/complementFile.h @@ -34,17 +34,17 @@ public: protected: FileRecordMergeMgr *_frm; Bed3Interval _outRecord; - QuickString _currChrom; + string _currChrom; const NewGenomeFile *_genomeFile; int _currStartPos; RecordOutputMgr *_outputMgr; - const vector &_chromList; + const vector &_chromList; int _currPosInGenomeList; virtual ContextComplement *upCast(ContextBase *context) { return static_cast(context); } void outPutLastRecordInPrevChrom(); - bool fastForward(const QuickString &newChrom); + bool fastForward(const string &newChrom); void printRecord(int endPos); }; diff --git a/src/coverageFile/coverageFile.cpp b/src/coverageFile/coverageFile.cpp index 9473eeb..b01eda4 100644 --- a/src/coverageFile/coverageFile.cpp +++ b/src/coverageFile/coverageFile.cpp @@ -6,6 +6,7 @@ */ #include "coverageFile.h" +#include CoverageFile::CoverageFile(ContextCoverage *context) : IntersectFile(context), @@ -13,6 +14,7 @@ CoverageFile::CoverageFile(ContextCoverage *context) _depthArrayCapacity(0), _queryLen(0), _totalQueryLen(0), + _hitCount(0), _queryOffset(0), _floatValBuf(NULL) { @@ -34,40 +36,38 @@ CoverageFile::~CoverageFile() { } -void CoverageFile::processHits(RecordOutputMgr *outputMgr, RecordKeyVector &hits) { - makeDepthCount(hits); - _finalOutput.clear(); - - switch(upCast(_context)->getCoverageType()) { - case ContextCoverage::COUNT: - doCounts(outputMgr, hits); - break; - - case ContextCoverage::PER_BASE: - doPerBase(outputMgr, hits); - break; - - case ContextCoverage::MEAN: - doMean(outputMgr, hits); - break; - - case ContextCoverage::HIST: - doHist(outputMgr, hits); - break; - - case ContextCoverage::DEFAULT: - default: - doDefault(outputMgr, hits); - break; - - } - +void CoverageFile::processHits(RecordOutputMgr *outputMgr, RecordKeyVector &hits) +{ + makeDepthCount(hits); + _finalOutput.clear(); + + switch(upCast(_context)->getCoverageType()) { + case ContextCoverage::COUNT: + doCounts(outputMgr, hits); + break; + + case ContextCoverage::PER_BASE: + doPerBase(outputMgr, hits); + break; + + case ContextCoverage::MEAN: + doMean(outputMgr, hits); + break; + + case ContextCoverage::HIST: + doHist(outputMgr, hits); + break; + + case ContextCoverage::DEFAULT: + default: + doDefault(outputMgr, hits); + break; + } } void CoverageFile::cleanupHits(RecordKeyVector &hits) { IntersectFile::cleanupHits(hits); memset(_depthArray, 0, sizeof(size_t) * _queryLen); - } void CoverageFile::giveFinalReport(RecordOutputMgr *outputMgr) { @@ -77,19 +77,25 @@ void CoverageFile::giveFinalReport(RecordOutputMgr *outputMgr) { return; } + for (depthMapType::iterator iter = _finalDepthMap.begin(); iter != _finalDepthMap.end(); iter++) { size_t depth = iter->first; size_t basesAtDepth = iter->second; + //cout << "x\n"; float depthPct = (float)basesAtDepth / (float)_totalQueryLen; - - _finalOutput = "all\t"; - _finalOutput.append(static_cast(depth)); - _finalOutput.append("\t"); - _finalOutput.append(static_cast(basesAtDepth)); - _finalOutput.append("\t"); - _finalOutput.append(static_cast(_totalQueryLen)); - _finalOutput.append("\t"); - format(depthPct); + //cout << "y\n"; + ostringstream s; + s << "all\t"; + s << depth; + s << "\t"; + s << basesAtDepth; + s << "\t"; + s << _totalQueryLen; + s << "\t"; + char *depthPctString; + asprintf(&depthPctString, "%0.7f", depthPct); + s << depthPctString; + _finalOutput = s.str(); outputMgr->printRecord(NULL, _finalOutput); } @@ -101,24 +107,57 @@ void CoverageFile::makeDepthCount(RecordKeyVector &hits) { _queryLen = (size_t)(key->getEndPos() - _queryOffset); _totalQueryLen += _queryLen; - //resize depth array if needed + // resize depth array if needed if (_depthArrayCapacity < _queryLen) { _depthArray = (size_t*)realloc(_depthArray, sizeof(size_t) * _queryLen); _depthArrayCapacity = _queryLen; memset(_depthArray, 0, sizeof(size_t) * _depthArrayCapacity); } - - //loop through hits, which may not be in sorted order, due to - //potential multiple databases, and increment the depth array as needed. - for (RecordKeyVector::const_iterator_type iter = hits.begin(); iter != hits.end(); iter = hits.next()) { - const Record *dbRec = *iter; - int dbStart = dbRec->getStartPos(); - int dbEnd = dbRec->getEndPos(); - int maxStart = max(_queryOffset, dbStart); - int minEnd = min(dbEnd, key->getEndPos()); - - for (int i=maxStart; i < minEnd; i++) { - _depthArray[i - _queryOffset]++; + _hitCount = 0; + // no -split + if (!(_context)->getObeySplits()) + { + //loop through hits, which may not be in sorted order, due to + //potential multiple databases, and increment the depth array as needed. + for (RecordKeyVector::iterator_type iter = hits.begin(); iter != hits.end(); iter = hits.next()) + { + const Record *dbRec = *iter; + int dbStart = dbRec->getStartPos(); + int dbEnd = dbRec->getEndPos(); + int maxStart = max(_queryOffset, dbStart); + int minEnd = min(dbEnd, key->getEndPos()); + + for (int i=maxStart; i < minEnd; i++) { + _depthArray[i - _queryOffset]++; + } + _hitCount++; + } + } + // -split + else + { + for (RecordKeyVector::iterator_type iter = hits.begin(); iter != hits.end(); iter = hits.next()) { + const Record *dbRec = *iter; + bool count_hit = false; + for (size_t i = 0; i < dbRec->block_starts.size(); ++i) + { + int block_start = dbRec->block_starts[i]; + int block_end = dbRec->block_ends[i]; + int maxStart = max(_queryOffset, block_start); + int minEnd = min(block_end, key->getEndPos()); + if ((minEnd - maxStart) > 0) + { + for (int i = maxStart; i < minEnd; i++) + { + _depthArray[i - _queryOffset]++; + } + count_hit = true; + } + } + if (count_hit) + { + _hitCount++; + } } } } @@ -135,19 +174,23 @@ size_t CoverageFile::countBasesAtDepth(size_t depth) { void CoverageFile::doCounts(RecordOutputMgr *outputMgr, RecordKeyVector &hits) { - _finalOutput = static_cast(hits.size()); + ostringstream s; + s << _hitCount; + _finalOutput.append(s.str()); outputMgr->printRecord(hits.getKey(), _finalOutput); } void CoverageFile::doPerBase(RecordOutputMgr *outputMgr, RecordKeyVector &hits) { //loop through all bases in query, printing full record and metrics for each - const Record * queryRec = hits.getKey(); + + Record * queryRec = hits.getKey(); for (size_t i= 0; i < _queryLen; i++) { - _finalOutput = static_cast(i+1); - _finalOutput.append("\t"); - _finalOutput.append(static_cast(_depthArray[i])); - + ostringstream s; + s << (i+1); + s << "\t"; + s << _depthArray[i]; + _finalOutput = s.str(); outputMgr->printRecord(queryRec, _finalOutput); } } @@ -158,7 +201,12 @@ void CoverageFile::doMean(RecordOutputMgr *outputMgr, RecordKeyVector &hits) for (size_t i= 0; i < _queryLen; i++) { sum += _depthArray[i]; } - format((float)sum / (float)_queryLen); + ostringstream s; + float mean = ((float)sum / (float)_queryLen); + char *meanString; + asprintf(&meanString, "%0.7f", mean); + s << meanString; + _finalOutput.append(s.str()); outputMgr->printRecord(hits.getKey(), _finalOutput); } @@ -166,7 +214,6 @@ void CoverageFile::doMean(RecordOutputMgr *outputMgr, RecordKeyVector &hits) void CoverageFile::doHist(RecordOutputMgr *outputMgr, RecordKeyVector &hits) { //make a map of depths to num bases with that depth - _currDepthMap.clear(); for (size_t i=0; i < _queryLen; i++) { _currDepthMap[_depthArray[i]]++; @@ -176,40 +223,38 @@ void CoverageFile::doHist(RecordOutputMgr *outputMgr, RecordKeyVector &hits) for (depthMapType::iterator iter = _currDepthMap.begin(); iter != _currDepthMap.end(); iter++) { size_t depth = iter->first; size_t numBasesAtDepth = iter->second; - float coveredBases = (float)numBasesAtDepth / (float)_queryLen; - - _finalOutput = static_cast(depth); - _finalOutput.append("\t"); - _finalOutput.append(static_cast(numBasesAtDepth)); - _finalOutput.append("\t"); - _finalOutput.append(static_cast(_queryLen)); - _finalOutput.append("\t"); - format(coveredBases); - + float coveredFraction = (float)numBasesAtDepth / (float)_queryLen; + + ostringstream s; + s << depth; + s << "\t"; + s << numBasesAtDepth; + s << "\t"; + s << _queryLen; + s << "\t"; + char *coveredFractionString; + asprintf(&coveredFractionString, "%0.7f", coveredFraction); + s << coveredFractionString; + _finalOutput = s.str(); outputMgr->printRecord(hits.getKey(), _finalOutput); } - } void CoverageFile::doDefault(RecordOutputMgr *outputMgr, RecordKeyVector &hits) { size_t nonZeroBases = _queryLen - countBasesAtDepth(0); - float coveredBases = (float)nonZeroBases / (float)_queryLen; - - _finalOutput = static_cast(hits.size()); - _finalOutput.append("\t"); - _finalOutput.append(static_cast(nonZeroBases)); - _finalOutput.append("\t"); - _finalOutput.append(static_cast(_queryLen)); - _finalOutput.append("\t"); - format(coveredBases); - + float coveredFraction = (float)nonZeroBases / (float)_queryLen; + + ostringstream s; + s << _hitCount; + s << "\t"; + s << nonZeroBases; + s << "\t"; + s << _queryLen; + s << "\t"; + char *coveredFractionString; + asprintf(&coveredFractionString, "%0.7f", coveredFraction); + s << coveredFractionString; + _finalOutput = s.str(); outputMgr->printRecord(hits.getKey(), _finalOutput); } - -void CoverageFile::format(float val) -{ - memset(_floatValBuf, 0, floatValBufLen); - sprintf(_floatValBuf, "%0.7f", val); - _finalOutput.append(_floatValBuf); -} diff --git a/src/coverageFile/coverageFile.h b/src/coverageFile/coverageFile.h index fa2c662..691b74f 100644 --- a/src/coverageFile/coverageFile.h +++ b/src/coverageFile/coverageFile.h @@ -8,6 +8,7 @@ #ifndef COVERAGEFILE_H_ #define COVERAGEFILE_H_ +#include // for asprintf #include "intersectFile.h" #include "ContextCoverage.h" @@ -21,12 +22,13 @@ public: protected: - QuickString _finalOutput; + string _finalOutput; size_t *_depthArray; size_t _depthArrayCapacity; size_t _queryLen; size_t _totalQueryLen; + size_t _hitCount; int _queryOffset; static const int DEFAULT_DEPTH_CAPACITY = 1024; char *_floatValBuf; @@ -47,9 +49,6 @@ protected: void doMean(RecordOutputMgr *outputMgr, RecordKeyVector &hits); void doHist(RecordOutputMgr *outputMgr, RecordKeyVector &hits); void doDefault(RecordOutputMgr *outputMgr, RecordKeyVector &hits); - - void format(float val); - }; diff --git a/src/fisher/fisher.cpp b/src/fisher/fisher.cpp index 7548f18..583b467 100644 --- a/src/fisher/fisher.cpp +++ b/src/fisher/fisher.cpp @@ -91,7 +91,7 @@ void Fisher::giveFinalReport(RecordOutputMgr *outputMgr) unsigned long Fisher::getTotalIntersection(RecordKeyVector &recList) { unsigned long intersection = 0; - const Record *key = recList.getKey(); + Record *key = recList.getKey(); int keyStart = key->getStartPos(); int keyEnd = key->getEndPos(); @@ -99,7 +99,7 @@ unsigned long Fisher::getTotalIntersection(RecordKeyVector &recList) _qsizes.push_back((keyEnd - keyStart)); int hitIdx = 0; - for (RecordKeyVector::const_iterator_type iter = recList.begin(); iter != recList.end(); iter = recList.next()) { + for (RecordKeyVector::iterator_type iter = recList.begin(); iter != recList.end(); iter = recList.next()) { int maxStart = max((*iter)->getStartPos(), keyStart); int minEnd = min((*iter)->getEndPos(), keyEnd); _qsizes.push_back((int)(minEnd - maxStart)); diff --git a/src/groupBy/Makefile b/src/groupBy/Makefile index 9bb141a..44cd7aa 100644 --- a/src/groupBy/Makefile +++ b/src/groupBy/Makefile @@ -10,6 +10,7 @@ INCLUDES = -I$(UTILITIES_DIR)/Contexts/ \ -I$(UTILITIES_DIR)/general/ \ -I$(UTILITIES_DIR)/fileType/ \ -I$(UTILITIES_DIR)/lineFileUtilities/ \ + -I$(UTILITIES_DIR)/stringUtilities/ \ -I$(UTILITIES_DIR)/gzstream/ \ -I$(UTILITIES_DIR)/GenomeFile/ \ -I$(UTILITIES_DIR)/BamTools/include \ diff --git a/src/groupBy/groupBy.cpp b/src/groupBy/groupBy.cpp index 867f15f..1e1dbda 100644 --- a/src/groupBy/groupBy.cpp +++ b/src/groupBy/groupBy.cpp @@ -7,6 +7,8 @@ #include "groupBy.h" #include "Tokenizer.h" #include "ParseTools.h" +#include "stringUtilities.h" +#include GroupBy::GroupBy(ContextGroupBy *context) : ToolBase(context), @@ -29,8 +31,8 @@ bool GroupBy::init() for (int i=0; i < numElems; i++) { //if the item is a range, such as 3-5, //must split that as well. - const QuickString &elem = groupColsTokens.getElem(i); + const string &elem = groupColsTokens.getElem(i); if (strchr(elem.c_str(), '-')) { Tokenizer rangeElems; rangeElems.tokenize(elem, '-'); @@ -59,14 +61,19 @@ bool GroupBy::findNext(RecordKeyVector &hits) assignPrevFields(); hits.setKey(_prevRecord); hits.push_back(_prevRecord); //key should also be part of group for calculations - while (1) { - const Record *newRecord = getNextRecord(); - if (newRecord == NULL) { + while (1) + { + Record *newRecord = getNextRecord(); + if (newRecord == NULL) + { _prevRecord = NULL; break; - } else if (canGroup(newRecord)) { + } else if (canGroup(newRecord)) + { hits.push_back(newRecord); - } else { + } + else + { _prevRecord = newRecord; break; } @@ -77,15 +84,19 @@ bool GroupBy::findNext(RecordKeyVector &hits) void GroupBy::processHits(RecordOutputMgr *outputMgr, RecordKeyVector &hits) { - const Record *rec = hits.getKey(); - const QuickString &opVal = _context->getColumnOpsVal(hits); - if (upCast(_context)->printFullCols()) { + Record *rec = hits.getKey(); + const string &opVal = _context->getColumnOpsVal(hits); + if (upCast(_context)->printFullCols()) + { outputMgr->printRecord(rec, opVal); - } else { - QuickString outBuf; - for (int i=0; i < (int)_groupCols.size(); i++) { + } + else + { + string outBuf; + for (int i = 0; i < (int)_groupCols.size(); i++) + { outBuf.append(rec->getField(_groupCols[i])); - outBuf.append('\t'); + outBuf.append("\t"); } outBuf.append(opVal); outputMgr->printRecord(NULL, outBuf); @@ -95,7 +106,7 @@ void GroupBy::processHits(RecordOutputMgr *outputMgr, RecordKeyVector &hits) void GroupBy::cleanupHits(RecordKeyVector &hits) { - RecordKeyVector::const_iterator_type iter = hits.begin(); + RecordKeyVector::iterator_type iter = hits.begin(); for (; iter != hits.end(); iter = hits.next()) { _queryFRM->deleteRecord(*iter); @@ -103,12 +114,16 @@ void GroupBy::cleanupHits(RecordKeyVector &hits) hits.clearAll(); } -const Record *GroupBy::getNextRecord() { - while (!_queryFRM->eof()) { +Record *GroupBy::getNextRecord() { + while (!_queryFRM->eof()) + { Record *queryRecord = _queryFRM->getNextRecord(); - if (queryRecord == NULL) { + if (queryRecord == NULL) + { continue; - } else { + } + else + { return queryRecord; } } @@ -121,19 +136,22 @@ void GroupBy::assignPrevFields() { } } -bool GroupBy::canGroup(const Record *newRecord) { - - for (int i=0; i < (int)_groupCols.size(); i++) { +bool GroupBy::canGroup(Record *newRecord) +{ + for (int i = 0; i < (int)_groupCols.size(); i++) + { int fieldNum = _groupCols[i]; - const QuickString &newField = newRecord->getField(fieldNum); - const QuickString &oldField = _prevFields[i]; - if (upCast(_context)->ignoreCase()) { - if (oldField.stricmp(newField)) return false; - } else { + const string &newField = newRecord->getField(fieldNum); + const string &oldField = _prevFields[i]; + if (upCast(_context)->ignoreCase()) + { + if (toLower(oldField) != toLower(newField)) return false; + } + else + { if (oldField != newField) return false; } } return true; - } diff --git a/src/groupBy/groupBy.h b/src/groupBy/groupBy.h index 2c96dc9..c44ba3c 100644 --- a/src/groupBy/groupBy.h +++ b/src/groupBy/groupBy.h @@ -27,11 +27,11 @@ protected: virtual ContextGroupBy *upCast(ContextBase *context) { return static_cast(context); } vector _groupCols; - vector _prevFields; + vector _prevFields; FileRecordMgr *_queryFRM; - const Record *_prevRecord; - const Record *getNextRecord(); - bool canGroup(const Record *); + Record *_prevRecord; + Record *getNextRecord(); + bool canGroup(Record *); void assignPrevFields(); }; diff --git a/src/intersectFile/intersectFile.cpp b/src/intersectFile/intersectFile.cpp index 01bb222..45977fc 100644 --- a/src/intersectFile/intersectFile.cpp +++ b/src/intersectFile/intersectFile.cpp @@ -67,6 +67,7 @@ bool IntersectFile::findNext(RecordKeyVector &hits) void IntersectFile::processHits(RecordOutputMgr *outputMgr, RecordKeyVector &hits) { + RecordKeyVector::iterator_type hitListIter = hits.begin(); outputMgr->printRecord(hits); } @@ -120,19 +121,16 @@ void IntersectFile::makeSweep() { void IntersectFile::checkSplits(RecordKeyVector &hitSet) { if (upCast(_context)->getObeySplits()) { - RecordKeyVector keySet(hitSet.getKey()); - RecordKeyVector resultSet(hitSet.getKey()); - RecordKeyVector overlapSet(hitSet.getKey()); - upCast(_context)->getSplitBlockInfo()->findBlockedOverlaps(keySet, hitSet, resultSet, overlapSet); - + // when using coverage, we need a list of the sub-intervals of coverage // so that per-base depth can be properly calculated when obeying splits if (_context->getProgram() == ContextBase::COVERAGE) { - hitSet.swap(overlapSet); + upCast(_context)->getSplitBlockInfo()->findBlockedOverlaps(hitSet, true); } - else { - hitSet.swap(resultSet); + else + { + upCast(_context)->getSplitBlockInfo()->findBlockedOverlaps(hitSet, false); } } } diff --git a/src/intersectFile/intersectFile.h b/src/intersectFile/intersectFile.h index f40e750..3c85f93 100644 --- a/src/intersectFile/intersectFile.h +++ b/src/intersectFile/intersectFile.h @@ -26,11 +26,11 @@ public: IntersectFile(ContextIntersect *context); virtual ~IntersectFile(); virtual bool init(); - virtual bool findNext(RecordKeyVector &hits); - virtual void processHits(RecordOutputMgr *outputMgr, RecordKeyVector &hits); - virtual void cleanupHits(RecordKeyVector &hits); + virtual bool findNext(RecordKeyVector &); + virtual void processHits(RecordOutputMgr *, RecordKeyVector &); + virtual void cleanupHits(RecordKeyVector &); virtual bool finalizeCalculations(); - virtual void giveFinalReport(RecordOutputMgr *outputMgr) {} + virtual void giveFinalReport(RecordOutputMgr *) {} protected: diff --git a/src/jaccard/jaccard.cpp b/src/jaccard/jaccard.cpp index c99c117..2f61b86 100644 --- a/src/jaccard/jaccard.cpp +++ b/src/jaccard/jaccard.cpp @@ -57,13 +57,13 @@ void Jaccard::giveFinalReport(RecordOutputMgr *outputMgr) { unsigned long Jaccard::getTotalIntersection(RecordKeyVector &hits) { unsigned long intersection = 0; - const Record *key = hits.getKey(); + Record *key = hits.getKey(); int keyStart = key->getStartPos(); int keyEnd = key->getEndPos(); int hitIdx = 0; - for (RecordKeyVector::const_iterator_type iter = hits.begin(); iter != hits.end(); iter = hits.next()) { - const Record *currRec = *iter; + for (RecordKeyVector::iterator_type iter = hits.begin(); iter != hits.end(); iter = hits.next()) { + Record *currRec = *iter; int maxStart = max(currRec->getStartPos(), keyStart); int minEnd = min(currRec->getEndPos(), keyEnd); if (_context->getObeySplits()) { diff --git a/src/jaccard/jaccard.h b/src/jaccard/jaccard.h index e23ad9c..8c4f6db 100644 --- a/src/jaccard/jaccard.h +++ b/src/jaccard/jaccard.h @@ -15,11 +15,11 @@ class Jaccard : public IntersectFile { public: Jaccard(ContextJaccard *context); - virtual bool findNext(RecordKeyVector &hits); - virtual void processHits(RecordOutputMgr *outputMgr, RecordKeyVector &hits) {} - virtual void cleanupHits(RecordKeyVector &hits); + virtual bool findNext(RecordKeyVector &); + virtual void processHits(RecordOutputMgr *, RecordKeyVector &) {} + virtual void cleanupHits(RecordKeyVector &); virtual bool finalizeCalculations(); - virtual void giveFinalReport(RecordOutputMgr *outputMgr); + virtual void giveFinalReport(RecordOutputMgr *); protected: diff --git a/src/nekSandbox1/nekSandboxMain.cpp b/src/nekSandbox1/nekSandboxMain.cpp index d228540..d9b298a 100644 --- a/src/nekSandbox1/nekSandboxMain.cpp +++ b/src/nekSandbox1/nekSandboxMain.cpp @@ -67,7 +67,7 @@ int nek_sandbox1_main(int argc,char** argv) // printf("%s", sLine); // } // return 0; -// QuickString filename(argv[1]); +// string filename(argv[1]); // istream *inputStream = NULL; // if (filename == "-") { // inputStream = &cin; @@ -91,7 +91,7 @@ int nek_sandbox1_main(int argc,char** argv) //// exit(1); //// } //// } -// QuickString _bamHeader = _bamReader.GetHeaderText(); +// string _bamHeader = _bamReader.GetHeaderText(); // BamTools::RefVector _references = _bamReader.GetReferenceData(); // // if (_bamHeader.empty() || _references.empty()) { @@ -107,10 +107,10 @@ int nek_sandbox1_main(int argc,char** argv) // exit(1); // } // string sLine; -// vector fields; -// QuickString chrName; +// vector fields; +// string chrName; // -// vector chroms; +// vector chroms; // chroms.push_back("1"); // chroms.push_back("2"); // chroms.push_back("10"); @@ -127,7 +127,7 @@ int nek_sandbox1_main(int argc,char** argv) // continue; // } // Tokenize(sLine.c_str(), fields); -// const QuickString &currChrom = fields[2]; +// const string &currChrom = fields[2]; // if (currChrom == chroms[chromIdx]) { // cout << sLine << endl; // chromCounts[chromIdx]++; @@ -157,7 +157,7 @@ int nek_sandbox1_main(int argc,char** argv) // cout << "RecordType is : " << frm.getRecordType() << ", " << frm.getRecordTypeName() << "." << endl; // // bool headerFound = false; -// QuickString outbuf; +// string outbuf; // while (!frm.eof()) { // Record *record = frm.getNextRecord(); // if (!headerFound && frm.hasHeader()) { diff --git a/src/regressTest/regressTestMain.cpp b/src/regressTest/regressTestMain.cpp index 0377ca6..01a2816 100644 --- a/src/regressTest/regressTestMain.cpp +++ b/src/regressTest/regressTestMain.cpp @@ -3,7 +3,7 @@ #include #include #include -#include "QuickString.h" +#include "string.h" void usage() { printf("Usage: bedtools regressTest sub-prog targetVersion configFile [optionsToTest]\n"); @@ -31,7 +31,7 @@ int regress_test_main(int argc, char **argv) { usage(); exit(1); } - QuickString program(argv[2]); + string program(argv[2]); RegressTest *regressTest = new RegressTest(); diff --git a/src/shiftBed/shiftBed.cpp b/src/shiftBed/shiftBed.cpp index 81022f8..50724ce 100644 --- a/src/shiftBed/shiftBed.cpp +++ b/src/shiftBed/shiftBed.cpp @@ -51,7 +51,7 @@ void BedShift::AddShift(BED &bed) { CHRPOS chromSize = (CHRPOS)_genome->getChromSize(bed.chrom); - float shift; + double shift; if (bed.strand == "-") { shift = _shiftMinus; @@ -59,7 +59,7 @@ void BedShift::AddShift(BED &bed) { shift = _shiftPlus; } if (_fractional == true) - shift = shift * (float)bed.size(); + shift = shift * (double)bed.size(); if ((bed.start + shift) < 0) bed.start = 0; diff --git a/src/shuffleBed/shuffleBed.cpp b/src/shuffleBed/shuffleBed.cpp index 9b71125..2478ccc 100644 --- a/src/shuffleBed/shuffleBed.cpp +++ b/src/shuffleBed/shuffleBed.cpp @@ -73,14 +73,15 @@ BedShuffle::BedShuffle(string &bedFile, string &genomeFile, _haveExclude = true; } - if (_haveInclude) { + if (_haveInclude) + { _include = new BedFile(includeFile); - _include->loadBedFileIntoVector(); - - for(std::vector::iterator it = _include->bedList.begin(); - it != _include->bedList.end(); it++){ - _cumLen += (*it).end - (*it).start; - } + _include->loadBedFileIntoVector(); + _include->assignWeightsBasedOnSize(); + // for(std::vector::iterator it = _include->bedList.begin(); it != _include->bedList.end(); it++) + // { + // _cumLen += (*it).end - (*it).start; + // } } if (_haveExclude == true && _haveInclude == false) @@ -451,37 +452,16 @@ void BedShuffle::ChoosePairedLocus(BEDPE &b) { } -void BedShuffle::ChooseLocusFromInclusionFile(BED &bedEntry) { - - string chrom = bedEntry.chrom; - CHRPOS length = bedEntry.end - bedEntry.start; - - string randomChrom; - CHRPOS randomStart; - BED includeInterval; - - // choose an -incl interval randomly. +void BedShuffle::ChooseLocusFromInclusionFile(BED &bedEntry) +{ + // choose an -incl interval randomly, yet weighted by the size of the incl interval. + size_t length = (bedEntry.end - bedEntry.start); + double runif =((double)rand()/(double)RAND_MAX); + BED *includeInterval = _include->sizeWeightedSearch(runif); - bool nohit = true; - while(nohit){ - - includeInterval = _include->bedList[rand() % _include->bedList.size()]; - - double prop = double(includeInterval.end - - includeInterval.start) / _cumLen; - double runif =((double)rand()/(double)RAND_MAX); - - if(runif < prop){ - nohit = false; - } - if(_sameChrom == true && (includeInterval.chrom != chrom)){ - nohit = true; - } - - } - - bedEntry.chrom = includeInterval.chrom; - randomStart = includeInterval.start + rand() % (includeInterval.size()); + // choose a random start within the -incl interval and reconstruct shuffled record + CHRPOS randomStart = includeInterval->start + (rand() % (includeInterval->size())); + bedEntry.chrom = includeInterval->chrom; bedEntry.start = randomStart; bedEntry.end = randomStart + length; } diff --git a/src/spacingFile/spacingFile.cpp b/src/spacingFile/spacingFile.cpp index 87f7528..ca613ba 100644 --- a/src/spacingFile/spacingFile.cpp +++ b/src/spacingFile/spacingFile.cpp @@ -49,9 +49,14 @@ bool SpacingFile::findNext(RecordKeyVector &hits) { // do _currRec and _prevRec overlap? if (_currRec->sameChromIntersects(_prevRec, false, false, 1E-9, 1E-9, false, false)) - _distance.append(0); + _distance.append("0"); else - _distance.append(_currRec->getStartPos() - _prevRec->getEndPos()); + { + int distance = _currRec->getStartPos() - _prevRec->getEndPos(); + ostringstream s; + s << distance; + _distance.append(s.str()); + } } // we have changed chromosomes else if (_currRec->getChrName() != _prevRec->getChrName()) diff --git a/src/spacingFile/spacingFile.h b/src/spacingFile/spacingFile.h index e1556c8..d7321b9 100644 --- a/src/spacingFile/spacingFile.h +++ b/src/spacingFile/spacingFile.h @@ -22,13 +22,13 @@ public: virtual void processHits(RecordOutputMgr *outputMgr, RecordKeyVector &hits); virtual void cleanupHits(RecordKeyVector &hits); virtual bool finalizeCalculations() { return true; } - virtual void giveFinalReport(RecordOutputMgr *outputMgr) {} + virtual void giveFinalReport(RecordOutputMgr *) {} protected: - const Record *_prevRec; - const Record *_currRec; - QuickString _distance; + Record *_prevRec; + Record *_currRec; + string _distance; FileRecordMgr *_inputFile; virtual ContextSpacing *upCast(ContextBase *context) { return static_cast(context); } diff --git a/src/subtractFile/subtractFile.cpp b/src/subtractFile/subtractFile.cpp index f763239..cd77cf7 100644 --- a/src/subtractFile/subtractFile.cpp +++ b/src/subtractFile/subtractFile.cpp @@ -59,7 +59,7 @@ void SubtractFile::subtractHits(RecordKeyVector &hits) { } //loop through hits. Track which bases in query were covered - const Record *keyRec = hits.getKey(); + Record *keyRec = hits.getKey(); int keyStart = keyRec->getStartPos(); int keyEnd = keyRec->getEndPos(); @@ -71,8 +71,8 @@ void SubtractFile::subtractHits(RecordKeyVector &hits) { //now loop through the hits, and cover corresponding query bases //by setting them to false. bool basesRemoved = false; - for (RecordKeyVector::const_iterator_type iter = hits.begin(); iter != hits.end(); iter = hits.next()) { - const Record *hitRec = *iter; + for (RecordKeyVector::iterator_type iter = hits.begin(); iter != hits.end(); iter = hits.next()) { + Record *hitRec = *iter; int hitStart = hitRec->getStartPos(); int hitEnd = hitRec->getEndPos(); diff --git a/src/utils/BinTree/BinTree.cpp b/src/utils/BinTree/BinTree.cpp index 18181e3..6f34d1d 100644 --- a/src/utils/BinTree/BinTree.cpp +++ b/src/utils/BinTree/BinTree.cpp @@ -49,7 +49,7 @@ void BinTree::getHits(Record *record, RecordKeyVector &hitSet) if (record->isUnmapped()) { return; } - const QuickString &chr = record->getChrName(); + const string &chr = record->getChrName(); mainMapType::iterator mainIter = _mainMap.find(chr); if (mainIter == _mainMap.end()) { //given chrom not even in map. @@ -63,31 +63,31 @@ void BinTree::getHits(Record *record, RecordKeyVector &hitSet) binNumType endBin = ((endPos-1) >> _binFirstShift); - const allBinsType &bins = mainIter->second; + allBinsType &bins = mainIter->second; /* SYNOPSIS: 1. We loop through each UCSC BIN level for feature A's chrom. 2. For each BIN, we loop through each B feature and add it to hits if it meets all of the user's requests, which include: - (a) overlap fractio, (b) strandedness, (c) reciprocal overlap + (a) overlap fraction, (b) strandedness, (c) reciprocal overlap */ for (binNumType i = 0; i < NUM_BIN_LEVELS; i++) { binNumType offset = _binOffsetsExtended[i]; for (binNumType j = (startBin+offset); j <= (endBin+offset); j++) { // move to the next bin if this one is empty - allBinsType::const_iterator allBinsIter = bins.find(j); + allBinsType::iterator allBinsIter = bins.find(j); if (allBinsIter == bins.end()) { continue; } - const binType &bin = allBinsIter->second; + binType &bin = allBinsIter->second; - for (binType::const_iterator iter = bin.begin(); iter != bin.end(); iter++) { - const Record *dbRec = *iter; + for (binType::iterator iter = bin.begin(); iter != bin.end(); iter++) { + Record *dbRec = *iter; if (record->intersects(dbRec, _context->getSameStrand(), _context->getDiffStrand(), - _context->getOverlapFractionA(), + _context->getOverlapFractionA(), _context->getOverlapFractionB(), _context->getReciprocalFraction(), _context->getEitherFraction() @@ -106,10 +106,10 @@ void BinTree::getHits(Record *record, RecordKeyVector &hitSet) } } -bool BinTree::addRecordToTree(const Record *record) +bool BinTree::addRecordToTree(Record *record) { // Get chr, bin. - const QuickString &chr = record->getChrName(); + const string &chr = record->getChrName(); binNumType startPos = (binNumType)(record->getStartPos()); binNumType endPos = (binNumType)(record->getEndPos()); binNumType binNum = getBin(startPos, endPos); diff --git a/src/utils/BinTree/BinTree.h b/src/utils/BinTree/BinTree.h index a688b92..e4c575f 100644 --- a/src/utils/BinTree/BinTree.h +++ b/src/utils/BinTree/BinTree.h @@ -13,7 +13,7 @@ #include #include -#include "QuickString.h" +#include "string.h" #include "RecordKeyList.h" #include "ContextIntersect.h" @@ -56,18 +56,18 @@ private: // typedef const RecordListNode * innerListIterType; // typedef innerListType * binType; // typedef binType * allBinsType; -// typedef QuickString mainKeyType; +// typedef string mainKeyType; // typedef map mainMapType; // mainMapType _mainMap; - typedef vector binType; + typedef vector binType; typedef map allBinsType; //for each bin number, have a RecordList - typedef map mainMapType; //for each chrom, a map of bin num to RecordLists. + typedef map mainMapType; //for each chrom, a map of bin num to RecordLists. mainMapType _mainMap; map _binsHit; - bool addRecordToTree(const Record *); + bool addRecordToTree(Record *); binNumType getBin(binNumType start, binNumType end) const; binNumType getBin(const Record *record) const; diff --git a/src/utils/Contexts/ContextBase.cpp b/src/utils/Contexts/ContextBase.cpp index 21ea11f..3856851 100644 --- a/src/utils/Contexts/ContextBase.cpp +++ b/src/utils/Contexts/ContextBase.cpp @@ -13,6 +13,7 @@ ContextBase::ContextBase() : _program(UNSPECIFIED_PROGRAM), + _files(NULL), _allFilesOpened(false), _genomeFile(NULL), _outputFileType(FileRecordTypeChecker::UNKNOWN_FILE_TYPE), @@ -45,7 +46,7 @@ ContextBase::ContextBase() _reportDBfileNames(false), _printHeader(false), _printable(true), - _explicitBedOutput(false), + _explicitBedOutput(false), _queryFileIdx(-1), _bamHeaderAndRefIdx(-1), _maxNumDatabaseFields(0), @@ -95,7 +96,6 @@ ContextBase::~ContextBase() { delete _genomeFile; _genomeFile = NULL; - delete _splitBlockInfo; _splitBlockInfo = NULL; @@ -103,7 +103,6 @@ ContextBase::~ContextBase() cerr << _nameConventionWarningMsg << endl; } - //close all files and delete FRM objects. for (int i=0; i < (int)_files.size(); i++) { _files[i]->close(); @@ -149,7 +148,7 @@ bool ContextBase::determineOutputType() { } -void ContextBase::openGenomeFile(const QuickString &genomeFilename) +void ContextBase::openGenomeFile(const string &genomeFilename) { _genomeFile = new NewGenomeFile(genomeFilename.c_str()); } @@ -619,14 +618,14 @@ void ContextBase::setColumnOpsMethods(bool val) _hasColumnOpsMethods = val; } -const QuickString &ContextBase::getColumnOpsVal(RecordKeyVector &keyList) const { +const string &ContextBase::getColumnOpsVal(RecordKeyVector &keyList) const { if (!hasColumnOpsMethods()) { return _nullStr; } return _keyListOps->getOpVals(keyList); } -FileRecordMgr *ContextBase::getNewFRM(const QuickString &filename, int fileIdx) { +FileRecordMgr *ContextBase::getNewFRM(const string &filename, int fileIdx) { if (_useMergedIntervals) { FileRecordMergeMgr *frm = new FileRecordMergeMgr(filename); @@ -641,7 +640,7 @@ FileRecordMgr *ContextBase::getNewFRM(const QuickString &filename, int fileIdx) } } -bool ContextBase::parseIoBufSize(QuickString bufStr) +bool ContextBase::parseIoBufSize(string bufStr) { char lastChar = bufStr[bufStr.size()-1]; int multiplier = 1; @@ -741,20 +740,20 @@ ContextBase::testType ContextBase::fileHasLeadingZeroInChromNames(int fileIdx) { -void ContextBase::warn(const Record *record, const QuickString str1, const QuickString str2, const QuickString str3) { - QuickString msg; +void ContextBase::warn(const Record *record, const string str1, const string str2, const string str3) { + string msg; setErrorMsg(msg, true, record, str1, str2, str3); cerr << msg << endl; } -void ContextBase::die(const Record *record, const QuickString str1, const QuickString str2, const QuickString str3) { - QuickString msg; +void ContextBase::die(const Record *record, const string str1, const string str2, const string str3) { + string msg; setErrorMsg(msg, false, record, str1, str2, str3); cerr << msg << endl; exit(1); } -void ContextBase::setErrorMsg(QuickString &msg, bool onlyWarn, const Record * record, QuickString str1, const QuickString str2, const QuickString str3) { +void ContextBase::setErrorMsg(string &msg, bool onlyWarn, const Record * record, string str1, const string str2, const string str3) { if (onlyWarn) { msg = "\n***** WARNING: "; } else { @@ -769,7 +768,7 @@ void ContextBase::setErrorMsg(QuickString &msg, bool onlyWarn, const Record * re } } -void ContextBase::nameConventionWarning(const Record *record, const QuickString &filename, const QuickString &message) +void ContextBase::nameConventionWarning(const Record *record, const string &filename, const string &message) { _nameConventionWarningMsg = "***** WARNING: File "; _nameConventionWarningMsg.append(filename); diff --git a/src/utils/Contexts/ContextBase.h b/src/utils/Contexts/ContextBase.h index 0cea2e9..6bac10f 100644 --- a/src/utils/Contexts/ContextBase.h +++ b/src/utils/Contexts/ContextBase.h @@ -44,16 +44,16 @@ public: FileRecordMgr *getFile(int fileIdx) { return _files[fileIdx]; } void setProgram(PROGRAM_TYPE program) { _program = program; } - void addInputFile(const QuickString &inputFile) { _fileNames.push_back(inputFile); } + void addInputFile(const string &inputFile) { _fileNames.push_back(inputFile); } int getNumInputFiles() const { return _fileNames.size(); } - const QuickString &getInputFileName(int fileNum) const { return _fileNames[fileNum]; } + const string &getInputFileName(int fileNum) const { return _fileNames[fileNum]; } ContextFileType getInputFileType(int fileNum) const { return _files[fileNum]->getFileType(); } ContextRecordType getInputRecordType(int fileNum) const { return _files[fileNum]->getRecordType(); } virtual bool determineOutputType(); - const QuickString &getHeader(int fileIdx) { return _files[fileIdx]->getHeader(); } + const string &getHeader(int fileIdx) { return _files[fileIdx]->getHeader(); } const BamTools::RefVector &getBamReferences(int fileIdx) { return _files[fileIdx]->getBamReferences(); } int getBamHeaderAndRefIdx(); //return idx of 1st query that is BAM. If none, first DB that is BAM. @@ -61,7 +61,7 @@ public: void setUseMergedIntervals(bool val) { _useMergedIntervals = val; } FileRecordMergeMgr::WANTED_STRAND_TYPE getDesiredStrand() const { return _desiredStrand; } - void openGenomeFile(const QuickString &genomeFilename); + void openGenomeFile(const string &genomeFilename); void openGenomeFile(const BamTools::RefVector &refVector); bool hasGenomeFile() const { return _genomeFile != NULL; } NewGenomeFile *getGenomeFile() const { return _genomeFile; } @@ -78,8 +78,8 @@ public: bool getShowHelp() const { return _showHelp; } void setShowHelp(bool val) { _showHelp = val; } - const QuickString &getErrorMsg() const { return _errorMsg; } - void setErrorMessage(const QuickString &errorMsg) { _errorMsg = errorMsg; } + const string &getErrorMsg() const { return _errorMsg; } + void setErrorMessage(const string &errorMsg) { _errorMsg = errorMsg; } //split handling. bool getObeySplits() const {return _obeySplits; } @@ -144,7 +144,7 @@ public: // are available. void setColumnOpsMethods(bool val); virtual bool hasColumnOpsMethods() const { return _hasColumnOpsMethods; } - const QuickString &getColumnOpsVal(RecordKeyVector &keyList) const; + const string &getColumnOpsVal(RecordKeyVector &keyList) const; //methods applicable only to column operations. int getReportPrecision() const { return _reportPrecision; } @@ -155,21 +155,21 @@ public: protected: PROGRAM_TYPE _program; - vector _fileNames; + vector _fileNames; vector _files; bool _allFilesOpened; - map _programNames; - QuickString _origProgramName; + map _programNames; + string _origProgramName; NewGenomeFile *_genomeFile; ContextFileType _outputFileType; bool _outputTypeDetermined; - map _headers; + map _headers; map _references; - QuickString _errorMsg; + string _errorMsg; vector _argsProcessed; //used for processing cmdLine args. int _skipFirstArgs; bool _showHelp; @@ -204,7 +204,7 @@ protected: bool _runToQueryEnd; int _queryFileIdx; vector _dbFileIdxs; - vector _dbNameTags; + vector _dbNameTags; map _fileIdsToDbIdxs; int _bamHeaderAndRefIdx; int _maxNumDatabaseFields; @@ -221,7 +221,7 @@ protected: //Members for column operations bool _hasColumnOpsMethods; KeyListOps *_keyListOps; - QuickString _nullStr; //placeholder return value when col ops aren't valid. + string _nullStr; //placeholder return value when col ops aren't valid. //Members for merged records FileRecordMergeMgr::WANTED_STRAND_TYPE _desiredStrand; @@ -236,7 +236,7 @@ protected: virtual bool parseCmdArgs(int argc, char **argv, int skipFirstArgs); bool cmdArgsValid(); virtual bool openFiles(); - virtual FileRecordMgr *getNewFRM(const QuickString &filename, int fileIdx); + virtual FileRecordMgr *getNewFRM(const string &filename, int fileIdx); //set cmd line params and counter, i, as members so code //is more readable (as opposed to passing all 3 everywhere). @@ -285,7 +285,7 @@ protected: virtual bool handle_sortout(); virtual bool handle_nonamecheck(); bool handle_prec(); - bool parseIoBufSize(QuickString bufStr); + bool parseIoBufSize(string bufStr); testType fileHasChrInChromNames(int fileIdx); testType fileHasLeadingZeroInChromNames(int fileIdx); @@ -293,16 +293,16 @@ protected: void setNoEnforceCoordSort(bool val) { _noEnforceCoordSort = val; } //Warning messages. bool _nameConventionWarningTripped; - QuickString _nameConventionWarningMsg; - void nameConventionWarning(const Record *record, const QuickString &filename, const QuickString &message); + string _nameConventionWarningMsg; + void nameConventionWarning(const Record *record, const string &filename, const string &message); //give warning but continue. - void warn(const Record *, const QuickString str1, const QuickString str2 = "", const QuickString str3 = ""); + void warn(const Record *, const string str1, const string str2 = "", const string str3 = ""); // Give error and exit. - void die(const Record *, const QuickString str1, const QuickString str2 = "", const QuickString str3 = ""); + void die(const Record *, const string str1, const string str2 = "", const string str3 = ""); //private error handler - void setErrorMsg(QuickString &msg, bool onlyWarn, const Record * record, QuickString str1, const QuickString str2, const QuickString str3); + void setErrorMsg(string &msg, bool onlyWarn, const Record * record, string str1, const string str2, const string str3); bool strandedToolSupported(); diff --git a/src/utils/Contexts/ContextClosest.cpp b/src/utils/Contexts/ContextClosest.cpp index 2e774b3..4b8e60e 100644 --- a/src/utils/Contexts/ContextClosest.cpp +++ b/src/utils/Contexts/ContextClosest.cpp @@ -139,7 +139,7 @@ bool ContextClosest::handle_D() { _reportDistance = true; _signDistance = true; _haveStrandedDistMode = true; - QuickString modeStr(_argv[_i + 1]); + string modeStr(_argv[_i + 1]); if (modeStr == "ref") { _strandedDistMode = REF_DIST; } else if (modeStr == "a") { @@ -203,7 +203,7 @@ bool ContextClosest::handle_t() bool tieError = false; if ((_i+1) < _argc) { _haveTieMode = true; - QuickString tieStr(_argv[_i+1]); + string tieStr(_argv[_i+1]); if (tieStr == "all") { _tieMode = ALL_TIES; } else if (tieStr == "first") { @@ -230,7 +230,7 @@ bool ContextClosest::handle_mdb() { bool mdbError = false; if ((_i+1) < _argc) { - QuickString mdbStr(_argv[_i+1]); + string mdbStr(_argv[_i+1]); if (mdbStr == "each") { _multiDbMode = EACH_DB; } else if (mdbStr == "all") { diff --git a/src/utils/Contexts/ContextGroupBy.cpp b/src/utils/Contexts/ContextGroupBy.cpp index 990e696..ebee7bb 100644 --- a/src/utils/Contexts/ContextGroupBy.cpp +++ b/src/utils/Contexts/ContextGroupBy.cpp @@ -122,16 +122,18 @@ bool ContextGroupBy::handle_ignorecase() { return true; } -const QuickString &ContextGroupBy::getDefaultHeader() { +const string &ContextGroupBy::getDefaultHeader() { //groupBy does not support multiple databases. FileRecordMgr *frm = _files[0]; int numFields = frm->getNumFields(); _defaultHeader.clear(); + ostringstream s; for (int i=1; i <= numFields; i++) { - _defaultHeader.append("col_"); - _defaultHeader.append(i); - _defaultHeader.append('\t'); + s << "col_"; + s << i; + s << "\t"; } + _defaultHeader.append(s.str()); //change last tab into newline _defaultHeader[_defaultHeader.size()-1] = '\n'; return _defaultHeader; diff --git a/src/utils/Contexts/ContextGroupBy.h b/src/utils/Contexts/ContextGroupBy.h index 0e6b2d9..c189850 100644 --- a/src/utils/Contexts/ContextGroupBy.h +++ b/src/utils/Contexts/ContextGroupBy.h @@ -18,13 +18,13 @@ public: virtual bool isValidState(); bool printFullCols() const { return _printFullCols; } - const QuickString &getGroupCols() const { return _groupStr; } + const string &getGroupCols() const { return _groupStr; } bool ignoreCase() const { return _ignoreCase; } - const QuickString &getDefaultHeader(); + const string &getDefaultHeader(); protected: - QuickString _groupStr; - QuickString _defaultHeader; + string _groupStr; + string _defaultHeader; bool _printFullCols; bool _ignoreCase; diff --git a/src/utils/Contexts/ContextIntersect.h b/src/utils/Contexts/ContextIntersect.h index ef2c3e0..0bf575d 100644 --- a/src/utils/Contexts/ContextIntersect.h +++ b/src/utils/Contexts/ContextIntersect.h @@ -27,8 +27,8 @@ public: void setQueryFileIdx(int idx) { _queryFileIdx = idx; } int getNumDatabaseFiles() { return (int)_dbFileIdxs.size(); } const vector &getDbFileIdxs() const { return _dbFileIdxs; } - const QuickString &getQueryFileName() const { return _files[_queryFileIdx]->getFileName(); } - const QuickString &getDatabaseFileName(int idx) const { return _files[_dbFileIdxs[idx]]->getFileName(); } + const string &getQueryFileName() const { return _files[_queryFileIdx]->getFileName(); } + const string &getDatabaseFileName(int idx) const { return _files[_dbFileIdxs[idx]]->getFileName(); } ContextFileType getQueryFileType() const { return _files[_queryFileIdx]->getFileType(); } ContextFileType getDatabaseFileType(int idx) const { return _files[_dbFileIdxs[idx]]->getFileType(); } ContextRecordType getQueryRecordType() const { return _files[_queryFileIdx]->getRecordType(); } @@ -36,8 +36,8 @@ public: int getMaxNumDatabaseFields() const { return _maxNumDatabaseFields; } void setMaxNumDatabaseFields(int val) { _maxNumDatabaseFields = val; } int getDbIdx(int fileId) { return _fileIdsToDbIdxs.find(fileId)->second; } - void addDatabaseNameTag(const QuickString &tag) { _dbNameTags.push_back(tag); } - const QuickString &getDatabaseNameTag(int dbIdx) const { return _dbNameTags[dbIdx]; } + void addDatabaseNameTag(const string &tag) { _dbNameTags.push_back(tag); } + const string &getDatabaseNameTag(int dbIdx) const { return _dbNameTags[dbIdx]; } bool getAnyHit() const {return _anyHit; } void setAnyHit(bool val) { _anyHit = val; } diff --git a/src/utils/Contexts/Makefile b/src/utils/Contexts/Makefile index 0f499ee..40aeec8 100644 --- a/src/utils/Contexts/Makefile +++ b/src/utils/Contexts/Makefile @@ -26,7 +26,7 @@ SOURCES= ContextBase.cpp ContextBase.h ContextIntersect.cpp ContextIntersect.h C ContextGroupBy.cpp ContextGroupBy.cpp OBJECTS= ContextBase.o ContextIntersect.o ContextFisher.o ContextMap.o ContextSample.o ContextSpacing.o ContextMerge.o ContextJaccard.o ContextClosest.o \ ContextSubtract.o ContextCoverage.o ContextComplement.o ContextGroupBy.o -_EXT_OBJECTS=ParseTools.o QuickString.o +_EXT_OBJECTS=ParseTools.o string.o EXT_OBJECTS=$(patsubst %,$(OBJ_DIR)/%,$(_EXT_OBJECTS)) BUILT_OBJECTS= $(patsubst %,$(OBJ_DIR)/%,$(OBJECTS)) diff --git a/src/utils/FileRecordTools/FileReaders/BamFileReader.cpp b/src/utils/FileRecordTools/FileReaders/BamFileReader.cpp index f2344f0..1a2979f 100644 --- a/src/utils/FileRecordTools/FileReaders/BamFileReader.cpp +++ b/src/utils/FileRecordTools/FileReaders/BamFileReader.cpp @@ -47,7 +47,7 @@ bool BamFileReader::readEntry() return false; } -void BamFileReader::getChrName(QuickString &str) const +void BamFileReader::getChrName(string &str) const { int refId = _bamAlignment.RefID; if (refId < 0) { @@ -71,7 +71,7 @@ int BamFileReader::getEndPos() const return _bamAlignment.GetEndPosition(false, false); } -void BamFileReader::getName(QuickString &str) const +void BamFileReader::getName(string &str) const { if (!_useTags) { str = _bamAlignment.SupportData.AllCharData.c_str(); @@ -86,7 +86,7 @@ void BamFileReader::getName(QuickString &str) const } } -void BamFileReader::getScore(QuickString &str) const +void BamFileReader::getScore(string &str) const { int2str(_bamAlignment.MapQuality, str); } @@ -99,7 +99,7 @@ char BamFileReader::getStrand() const return '+'; } -void BamFileReader::getMateChrName(QuickString &str) const +void BamFileReader::getMateChrName(string &str) const { int refId = _bamAlignment.MateRefID; if (refId < 0) { diff --git a/src/utils/FileRecordTools/FileReaders/BamFileReader.h b/src/utils/FileRecordTools/FileReaders/BamFileReader.h index c158a08..203bef0 100644 --- a/src/utils/FileRecordTools/FileReaders/BamFileReader.h +++ b/src/utils/FileRecordTools/FileReaders/BamFileReader.h @@ -9,7 +9,7 @@ #define BAMFILEREADER_H_ #include "FileReader.h" -#include "QuickString.h" +#include "string.h" #include "api/BamReader.h" #include "api/BamAux.h" @@ -33,20 +33,20 @@ public: virtual bool readEntry(); virtual bool hasHeader() const { return _bamReader->IsOpen(); } //any open Bam file automatically has a header - virtual const QuickString &getHeader() const { return _bamHeader; } + virtual const string &getHeader() const { return _bamHeader; } const BamTools::RefVector &getReferences() const { return _references; } const BamTools::BamAlignment &getAlignment() const { return _bamAlignment; } - void getChrName(QuickString &) const; + void getChrName(string &) const; int getBamChrId() const; int getStartPos() const; int getEndPos() const; - void getName(QuickString &) const; - void getScore(QuickString &) const; + void getName(string &) const; + void getScore(string &) const; char getStrand() const; - void getMateChrName(QuickString &str) const; + void getMateChrName(string &str) const; virtual int getNumFields() const { return MINIMUM_VALID_BAM_FIELDS; } protected: @@ -54,7 +54,7 @@ protected: BamTools::BamReader *_bamReader; BamTools::BamAlignment _bamAlignment; bool _eof; - QuickString _bamHeader; + string _bamHeader; BamTools::RefVector _references; bool _useTags; diff --git a/src/utils/FileRecordTools/FileReaders/BufferedStreamMgr.cpp b/src/utils/FileRecordTools/FileReaders/BufferedStreamMgr.cpp index 6a338ce..5dc3176 100644 --- a/src/utils/FileRecordTools/FileReaders/BufferedStreamMgr.cpp +++ b/src/utils/FileRecordTools/FileReaders/BufferedStreamMgr.cpp @@ -10,7 +10,7 @@ #include "InputStreamMgr.h" #include -BufferedStreamMgr::BufferedStreamMgr(const QuickString &filename) +BufferedStreamMgr::BufferedStreamMgr(const string &filename) : _inputStreamMgr(NULL), _mainBuf(NULL), _filename(filename), @@ -92,7 +92,7 @@ bool BufferedStreamMgr::getTypeData() return true; } -bool BufferedStreamMgr::getLine(QuickString &line) +bool BufferedStreamMgr::getLine(string &line) { line.clear(); diff --git a/src/utils/FileRecordTools/FileReaders/BufferedStreamMgr.h b/src/utils/FileRecordTools/FileReaders/BufferedStreamMgr.h index eb9f6bd..2d4382c 100644 --- a/src/utils/FileRecordTools/FileReaders/BufferedStreamMgr.h +++ b/src/utils/FileRecordTools/FileReaders/BufferedStreamMgr.h @@ -9,13 +9,13 @@ #define BUFFEREDSTREAMMGR_H_ #include -#include "QuickString.h" +#include "string.h" #include "FileRecordTypeChecker.h" #include "InputStreamMgr.h" class BufferedStreamMgr { public: - BufferedStreamMgr(const QuickString &filename); + BufferedStreamMgr(const string &filename); ~BufferedStreamMgr(); bool init(); @@ -23,7 +23,7 @@ public: FileRecordTypeChecker & getTypeChecker() { return _typeChecker; } bool eof() const { return _eof; } - bool getLine(QuickString &line); + bool getLine(string &line); BamTools::BamReader *getBamReader() { return _inputStreamMgr->getBamReader(); } static const int DEFAULT_MAIN_BUF_READ_SIZE = 1023; void setIoBufSize(int val) { _useBufSize = val; } @@ -33,14 +33,14 @@ private: bufType *_mainBuf; FileRecordTypeChecker _typeChecker; - QuickString _filename; + string _filename; int _mainBufCurrStartPos; int _mainBufCurrLen; bool _eof; int _useBufSize; bool _streamFinished; - QuickString _currScanBuffer; + string _currScanBuffer; //The minus ones in these constants are for leaving room for a null terminator after reading into buffers. static const int GZIP_LINE_BUF_SIZE = 8191; // 8K diff --git a/src/utils/FileRecordTools/FileReaders/FileReader.h b/src/utils/FileRecordTools/FileReaders/FileReader.h index 48b861a..d05f97b 100644 --- a/src/utils/FileRecordTools/FileReaders/FileReader.h +++ b/src/utils/FileRecordTools/FileReaders/FileReader.h @@ -4,7 +4,7 @@ #include #include #include -#include "QuickString.h" +#include "string.h" //#include "ContextBase.h" #include "BufferedStreamMgr.h" @@ -31,7 +31,7 @@ public: virtual bool readEntry() =0; // this is an abstract base class. virtual int getCurrChromdId() const { return _currChromId; } virtual bool hasHeader() const = 0; - virtual const QuickString &getHeader() const =0; + virtual const string &getHeader() const =0; virtual int getNumFields() const = 0; protected: int _fileIdx; diff --git a/src/utils/FileRecordTools/FileReaders/InputStreamMgr.cpp b/src/utils/FileRecordTools/FileReaders/InputStreamMgr.cpp index b147b1d..e9836da 100644 --- a/src/utils/FileRecordTools/FileReaders/InputStreamMgr.cpp +++ b/src/utils/FileRecordTools/FileReaders/InputStreamMgr.cpp @@ -12,7 +12,7 @@ const char *InputStreamMgr::FIFO_STRING_LITERAL = "/dev/fd"; -InputStreamMgr::InputStreamMgr(const QuickString &filename, bool buildScanBuffer) +InputStreamMgr::InputStreamMgr(const string &filename, bool buildScanBuffer) : _filename(filename), _pushBackStreamBuf(NULL), @@ -110,8 +110,8 @@ int InputStreamMgr::read(char *data, size_t dataSize) //This part is tricky. They want less data than we saved. Give them what they //requested, then delete from the front of the saveDataStr by using it's substr method. memcpy(data, _saveDataStr.c_str(), dataSize); - QuickString newDataStr; - _saveDataStr.substr(newDataStr, dataSize, _saveDataStr.size() - dataSize); + string newDataStr; + newDataStr = _saveDataStr.substr(dataSize, _saveDataStr.size() - dataSize); _saveDataStr = newDataStr; return dataSize; } @@ -162,12 +162,10 @@ bool InputStreamMgr::populateScanBuffer() } } _numBytesInBuffer = _scanBuffer.size(); - //append it to the savedDataStr. - _scanBuffer.toStr(_saveDataStr, true); + _scanBuffer.toStr(_saveDataStr, true); if (_numBytesInBuffer == 0) return false; return true; - } bool InputStreamMgr::detectBamOrBgzip(int &numChars, int currChar) diff --git a/src/utils/FileRecordTools/FileReaders/InputStreamMgr.h b/src/utils/FileRecordTools/FileReaders/InputStreamMgr.h index 13942d3..be406b4 100644 --- a/src/utils/FileRecordTools/FileReaders/InputStreamMgr.h +++ b/src/utils/FileRecordTools/FileReaders/InputStreamMgr.h @@ -10,7 +10,7 @@ #include "PushBackStreamBuf.h" #include "InflateStreamBuf.h" -#include "QuickString.h" +#include "string.h" #include "api/BamReader.h" #include "api/internal/io/BgzfStream_p.h" @@ -21,7 +21,7 @@ using namespace std; class InputStreamMgr { public: //Contsructor: 1st arg can be "-" for stdin. set 2nd arg false if fileType already known. - InputStreamMgr(const QuickString &filename, bool buildScanBuffer = true); + InputStreamMgr(const string &filename, bool buildScanBuffer = true); ~InputStreamMgr(); bool init(); int read(char *data, size_t dataSize); @@ -31,24 +31,24 @@ public: const BTlist &getScanBuffer() const { return _scanBuffer; } int getBufferLength() const { return _numBytesInBuffer; } bool populateScanBuffer(); - const QuickString &getSavedData() const { return _saveDataStr; } + const string &getSavedData() const { return _saveDataStr; } bool isGzipped() const { return _isGzipped; } bool isBGzipped() const { return _isBgzipped; } bool isBam() const { return _isBam; } bool isCompressed() const { return _isGzipped || _isBgzipped || _isBam; } PushBackStreamBuf *getPushBackStreamBuf() const {return _pushBackStreamBuf; } -// void getSavedData(QuickString &str) const { str = _saveDataStr; } +// void getSavedData(string &str) const { str = _saveDataStr; } BamTools::BamReader *getBamReader() { return _bamReader; } bool resetStream(); bool getEofHit() { return _eofHit; } private: - QuickString _filename; + string _filename; PushBackStreamBuf *_pushBackStreamBuf; ifstream *_inputFileStream; BTlist _scanBuffer; - QuickString _saveDataStr; + string _saveDataStr; InflateStreamBuf *_infStreamBuf; istream * _finalInputStream; istream *_oldInputStream; diff --git a/src/utils/FileRecordTools/FileReaders/Makefile b/src/utils/FileRecordTools/FileReaders/Makefile index 2fcacb2..4bb5908 100644 --- a/src/utils/FileRecordTools/FileReaders/Makefile +++ b/src/utils/FileRecordTools/FileReaders/Makefile @@ -7,12 +7,12 @@ UTILITIES_DIR = ../../../utils/ INCLUDES = -I$(UTILITIES_DIR)/BamTools/include/ \ -I$(UTILITIES_DIR)/BamTools/src/ \ -I$(UTILITIES_DIR)/fileType/ \ - -I$(UTILITIES_DIR)/Contexts/ \ + -I$(UTILITIES_DIR)/Contexts/ \ -I$(UTILITIES_DIR)/GenomeFile/ \ -I$(UTILITIES_DIR)/general/ \ -I$(UTILITIES_DIR)/gzstream/ \ - -I$(UTILITIES_DIR)/version/ \ - -I$(UTILITIES_DIR)/lineFileUtilities/ \ + -I$(UTILITIES_DIR)/version/ \ + -I$(UTILITIES_DIR)/lineFileUtilities/ \ # ---------------------------------- @@ -22,7 +22,7 @@ SOURCES= FileReader.h FileReader.cpp \ SingleLineDelimTextFileReader.h SingleLineDelimTextFileReader.cpp BamFileReader.h BamFileReader.cpp \ BufferedStreamMgr.h BufferedStreamMgr.cpp InputStreamMgr.h InputStreamMgr.cpp OBJECTS= FileReader.o SingleLineDelimTextFileReader.o BamFileReader.o BufferedStreamMgr.o InputStreamMgr.o -_EXT_OBJECTS=ParseTools.o QuickString.o CompressionTools.o +_EXT_OBJECTS=string.o CompressionTools.o EXT_OBJECTS=$(patsubst %,$(OBJ_DIR)/%,$(_EXT_OBJECTS)) BUILT_OBJECTS= $(patsubst %,$(OBJ_DIR)/%,$(OBJECTS)) diff --git a/src/utils/FileRecordTools/FileReaders/Makefile~ b/src/utils/FileRecordTools/FileReaders/Makefile~ index 556c7f5..0a9b111 100644 --- a/src/utils/FileRecordTools/FileReaders/Makefile~ +++ b/src/utils/FileRecordTools/FileReaders/Makefile~ @@ -21,7 +21,7 @@ SOURCES= FileReader.h FileReader.cpp SingleLineDelimTransferBuffer.h SingleLineD SingleLineDelimTextFileReader.h SingleLineDelimTextFileReader.cpp BamFileReader.h BamFileReader.cpp \ BufferedStreamMgr.h BufferedStreamMgr.cpp InputStreamMgr.h InputStreamMgr.cpp OBJECTS= FileReader.o SingleLineDelimTransferBuffer.o SingleLineDelimTextFileReader.o BamFileReader.o BufferedStreamMgr.o InputStreamMgr.o -_EXT_OBJECTS=ParseTools.o QuickString.o CompressionTools.o +_EXT_OBJECTS=ParseTools.o string.o CompressionTools.o EXT_OBJECTS=$(patsubst %,$(OBJ_DIR)/%,$(_EXT_OBJECTS)) BUILT_OBJECTS= $(patsubst %,$(OBJ_DIR)/%,$(OBJECTS)) diff --git a/src/utils/FileRecordTools/FileReaders/SingleLineDelimTextFileReader.cpp b/src/utils/FileRecordTools/FileReaders/SingleLineDelimTextFileReader.cpp index 09fd483..8b158c0 100644 --- a/src/utils/FileRecordTools/FileReaders/SingleLineDelimTextFileReader.cpp +++ b/src/utils/FileRecordTools/FileReaders/SingleLineDelimTextFileReader.cpp @@ -1,5 +1,6 @@ #include "SingleLineDelimTextFileReader.h" #include +#include #include "BufferedStreamMgr.h" #include "ParseTools.h" @@ -76,23 +77,24 @@ bool SingleLineDelimTextFileReader::readEntry() } -void SingleLineDelimTextFileReader::getField(int fieldNum, QuickString &str) const { +void SingleLineDelimTextFileReader::getField(int fieldNum, string &str) const { int startPos = _delimPositions[fieldNum] +1; int endPos = _delimPositions[fieldNum+1]; str.assign(_sLine.c_str() + startPos, endPos - startPos); } -void SingleLineDelimTextFileReader::getField(int fieldNum, int &val) { - getField(fieldNum, _tempChrPosStr); - val = str2chrPos(_tempChrPosStr.c_str()); +void SingleLineDelimTextFileReader::getField(int fieldNum, int &val) const { + string temp; + getField(fieldNum, temp); + val = str2chrPos(temp.c_str()); } void SingleLineDelimTextFileReader::getField(int fieldNum, char &val) const { val = _sLine[_delimPositions[fieldNum] +1]; } -void SingleLineDelimTextFileReader::appendField(int fieldNum, QuickString &str) const { +void SingleLineDelimTextFileReader::appendField(int fieldNum, string &str) const { int startPos = _delimPositions[fieldNum] +1; int endPos = _delimPositions[fieldNum+1]; str.append(_sLine.c_str() + startPos, endPos - startPos); @@ -101,9 +103,9 @@ void SingleLineDelimTextFileReader::appendField(int fieldNum, QuickString &str) bool SingleLineDelimTextFileReader::detectAndHandleHeader() { //not sure why the linker is giving me a hard time about - //passing a non-const QuickString to isHeaderLine, but + //passing a non-const string to isHeaderLine, but //this const ref is a workaround. - const QuickString &sLine2 = _sLine; + const string &sLine2 = _sLine; if (!isHeaderLine(sLine2) && (!(_inheader && _lineNum==1))) { return false; } @@ -148,10 +150,10 @@ bool SingleLineDelimTextFileReader::findDelimiters() { int SingleLineDelimTextFileReader::getVcfSVlen() { // tokenize the INFO field - QuickString info_str; + string info_str; vector infofields; getField(VCF_TAG_FIELD, info_str); - Tokenize(info_str.str(), infofields, ';'); + Tokenize(info_str, infofields, ';'); // FOO=BAR;BIZ=BAM;SVLEN=100;END=200 for (vector::iterator f = infofields.begin(); f != infofields.end(); ++f) { @@ -177,7 +179,7 @@ int SingleLineDelimTextFileReader::getVcfSVlen() { } } else if (keytoval.at(0) == "END") { - QuickString start_str; + string start_str; getField(1, start_str); // length is END - POS + 1 return str2chrPos(keytoval.at(1)) - str2chrPos(start_str) + 1; diff --git a/src/utils/FileRecordTools/FileReaders/SingleLineDelimTextFileReader.h b/src/utils/FileRecordTools/FileReaders/SingleLineDelimTextFileReader.h index 6b55772..d404664 100644 --- a/src/utils/FileRecordTools/FileReaders/SingleLineDelimTextFileReader.h +++ b/src/utils/FileRecordTools/FileReaders/SingleLineDelimTextFileReader.h @@ -10,7 +10,7 @@ #include #include "FileReader.h" -#include "QuickString.h" +#include "string.h" #include "lineFileUtilities.h" class SingleLineDelimTextFileReader : public FileReader { @@ -24,24 +24,24 @@ public: virtual bool readEntry(); virtual int getNumFields() const { return _numFields; } - virtual void getField(int numField, QuickString &val) const; - virtual void getField(int numField, int &val); //this signaiture isn't const because it operates on an internal QuickString for speed. + virtual void getField(int numField, string &val) const; + virtual void getField(int numField, int &val) const; //this signaiture isn't const because it operates on an internal string for speed. virtual void getField(int fieldNum, char &val) const; - virtual void appendField(int fieldNum, QuickString &str) const; - virtual const QuickString &getHeader() const { return _header; } + virtual void appendField(int fieldNum, string &str) const; + virtual const string &getHeader() const { return _header; } virtual bool hasHeader() const { return _fullHeaderFound; } virtual void setInHeader(bool val) { _inheader = val; } protected: int _numFields; char _delimChar; - QuickString _header; + string _header; bool _fullHeaderFound; int _currDataPos; - QuickString _sLine; + string _sLine; int *_delimPositions; - QuickString _currChromStr; - QuickString _tempChrPosStr; + string _currChromStr; + string _tempChrPosStr; int _lineNum; bool _inheader; bool detectAndHandleHeader(); diff --git a/src/utils/FileRecordTools/FileRecordMergeMgr.cpp b/src/utils/FileRecordTools/FileRecordMergeMgr.cpp index 40e42b3..9654009 100644 --- a/src/utils/FileRecordTools/FileRecordMergeMgr.cpp +++ b/src/utils/FileRecordTools/FileRecordMergeMgr.cpp @@ -8,7 +8,7 @@ #include "FileRecordMergeMgr.h" -FileRecordMergeMgr::FileRecordMergeMgr(const QuickString & filename) +FileRecordMergeMgr::FileRecordMergeMgr(const string & filename) : FileRecordMgr(filename), _desiredStrand(ANY_STRAND), _maxDistance(0) @@ -64,7 +64,7 @@ Record *FileRecordMergeMgr::getNextRecord(RecordKeyVector *recList) _mustBeReverse = _desiredStrand == SAME_STRAND_REVERSE || (_desiredStrand == SAME_STRAND_EITHER && (startRecord->getStrandVal() == Record::REVERSE)); bool mustKeepOpposite = (_desiredStrand == SAME_STRAND_EITHER); - const QuickString &currChrom = startRecord->getChrName(); + const string &currChrom = startRecord->getChrName(); _foundChroms.insert(currChrom); bool madeComposite = false; @@ -97,7 +97,7 @@ Record *FileRecordMergeMgr::getNextRecord(RecordKeyVector *recList) bool mustDelete = (mustMatchStrand && nextRecord->getStrandVal() == Record::UNKNOWN); //check that we are still on the same chromosome. - const QuickString &newChrom = nextRecord->getChrName(); + const string &newChrom = nextRecord->getChrName(); if (newChrom != currChrom) { //hit a different chromosome. //haven't seen this chromosome before, sort order is already enforced in the base class method. if (!mustDelete) { @@ -205,7 +205,7 @@ bool FileRecordMergeMgr::eof(){ void FileRecordMergeMgr::deleteAllMergedItemsButKey(RecordKeyVector &recList) { //if the key is also in the list, this method won't delete it. - for (RecordKeyVector::const_iterator_type iter = recList.begin(); iter != recList.end(); iter = recList.next()) { + for (RecordKeyVector::iterator_type iter = recList.begin(); iter != recList.end(); iter = recList.next()) { if (*iter == recList.getKey()) { continue; } diff --git a/src/utils/FileRecordTools/FileRecordMergeMgr.h b/src/utils/FileRecordTools/FileRecordMergeMgr.h index ce6cfcf..cd64b7d 100644 --- a/src/utils/FileRecordTools/FileRecordMergeMgr.h +++ b/src/utils/FileRecordTools/FileRecordMergeMgr.h @@ -14,7 +14,7 @@ class FileRecordMergeMgr : public FileRecordMgr { public: - FileRecordMergeMgr(const QuickString & filename); + FileRecordMergeMgr(const string & filename); ////////////////////////////////////////////////////////////////////////////////// // diff --git a/src/utils/FileRecordTools/FileRecordMgr.cpp b/src/utils/FileRecordTools/FileRecordMgr.cpp index 59dd433..e8bfbd9 100644 --- a/src/utils/FileRecordTools/FileRecordMgr.cpp +++ b/src/utils/FileRecordTools/FileRecordMgr.cpp @@ -4,7 +4,7 @@ #include "Record.h" #include "NewGenomeFile.h" -FileRecordMgr::FileRecordMgr(const QuickString &filename) +FileRecordMgr::FileRecordMgr(const string &filename) : _fileIdx(-1), _filename(filename), _bufStreamMgr(NULL), @@ -31,16 +31,10 @@ FileRecordMgr::FileRecordMgr(const QuickString &filename) { } -FileRecordMgr::~FileRecordMgr(){ - - delete _bufStreamMgr; - _bufStreamMgr = NULL; - - close(); //just make sure file was closed. - delete _fileReader; - _fileReader = NULL; - - delete _recordMgr; +FileRecordMgr::~FileRecordMgr() +{ + close(); + //delete _recordMgr; _recordMgr = NULL; } @@ -137,11 +131,12 @@ Record *FileRecordMgr::getNextRecord(RecordKeyVector *keyList) if (keyList != NULL) { keyList->setKey(record); } + record->setFileRecordManager(this); return record; } void FileRecordMgr::assignChromId(Record *record) { - const QuickString &currChrom = record->getChrName(); + const string &currChrom = record->getChrName(); if (currChrom != _prevChrom && _hasGenomeFile) { _prevChromId = _genomeFile->getChromId(currChrom); record->setChromId(_prevChromId); @@ -160,7 +155,7 @@ void FileRecordMgr::testInputSortOrder(Record *record) } - const QuickString &currChrom = record->getChrName(); + const string &currChrom = record->getChrName(); int currStart = record->getStartPos(); if (record->isZeroLength()) { currStart++; diff --git a/src/utils/FileRecordTools/FileRecordMgr.h b/src/utils/FileRecordTools/FileRecordMgr.h index 872f0d1..0a38722 100644 --- a/src/utils/FileRecordTools/FileRecordMgr.h +++ b/src/utils/FileRecordTools/FileRecordMgr.h @@ -9,7 +9,7 @@ #define FILERECORDMGR_H_ #include -#include "QuickString.h" +#include "string.h" #include //#include "DualQueue.h" @@ -32,7 +32,7 @@ class NewGenomeFile; class FileRecordMgr { public: - FileRecordMgr(const QuickString & filename); + FileRecordMgr(const string & filename); virtual ~FileRecordMgr(); bool open(bool inheader=false); void close(); @@ -51,9 +51,9 @@ public: - const QuickString &getFileName() const { return _filename;} + const string &getFileName() const { return _filename;} bool hasHeader() const { return _fileReader->hasHeader(); } - const QuickString &getHeader() const { return _fileReader->getHeader(); } + const string &getHeader() const { return _fileReader->getHeader(); } bool recordsHaveName() const { return _bufStreamMgr->getTypeChecker().recordTypeHasName(_recordType); @@ -111,7 +111,7 @@ public: protected: int _fileIdx; - QuickString _filename; + string _filename; BufferedStreamMgr *_bufStreamMgr; FileReader *_fileReader; @@ -123,8 +123,8 @@ protected: bool _useFullBamTags; //members for enforcing sorted order. - set _foundChroms; - QuickString _prevChrom; + set _foundChroms; + string _prevChrom; int _prevStart; int _prevChromId; diff --git a/src/utils/FileRecordTools/Makefile b/src/utils/FileRecordTools/Makefile index d152c38..1b88d1e 100644 --- a/src/utils/FileRecordTools/Makefile +++ b/src/utils/FileRecordTools/Makefile @@ -5,14 +5,14 @@ UTILITIES_DIR = ../../utils/ # define our includes # ------------------- INCLUDES = -I$(UTILITIES_DIR)/fileType/ \ - -I$(UTILITIES_DIR)/FileRecordTools/FileReaders/ \ - -I$(UTILITIES_DIR)/FileRecordTools/Records/ \ - -I$(UTILITIES_DIR)/GenomeFile/ \ - -I$(UTILITIES_DIR)/general/ \ - -I$(UTILITIES_DIR)/lineFileUtilities/ \ - -I$(UTILITIES_DIR)/BamTools/include \ - -I$(UTILITIES_DIR)/BamTools/src/ \ - -I$(UTILITIES_DIR)/version/ + -I$(UTILITIES_DIR)/FileRecordTools/FileReaders/ \ + -I$(UTILITIES_DIR)/FileRecordTools/Records/ \ + -I$(UTILITIES_DIR)/GenomeFile/ \ + -I$(UTILITIES_DIR)/general/ \ + -I$(UTILITIES_DIR)/lineFileUtilities/ \ + -I$(UTILITIES_DIR)/BamTools/include \ + -I$(UTILITIES_DIR)/BamTools/src/ \ + -I$(UTILITIES_DIR)/version/ SUBDIRS = ./FileReaders \ @@ -25,7 +25,7 @@ SUBDIRS = ./FileReaders \ SOURCES= FileRecordMgr.cpp FileRecordMgr.h FileRecordMergeMgr.cpp FileRecordMergeMgr.h OBJECTS= FileRecordMgr.o FileRecordMergeMgr.o _EXT_OBJECTS=SingleLineDelimTextFileReader.o BamFileReader.o Bed3Interval.o Bed6Interval.o BedPlusInterval.o Bed12Interval.o BamRecord.o \ - SingleLineDelimTransferBuffer.o FileRecordTypeChecker.o QuickString.o ParseTools.o RecordKeyList.o BufferedStreamMgr.o + SingleLineDelimTransferBuffer.o FileRecordTypeChecker.o string.o ParseTools.o RecordKeyList.o BufferedStreamMgr.o EXT_OBJECTS=$(patsubst %,$(OBJ_DIR)/%,$(_EXT_OBJECTS)) BUILT_OBJECTS= $(patsubst %,$(OBJ_DIR)/%,$(OBJECTS)) diff --git a/src/utils/FileRecordTools/Records/BamRecord.cpp b/src/utils/FileRecordTools/Records/BamRecord.cpp index deb032b..643cd44 100644 --- a/src/utils/FileRecordTools/Records/BamRecord.cpp +++ b/src/utils/FileRecordTools/Records/BamRecord.cpp @@ -1,3 +1,4 @@ + /* * BamRecord.cpp * @@ -117,78 +118,82 @@ void BamRecord::clear() } -void BamRecord::print(QuickString &outBuf, RecordKeyVector *keyList) const +void BamRecord::print(string &outBuf, RecordKeyVector *keyList) const { - Bed6Interval::print(outBuf); + Bed6Interval::print(outBuf); printRemainingBamFields(outBuf, keyList); } -void BamRecord::print(QuickString &outBuf, int start, int end, RecordKeyVector *keyList) const +void BamRecord::print(string &outBuf, int start, int end, RecordKeyVector *keyList) const { - Bed6Interval::print(outBuf, start, end); + Bed6Interval::print(outBuf, start, end); printRemainingBamFields(outBuf, keyList); } -void BamRecord::print(QuickString &outBuf, const QuickString & start, const QuickString & end, RecordKeyVector *keyList) const +void BamRecord::print(string &outBuf, const string & start, const string & end, RecordKeyVector *keyList) const { - Bed6Interval::print(outBuf, start, end); + Bed6Interval::print(outBuf, start, end); printRemainingBamFields(outBuf, keyList); } -void BamRecord::printNull(QuickString &outBuf) const +void BamRecord::printNull(string &outBuf) const { Bed6Interval::printNull(outBuf); outBuf.append("\t.\t.\t.\t.\t.\t.", 12); } -void BamRecord::printRemainingBamFields(QuickString &outBuf, RecordKeyVector *keyList) const +void BamRecord::printRemainingBamFields(string &outBuf, RecordKeyVector *keyList) const { - outBuf.append('\t'); - outBuf.append(_startPosStr); - outBuf.append('\t'); - outBuf.append(_endPos); - outBuf.append("\t0,0,0", 6); - outBuf.append('\t'); - - int numBlocks = (int)keyList->size(); - - if (numBlocks > 0) { - outBuf.append(numBlocks); - - vector blockLengths; - vector blockStarts; - for (RecordKeyVector::const_iterator_type iter = keyList->begin(); iter != keyList->end(); iter = keyList->next()) { - const Record *block = *iter; - blockLengths.push_back(block->getEndPos() - block->getStartPos()); - blockStarts.push_back(block->getStartPos() - _startPos); - } - - outBuf.append('\t'); - for (int i=0; i < (int)blockLengths.size(); i++) { - outBuf.append(blockLengths[i]); - outBuf.append(','); - } - outBuf.append('\t'); - for (int i=0; i < (int)blockStarts.size(); i++) { - outBuf.append( blockStarts[i]); - outBuf.append(','); - } - } - else { - outBuf.append("1\t0,\t0,"); - } + ostringstream s; + s << "\t"; + s << _startPosStr; + s << "\t"; + s << _endPos; + s << "\t0,0,0"; + s << "\t"; + + int numBlocks = (int)keyList->size(); + + if (numBlocks > 0) { + s << numBlocks; + + vector blockLengths; + vector blockStarts; + for (RecordKeyVector::iterator_type iter = keyList->begin(); iter != keyList->end(); iter = keyList->next()) { + const Record *block = *iter; + blockLengths.push_back(block->getEndPos() - block->getStartPos()); + blockStarts.push_back(block->getStartPos() - _startPos); + } + + s << "\t"; + for (int i=0; i < (int)blockLengths.size(); i++) { + s << blockLengths[i]; + s << ','; + } + s << "\t"; + for (int i=0; i < (int)blockStarts.size(); i++) { + s << blockStarts[i]; + s << ','; + } + } + else { + s << "1\t0,\t0,"; + } + outBuf.append(s.str()); } -void BamRecord::printUnmapped(QuickString &outBuf) const { - outBuf.append(_chrName.empty() ? "." : _chrName); - outBuf.append("\t-1\t-1\t"); - outBuf.append(_name.empty() ? "." : _name); - outBuf.append('\t'); - outBuf.append(_score.empty() ? "." : _score); - outBuf.append("\t.\t-1\t-1\t-1\t0,0,0\t0\t.\t."); // dot for strand, -1 for blockStarts and blockEnd +void BamRecord::printUnmapped(string &outBuf) const { + ostringstream s; + s << (_chrName.empty() ? "." : _chrName); + s << "\t-1\t-1\t"; + s << (_name.empty() ? "." : _name); + s << "\t"; + s << (_score.empty() ? "." : _score); + s << "\t.\t-1\t-1\t-1\t0,0,0\t0\t.\t."; // dot for strand, -1 for blockStarts and blockEnd + outBuf.append(s.str()); } -const QuickString &BamRecord::getField(int fieldNum) const +const string &BamRecord::getField(int fieldNum) const { // Unlike other records, Bam records should return the fields specified in // in the BAM spec. In order, they are: @@ -265,10 +270,13 @@ void BamRecord::buildCigarStr() { _cigarStr.clear(); _cigarStr.reserve(2 * cigarVecLen); + std::ostringstream tmp; for (size_t i=0; i < cigarVecLen; i++) { - _cigarStr.append(cigarData[i].Type); - _cigarStr.append(cigarData[i].Length); + tmp << cigarData[i].Type; + tmp << cigarData[i].Length; } + _cigarStr = tmp.str(); + } diff --git a/src/utils/FileRecordTools/Records/BamRecord.h b/src/utils/FileRecordTools/Records/BamRecord.h index eb80a2c..a9c1aab 100644 --- a/src/utils/FileRecordTools/Records/BamRecord.h +++ b/src/utils/FileRecordTools/Records/BamRecord.h @@ -10,7 +10,7 @@ #include "Bed6Interval.h" #include "ParseTools.h" -#include "QuickString.h" +#include "string.h" #include "api/BamAlignment.h" class FileReader; @@ -42,21 +42,21 @@ public: using Bed6Interval::print; - virtual void print(QuickString &outBuf, int start, int end, RecordKeyVector *keyList) const; - virtual void print(QuickString &outBuf, RecordKeyVector *keyList) const; - virtual void print(QuickString &outBuf, const QuickString & start, const QuickString & end, RecordKeyVector *keyList) const; - virtual void printNull(QuickString &outBuf) const; - virtual void printRemainingBamFields(QuickString &outBuf, RecordKeyVector *keyList) const; - virtual void printUnmapped(QuickString &outBuf) const; + virtual void print(string &outBuf, int start, int end, RecordKeyVector *keyList) const; + virtual void print(string &outBuf, RecordKeyVector *keyList) const; + virtual void print(string &outBuf, const string & start, const string & end, RecordKeyVector *keyList) const; + virtual void printNull(string &outBuf) const; + virtual void printRemainingBamFields(string &outBuf, RecordKeyVector *keyList) const; + virtual void printUnmapped(string &outBuf) const; virtual FileRecordTypeChecker::RECORD_TYPE getType() const { return FileRecordTypeChecker::BAM_RECORD_TYPE; } - const QuickString &getCigarStr() const { return _cigarStr; } + const string &getCigarStr() const { return _cigarStr; } const vector &getCigarData() const { return _bamAlignment.CigarData; } const BamTools::BamAlignment &getAlignment() const { return _bamAlignment; } int getBamChromId() const { return _bamChromId; } - virtual const QuickString &getField(int fieldNum) const; + virtual const string &getField(int fieldNum) const; virtual int getNumFields() const { return 12; } static bool isNumericField(int fieldNum); @@ -67,12 +67,12 @@ protected: int _bamChromId; //different from chromId, because BAM file may be in different order //than the genomeFile. - QuickString _cigarStr; //stored for fast retrieval in column ops - QuickString _mateChrName; - QuickString _matePos; - QuickString _insertSize; - QuickString _queryBases; - QuickString _qualities; + string _cigarStr; //stored for fast retrieval in column ops + string _mateChrName; + string _matePos; + string _insertSize; + string _queryBases; + string _qualities; virtual ~BamRecord(); void printRemainingBamFields(); diff --git a/src/utils/FileRecordTools/Records/Bed12Interval.cpp b/src/utils/FileRecordTools/Records/Bed12Interval.cpp index 4f91aca..e41c64b 100644 --- a/src/utils/FileRecordTools/Records/Bed12Interval.cpp +++ b/src/utils/FileRecordTools/Records/Bed12Interval.cpp @@ -58,68 +58,68 @@ void Bed12Interval::clear() { } -void Bed12Interval::print(QuickString &outBuf) const +void Bed12Interval::print(string &outBuf) const { Bed6Interval::print(outBuf); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_thickStartStr); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_thickEndStr); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_itemRGB); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_blockCountStr); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_blockSizes); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_blockStarts); } -void Bed12Interval::print(QuickString &outBuf, int start, int end) const +void Bed12Interval::print(string &outBuf, int start, int end) const { Bed6Interval::print(outBuf, start, end); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_thickStartStr); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_thickEndStr); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_itemRGB); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_blockCountStr); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_blockSizes); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_blockStarts); } -void Bed12Interval::print(QuickString &outBuf, const QuickString & start, const QuickString & end) const +void Bed12Interval::print(string &outBuf, const string & start, const string & end) const { Bed6Interval::print(outBuf, start, end); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_thickStartStr); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_thickEndStr); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_itemRGB); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_blockCountStr); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_blockSizes); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_blockStarts); } -void Bed12Interval::printNull(QuickString &outBuf) const +void Bed12Interval::printNull(string &outBuf) const { Bed6Interval::printNull(outBuf); outBuf.append("\t.\t.\t.\t.\t.\t.", 12); } -const QuickString &Bed12Interval::getField(int fieldNum) const +const string &Bed12Interval::getField(int fieldNum) const { switch (fieldNum) { case 7: @@ -178,7 +178,7 @@ int Bed12Interval::getLength(bool obeySplits) const { return _endPos - _startPos; } else { vector vBlockSizes; - Tokenize(_blockSizes.str(), vBlockSizes, ','); + Tokenize(_blockSizes, vBlockSizes, ','); return accumulate(vBlockSizes.begin(), vBlockSizes.end(), 0); } } diff --git a/src/utils/FileRecordTools/Records/Bed12Interval.h b/src/utils/FileRecordTools/Records/Bed12Interval.h index c1c97b7..5d90759 100644 --- a/src/utils/FileRecordTools/Records/Bed12Interval.h +++ b/src/utils/FileRecordTools/Records/Bed12Interval.h @@ -21,10 +21,10 @@ public: Bed12Interval(); virtual bool initFromFile(SingleLineDelimTextFileReader *); virtual void clear(); - virtual void print(QuickString &outBuf) const; - virtual void print(QuickString &outBuf, int start, int end) const; - virtual void print(QuickString &outBuf, const QuickString & start, const QuickString & end) const; - virtual void printNull(QuickString &outBuf) const; + virtual void print(string &outBuf) const; + virtual void print(string &outBuf, int start, int end) const; + virtual void print(string &outBuf, const string & start, const string & end) const; + virtual void printNull(string &outBuf) const; virtual FileRecordTypeChecker::RECORD_TYPE getType() const { return FileRecordTypeChecker::BED12_RECORD_TYPE; } const Bed12Interval &operator=(const Bed12Interval &other); @@ -35,25 +35,22 @@ public: virtual int getThickEnd() const { return _thickEnd; } virtual void setThickEnd(int thickEnd) { _thickEnd = thickEnd; } - virtual const QuickString & getItemRGB() const { return _itemRGB; } - virtual void setItemRGB(const QuickString & rgb) { _itemRGB = rgb; } + virtual const string & getItemRGB() const { return _itemRGB; } virtual void setItemRGB(const string & rgb) { _itemRGB = rgb; } virtual void setItemRGB(const char *rgb) { _itemRGB = rgb; } virtual int getBlockCount() const { return _blockCount; } virtual void setBlockCount(int blockCount) { _blockCount = blockCount; } - virtual const QuickString & getBlockSizes() const { return _blockSizes; } - virtual void setBlockSizes(const QuickString & blockSizes) { _blockSizes = blockSizes; } + virtual const string & getBlockSizes() const { return _blockSizes; } virtual void setBlockSizes(const string & blockSizes) { _blockSizes = blockSizes; } virtual void setBlockSizes(const char *blockSizes) { _blockSizes = blockSizes; } - virtual const QuickString & getBlockStarts() const { return _blockStarts; } - virtual void setBlockStarts(const QuickString & blockStarts) { _blockStarts = blockStarts; } + virtual const string & getBlockStarts() const { return _blockStarts; } virtual void setBlockStarts(const string & blockStarts) { _blockStarts = blockStarts; } virtual void setBlockStarts(const char *blockStarts) { _blockStarts = blockStarts; } - virtual const QuickString &getField(int fieldNum) const; + virtual const string &getField(int fieldNum) const; virtual int getNumFields() const { return 12; } static bool isNumericField(int fieldNum); int getLength(bool obeySplits) const; @@ -64,15 +61,15 @@ protected: int _thickStart; int _thickEnd; - QuickString _itemRGB; + string _itemRGB; int _blockCount; - QuickString _blockSizes; - QuickString _blockStarts; + string _blockSizes; + string _blockStarts; //store int values as their originial strings for faster outputting. - QuickString _thickStartStr; - QuickString _thickEndStr; - QuickString _blockCountStr; + string _thickStartStr; + string _thickEndStr; + string _blockCountStr; }; diff --git a/src/utils/FileRecordTools/Records/Bed3Interval.cpp b/src/utils/FileRecordTools/Records/Bed3Interval.cpp index 036d0c6..d2d3441 100644 --- a/src/utils/FileRecordTools/Records/Bed3Interval.cpp +++ b/src/utils/FileRecordTools/Records/Bed3Interval.cpp @@ -31,38 +31,42 @@ bool Bed3Interval::initFromFile(SingleLineDelimTextFileReader *fileReader) return true; } -void Bed3Interval::print(QuickString &outBuf) const +void Bed3Interval::print(string &outBuf) const { - outBuf.append(_chrName); - outBuf.append('\t'); - outBuf.append(_startPos); - outBuf.append('\t'); - outBuf.append(_endPos); + ostringstream s; + s << _chrName; + s << "\t"; + s << _startPos; + s << "\t"; + s << _endPos; + outBuf.append(s.str()); } -void Bed3Interval::print(QuickString &outBuf, int start, int end) const +void Bed3Interval::print(string &outBuf, int start, int end) const { - outBuf.append(_chrName); - outBuf.append('\t'); - outBuf.append(start); - outBuf.append('\t'); - outBuf.append(end); + ostringstream s; + s << _chrName; + s << "\t"; + s << start; + s << "\t"; + s << end; + outBuf.append(s.str()); } -void Bed3Interval::print(QuickString &outBuf, const QuickString & start, const QuickString & end) const +void Bed3Interval::print(string &outBuf, const string & start, const string & end) const { outBuf.append(_chrName); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(start); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(end); } -void Bed3Interval::printNull(QuickString &outBuf) const { +void Bed3Interval::printNull(string &outBuf) const { outBuf.append(".\t-1\t-1", 7); } -const QuickString &Bed3Interval::getField(int fieldNum) const +const string &Bed3Interval::getField(int fieldNum) const { switch (fieldNum) { case 1: diff --git a/src/utils/FileRecordTools/Records/Bed3Interval.h b/src/utils/FileRecordTools/Records/Bed3Interval.h index 2e9a878..fcc1b1c 100644 --- a/src/utils/FileRecordTools/Records/Bed3Interval.h +++ b/src/utils/FileRecordTools/Records/Bed3Interval.h @@ -10,7 +10,7 @@ #include "Record.h" #include "ParseTools.h" -#include "QuickString.h" +#include "string.h" class FileReader; class SingleLineDelimTextFileReader; @@ -23,13 +23,13 @@ public: Bed3Interval(); bool initFromFile(FileReader *); virtual bool initFromFile(SingleLineDelimTextFileReader *); - virtual void print(QuickString &outBuf) const; - virtual void print(QuickString &outBuf, int start, int end) const; - virtual void print(QuickString &outBuf, const QuickString & start, const QuickString & end) const; - virtual void printNull(QuickString &outBuf) const; + virtual void print(string &outBuf) const; + virtual void print(string &outBuf, int start, int end) const; + virtual void print(string &outBuf, const string & start, const string & end) const; + virtual void printNull(string &outBuf) const; virtual FileRecordTypeChecker::RECORD_TYPE getType() const { return FileRecordTypeChecker::BED3_RECORD_TYPE; } - virtual const QuickString &getField(int fieldNum) const; + virtual const string &getField(int fieldNum) const; virtual int getNumFields() const { return 3; } static bool isNumericField(int fieldNum); diff --git a/src/utils/FileRecordTools/Records/Bed4Interval.cpp b/src/utils/FileRecordTools/Records/Bed4Interval.cpp index 4d16b75..6d47e5f 100644 --- a/src/utils/FileRecordTools/Records/Bed4Interval.cpp +++ b/src/utils/FileRecordTools/Records/Bed4Interval.cpp @@ -20,35 +20,35 @@ bool Bed4Interval::initFromFile(SingleLineDelimTextFileReader *fileReader) return baseRetFlag; } -void Bed4Interval::print(QuickString &outBuf) const +void Bed4Interval::print(string &outBuf) const { Bed3Interval::print(outBuf); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_name); } -void Bed4Interval::print(QuickString &outBuf, int start, int end) const +void Bed4Interval::print(string &outBuf, int start, int end) const { Bed3Interval::print(outBuf, start, end); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_name); } -void Bed4Interval::print(QuickString &outBuf, const QuickString & start, const QuickString & end) const +void Bed4Interval::print(string &outBuf, const string & start, const string & end) const { Bed3Interval::print(outBuf, start, end); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_name); } -void Bed4Interval::printNull(QuickString &outBuf) const +void Bed4Interval::printNull(string &outBuf) const { Bed3Interval::printNull(outBuf); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append("."); } -const QuickString &Bed4Interval::getField(int fieldNum) const +const string &Bed4Interval::getField(int fieldNum) const { switch (fieldNum) { case 4: diff --git a/src/utils/FileRecordTools/Records/Bed4Interval.h b/src/utils/FileRecordTools/Records/Bed4Interval.h index b038446..2e6bb94 100644 --- a/src/utils/FileRecordTools/Records/Bed4Interval.h +++ b/src/utils/FileRecordTools/Records/Bed4Interval.h @@ -20,13 +20,13 @@ public: Bed4Interval(); virtual bool initFromFile(SingleLineDelimTextFileReader *); - virtual void print(QuickString &outBuf) const; - virtual void print(QuickString &outBuf, int start, int end) const; - virtual void print(QuickString &outBuf, const QuickString & start, const QuickString & end) const; - virtual void printNull(QuickString &outBuf) const; + virtual void print(string &outBuf) const; + virtual void print(string &outBuf, int start, int end) const; + virtual void print(string &outBuf, const string & start, const string & end) const; + virtual void printNull(string &outBuf) const; virtual FileRecordTypeChecker::RECORD_TYPE getType() const { return FileRecordTypeChecker::BED4_RECORD_TYPE; } - virtual const QuickString &getField(int fieldNum) const; + virtual const string &getField(int fieldNum) const; virtual int getNumFields() const { return 4; } static bool isNumericField(int fieldNum); diff --git a/src/utils/FileRecordTools/Records/Bed5Interval.cpp b/src/utils/FileRecordTools/Records/Bed5Interval.cpp index 130a788..8f80d50 100644 --- a/src/utils/FileRecordTools/Records/Bed5Interval.cpp +++ b/src/utils/FileRecordTools/Records/Bed5Interval.cpp @@ -21,41 +21,41 @@ bool Bed5Interval::initFromFile(SingleLineDelimTextFileReader *fileReader) return baseRetFlag; } -void Bed5Interval::print(QuickString &outBuf) const +void Bed5Interval::print(string &outBuf) const { Bed3Interval::print(outBuf); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_name); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_score); } -void Bed5Interval::print(QuickString &outBuf, int start, int end) const +void Bed5Interval::print(string &outBuf, int start, int end) const { Bed3Interval::print(outBuf, start, end); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_name); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_score); } -void Bed5Interval::print(QuickString &outBuf, const QuickString & start, const QuickString & end) const +void Bed5Interval::print(string &outBuf, const string & start, const string & end) const { Bed3Interval::print(outBuf, start, end); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_name); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_score); } -void Bed5Interval::printNull(QuickString &outBuf) const +void Bed5Interval::printNull(string &outBuf) const { Bed3Interval::printNull(outBuf); outBuf.append("\t.\t-1", 5); } -const QuickString &Bed5Interval::getField(int fieldNum) const +const string &Bed5Interval::getField(int fieldNum) const { switch (fieldNum) { case 4: diff --git a/src/utils/FileRecordTools/Records/Bed5Interval.h b/src/utils/FileRecordTools/Records/Bed5Interval.h index 2064d35..906a3c1 100644 --- a/src/utils/FileRecordTools/Records/Bed5Interval.h +++ b/src/utils/FileRecordTools/Records/Bed5Interval.h @@ -19,13 +19,13 @@ public: Bed5Interval(); virtual bool initFromFile(SingleLineDelimTextFileReader *); - virtual void print(QuickString &outBuf) const; - virtual void print(QuickString &outBuf, int start, int end) const; - virtual void print(QuickString &outBuf, const QuickString & start, const QuickString & end) const; - virtual void printNull(QuickString &outBuf) const; + virtual void print(string &outBuf) const; + virtual void print(string &outBuf, int start, int end) const; + virtual void print(string &outBuf, const string & start, const string & end) const; + virtual void printNull(string &outBuf) const; virtual FileRecordTypeChecker::RECORD_TYPE getType() const { return FileRecordTypeChecker::BED5_RECORD_TYPE; } - virtual const QuickString &getField(int fieldNum) const; + virtual const string &getField(int fieldNum) const; virtual int getNumFields() const { return 5; } static bool isNumericField(int fieldNum); diff --git a/src/utils/FileRecordTools/Records/Bed6Interval.cpp b/src/utils/FileRecordTools/Records/Bed6Interval.cpp index 5bc783c..7cf744b 100644 --- a/src/utils/FileRecordTools/Records/Bed6Interval.cpp +++ b/src/utils/FileRecordTools/Records/Bed6Interval.cpp @@ -23,48 +23,48 @@ bool Bed6Interval::initFromFile(SingleLineDelimTextFileReader *fileReader) return baseRetFlag; } -void Bed6Interval::print(QuickString &outBuf) const +void Bed6Interval::print(string &outBuf) const { Bed3Interval::print(outBuf); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_name); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_score); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_strand); } -void Bed6Interval::print(QuickString &outBuf, int start, int end) const +void Bed6Interval::print(string &outBuf, int start, int end) const { Bed3Interval::print(outBuf, start, end); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_name); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_score); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_strand); } -void Bed6Interval::print(QuickString &outBuf, const QuickString & start, const QuickString & end) const +void Bed6Interval::print(string &outBuf, const string & start, const string & end) const { Bed3Interval::print(outBuf, start, end); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_name); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_score); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_strand); } -void Bed6Interval::printNull(QuickString &outBuf) const +void Bed6Interval::printNull(string &outBuf) const { Bed3Interval::printNull(outBuf); outBuf.append("\t.\t-1\t.", 7); } -const QuickString &Bed6Interval::getField(int fieldNum) const +const string &Bed6Interval::getField(int fieldNum) const { switch (fieldNum) { case 4: diff --git a/src/utils/FileRecordTools/Records/Bed6Interval.h b/src/utils/FileRecordTools/Records/Bed6Interval.h index 023683f..d6787ca 100644 --- a/src/utils/FileRecordTools/Records/Bed6Interval.h +++ b/src/utils/FileRecordTools/Records/Bed6Interval.h @@ -19,13 +19,13 @@ public: Bed6Interval(); virtual bool initFromFile(SingleLineDelimTextFileReader *); - virtual void print(QuickString &outBuf) const; - virtual void print(QuickString &outBuf, int start, int end) const; - virtual void print(QuickString &outBuf, const QuickString & start, const QuickString & end) const; - virtual void printNull(QuickString &outBuf) const; + virtual void print(string &outBuf) const; + virtual void print(string &outBuf, int start, int end) const; + virtual void print(string &outBuf, const string & start, const string & end) const; + virtual void printNull(string &outBuf) const; virtual FileRecordTypeChecker::RECORD_TYPE getType() const { return FileRecordTypeChecker::BED6_RECORD_TYPE; } - virtual const QuickString &getField(int fieldNum) const; + virtual const string &getField(int fieldNum) const; virtual int getNumFields() const { return 6; } static bool isNumericField(int fieldNum); diff --git a/src/utils/FileRecordTools/Records/BedGraphInterval.cpp b/src/utils/FileRecordTools/Records/BedGraphInterval.cpp index 9cfda48..781f7d9 100644 --- a/src/utils/FileRecordTools/Records/BedGraphInterval.cpp +++ b/src/utils/FileRecordTools/Records/BedGraphInterval.cpp @@ -20,35 +20,35 @@ bool BedGraphInterval::initFromFile(SingleLineDelimTextFileReader *fileReader) return baseRetFlag; } -void BedGraphInterval::print(QuickString &outBuf) const +void BedGraphInterval::print(string &outBuf) const { Bed3Interval::print(outBuf); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_name); } -void BedGraphInterval::print(QuickString &outBuf, int start, int end) const +void BedGraphInterval::print(string &outBuf, int start, int end) const { Bed3Interval::print(outBuf, start, end); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_name); } -void BedGraphInterval::print(QuickString &outBuf, const QuickString & start, const QuickString & end) const +void BedGraphInterval::print(string &outBuf, const string & start, const string & end) const { Bed3Interval::print(outBuf, start, end); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_name); } -void BedGraphInterval::printNull(QuickString &outBuf) const +void BedGraphInterval::printNull(string &outBuf) const { Bed3Interval::printNull(outBuf); outBuf.append("\t.", 2); } -const QuickString &BedGraphInterval::getField(int fieldNum) const +const string &BedGraphInterval::getField(int fieldNum) const { switch (fieldNum) { case 4: diff --git a/src/utils/FileRecordTools/Records/BedGraphInterval.h b/src/utils/FileRecordTools/Records/BedGraphInterval.h index 5db6fea..767b3a0 100644 --- a/src/utils/FileRecordTools/Records/BedGraphInterval.h +++ b/src/utils/FileRecordTools/Records/BedGraphInterval.h @@ -19,13 +19,13 @@ public: BedGraphInterval(); virtual bool initFromFile(SingleLineDelimTextFileReader *); - virtual void print(QuickString &outBuf) const; - virtual void print(QuickString &outBuf, int start, int end) const; - virtual void print(QuickString &outBuf, const QuickString & start, const QuickString & end) const; - virtual void printNull(QuickString &outBuf) const; + virtual void print(string &outBuf) const; + virtual void print(string &outBuf, int start, int end) const; + virtual void print(string &outBuf, const string & start, const string & end) const; + virtual void printNull(string &outBuf) const; virtual FileRecordTypeChecker::RECORD_TYPE getType() const { return FileRecordTypeChecker::BEDGRAPH_RECORD_TYPE; } - virtual const QuickString &getField(int fieldNum) const; + virtual const string &getField(int fieldNum) const; virtual int getNumFields() const { return 4; } static bool isNumericField(int fieldNum); diff --git a/src/utils/FileRecordTools/Records/BedPlusInterval.cpp b/src/utils/FileRecordTools/Records/BedPlusInterval.cpp index da6ae96..3750751 100644 --- a/src/utils/FileRecordTools/Records/BedPlusInterval.cpp +++ b/src/utils/FileRecordTools/Records/BedPlusInterval.cpp @@ -35,29 +35,32 @@ void BedPlusInterval::clear() { _plusFields.clear(); } -void BedPlusInterval::print(QuickString &outBuf) const +void BedPlusInterval::print(string &outBuf) const { Bed3Interval::print(outBuf); + outBuf.append("\t"); printBed6PlusFields(outBuf); _plusFields.printFields(outBuf); } -void BedPlusInterval::print(QuickString &outBuf, int start, int end) const +void BedPlusInterval::print(string &outBuf, int start, int end) const { Bed3Interval::print(outBuf, start, end); + outBuf.append("\t"); printBed6PlusFields(outBuf); _plusFields.printFields(outBuf); } -void BedPlusInterval::print(QuickString &outBuf, const QuickString & start, const QuickString & end) const +void BedPlusInterval::print(string &outBuf, const string & start, const string & end) const { Bed3Interval::print(outBuf, start, end); + outBuf.append("\t"); printBed6PlusFields(outBuf); _plusFields.printFields(outBuf); } -void BedPlusInterval::printNull(QuickString &outBuf) const +void BedPlusInterval::printNull(string &outBuf) const { Bed3Interval::printNull(outBuf); printBed6PlusNullFields(outBuf); @@ -66,7 +69,7 @@ void BedPlusInterval::printNull(QuickString &outBuf) const } } -const QuickString &BedPlusInterval::getField(int fieldNum) const +const string &BedPlusInterval::getField(int fieldNum) const { if (fieldNum > _numFixedFields) { return _plusFields.getField(fieldNum); @@ -94,19 +97,18 @@ bool BedPlusInterval::isNumericField(int fieldNum) { return Bed3Interval::isNumericField(fieldNum); } -void BedPlusInterval::printBed6PlusFields(QuickString &outBuf) const { +void BedPlusInterval::printBed6PlusFields(string &outBuf) const { if (_numFixedFields != defaultNumFixedFields) { - outBuf.append('\t'); outBuf.append(_name); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_score); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_strand); + outBuf.append("\t"); } - } -void BedPlusInterval::printBed6PlusNullFields(QuickString &outBuf) const { +void BedPlusInterval::printBed6PlusNullFields(string &outBuf) const { if (_numFixedFields != defaultNumFixedFields) { outBuf.append("\t.\t.\t."); } diff --git a/src/utils/FileRecordTools/Records/BedPlusInterval.h b/src/utils/FileRecordTools/Records/BedPlusInterval.h index bf75db7..0eb0b42 100644 --- a/src/utils/FileRecordTools/Records/BedPlusInterval.h +++ b/src/utils/FileRecordTools/Records/BedPlusInterval.h @@ -22,13 +22,13 @@ public: void setNumFixedFields(int numFields); virtual bool initFromFile(SingleLineDelimTextFileReader *); virtual void clear(); - virtual void print(QuickString &outBuf) const; - virtual void print(QuickString &outBuf, int start, int end) const; - virtual void print(QuickString &outBuf, const QuickString & start, const QuickString & end) const; - virtual void printNull(QuickString &outBuf) const; + virtual void print(string &outBuf) const; + virtual void print(string &outBuf, int start, int end) const; + virtual void print(string &outBuf, const string & start, const string & end) const; + virtual void printNull(string &outBuf) const; virtual FileRecordTypeChecker::RECORD_TYPE getType() const { return FileRecordTypeChecker::BED_PLUS_RECORD_TYPE; } - virtual const QuickString &getField(int fieldNum) const; + virtual const string &getField(int fieldNum) const; virtual int getNumFields() const { return _numFixedFields + _plusFields.size(); } virtual void setNumPrintFields(int num) { _numPrintFields = num; } @@ -42,8 +42,8 @@ protected: PlusFields _plusFields; int _numPrintFields; - void printBed6PlusFields(QuickString &outBuf) const; - void printBed6PlusNullFields(QuickString &outBuf) const; + void printBed6PlusFields(string &outBuf) const; + void printBed6PlusNullFields(string &outBuf) const; }; diff --git a/src/utils/FileRecordTools/Records/BlockMgr.cpp b/src/utils/FileRecordTools/Records/BlockMgr.cpp index eb63972..bfccc60 100644 --- a/src/utils/FileRecordTools/Records/BlockMgr.cpp +++ b/src/utils/FileRecordTools/Records/BlockMgr.cpp @@ -48,8 +48,6 @@ void BlockMgr::getBlocks(RecordKeyVector &keyList, bool &mustDelete) } } - - void BlockMgr::getBlocksFromBed12(RecordKeyVector &keyList, bool &mustDelete) { const Bed12Interval *keyRecord = static_cast(keyList.getKey()); @@ -72,7 +70,7 @@ void BlockMgr::getBlocksFromBed12(RecordKeyVector &keyList, bool &mustDelete) int startPos = keyRecord->getStartPos() + str2chrPos(_blockStartTokens.getElem(i).c_str()); int endPos = startPos + str2chrPos(_blockSizeTokens.getElem(i).c_str()); - const Record *record = allocateAndAssignRecord(keyRecord, startPos, endPos); + Record *record = allocateAndAssignRecord(keyRecord, startPos, endPos); keyList.push_back(record); } mustDelete = true; @@ -128,22 +126,12 @@ Record *BlockMgr::allocateAndAssignRecord(const Record *keyRecord, int startPos, record->setChromId(keyRecord->getChromId()); record->setStartPos(startPos); record->setEndPos(endPos); - QuickString startPosStr; - QuickString endPosStr; - startPosStr.append(startPos); - endPosStr.append(endPos); - record->setStartPosStr(startPosStr); - record->setEndPosStr(endPosStr); - record->setName(keyRecord->getName()); - record->setScore(keyRecord->getScore()); - record->setStrand(keyRecord->getStrand()); - return record; } int BlockMgr::getTotalBlockLength(RecordKeyVector &keyList) { int sum = 0; - for (RecordKeyVector::const_iterator_type iter = keyList.begin(); iter != keyList.end(); iter = keyList.next()) { + for (RecordKeyVector::iterator_type iter = keyList.begin(); iter != keyList.end(); iter = keyList.next()) { const Record *record = *iter; sum += record->getEndPos() - record->getStartPos(); } @@ -152,28 +140,25 @@ int BlockMgr::getTotalBlockLength(RecordKeyVector &keyList) { void BlockMgr::deleteBlocks(RecordKeyVector &keyList) { - for (RecordKeyVector::const_iterator_type iter = keyList.begin(); iter != keyList.end(); iter = keyList.next()) { + for (RecordKeyVector::iterator_type iter = keyList.begin(); iter != keyList.end(); iter = keyList.next()) { _blockRecordsMgr->deleteRecord(*iter); } keyList.clearVector(); - } -int BlockMgr::findBlockedOverlaps(RecordKeyVector &keyList, RecordKeyVector &hitList, - RecordKeyVector &resultList, RecordKeyVector &overlapList) +int BlockMgr::findBlockedOverlaps(RecordKeyVector &hitList, bool useOverlappingSubBlocks) { - bool deleteKeyBlocks = false; - if (keyList.empty()) { - //get all the blocks for the query record, put them in it's list. - getBlocks(keyList, deleteKeyBlocks); - } + RecordKeyVector keyList(hitList.getKey()); + bool deleteKeyBlocks = true; + getBlocks(keyList, deleteKeyBlocks); + _overlapBases.clear(); int keyBlocksSumLength = getTotalBlockLength(keyList); //Loop through every database record the query intersected with - RecordKeyVector::const_iterator_type hitListIter = hitList.begin(); - for (; hitListIter != hitList.end(); hitListIter = hitList.next()) + RecordKeyVector::iterator_type hitListIter = hitList.begin(); + for (; hitListIter != hitList.end();) { RecordKeyVector hitBlocks(*hitListIter); bool deleteHitBlocks = false; @@ -183,46 +168,78 @@ int BlockMgr::findBlockedOverlaps(RecordKeyVector &keyList, RecordKeyVector &hit bool hitHasOverlap = false; //loop through every block of the database record. - RecordKeyVector::const_iterator_type hitBlockIter = hitBlocks.begin(); + RecordKeyVector::iterator_type hitBlockIter = hitBlocks.begin(); for (; hitBlockIter != hitBlocks.end(); hitBlockIter = hitBlocks.next()) { //loop through every block of the query record. - RecordKeyVector::const_iterator_type keyListIter = keyList.begin(); + RecordKeyVector::iterator_type keyListIter = keyList.begin(); for (; keyListIter != keyList.end(); keyListIter = keyList.next()) { const Record *keyBlock = *keyListIter; const Record *hitBlock = *hitBlockIter; - int maxStart = max(keyBlock->getStartPos(), hitBlock->getStartPos()); - int minEnd = min(keyBlock->getEndPos(), hitBlock->getEndPos()); + int minEnd = min(keyBlock->getEndPos(), hitBlock->getEndPos()); int overlap = minEnd - maxStart; - if (overlap > 0) { + if (overlap > 0) + { hitHasOverlap = true; - overlapList.push_back(allocateAndAssignRecord(keyList.getKey(), maxStart, minEnd)); totalHitOverlap += overlap; + if (useOverlappingSubBlocks == true) + { + (*hitListIter)->block_starts.push_back(maxStart); + (*hitListIter)->block_ends.push_back(minEnd); + } } } } - if (hitHasOverlap) { - if ((float) totalHitOverlap / (float)keyBlocksSumLength >= _overlapFraction) { - if (_hasReciprocal && - ((float)totalHitOverlap / (float)hitBlockSumLength >= _overlapFraction)) { + if (hitHasOverlap && useOverlappingSubBlocks == false) + { + bool enoughKeyOverlap = (float) totalHitOverlap / (float) keyBlocksSumLength >= _overlapFraction; + bool enoughHitOverlap = (float) totalHitOverlap / (float) hitBlockSumLength >= _overlapFraction; + + if (enoughKeyOverlap) + { + if (_hasReciprocal && enoughHitOverlap) + { + //(*hitListIter)->setValid(true); _overlapBases.push_back(totalHitOverlap); - resultList.push_back(*hitListIter); - } else if (!_hasReciprocal) { + hitListIter = hitList.next(); + } + else if (_hasReciprocal && !enoughHitOverlap) + { + hitList.erase(); + //(*hitListIter)->setValid(false); + } + else if (!_hasReciprocal) + { + //(*hitListIter)->setValid(true); _overlapBases.push_back(totalHitOverlap); - resultList.push_back(*hitListIter); + hitListIter = hitList.next(); } } + else + { + hitList.erase(); + //(*hitListIter)->setValid(false); + } + } + else if (!hitHasOverlap && useOverlappingSubBlocks == false) + { + hitList.erase(); + //(*hitListIter)->setValid(false); } - if (deleteHitBlocks) { + else { + hitListIter = hitList.next(); + } + if (deleteHitBlocks) + { deleteBlocks(hitBlocks); } - } - if (deleteKeyBlocks) { + } // end for loop through main hits + if (deleteKeyBlocks) + { deleteBlocks(keyList); } - resultList.setKey(keyList.getKey()); - return (int)resultList.size(); + return (int)hitList.size(); } diff --git a/src/utils/FileRecordTools/Records/BlockMgr.h b/src/utils/FileRecordTools/Records/BlockMgr.h index fce996a..4fe739c 100644 --- a/src/utils/FileRecordTools/Records/BlockMgr.h +++ b/src/utils/FileRecordTools/Records/BlockMgr.h @@ -34,10 +34,12 @@ public: // Determine which hits in the hitList intersect the hits in the keyList by comparing all blocks in each // and checking that their total intersection meets any overlapFraction and reciprocal criteria compared to // the total block lengths of the hitList and keyList. All hits that pass will be in the resultList. + // + // If useOverlappingSubBlocks is true, resultList will contain the sub-intervals of the hit blocks + // that overlap the query blocks. + // // Return value is the number of hits in the result set. - - int findBlockedOverlaps(RecordKeyVector &keyList, RecordKeyVector &hitList, - RecordKeyVector &resultList, RecordKeyVector &overlapList); + int findBlockedOverlaps(RecordKeyVector &hitList, bool useOverlappingSubBlocks); //these are setting options for splitting BAM records void setBreakOnDeletionOps(bool val) { _breakOnDeletionOps = val; } diff --git a/src/utils/FileRecordTools/Records/GffPlusRecord.cpp b/src/utils/FileRecordTools/Records/GffPlusRecord.cpp index d09bc48..c155b2c 100644 --- a/src/utils/FileRecordTools/Records/GffPlusRecord.cpp +++ b/src/utils/FileRecordTools/Records/GffPlusRecord.cpp @@ -25,26 +25,26 @@ void GffPlusRecord::clear() { _plusFields.clear(); } -void GffPlusRecord::print(QuickString &outBuf) const +void GffPlusRecord::print(string &outBuf) const { GffRecord::print(outBuf); _plusFields.printFields(outBuf); } -void GffPlusRecord::print(QuickString &outBuf, int start, int end) const +void GffPlusRecord::print(string &outBuf, int start, int end) const { GffRecord::print(outBuf, start, end); _plusFields.printFields(outBuf); } -void GffPlusRecord::print(QuickString &outBuf, const QuickString & start, const QuickString & end) const +void GffPlusRecord::print(string &outBuf, const string & start, const string & end) const { GffRecord::print(outBuf, start, end); _plusFields.printFields(outBuf); } -void GffPlusRecord::printNull(QuickString &outBuf) const +void GffPlusRecord::printNull(string &outBuf) const { GffRecord::printNull(outBuf); for (int i=_numFields; i < _numPrintFields; i++) { @@ -52,7 +52,7 @@ void GffPlusRecord::printNull(QuickString &outBuf) const } } -const QuickString &GffPlusRecord::getField(int fieldNum) const +const string &GffPlusRecord::getField(int fieldNum) const { if (fieldNum > _numFields) { return _plusFields.getField(fieldNum); diff --git a/src/utils/FileRecordTools/Records/GffPlusRecord.h b/src/utils/FileRecordTools/Records/GffPlusRecord.h index e485b43..ac72b89 100644 --- a/src/utils/FileRecordTools/Records/GffPlusRecord.h +++ b/src/utils/FileRecordTools/Records/GffPlusRecord.h @@ -21,13 +21,13 @@ public: virtual ~GffPlusRecord(); virtual bool initFromFile(SingleLineDelimTextFileReader *); virtual void clear(); - virtual void print(QuickString &outBuf) const; - virtual void print(QuickString &outBuf, int start, int end) const; - virtual void print(QuickString &outBuf, const QuickString & start, const QuickString & end) const; - virtual void printNull(QuickString &outBuf) const; + virtual void print(string &outBuf) const; + virtual void print(string &outBuf, int start, int end) const; + virtual void print(string &outBuf, const string & start, const string & end) const; + virtual void printNull(string &outBuf) const; virtual FileRecordTypeChecker::RECORD_TYPE getType() const { return FileRecordTypeChecker::GFF_PLUS_RECORD_TYPE; } - virtual const QuickString &getField(int fieldNum) const; + virtual const string &getField(int fieldNum) const; virtual int getNumFields() const { return GffRecord::getNumFields() + _plusFields.size(); } virtual void setNumPrintFields(int num) { _numPrintFields = num; } diff --git a/src/utils/FileRecordTools/Records/GffRecord.cpp b/src/utils/FileRecordTools/Records/GffRecord.cpp index d111ad9..11f3d77 100644 --- a/src/utils/FileRecordTools/Records/GffRecord.cpp +++ b/src/utils/FileRecordTools/Records/GffRecord.cpp @@ -50,68 +50,70 @@ bool GffRecord::initFromFile(SingleLineDelimTextFileReader *fileReader) return true; } -void GffRecord::print(QuickString &outBuf) const +void GffRecord::print(string &outBuf) const { - outBuf.append(_chrName); - outBuf.append('\t'); - outBuf.append(_source); - outBuf.append('\t'); - outBuf.append(_name); - outBuf.append('\t'); - outBuf.append(_startPosStr); - outBuf.append('\t'); - outBuf.append(_endPosStr); - outBuf.append('\t'); - + ostringstream s; + s << _chrName; + s << "\t"; + s << _source; + s << "\t"; + s << _name; + s << "\t"; + s << _startPosStr; + s << "\t"; + s << _endPosStr; + s << "\t"; + outBuf.append(s.str()); printRemainingFields(outBuf); } -void GffRecord::print(QuickString &outBuf, int start, int end) const +void GffRecord::print(string &outBuf, int start, int end) const { - outBuf.append(_chrName); - outBuf.append('\t'); - outBuf.append(_source); - outBuf.append('\t'); - outBuf.append(_name); - outBuf.append('\t'); - outBuf.append(start); - outBuf.append('\t'); - outBuf.append(end); - outBuf.append('\t'); - + ostringstream s; + s << _chrName; + s << "\t"; + s << _source; + s << "\t"; + s << _name; + s << "\t"; + s << start; + s << "\t"; + s << end; + s << "\t"; + outBuf.append(s.str()); printRemainingFields(outBuf); } -void GffRecord::print(QuickString &outBuf, const QuickString & start, const QuickString & end) const +void GffRecord::print(string &outBuf, const string & start, const string & end) const { outBuf.append(_chrName); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_source); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_name); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(start); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(end); - outBuf.append('\t'); + outBuf.append("\t"); printRemainingFields(outBuf); } -void GffRecord::printRemainingFields(QuickString &outBuf) const +void GffRecord::printRemainingFields(string &outBuf) const { outBuf.append(_score); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_strand); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_frame); if (_numFields == 9) { - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_group); } } -void GffRecord::printNull(QuickString &outBuf) const +void GffRecord::printNull(string &outBuf) const { outBuf.append(".\t.\t.\t-1\t-1\t.\t.\t.", 17); if (_numFields > 8) { @@ -119,7 +121,7 @@ void GffRecord::printNull(QuickString &outBuf) const } } -const QuickString &GffRecord::getField(int fieldNum) const +const string &GffRecord::getField(int fieldNum) const { if (fieldNum == 9 && _numFields == 9) { return _group; diff --git a/src/utils/FileRecordTools/Records/GffRecord.h b/src/utils/FileRecordTools/Records/GffRecord.h index 40b0d77..040406b 100644 --- a/src/utils/FileRecordTools/Records/GffRecord.h +++ b/src/utils/FileRecordTools/Records/GffRecord.h @@ -20,28 +20,28 @@ public: virtual ~GffRecord(); virtual bool initFromFile(SingleLineDelimTextFileReader *); virtual void clear(); - virtual void print(QuickString &outBuf) const; - virtual void print(QuickString &outBuf, int start, int end) const; - virtual void print(QuickString &outBuf, const QuickString & start, const QuickString & end) const; - virtual void printNull(QuickString &outBuf) const; + virtual void print(string &outBuf) const; + virtual void print(string &outBuf, int start, int end) const; + virtual void print(string &outBuf, const string & start, const string & end) const; + virtual void printNull(string &outBuf) const; virtual FileRecordTypeChecker::RECORD_TYPE getType() const { return FileRecordTypeChecker::GFF_RECORD_TYPE; } - virtual const QuickString &getSource() const { return _source; } - virtual const QuickString &getFrame() const { return _frame; } - virtual const QuickString &getGroup() const { return _group; } + virtual const string &getSource() const { return _source; } + virtual const string &getFrame() const { return _frame; } + virtual const string &getGroup() const { return _group; } virtual int getNumFields() const { return _numFields; } virtual void setNumFields(int val) { _numFields = val; } - virtual const QuickString &getField(int fieldNum) const; + virtual const string &getField(int fieldNum) const; static bool isNumericField(int fieldNum); virtual bool isZeroBased() const {return false;}; protected: - void printRemainingFields(QuickString &outbuf) const; + void printRemainingFields(string &outbuf) const; int _numFields; - QuickString _source; - QuickString _frame; - QuickString _group; + string _source; + string _frame; + string _group; }; diff --git a/src/utils/FileRecordTools/Records/Makefile b/src/utils/FileRecordTools/Records/Makefile index 9de60d3..e6be94b 100644 --- a/src/utils/FileRecordTools/Records/Makefile +++ b/src/utils/FileRecordTools/Records/Makefile @@ -5,14 +5,14 @@ UTILITIES_DIR = ../../../utils/ # define our includes # ------------------- INCLUDES = -I$(UTILITIES_DIR)/lineFileUtilities/ \ - -I$(UTILITIES_DIR)/FileRecordTools/FileReaders/ \ - -I$(UTILITIES_DIR)/general/ \ - -I$(UTILITIES_DIR)/fileType/ \ - -I$(UTILITIES_DIR)/Contexts/ \ - -I$(UTILITIES_DIR)/GenomeFile/ \ - -I$(UTILITIES_DIR)/BamTools/include \ - -I$(UTILITIES_DIR)/BamTools/src/ \ - -I$(UTILITIES_DIR)/version/ + -I$(UTILITIES_DIR)/FileRecordTools/FileReaders/ \ + -I$(UTILITIES_DIR)/general/ \ + -I$(UTILITIES_DIR)/fileType/ \ + -I$(UTILITIES_DIR)/Contexts/ \ + -I$(UTILITIES_DIR)/GenomeFile/ \ + -I$(UTILITIES_DIR)/BamTools/include \ + -I$(UTILITIES_DIR)/BamTools/src/ \ + -I$(UTILITIES_DIR)/version/ # ---------------------------------- @@ -27,7 +27,7 @@ SOURCES = Record.cpp EmptyRecord.cpp Bed3Interval.cpp \ RecordMgr.cpp RecordList.cpp RecordKeyList.cpp RecordKeyVector.cpp OBJECTS= Record.o EmptyRecord.o Bed3Interval.o Bed4Interval.o BedGraphInterval.o Bed5Interval.o Bed6Interval.o PlusFields.o BedPlusInterval.o Bed12Interval.o BamRecord.o \ GffRecord.o GffPlusRecord.o VcfRecord.o NoPosPlusRecord.o BlockMgr.o StrandQueue.o RecordMgr.o RecordList.o RecordKeyList.o RecordKeyVector.o -_EXT_OBJECTS=ParseTools.o QuickString.o ChromIdLookup.o +_EXT_OBJECTS=ParseTools.o string.o ChromIdLookup.o EXT_OBJECTS=$(patsubst %,$(OBJ_DIR)/%,$(_EXT_OBJECTS)) BUILT_OBJECTS= $(patsubst %,$(OBJ_DIR)/%,$(OBJECTS)) diff --git a/src/utils/FileRecordTools/Records/NoPosPlusRecord.cpp b/src/utils/FileRecordTools/Records/NoPosPlusRecord.cpp index 08ceccc..af9ad5e 100644 --- a/src/utils/FileRecordTools/Records/NoPosPlusRecord.cpp +++ b/src/utils/FileRecordTools/Records/NoPosPlusRecord.cpp @@ -26,12 +26,12 @@ void NoPosPlusRecord::clear() { _plusFields.clear(); } -void NoPosPlusRecord::print(QuickString &outBuf) const +void NoPosPlusRecord::print(string &outBuf) const { _plusFields.printFields(outBuf); } -const QuickString &NoPosPlusRecord::getField(int fieldNum) const +const string &NoPosPlusRecord::getField(int fieldNum) const { return _plusFields.getField(fieldNum); } diff --git a/src/utils/FileRecordTools/Records/NoPosPlusRecord.h b/src/utils/FileRecordTools/Records/NoPosPlusRecord.h index b3293ef..c953d00 100644 --- a/src/utils/FileRecordTools/Records/NoPosPlusRecord.h +++ b/src/utils/FileRecordTools/Records/NoPosPlusRecord.h @@ -22,10 +22,10 @@ public: bool initFromFile(FileReader *); virtual bool initFromFile(SingleLineDelimTextFileReader *); virtual void clear(); - virtual void print(QuickString &outBuf) const; + virtual void print(string &outBuf) const; virtual FileRecordTypeChecker::RECORD_TYPE getType() const { return FileRecordTypeChecker::NO_POS_PLUS_RECORD_TYPE; } - virtual const QuickString &getField(int fieldNum) const; + virtual const string &getField(int fieldNum) const; virtual int getNumFields() const { return defaultNumFixedFields + (int)_plusFields.size(); } static bool isNumericField(int fieldNum); diff --git a/src/utils/FileRecordTools/Records/PlusFields.cpp b/src/utils/FileRecordTools/Records/PlusFields.cpp index b272b71..19cd4ad 100644 --- a/src/utils/FileRecordTools/Records/PlusFields.cpp +++ b/src/utils/FileRecordTools/Records/PlusFields.cpp @@ -26,15 +26,14 @@ void PlusFields::clear() { } } -const QuickString &PlusFields::getField(int fieldNum) const +const string &PlusFields::getField(int fieldNum) const { return _fields[fieldNum - _numOffsetFields - 1]; } -void PlusFields::printFields(QuickString &outBuf) const { +void PlusFields::printFields(string &outBuf) const { for (size_t i=0; i < size(); i++) { - outBuf.append('\t'); outBuf.append(_fields[i]); + if (i < size() - 1) outBuf.append("\t"); } - } diff --git a/src/utils/FileRecordTools/Records/PlusFields.h b/src/utils/FileRecordTools/Records/PlusFields.h index c077a57..a6e7014 100644 --- a/src/utils/FileRecordTools/Records/PlusFields.h +++ b/src/utils/FileRecordTools/Records/PlusFields.h @@ -8,7 +8,8 @@ #ifndef PLUSFIELDS_H_ #define PLUSFIELDS_H_ -#include "QuickString.h" +#include "string.h" +#include #include using namespace std; @@ -23,14 +24,14 @@ public: void setNumOffsetFields(int numOffsetFields) { _numOffsetFields = numOffsetFields; } virtual bool initFromFile(SingleLineDelimTextFileReader *); virtual void clear(); - virtual void printFields(QuickString &outBuf) const; + virtual void printFields(string &outBuf) const; - virtual const QuickString &getField(int fieldNum) const; + virtual const string &getField(int fieldNum) const; virtual size_t size() const { return _fields.size(); } protected: - vector _fields; + vector _fields; int _numOffsetFields; //could be 3 for BedPlus, but GFF has 8 or 9 }; diff --git a/src/utils/FileRecordTools/Records/Record.cpp b/src/utils/FileRecordTools/Records/Record.cpp index b6a2da7..33c06c9 100644 --- a/src/utils/FileRecordTools/Records/Record.cpp +++ b/src/utils/FileRecordTools/Records/Record.cpp @@ -9,11 +9,14 @@ Record::Record() _strandVal(UNKNOWN), _zeroLength(false), _isUnmapped(false), - _isMateUnmapped(false) -{ -} + _isMateUnmapped(false), + _isValidHit(true), + _frm(NULL) +{} -Record::~Record() { +Record::~Record() +{ + //_frm->deleteRecord(this); } const Record &Record::operator=(const Record &other) @@ -44,6 +47,7 @@ void Record::clear() { _zeroLength = false; _isUnmapped = false; _isMateUnmapped = false; + _isValidHit = false; } bool Record::operator < (const Record &other) const @@ -243,13 +247,13 @@ void Record::undoZeroLength() ostream &operator << (ostream &out, const Record &record) { - QuickString outBuf; + string outBuf; record.print(outBuf); out << outBuf; return out; } -const QuickString &Record::getField(int fieldNum) const +const string &Record::getField(int fieldNum) const { cerr << endl << "*****" << endl << "*****ERROR: requested column " << fieldNum << @@ -278,7 +282,7 @@ bool Record::hasLeadingZeroInChromName(bool chrKnown) const { } void Record::print(FILE *fp, bool newline) const { - QuickString buf; + string buf; print(buf); fprintf(fp, "%s", buf.c_str()); if(newline) fprintf(fp, "\n"); @@ -288,3 +292,13 @@ int Record::getLength(bool obeySplits) const { //only bed12 and BAM need to check splits return _endPos - _startPos; } + +void Record::setFileRecordManager(FileRecordMgr *frm) +{ + _frm = frm; +} + +FileRecordMgr * Record::getFileRecordManager() +{ + return _frm; +} \ No newline at end of file diff --git a/src/utils/FileRecordTools/Records/Record.h b/src/utils/FileRecordTools/Records/Record.h index c199d83..eeed218 100644 --- a/src/utils/FileRecordTools/Records/Record.h +++ b/src/utils/FileRecordTools/Records/Record.h @@ -10,7 +10,7 @@ #include #include "FreeList.h" -#include "QuickString.h" +#include "string.h" #include "FileRecordTypeChecker.h" using namespace std; @@ -26,24 +26,27 @@ public: friend class FreeList; + virtual ~Record(); //by making the destructor protected, only the friend class(es) can actually delete Record objects, or objects derived from Record. + typedef enum { FORWARD, REVERSE, UNKNOWN } strandType; Record(); virtual bool initFromFile(FileReader *) =0; virtual void clear(); - virtual void print(QuickString &outBuf) const {} - virtual void print(QuickString &outBuf, int start, int end) const {} - virtual void print(QuickString &outBuf, const QuickString & start, const QuickString & end) const {} + virtual void print(string &) const {} + virtual void print(string &, int, int ) const {} + virtual void print(string &, const string &, const string &) const {} virtual void print(FILE *fp, bool newline = false) const; - virtual void printNull(QuickString &outBuf) const {} + virtual void printNull(string &) const {} friend ostream &operator << (ostream &out, const Record &record); virtual const Record & operator=(const Record &); - virtual bool isZeroBased() const {return true;}; - virtual const QuickString &getChrName() const { return _chrName; } - virtual void setChrName(const QuickString &chr) { _chrName = chr; } + virtual void setValid(const bool valid) { _isValidHit = valid; } + virtual bool isValid() const { return _isValidHit; } + + virtual const string &getChrName() const { return _chrName; } virtual void setChrName(const string &chr) { _chrName = chr; } virtual void setChrName(const char *chr) { _chrName = chr; } @@ -55,19 +58,19 @@ public: virtual int getStartPos() const { return _startPos; } virtual void setStartPos(int startPos) { _startPos = startPos; } - virtual const QuickString &getStartPosStr() const { return _startPosStr; } - virtual void setStartPosStr(const QuickString &str) { _startPosStr = str; } + virtual const string &getStartPosStr() const { return _startPosStr; } + virtual void setStartPosStr(const string &str) { _startPosStr = str; } virtual int getEndPos() const { return _endPos; } virtual void setEndPos(int endPos) { _endPos = endPos; } - virtual const QuickString &getEndPosStr() const { return _endPosStr; } - virtual void setEndPosStr(const QuickString &str) { _endPosStr = str; } + virtual const string &getEndPosStr() const { return _endPosStr; } + virtual void setEndPosStr(const string &str) { _endPosStr = str; } virtual bool getZeroLength() const { return _zeroLength; } virtual void setZeroLength(bool val) { _zeroLength = val; } - virtual const QuickString &getStrand() const { return _strand; } - virtual void setStrand(const QuickString &val) { _strand = val; + virtual const string &getStrand() const { return _strand; } + virtual void setStrand(const string &val) { _strand = val; _strandVal = (val == "+" ? FORWARD : (val == "-" ? REVERSE : UNKNOWN)); } virtual void setStrand(char val) { _strand = val; @@ -79,17 +82,15 @@ public: virtual strandType getStrandVal() const {return _strandVal; } - virtual const QuickString &getName() const { return _name; } - virtual void setName(const QuickString &chr) { _name = chr; } - virtual void setName(const string &chr) { _name = chr; } + virtual const string &getName() const { return _name; } + virtual void setName(const string &name) { _name = name; } virtual void setName(const char *chr) { _name = chr; } - virtual const QuickString &getScore() const { return _score; } - virtual void setScore(const QuickString &chr) { _score = chr; } - virtual void setScore(const string &chr) { _score = chr; } + virtual const string &getScore() const { return _score; } + virtual void setScore(const string &score) { _score = score; } virtual void setScore(const char *chr) { _score = chr; } - virtual const QuickString &getField(int fieldNum) const; + virtual const string &getField(int fieldNum) const; virtual int getNumFields() const = 0; virtual FileRecordTypeChecker::RECORD_TYPE getType() const { return FileRecordTypeChecker::UNKNOWN_RECORD_TYPE; } @@ -110,7 +111,7 @@ public: // Bam record. bool isUnmapped() const { return _isUnmapped; } bool isMateUnmapped() const { return _isMateUnmapped; } - virtual void printUnmapped(QuickString &outBuf) const {} + virtual void printUnmapped(string &) const {} @@ -153,26 +154,32 @@ public: bool hasLeadingZeroInChromName(bool chrKnown = false) const; virtual int getLength(bool obeySplits) const; + void setFileRecordManager(FileRecordMgr *frm); + FileRecordMgr * getFileRecordManager(); + + vector block_starts; + vector block_ends; protected: - virtual ~Record(); //by making the destructor protected, only the friend class(es) can actually delete Record objects, or objects derived from Record. int _fileIdx; //associated file the record came from - QuickString _chrName; + string _chrName; int _chrId; int _startPos; int _endPos; //It is actually faster to also store the start and end positions as their original strings than to //have to convert their integer representations back to strings when printing them. - QuickString _startPosStr; - QuickString _endPosStr; - QuickString _name; - QuickString _score; - QuickString _strand; + string _startPosStr; + string _endPosStr; + string _name; + string _score; + string _strand; strandType _strandVal; bool _zeroLength; bool _isUnmapped; bool _isMateUnmapped; + bool _isValidHit; + FileRecordMgr *_frm; }; class RecordPtrSortAscFunctor { diff --git a/src/utils/FileRecordTools/Records/RecordKeyList.cpp b/src/utils/FileRecordTools/Records/RecordKeyList.cpp index 049bcdd..838f18a 100644 --- a/src/utils/FileRecordTools/Records/RecordKeyList.cpp +++ b/src/utils/FileRecordTools/Records/RecordKeyList.cpp @@ -5,12 +5,12 @@ RecordKeyList::RecordKeyList() { } -RecordKeyList::RecordKeyList(const Record * item) +RecordKeyList::RecordKeyList(Record * item) : _key(item) { } -RecordKeyList::RecordKeyList(const Record * item, const listType &list) +RecordKeyList::RecordKeyList(Record * item, listType &list) : _key(item) { _list = list; @@ -19,7 +19,7 @@ RecordKeyList::RecordKeyList(const Record * item, const listType &list) RecordKeyList::~RecordKeyList() { } -const RecordKeyList &RecordKeyList::operator=(const RecordKeyList &other) +RecordKeyList &RecordKeyList::operator=(RecordKeyList &other) { setKey(other._key); _list = other._list; @@ -51,7 +51,7 @@ void RecordKeyList::push_back(elemType item) { _list.push_back(item); } -const Record *RecordKeyList::getKey() const { +Record *RecordKeyList::getKey() const { return _key; } diff --git a/src/utils/FileRecordTools/Records/RecordKeyList.h b/src/utils/FileRecordTools/Records/RecordKeyList.h index b3d94f2..de2af22 100644 --- a/src/utils/FileRecordTools/Records/RecordKeyList.h +++ b/src/utils/FileRecordTools/Records/RecordKeyList.h @@ -13,15 +13,15 @@ class RecordKeyList { public: - typedef const Record * elemType; + typedef Record * elemType; typedef RecordList listType; typedef const RecordListNode *const_iterator_type; RecordKeyList(); RecordKeyList(elemType item); - RecordKeyList(elemType item, const listType &list); + RecordKeyList(elemType item, listType &list); ~RecordKeyList(); - const RecordKeyList &operator=(const RecordKeyList &other); + RecordKeyList &operator=(RecordKeyList &other); const_iterator_type begin(); const_iterator_type next(); const_iterator_type end(); diff --git a/src/utils/FileRecordTools/Records/RecordKeyVector.cpp b/src/utils/FileRecordTools/Records/RecordKeyVector.cpp index bb3837c..2b75846 100644 --- a/src/utils/FileRecordTools/Records/RecordKeyVector.cpp +++ b/src/utils/FileRecordTools/Records/RecordKeyVector.cpp @@ -17,7 +17,7 @@ RecordKeyVector::RecordKeyVector() _mustDeleteVec = true; } -RecordKeyVector::RecordKeyVector(const Record * item) +RecordKeyVector::RecordKeyVector(Record * item) : _key(item), _currPos(0) { @@ -25,7 +25,7 @@ RecordKeyVector::RecordKeyVector(const Record * item) _mustDeleteVec = true; } -RecordKeyVector::RecordKeyVector(const Record * item, const vecType *vec) +RecordKeyVector::RecordKeyVector(Record * item, vecType *vec) : _key(item), _currPos(0) { @@ -33,8 +33,10 @@ RecordKeyVector::RecordKeyVector(const Record * item, const vecType *vec) _mustDeleteVec = true; } -RecordKeyVector::~RecordKeyVector() { - if (_mustDeleteVec) { +RecordKeyVector::~RecordKeyVector() +{ + if (_mustDeleteVec) + { delete _recVec; _recVec = NULL; _mustDeleteVec = false; @@ -48,21 +50,27 @@ const RecordKeyVector &RecordKeyVector::operator=(const RecordKeyVector &other) return *this; } -RecordKeyVector::const_iterator_type RecordKeyVector::begin() { +RecordKeyVector::iterator_type RecordKeyVector::begin() { _currPos = 0; return _recVec->begin(); } -RecordKeyVector::const_iterator_type RecordKeyVector::next() { +RecordKeyVector::iterator_type RecordKeyVector::next() { _currPos++; return _recVec->begin() + _currPos; } -RecordKeyVector::const_iterator_type RecordKeyVector::end() { +RecordKeyVector::iterator_type RecordKeyVector::end() { return _recVec->end(); } +void RecordKeyVector::erase() +{ + delete _recVec->at(_currPos); + _recVec->erase (_recVec->begin() + _currPos); +} + size_t RecordKeyVector::size() const { return _recVec->size(); } @@ -75,7 +83,7 @@ void RecordKeyVector::push_back(elemType item) { _recVec->push_back(item); } -const Record *RecordKeyVector::getKey() const { +Record * RecordKeyVector::getKey() const { return _key; } @@ -90,6 +98,10 @@ void RecordKeyVector::setVector(vecType *vec) { void RecordKeyVector::clearVector() { _currPos = 0; + //for (vecType::iterator it = _recVec->begin() ; it != _recVec->end(); ++it) + //{ + // delete *it; + //} _recVec->clear(); } diff --git a/src/utils/FileRecordTools/Records/RecordKeyVector.h b/src/utils/FileRecordTools/Records/RecordKeyVector.h index 36ef1db..f41511b 100644 --- a/src/utils/FileRecordTools/Records/RecordKeyVector.h +++ b/src/utils/FileRecordTools/Records/RecordKeyVector.h @@ -17,18 +17,19 @@ using namespace std; class RecordKeyVector { public: - typedef const Record * elemType; - typedef vector vecType; - typedef vecType::const_iterator const_iterator_type; + typedef Record * elemType; + typedef vector vecType; + typedef vecType::iterator iterator_type; RecordKeyVector(); RecordKeyVector(elemType item); - RecordKeyVector(elemType item, const vecType *vector); + RecordKeyVector(elemType item, vecType *vector); ~RecordKeyVector(); const RecordKeyVector &operator=(const RecordKeyVector &other); - const_iterator_type begin(); - const_iterator_type next(); - const_iterator_type end(); + iterator_type begin(); + iterator_type next(); + iterator_type end(); + void erase(); size_t size() const ; bool empty() const ; //only checks whether list is empty. Doesn't check key. void push_back(elemType item); diff --git a/src/utils/FileRecordTools/Records/RecordList.cpp b/src/utils/FileRecordTools/Records/RecordList.cpp index 142706f..fc0a0fe 100644 --- a/src/utils/FileRecordTools/Records/RecordList.cpp +++ b/src/utils/FileRecordTools/Records/RecordList.cpp @@ -73,7 +73,7 @@ RecordListNode *RecordList::deleteCurrent() { return returnNode; } -void RecordList::push_back(const Record * &val) { +void RecordList::push_back(Record * &val) { RecordListNode *newNode = new RecordListNode(val); if (empty()) { _begin = newNode; @@ -89,6 +89,7 @@ void RecordList::push_back(const Record * &val) { void RecordList::clear() { + _size = 0; if (_dontDelete) { return; } @@ -105,7 +106,7 @@ void RecordList::clear() { _size = 0; } -const RecordList &RecordList::operator=(const RecordList &other) { +RecordList &RecordList::operator=(const RecordList &other) { //need to make copies of all nodes and assign values clear(); diff --git a/src/utils/FileRecordTools/Records/RecordList.h b/src/utils/FileRecordTools/Records/RecordList.h index e1b24b5..859fab4 100644 --- a/src/utils/FileRecordTools/Records/RecordList.h +++ b/src/utils/FileRecordTools/Records/RecordList.h @@ -26,7 +26,7 @@ #include "FreeList.h" -#include "QuickString.h" +#include "string.h" #include //for memset #include "Record.h" @@ -35,8 +35,8 @@ public: friend class RecordList; RecordListNode() : _next(NULL){} - RecordListNode(const Record * val) : _val(val), _next(NULL) {} - const Record * value() const { return _val; } + RecordListNode(Record * val) : _val(val), _next(NULL) {} + Record * value() const { return _val; } const RecordListNode *next() const { return _next; } RecordListNode *next() { return _next; } bool hasNext() const { return _next != NULL; } @@ -48,7 +48,7 @@ public: private: - const Record * _val; + Record * _val; RecordListNode *_next; }; @@ -76,10 +76,10 @@ public: const RecordListNode *end() const { return NULL; } RecordListNode * deleteCurrent(); - void push_back(const Record * &val); + void push_back(Record * &val); void clear(); - const RecordList &operator=(const RecordList &other); + RecordList &operator=(const RecordList &other); void assignNoCopy(RecordList &other); void sort() { mergeSort(&_begin); } diff --git a/src/utils/FileRecordTools/Records/VcfRecord.cpp b/src/utils/FileRecordTools/Records/VcfRecord.cpp index e5bd914..6af2920 100644 --- a/src/utils/FileRecordTools/Records/VcfRecord.cpp +++ b/src/utils/FileRecordTools/Records/VcfRecord.cpp @@ -44,52 +44,53 @@ bool VcfRecord::initFromFile(SingleLineDelimTextFileReader *fileReader) void VcfRecord::clear() { BedPlusInterval::clear(); - _varRef.release(); - _varAlt.release(); + _varRef.clear(); + _varAlt.clear(); } -void VcfRecord::print(QuickString &outBuf) const { +void VcfRecord::print(string &outBuf) const { outBuf.append(_chrName); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_startPosStr); printOtherFields(outBuf); } -void VcfRecord::print(QuickString &outBuf, int start, int end) const { +void VcfRecord::print(string &outBuf, int start, int end) const { outBuf.append(_chrName); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_startPosStr); printOtherFields(outBuf); } -void VcfRecord::print(QuickString &outBuf, const QuickString & start, const QuickString & end) const { +void VcfRecord::print(string &outBuf, const string & start, const string & end) const { outBuf.append(_chrName); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_startPosStr); printOtherFields(outBuf); } -void VcfRecord::printNull(QuickString &outBuf) const { +void VcfRecord::printNull(string &outBuf) const { outBuf.append(".\t-1\t."); - for (int i= 2; i < _numPrintFields; i++) { + for (int i=3; i < _numPrintFields; i++) { outBuf.append("\t."); } } -void VcfRecord::printOtherFields(QuickString &outBuf) const { - outBuf.append('\t'); +void VcfRecord::printOtherFields(string &outBuf) const { + outBuf.append("\t"); outBuf.append(_name); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_varRef); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_varAlt); - outBuf.append('\t'); + outBuf.append("\t"); outBuf.append(_score); + outBuf.append("\t"); _plusFields.printFields(outBuf); } -const QuickString &VcfRecord::getField(int fieldNum) const +const string &VcfRecord::getField(int fieldNum) const { //a request for any of the first six fields will retrieve //chrom, start, name, varRef, varAlt, score, in that order. diff --git a/src/utils/FileRecordTools/Records/VcfRecord.h b/src/utils/FileRecordTools/Records/VcfRecord.h index c140b69..410c40a 100644 --- a/src/utils/FileRecordTools/Records/VcfRecord.h +++ b/src/utils/FileRecordTools/Records/VcfRecord.h @@ -19,22 +19,22 @@ public: VcfRecord() {} virtual bool initFromFile(SingleLineDelimTextFileReader *); virtual void clear(); - void print(QuickString &outBuf) const; - void print(QuickString &outBuf, int start, int end) const; - void print(QuickString &outBuf, const QuickString & start, const QuickString & end) const; - virtual void printNull(QuickString &outBuf) const; + void print(string &outBuf) const; + void print(string &outBuf, int start, int end) const; + void print(string &outBuf, const string & start, const string & end) const; + virtual void printNull(string &outBuf) const; virtual FileRecordTypeChecker::RECORD_TYPE getType() const { return FileRecordTypeChecker::VCF_RECORD_TYPE; } - virtual const QuickString &getField(int fieldNum) const; + virtual const string &getField(int fieldNum) const; static bool isNumericField(int fieldNum); virtual bool isZeroBased() const {return false;}; protected: - QuickString _varRef; - QuickString _varAlt; + string _varRef; + string _varAlt; static const int numFixedFields = 6; - void printOtherFields(QuickString &outBuf) const; + void printOtherFields(string &outBuf) const; }; #endif /* VCFRECORD_H_ */ diff --git a/src/utils/GenomeFile/NewGenomeFile.cpp b/src/utils/GenomeFile/NewGenomeFile.cpp index 53c9540..9ddbc20 100644 --- a/src/utils/GenomeFile/NewGenomeFile.cpp +++ b/src/utils/GenomeFile/NewGenomeFile.cpp @@ -13,7 +13,7 @@ #include "ParseTools.h" #include "Tokenizer.h" -NewGenomeFile::NewGenomeFile(const QuickString &genomeFilename) +NewGenomeFile::NewGenomeFile(const string &genomeFilename) : _maxId(-1) { _genomeFileName = genomeFilename; @@ -25,7 +25,7 @@ NewGenomeFile::NewGenomeFile(const BamTools::RefVector &refVector) { size_t i = 0; for (; i < refVector.size(); ++i) { - QuickString chrom = refVector[i].RefName; + string chrom = refVector[i].RefName; CHRPOS length = refVector[i].RefLength; _maxId++; _chromSizeIds[chrom] = pair(length, _maxId); @@ -89,7 +89,7 @@ void NewGenomeFile::loadGenomeFileIntoMap() { genFile.close(); } -bool NewGenomeFile::projectOnGenome(CHRPOS genome_pos, QuickString &chrom, CHRPOS &start) { +bool NewGenomeFile::projectOnGenome(CHRPOS genome_pos, string &chrom, CHRPOS &start) { // search for the chrom that the position belongs on. // add 1 to genome position b/c of zero-based, half open. vector::const_iterator low = @@ -106,7 +106,7 @@ bool NewGenomeFile::projectOnGenome(CHRPOS genome_pos, QuickString &chrom, CHRPO return true; } -CHRPOS NewGenomeFile::getChromSize(const QuickString &chrom) { +CHRPOS NewGenomeFile::getChromSize(const string &chrom) { if (chrom == _currChromName) { return _currChromSize; } @@ -121,7 +121,7 @@ CHRPOS NewGenomeFile::getChromSize(const QuickString &chrom) { return INT_MAX; } -CHRPOS NewGenomeFile::getChromSize(const QuickString &chrom) const { +CHRPOS NewGenomeFile::getChromSize(const string &chrom) const { if (chrom == _currChromName) { return _currChromSize; } @@ -133,7 +133,7 @@ CHRPOS NewGenomeFile::getChromSize(const QuickString &chrom) const { return INT_MAX; } -CHRPOS NewGenomeFile::getChromId(const QuickString &chrom) { +CHRPOS NewGenomeFile::getChromId(const string &chrom) { if (chrom == _currChromName) { return _currChromId; } diff --git a/src/utils/GenomeFile/NewGenomeFile.h b/src/utils/GenomeFile/NewGenomeFile.h index 6d45fae..7d0a6c1 100644 --- a/src/utils/GenomeFile/NewGenomeFile.h +++ b/src/utils/GenomeFile/NewGenomeFile.h @@ -25,32 +25,32 @@ class NewGenomeFile { public: - NewGenomeFile(const QuickString &genomeFileName); + NewGenomeFile(const string &genomeFileName); NewGenomeFile(const BamTools::RefVector &genome); ~NewGenomeFile(void); // load a GENOME file into a map keyed by chrom. value is a pair of id and size. void loadGenomeFileIntoMap(); - bool projectOnGenome(CHRPOS genome_pos, QuickString &chrom, CHRPOS &start); + bool projectOnGenome(CHRPOS genome_pos, string &chrom, CHRPOS &start); CHRPOS getGenomeSize(void) const { return _genomeLength; } // return the total size of the genome - CHRPOS getChromSize(const QuickString &chrom); // return the size of a chromosome - CHRPOS getChromSize(const QuickString &chrom) const; // return the size of a chromosome - CHRPOS getChromId(const QuickString &chrom); // return chromosome's sort order - const vector &getChromList() const { return _chromList; } // return a list of chrom names + CHRPOS getChromSize(const string &chrom); // return the size of a chromosome + CHRPOS getChromSize(const string &chrom) const; // return the size of a chromosome + CHRPOS getChromId(const string &chrom); // return chromosome's sort order + const vector &getChromList() const { return _chromList; } // return a list of chrom names CHRPOS getNumberOfChroms() const { return _chromList.size() -1; }//the -1 excludes the blank chrom added for unmapped reads - const QuickString &getGenomeFileName() const { return _genomeFileName; } - bool hasChrom(const QuickString &chrom) const { return _chromSizeIds.find(chrom) != _chromSizeIds.end(); } + const string &getGenomeFileName() const { return _genomeFileName; } + bool hasChrom(const string &chrom) const { return _chromSizeIds.find(chrom) != _chromSizeIds.end(); } private: - QuickString _genomeFileName; - typedef map > lookupType; + string _genomeFileName; + typedef map > lookupType; lookupType _chromSizeIds; - vector _chromList; + vector _chromList; int _maxId; // projecting chroms onto a single coordinate system @@ -58,7 +58,7 @@ private: vector _startOffsets; //cache members for quick lookup - QuickString _currChromName; + string _currChromName; CHRPOS _currChromSize; int _currChromId; diff --git a/src/utils/KeyListOps/KeyListOps.cpp b/src/utils/KeyListOps/KeyListOps.cpp index 8e184c8..c329062 100644 --- a/src/utils/KeyListOps/KeyListOps.cpp +++ b/src/utils/KeyListOps/KeyListOps.cpp @@ -74,14 +74,14 @@ bool KeyListOps::isNumericOp(OP_TYPES op) const { return (iter == _isNumericOp.end() ? false : iter->second); } -bool KeyListOps::isNumericOp(const QuickString &op) const { +bool KeyListOps::isNumericOp(const string &op) const { return isNumericOp(getOpCode(op)); } -KeyListOps::OP_TYPES KeyListOps::getOpCode(const QuickString &operation) const { +KeyListOps::OP_TYPES KeyListOps::getOpCode(const string &operation) const { //If the operation does not exist, return INVALID. //otherwise, return code for given operation. - map::const_iterator iter = _opCodes.find(operation); + map::const_iterator iter = _opCodes.find(operation); if (iter == _opCodes.end()) { return INVALID; } @@ -132,7 +132,7 @@ bool KeyListOps::isValidColumnOps(FileRecordMgr *dbFile) { << dbFile->getFileName() << " only has fields 1 - " << dbFile->getNumFields() << "." << endl; return false; } - const QuickString &operation = opsTokens.getElem(numOps > 1 ? i : 0); + const string &operation = opsTokens.getElem(numOps > 1 ? i : 0); OP_TYPES opCode = getOpCode(operation); if (opCode == INVALID) { cerr << endl << "*****" << endl @@ -160,7 +160,7 @@ bool KeyListOps::isValidColumnOps(FileRecordMgr *dbFile) { return true; } -const QuickString & KeyListOps::getOpVals(RecordKeyVector &hits) +const string & KeyListOps::getOpVals(RecordKeyVector &hits) { //loop through all requested columns, and for each one, call the method needed //for the operation specified. @@ -168,6 +168,7 @@ const QuickString & KeyListOps::getOpVals(RecordKeyVector &hits) _outVals.clear(); double val = 0.0; for (int i=0; i < (int)_colOps.size(); i++) { + ostringstream s; int col = _colOps[i].first; OP_TYPES opCode = _colOps[i].second; @@ -176,138 +177,138 @@ const QuickString & KeyListOps::getOpVals(RecordKeyVector &hits) case SUM: val = _methods.getSum(); if (isnan(val)) { - _outVals.append(_methods.getNullValue()); + s << _methods.getNullValue(); } else { - _outVals.append(format(val)); + s << format(val); } break; case MEAN: val = _methods.getMean(); if (isnan(val)) { - _outVals.append(_methods.getNullValue()); + s << _methods.getNullValue(); } else { - _outVals.append(format(val)); + s << format(val); } break; case STDDEV: val = _methods.getStddev(); if (isnan(val)) { - _outVals.append(_methods.getNullValue()); + s << _methods.getNullValue(); } else { - _outVals.append(format(val)); + s << format(val); } break; case SAMPLE_STDDEV: val = _methods.getSampleStddev(); if (isnan(val)) { - _outVals.append(_methods.getNullValue()); + s << _methods.getNullValue(); } else { - _outVals.append(format(val)); + s << format(val); } break; case MEDIAN: val = _methods.getMedian(); if (isnan(val)) { - _outVals.append(_methods.getNullValue()); + s << _methods.getNullValue(); } else { - _outVals.append(format(val)); + s << format(val); } break; case MODE: - _outVals.append(_methods.getMode()); + s << _methods.getMode(); break; case ANTIMODE: - _outVals.append(_methods.getAntiMode()); + s << _methods.getAntiMode(); break; case MIN: val = _methods.getMin(); if (isnan(val)) { - _outVals.append(_methods.getNullValue()); + s << _methods.getNullValue(); } else { - _outVals.append(format(val)); + s << format(val); } break; case MAX: val = _methods.getMax(); if (isnan(val)) { - _outVals.append(_methods.getNullValue()); + s << _methods.getNullValue(); } else { - _outVals.append(format(val)); + s << format(val); } break; case ABSMIN: val = _methods.getAbsMin(); if (isnan(val)) { - _outVals.append(_methods.getNullValue()); + s << _methods.getNullValue(); } else { - _outVals.append(format(val)); + s << format(val); } break; case ABSMAX: val = _methods.getAbsMax(); if (isnan(val)) { - _outVals.append(_methods.getNullValue()); + s << _methods.getNullValue(); } else { - _outVals.append(format(val)); + s << format(val); } break; case COUNT: - _outVals.append(_methods.getCount()); + s << _methods.getCount(); break; case DISTINCT: - _outVals.append(_methods.getDistinct()); + s << _methods.getDistinct(); break; case DISTINCT_SORT_NUM: - _outVals.append(_methods.getDistinctSortNum()); + s << _methods.getDistinctSortNum(); break; case DISTINCT_SORT_NUM_DESC: - _outVals.append(_methods.getDistinctSortNum(false)); + s << _methods.getDistinctSortNum(false); break; case COUNT_DISTINCT: - _outVals.append(_methods.getCountDistinct()); + s << _methods.getCountDistinct(); break; case DISTINCT_ONLY: - _outVals.append(_methods.getDistinctOnly()); + s << _methods.getDistinctOnly(); break; case COLLAPSE: - _outVals.append(_methods.getCollapse()); + s << _methods.getCollapse(); break; case CONCAT: - _outVals.append(_methods.getConcat()); + s << _methods.getConcat(); break; case FREQ_ASC: - _outVals.append(_methods.getFreqAsc()); + s << _methods.getFreqAsc(); break; case FREQ_DESC: - _outVals.append(_methods.getFreqDesc()); + s << _methods.getFreqDesc(); break; case FIRST: - _outVals.append(_methods.getFirst()); + s << _methods.getFirst(); break; case LAST: - _outVals.append(_methods.getLast()); + s << _methods.getLast(); break; case INVALID: @@ -318,9 +319,10 @@ const QuickString & KeyListOps::getOpVals(RecordKeyVector &hits) cerr << "ERROR: Invalid operation given for column " << col << ". Exiting..." << endl; break; } + _outVals.append(s.str()); //if this isn't the last column, add a tab. if (i < (int)_colOps.size() -1) { - _outVals.append('\t'); + _outVals.append("\t"); } } if (_methods.nonNumErrFlagSet()) { @@ -331,7 +333,7 @@ const QuickString & KeyListOps::getOpVals(RecordKeyVector &hits) return _outVals; } -const QuickString &KeyListOps::format(double val) +const string &KeyListOps::format(double val) { std::stringstream strmBuf; strmBuf << std::setprecision (_precision) << val; diff --git a/src/utils/KeyListOps/KeyListOps.h b/src/utils/KeyListOps/KeyListOps.h index b6d4949..3e899e5 100644 --- a/src/utils/KeyListOps/KeyListOps.h +++ b/src/utils/KeyListOps/KeyListOps.h @@ -21,24 +21,24 @@ public: KeyListOps(); - void setColumns(const QuickString &columns) { _columns = columns; } - void addColumns(const QuickString &newCols) { + void setColumns(const string &columns) { _columns = columns; } + void addColumns(const string &newCols) { if (!_columns.empty()) _columns += ","; _columns += newCols; } - void setOperations(const QuickString & operation) { _operations = operation; } - void addOperations(const QuickString &newOps) { + void setOperations(const string & operation) { _operations = operation; } + void addOperations(const string &newOps) { if (!_operations.empty()) _operations += ","; _operations += newOps; } - void setNullValue(const QuickString & nullValue) { _methods.setNullValue(nullValue); } - void setDelimStr(const QuickString & delimStr) { _methods.setDelimStr(delimStr); } + void setNullValue(const string & nullValue) { _methods.setNullValue(nullValue); } + void setDelimStr(const string & delimStr) { _methods.setDelimStr(delimStr); } - const QuickString &getColumns() { return _columns; } - const QuickString &getOperations() { return _operations; } - const QuickString &getNullValue() { return _methods.getNullValue(); } - const QuickString &getDelimStr() { return _methods.getDelimStr(); } + const string &getColumns() { return _columns; } + const string &getOperations() { return _operations; } + const string &getNullValue() { return _methods.getNullValue(); } + const string &getDelimStr() { return _methods.getDelimStr(); } void setKeyList(RecordKeyVector *keyList) { _methods.setKeyList(keyList); } @@ -48,32 +48,32 @@ public: void setDBfileType(FileRecordTypeChecker::FILE_TYPE type) { _dbFileType = type; } bool isValidColumnOps(FileRecordMgr *dbFile); - const QuickString &getOpVals(RecordKeyVector &hits); + const string &getOpVals(RecordKeyVector &hits); void setPrecision(int val) { _precision = val; } private: void init(); FileRecordTypeChecker::FILE_TYPE _dbFileType; - QuickString _operations; - QuickString _columns; + string _operations; + string _columns; KeyListOpsMethods _methods; - map _opCodes; + map _opCodes; map _isNumericOp; typedef vector > colOpsType; colOpsType _colOps; - QuickString _outVals; + string _outVals; - QuickString _formatStr; + string _formatStr; int _precision; static const int DEFAULT_PRECISION = 10; - OP_TYPES getOpCode(const QuickString &operation) const; + OP_TYPES getOpCode(const string &operation) const; bool isNumericOp(OP_TYPES op) const; - bool isNumericOp(const QuickString &op) const; - const QuickString &format(double val); + bool isNumericOp(const string &op) const; + const string &format(double val); }; diff --git a/src/utils/KeyListOps/KeyListOpsMethods.cpp b/src/utils/KeyListOps/KeyListOpsMethods.cpp index f46f76e..6bb3a35 100644 --- a/src/utils/KeyListOps/KeyListOpsMethods.cpp +++ b/src/utils/KeyListOps/KeyListOpsMethods.cpp @@ -8,6 +8,7 @@ #include "KeyListOpsMethods.h" #include #include +#include #include "ParseTools.h" //to get the isNumeric function KeyListOpsMethods::KeyListOpsMethods() @@ -100,7 +101,7 @@ double KeyListOpsMethods::getMedian() { } // return the most common value in the vector -const QuickString &KeyListOpsMethods::getMode() { +const string &KeyListOpsMethods::getMode() { if (empty()) return _nullVal; makeFreqMap(); @@ -118,7 +119,7 @@ const QuickString &KeyListOpsMethods::getMode() { return _retStr; } // return the least common value in the vector -const QuickString &KeyListOpsMethods::getAntiMode() { +const string &KeyListOpsMethods::getAntiMode() { if (empty()) return _nullVal; makeFreqMap(); @@ -190,7 +191,7 @@ uint32_t KeyListOpsMethods::getCount() { return _keyList->size(); } // return a delimited list of the unique elements -const QuickString &KeyListOpsMethods::getDistinct() { +const string &KeyListOpsMethods::getDistinct() { if (empty()) return _nullVal; // separated list of unique values. If something repeats, only report once. makeFreqMap(); @@ -202,7 +203,7 @@ const QuickString &KeyListOpsMethods::getDistinct() { return _retStr; } -const QuickString &KeyListOpsMethods::getDistinctOnly() { +const string &KeyListOpsMethods::getDistinctOnly() { if (empty()) return _nullVal; // separated list of unique values. If something repeats, don't report. makeFreqMap(); @@ -215,15 +216,17 @@ const QuickString &KeyListOpsMethods::getDistinctOnly() { return _retStr; } -const QuickString &KeyListOpsMethods::getDistinctSortNum(bool asc) { +const string &KeyListOpsMethods::getDistinctSortNum(bool asc) { toArray(true, asc ? ASC : DESC); vector::iterator endIter = std::unique(_numArray.begin(), _numArray.end()); _retStr.clear(); + ostringstream s; for (vector::iterator iter = _numArray.begin(); iter != endIter; iter++) { if (iter != _numArray.begin()) _retStr += _delimStr; - _retStr.append(*iter); + s << *iter; } + _retStr.append(s.str()); return _retStr; } @@ -238,7 +241,7 @@ uint32_t KeyListOpsMethods::getCountDistinct() { } // return a delimiter-separated list of elements -const QuickString &KeyListOpsMethods::getCollapse(const QuickString &delimiter) { +const string &KeyListOpsMethods::getCollapse(const string &delimiter) { if (empty()) return _nullVal; //just put all items in one big separated list. @@ -253,13 +256,13 @@ const QuickString &KeyListOpsMethods::getCollapse(const QuickString &delimiter) } // return a concatenation of all elements in the vector -const QuickString &KeyListOpsMethods::getConcat() { +const string &KeyListOpsMethods::getConcat() { if (empty()) return _nullVal; //like collapse but w/o commas. Just a true concat of all vals. //just swap out the delimChar with '' and call collapse, then //restore the delimChar. - QuickString oldDelimStr(_delimStr); + string oldDelimStr(_delimStr); _delimStr = ""; getCollapse(); //this will store it's results in the _retStr method. _delimStr = oldDelimStr; @@ -267,7 +270,7 @@ const QuickString &KeyListOpsMethods::getConcat() { } // return a histogram of values and their freqs. in desc. order of frequency -const QuickString &KeyListOpsMethods::getFreqDesc() { +const string &KeyListOpsMethods::getFreqDesc() { if (empty()) return _nullVal; //for each uniq val, report # occurances, in desc order. @@ -275,20 +278,22 @@ const QuickString &KeyListOpsMethods::getFreqDesc() { //put freq map into multimap where key is the freq and val is the item. In other words, basically a reverse freq map. histDescType hist; for (; _freqIter != _freqMap.end(); _freqIter++) { - hist.insert(pair(_freqIter->second, _freqIter->first)); + hist.insert(pair(_freqIter->second, _freqIter->first)); } //now iterate through the reverse map we just made and output it's pairs in val:key format. _retStr.clear(); + ostringstream s; for (histDescType::iterator histIter = hist.begin(); histIter != hist.end(); histIter++) { if (histIter != hist.begin()) _retStr += _delimStr; - _retStr.append(histIter->second); - _retStr += ":"; - _retStr.append(histIter->first); + s << histIter->second; + s << ":"; + s << histIter->first; } + _retStr.append(s.str()); return _retStr; } // return a histogram of values and their freqs. in asc. order of frequency -const QuickString &KeyListOpsMethods::getFreqAsc() { +const string &KeyListOpsMethods::getFreqAsc() { if (empty()) return _nullVal; //for each uniq val, report # occurances, in asc order. @@ -296,21 +301,23 @@ const QuickString &KeyListOpsMethods::getFreqAsc() { //put freq map into multimap where key is the freq and val is the item. In other words, basically a reverse freq map. histAscType hist; for (; _freqIter != _freqMap.end(); _freqIter++) { - hist.insert(pair(_freqIter->second, _freqIter->first)); + hist.insert(pair(_freqIter->second, _freqIter->first)); // hist[*(_freqIter->second)] = _freqIter->first; } //now iterate through the reverse map we just made and output it's pairs in val:key format. _retStr.clear(); + ostringstream s; for (histAscType::iterator histIter = hist.begin(); histIter != hist.end(); histIter++) { if (histIter != hist.begin()) _retStr += _delimStr; - _retStr.append(histIter->second); - _retStr += ":"; - _retStr.append(histIter->first); + s << histIter->second; + s << ":"; + s << histIter->first; } + _retStr.append(s.str()); return _retStr; } // return the first value in the list -const QuickString &KeyListOpsMethods::getFirst() { +const string &KeyListOpsMethods::getFirst() { if (empty()) return _nullVal; //just the first item. @@ -318,7 +325,7 @@ const QuickString &KeyListOpsMethods::getFirst() { return getColVal(); } // return the last value in the list -const QuickString &KeyListOpsMethods::getLast() { +const string &KeyListOpsMethods::getLast() { if (empty()) return _nullVal; //just the last item. @@ -329,21 +336,23 @@ const QuickString &KeyListOpsMethods::getLast() { return getColVal(); } -const QuickString &KeyListOpsMethods::getColVal() { - const QuickString &retVal = (*_iter)->getField(_column); +const string &KeyListOpsMethods::getColVal() { + const string &retVal = (*_iter)->getField(_column); if (_isBam && retVal.empty()) return _nullVal; return retVal; } double KeyListOpsMethods::getColValNum() { - const QuickString &strVal = (*_iter)->getField(_column); + const string &strVal = (*_iter)->getField(_column); if (!isNumeric(strVal)) { _nonNumErrFlag = true; + ostringstream s; _errMsg = " ***** WARNING: Non numeric value "; - _errMsg.append(strVal); - _errMsg.append(" in "); - _errMsg.append(_column); - _errMsg.append("."); + s << strVal; + s << " in "; + s << _column; + s << "."; + _errMsg.append(s.str()); return NAN; } return atof(strVal.c_str()); @@ -382,9 +391,9 @@ void KeyListOpsMethods::sortArray(bool useNum, bool ascOrder) } } else { if (ascOrder) { - sort(_qsArray.begin(), _qsArray.end(), less()); + sort(_qsArray.begin(), _qsArray.end(), less()); } else { - sort(_qsArray.begin(), _qsArray.end(), greater()); + sort(_qsArray.begin(), _qsArray.end(), greater()); } } } diff --git a/src/utils/KeyListOps/KeyListOpsMethods.h b/src/utils/KeyListOps/KeyListOpsMethods.h index 1d0c963..d1eea62 100644 --- a/src/utils/KeyListOps/KeyListOpsMethods.h +++ b/src/utils/KeyListOps/KeyListOpsMethods.h @@ -10,7 +10,7 @@ #include #include //for pair -#include "QuickString.h" +#include "string.h" #include #include "RecordKeyVector.h" @@ -25,10 +25,10 @@ public: void setIsBam(bool isBam) { _isBam = isBam; } void setKeyList(RecordKeyVector *keyList) { _keyList = keyList; } void setColumn(int col) { _column = col; } - void setNullValue(const QuickString & nullVal) { _nullVal = nullVal; } - const QuickString &getNullValue() const { return _nullVal; } - void setDelimStr(const QuickString &delimStr) { _delimStr = delimStr; } - const QuickString &getDelimStr() const { return _delimStr; } + void setNullValue(const string & nullVal) { _nullVal = nullVal; } + const string &getNullValue() const { return _nullVal; } + void setDelimStr(const string &delimStr) { _delimStr = delimStr; } + const string &getDelimStr() const { return _delimStr; } // return the total of the values in the vector double getSum(); @@ -41,9 +41,9 @@ public: // return the median value in the vector double getMedian(); // return the most common value in the vector - const QuickString &getMode(); + const string &getMode(); // return the least common value in the vector - const QuickString &getAntiMode(); + const string &getAntiMode(); // return the minimum element of the vector double getMin(); // return the maximum element of the vector @@ -57,29 +57,29 @@ public: // return a the count of _unique_ elements in the vector uint32_t getCountDistinct(); // return only those elements that occur once - const QuickString &getDistinctOnly(); + const string &getDistinctOnly(); // as distinct, but sorted numerically. - const QuickString &getDistinctSortNum(bool ascending = true); + const string &getDistinctSortNum(bool ascending = true); // as distinct, but sorted numerically, descending // return a delimiter-separated list of elements - const QuickString & getCollapse(const QuickString & delimiter = ","); + const string & getCollapse(const string & delimiter = ","); // return a concatenation of all elements in the vector - const QuickString & getConcat(); + const string & getConcat(); // return a comma-separated list of the _unique_ elements - const QuickString & getDistinct(); + const string & getDistinct(); // return a histogram of values and their freqs. in desc. order of frequency - const QuickString & getFreqDesc(); + const string & getFreqDesc(); // return a histogram of values and their freqs. in asc. order of frequency - const QuickString & getFreqAsc(); + const string & getFreqAsc(); // return the first value in the list - const QuickString & getFirst(); + const string & getFirst(); // return the last value in the list - const QuickString & getLast(); + const string & getLast(); bool nonNumErrFlagSet() const { return _nonNumErrFlag; } - const QuickString &getErrMsg() const { return _errMsg; } + const string &getErrMsg() const { return _errMsg; } void resetNonNumErrFlag() { _nonNumErrFlag = false; _errMsg.clear(); @@ -88,31 +88,31 @@ public: private: RecordKeyVector *_keyList; int _column; - QuickString _nullVal; - QuickString _delimStr; - QuickString _retStr; + string _nullVal; + string _delimStr; + string _retStr; RecordKeyVector _nullKeyList; //this has to exist just so we can initialize _iter, below. - RecordKeyVector::const_iterator_type _iter; + RecordKeyVector::iterator_type _iter; // Some methods need to put values into a vector, mostly for sorting. vector _numArray; - vector _qsArray; + vector _qsArray; - typedef map freqMapType; + typedef map freqMapType; freqMapType _freqMap; freqMapType::iterator _freqIter; typedef enum { UNSORTED, ASC, DESC} SORT_TYPE; bool _nonNumErrFlag; - QuickString _errMsg; + string _errMsg; bool _isBam; - typedef multimap > histAscType; - typedef multimap > histDescType; + typedef multimap > histAscType; + typedef multimap > histDescType; void init(); - const QuickString &getColVal(); + const string &getColVal(); double getColValNum(); bool empty() { return _keyList->empty(); } void begin() { _iter = _keyList->begin(); } diff --git a/src/utils/NewChromsweep/CloseSweep.cpp b/src/utils/NewChromsweep/CloseSweep.cpp index 171a87a..06c4d17 100644 --- a/src/utils/NewChromsweep/CloseSweep.cpp +++ b/src/utils/NewChromsweep/CloseSweep.cpp @@ -48,7 +48,7 @@ void RecDistList::clear() { _totalRecs = 0; } -bool RecDistList::addRec(int dist, const Record *record, chromDirType chromDir) { +bool RecDistList::addRec(int dist, Record *record, chromDirType chromDir) { int newPos = 0; bool mustAppend = false; int useElemIdx = 0; @@ -313,7 +313,7 @@ void CloseSweep::scanCache(int dbIdx, RecordKeyVector &retList) { recListIterType cacheIter = _caches[dbIdx].begin(); while (cacheIter != _caches[dbIdx].end()) { - const Record *cacheRec = cacheIter->value(); + Record *cacheRec = cacheIter->value(); bool stopScanning = false; if (considerRecord(cacheRec, dbIdx, stopScanning) == DELETE) { cacheIter = _caches[dbIdx].deleteCurrent(); @@ -326,7 +326,7 @@ void CloseSweep::scanCache(int dbIdx, RecordKeyVector &retList) { } -CloseSweep::rateOvlpType CloseSweep::considerRecord(const Record *cacheRec, int dbIdx, bool &stopScanning) { +CloseSweep::rateOvlpType CloseSweep::considerRecord(Record *cacheRec, int dbIdx, bool &stopScanning) { // Determine whether the hit and query intersect, and if so, what to do about it. _dbForward = cacheRec->getStrandVal() == Record::FORWARD; @@ -466,7 +466,7 @@ void CloseSweep::finalizeSelections(int dbIdx, RecordKeyVector &retList) { -int CloseSweep::addRecsToRetList(const RecDistList::elemsType *recs, int currDist, RecordKeyVector &retList) { +int CloseSweep::addRecsToRetList(RecDistList::elemsType *recs, int currDist, RecordKeyVector &retList) { int hitsUsed = 0; int numRecs = (int)recs->size(); //just to clean the code some. @@ -489,7 +489,7 @@ int CloseSweep::addRecsToRetList(const RecDistList::elemsType *recs, int currDis } } -void CloseSweep::addSingleRec(const Record *rec, int currDist, int &hitsUsed, RecordKeyVector &retList) { +void CloseSweep::addSingleRec(Record *rec, int currDist, int &hitsUsed, RecordKeyVector &retList) { retList.push_back(rec); _finalDistances.push_back(currDist); hitsUsed++; @@ -511,7 +511,7 @@ void CloseSweep::checkMultiDbs(RecordKeyVector &retList) { int numHits = (int)retList.size(); copyDists.resize(numHits); int i=0; - for (RecordKeyVector::const_iterator_type iter = retList.begin(); iter != retList.end(); iter++) { + for (RecordKeyVector::iterator_type iter = retList.begin(); iter != retList.end(); iter++) { int dist = _finalDistances[i]; copyDists[i]._dist = abs(dist); copyDists[i]._rec = *iter; @@ -575,7 +575,7 @@ void CloseSweep::checkMultiDbs(RecordKeyVector &retList) { bool CloseSweep::chromChange(int dbIdx, RecordKeyVector &retList, bool wantScan) { - const Record *dbRec = _currDbRecs[dbIdx]; + Record *dbRec = _currDbRecs[dbIdx]; bool haveQuery = _currQueryRec != NULL; bool haveDB = dbRec != NULL; @@ -615,14 +615,14 @@ bool CloseSweep::chromChange(int dbIdx, RecordKeyVector &retList, bool wantScan) // the query is ahead of the database. fast-forward the database to catch-up. if (queryChromAfterDbRec(dbRec)) { - QuickString oldDbChrom(dbRec->getChrName()); + string oldDbChrom(dbRec->getChrName()); while (dbRec != NULL && queryChromAfterDbRec(dbRec)) { _dbFRMs[dbIdx]->deleteRecord(dbRec); if (!nextRecord(false, dbIdx)) break; dbRec = _currDbRecs[dbIdx]; - const QuickString &newDbChrom = dbRec->getChrName(); + const string &newDbChrom = dbRec->getChrName(); if (newDbChrom != oldDbChrom) { testChromOrder(dbRec); oldDbChrom = newDbChrom; @@ -683,7 +683,7 @@ void CloseSweep::setLeftClosestEndPos(int dbIdx) } } -bool CloseSweep::beforeLeftClosestEndPos(int dbIdx, const Record *rec) +bool CloseSweep::beforeLeftClosestEndPos(int dbIdx, Record *rec) { int recEndPos = rec->getEndPos(); int prevPos = _maxPrevLeftClosestEndPos[dbIdx]; @@ -708,7 +708,7 @@ void CloseSweep::clearClosestEndPos(int dbIdx) _maxPrevLeftClosestEndPosReverse[dbIdx] = 0; } -CloseSweep::rateOvlpType CloseSweep::tryToAddRecord(const Record *cacheRec, int dist, int dbIdx, bool &stopScanning, chromDirType chromDir, streamDirType streamDir) { +CloseSweep::rateOvlpType CloseSweep::tryToAddRecord(Record *cacheRec, int dist, int dbIdx, bool &stopScanning, chromDirType chromDir, streamDirType streamDir) { // // Decide whether to ignore hit diff --git a/src/utils/NewChromsweep/CloseSweep.h b/src/utils/NewChromsweep/CloseSweep.h index 2627562..8165cbe 100644 --- a/src/utils/NewChromsweep/CloseSweep.h +++ b/src/utils/NewChromsweep/CloseSweep.h @@ -17,10 +17,10 @@ class distanceTuple { public: distanceTuple() : _dist(0), _rec(NULL), _isNeg(false) {} - distanceTuple(int dist, const Record *rec, bool isNeg = false) : _dist(dist), _rec(rec), _isNeg(isNeg) {} + distanceTuple(int dist, Record *rec, bool isNeg = false) : _dist(dist), _rec(rec), _isNeg(isNeg) {} // bool operator < (const distanceTuple & other) const { return (_dist < other._dist); } int _dist; - const Record *_rec; + Record *_rec; bool _isNeg; }; @@ -51,12 +51,12 @@ public: void clear(); int uniqueSize() const { return _currNumIdxs; } size_t totalSize() const { return _totalRecs; } - bool addRec(int dist, const Record *, chromDirType chromDir); + bool addRec(int dist, Record *, chromDirType chromDir); bool exists(int dist) const { int dummyVal = 0; return find(dist, dummyVal); } - typedef pair elemPairType; + typedef pair elemPairType; typedef vector elemsType; typedef pair indexType; @@ -66,12 +66,12 @@ public: constIterType end() const { return _currNumIdxs; } int currDist(constIterType iter) const { return _distIndex[iter].first; } size_t currNumElems(constIterType iter) const { return allElems(iter)->size(); } - const elemsType *allElems(constIterType iter) const { return _allRecs[_distIndex[iter].second]; } + elemsType *allElems(constIterType iter) const { return _allRecs[_distIndex[iter].second]; } int getMaxLeftEndPos() const; private: - void insert(int dist, const Record *, chromDirType chromDir); + void insert(int dist, Record *, chromDirType chromDir); //if true, pos will be the idx the distance is at. @@ -148,7 +148,7 @@ private: typedef enum { IGNORE, DELETE } rateOvlpType; - rateOvlpType considerRecord(const Record *cacheRec, int dbIdx, bool &stopScanning); + rateOvlpType considerRecord(Record *cacheRec, int dbIdx, bool &stopScanning); void finalizeSelections(int dbIdx, RecordKeyVector &retList); void checkMultiDbs(RecordKeyVector &retList); @@ -157,11 +157,11 @@ private: typedef enum { NEITHER, FORWARD_ONLY, REVERSE_ONLY, BOTH } purgeDirectionType; void setLeftClosestEndPos(int dbIdx); - bool beforeLeftClosestEndPos(int dbIdx, const Record *rec); + bool beforeLeftClosestEndPos(int dbIdx, Record *rec); void clearClosestEndPos(int dbIdx); - int addRecsToRetList(const RecDistList::elemsType *recs, int currDist, RecordKeyVector &retList); - void addSingleRec(const Record *rec, int currDist, int &hitsUsed, RecordKeyVector &retList); - rateOvlpType tryToAddRecord(const Record *cacheRec, int dist, int dbIdx, bool &stopScanning, chromDirType chromDir, streamDirType streamDir); + int addRecsToRetList(RecDistList::elemsType *recs, int currDist, RecordKeyVector &retList); + void addSingleRec(Record *rec, int currDist, int &hitsUsed, RecordKeyVector &retList); + rateOvlpType tryToAddRecord(Record *cacheRec, int dist, int dbIdx, bool &stopScanning, chromDirType chromDir, streamDirType streamDir); purgeDirectionType purgePointException(int dbIdx); }; diff --git a/src/utils/NewChromsweep/NewChromsweep.cpp b/src/utils/NewChromsweep/NewChromsweep.cpp index 9a8e375..76a68e1 100644 --- a/src/utils/NewChromsweep/NewChromsweep.cpp +++ b/src/utils/NewChromsweep/NewChromsweep.cpp @@ -121,16 +121,20 @@ void NewChromSweep::scanCache(int dbIdx, RecordKeyVector &retList) { recListIterType cacheIter = _caches[dbIdx].begin(); while (cacheIter != _caches[dbIdx].end()) { - const Record *cacheRec = cacheIter->value(); - if (_currQueryRec->sameChrom(cacheRec) && !_currQueryRec->after(cacheRec)) { - if (intersects(_currQueryRec, cacheRec)) { + Record *cacheRec = cacheIter->value(); + if (_currQueryRec->sameChrom(cacheRec) && !_currQueryRec->after(cacheRec)) + { + if (intersects(_currQueryRec, cacheRec)) + { retList.push_back(cacheRec); - } else if (cacheRec->after(_currQueryRec)) break; // cacheRec is after the query rec, stop scanning. + } + else if (cacheRec->after(_currQueryRec)) break; // cacheRec is after the query rec, stop scanning. cacheIter = _caches[dbIdx].next(); } - else { - cacheIter = _caches[dbIdx].deleteCurrent(); + else + { _dbFRMs[dbIdx]->deleteRecord(cacheRec); + cacheIter = _caches[dbIdx].deleteCurrent(); } } } @@ -139,7 +143,8 @@ void NewChromSweep::clearCache(int dbIdx) { //delete all objects pointed to by cache recListType &cache = _caches[dbIdx]; - for (recListIterType iter = cache.begin(); iter != cache.end(); iter = cache.next()) { + for (recListIterType iter = cache.begin(); iter != cache.end(); iter = cache.next()) + { _dbFRMs[dbIdx]->deleteRecord(iter->value()); } cache.clear(); @@ -147,10 +152,14 @@ void NewChromSweep::clearCache(int dbIdx) void NewChromSweep::masterScan(RecordKeyVector &retList) { - for (int i=0; i < _numDBs; i++) { - if (dbFinished(i) || chromChange(i, retList, true)) { + for (int i=0; i < _numDBs; i++) + { + if (dbFinished(i) || chromChange(i, retList, true)) + { continue; - } else { + } + else + { // scan the database cache for hits scanCache(i, retList); @@ -198,13 +207,13 @@ bool NewChromSweep::chromChange(int dbIdx, RecordKeyVector &retList, bool wantSc if (queryChromAfterDbRec(dbRec)) { // the query is ahead of the database. fast-forward the database to catch-up. - QuickString oldDbChrom(dbRec->getChrName()); - while (dbRec != NULL && - queryChromAfterDbRec(dbRec)) { - _dbFRMs[dbIdx]->deleteRecord(dbRec); + string oldDbChrom(dbRec->getChrName()); + while (dbRec != NULL && queryChromAfterDbRec(dbRec)) + { + _dbFRMs[dbIdx]->deleteRecord(dbRec); if (!nextRecord(false, dbIdx)) break; dbRec = _currDbRecs[dbIdx]; - const QuickString &newDbChrom = dbRec->getChrName(); + const string &newDbChrom = dbRec->getChrName(); if (newDbChrom != oldDbChrom) { testChromOrder(dbRec); oldDbChrom = newDbChrom; @@ -324,17 +333,17 @@ void NewChromSweep::testChromOrder(const Record *rec) int fileIdx = rec->getFileIdx(); - const QuickString &chrom = rec->getChrName(); + const string &chrom = rec->getChrName(); findChromOrder(rec); //determine what the previous chrom was for this file. - map::iterator prevIter = _filePrevChrom.find(fileIdx); + map::iterator prevIter = _filePrevChrom.find(fileIdx); if (prevIter == _filePrevChrom.end()) { _filePrevChrom[fileIdx] = chrom; return; //no previously stored chrom for this file. } - const QuickString prevChrom(prevIter->second); + const string prevChrom(prevIter->second); _filePrevChrom[fileIdx] = chrom; if (chrom == prevChrom) return; @@ -365,8 +374,8 @@ bool NewChromSweep::queryChromAfterDbRec(const Record *dbRec) return (_currQueryRec->getChromId() > dbRec->getChromId()) ; } //see if query has both - const QuickString &qChrom = _currQueryRec->getChrName(); - const QuickString &dbChrom = dbRec->getChrName(); + const string &qChrom = _currQueryRec->getChrName(); + const string &dbChrom = dbRec->getChrName(); const _orderTrackType *track = _fileTracks[_currQueryRec->getFileIdx()]; _orderTrackType::const_iterator iter = track->find(qChrom); @@ -385,7 +394,7 @@ bool NewChromSweep::queryChromAfterDbRec(const Record *dbRec) int NewChromSweep::findChromOrder(const Record *rec) { - const QuickString &chrom = rec->getChrName(); + const string &chrom = rec->getChrName(); int fileIdx = rec->getFileIdx(); _orderTrackType *track = _fileTracks[fileIdx]; @@ -393,14 +402,14 @@ int NewChromSweep::findChromOrder(const Record *rec) { if (iter == track->end()) { //chrom never seen before. Enter into map. int val = (int)track->size(); - track->insert(pair(chrom, val)); + track->insert(pair(chrom, val)); return val; } else { return iter->second; } } -bool NewChromSweep::verifyChromOrderMismatch(const QuickString & chrom, const QuickString &prevChrom, int skipFile) { +bool NewChromSweep::verifyChromOrderMismatch(const string & chrom, const string &prevChrom, int skipFile) { //for every file except the one being checked, //find the current and previous chrom. If a given file //is missing either, skip it and go on. If it has both, @@ -434,7 +443,7 @@ void NewChromSweep::testThatAllDbChromsExistInQuery() if (i == queryIdx) continue; const _orderTrackType *dbTrack = _fileTracks[i]; for (_orderTrackType::const_iterator iter = dbTrack->begin(); iter != dbTrack->end(); iter++) { - const QuickString &chrom = iter->first; + const string &chrom = iter->first; if (qTrack->find(chrom) == qTrack->end() && !chrom.empty()) // don't raise an error if the chrom is unknown (e.g., unmapped BAM) { diff --git a/src/utils/NewChromsweep/NewChromsweep.h b/src/utils/NewChromsweep/NewChromsweep.h index dc7f0a0..18fb165 100644 --- a/src/utils/NewChromsweep/NewChromsweep.h +++ b/src/utils/NewChromsweep/NewChromsweep.h @@ -20,7 +20,7 @@ #include #include #include -#include "QuickString.h" +#include "string.h" using namespace std; @@ -83,12 +83,12 @@ protected: // recListType _hits; // the current query and db features. - const Record * _currQueryRec; - vector _currDbRecs; + Record * _currQueryRec; + vector _currDbRecs; // a cache of the current chrom from the query. used to handle chrom changes. - QuickString _currQueryChromName; - QuickString _prevQueryChromName; + string _currQueryChromName; + string _prevQueryChromName; bool _runToQueryEnd; @@ -113,19 +113,19 @@ protected: // sorted files without a genome file. // - typedef map _orderTrackType; + typedef map _orderTrackType; vector<_orderTrackType *> _fileTracks; - map _filePrevChrom; + map _filePrevChrom; bool _lexicoDisproven; //whether we've established that any file ISN'T in lexicographical order bool _lexicoAssumed; //whether we've had to try to guess that any file might be in lexicographical order. - QuickString _lexicoAssumedChromName; //which chromosome we had to make that guess for. Used in error reporting. + string _lexicoAssumedChromName; //which chromosome we had to make that guess for. Used in error reporting. int _lexicoAssumedFileIdx; //which file we had to make the guess for. Also for error reporting. bool _testLastQueryRec; void testChromOrder(const Record *rec); bool queryChromAfterDbRec(const Record *dbRec); int findChromOrder(const Record *rec); - bool verifyChromOrderMismatch(const QuickString & chrom, const QuickString &prevChrom, int skipFile); + bool verifyChromOrderMismatch(const string & chrom, const string &prevChrom, int skipFile); void testThatAllDbChromsExistInQuery(); bool testLexicoQueryAfterDb(const Record *queryRec, const Record *dbRec); diff --git a/src/utils/RecordOutputMgr/RecordOutputMgr.cpp b/src/utils/RecordOutputMgr/RecordOutputMgr.cpp index 58aba85..20a2aa8 100644 --- a/src/utils/RecordOutputMgr/RecordOutputMgr.cpp +++ b/src/utils/RecordOutputMgr/RecordOutputMgr.cpp @@ -125,13 +125,13 @@ RecordOutputMgr::printBamType RecordOutputMgr::printBamRecord(RecordKeyVector &k return NOT_BAM; } -void RecordOutputMgr::printRecord(const Record *record) +void RecordOutputMgr::printRecord(Record *record) { RecordKeyVector keyList(record); printRecord(keyList); } -void RecordOutputMgr::printRecord(const Record *record, const QuickString & value) +void RecordOutputMgr::printRecord(Record *record, const string & value) { checkForHeader(); @@ -158,7 +158,7 @@ void RecordOutputMgr::printClosest(RecordKeyVector &keyList, const vector * const ContextClosest *context = static_cast(_context); bool deleteBlocks = false; - const Record *keyRec = keyList.getKey(); + Record *keyRec = keyList.getKey(); RecordKeyVector blockList(keyRec); if (keyRec->getType() == FileRecordTypeChecker::BAM_RECORD_TYPE) { _bamBlockMgr->getBlocks(blockList, deleteBlocks); @@ -166,7 +166,7 @@ void RecordOutputMgr::printClosest(RecordKeyVector &keyList, const vector * } if (!keyList.empty()) { int distCount = 0; - for (RecordKeyVector::const_iterator_type iter = keyList.begin(); iter != keyList.end(); iter = keyList.next()) { + for (RecordKeyVector::iterator_type iter = keyList.begin(); iter != keyList.end(); iter = keyList.next()) { const Record *hitRec = *iter; printKey(keyRec, keyRec->getStartPosStr(), keyRec->getEndPosStr()); tab(); @@ -177,7 +177,9 @@ void RecordOutputMgr::printClosest(RecordKeyVector &keyList, const vector * int dist = (*dists)[distCount]; //if not using sign distance, use absolute value instead. dist = context->signDistance() ? dist : abs(dist); - _outBuf.append(dist); + ostringstream s; + s << dist; + _outBuf.append(s.str()); distCount++; } newline(); @@ -188,13 +190,14 @@ void RecordOutputMgr::printClosest(RecordKeyVector &keyList, const vector * tab(); // need to add a dummy file id if multiple DB files are used if (_context->getNumInputFiles() > 2) { - _outBuf.append('.'); + _outBuf.append("."); tab(); } null(false, true); if (context->reportDistance()) { tab(); - _outBuf.append(-1); + + _outBuf.append("-1"); } newline(); } @@ -249,12 +252,12 @@ void RecordOutputMgr::printRecord(RecordKeyVector &keyList, RecordKeyVector *blo tab(); // need to add a dummy file id if multiple DB files are used if (_context->getNumInputFiles() > 2) { - _outBuf.append('.'); + _outBuf.append("."); tab(); } null(false, true); tab(); - _outBuf.append('0'); + _outBuf.append("0"); newline(); if (needsFlush()) flush(); } @@ -269,7 +272,7 @@ void RecordOutputMgr::printRecord(RecordKeyVector &keyList, RecordKeyVector *blo tab(); // need to add a dummy file id if multiple DB files are used if (_context->getNumInputFiles() > 2) { - _outBuf.append('.'); + _outBuf.append("."); tab(); } null(false, true); @@ -279,7 +282,9 @@ void RecordOutputMgr::printRecord(RecordKeyVector &keyList, RecordKeyVector *blo return; } - } else { + } + else + { if (printBamRecord(keyList, true) == BAM_AS_BAM) { _currBamBlockList = NULL; @@ -287,9 +292,14 @@ void RecordOutputMgr::printRecord(RecordKeyVector &keyList, RecordKeyVector *blo return; } int hitIdx = 0; - for (RecordKeyVector::const_iterator_type iter = keyList.begin(); iter != keyList.end(); iter = keyList.next()) { - reportOverlapDetail(keyList.getKey(), *iter, hitIdx); - hitIdx++; + for (RecordKeyVector::iterator_type iter = keyList.begin(); iter != keyList.end(); iter = keyList.next()) + { + // a hit can be invalid if there was no enough overlap, etc. + //if ((*iter)->isValid()) + //{ + reportOverlapDetail(keyList.getKey(), *iter, hitIdx); + hitIdx++; + //} } } } else { // not printable @@ -315,9 +325,9 @@ void RecordOutputMgr::checkForHeader() { //If the tool is groupBy, and outheader was set, but the header is empty, we need to print groupBy's //default header if (_context->getProgram() == ContextBase::GROUP_BY) { - const QuickString &header = _context->getFile(0)->getHeader(); + const string &header = _context->getFile(0)->getHeader(); if (header.empty()) { - const QuickString &defaultHeader = (static_cast(_context))->getDefaultHeader(); + const string &defaultHeader = (static_cast(_context))->getDefaultHeader(); _outBuf.append(defaultHeader); } else { _outBuf.append(header); @@ -326,7 +336,7 @@ void RecordOutputMgr::checkForHeader() { //if the tool is based on intersection, we want the header from the query file. int queryIdx = (static_cast(_context))->getQueryFileIdx(); - const QuickString &header = _context->getFile(queryIdx)->getHeader(); + const string &header = _context->getFile(queryIdx)->getHeader(); _outBuf.append(header); } else { _outBuf.append(_context->getFile(0)->getHeader()); @@ -428,14 +438,16 @@ void RecordOutputMgr::reportOverlapSummary(RecordKeyVector &keyList) } void RecordOutputMgr::addDbFileId(int fileId) { + ostringstream s; if ((static_cast(_context))->getNumDatabaseFiles() == 1) return; if (!_context->getUseDBnameTags() && (!_context->getUseDBfileNames())) { - _outBuf.append(fileId); + s << fileId; } else if (_context->getUseDBnameTags()){ - _outBuf.append((static_cast(_context))->getDatabaseNameTag((static_cast(_context))->getDbIdx(fileId))); + s << (static_cast(_context))->getDatabaseNameTag((static_cast(_context))->getDbIdx(fileId)); } else { - _outBuf.append(_context->getInputFileName(fileId)); + s << _context->getInputFileName(fileId); } + _outBuf.append(s.str()); tab(); } @@ -502,7 +514,7 @@ void RecordOutputMgr::null(bool queryType, bool dbType) delete dummyRecord; } -void RecordOutputMgr::printKey(const Record *key, const QuickString & start, const QuickString & end) +void RecordOutputMgr::printKey(const Record *key, const string & start, const string & end) { if (key->getType() != FileRecordTypeChecker::BAM_RECORD_TYPE) { key->print(_outBuf, start, end); diff --git a/src/utils/RecordOutputMgr/RecordOutputMgr.h b/src/utils/RecordOutputMgr/RecordOutputMgr.h index 2639d9d..782c9d8 100644 --- a/src/utils/RecordOutputMgr/RecordOutputMgr.h +++ b/src/utils/RecordOutputMgr/RecordOutputMgr.h @@ -24,15 +24,15 @@ public: //The init method must be called after all the input files are open. void init(ContextBase *context); - void printRecord(const Record *record); + void printRecord(Record *record); void printRecord(RecordKeyVector &keyList); - void printRecord(const Record *record, const QuickString & value); + void printRecord(Record *record, const string & value); void checkForHeader(); void printClosest(RecordKeyVector &keyList, const vector *dists = NULL); - void tab() { _outBuf.append('\t'); } - void newline() { _outBuf.append('\n'); } + void tab() { _outBuf.append("\t"); } + void newline() { _outBuf.append("\n"); } private: typedef enum { NOT_BAM, BAM_AS_BAM, BAM_AS_BED} printBamType; @@ -42,16 +42,16 @@ private: BamTools::BamWriter *_bamWriter; RecordKeyVector *_currBamBlockList; - QuickString _outBuf; + string _outBuf; BlockMgr *_bamBlockMgr; - QuickString _afterVal; //to store values to be printed after record, such as column operations. + string _afterVal; //to store values to be printed after record, such as column operations. //some helper functions to neaten the code. void null(bool queryType, bool dbType); void printRecord(RecordKeyVector &keyList, RecordKeyVector *blockList); void printKey(const Record *key); - void printKey(const Record *key, const QuickString & start, const QuickString & end); + void printKey(const Record *key, const string & start, const string & end); void printKey(const Record *key, int start, int end); void addDbFileId(int fileId); bool printKeyAndTerminate(RecordKeyVector &keyList); diff --git a/src/utils/bedFile/bedFile.cpp b/src/utils/bedFile/bedFile.cpp index 0db7f07..9ce59d8 100644 --- a/src/utils/bedFile/bedFile.cpp +++ b/src/utils/bedFile/bedFile.cpp @@ -64,7 +64,10 @@ bool byChromThenStart(BED const &a, BED const &b) { return false; }; - +bool sortByWeight(const BED &a, const BED &b) { + if (a.weight > b.weight) return true; + else return false; +}; /******************************************* Class methods *******************************************/ @@ -767,3 +770,35 @@ void BedFile::loadBedFileIntoVector() { Close(); } +void BedFile::assignWeightsBasedOnSize() { + // sort by size + sort(bedList.begin(), bedList.end(), sortBySizeAsc); + // then assign a weight to each interval based on the + // proportion of the total interval length of the file + size_t totalSize = 0; + for (unsigned int i = 0; i < bedList.size(); ++i) + { + totalSize += bedList[i].size(); + } + double totalWeight = 0.0; + for (unsigned int i = 0; i < bedList.size(); ++i) + { + totalWeight += (double) bedList[i].size() / (double) totalSize; + bedList[i].weight = totalWeight; + } +} + +struct CompareByWeight { + bool operator()(double const val, BED const& bed) const + { + return bed.weight > val; + } +}; + +BED * BedFile::sizeWeightedSearch(double val) { + // binary search for first interval with weight greater than search val + vector::iterator up = upper_bound(bedList.begin(), bedList.end(), val, CompareByWeight()); + return &(*up); +} + + diff --git a/src/utils/bedFile/bedFile.h b/src/utils/bedFile/bedFile.h index 0ef508f..8e7e4c9 100644 --- a/src/utils/bedFile/bedFile.h +++ b/src/utils/bedFile/bedFile.h @@ -91,6 +91,7 @@ struct BED { vector other_idxs; // is this a zero length feature: i.e., start == end bool zeroLength; + double weight; public: // constructors @@ -105,7 +106,8 @@ public: strand(""), fields(), other_idxs(), - zeroLength(false) + zeroLength(false), + weight(0.0) {} // BED3 @@ -118,7 +120,8 @@ public: strand(""), fields(), other_idxs(), - zeroLength(false) + zeroLength(false), + weight(0.0) {} // BED4 @@ -131,7 +134,8 @@ public: strand(strand), fields(), other_idxs(), - zeroLength(false) + zeroLength(false), + weight(0.0) {} // BED6 @@ -145,7 +149,8 @@ public: strand(strand), fields(), other_idxs(), - zeroLength(false) + zeroLength(false), + weight(0.0) {} // BEDALL @@ -160,7 +165,8 @@ public: strand(strand), fields(fields), other_idxs(other_idxs), - zeroLength(false) + zeroLength(false), + weight(0.0) {} int size() const { @@ -434,6 +440,11 @@ public: // load a BED file into a vector of BEDs void loadBedFileIntoVector(); + // load a BED file into a vector ordered in decreasing order by size + void assignWeightsBasedOnSize(); + + BED * sizeWeightedSearch(double val); + // 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 @@ -484,7 +495,7 @@ public: bool isBed12; // is it file of true blocked BED12 records? bool isZeroBased; - // Main data structires used by BEDTools + // Main data structures used by BEDTools masterBedCovMap bedCovMap; masterBedCovListMap bedCovListMap; masterBedMap bedMap; diff --git a/src/utils/driver/BedtoolsDriver.cpp b/src/utils/driver/BedtoolsDriver.cpp index 093cc0e..ecab8c3 100644 --- a/src/utils/driver/BedtoolsDriver.cpp +++ b/src/utils/driver/BedtoolsDriver.cpp @@ -43,7 +43,7 @@ BedtoolsDriver::BedtoolsDriver() } -bool BedtoolsDriver::supports(const QuickString &tool) { +bool BedtoolsDriver::supports(const string &tool) { supportType::iterator iter = _supported.find(tool); return (iter != _supported.end()); } diff --git a/src/utils/driver/BedtoolsDriver.h b/src/utils/driver/BedtoolsDriver.h index d4a1853..097031d 100644 --- a/src/utils/driver/BedtoolsDriver.h +++ b/src/utils/driver/BedtoolsDriver.h @@ -5,13 +5,13 @@ class BedtoolsDriver { public: BedtoolsDriver(); bool subMain(int argc, char **argv); - bool supports(const QuickString &tool); + bool supports(const string &tool); ContextBase *getContext(); ToolBase *getTool(ContextBase *context); bool hadError() const { return _hadError; } protected: - QuickString _subCmd; - typedef set supportType; + string _subCmd; + typedef set supportType; supportType _supported; bool _hadError; diff --git a/src/utils/fileType/FileRecordTypeChecker.cpp b/src/utils/fileType/FileRecordTypeChecker.cpp index 71dc42e..d6166ba 100644 --- a/src/utils/fileType/FileRecordTypeChecker.cpp +++ b/src/utils/fileType/FileRecordTypeChecker.cpp @@ -181,12 +181,12 @@ bool FileRecordTypeChecker::handleTextFormat(const char *buffer, size_t len) //Tokenize the first line of valid data into fields. //Need to make a copy so next call to tokenizer doesn't overwrite the line. - QuickString line(_tokenizer.getElem(_firstValidDataLineIdx)); + string line(_tokenizer.getElem(_firstValidDataLineIdx)); _tokenizer.setKeepFinalIncompleteElem(Tokenizer::USE_NOW); _tokenizer.setNumExpectedItems(_numFields); _tokenizer.tokenize(line, _delimChar); - if (_tokenizer.getNumFields(line.str(), _delimChar) != _numFields) { + if (_tokenizer.getNumFields(line, _delimChar) != _numFields) { cerr << "Error: Type checker found wrong number of fields while tokenizing data line." << endl; exit(1); } @@ -293,7 +293,7 @@ bool FileRecordTypeChecker::isGFFformat() bool FileRecordTypeChecker::isTextDelimtedFormat(const char *buffer, size_t len) { - //Break single string buffer into vector of QuickStrings. Delimiter is newline. + //Break single string buffer into vector of strings. Delimiter is newline. _tokenizer.setKeepFinalIncompleteElem(Tokenizer::IGNORE); int numLines = _tokenizer.tokenize(buffer, '\n', _eofHit, _isCompressed); @@ -455,6 +455,6 @@ bool FileRecordTypeChecker::passesBed12() { } bool FileRecordTypeChecker::isStrandField(int field) { - const QuickString &strandChar = _tokenizer.getElem(field); + const string &strandChar = _tokenizer.getElem(field); return (strandChar == "+" || strandChar == "-" || strandChar == "."); } diff --git a/src/utils/fileType/FileRecordTypeChecker.h b/src/utils/fileType/FileRecordTypeChecker.h index a384a27..21ea896 100644 --- a/src/utils/fileType/FileRecordTypeChecker.h +++ b/src/utils/fileType/FileRecordTypeChecker.h @@ -35,7 +35,7 @@ public: BED6_RECORD_TYPE, BED12_RECORD_TYPE, BED_PLUS_RECORD_TYPE, BED6_PLUS_RECORD_TYPE, BAM_RECORD_TYPE, VCF_RECORD_TYPE, GFF_RECORD_TYPE, GFF_PLUS_RECORD_TYPE, NO_POS_PLUS_RECORD_TYPE} RECORD_TYPE; - void setFilename(const QuickString & filename) { _filename = filename; } + void setFilename(const string & filename) { _filename = filename; } bool scanBuffer(const char *buf, size_t len, bool eofHit, bool isCompressed = false); bool needsMoreData() const { return _insufficientData; } @@ -89,7 +89,7 @@ private: FILE_TYPE _fileType; RECORD_TYPE _recordType; - QuickString _filename; //useful for reporting errors with file. + string _filename; //useful for reporting errors with file. Tokenizer _tokenizer; int _firstValidDataLineIdx; diff --git a/src/utils/fileType/Makefile b/src/utils/fileType/Makefile index ec0c518..57f7650 100644 --- a/src/utils/fileType/Makefile +++ b/src/utils/fileType/Makefile @@ -12,7 +12,7 @@ INCLUDES = -I$(UTILITIES_DIR)/BamTools/include/ \ # ---------------------------------- SOURCES= fileType.cpp fileType.h FileRecordTypeChecker.cpp FileRecordTypeChecker.h OBJECTS= fileType.o FileRecordTypeChecker.o -#_EXT_OBJECTS=ParseTools.o QuickString.o +#_EXT_OBJECTS=ParseTools.o string.o #EXT_OBJECTS=$(patsubst %,$(OBJ_DIR)/%,$(_EXT_OBJECTS)) BUILT_OBJECTS= $(patsubst %,$(OBJ_DIR)/%,$(OBJECTS)) diff --git a/src/utils/general/BTlist.h b/src/utils/general/BTlist.h index 7bae4f3..d64d845 100644 --- a/src/utils/general/BTlist.h +++ b/src/utils/general/BTlist.h @@ -26,7 +26,8 @@ #include "FreeList.h" -#include "QuickString.h" +#include "string.h" +#include #include #include //for memset @@ -65,9 +66,9 @@ public: _dontDelete(false) { } - //This version of the constructor will convert a QuickString into a BTlist. + //This version of the constructor will convert a string into a BTlist. //It is effectively the opposite of the toStr method. - BTlist(const QuickString &str) : + BTlist(const string &str) : _begin(NULL), _currEnd(NULL), _prevCursor(NULL), @@ -230,18 +231,19 @@ public: _dontDelete = true; } - //this method will convert the contents of the list into a QuickString. + //this method will convert the contents of the list into a string. //It assumes that the templated type of the listNode can be converted to a //char using the (char) cast. The user must ensure that this is the case. //The 2nd parameter needs only be true if you wish to append the data - //to the QuickString's existing contents. Otherwise, it will be cleared first. - void toStr(QuickString &str, bool append = false) const { + //to the string's existing contents. Otherwise, it will be cleared first. + void toStr(string &str, bool append = false) const + { if (!append) { str.clear(); } str.reserve(_size + str.size()); for (const BTlistNode *iter = begin(); iter != end(); iter = iter->next()) { - str.append((char)iter->value()); + str += iter->value(); } } diff --git a/src/utils/general/BedtoolsTypes.h b/src/utils/general/BedtoolsTypes.h index 46aef49..c4b4dfd 100644 --- a/src/utils/general/BedtoolsTypes.h +++ b/src/utils/general/BedtoolsTypes.h @@ -17,7 +17,7 @@ using namespace std; #include #include #include -#include "QuickString.h" +#include "string.h" //STL headers #include //include pair and make_pair diff --git a/src/utils/general/Makefile b/src/utils/general/Makefile index 7fe5316..905eb5a 100644 --- a/src/utils/general/Makefile +++ b/src/utils/general/Makefile @@ -10,9 +10,9 @@ INCLUDES = -I$(UTILITIES_DIR)/lineFileUtilities/ \ # ---------------------------------- # define our source and object files # ---------------------------------- -SOURCES= QuickString.h QuickString.cpp ParseTools.h ParseTools.cpp PushBackStreamBuf.cpp PushBackStreamBuf.h CompressionTools.h CompressionTools.cpp \ +SOURCES= ParseTools.h ParseTools.cpp PushBackStreamBuf.cpp PushBackStreamBuf.h CompressionTools.h CompressionTools.cpp \ Tokenizer.h Tokenizer.cpp CommonHelp.h CommonHelp.cpp ErrorMsg.h ErrorMsg.cpp -OBJECTS= QuickString.o ParseTools.o PushBackStreamBuf.o CompressionTools.o Tokenizer.o CommonHelp.o +OBJECTS= ParseTools.o PushBackStreamBuf.o CompressionTools.o Tokenizer.o CommonHelp.o BUILT_OBJECTS= $(patsubst %,$(OBJ_DIR)/%,$(OBJECTS)) all: $(BUILT_OBJECTS) @@ -25,6 +25,6 @@ $(BUILT_OBJECTS): $(SOURCES) clean: @echo "Cleaning up." - @rm -f $(OBJ_DIR)/QuickString.o $(OBJ_DIR)/ParseTools.o $(OBJ_DIR)/PushBackStreamBuf.o $(OBJ_DIR)/Tokenizer.o $(OBJ_DIR)/CommonHelp.o + @rm -f $(OBJ_DIR)/string.o $(OBJ_DIR)/ParseTools.o $(OBJ_DIR)/PushBackStreamBuf.o $(OBJ_DIR)/Tokenizer.o $(OBJ_DIR)/CommonHelp.o .PHONY: clean diff --git a/src/utils/general/ParseTools.cpp b/src/utils/general/ParseTools.cpp index 372efdd..43f71c4 100644 --- a/src/utils/general/ParseTools.cpp +++ b/src/utils/general/ParseTools.cpp @@ -7,7 +7,7 @@ #include //This functions recognizes only numbers with digits, plus sign, minus sign, decimal point, e, or E. Hexadecimal and pointers not currently supported. -bool isNumeric(const QuickString &str) { +bool isNumeric(const string &str) { for (int i=0; i < (int)str.size(); i++) { char currChar = str[i]; if (!(isdigit(currChar) || currChar == '-' || currChar == '.' || currChar == '+' || currChar == 'e' || currChar == 'E')) { @@ -18,7 +18,7 @@ bool isNumeric(const QuickString &str) { } //As above, but does not allow decimal points -bool isInteger(const QuickString &str) { +bool isInteger(const string &str) { for (int i=0; i < (int)str.size(); i++) { char currChar = str[i]; if (!(isdigit(currChar) || currChar == '-' || currChar == '+' || currChar == 'e' || currChar == 'E')) { @@ -30,7 +30,7 @@ bool isInteger(const QuickString &str) { -int str2chrPos(const QuickString &str) { +int str2chrPos(const string &str) { return str2chrPos(str.c_str(), str.size()); } @@ -128,7 +128,7 @@ string vectorIntToStr(const vector &vec) { return str; } -bool isHeaderLine(const QuickString &line) { +bool isHeaderLine(const string &line) { if (line[0] == '>') { return true; } @@ -138,7 +138,15 @@ bool isHeaderLine(const QuickString &line) { if (line[0] == '#') { return true; } - //GFF file headers can also start with the words "browser" or "track", followed by a whitespace character. + //allow chr chrom to start a header line + if (memcmp(line.c_str(), "chrom", 5) == 0 && isspace(line[5])) { + return true; + } + //allow chr chrom to start a header line + if (memcmp(line.c_str(), "chr", 3) == 0 && isspace(line[3])) { + return true; + } + //UCSC file headers can also start with the words "browser" or "track", followed by a whitespace character. if (memcmp(line.c_str(), "browser", 7) == 0 && isspace(line[7])) { return true; } diff --git a/src/utils/general/ParseTools.h b/src/utils/general/ParseTools.h index 9432f98..b354cdc 100644 --- a/src/utils/general/ParseTools.h +++ b/src/utils/general/ParseTools.h @@ -12,14 +12,14 @@ #include #include #include -#include "QuickString.h" +#include "string.h" #include #include using namespace std; -bool isNumeric(const QuickString &str); -bool isInteger(const QuickString &str); +bool isNumeric(const string &str); +bool isInteger(const string &str); //This method is a faster version of atoi, but is limited to a maximum of //9 digit numbers in Base 10 only. The string may begin with a negative. @@ -27,14 +27,14 @@ bool isInteger(const QuickString &str); //digits (with the excpetion of a minus sign in the first position) //will result in error. Errors return INT_MIN. int str2chrPos(const char *str, size_t len = 0); -int str2chrPos(const QuickString &str); +int str2chrPos(const string &str); //int2str is faster but less flexible version of the ToString method in //lineFileUtilities. Unlike ToString, which uses streams, this method //can only handle integers. The buffer, which is templated, needs to support the //assignment operater for char *, meaning it needs a T::operator = (const char *) method. -//strings, QuickStrings, stringbuffers, and the like are acceptable. +//strings, strings, stringbuffers, and the like are acceptable. template void int2str(int number, T& buffer, bool appendToBuf = false) @@ -75,12 +75,12 @@ void int2str(int number, T& buffer, bool appendToBuf = false) } -bool isHeaderLine(const QuickString &line); +bool isHeaderLine(const string &line); string vectorIntToStr(const vector &vec); //This is a faster version of tokenize that doesn't use strings. Return value is final size of elems vector. -int Tokenize(const QuickString &str, vector &elems, char delimiter = '\t', int numExpectedItems = 0); +//int Tokenize(const string &str, vector &elems, char delimiter = '\t', int numExpectedItems = 0); #endif /* PARSETOOLS_H_ */ diff --git a/src/utils/general/QuickString.cpp b/src/utils/general/QuickString.cpp index a83263e..4507a8c 100644 --- a/src/utils/general/QuickString.cpp +++ b/src/utils/general/QuickString.cpp @@ -1,11 +1,11 @@ -#include "QuickString.h" +#include "string.h" #include #include #include #include "ParseTools.h" #include "lineFileUtilities.h" -QuickString::QuickString(size_t capacity) +string::string(size_t capacity) : _buffer(NULL), _currCapacity(capacity), _currSize(0) @@ -13,7 +13,7 @@ QuickString::QuickString(size_t capacity) build(); } -QuickString::QuickString(const QuickString &qs) +string::string(const string &qs) : _buffer(NULL), _currCapacity(qs._currCapacity), _currSize(0) @@ -22,7 +22,7 @@ QuickString::QuickString(const QuickString &qs) set(qs._buffer, qs._currSize); } -QuickString::QuickString(const char *inBuf) +string::string(const char *inBuf) { size_t len = strlen(inBuf); _currCapacity = len +1; @@ -31,7 +31,7 @@ QuickString::QuickString(const char *inBuf) set(inBuf, len); } -QuickString::QuickString(const string &inString) +string::string(const string &inString) { size_t len = (int)inString.size(); _currCapacity = len +1; @@ -40,7 +40,7 @@ QuickString::QuickString(const string &inString) set(inString.c_str(), len); } -QuickString::QuickString(char c) +string::string(char c) { _currCapacity =2; @@ -53,127 +53,127 @@ QuickString::QuickString(char c) set(buffer, 1); } -void QuickString::build() { +void string::build() { _buffer = (char *)malloc(_currCapacity); clear(); } -QuickString::~QuickString(){ +string::~string(){ free(_buffer); } -void QuickString::clear() { +void string::clear() { memset(_buffer, 0, _currCapacity); _currSize = 0; } -void QuickString::release() { +void string::release() { free(_buffer); _currCapacity = DEFAULT_CAPACITY; build(); } -QuickString &QuickString::operator = (const char *inBuf){ +string &string::operator = (const char *inBuf){ set(inBuf, strlen(inBuf)); return *this; } -QuickString &QuickString::operator = (const string & inBuf){ +string &string::operator = (const string & inBuf){ set(inBuf.c_str(), (int)inBuf.size()); return *this; } -QuickString &QuickString::operator = (const QuickString & inBuf){ +string &string::operator = (const string & inBuf){ set(inBuf._buffer, (int)inBuf._currSize); return *this; } -QuickString &QuickString::operator = (char val) { +string &string::operator = (char val) { clear(); append(val); return *this; } -QuickString &QuickString::operator = (int val) { +string &string::operator = (int val) { clear(); append(val); return *this; } -QuickString &QuickString::operator = (uint32_t val) { +string &string::operator = (uint32_t val) { clear(); append(val); return *this; } -// QuickString &QuickString::operator = (size_t val) { +// string &string::operator = (size_t val) { // clear(); // append(val); // return *this; // } -QuickString &QuickString::operator = (float val) { +string &string::operator = (float val) { clear(); append(val); return *this; } -QuickString &QuickString::operator = (double val) { +string &string::operator = (double val) { clear(); append(val); return *this; } -QuickString &QuickString::operator += (const QuickString & inBuf) +string &string::operator += (const string & inBuf) { append(inBuf._buffer, (int)inBuf._currSize); return *this; } -QuickString &QuickString::operator +=(const string &inBuf) +string &string::operator +=(const string &inBuf) { append(inBuf.c_str(), (int)inBuf.size()); return *this; } -QuickString &QuickString::operator +=(char c) { +string &string::operator +=(char c) { append(c); return *this; } -QuickString &QuickString::operator += (const char *inBuf) +string &string::operator += (const char *inBuf) { append(inBuf, strlen(inBuf)); return *this; } -QuickString &QuickString::operator += (int num) { +string &string::operator += (int num) { append(num); return *this; } -QuickString &QuickString::operator += (uint32_t num) { +string &string::operator += (uint32_t num) { append(num); return *this; } -// QuickString &QuickString::operator += (size_t num) { +// string &string::operator += (size_t num) { // append(num); // return *this; // } -QuickString &QuickString::operator += (float num) { +string &string::operator += (float num) { append(num); return *this; } -QuickString &QuickString::operator += (double num) { +string &string::operator += (double num) { append(num); return *this; } -bool QuickString::operator == (const QuickString &qs) const { +bool string::operator == (const string &qs) const { if ( _currSize != qs._currSize) { return false; } @@ -183,7 +183,7 @@ bool QuickString::operator == (const QuickString &qs) const { return true; } -bool QuickString::operator == (const string &str) const { +bool string::operator == (const string &str) const { if ( _currSize != str.size()) { return false; } @@ -194,7 +194,7 @@ bool QuickString::operator == (const string &str) const { } -bool QuickString::stricmp(const QuickString &str) const { +bool string::stricmp(const string &str) const { if (str.size() != _currSize) { return true; } @@ -206,7 +206,7 @@ bool QuickString::stricmp(const QuickString &str) const { return false; } -bool QuickString::operator == (const char *str) const { +bool string::operator == (const char *str) const { size_t inLen = strlen(str); if (inLen != _currSize) { return false; @@ -218,26 +218,26 @@ bool QuickString::operator == (const char *str) const { } -bool QuickString::operator != (const QuickString &qs) const { +bool string::operator != (const string &qs) const { return !(*this == qs); } -bool QuickString::operator < (const QuickString &qs) const { +bool string::operator < (const string &qs) const { return (memcmp(_buffer, qs._buffer, max(_currSize, qs._currSize)) < 0); } -bool QuickString::operator > (const QuickString &qs) const { +bool string::operator > (const string &qs) const { return (memcmp(_buffer, qs._buffer, max(_currSize, qs._currSize))> 0); } -void QuickString::set(const char *inBuf, size_t newLen) { +void string::set(const char *inBuf, size_t newLen) { reserve(newLen); clear(); memcpy(_buffer, inBuf, newLen); _currSize = newLen; } -void QuickString::reserve(size_t newLen) { +void string::reserve(size_t newLen) { newLen++; //always leave room for a null termninator. if (_currCapacity <= newLen) { while (_currCapacity <= newLen) { @@ -255,50 +255,50 @@ void QuickString::reserve(size_t newLen) { } } -void QuickString::append(char c) +void string::append(char c) { reserve(_currSize +1); _buffer[_currSize] = c; _currSize++; } -void QuickString::append(const char *inBuf, size_t inBufLen) +void string::append(const char *inBuf, size_t inBufLen) { reserve(_currSize + inBufLen); memcpy(_buffer + _currSize, inBuf, inBufLen); _currSize += inBufLen; } -void QuickString::append(int num) { +void string::append(int num) { int2str(num, *this, true); } -void QuickString::append(uint32_t num) { +void string::append(uint32_t num) { int2str((int)num, *this, true); } -// void QuickString::append(size_t num) { +// void string::append(size_t num) { // int2str((int)num, *this, true); // } -void QuickString::append(float num) { +void string::append(float num) { append(ToString(num)); } -void QuickString::append(double num) { +void string::append(double num) { append(ToString(num)); } -QuickString &QuickString::assign(const char *inBuf, size_t inBufLen) +string &string::assign(const char *inBuf, size_t inBufLen) { clear(); append(inBuf, inBufLen); return *this; } -void QuickString::resize(size_t newSize, char fillChar) +void string::resize(size_t newSize, char fillChar) { if (newSize > _currSize) { //grow the string, pad with fillChar reserve(newSize); @@ -310,7 +310,7 @@ void QuickString::resize(size_t newSize, char fillChar) } -void QuickString::substr (QuickString &newStr, size_t pos, size_t len) const +void string::substr (string &newStr, size_t pos, size_t len) const { if (pos >= _currSize) { return; @@ -321,7 +321,7 @@ void QuickString::substr (QuickString &newStr, size_t pos, size_t len) const newStr.set(_buffer + pos, len); } -ostream &operator << (ostream &out, const QuickString &str) { +ostream &operator << (ostream &out, const string &str) { out << str._buffer; return out; } diff --git a/src/utils/general/QuickString.h b/src/utils/general/QuickString.h index 6e6fa94..c5e768e 100644 --- a/src/utils/general/QuickString.h +++ b/src/utils/general/QuickString.h @@ -1,12 +1,12 @@ /* - * QuickString.h + * string.h * * Created on: Dec 3, 2012 * Author: nek3d */ -#ifndef QUICKSTRING_H_ -#define QUICKSTRING_H_ +#ifndef string_H_ +#define string_H_ #include #include @@ -15,16 +15,16 @@ using namespace std; -class QuickString { +class string { public: - QuickString(size_t capacity = DEFAULT_CAPACITY); - QuickString(const QuickString &); //need explicit copy constructor - //so address of _buffer member is not copied! Each QuickString object + string(size_t capacity = DEFAULT_CAPACITY); + string(const string &); //need explicit copy constructor + //so address of _buffer member is not copied! Each string object //needs to build it's own buffer. - QuickString(const char *); - QuickString(const string &); - QuickString(char c); - ~QuickString(); + string(const char *); + string(const string &); + string(char c); + ~string(); size_t size() const { return _currSize; } size_t capacity() const { return _currCapacity; } void reserve(size_t newCapacity=0); @@ -32,40 +32,40 @@ public: void clear(); //only clears buffer, doesn't delete it. void release(); //will deallocate current buffer, reallocate it at default size. - QuickString &operator = (const string &); - QuickString &operator = (const char *); - QuickString &operator = (const QuickString &); - QuickString &operator = (char); - QuickString &operator = (int); - QuickString &operator = (uint32_t); - //QuickString &operator = (size_t); - QuickString &operator = (float); - QuickString &operator = (double); - QuickString &operator += (const QuickString &); - QuickString &operator += (const string &); - QuickString &operator += (const char *); - QuickString &operator += (char); - QuickString &operator += (int); - QuickString &operator += (uint32_t); - //QuickString &operator += (size_t); - QuickString &operator += (float); - QuickString &operator += (double); + string &operator = (const string &); + string &operator = (const char *); + string &operator = (const string &); + string &operator = (char); + string &operator = (int); + string &operator = (uint32_t); + //string &operator = (size_t); + string &operator = (float); + string &operator = (double); + string &operator += (const string &); + string &operator += (const string &); + string &operator += (const char *); + string &operator += (char); + string &operator += (int); + string &operator += (uint32_t); + //string &operator += (size_t); + string &operator += (float); + string &operator += (double); - friend ostream &operator << (ostream &out, const QuickString &str); - bool operator == (const QuickString &) const; + friend ostream &operator << (ostream &out, const string &str); + bool operator == (const string &) const; bool operator == (const string &) const; bool operator == (const char *) const; - bool operator != (const QuickString &) const; - bool operator < (const QuickString &) const; - bool operator > (const QuickString &) const; + bool operator != (const string &) const; + bool operator < (const string &) const; + bool operator > (const string &) const; const char *c_str() const { return _buffer; } const string str() const { return _buffer; } const char &operator [] (int pos) const { return _buffer[pos]; } char &operator [] (int pos) { return _buffer[pos]; } char &at(size_t pos) { return _buffer[pos]; } - bool stricmp(const QuickString &str) const; //case insensitive compare. False if same aside from case, true if different aside from case. + bool stricmp(const string &str) const; //case insensitive compare. False if same aside from case, true if different aside from case. - void append(const QuickString &str) { append(str.c_str(), str.size()); } + void append(const string &str) { append(str.c_str(), str.size()); } void append(const char *buf, size_t bufLen); void append(char c); @@ -80,9 +80,9 @@ public: - QuickString &assign(const char *str, size_t n); + string &assign(const char *str, size_t n); void resize(size_t n, char c = '\0'); - void substr(QuickString &newStr, size_t pos = 0, size_t len = UINT_MAX) const; + void substr(string &newStr, size_t pos = 0, size_t len = UINT_MAX) const; private: char *_buffer; @@ -95,4 +95,4 @@ private: }; -#endif /* QUICKSTRING_H_ */ +#endif /* string_H_ */ diff --git a/src/utils/general/Tokenizer.cpp b/src/utils/general/Tokenizer.cpp index ab3c8ea..779e261 100644 --- a/src/utils/general/Tokenizer.cpp +++ b/src/utils/general/Tokenizer.cpp @@ -35,11 +35,11 @@ int Tokenizer::getNumFields(const string &str, char delimiter) return tmp.size(); } -int Tokenizer::tokenize(const QuickString &str, char delimiter, bool eofHit, bool isCompressed) { +int Tokenizer::tokenize(const string &str, char delimiter, bool eofHit, bool isCompressed) { // http://stackoverflow.com/questions/236129/how-to-split-a-string-in-c/236803#236803 // NOTE: this approach intentionally allows consecutive delimiters - std::stringstream ss(str.str()); + std::stringstream ss(str); std::string item; _elems.clear(); while(getline(ss, item, delimiter)) { @@ -62,7 +62,8 @@ int Tokenizer::tokenize(const QuickString &str, char delimiter, bool eofHit, boo _elems.push_back(item); } } - return _elems.size(); + _numValidElems = _elems.size(); + return _numValidElems; // int strLen = (int)str.size(); @@ -82,7 +83,7 @@ int Tokenizer::tokenize(const QuickString &str, char delimiter, bool eofHit, boo // currIdx--; //make sure it's not included in the final count of valid elems. // } else { - // QuickString *newStr = fetchElem(currIdx); + // string *newStr = fetchElem(currIdx); // newStr->assign(str.c_str() + startPos, min(currPos, strLen) - startPos); // // If splitting lines, strip any white space from the end of the line diff --git a/src/utils/general/Tokenizer.h b/src/utils/general/Tokenizer.h index 88704de..797e1c1 100644 --- a/src/utils/general/Tokenizer.h +++ b/src/utils/general/Tokenizer.h @@ -8,7 +8,7 @@ #ifndef TOKENIZER_H_ #define TOKENIZER_H_ -#include "QuickString.h" +#include "string.h" #include #include @@ -23,7 +23,7 @@ public: // If not, don't worry about it. void setNumExpectedItems(int val); - int tokenize(const QuickString &str, char delimiter = '\t', bool eofHit = false, bool isCompressed = true); + int tokenize(const string &str, char delimiter = '\t', bool eofHit = false, bool isCompressed = true); // If the final element ends before a delim char, that means // the buffer passed in ends mid-element. The last, incomplete diff --git a/src/utils/stringUtilities/stringUtilities.h b/src/utils/stringUtilities/stringUtilities.h index 6f3b459..36393da 100644 --- a/src/utils/stringUtilities/stringUtilities.h +++ b/src/utils/stringUtilities/stringUtilities.h @@ -1,18 +1,32 @@ #ifndef STRINGUTILITIES_H #define STRINGUTILITIES_H -#include +#include #include +#include +#include +#include + +using namespace std; /**************************************************** // isInteger(s): Tests if string s is a valid integer *****************************************************/ inline bool isInteger(const std::string& s) { int len = s.length(); - for (int i = 0; i < len; i++) { + for (int i = 0; i < len; i++) if (!std::isdigit(s[i])) return false; return true; } +string toLower(const string& s) { + string t = s; + for (string::iterator p = t.begin(); p != t.end(); ++p) + { + *p = tolower(*p); + } + return t; +} + #endif /* STRINGUTILITIES_H */ diff --git a/test/coverage/test-coverage.sh b/test/coverage/test-coverage.sh index 7b534e0..95375fa 100644 --- a/test/coverage/test-coverage.sh +++ b/test/coverage/test-coverage.sh @@ -495,7 +495,7 @@ rm exp obs ################################################################## echo " coverage.t10...\c" echo \ -"chr1 0 50 3 30 50 0.6000000 +"chr1 0 50 1 30 50 0.6000000 chr1 12 20 0 0 8 0.0000000" > exp $BT coverage -a c.bed -b three_blocks_match.bam -split > obs check exp obs diff --git a/test/general/t.bed b/test/general/t.bed new file mode 100644 index 0000000..4a48d79 --- /dev/null +++ b/test/general/t.bed @@ -0,0 +1,5 @@ +chrom chromStart chromEnd name score strand +chr14 24800000 24810000 blarg 0 . +chr11 64610000 64620000 blarg 0 . +chr14 24710000 24720000 blarg 0 . +chr11 111230000 111240000 blarg 0 . diff --git a/test/general/test-general.sh b/test/general/test-general.sh index 541be1a..2355836 100644 --- a/test/general/test-general.sh +++ b/test/general/test-general.sh @@ -277,5 +277,16 @@ $BT merge -i c.bed.gz > obs echo -n "" > exp check obs exp +# allow header lines to start with chr or chrom +echo " general.t43...\c" +echo "chrom chromStart chromEnd name score strand +chr14 24800000 24810000 blarg 0 . +chr11 64610000 64620000 blarg 0 . +chr14 24710000 24720000 blarg 0 . +chr11 111230000 111240000 blarg 0 ." > exp +$BT intersect -a t.bed -b t.bed -header > obs +check obs exp + + rm a.bed.gz b.bed.gz c.bed.gz a.bed b.bed c.bed genome.txt exp obs diff --git a/test/groupBy/test-groupby.sh b/test/groupBy/test-groupby.sh index 6a239d1..6d0036a 100644 --- a/test/groupBy/test-groupby.sh +++ b/test/groupBy/test-groupby.sh @@ -293,9 +293,8 @@ rm obs exp # non-positional records ########################################################### echo " groupby.t15...\c" -echo \ -"ERROR: file noPosvalues.header.bed has non positional records, which are only valid for the groupBy tool." > exp -$BT merge -i noPosvalues.header.bed 2>&1 >/dev/null | cat - > obs +echo "ERROR: file noPosvalues.header.bed has non positional records, which are only valid for the groupBy tool." > exp +$BT merge -i noPosvalues.header.bed 2>&1 | head -n 1 > obs check obs exp rm obs exp diff --git a/test/shift/b.bed b/test/shift/b.bed new file mode 100644 index 0000000..a147e8a --- /dev/null +++ b/test/shift/b.bed @@ -0,0 +1,2 @@ +chr1 66999638 67216822 NM_032291 0 + +chr1 92145899 92351836 NR_036634 0 - diff --git a/test/shift/huge.genome b/test/shift/huge.genome new file mode 100644 index 0000000..d8ebc53 --- /dev/null +++ b/test/shift/huge.genome @@ -0,0 +1 @@ +chr1 249250621 diff --git a/test/shift/test-shift.sh b/test/shift/test-shift.sh index 9c3c6a2..a78b15a 100644 --- a/test/shift/test-shift.sh +++ b/test/shift/test-shift.sh @@ -113,3 +113,14 @@ chr1 999 1000 a2 2 -" > exp $BT shift -i a.bed -s 3000000000 -g tiny.genome > obs check obs exp rm obs exp + +########################################################### +# test shift huge genome +########################################################### +echo " shift.t9...\c" +echo \ +"chr1 67000638 67217822 NM_032291 0 + +chr1 92146899 92352836 NR_036634 0 -" > exp +$BT shift -i b.bed -s 1000 -g huge.genome > obs +check obs exp +rm obs exp diff --git a/test/test.sh b/test/test.sh index f249557..9b9e69a 100644 --- a/test/test.sh +++ b/test/test.sh @@ -31,6 +31,9 @@ cd genomecov; bash test-genomecov.sh; cd .. echo " Testing bedtools getfasta:" cd getfasta; bash test-getfasta.sh; cd .. +echo " Testing bedtools groupby:" +cd groupby; bash test-groupby.sh; cd .. + echo " Testing bedtools intersect:" cd intersect; bash test-intersect.sh; bash new_test-intersect.sh; cd ..