X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=trimseqscommand.h;h=80e1ebe1a00e2f56ec19a6f23c3ba890af1c4f10;hb=66d24c0ac3c96d3e1bce9217032ece55dd3609eb;hp=8d9a57a54ffd0db053956200602f3aa06fb4de5b;hpb=ea4f373c28543cd1002b0dd7dc6e55c526647d59;p=mothur.git diff --git a/trimseqscommand.h b/trimseqscommand.h index 8d9a57a..80e1ebe 100644 --- a/trimseqscommand.h +++ b/trimseqscommand.h @@ -27,8 +27,9 @@ public: vector setParameters(); string getCommandName() { return "trim.seqs"; } string getCommandCategory() { return "Sequence Processing"; } - string getOutputFileNameTag(string, string); + string getHelpString(); + string getOutputPattern(string); string getCitation() { return "http://www.mothur.org/wiki/Trim.seqs"; } string getDescription() { return "provides the preprocessing features needed to screen and sort pyrosequences"; } @@ -61,7 +62,6 @@ private: vector revPrimer, outputNames; set filesToRemove; map barcodes; - map rbarcodes; vector groupVector; map primers; vector linker; @@ -102,7 +102,6 @@ struct trimData { double qRollAverage, qThreshold, qWindowAverage, qAverage; vector revPrimer; map barcodes; - map rbarcodes; map primers; map nameCount; vector linker; @@ -116,7 +115,7 @@ struct trimData { trimData(){} trimData(string fn, string qn, string nf, string cf, string tn, string sn, string tqn, string sqn, string tnn, string snn, string tcn, string scn,string gn, vector > ffn, vector > qfn, vector > nfn, unsigned long long lstart, unsigned long long lend, unsigned long long qstart, unsigned long long qend, MothurOut* mout, - int pd, int bd, int ld, int sd, int td, map pri, map bar, map rbar, vector revP, vector li, vector spa, + int pd, int bd, int ld, int sd, int td, map pri, map bar, vector revP, vector li, vector spa, vector priNameVector, vector barNameVector, bool cGroup, bool aFiles, bool keepF, int keepfi, int removeL, int WindowStep, int WindowSize, int WindowAverage, bool trim, double Threshold, double Average, double RollAverage, int minL, int maxA, int maxH, int maxL, bool fli, map nm, map ncount) { @@ -149,7 +148,6 @@ struct trimData { sdiffs = sd; tdiffs = td; barcodes = bar; - rbarcodes = rbar; primers = pri; numFPrimers = primers.size(); revPrimer = revP; numRPrimers = revPrimer.size(); linker = li; numLinkers = linker.size(); @@ -254,9 +252,9 @@ static DWORD WINAPI MyTrimThreadFunction(LPVOID lpParam){ } - TrimOligos trimOligos(pDataArray->pdiffs, pDataArray->bdiffs, pDataArray->ldiffs, pDataArray->sdiffs, pDataArray->primers, pDataArray->barcodes, pDataArray->rbarcodes, pDataArray->revPrimer, pDataArray->linker, pDataArray->spacer); + TrimOligos trimOligos(pDataArray->pdiffs, pDataArray->bdiffs, pDataArray->ldiffs, pDataArray->sdiffs, pDataArray->primers, pDataArray->barcodes, pDataArray->revPrimer, pDataArray->linker, pDataArray->spacer); - pDataArray->count = pDataArray->lineEnd; + pDataArray->count = 0; for(int i = 0; i < pDataArray->lineEnd; i++){ //end is the number of sequences to process if (pDataArray->m->control_pressed) { @@ -283,6 +281,7 @@ static DWORD WINAPI MyTrimThreadFunction(LPVOID lpParam){ string origSeq = currSeq.getUnaligned(); if (origSeq != "") { + pDataArray->count++; int barcodeIndex = 0; int primerIndex = 0; @@ -299,12 +298,6 @@ static DWORD WINAPI MyTrimThreadFunction(LPVOID lpParam){ else{ currentSeqsDiffs += success; } } - if(pDataArray->rbarcodes.size() != 0){ - success = trimOligos.stripRBarcode(currSeq, currQual, barcodeIndex); - if(success > pDataArray->bdiffs) { trashCode += 'b'; } - else{ currentSeqsDiffs += success; } - } - if(pDataArray->numSpacers != 0){ success = trimOligos.stripSpacer(currSeq, currQual); if(success > pDataArray->sdiffs) { trashCode += 's'; } @@ -403,31 +396,10 @@ static DWORD WINAPI MyTrimThreadFunction(LPVOID lpParam){ } if(trashCode.length() == 0){ - currSeq.setAligned(currSeq.getUnaligned()); - currSeq.printSequence(trimFASTAFile); - - if(pDataArray->qFileName != ""){ - currQual.printQScores(trimQualFile); - } - - if(pDataArray->nameFile != ""){ - map::iterator itName = pDataArray->nameMap.find(currSeq.getName()); - if (itName != pDataArray->nameMap.end()) { trimNameFile << itName->first << '\t' << itName->second << endl; } - else { pDataArray->m->mothurOut("[ERROR]: " + currSeq.getName() + " is not in your namefile, please correct."); pDataArray->m->mothurOutEndLine(); } - } - - int numRedundants = 0; - if (pDataArray->countfile != "") { - map::iterator itCount = pDataArray->nameCount.find(currSeq.getName()); - if (itCount != pDataArray->nameCount.end()) { - trimCountFile << itCount->first << '\t' << itCount->second << endl; - numRedundants = itCount->second-1; - }else { pDataArray->m->mothurOut("[ERROR]: " + currSeq.getName() + " is not in your count file, please correct."); pDataArray->m->mothurOutEndLine(); } - } - - if (pDataArray->createGroup) { + string thisGroup = ""; + if (pDataArray->createGroup) { if(pDataArray->barcodes.size() != 0){ - string thisGroup = pDataArray->barcodeNameVector[barcodeIndex]; + thisGroup = pDataArray->barcodeNameVector[barcodeIndex]; if (pDataArray->primers.size() != 0) { if (pDataArray->primerNameVector[primerIndex] != "") { if(thisGroup != "") { @@ -437,50 +409,81 @@ static DWORD WINAPI MyTrimThreadFunction(LPVOID lpParam){ } } } - - if (pDataArray->countfile == "") { outGroupsFile << currSeq.getName() << '\t' << thisGroup << endl; } - else { pDataArray->groupMap[currSeq.getName()] = thisGroup; } - - if (pDataArray->nameFile != "") { - map::iterator itName = pDataArray->nameMap.find(currSeq.getName()); - if (itName != pDataArray->nameMap.end()) { - vector thisSeqsNames; - pDataArray->m->splitAtChar(itName->second, thisSeqsNames, ','); - numRedundants = thisSeqsNames.size()-1; //we already include ourselves below - for (int k = 1; k < thisSeqsNames.size(); k++) { //start at 1 to skip self - outGroupsFile << thisSeqsNames[k] << '\t' << thisGroup << endl; - } - }else { pDataArray->m->mothurOut("[ERROR]: " + currSeq.getName() + " is not in your namefile, please correct."); pDataArray->m->mothurOutEndLine(); } - } - - map::iterator it = pDataArray->groupCounts.find(thisGroup); - if (it == pDataArray->groupCounts.end()) { pDataArray->groupCounts[thisGroup] = 1 + numRedundants; } - else { pDataArray->groupCounts[it->first] += (1 + numRedundants); } + } + } + + int pos = thisGroup.find("ignore"); + if (pos == string::npos) { + + currSeq.setAligned(currSeq.getUnaligned()); + currSeq.printSequence(trimFASTAFile); + + if(pDataArray->qFileName != ""){ + currQual.printQScores(trimQualFile); + } + + if(pDataArray->nameFile != ""){ + map::iterator itName = pDataArray->nameMap.find(currSeq.getName()); + if (itName != pDataArray->nameMap.end()) { trimNameFile << itName->first << '\t' << itName->second << endl; } + else { pDataArray->m->mothurOut("[ERROR]: " + currSeq.getName() + " is not in your namefile, please correct."); pDataArray->m->mothurOutEndLine(); } + } + + int numRedundants = 0; + if (pDataArray->countfile != "") { + map::iterator itCount = pDataArray->nameCount.find(currSeq.getName()); + if (itCount != pDataArray->nameCount.end()) { + trimCountFile << itCount->first << '\t' << itCount->second << endl; + numRedundants = itCount->second-1; + }else { pDataArray->m->mothurOut("[ERROR]: " + currSeq.getName() + " is not in your count file, please correct."); pDataArray->m->mothurOutEndLine(); } + } + + if (pDataArray->createGroup) { + if(pDataArray->barcodes.size() != 0){ + + if (pDataArray->countfile == "") { outGroupsFile << currSeq.getName() << '\t' << thisGroup << endl; } + else { pDataArray->groupMap[currSeq.getName()] = thisGroup; } + + if (pDataArray->nameFile != "") { + map::iterator itName = pDataArray->nameMap.find(currSeq.getName()); + if (itName != pDataArray->nameMap.end()) { + vector thisSeqsNames; + pDataArray->m->splitAtChar(itName->second, thisSeqsNames, ','); + numRedundants = thisSeqsNames.size()-1; //we already include ourselves below + for (int k = 1; k < thisSeqsNames.size(); k++) { //start at 1 to skip self + outGroupsFile << thisSeqsNames[k] << '\t' << thisGroup << endl; + } + }else { pDataArray->m->mothurOut("[ERROR]: " + currSeq.getName() + " is not in your namefile, please correct."); pDataArray->m->mothurOutEndLine(); } + } + + map::iterator it = pDataArray->groupCounts.find(thisGroup); + if (it == pDataArray->groupCounts.end()) { pDataArray->groupCounts[thisGroup] = 1 + numRedundants; } + else { pDataArray->groupCounts[it->first] += (1 + numRedundants); } + + } + } + + if(pDataArray->allFiles){ + ofstream output; + pDataArray->m->openOutputFileAppend(pDataArray->fastaFileNames[barcodeIndex][primerIndex], output); + currSeq.printSequence(output); + output.close(); - } - } - - if(pDataArray->allFiles){ - ofstream output; - pDataArray->m->openOutputFileAppend(pDataArray->fastaFileNames[barcodeIndex][primerIndex], output); - currSeq.printSequence(output); - output.close(); - - if(pDataArray->qFileName != ""){ - pDataArray->m->openOutputFileAppend(pDataArray->qualFileNames[barcodeIndex][primerIndex], output); - currQual.printQScores(output); - output.close(); - } - - if(pDataArray->nameFile != ""){ - map::iterator itName = pDataArray->nameMap.find(currSeq.getName()); - if (itName != pDataArray->nameMap.end()) { - pDataArray->m->openOutputFileAppend(pDataArray->nameFileNames[barcodeIndex][primerIndex], output); - output << itName->first << '\t' << itName->second << endl; - output.close(); - }else { pDataArray->m->mothurOut("[ERROR]: " + currSeq.getName() + " is not in your namefile, please correct."); pDataArray->m->mothurOutEndLine(); } - } - } + if(pDataArray->qFileName != ""){ + pDataArray->m->openOutputFileAppend(pDataArray->qualFileNames[barcodeIndex][primerIndex], output); + currQual.printQScores(output); + output.close(); + } + + if(pDataArray->nameFile != ""){ + map::iterator itName = pDataArray->nameMap.find(currSeq.getName()); + if (itName != pDataArray->nameMap.end()) { + pDataArray->m->openOutputFileAppend(pDataArray->nameFileNames[barcodeIndex][primerIndex], output); + output << itName->first << '\t' << itName->second << endl; + output.close(); + }else { pDataArray->m->mothurOut("[ERROR]: " + currSeq.getName() + " is not in your namefile, please correct."); pDataArray->m->mothurOutEndLine(); } + } + } + } } else{ if(pDataArray->nameFile != ""){ //needs to be before the currSeq name is changed