X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=screenseqscommand.cpp;h=cedb74a9b6c7f0a4162cdc96d9b774105e6cc1d0;hb=3094cb29c613d9687e861e1d0cf9104b7141d24e;hp=8c334cb217b00d709f7bfa35220dce6a8d6c5dad;hpb=348de0f8b17d84ede77081dcf67bd6ef43496677;p=mothur.git diff --git a/screenseqscommand.cpp b/screenseqscommand.cpp index 8c334cb..cedb74a 100644 --- a/screenseqscommand.cpp +++ b/screenseqscommand.cpp @@ -11,15 +11,62 @@ #include "sequence.hpp" //********************************************************************************************************************** -vector ScreenSeqsCommand::getValidParameters(){ +vector ScreenSeqsCommand::setParameters(){ try { - string Array[] = {"fasta", "start", "end", "maxambig", "maxhomop","optimize","criteria", "minlength", "maxlength", - "name", "group", "alignreport","processors","outputdir","inputdir"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(pfasta); + CommandParameter pname("name", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(pname); + CommandParameter pgroup("group", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(pgroup); + CommandParameter pqfile("qfile", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(pqfile); + CommandParameter palignreport("alignreport", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(palignreport); + CommandParameter ptax("taxonomy", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(ptax); + CommandParameter pstart("start", "Number", "", "-1", "", "", "",false,false); parameters.push_back(pstart); + CommandParameter pend("end", "Number", "", "-1", "", "", "",false,false); parameters.push_back(pend); + CommandParameter pmaxambig("maxambig", "Number", "", "-1", "", "", "",false,false); parameters.push_back(pmaxambig); + CommandParameter pmaxhomop("maxhomop", "Number", "", "-1", "", "", "",false,false); parameters.push_back(pmaxhomop); + CommandParameter pminlength("minlength", "Number", "", "-1", "", "", "",false,false); parameters.push_back(pminlength); + CommandParameter pmaxlength("maxlength", "Number", "", "-1", "", "", "",false,false); parameters.push_back(pmaxlength); + CommandParameter pprocessors("processors", "Number", "", "1", "", "", "",false,false); parameters.push_back(pprocessors); + CommandParameter pcriteria("criteria", "Number", "", "90", "", "", "",false,false); parameters.push_back(pcriteria); + CommandParameter poptimize("optimize", "Multiple", "none-start-end-maxambig-maxhomop-minlength-maxlength", "none", "", "", "",true,false); parameters.push_back(poptimize); + CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir); + CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir); + + vector myArray; + for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); } return myArray; } catch(exception& e) { - m->errorOut(e, "ScreenSeqsCommand", "getValidParameters"); + m->errorOut(e, "ScreenSeqsCommand", "setParameters"); + exit(1); + } +} +//********************************************************************************************************************** +string ScreenSeqsCommand::getHelpString(){ + try { + string helpString = ""; + helpString += "The screen.seqs command reads a fastafile and creates .....\n"; + helpString += "The screen.seqs command parameters are fasta, start, end, maxambig, maxhomop, minlength, maxlength, name, group, qfile, alignreport, taxonomy, optimize, criteria and processors.\n"; + helpString += "The fasta parameter is required.\n"; + helpString += "The alignreport and taxonomy parameters allow you to remove bad seqs from taxonomy and alignreport files.\n"; + helpString += "The start parameter .... The default is -1.\n"; + helpString += "The end parameter .... The default is -1.\n"; + helpString += "The maxambig parameter allows you to set the maximum number of ambigious bases allowed. The default is -1.\n"; + helpString += "The maxhomop parameter allows you to set a maximum homopolymer length. \n"; + helpString += "The minlength parameter allows you to set and minimum sequence length. \n"; + helpString += "The maxlength parameter allows you to set and maximum sequence length. \n"; + helpString += "The processors parameter allows you to specify the number of processors to use while running the command. The default is 1.\n"; + helpString += "The optimize and criteria parameters allow you set the start, end, maxabig, maxhomop, minlength and maxlength parameters relative to your set of sequences .\n"; + helpString += "For example optimize=start-end, criteria=90, would set the start and end values to the position 90% of your sequences started and ended.\n"; + helpString += "The name parameter allows you to provide a namesfile, and the group parameter allows you to provide a groupfile.\n"; + helpString += "The screen.seqs command should be in the following format: \n"; + helpString += "screen.seqs(fasta=yourFastaFile, name=youNameFile, group=yourGroupFIle, start=yourStart, end=yourEnd, maxambig=yourMaxambig, \n"; + helpString += "maxhomop=yourMaxhomop, minlength=youMinlength, maxlength=yourMaxlength) \n"; + helpString += "Example screen.seqs(fasta=abrecovery.fasta, name=abrecovery.names, group=abrecovery.groups, start=..., end=..., maxambig=..., maxhomop=..., minlength=..., maxlength=...).\n"; + helpString += "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n"; + return helpString; + } + catch(exception& e) { + m->errorOut(e, "ScreenSeqsCommand", "getHelpString"); exit(1); } } @@ -27,41 +74,21 @@ vector ScreenSeqsCommand::getValidParameters(){ ScreenSeqsCommand::ScreenSeqsCommand(){ try { abort = true; calledHelp = true; + setParameters(); vector tempOutNames; outputTypes["fasta"] = tempOutNames; outputTypes["name"] = tempOutNames; outputTypes["group"] = tempOutNames; outputTypes["alignreport"] = tempOutNames; outputTypes["accnos"] = tempOutNames; + outputTypes["qfile"] = tempOutNames; + outputTypes["taxonomy"] = tempOutNames; } catch(exception& e) { m->errorOut(e, "ScreenSeqsCommand", "ScreenSeqsCommand"); exit(1); } } -//********************************************************************************************************************** -vector ScreenSeqsCommand::getRequiredParameters(){ - try { - string Array[] = {"fasta"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); - return myArray; - } - catch(exception& e) { - m->errorOut(e, "ScreenSeqsCommand", "getRequiredParameters"); - exit(1); - } -} -//********************************************************************************************************************** -vector ScreenSeqsCommand::getRequiredFiles(){ - try { - vector myArray; - return myArray; - } - catch(exception& e) { - m->errorOut(e, "ScreenSeqsCommand", "getRequiredFiles"); - exit(1); - } -} //*************************************************************************************************************** ScreenSeqsCommand::ScreenSeqsCommand(string option) { @@ -70,12 +97,10 @@ ScreenSeqsCommand::ScreenSeqsCommand(string option) { //allow user to run help if(option == "help") { help(); abort = true; calledHelp = true; } + else if(option == "citation") { citation(); abort = true; calledHelp = true;} else { - //valid paramters for this command - string AlignArray[] = {"fasta", "start", "end", "maxambig", "maxhomop","optimize","criteria", "minlength", "maxlength", - "name", "group", "alignreport","processors","outputdir","inputdir"}; - vector myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string))); + vector myArray = setParameters(); OptionParser parser(option); map parameters = parser.getParameters(); @@ -95,6 +120,8 @@ ScreenSeqsCommand::ScreenSeqsCommand(string option) { outputTypes["group"] = tempOutNames; outputTypes["alignreport"] = tempOutNames; outputTypes["accnos"] = tempOutNames; + outputTypes["qfile"] = tempOutNames; + outputTypes["taxonomy"] = tempOutNames; //if the user changes the input directory command factory will send this info to us in the output parameter string inputDir = validParameter.validFile(parameters, "inputdir", false); @@ -132,24 +159,56 @@ ScreenSeqsCommand::ScreenSeqsCommand(string option) { //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["alignreport"] = inputDir + it->second; } } + + it = parameters.find("qfile"); + //user has given a template file + if(it != parameters.end()){ + path = m->hasPath(it->second); + //if the user has not given a path then, add inputdir. else leave path alone. + if (path == "") { parameters["qfile"] = inputDir + it->second; } + } + + it = parameters.find("taxonomy"); + //user has given a template file + if(it != parameters.end()){ + path = m->hasPath(it->second); + //if the user has not given a path then, add inputdir. else leave path alone. + if (path == "") { parameters["taxonomy"] = inputDir + it->second; } + } } //check for required parameters fastafile = validParameter.validFile(parameters, "fasta", true); - if (fastafile == "not found") { m->mothurOut("fasta is a required parameter for the screen.seqs command."); m->mothurOutEndLine(); abort = true; } - else if (fastafile == "not open") { abort = true; } + if (fastafile == "not found") { + fastafile = m->getFastaFile(); + if (fastafile != "") { m->mothurOut("Using " + fastafile + " as input file for the fasta parameter."); m->mothurOutEndLine(); } + else { m->mothurOut("You have no current fastafile and the fasta parameter is required."); m->mothurOutEndLine(); abort = true; } + } + else if (fastafile == "not open") { abort = true; } + else { m->setFastaFile(fastafile); } groupfile = validParameter.validFile(parameters, "group", true); if (groupfile == "not open") { abort = true; } else if (groupfile == "not found") { groupfile = ""; } + else { m->setGroupFile(groupfile); } + + qualfile = validParameter.validFile(parameters, "qfile", true); + if (qualfile == "not open") { abort = true; } + else if (qualfile == "not found") { qualfile = ""; } + else { m->setQualFile(qualfile); } namefile = validParameter.validFile(parameters, "name", true); if (namefile == "not open") { namefile = ""; abort = true; } else if (namefile == "not found") { namefile = ""; } - + else { m->setNameFile(namefile); } + alignreport = validParameter.validFile(parameters, "alignreport", true); if (alignreport == "not open") { abort = true; } - else if (alignreport == "not found") { alignreport = ""; } + else if (alignreport == "not found") { alignreport = ""; } + + taxonomy = validParameter.validFile(parameters, "taxonomy", true); + if (taxonomy == "not open") { abort = true; } + else if (taxonomy == "not found") { taxonomy = ""; } //if the user changes the output directory command factory will send this info to us in the output parameter outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){ @@ -178,17 +237,17 @@ ScreenSeqsCommand::ScreenSeqsCommand(string option) { temp = validParameter.validFile(parameters, "maxlength", false); if (temp == "not found") { temp = "-1"; } convert(temp, maxLength); - temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found"){ temp = "1"; } - convert(temp, processors); + temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found"){ temp = m->getProcessors(); } + m->setProcessors(temp); + convert(temp, processors); temp = validParameter.validFile(parameters, "optimize", false); //optimizing trumps the optimized values original value - if (temp == "not found"){ temp = ""; } - else { m->splitAtDash(temp, optimize); } + if (temp == "not found"){ temp = "none"; } + m->splitAtDash(temp, optimize); //check for invalid optimize options set validOptimizers; - validOptimizers.insert("start"); validOptimizers.insert("end"); validOptimizers.insert("maxambig"); validOptimizers.insert("maxhomop"); validOptimizers.insert("minlength"); validOptimizers.insert("maxlength"); - + validOptimizers.insert("none"); validOptimizers.insert("start"); validOptimizers.insert("end"); validOptimizers.insert("maxambig"); validOptimizers.insert("maxhomop"); validOptimizers.insert("minlength"); validOptimizers.insert("maxlength"); for (int i = 0; i < optimize.size(); i++) { if (validOptimizers.count(optimize[i]) == 0) { m->mothurOut(optimize[i] + " is not a valid optimizer. Valid options are start, end, maxambig, maxhomop, minlength and maxlength."); m->mothurOutEndLine(); @@ -197,6 +256,8 @@ ScreenSeqsCommand::ScreenSeqsCommand(string option) { } } + if (optimize.size() == 1) { if (optimize[0] == "none") { optimize.clear(); } } + temp = validParameter.validFile(parameters, "criteria", false); if (temp == "not found"){ temp = "90"; } convert(temp, criteria); } @@ -207,40 +268,6 @@ ScreenSeqsCommand::ScreenSeqsCommand(string option) { exit(1); } } -//********************************************************************************************************************** - -void ScreenSeqsCommand::help(){ - try { - m->mothurOut("The screen.seqs command reads a fastafile and creates .....\n"); - m->mothurOut("The screen.seqs command parameters are fasta, start, end, maxambig, maxhomop, minlength, maxlength, name, group, optimize, criteria and processors.\n"); - m->mothurOut("The fasta parameter is required.\n"); - m->mothurOut("The start parameter .... The default is -1.\n"); - m->mothurOut("The end parameter .... The default is -1.\n"); - m->mothurOut("The maxambig parameter .... The default is -1.\n"); - m->mothurOut("The maxhomop parameter .... The default is -1.\n"); - m->mothurOut("The minlength parameter .... The default is -1.\n"); - m->mothurOut("The maxlength parameter .... The default is -1.\n"); - m->mothurOut("The processors parameter allows you to specify the number of processors to use while running the command. The default is 1.\n"); - m->mothurOut("The optimize and criteria parameters allow you set the start, end, maxabig, maxhomop, minlength and maxlength parameters relative to your set of sequences .\n"); - m->mothurOut("For example optimize=start-end, criteria=90, would set the start and end values to the position 90% of your sequences started and ended.\n"); - m->mothurOut("The name parameter allows you to provide a namesfile, and the group parameter allows you to provide a groupfile.\n"); - m->mothurOut("The screen.seqs command should be in the following format: \n"); - m->mothurOut("screen.seqs(fasta=yourFastaFile, name=youNameFile, group=yourGroupFIle, start=yourStart, end=yourEnd, maxambig=yourMaxambig, \n"); - m->mothurOut("maxhomop=yourMaxhomop, minlength=youMinlength, maxlength=yourMaxlength) \n"); - m->mothurOut("Example screen.seqs(fasta=abrecovery.fasta, name=abrecovery.names, group=abrecovery.groups, start=..., end=..., maxambig=..., maxhomop=..., minlength=..., maxlength=...).\n"); - m->mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n\n"); - - } - catch(exception& e) { - m->errorOut(e, "ScreenSeqsCommand", "help"); - exit(1); - } -} - -//*************************************************************************************************************** - -ScreenSeqsCommand::~ScreenSeqsCommand(){ /* do nothing */ } - //*************************************************************************************************************** int ScreenSeqsCommand::execute(){ @@ -249,7 +276,7 @@ int ScreenSeqsCommand::execute(){ if (abort == true) { if (calledHelp) { return 0; } return 2; } //if the user want to optimize we need to know the 90% mark - vector positions; + vector positions; if (optimize.size() != 0) { //get summary is paralellized so we need to divideFile, no need to do this step twice so I moved it here //use the namefile to optimize correctly if (namefile != "") { nameMap = m->readNames(namefile); } @@ -272,7 +299,7 @@ int ScreenSeqsCommand::execute(){ #ifdef USE_MPI int pid, numSeqsPerProcessor; int tag = 2001; - vector MPIPos; + vector MPIPos; MPI_Status status; MPI_Comm_rank(MPI_COMM_WORLD, &pid); //find out who we are @@ -382,7 +409,7 @@ int ScreenSeqsCommand::execute(){ if(processors == 1){ numFastaSeqs = driver(lines[0], goodSeqFile, badAccnosFile, fastafile, badSeqNames); - if (m->control_pressed) { remove(goodSeqFile.c_str()); return 0; } + if (m->control_pressed) { m->mothurRemove(goodSeqFile); return 0; } }else{ processIDS.resize(0); @@ -395,13 +422,13 @@ int ScreenSeqsCommand::execute(){ //append alignment and report files for(int i=1;iappendFiles((goodSeqFile + toString(processIDS[i]) + ".temp"), goodSeqFile); - remove((goodSeqFile + toString(processIDS[i]) + ".temp").c_str()); + m->mothurRemove((goodSeqFile + toString(processIDS[i]) + ".temp")); m->appendFiles((badAccnosFile + toString(processIDS[i]) + ".temp"), badAccnosFile); - remove((badAccnosFile + toString(processIDS[i]) + ".temp").c_str()); + m->mothurRemove((badAccnosFile + toString(processIDS[i]) + ".temp")); } - if (m->control_pressed) { remove(goodSeqFile.c_str()); return 0; } + if (m->control_pressed) { m->mothurRemove(goodSeqFile); return 0; } //read badSeqs in because root process doesnt know what other "bad" seqs the children found ifstream inBad; @@ -420,7 +447,7 @@ int ScreenSeqsCommand::execute(){ #else numFastaSeqs = driver(lines[0], goodSeqFile, badAccnosFile, fastafile, badSeqNames); - if (m->control_pressed) { remove(goodSeqFile.c_str()); return 0; } + if (m->control_pressed) { m->mothurRemove(goodSeqFile); return 0; } #endif @@ -461,17 +488,19 @@ int ScreenSeqsCommand::execute(){ if(namefile != "" && groupfile != "") { screenNameGroupFile(badSeqNames); - if (m->control_pressed) { remove(goodSeqFile.c_str()); return 0; } + if (m->control_pressed) { m->mothurRemove(goodSeqFile); return 0; } }else if(namefile != "") { screenNameGroupFile(badSeqNames); - if (m->control_pressed) { remove(goodSeqFile.c_str()); return 0; } + if (m->control_pressed) { m->mothurRemove(goodSeqFile); return 0; } }else if(groupfile != "") { screenGroupFile(badSeqNames); } // this screens just the group - if (m->control_pressed) { remove(goodSeqFile.c_str()); return 0; } + if (m->control_pressed) { m->mothurRemove(goodSeqFile); return 0; } if(alignreport != "") { screenAlignReport(badSeqNames); } + if(qualfile != "") { screenQual(badSeqNames); } + if(taxonomy != "") { screenTaxonomy(badSeqNames); } - if (m->control_pressed) { remove(goodSeqFile.c_str()); return 0; } + if (m->control_pressed) { m->mothurRemove(goodSeqFile); return 0; } #ifdef USE_MPI } @@ -501,6 +530,16 @@ int ScreenSeqsCommand::execute(){ if (itTypes != outputTypes.end()) { if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setGroupFile(current); } } + + itTypes = outputTypes.find("qfile"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setQualFile(current); } + } + + itTypes = outputTypes.find("taxonomy"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setTaxonomyFile(current); } + } m->mothurOut("It took " + toString(time(NULL) - start) + " secs to screen " + toString(numFastaSeqs) + " sequences."); m->mothurOutEndLine(); @@ -529,7 +568,7 @@ int ScreenSeqsCommand::screenNameGroupFile(set badSeqNames){ ofstream goodNameOut; m->openOutputFile(goodNameFile, goodNameOut); while(!inputNames.eof()){ - if (m->control_pressed) { goodNameOut.close(); inputNames.close(); remove(goodNameFile.c_str()); return 0; } + if (m->control_pressed) { goodNameOut.close(); inputNames.close(); m->mothurRemove(goodNameFile); return 0; } inputNames >> seqName >> seqList; it = badSeqNames.find(seqName); @@ -575,7 +614,7 @@ int ScreenSeqsCommand::screenNameGroupFile(set badSeqNames){ ofstream goodGroupOut; m->openOutputFile(goodGroupFile, goodGroupOut); while(!inputGroups.eof()){ - if (m->control_pressed) { goodGroupOut.close(); inputGroups.close(); remove(goodNameFile.c_str()); remove(goodGroupFile.c_str()); return 0; } + if (m->control_pressed) { goodGroupOut.close(); inputGroups.close(); m->mothurRemove(goodNameFile); m->mothurRemove(goodGroupFile); return 0; } inputGroups >> seqName >> group; @@ -611,7 +650,7 @@ int ScreenSeqsCommand::screenNameGroupFile(set badSeqNames){ } } //*************************************************************************************************************** -int ScreenSeqsCommand::getSummary(vector& positions){ +int ScreenSeqsCommand::getSummary(vector& positions){ try { vector startPosition; @@ -620,12 +659,22 @@ int ScreenSeqsCommand::getSummary(vector& positions){ vector ambigBases; vector longHomoPolymer; - vector positions = m->divideFile(fastafile, processors); + vector positions = m->divideFile(fastafile, processors); for (int i = 0; i < (positions.size()-1); i++) { lines.push_back(new linePair(positions[i], positions[(i+1)])); } + +#ifdef USE_MPI + MPI_Comm_rank(MPI_COMM_WORLD, &pid); + + if (pid == 0) { //only one process should fix files + driverCreateSummary(startPosition, endPosition, seqLength, ambigBases, longHomoPolymer, fastafile, lines[0]); + } + + MPI_Barrier(MPI_COMM_WORLD); //make everyone wait +#else int numSeqs = 0; #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) if(processors == 1){ @@ -639,7 +688,7 @@ int ScreenSeqsCommand::getSummary(vector& positions){ numSeqs = driverCreateSummary(startPosition, endPosition, seqLength, ambigBases, longHomoPolymer, fastafile, lines[0]); if (m->control_pressed) { return 0; } #endif - +#endif sort(startPosition.begin(), startPosition.end()); sort(endPosition.begin(), endPosition.end()); sort(seqLength.begin(), seqLength.end()); @@ -706,7 +755,7 @@ int ScreenSeqsCommand::driverCreateSummary(vector& startPosition, vector= filePos->end)) { break; } #else if (in.eof()) { break; } @@ -788,7 +837,7 @@ int ScreenSeqsCommand::createProcessesCreateSummary(vector& startPosition, for (int k = 0; k < tempNum; k++) { in >> temp; longHomoPolymer.push_back(temp); } m->gobble(in); in.close(); - remove(tempFilename.c_str()); + m->mothurRemove(tempFilename); } return num; @@ -814,7 +863,7 @@ int ScreenSeqsCommand::screenGroupFile(set badSeqNames){ ofstream goodGroupOut; m->openOutputFile(goodGroupFile, goodGroupOut); while(!inputGroups.eof()){ - if (m->control_pressed) { goodGroupOut.close(); inputGroups.close(); remove(goodGroupFile.c_str()); return 0; } + if (m->control_pressed) { goodGroupOut.close(); inputGroups.close(); m->mothurRemove(goodGroupFile); return 0; } inputGroups >> seqName >> group; it = badSeqNames.find(seqName); @@ -828,7 +877,7 @@ int ScreenSeqsCommand::screenGroupFile(set badSeqNames){ m->gobble(inputGroups); } - if (m->control_pressed) { goodGroupOut.close(); inputGroups.close(); remove(goodGroupFile.c_str()); return 0; } + if (m->control_pressed) { goodGroupOut.close(); inputGroups.close(); m->mothurRemove(goodGroupFile); return 0; } //we were unable to remove some of the bad sequences if (badSeqNames.size() != 0) { @@ -841,7 +890,7 @@ int ScreenSeqsCommand::screenGroupFile(set badSeqNames){ inputGroups.close(); goodGroupOut.close(); - if (m->control_pressed) { remove(goodGroupFile.c_str()); } + if (m->control_pressed) { m->mothurRemove(goodGroupFile); } return 0; @@ -872,7 +921,7 @@ int ScreenSeqsCommand::screenAlignReport(set badSeqNames){ } while(!inputAlignReport.eof()){ - if (m->control_pressed) { goodAlignReportOut.close(); inputAlignReport.close(); remove(goodAlignReportFile.c_str()); return 0; } + if (m->control_pressed) { goodAlignReportOut.close(); inputAlignReport.close(); m->mothurRemove(goodAlignReportFile); return 0; } inputAlignReport >> seqName; it = badSeqNames.find(seqName); @@ -892,7 +941,7 @@ int ScreenSeqsCommand::screenAlignReport(set badSeqNames){ m->gobble(inputAlignReport); } - if (m->control_pressed) { goodAlignReportOut.close(); inputAlignReport.close(); remove(goodAlignReportFile.c_str()); return 0; } + if (m->control_pressed) { goodAlignReportOut.close(); inputAlignReport.close(); m->mothurRemove(goodAlignReportFile); return 0; } //we were unable to remove some of the bad sequences if (badSeqNames.size() != 0) { @@ -905,7 +954,7 @@ int ScreenSeqsCommand::screenAlignReport(set badSeqNames){ inputAlignReport.close(); goodAlignReportOut.close(); - if (m->control_pressed) { remove(goodAlignReportFile.c_str()); return 0; } + if (m->control_pressed) { m->mothurRemove(goodAlignReportFile); return 0; } return 0; @@ -915,6 +964,129 @@ int ScreenSeqsCommand::screenAlignReport(set badSeqNames){ exit(1); } +} +//*************************************************************************************************************** + +int ScreenSeqsCommand::screenTaxonomy(set badSeqNames){ + try { + ifstream input; + m->openInputFile(taxonomy, input); + string seqName, tax; + set::iterator it; + + string goodTaxFile = outputDir + m->getRootName(m->getSimpleName(taxonomy)) + "good" + m->getExtension(taxonomy); + outputNames.push_back(goodTaxFile); outputTypes["taxonomy"].push_back(goodTaxFile); + ofstream goodTaxOut; m->openOutputFile(goodTaxFile, goodTaxOut); + + while(!input.eof()){ + if (m->control_pressed) { goodTaxOut.close(); input.close(); m->mothurRemove(goodTaxFile); return 0; } + + input >> seqName >> tax; + it = badSeqNames.find(seqName); + + if(it != badSeqNames.end()){ badSeqNames.erase(it); } + else{ + goodTaxOut << seqName << '\t' << tax << endl; + } + m->gobble(input); + } + + if (m->control_pressed) { goodTaxOut.close(); input.close(); m->mothurRemove(goodTaxFile); return 0; } + + //we were unable to remove some of the bad sequences + if (badSeqNames.size() != 0) { + for (it = badSeqNames.begin(); it != badSeqNames.end(); it++) { + m->mothurOut("Your taxonomy file does not include the sequence " + *it + " please correct."); + m->mothurOutEndLine(); + } + } + + input.close(); + goodTaxOut.close(); + + if (m->control_pressed) { m->mothurRemove(goodTaxFile); return 0; } + + return 0; + + } + catch(exception& e) { + m->errorOut(e, "ScreenSeqsCommand", "screenTaxonomy"); + exit(1); + } + +} +//*************************************************************************************************************** + +int ScreenSeqsCommand::screenQual(set badSeqNames){ + try { + ifstream in; + m->openInputFile(qualfile, in); + set::iterator it; + + string goodQualFile = outputDir + m->getRootName(m->getSimpleName(qualfile)) + "good" + m->getExtension(qualfile); + outputNames.push_back(goodQualFile); outputTypes["qfile"].push_back(goodQualFile); + ofstream goodQual; m->openOutputFile(goodQualFile, goodQual); + + while(!in.eof()){ + + if (m->control_pressed) { goodQual.close(); in.close(); m->mothurRemove(goodQualFile); return 0; } + + string saveName = ""; + string name = ""; + string scores = ""; + + in >> name; + + if (name.length() != 0) { + saveName = name.substr(1); + while (!in.eof()) { + char c = in.get(); + if (c == 10 || c == 13){ break; } + else { name += c; } + } + m->gobble(in); + } + + while(in){ + char letter= in.get(); + if(letter == '>'){ in.putback(letter); break; } + else{ scores += letter; } + } + + m->gobble(in); + + it = badSeqNames.find(saveName); + + if(it != badSeqNames.end()){ + badSeqNames.erase(it); + }else{ + goodQual << name << endl << scores; + } + + m->gobble(in); + } + + in.close(); + goodQual.close(); + + //we were unable to remove some of the bad sequences + if (badSeqNames.size() != 0) { + for (it = badSeqNames.begin(); it != badSeqNames.end(); it++) { + m->mothurOut("Your qual file does not include the sequence " + *it + " please correct."); + m->mothurOutEndLine(); + } + } + + if (m->control_pressed) { m->mothurRemove(goodQualFile); return 0; } + + return 0; + + } + catch(exception& e) { + m->errorOut(e, "ScreenSeqsCommand", "screenQual"); + exit(1); + } + } //********************************************************************************************************************** @@ -959,7 +1131,7 @@ int ScreenSeqsCommand::driver(linePair* filePos, string goodFName, string badAcc } #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) - unsigned long int pos = inFASTA.tellg(); + unsigned long long pos = inFASTA.tellg(); if ((pos == -1) || (pos >= filePos->end)) { break; } #else if (inFASTA.eof()) { break; } @@ -985,7 +1157,7 @@ int ScreenSeqsCommand::driver(linePair* filePos, string goodFName, string badAcc } //********************************************************************************************************************** #ifdef USE_MPI -int ScreenSeqsCommand::driverMPI(int start, int num, MPI_File& inMPI, MPI_File& goodFile, MPI_File& badAccnosFile, vector& MPIPos, set& badSeqNames){ +int ScreenSeqsCommand::driverMPI(int start, int num, MPI_File& inMPI, MPI_File& goodFile, MPI_File& badAccnosFile, vector& MPIPos, set& badSeqNames){ try { string outputString = ""; MPI_Status statusGood; @@ -1105,7 +1277,7 @@ int ScreenSeqsCommand::createProcesses(string goodFileName, string badAccnos, st string tempFile = filename + toString(processIDS[i]) + ".num.temp"; m->openInputFile(tempFile, in); if (!in.eof()) { int tempNum = 0; in >> tempNum; num += tempNum; } - in.close(); remove(tempFile.c_str()); + in.close(); m->mothurRemove(tempFile); } return num;