X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=getseqscommand.cpp;h=a1cf493f9e515f91ed962726b392426db9efd978;hp=5db28888b8dbe0ac643779b1cdcbe6ae01a37389;hb=cf9987b67aa49777a4c91c2d21f96e58bf17aa82;hpb=ca9ac1d80c62f57270b0dcd49410ebe08a8aecd6 diff --git a/getseqscommand.cpp b/getseqscommand.cpp index 5db2888..a1cf493 100644 --- a/getseqscommand.cpp +++ b/getseqscommand.cpp @@ -10,22 +10,26 @@ #include "getseqscommand.h" #include "sequence.hpp" #include "listvector.hpp" +#include "counttable.h" //********************************************************************************************************************** vector GetSeqsCommand::setParameters(){ try { - CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pfasta); - CommandParameter pname("name", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pname); - CommandParameter pgroup("group", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pgroup); - CommandParameter plist("list", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(plist); - CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(ptaxonomy); - CommandParameter palignreport("alignreport", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(palignreport); - CommandParameter pqfile("qfile", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pqfile); - CommandParameter paccnos("accnos", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(paccnos); - CommandParameter pdups("dups", "Boolean", "", "T", "", "", "",false,false); parameters.push_back(pdups); - CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir); - CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir); - + CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "FNGLT", "none","fasta",false,false,true); parameters.push_back(pfasta); + CommandParameter pfastq("fastq", "InputTypes", "", "", "none", "FNGLT", "none","fastq",false,false,true); parameters.push_back(pfastq); + CommandParameter pname("name", "InputTypes", "", "", "NameCount", "FNGLT", "none","name",false,false,true); parameters.push_back(pname); + CommandParameter pcount("count", "InputTypes", "", "", "NameCount-CountGroup", "FNGLT", "none","count",false,false,true); parameters.push_back(pcount); + CommandParameter pgroup("group", "InputTypes", "", "", "CountGroup", "FNGLT", "none","group",false,false,true); parameters.push_back(pgroup); + CommandParameter plist("list", "InputTypes", "", "", "none", "FNGLT", "none","list",false,false,true); parameters.push_back(plist); + CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "none", "FNGLT", "none","taxonomy",false,false,true); parameters.push_back(ptaxonomy); + CommandParameter palignreport("alignreport", "InputTypes", "", "", "none", "FNGLT", "none","alignreport",false,false); parameters.push_back(palignreport); + CommandParameter pqfile("qfile", "InputTypes", "", "", "none", "FNGLT", "none","qfile",false,false); parameters.push_back(pqfile); + CommandParameter paccnos("accnos", "InputTypes", "", "", "none", "none", "none","",false,true,true); parameters.push_back(paccnos); + CommandParameter pdups("dups", "Boolean", "", "T", "", "", "","",false,false); parameters.push_back(pdups); + CommandParameter pinputdir("inputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(pinputdir); + CommandParameter poutputdir("outputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(poutputdir); + CommandParameter paccnos2("accnos2", "InputTypes", "", "", "none", "none", "none","",false,false); parameters.push_back(paccnos2); + vector myArray; for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); } return myArray; @@ -39,13 +43,13 @@ vector GetSeqsCommand::setParameters(){ string GetSeqsCommand::getHelpString(){ try { string helpString = ""; - helpString += "The get.seqs command reads an .accnos file and any of the following file types: fasta, name, group, list, taxonomy, quality or alignreport file.\n"; + helpString += "The get.seqs command reads an .accnos file and any of the following file types: fasta, name, group, count, list, taxonomy, quality, fastq or alignreport file.\n"; helpString += "It outputs a file containing only the sequences in the .accnos file.\n"; - helpString += "The get.seqs command parameters are accnos, fasta, name, group, list, taxonomy, qfile, alignreport and dups. You must provide accnos unless you have a valid current accnos file, and at least one of the other parameters.\n"; - helpString += "The dups parameter allows you to add the entire line from a name file if you add any name from the line. default=false. \n"; + helpString += "The get.seqs command parameters are accnos, fasta, name, group, list, taxonomy, qfile, alignreport, fastq and dups. You must provide accnos unless you have a valid current accnos file, and at least one of the other parameters.\n"; + helpString += "The dups parameter allows you to add the entire line from a name file if you add any name from the line. default=true. \n"; helpString += "The get.seqs command should be in the following format: get.seqs(accnos=yourAccnos, fasta=yourFasta).\n"; helpString += "Example get.seqs(accnos=amazon.accnos, fasta=amazon.fasta).\n"; - helpString += "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n\n"; + helpString += "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n"; return helpString; } catch(exception& e) { @@ -61,12 +65,14 @@ GetSeqsCommand::GetSeqsCommand(){ setParameters(); vector tempOutNames; outputTypes["fasta"] = tempOutNames; + outputTypes["fastq"] = tempOutNames; outputTypes["taxonomy"] = tempOutNames; outputTypes["name"] = tempOutNames; outputTypes["group"] = tempOutNames; outputTypes["alignreport"] = tempOutNames; outputTypes["list"] = tempOutNames; outputTypes["qfile"] = tempOutNames; + outputTypes["count"] = tempOutNames; outputTypes["accnosreport"] = tempOutNames; } catch(exception& e) { @@ -75,12 +81,37 @@ GetSeqsCommand::GetSeqsCommand(){ } } //********************************************************************************************************************** +string GetSeqsCommand::getOutputPattern(string type) { + try { + string pattern = ""; + + if (type == "fasta") { pattern = "[filename],pick,[extension]"; } + else if (type == "fastq") { pattern = "[filename],pick,[extension]"; } + else if (type == "taxonomy") { pattern = "[filename],pick,[extension]"; } + else if (type == "name") { pattern = "[filename],pick,[extension]"; } + else if (type == "group") { pattern = "[filename],pick,[extension]"; } + else if (type == "count") { pattern = "[filename],pick,[extension]"; } + else if (type == "list") { pattern = "[filename],[distance],pick,[extension]"; } + else if (type == "qfile") { pattern = "[filename],pick,[extension]"; } + else if (type == "accnosreport") { pattern = "[filename],pick.accnos.report"; } + else if (type == "alignreport") { pattern = "[filename],pick.align.report"; } + else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; } + + return pattern; + } + catch(exception& e) { + m->errorOut(e, "GetSeqsCommand", "getOutputPattern"); + exit(1); + } +} +//********************************************************************************************************************** GetSeqsCommand::GetSeqsCommand(string option) { try { abort = false; calledHelp = false; //allow user to run help if(option == "help") { help(); abort = true; calledHelp = true; } + else if(option == "citation") { citation(); abort = true; calledHelp = true;} else { vector myArray = setParameters(); @@ -99,6 +130,7 @@ GetSeqsCommand::GetSeqsCommand(string option) { //initialize outputTypes vector tempOutNames; outputTypes["fasta"] = tempOutNames; + outputTypes["fastq"] = tempOutNames; outputTypes["taxonomy"] = tempOutNames; outputTypes["name"] = tempOutNames; outputTypes["group"] = tempOutNames; @@ -106,6 +138,7 @@ GetSeqsCommand::GetSeqsCommand(string option) { outputTypes["list"] = tempOutNames; outputTypes["qfile"] = tempOutNames; outputTypes["accnosreport"] = tempOutNames; + outputTypes["count"] = tempOutNames; //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"){ outputDir = ""; } @@ -186,6 +219,22 @@ GetSeqsCommand::GetSeqsCommand(string option) { //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("count"); + //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["count"] = inputDir + it->second; } + } + + it = parameters.find("fastq"); + //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["fastq"] = inputDir + it->second; } + } } @@ -199,21 +248,24 @@ GetSeqsCommand::GetSeqsCommand(string option) { m->mothurOut("You have no valid accnos file and accnos is required."); m->mothurOutEndLine(); abort = true; } - } + }else { m->setAccnosFile(accnosfile); } if (accnosfile2 == "not found") { accnosfile2 = ""; } fastafile = validParameter.validFile(parameters, "fasta", true); - if (fastafile == "not open") { abort = true; } - else if (fastafile == "not found") { fastafile = ""; } + if (fastafile == "not open") { fastafile = ""; abort = true; } + else if (fastafile == "not found") { fastafile = ""; } + else { m->setFastaFile(fastafile); } namefile = validParameter.validFile(parameters, "name", true); - if (namefile == "not open") { abort = true; } + if (namefile == "not open") { namefile = ""; abort = true; } else if (namefile == "not found") { namefile = ""; } + else { m->setNameFile(namefile); } groupfile = validParameter.validFile(parameters, "group", true); if (groupfile == "not open") { abort = true; } else if (groupfile == "not found") { groupfile = ""; } + else { m->setGroupFile(groupfile); } alignfile = validParameter.validFile(parameters, "alignreport", true); if (alignfile == "not open") { abort = true; } @@ -222,20 +274,52 @@ GetSeqsCommand::GetSeqsCommand(string option) { listfile = validParameter.validFile(parameters, "list", true); if (listfile == "not open") { abort = true; } else if (listfile == "not found") { listfile = ""; } + else { m->setListFile(listfile); } taxfile = validParameter.validFile(parameters, "taxonomy", true); - if (taxfile == "not open") { abort = true; } + if (taxfile == "not open") { taxfile = ""; abort = true; } else if (taxfile == "not found") { taxfile = ""; } + else { m->setTaxonomyFile(taxfile); } qualfile = validParameter.validFile(parameters, "qfile", true); if (qualfile == "not open") { abort = true; } else if (qualfile == "not found") { qualfile = ""; } + else { m->setQualFile(qualfile); } + + fastqfile = validParameter.validFile(parameters, "fastq", true); + if (fastqfile == "not open") { abort = true; } + else if (fastqfile == "not found") { fastqfile = ""; } + + accnosfile2 = validParameter.validFile(parameters, "accnos2", true); + if (accnosfile2 == "not open") { abort = true; } + else if (accnosfile2 == "not found") { accnosfile2 = ""; } + + countfile = validParameter.validFile(parameters, "count", true); + if (countfile == "not open") { countfile = ""; abort = true; } + else if (countfile == "not found") { countfile = ""; } + else { m->setCountTableFile(countfile); } + + if ((namefile != "") && (countfile != "")) { + m->mothurOut("[ERROR]: you may only use one of the following: name or count."); m->mothurOutEndLine(); abort = true; + } + + if ((groupfile != "") && (countfile != "")) { + m->mothurOut("[ERROR]: you may only use one of the following: group or count."); m->mothurOutEndLine(); abort=true; + } + string usedDups = "true"; string temp = validParameter.validFile(parameters, "dups", false); if (temp == "not found") { temp = "true"; usedDups = ""; } dups = m->isTrue(temp); - if ((fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == "") && (taxfile == "") && (qualfile == "") && (accnosfile2 == "")) { m->mothurOut("You must provide one of the following: fasta, name, group, alignreport, taxonomy, quality or listfile."); m->mothurOutEndLine(); abort = true; } + if ((fastqfile == "") && (fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == "") && (taxfile == "") && (qualfile == "") && (accnosfile2 == "") && (countfile == "")) { m->mothurOut("You must provide one of the following: fasta, name, group, count, alignreport, taxonomy, quality, fastq or listfile."); m->mothurOutEndLine(); abort = true; } + + if (countfile == "") { + if ((namefile == "") && ((fastafile != "") || (taxfile != ""))){ + vector files; files.push_back(fastafile); files.push_back(taxfile); + parser.getNameFile(files); + } + } } } @@ -252,23 +336,32 @@ int GetSeqsCommand::execute(){ if (abort == true) { if (calledHelp) { return 0; } return 2; } //get names you want to keep - readAccnos(); + names = m->readAccnos(accnosfile); if (m->control_pressed) { return 0; } + + if (countfile != "") { + if ((fastafile != "") || (listfile != "") || (taxfile != "")) { + m->mothurOut("\n[NOTE]: The count file should contain only unique names, so mothur assumes your fasta, list and taxonomy files also contain only uniques.\n\n"); + } + } //read through the correct file and output lines you want to keep if (namefile != "") { readName(); } if (fastafile != "") { readFasta(); } + if (fastqfile != "") { readFastq(); } if (groupfile != "") { readGroup(); } + if (countfile != "") { readCount(); } if (alignfile != "") { readAlign(); } if (listfile != "") { readList(); } if (taxfile != "") { readTax(); } if (qualfile != "") { readQual(); } if (accnosfile2 != "") { compareAccnos(); } + + if (m->debug) { runSanityCheck(); } - if (m->control_pressed) { outputTypes.clear(); for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } + if (m->control_pressed) { outputTypes.clear(); for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } - m->mothurOut("Selected " + toString(names.size()) + " sequences."); m->mothurOutEndLine(); if (outputNames.size() != 0) { m->mothurOutEndLine(); @@ -308,6 +401,10 @@ int GetSeqsCommand::execute(){ if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setQualFile(current); } } + itTypes = outputTypes.find("count"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setCountTableFile(current); } + } } return 0; @@ -318,13 +415,81 @@ int GetSeqsCommand::execute(){ exit(1); } } +//********************************************************************************************************************** +int GetSeqsCommand::readFastq(){ + try { + bool wroteSomething = false; + int selectedCount = 0; + + ifstream in; + m->openInputFile(fastqfile, in); + + string thisOutputDir = outputDir; + if (outputDir == "") { thisOutputDir += m->hasPath(fastqfile); } + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(fastqfile)); + variables["[extension]"] = m->getExtension(fastqfile); + string outputFileName = getOutputFileName("fastq", variables); + ofstream out; + m->openOutputFile(outputFileName, out); + + + while(!in.eof()){ + + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } + + //read sequence name + string input = m->getline(in); m->gobble(in); + + string outputString = input + "\n"; + + if (input[0] == '@') { + //get rest of lines + outputString += m->getline(in) + "\n"; m->gobble(in); + outputString += m->getline(in) + "\n"; m->gobble(in); + outputString += m->getline(in) + "\n"; m->gobble(in); + + vector splits = m->splitWhiteSpace(input); + string name = splits[0]; + name = name.substr(1); + m->checkName(name); + + if (names.count(name) != 0) { + wroteSomething = true; + selectedCount++; + out << outputString; + } + } + + m->gobble(in); + } + in.close(); + out.close(); + + + if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); } + outputNames.push_back(outputFileName); outputTypes["fastq"].push_back(outputFileName); + + m->mothurOut("Selected " + toString(selectedCount) + " sequences from your fastq file."); m->mothurOutEndLine(); + + return 0; + + } + catch(exception& e) { + m->errorOut(e, "GetSeqsCommand", "readFastq"); + exit(1); + } +} //********************************************************************************************************************** int GetSeqsCommand::readFasta(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(fastafile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(fastafile)) + "pick" + m->getExtension(fastafile); + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(fastafile)); + variables["[extension]"] = m->getExtension(fastafile); + string outputFileName = getOutputFileName("fasta", variables); ofstream out; m->openOutputFile(outputFileName, out); @@ -334,20 +499,33 @@ int GetSeqsCommand::readFasta(){ string name; bool wroteSomething = false; + int selectedCount = 0; + + if (m->debug) { set temp; sanity["fasta"] = temp; } while(!in.eof()){ - if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } Sequence currSeq(in); name = currSeq.getName(); + + if (!dups) {//adjust name if needed + map::iterator it = uniqueMap.find(name); + if (it != uniqueMap.end()) { currSeq.setName(it->second); } + } + name = currSeq.getName(); + if (name != "") { //if this name is in the accnos file if (names.count(name) != 0) { wroteSomething = true; currSeq.printSequence(out); + selectedCount++; + + if (m->debug) { sanity["fasta"].insert(name); } } } m->gobble(in); @@ -359,6 +537,8 @@ int GetSeqsCommand::readFasta(){ if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); } outputNames.push_back(outputFileName); outputTypes["fasta"].push_back(outputFileName); + m->mothurOut("Selected " + toString(selectedCount) + " sequences from your fasta file."); m->mothurOutEndLine(); + return 0; } @@ -372,7 +552,10 @@ int GetSeqsCommand::readQual(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(qualfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(qualfile)) + "pick" + m->getExtension(qualfile); + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(qualfile)); + variables["[extension]"] = m->getExtension(qualfile); + string outputFileName = getOutputFileName("qfile", variables); ofstream out; m->openOutputFile(outputFileName, out); @@ -382,20 +565,27 @@ int GetSeqsCommand::readQual(){ string name; bool wroteSomething = false; + int selectedCount = 0; + if (m->debug) { set temp; sanity["qual"] = temp; } while(!in.eof()){ string saveName = ""; string name = ""; string scores = ""; - in >> name; + in >> name; + + if (!dups) {//adjust name if needed + map::iterator it = uniqueMap.find(name); + if (it != uniqueMap.end()) { name = it->second; } + } if (name.length() != 0) { saveName = name.substr(1); while (!in.eof()) { char c = in.get(); - if (c == 10 || c == 13){ break; } + if (c == 10 || c == 13 || c == -1){ break; } else { name += c; } } m->gobble(in); @@ -413,6 +603,8 @@ int GetSeqsCommand::readQual(){ wroteSomething = true; out << name << endl << scores; + selectedCount++; + if (m->debug) { sanity["qual"].insert(name); } } m->gobble(in); @@ -424,6 +616,9 @@ int GetSeqsCommand::readQual(){ if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); } outputNames.push_back(outputFileName); outputTypes["qfile"].push_back(outputFileName); + m->mothurOut("Selected " + toString(selectedCount) + " sequences from your quality file."); m->mothurOutEndLine(); + + return 0; } @@ -433,22 +628,86 @@ int GetSeqsCommand::readQual(){ } } //********************************************************************************************************************** -int GetSeqsCommand::readList(){ +int GetSeqsCommand::readCount(){ try { string thisOutputDir = outputDir; - if (outputDir == "") { thisOutputDir += m->hasPath(listfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(listfile)) + "pick" + m->getExtension(listfile); + if (outputDir == "") { thisOutputDir += m->hasPath(countfile); } + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(countfile)); + variables["[extension]"] = m->getExtension(countfile); + string outputFileName = getOutputFileName("count", variables); + ofstream out; m->openOutputFile(outputFileName, out); + ifstream in; + m->openInputFile(countfile, in); + + bool wroteSomething = false; + int selectedCount = 0; + + string headers = m->getline(in); m->gobble(in); + out << headers << endl; + + string name, rest; int thisTotal; + while (!in.eof()) { + + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } + + in >> name; m->gobble(in); + in >> thisTotal; m->gobble(in); + rest = m->getline(in); m->gobble(in); + if (m->debug) { m->mothurOut("[DEBUG]: " + name + '\t' + rest + "\n"); } + + if (names.count(name) != 0) { + out << name << '\t' << thisTotal << '\t' << rest << endl; + wroteSomething = true; + selectedCount+= thisTotal; + } + } + in.close(); + out.close(); + + //check for groups that have been eliminated + CountTable ct; + if (ct.testGroups(outputFileName)) { + ct.readTable(outputFileName, true, false); + ct.printTable(outputFileName); + } + + if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); } + outputTypes["count"].push_back(outputFileName); outputNames.push_back(outputFileName); + + m->mothurOut("Selected " + toString(selectedCount) + " sequences from your count file."); m->mothurOutEndLine(); + + return 0; + } + catch(exception& e) { + m->errorOut(e, "GetSeqsCommand", "readCount"); + exit(1); + } +} + +//********************************************************************************************************************** +int GetSeqsCommand::readList(){ + try { + string thisOutputDir = outputDir; + if (outputDir == "") { thisOutputDir += m->hasPath(listfile); } + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(listfile)); + variables["[extension]"] = m->getExtension(listfile); + ifstream in; m->openInputFile(listfile, in); bool wroteSomething = false; + int selectedCount = 0; + + if (m->debug) { set temp; sanity["list"] = temp; } while(!in.eof()){ - if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } + selectedCount = 0; //read in list vector ListVector list(in); @@ -456,45 +715,59 @@ int GetSeqsCommand::readList(){ //make a new list vector ListVector newList; newList.setLabel(list.getLabel()); + + variables["[distance]"] = list.getLabel(); + string outputFileName = getOutputFileName("list", variables); + + ofstream out; + m->openOutputFile(outputFileName, out); + outputTypes["list"].push_back(outputFileName); outputNames.push_back(outputFileName); + + vector binLabels = list.getLabels(); + vector newBinLabels; + + if (m->control_pressed) { in.close(); out.close(); return 0; } //for each bin for (int i = 0; i < list.getNumBins(); i++) { //parse out names that are in accnos file string binnames = list.get(i); + vector bnames; + m->splitAtComma(binnames, bnames); string newNames = ""; - while (binnames.find_first_of(',') != -1) { - string name = binnames.substr(0,binnames.find_first_of(',')); - binnames = binnames.substr(binnames.find_first_of(',')+1, binnames.length()); - + for (int j = 0; j < bnames.size(); j++) { + string name = bnames[j]; //if that name is in the .accnos file, add it - if (names.count(name) != 0) { newNames += name + ","; } + if (names.count(name) != 0) { newNames += name + ","; selectedCount++; if (m->debug) { sanity["list"].insert(name); } } } - //get last name - if (names.count(binnames) != 0) { newNames += binnames + ","; } - //if there are names in this bin add to new list if (newNames != "") { newNames = newNames.substr(0, newNames.length()-1); //rip off extra comma - newList.push_back(newNames); + newList.push_back(newNames); + newBinLabels.push_back(binLabels[i]); } } //print new listvector if (newList.getNumBins() != 0) { wroteSomething = true; + newList.setLabels(newBinLabels); + newList.printHeaders(out); newList.print(out); } m->gobble(in); + out.close(); } in.close(); - out.close(); + if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); } - outputNames.push_back(outputFileName); outputTypes["list"].push_back(outputFileName); + + m->mothurOut("Selected " + toString(selectedCount) + " sequences from your list file."); m->mothurOutEndLine(); return 0; @@ -509,7 +782,10 @@ int GetSeqsCommand::readName(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(namefile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(namefile)) + "pick" + m->getExtension(namefile); + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(namefile)); + variables["[extension]"] = m->getExtension(namefile); + string outputFileName = getOutputFileName("name", variables); ofstream out; m->openOutputFile(outputFileName, out); @@ -519,13 +795,16 @@ int GetSeqsCommand::readName(){ string name, firstCol, secondCol; bool wroteSomething = false; - + int selectedCount = 0; + + if (m->debug) { set temp; sanity["name"] = temp; } + if (m->debug) { set temp; sanity["dupname"] = temp; } while(!in.eof()){ - if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } - in >> firstCol; + in >> firstCol; m->gobble(in); in >> secondCol; string hold = ""; @@ -538,14 +817,20 @@ int GetSeqsCommand::readName(){ for (int i = 0; i < parsedNames.size(); i++) { if (names.count(parsedNames[i]) != 0) { validSecond.push_back(parsedNames[i]); + if (m->debug) { sanity["dupname"].insert(parsedNames[i]); } } } if ((dups) && (validSecond.size() != 0)) { //dups = true and we want to add someone, then add everyone - for (int i = 0; i < parsedNames.size(); i++) { names.insert(parsedNames[i]); } + for (int i = 0; i < parsedNames.size(); i++) { names.insert(parsedNames[i]); if (m->debug) { sanity["dupname"].insert(parsedNames[i]); } } out << firstCol << '\t' << hold << endl; wroteSomething = true; + selectedCount += parsedNames.size(); + if (m->debug) { sanity["name"].insert(firstCol); } }else { + + selectedCount += validSecond.size(); + //if the name in the first column is in the set then print it and any other names in second column also in set if (names.count(firstCol) != 0) { @@ -556,20 +841,27 @@ int GetSeqsCommand::readName(){ //you know you have at least one valid second since first column is valid for (int i = 0; i < validSecond.size()-1; i++) { out << validSecond[i] << ','; } out << validSecond[validSecond.size()-1] << endl; + + if (m->debug) { sanity["name"].insert(firstCol); } //make first name in set you come to first column and then add the remaining names to second column }else { + //you want part of this row if (validSecond.size() != 0) { wroteSomething = true; out << validSecond[0] << '\t'; + //we are changing the unique name in the fasta file + uniqueMap[firstCol] = validSecond[0]; //you know you have at least one valid second since first column is valid for (int i = 0; i < validSecond.size()-1; i++) { out << validSecond[i] << ','; } out << validSecond[validSecond.size()-1] << endl; + + if (m->debug) { sanity["name"].insert(validSecond[0]); } } } } @@ -581,6 +873,8 @@ int GetSeqsCommand::readName(){ if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); } outputNames.push_back(outputFileName); outputTypes["name"].push_back(outputFileName); + m->mothurOut("Selected " + toString(selectedCount) + " sequences from your name file."); m->mothurOutEndLine(); + return 0; } @@ -595,7 +889,10 @@ int GetSeqsCommand::readGroup(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(groupfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(groupfile)) + "pick" + m->getExtension(groupfile); + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(groupfile)); + variables["[extension]"] = m->getExtension(groupfile); + string outputFileName = getOutputFileName("group", variables); ofstream out; m->openOutputFile(outputFileName, out); @@ -605,20 +902,27 @@ int GetSeqsCommand::readGroup(){ string name, group; bool wroteSomething = false; + int selectedCount = 0; + + if (m->debug) { set temp; sanity["group"] = temp; } while(!in.eof()){ - if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } in >> name; //read from first column in >> group; //read from second column + //if this name is in the accnos file if (names.count(name) != 0) { wroteSomething = true; out << name << '\t' << group << endl; + selectedCount++; + + if (m->debug) { sanity["group"].insert(name); } } m->gobble(in); @@ -629,6 +933,9 @@ int GetSeqsCommand::readGroup(){ if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); } outputNames.push_back(outputFileName); outputTypes["group"].push_back(outputFileName); + m->mothurOut("Selected " + toString(selectedCount) + " sequences from your group file."); m->mothurOutEndLine(); + + return 0; } @@ -642,7 +949,10 @@ int GetSeqsCommand::readTax(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(taxfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(taxfile)) + "pick" + m->getExtension(taxfile); + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(taxfile)); + variables["[extension]"] = m->getExtension(taxfile); + string outputFileName = getOutputFileName("taxonomy", variables); ofstream out; m->openOutputFile(outputFileName, out); @@ -651,19 +961,30 @@ int GetSeqsCommand::readTax(){ string name, tax; bool wroteSomething = false; + int selectedCount = 0; + + if (m->debug) { set temp; sanity["tax"] = temp; } while(!in.eof()){ - if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } in >> name; //read from first column in >> tax; //read from second column + + if (!dups) {//adjust name if needed + map::iterator it = uniqueMap.find(name); + if (it != uniqueMap.end()) { name = it->second; } + } //if this name is in the accnos file if (names.count(name) != 0) { wroteSomething = true; out << name << '\t' << tax << endl; + selectedCount++; + + if (m->debug) { sanity["tax"].insert(name); } } m->gobble(in); @@ -673,6 +994,8 @@ int GetSeqsCommand::readTax(){ if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); } outputNames.push_back(outputFileName); outputTypes["taxonomy"].push_back(outputFileName); + + m->mothurOut("Selected " + toString(selectedCount) + " sequences from your taxonomy file."); m->mothurOutEndLine(); return 0; @@ -688,7 +1011,9 @@ int GetSeqsCommand::readAlign(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(alignfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(alignfile)) + "pick.align.report"; + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(alignfile)); + string outputFileName = getOutputFileName("alignreport", variables); ofstream out; m->openOutputFile(outputFileName, out); @@ -698,6 +1023,7 @@ int GetSeqsCommand::readAlign(){ string name, junk; bool wroteSomething = false; + int selectedCount = 0; //read column headers for (int i = 0; i < 16; i++) { @@ -708,14 +1034,20 @@ int GetSeqsCommand::readAlign(){ while(!in.eof()){ - if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } in >> name; //read from first column + + if (!dups) {//adjust name if needed + map::iterator it = uniqueMap.find(name); + if (it != uniqueMap.end()) { name = it->second; } + } //if this name is in the accnos file if (names.count(name) != 0) { wroteSomething = true; + selectedCount++; out << name << '\t'; @@ -742,6 +1074,8 @@ int GetSeqsCommand::readAlign(){ if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); } outputNames.push_back(outputFileName); outputTypes["alignreport"].push_back(outputFileName); + m->mothurOut("Selected " + toString(selectedCount) + " sequences from your alignreport file."); m->mothurOutEndLine(); + return 0; } @@ -751,28 +1085,95 @@ int GetSeqsCommand::readAlign(){ } } //********************************************************************************************************************** - -int GetSeqsCommand::readAccnos(){ +//just looking at common mistakes. +int GetSeqsCommand::runSanityCheck(){ try { - - ifstream in; - m->openInputFile(accnosfile, in); - string name; - - while(!in.eof()){ - in >> name; - - names.insert(name); - - m->gobble(in); - } - in.close(); - - return 0; + string thisOutputDir = outputDir; + if (outputDir == "") { thisOutputDir += m->hasPath(fastafile); } + string filename = outputDir + "get.seqs.debug.report"; + + ofstream out; + m->openOutputFile(filename, out); + + + //compare fasta, name, qual and taxonomy if given to make sure they contain the same seqs + if (fastafile != "") { + if (namefile != "") { //compare with fasta + if (sanity["fasta"] != sanity["name"]) { //create mismatch file + createMisMatchFile(out, fastafile, namefile, sanity["fasta"], sanity["name"]); + } + } + if (qualfile != "") { + if (sanity["fasta"] != sanity["qual"]) { //create mismatch file + createMisMatchFile(out, fastafile, qualfile, sanity["fasta"], sanity["qual"]); + } + } + if (taxfile != "") { + if (sanity["fasta"] != sanity["tax"]) { //create mismatch file + createMisMatchFile(out, fastafile, taxfile, sanity["fasta"], sanity["tax"]); + } + } + } + + //compare dupnames, groups and list if given to make sure they match + if (namefile != "") { + if (groupfile != "") { + if (sanity["dupname"] != sanity["group"]) { //create mismatch file + createMisMatchFile(out, namefile, groupfile, sanity["dupname"], sanity["group"]); + } + } + if (listfile != "") { + if (sanity["dupname"] != sanity["list"]) { //create mismatch file + createMisMatchFile(out, namefile, listfile, sanity["dupname"], sanity["list"]); + } + } + }else{ + if ((groupfile != "") && (fastafile != "")) { + if (sanity["fasta"] != sanity["group"]) { //create mismatch file + createMisMatchFile(out, fastafile, groupfile, sanity["fasta"], sanity["group"]); + } + } + } + + out.close(); + + if (m->isBlank(filename)) { m->mothurRemove(filename); } + else { m->mothurOut("\n[DEBUG]: " + filename + " contains the file mismatches.\n");outputNames.push_back(filename); outputTypes["debug"].push_back(filename); } + + return 0; + } + catch(exception& e) { + m->errorOut(e, "GetSeqsCommand", "runSanityCheck"); + exit(1); } +} +//********************************************************************************************************************** +//just looking at common mistakes. +int GetSeqsCommand::createMisMatchFile(ofstream& out, string filename1, string filename2, set set1, set set2){ + try { + out << "****************************************" << endl << endl; + out << "Names unique to " << filename1 << ":\n"; + + //remove names in set1 that are also in set2 + for (set::iterator it = set1.begin(); it != set1.end();) { + string name = *it; + + if (set2.count(name) == 0) { out << name << endl; } //name unique to set1 + else { set2.erase(name); } //you are in both so erase + set1.erase(it++); + } + + out << "\nNames unique to " << filename2 << ":\n"; + //output results + for (set::iterator it = set2.begin(); it != set2.end(); it++) { out << *it << endl; } + + out << "****************************************" << endl << endl; + + return 0; + } catch(exception& e) { - m->errorOut(e, "GetSeqsCommand", "readAccnos"); + m->errorOut(e, "GetSeqsCommand", "runSanityCheck"); exit(1); } } @@ -783,7 +1184,10 @@ int GetSeqsCommand::compareAccnos(){ string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(accnosfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(accnosfile)) + "accnos.report"; + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(accnosfile)); + string outputFileName = getOutputFileName("accnosreport", variables); + ofstream out; m->openOutputFile(outputFileName, out); @@ -823,7 +1227,15 @@ int GetSeqsCommand::compareAccnos(){ in >> name; if (namesAccnos.count(name) == 0){ //name unique to accnos2 - namesAccnos2.insert(name); + int pos = name.find_last_of('_'); + string tempName = name; + if (pos != string::npos) { tempName = tempName.substr(pos+1); cout << tempName << endl; } + if (namesAccnos.count(tempName) == 0){ + namesAccnos2.insert(name); + }else { //you are in both so erase + namesAccnos.erase(name); + namesDups.insert(name); + } }else { //you are in both so erase namesAccnos.erase(name); namesDups.insert(name); @@ -868,7 +1280,7 @@ int GetSeqsCommand::compareAccnos(){ } catch(exception& e) { - m->errorOut(e, "GetSeqsCommand", "readAccnos"); + m->errorOut(e, "GetSeqsCommand", "compareAccnos"); exit(1); } }