X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=getseqscommand.cpp;h=142023e7a40881c1c6397a761ba350132490b75c;hp=84fe0acab9abc0ec603df10896be1c0fe1e7f47c;hb=70491a12902e89b85cfa6b44a7b7fbe066ee2ac1;hpb=4f3d46bdb42c23468a534486fd105180b030fc65 diff --git a/getseqscommand.cpp b/getseqscommand.cpp index 84fe0ac..142023e 100644 --- a/getseqscommand.cpp +++ b/getseqscommand.cpp @@ -10,22 +10,24 @@ #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 paccnos2("accnos2", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(paccnos2); + CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "FNGLT", "none","fasta",false,false,true); parameters.push_back(pfasta); + 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); } @@ -40,7 +42,7 @@ 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 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"; @@ -68,6 +70,7 @@ GetSeqsCommand::GetSeqsCommand(){ outputTypes["alignreport"] = tempOutNames; outputTypes["list"] = tempOutNames; outputTypes["qfile"] = tempOutNames; + outputTypes["count"] = tempOutNames; outputTypes["accnosreport"] = tempOutNames; } catch(exception& e) { @@ -76,6 +79,29 @@ GetSeqsCommand::GetSeqsCommand(){ } } //********************************************************************************************************************** +string GetSeqsCommand::getOutputPattern(string type) { + try { + string pattern = ""; + + if (type == "fasta") { 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],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; @@ -108,6 +134,7 @@ 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 = ""; } @@ -188,6 +215,14 @@ 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; } + } } @@ -243,17 +278,32 @@ GetSeqsCommand::GetSeqsCommand(string option) { 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 ((namefile == "") && ((fastafile != "") || (taxfile != ""))){ - vector files; files.push_back(fastafile); files.push_back(taxfile); - parser.getNameFile(files); - } + if ((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 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); + } + } } } @@ -270,14 +320,21 @@ 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 (groupfile != "") { readGroup(); } + if (countfile != "") { readCount(); } if (alignfile != "") { readAlign(); } if (listfile != "") { readList(); } if (taxfile != "") { readTax(); } @@ -327,6 +384,10 @@ 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; @@ -343,7 +404,10 @@ 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); @@ -363,6 +427,11 @@ int GetSeqsCommand::readFasta(){ Sequence currSeq(in); name = currSeq.getName(); + + if (!dups) {//adjust name if needed + map::iterator it = uniqueMap.find(name); + if (it != uniqueMap.end()) { name = it->second; } + } if (name != "") { //if this name is in the accnos file @@ -399,7 +468,10 @@ 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); @@ -418,13 +490,18 @@ int GetSeqsCommand::readQual(){ 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); @@ -466,12 +543,76 @@ int GetSeqsCommand::readQual(){ exit(1); } } +//********************************************************************************************************************** +int GetSeqsCommand::readCount(){ + try { + string thisOutputDir = outputDir; + 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); + 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); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(listfile)) + "pick" + m->getExtension(listfile); + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(listfile)); + variables["[extension]"] = m->getExtension(listfile); + string outputFileName = getOutputFileName("list", variables); ofstream out; m->openOutputFile(outputFileName, out); @@ -501,19 +642,16 @@ int GetSeqsCommand::readList(){ //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 i = 0; i < bnames.size(); i++) { + string name = bnames[i]; //if that name is in the .accnos file, add it 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 + ","; selectedCount++; if (m->debug) { sanity["list"].insert(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 @@ -550,7 +688,10 @@ 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); @@ -617,6 +758,8 @@ int GetSeqsCommand::readName(){ 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] << ','; } @@ -650,7 +793,10 @@ 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); @@ -671,6 +817,7 @@ int GetSeqsCommand::readGroup(){ 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) { @@ -706,7 +853,10 @@ 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); @@ -725,6 +875,11 @@ int GetSeqsCommand::readTax(){ 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) { @@ -760,7 +915,9 @@ 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); @@ -785,6 +942,11 @@ int GetSeqsCommand::readAlign(){ 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) { @@ -827,32 +989,6 @@ int GetSeqsCommand::readAlign(){ } } //********************************************************************************************************************** - -int GetSeqsCommand::readAccnos(){ - try { - - ifstream in; - m->openInputFile(accnosfile, in); - string name; - - while(!in.eof()){ - in >> name; - - names.insert(name); - - m->gobble(in); - } - in.close(); - - return 0; - - } - catch(exception& e) { - m->errorOut(e, "GetSeqsCommand", "readAccnos"); - exit(1); - } -} -//********************************************************************************************************************** //just looking at common mistakes. int GetSeqsCommand::runSanityCheck(){ try { @@ -952,7 +1088,10 @@ 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); @@ -1045,7 +1184,7 @@ int GetSeqsCommand::compareAccnos(){ } catch(exception& e) { - m->errorOut(e, "GetSeqsCommand", "readAccnos"); + m->errorOut(e, "GetSeqsCommand", "compareAccnos"); exit(1); } }