X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=listseqscommand.cpp;h=cf884705cb26f341ef08713b118af32fd49c5bdf;hp=23c71ecdcf2ac06f522f034cbea813d4a1f2cd22;hb=050a3ff02473a3d4c0980964e1a9ebe52e55d6b8;hpb=21805b1c466a341d64a5a451f156a56d12c75dca diff --git a/listseqscommand.cpp b/listseqscommand.cpp index 23c71ec..cf88470 100644 --- a/listseqscommand.cpp +++ b/listseqscommand.cpp @@ -10,20 +10,86 @@ #include "listseqscommand.h" #include "sequence.hpp" #include "listvector.hpp" +#include "counttable.h" + +//********************************************************************************************************************** +vector ListSeqsCommand::setParameters(){ + try { + CommandParameter pfasta("fasta", "InputTypes", "", "", "FNGLT", "FNGLT", "none","accnos",false,false,true); parameters.push_back(pfasta); + CommandParameter pname("name", "InputTypes", "", "", "FNGLT", "FNGLT", "none","accnos",false,false,true); parameters.push_back(pname); + CommandParameter pcount("count", "InputTypes", "", "", "FNGLT", "FNGLT", "none","accnos",false,false,true); parameters.push_back(pcount); + CommandParameter pgroup("group", "InputTypes", "", "", "FNGLT", "FNGLT", "none","accnos",false,false,true); parameters.push_back(pgroup); + CommandParameter plist("list", "InputTypes", "", "", "FNGLT", "FNGLT", "none","accnos",false,false,true); parameters.push_back(plist); + CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "FNGLT", "FNGLT", "none","accnos",false,false,true); parameters.push_back(ptaxonomy); + CommandParameter palignreport("alignreport", "InputTypes", "", "", "FNGLT", "FNGLT", "none","accnos",false,false); parameters.push_back(palignreport); + 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, "ListSeqsCommand", "setParameters"); + exit(1); + } +} +//********************************************************************************************************************** +string ListSeqsCommand::getHelpString(){ + try { + string helpString = ""; + helpString += "The list.seqs command reads a fasta, name, group, count, list, taxonomy or alignreport file and outputs a .accnos file containing sequence names.\n"; + helpString += "The list.seqs command parameters are fasta, name, group, count, list, taxonomy and alignreport. You must provide one of these parameters.\n"; + helpString += "The list.seqs command should be in the following format: list.seqs(fasta=yourFasta).\n"; + helpString += "Example list.seqs(fasta=amazon.fasta).\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, "ListSeqsCommand", "getHelpString"); + exit(1); + } +} +//********************************************************************************************************************** +string ListSeqsCommand::getOutputPattern(string type) { + try { + string pattern = ""; + + if (type == "accnos") { pattern = "[filename],accnos"; } + else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; } + + return pattern; + } + catch(exception& e) { + m->errorOut(e, "ListSeqsCommand", "getOutputPattern"); + exit(1); + } +} +//********************************************************************************************************************** +ListSeqsCommand::ListSeqsCommand(){ + try { + abort = true; calledHelp = true; + setParameters(); + vector tempOutNames; + outputTypes["accnos"] = tempOutNames; + } + catch(exception& e) { + m->errorOut(e, "ListSeqsCommand", "ListSeqsCommand"); + exit(1); + } +} //********************************************************************************************************************** ListSeqsCommand::ListSeqsCommand(string option) { try { - abort = false; + abort = false; calledHelp = false; //allow user to run help - if(option == "help") { help(); abort = true; } - + if(option == "help") { help(); abort = true; calledHelp = true; } + else if(option == "citation") { citation(); abort = true; calledHelp = true;} else { - //valid paramters for this command - string Array[] = {"fasta","name", "group", "alignreport","list","outputdir","inputdir"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + vector myArray = setParameters(); OptionParser parser(option); map parameters = parser.getParameters(); @@ -36,6 +102,10 @@ ListSeqsCommand::ListSeqsCommand(string option) { if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; } } + //initialize outputTypes + vector tempOutNames; + outputTypes["accnos"] = 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 = ""; } @@ -47,7 +117,7 @@ ListSeqsCommand::ListSeqsCommand(string option) { it = parameters.find("alignreport"); //user has given a template file if(it != parameters.end()){ - path = hasPath(it->second); + path = m->hasPath(it->second); //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["alignreport"] = inputDir + it->second; } } @@ -55,7 +125,7 @@ ListSeqsCommand::ListSeqsCommand(string option) { it = parameters.find("fasta"); //user has given a template file if(it != parameters.end()){ - path = hasPath(it->second); + path = m->hasPath(it->second); //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["fasta"] = inputDir + it->second; } } @@ -63,7 +133,7 @@ ListSeqsCommand::ListSeqsCommand(string option) { it = parameters.find("list"); //user has given a template file if(it != parameters.end()){ - path = hasPath(it->second); + path = m->hasPath(it->second); //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["list"] = inputDir + it->second; } } @@ -71,7 +141,7 @@ ListSeqsCommand::ListSeqsCommand(string option) { it = parameters.find("name"); //user has given a template file if(it != parameters.end()){ - path = hasPath(it->second); + path = m->hasPath(it->second); //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["name"] = inputDir + it->second; } } @@ -79,24 +149,43 @@ ListSeqsCommand::ListSeqsCommand(string option) { it = parameters.find("group"); //user has given a template file if(it != parameters.end()){ - path = hasPath(it->second); + path = m->hasPath(it->second); //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["group"] = 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; } + } + + 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; } + } } //check for required parameters fastafile = validParameter.validFile(parameters, "fasta", true); if (fastafile == "not open") { abort = true; } - else if (fastafile == "not found") { fastafile = ""; } + else if (fastafile == "not found") { fastafile = ""; } + else { m->setFastaFile(fastafile); } namefile = validParameter.validFile(parameters, "name", true); if (namefile == "not open") { 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; } @@ -105,9 +194,19 @@ ListSeqsCommand::ListSeqsCommand(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; } + else if (taxfile == "not found") { taxfile = ""; } + else { m->setTaxonomyFile(taxfile); } + + countfile = validParameter.validFile(parameters, "count", true); + if (countfile == "not open") { abort = true; } + else if (countfile == "not found") { countfile = ""; } + else { m->setCountTableFile(countfile); } - if ((fastafile == "") && (namefile == "") && (listfile == "") && (groupfile == "") && (alignfile == "")) { m->mothurOut("You must provide a file."); m->mothurOutEndLine(); abort = true; } + if ((countfile == "") && (fastafile == "") && (namefile == "") && (listfile == "") && (groupfile == "") && (alignfile == "") && (taxfile == "")) { m->mothurOut("You must provide a file."); m->mothurOutEndLine(); abort = true; } int okay = 1; if (outputDir != "") { okay++; } @@ -124,26 +223,10 @@ ListSeqsCommand::ListSeqsCommand(string option) { } //********************************************************************************************************************** -void ListSeqsCommand::help(){ - try { - m->mothurOut("The list.seqs command reads a fasta, name, group, list or alignreport file and outputs a .accnos file containing sequence names.\n"); - m->mothurOut("The list.seqs command parameters are fasta, name, group and alignreport. You must provide one of these parameters.\n"); - m->mothurOut("The list.seqs command should be in the following format: list.seqs(fasta=yourFasta).\n"); - m->mothurOut("Example list.seqs(fasta=amazon.fasta).\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, "ListSeqsCommand", "help"); - exit(1); - } -} - -//********************************************************************************************************************** - int ListSeqsCommand::execute(){ try { - if (abort == true) { return 0; } + if (abort == true) { if (calledHelp) { return 0; } return 2; } //read functions fill names vector if (fastafile != "") { inputFileName = fastafile; readFasta(); } @@ -151,35 +234,49 @@ int ListSeqsCommand::execute(){ else if (groupfile != "") { inputFileName = groupfile; readGroup(); } else if (alignfile != "") { inputFileName = alignfile; readAlign(); } else if (listfile != "") { inputFileName = listfile; readList(); } + else if (taxfile != "") { inputFileName = taxfile; readTax(); } + else if (countfile != "") { inputFileName = countfile; readCount(); } - if (m->control_pressed) { return 0; } + if (m->control_pressed) { outputTypes.clear(); return 0; } //sort in alphabetical order sort(names.begin(), names.end()); - if (outputDir == "") { outputDir += hasPath(inputFileName); } + if (outputDir == "") { outputDir += m->hasPath(inputFileName); } - string outputFileName = outputDir + getRootName(getSimpleName(inputFileName)) + "accnos"; + map variables; + variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(inputFileName)); + string outputFileName = getOutputFileName("accnos", variables); ofstream out; - openOutputFile(outputFileName, out); + m->openOutputFile(outputFileName, out); + outputNames.push_back(outputFileName); outputTypes["accnos"].push_back(outputFileName); //output to .accnos file for (int i = 0; i < names.size(); i++) { - if (m->control_pressed) { out.close(); remove(outputFileName.c_str()); return 0; } + if (m->control_pressed) { outputTypes.clear(); out.close(); m->mothurRemove(outputFileName); return 0; } out << names[i] << endl; } out.close(); - if (m->control_pressed) { remove(outputFileName.c_str()); return 0; } - + if (m->control_pressed) { outputTypes.clear(); m->mothurRemove(outputFileName); return 0; } + + m->setAccnosFile(outputFileName); + m->mothurOutEndLine(); - m->mothurOut("Output File Name: "); m->mothurOutEndLine(); + m->mothurOut("Output File Names: "); m->mothurOutEndLine(); m->mothurOut(outputFileName); m->mothurOutEndLine(); m->mothurOutEndLine(); + //set accnos file as new current accnosfile + string current = ""; + itTypes = outputTypes.find("accnos"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setAccnosFile(current); } + } + return 0; } @@ -194,9 +291,15 @@ int ListSeqsCommand::readFasta(){ try { ifstream in; - openInputFile(fastafile, in); + m->openInputFile(fastafile, in); string name; + //ofstream out; + //string newFastaName = outputDir + m->getRootName(m->getSimpleName(fastafile)) + "numsAdded.fasta"; + //m->openOutputFile(newFastaName, out); + int count = 1; + //string lastName = ""; + while(!in.eof()){ if (m->control_pressed) { in.close(); return 0; } @@ -206,9 +309,11 @@ int ListSeqsCommand::readFasta(){ if (name != "") { names.push_back(name); } - gobble(in); + m->gobble(in); + if (m->debug) { count++; cout << "[DEBUG]: count = " + toString(count) + ", name = " + currSeq.getName() + "\n"; } } in.close(); + //out.close(); return 0; @@ -222,7 +327,7 @@ int ListSeqsCommand::readFasta(){ int ListSeqsCommand::readList(){ try { ifstream in; - openInputFile(listfile, in); + m->openInputFile(listfile, in); if(!in.eof()){ //read in list vector @@ -234,13 +339,7 @@ int ListSeqsCommand::readList(){ if (m->control_pressed) { in.close(); return 0; } - 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()); - names.push_back(name); - } - - names.push_back(binnames); + m->splitAtComma(binnames, names); } } in.close(); @@ -259,7 +358,7 @@ int ListSeqsCommand::readName(){ try { ifstream in; - openInputFile(namefile, in); + m->openInputFile(namefile, in); string name, firstCol, secondCol; while(!in.eof()){ @@ -270,16 +369,9 @@ int ListSeqsCommand::readName(){ in >> secondCol; //parse second column saving each name - while (secondCol.find_first_of(',') != -1) { - name = secondCol.substr(0,secondCol.find_first_of(',')); - secondCol = secondCol.substr(secondCol.find_first_of(',')+1, secondCol.length()); - names.push_back(name); - } - - //get name after last , - names.push_back(secondCol); + m->splitAtComma(secondCol, names); - gobble(in); + m->gobble(in); } in.close(); return 0; @@ -296,19 +388,19 @@ int ListSeqsCommand::readGroup(){ try { ifstream in; - openInputFile(groupfile, in); + m->openInputFile(groupfile, in); string name, group; while(!in.eof()){ if (m->control_pressed) { in.close(); return 0; } - in >> name; //read from first column + in >> name; m->gobble(in); //read from first column in >> group; //read from second column names.push_back(name); - gobble(in); + m->gobble(in); } in.close(); return 0; @@ -319,14 +411,31 @@ int ListSeqsCommand::readGroup(){ exit(1); } } - +//********************************************************************************************************************** +int ListSeqsCommand::readCount(){ + try { + CountTable ct; + ct.readTable(countfile, false); + + if (m->control_pressed) { return 0; } + + names = ct.getNamesOfSeqs(); + + return 0; + + } + catch(exception& e) { + m->errorOut(e, "ListSeqsCommand", "readCount"); + exit(1); + } +} //********************************************************************************************************************** //alignreport file has a column header line then all other lines contain 16 columns. we just want the first column since that contains the name int ListSeqsCommand::readAlign(){ try { ifstream in; - openInputFile(alignfile, in); + m->openInputFile(alignfile, in); string name, junk; //read column headers @@ -334,14 +443,14 @@ int ListSeqsCommand::readAlign(){ if (!in.eof()) { in >> junk; } else { break; } } - + //m->getline(in); while(!in.eof()){ if (m->control_pressed) { in.close(); return 0; } in >> name; //read from first column - + //m->getline(in); //read rest for (int i = 0; i < 15; i++) { if (!in.eof()) { in >> junk; } @@ -350,7 +459,7 @@ int ListSeqsCommand::readAlign(){ names.push_back(name); - gobble(in); + m->gobble(in); } in.close(); @@ -364,3 +473,33 @@ int ListSeqsCommand::readAlign(){ } } //********************************************************************************************************************** +int ListSeqsCommand::readTax(){ + try { + + ifstream in; + m->openInputFile(taxfile, in); + string name, firstCol, secondCol; + + while(!in.eof()){ + + if (m->control_pressed) { in.close(); return 0; } + + in >> firstCol; + in >> secondCol; + + names.push_back(firstCol); + + m->gobble(in); + + } + in.close(); + + return 0; + + } + catch(exception& e) { + m->errorOut(e, "ListSeqsCommand", "readTax"); + exit(1); + } +} +//**********************************************************************************************************************