X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=listseqscommand.cpp;h=833ac952a8db761b16ba59d9b53b561bef07ad0b;hb=4f2c7f477a1ef2d60a1c0c84ab1ba8243af67f87;hp=3200137343e8691e2e8df3f70fcd1940f933b88c;hpb=14edc148cb299c5624f72bb681375b704aa74f43;p=mothur.git diff --git a/listseqscommand.cpp b/listseqscommand.cpp index 3200137..833ac95 100644 --- a/listseqscommand.cpp +++ b/listseqscommand.cpp @@ -11,19 +11,69 @@ #include "sequence.hpp" #include "listvector.hpp" + +//********************************************************************************************************************** +vector ListSeqsCommand::setParameters(){ + try { + CommandParameter pfasta("fasta", "InputTypes", "", "", "FNGLT", "FNGLT", "none",false,false); parameters.push_back(pfasta); + CommandParameter pname("name", "InputTypes", "", "", "FNGLT", "FNGLT", "none",false,false); parameters.push_back(pname); + CommandParameter pgroup("group", "InputTypes", "", "", "FNGLT", "FNGLT", "none",false,false); parameters.push_back(pgroup); + CommandParameter plist("list", "InputTypes", "", "", "FNGLT", "FNGLT", "none",false,false); parameters.push_back(plist); + CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "FNGLT", "FNGLT", "none",false,false); parameters.push_back(ptaxonomy); + CommandParameter palignreport("alignreport", "InputTypes", "", "", "FNGLT", "FNGLT", "none",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, list, taxonomy or alignreport file and outputs a .accnos file containing sequence names.\n"; + helpString += "The list.seqs command parameters are fasta, name, group, 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); + } +} + +//********************************************************************************************************************** +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","taxonomy","outputdir","inputdir"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + vector myArray = setParameters(); OptionParser parser(option); map parameters = parser.getParameters(); @@ -36,6 +86,10 @@ 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 +101,7 @@ 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 +109,7 @@ 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 +117,7 @@ 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 +125,7 @@ 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; } } @@ -79,7 +133,7 @@ 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; } } @@ -87,7 +141,7 @@ ListSeqsCommand::ListSeqsCommand(string option) { it = parameters.find("taxonomy"); //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["taxonomy"] = inputDir + it->second; } } @@ -96,15 +150,18 @@ ListSeqsCommand::ListSeqsCommand(string option) { //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; } @@ -113,10 +170,12 @@ 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); } if ((fastafile == "") && (namefile == "") && (listfile == "") && (groupfile == "") && (alignfile == "") && (taxfile == "")) { m->mothurOut("You must provide a file."); m->mothurOutEndLine(); abort = true; } @@ -135,26 +194,10 @@ ListSeqsCommand::ListSeqsCommand(string option) { } //********************************************************************************************************************** -void ListSeqsCommand::help(){ - try { - m->mothurOut("The list.seqs command reads a fasta, name, group, list, taxonomy or alignreport file and outputs a .accnos file containing sequence names.\n"); - m->mothurOut("The list.seqs command parameters are fasta, name, group, list, taxonomy 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(); } @@ -164,34 +207,44 @@ int ListSeqsCommand::execute(){ else if (listfile != "") { inputFileName = listfile; readList(); } else if (taxfile != "") { inputFileName = taxfile; readTax(); } - 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"; + string outputFileName = outputDir + m->getRootName(m->getSimpleName(inputFileName)) + "accnos"; 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(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; } @@ -206,21 +259,35 @@ 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; } Sequence currSeq(in); name = currSeq.getName(); + //if (lastName == "") { lastName = name; } + //if (name != lastName) { count = 1; } + // lastName = name; + + //Sequence newSeq(name+"_"+toString(count), currSeq.getAligned()); + //newSeq.printSequence(out); if (name != "") { names.push_back(name); } - gobble(in); + m->gobble(in); + //count++; } in.close(); + //out.close(); return 0; @@ -234,7 +301,7 @@ int ListSeqsCommand::readFasta(){ int ListSeqsCommand::readList(){ try { ifstream in; - openInputFile(listfile, in); + m->openInputFile(listfile, in); if(!in.eof()){ //read in list vector @@ -246,13 +313,7 @@ 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(); @@ -271,7 +332,7 @@ int ListSeqsCommand::readName(){ try { ifstream in; - openInputFile(namefile, in); + m->openInputFile(namefile, in); string name, firstCol, secondCol; while(!in.eof()){ @@ -282,16 +343,9 @@ 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); - } + m->splitAtComma(secondCol, names); - //get name after last , - names.push_back(secondCol); - - gobble(in); + m->gobble(in); } in.close(); return 0; @@ -308,19 +362,19 @@ 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; @@ -338,7 +392,7 @@ int ListSeqsCommand::readAlign(){ try { ifstream in; - openInputFile(alignfile, in); + m->openInputFile(alignfile, in); string name, junk; //read column headers @@ -362,7 +416,7 @@ int ListSeqsCommand::readAlign(){ names.push_back(name); - gobble(in); + m->gobble(in); } in.close(); @@ -380,7 +434,7 @@ int ListSeqsCommand::readTax(){ try { ifstream in; - openInputFile(taxfile, in); + m->openInputFile(taxfile, in); string name, firstCol, secondCol; while(!in.eof()){ @@ -392,7 +446,8 @@ int ListSeqsCommand::readTax(){ names.push_back(firstCol); - gobble(in); + m->gobble(in); + } in.close();