X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=listseqscommand.cpp;h=cf884705cb26f341ef08713b118af32fd49c5bdf;hp=d60470cdebcc70114afcb79cc08edbb333816292;hb=050a3ff02473a3d4c0980964e1a9ebe52e55d6b8;hpb=4160a27002f4a3ca436fcd62eca0366b09f8e901 diff --git a/listseqscommand.cpp b/listseqscommand.cpp index d60470c..cf88470 100644 --- a/listseqscommand.cpp +++ b/listseqscommand.cpp @@ -10,19 +10,21 @@ #include "listseqscommand.h" #include "sequence.hpp" #include "listvector.hpp" +#include "counttable.h" //********************************************************************************************************************** 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); + 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); } @@ -37,8 +39,8 @@ vector ListSeqsCommand::setParameters(){ 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 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"; @@ -49,7 +51,21 @@ string 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 { @@ -71,7 +87,7 @@ ListSeqsCommand::ListSeqsCommand(string option) { //allow user to run help if(option == "help") { help(); abort = true; calledHelp = true; } - + else if(option == "citation") { citation(); abort = true; calledHelp = true;} else { vector myArray = setParameters(); @@ -145,20 +161,31 @@ ListSeqsCommand::ListSeqsCommand(string option) { //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; } @@ -167,12 +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 == "") && (taxfile == "")) { 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++; } @@ -201,6 +235,7 @@ int ListSeqsCommand::execute(){ 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) { outputTypes.clear(); return 0; } @@ -209,7 +244,9 @@ int ListSeqsCommand::execute(){ if (outputDir == "") { outputDir += m->hasPath(inputFileName); } - string outputFileName = outputDir + m->getRootName(m->getSimpleName(inputFileName)) + "accnos"; + map variables; + variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(inputFileName)); + string outputFileName = getOutputFileName("accnos", variables); ofstream out; m->openOutputFile(outputFileName, out); @@ -218,18 +255,18 @@ int ListSeqsCommand::execute(){ //output to .accnos file for (int i = 0; i < names.size(); i++) { - if (m->control_pressed) { outputTypes.clear(); 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) { outputTypes.clear(); 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(); @@ -260,7 +297,7 @@ int ListSeqsCommand::readFasta(){ //ofstream out; //string newFastaName = outputDir + m->getRootName(m->getSimpleName(fastafile)) + "numsAdded.fasta"; //m->openOutputFile(newFastaName, out); - //int count = 1; + int count = 1; //string lastName = ""; while(!in.eof()){ @@ -269,17 +306,11 @@ int ListSeqsCommand::readFasta(){ 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); } m->gobble(in); - //count++; + if (m->debug) { count++; cout << "[DEBUG]: count = " + toString(count) + ", name = " + currSeq.getName() + "\n"; } } in.close(); //out.close(); @@ -308,13 +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(); @@ -344,14 +369,7 @@ 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); m->gobble(in); } @@ -393,7 +411,24 @@ 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(){ @@ -408,14 +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; }