X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=listseqscommand.cpp;h=bfbb0788c5092382f22bea643c5405674361dd67;hb=8e67e9de1b200106bea5a468ac02125954656499;hp=a8a9d2b5a6cff6da2ab8e86e22af19782f5ce0bf;hpb=348de0f8b17d84ede77081dcf67bd6ef43496677;p=mothur.git diff --git a/listseqscommand.cpp b/listseqscommand.cpp index a8a9d2b..bfbb078 100644 --- a/listseqscommand.cpp +++ b/listseqscommand.cpp @@ -11,50 +11,74 @@ #include "sequence.hpp" #include "listvector.hpp" + //********************************************************************************************************************** -vector ListSeqsCommand::getValidParameters(){ +vector ListSeqsCommand::setParameters(){ try { - string Array[] = {"fasta","name", "group", "alignreport","list","taxonomy","outputdir","inputdir"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + 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", "getValidParameters"); + m->errorOut(e, "ListSeqsCommand", "setParameters"); exit(1); } } //********************************************************************************************************************** -ListSeqsCommand::ListSeqsCommand(){ +string ListSeqsCommand::getHelpString(){ try { - abort = true; calledHelp = true; - vector tempOutNames; - outputTypes["accnos"] = tempOutNames; + 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", "ListSeqsCommand"); + m->errorOut(e, "ListSeqsCommand", "getHelpString"); exit(1); } } //********************************************************************************************************************** -vector ListSeqsCommand::getRequiredParameters(){ +string ListSeqsCommand::getOutputFileNameTag(string type, string inputName=""){ try { - string Array[] = {"fasta","name", "group", "alignreport","list","taxonomy","or"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); - return myArray; + string outputFileName = ""; + map >::iterator it; + + //is this a type this command creates + it = outputTypes.find(type); + if (it == outputTypes.end()) { m->mothurOut("[ERROR]: this command doesn't create a " + type + " output file.\n"); } + else { + if (type == "accnos") { outputFileName = "accnos"; } + else { m->mothurOut("[ERROR]: No definition for type " + type + " output file tag.\n"); m->control_pressed = true; } + } + return outputFileName; } catch(exception& e) { - m->errorOut(e, "ListSeqsCommand", "getRequiredParameters"); + m->errorOut(e, "ListSeqsCommand", "getOutputFileNameTag"); exit(1); } } //********************************************************************************************************************** -vector ListSeqsCommand::getRequiredFiles(){ +ListSeqsCommand::ListSeqsCommand(){ try { - vector myArray; - return myArray; + abort = true; calledHelp = true; + setParameters(); + vector tempOutNames; + outputTypes["accnos"] = tempOutNames; } catch(exception& e) { - m->errorOut(e, "ListSeqsCommand", "getRequiredFiles"); + m->errorOut(e, "ListSeqsCommand", "ListSeqsCommand"); exit(1); } } @@ -66,11 +90,9 @@ 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 { - //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(); @@ -147,15 +169,18 @@ 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; } @@ -164,10 +189,12 @@ 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; } @@ -186,22 +213,6 @@ 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 { @@ -222,7 +233,7 @@ int ListSeqsCommand::execute(){ if (outputDir == "") { outputDir += m->hasPath(inputFileName); } - string outputFileName = outputDir + m->getRootName(m->getSimpleName(inputFileName)) + "accnos"; + string outputFileName = outputDir + m->getRootName(m->getSimpleName(inputFileName)) + getOutputFileNameTag("accnos"); ofstream out; m->openOutputFile(outputFileName, out); @@ -231,13 +242,13 @@ 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); @@ -270,18 +281,32 @@ int ListSeqsCommand::readFasta(){ 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); } m->gobble(in); + //count++; } in.close(); + //out.close(); return 0; @@ -307,13 +332,7 @@ 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(); @@ -343,14 +362,7 @@ 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); } @@ -407,14 +419,14 @@ 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; }