X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=listseqscommand.cpp;h=1488cdadac766b243252e87053a0132975961884;hb=4ad32478c7b1bbb464c839a6e133f5b517a3efec;hp=a7d79f39cd8fd271d448c32bc2a6180264a86392;hpb=861f46b74c17adec8c6ad6d89f232ae7485797bf;p=mothur.git diff --git a/listseqscommand.cpp b/listseqscommand.cpp index a7d79f3..1488cda 100644 --- a/listseqscommand.cpp +++ b/listseqscommand.cpp @@ -9,10 +9,59 @@ #include "listseqscommand.h" #include "sequence.hpp" +#include "listvector.hpp" +//********************************************************************************************************************** +vector ListSeqsCommand::getValidParameters(){ + try { + string Array[] = {"fasta","name", "group", "alignreport","list","taxonomy","outputdir","inputdir"}; + vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + return myArray; + } + catch(exception& e) { + m->errorOut(e, "ListSeqsCommand", "getValidParameters"); + exit(1); + } +} +//********************************************************************************************************************** +ListSeqsCommand::ListSeqsCommand(){ + try { + abort = true; + //initialize outputTypes + vector tempOutNames; + outputTypes["accnos"] = tempOutNames; + } + catch(exception& e) { + m->errorOut(e, "ListSeqsCommand", "ListSeqsCommand"); + exit(1); + } +} +//********************************************************************************************************************** +vector ListSeqsCommand::getRequiredParameters(){ + try { + string Array[] = {"fasta","name", "group", "alignreport","list","taxonomy","or"}; + vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + return myArray; + } + catch(exception& e) { + m->errorOut(e, "ListSeqsCommand", "getRequiredParameters"); + exit(1); + } +} +//********************************************************************************************************************** +vector ListSeqsCommand::getRequiredFiles(){ + try { + vector myArray; + return myArray; + } + catch(exception& e) { + m->errorOut(e, "ListSeqsCommand", "getRequiredFiles"); + exit(1); + } +} //********************************************************************************************************************** -ListSeqsCommand::ListSeqsCommand(string option){ +ListSeqsCommand::ListSeqsCommand(string option) { try { abort = false; @@ -21,19 +70,81 @@ ListSeqsCommand::ListSeqsCommand(string option){ else { //valid paramters for this command - string Array[] = {"fasta","name", "group", "align" }; + string Array[] = {"fasta","name", "group", "alignreport","list","taxonomy","outputdir","inputdir"}; vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); OptionParser parser(option); map parameters = parser.getParameters(); ValidParameters validParameter; + map::iterator it; //check to make sure all parameters are valid for command for (map::iterator it = parameters.begin(); it != parameters.end(); it++) { 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 = ""; } + + //if the user changes the input directory command factory will send this info to us in the output parameter + string inputDir = validParameter.validFile(parameters, "inputdir", false); + if (inputDir == "not found"){ inputDir = ""; } + else { + string path; + it = parameters.find("alignreport"); + //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["alignreport"] = inputDir + it->second; } + } + + it = parameters.find("fasta"); + //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["fasta"] = inputDir + it->second; } + } + + it = parameters.find("list"); + //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["list"] = inputDir + it->second; } + } + + it = parameters.find("name"); + //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["name"] = inputDir + it->second; } + } + + it = parameters.find("group"); + //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["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; } + } + } + //check for required parameters fastafile = validParameter.validFile(parameters, "fasta", true); if (fastafile == "not open") { abort = true; } @@ -47,18 +158,30 @@ ListSeqsCommand::ListSeqsCommand(string option){ if (groupfile == "not open") { abort = true; } else if (groupfile == "not found") { groupfile = ""; } - alignfile = validParameter.validFile(parameters, "align", true); + alignfile = validParameter.validFile(parameters, "alignreport", true); if (alignfile == "not open") { abort = true; } else if (alignfile == "not found") { alignfile = ""; } - if ((fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "")) { mothurOut("You must provide a file."); mothurOutEndLine(); abort = true; } + listfile = validParameter.validFile(parameters, "list", true); + if (listfile == "not open") { abort = true; } + else if (listfile == "not found") { listfile = ""; } + + taxfile = validParameter.validFile(parameters, "taxonomy", true); + if (taxfile == "not open") { abort = true; } + else if (taxfile == "not found") { taxfile = ""; } + + if ((fastafile == "") && (namefile == "") && (listfile == "") && (groupfile == "") && (alignfile == "") && (taxfile == "")) { m->mothurOut("You must provide a file."); m->mothurOutEndLine(); abort = true; } + + int okay = 1; + if (outputDir != "") { okay++; } + if (inputDir != "") { okay++; } - if (parameters.size() > 1) { mothurOut("You may only enter one file."); mothurOutEndLine(); abort = true; } + if (parameters.size() > okay) { m->mothurOut("You may only enter one file."); m->mothurOutEndLine(); abort = true; } } } catch(exception& e) { - errorOut(e, "ListSeqsCommand", "ListSeqsCommand"); + m->errorOut(e, "ListSeqsCommand", "ListSeqsCommand"); exit(1); } } @@ -66,14 +189,14 @@ ListSeqsCommand::ListSeqsCommand(string option){ void ListSeqsCommand::help(){ try { - mothurOut("The list.seqs command reads a fasta, name, group or alignreport file and outputs a .accnos file containing sequence names.\n"); - mothurOut("The list.seqs command parameters are fasta, name, group and align. You must provide one of these parameters.\n"); - mothurOut("The list.seqs command should be in the following format: list.seqs(fasta=yourFasta).\n"); - mothurOut("Example list.seqs(fasta=amazon.fasta).\n"); - mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n\n"); + 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) { - errorOut(e, "ListSeqsCommand", "help"); + m->errorOut(e, "ListSeqsCommand", "help"); exit(1); } } @@ -90,63 +213,122 @@ int ListSeqsCommand::execute(){ else if (namefile != "") { inputFileName = namefile; readName(); } else if (groupfile != "") { inputFileName = groupfile; readGroup(); } else if (alignfile != "") { inputFileName = alignfile; readAlign(); } + else if (listfile != "") { inputFileName = listfile; readList(); } + else if (taxfile != "") { inputFileName = taxfile; readTax(); } + + if (m->control_pressed) { outputTypes.clear(); return 0; } //sort in alphabetical order sort(names.begin(), names.end()); - string outputFileName = getRootName(inputFileName) + "accnos"; + if (outputDir == "") { outputDir += m->hasPath(inputFileName); } + + string outputFileName = outputDir + m->getRootName(m->getSimpleName(inputFileName)) + "accnos"; + ofstream out; - openOutputFile(outputFileName, out); + m->openOutputFile(outputFileName, out); //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; } + out << names[i] << endl; } out.close(); + if (m->control_pressed) { outputTypes.clear(); remove(outputFileName.c_str()); return 0; } + + m->mothurOutEndLine(); + m->mothurOut("Output File Name: "); m->mothurOutEndLine(); + m->mothurOut(outputFileName); m->mothurOutEndLine(); outputNames.push_back(outputFileName); outputTypes["accnos"].push_back(outputFileName); + m->mothurOutEndLine(); + return 0; } catch(exception& e) { - errorOut(e, "ListSeqsCommand", "execute"); + m->errorOut(e, "ListSeqsCommand", "execute"); exit(1); } } //********************************************************************************************************************** -void ListSeqsCommand::readFasta(){ +int ListSeqsCommand::readFasta(){ try { ifstream in; - openInputFile(fastafile, in); + m->openInputFile(fastafile, in); string name; - + while(!in.eof()){ + + if (m->control_pressed) { in.close(); return 0; } + Sequence currSeq(in); name = currSeq.getName(); - names.push_back(name); + if (name != "") { names.push_back(name); } - gobble(in); + m->gobble(in); } - in.close(); + in.close(); + + return 0; } catch(exception& e) { - errorOut(e, "ListSeqsCommand", "readFasta"); + m->errorOut(e, "ListSeqsCommand", "readFasta"); + exit(1); + } +} +//********************************************************************************************************************** +int ListSeqsCommand::readList(){ + try { + ifstream in; + m->openInputFile(listfile, in); + + if(!in.eof()){ + //read in list vector + ListVector list(in); + + //for each bin + for (int i = 0; i < list.getNumBins(); i++) { + string binnames = list.get(i); + + 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); + } + } + in.close(); + + return 0; + + } + catch(exception& e) { + m->errorOut(e, "ListSeqsCommand", "readList"); exit(1); } } //********************************************************************************************************************** -void ListSeqsCommand::readName(){ +int ListSeqsCommand::readName(){ try { ifstream in; - openInputFile(namefile, in); + m->openInputFile(namefile, in); string name, firstCol, secondCol; while(!in.eof()){ + + if (m->control_pressed) { in.close(); return 0; } in >> firstCol; in >> secondCol; @@ -161,50 +343,54 @@ void ListSeqsCommand::readName(){ //get name after last , names.push_back(secondCol); - gobble(in); + m->gobble(in); } in.close(); + return 0; } catch(exception& e) { - errorOut(e, "ListSeqsCommand", "readName"); + m->errorOut(e, "ListSeqsCommand", "readName"); exit(1); } } //********************************************************************************************************************** -void ListSeqsCommand::readGroup(){ +int ListSeqsCommand::readGroup(){ try { ifstream in; - openInputFile(groupfile, in); + m->openInputFile(groupfile, in); string name, group; while(!in.eof()){ - - in >> name; //read from first column + + if (m->control_pressed) { in.close(); return 0; } + + 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; } catch(exception& e) { - errorOut(e, "ListSeqsCommand", "readGroup"); + m->errorOut(e, "ListSeqsCommand", "readGroup"); 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 -void ListSeqsCommand::readAlign(){ +int ListSeqsCommand::readAlign(){ try { ifstream in; - openInputFile(alignfile, in); + m->openInputFile(alignfile, in); string name, junk; //read column headers @@ -215,6 +401,8 @@ void ListSeqsCommand::readAlign(){ while(!in.eof()){ + + if (m->control_pressed) { in.close(); return 0; } in >> name; //read from first column @@ -226,14 +414,45 @@ void ListSeqsCommand::readAlign(){ names.push_back(name); - gobble(in); + m->gobble(in); } in.close(); + + return 0; } catch(exception& e) { - errorOut(e, "ListSeqsCommand", "readAlign"); + m->errorOut(e, "ListSeqsCommand", "readAlign"); + exit(1); + } +} +//********************************************************************************************************************** +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); } }