X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;ds=sidebyside;f=chimeracheckcommand.cpp;h=5b249d7ff6892a53ce0493c3fa5319468681a8bd;hb=f5ef644ce76074de08b2bbb64097619b2b16d60d;hp=b3f49a4916056a3b9e9ddb881f041513507c49d2;hpb=df41d90a9611eab75d0516e2654ed8580f8df24c;p=mothur.git diff --git a/chimeracheckcommand.cpp b/chimeracheckcommand.cpp index b3f49a4..5b249d7 100644 --- a/chimeracheckcommand.cpp +++ b/chimeracheckcommand.cpp @@ -10,43 +10,62 @@ #include "chimeracheckcommand.h" //********************************************************************************************************************** -vector ChimeraCheckCommand::getValidParameters(){ +vector ChimeraCheckCommand::setParameters(){ try { - string AlignArray[] = {"fasta","processors","increment","template","ksize","svg", "name","outputdir","inputdir" }; - vector myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string))); - return myArray; - } - catch(exception& e) { - m->errorOut(e, "ChimeraCheckCommand", "getValidParameters"); - exit(1); - } -} -//********************************************************************************************************************** -vector ChimeraCheckCommand::getRequiredParameters(){ - try { - string AlignArray[] = {"template","fasta"}; - vector myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string))); + CommandParameter ptemplate("reference", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(ptemplate); + CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(pfasta); + CommandParameter pname("name", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(pname); + CommandParameter psvg("svg", "Boolean", "", "F", "", "", "",false,false); parameters.push_back(psvg); + CommandParameter pincrement("increment", "Number", "", "10", "", "", "",false,false); parameters.push_back(pincrement); + CommandParameter pksize("ksize", "Number", "", "7", "", "", "",false,false); parameters.push_back(pksize); + CommandParameter pprocessors("processors", "Number", "", "1", "", "", "",false,false); parameters.push_back(pprocessors); + 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, "ChimeraCheckCommand", "getRequiredParameters"); + m->errorOut(e, "ChimeraCheckCommand", "setParameters"); exit(1); } } //********************************************************************************************************************** -vector ChimeraCheckCommand::getRequiredFiles(){ +string ChimeraCheckCommand::getHelpString(){ try { - vector myArray; - return myArray; + string helpString = ""; + helpString += "The chimera.check command reads a fastafile and referencefile and outputs potentially chimeric sequences.\n"; + helpString += "This command was created using the algorythms described in CHIMERA_CHECK version 2.7 written by Niels Larsen. \n"; + helpString += "The chimera.check command parameters are fasta, reference, processors, ksize, increment, svg and name.\n"; + helpString += "The fasta parameter allows you to enter the fasta file containing your potentially chimeric sequences, and is required unless you have a valid current fasta file. \n"; + helpString += "You may enter multiple fasta files by separating their names with dashes. ie. fasta=abrecovery.fasta-amzon.fasta \n"; + helpString += "The reference parameter allows you to enter a reference file containing known non-chimeric sequences, and is required. \n"; + helpString += "The processors parameter allows you to specify how many processors you would like to use. The default is 1. \n"; +#ifdef USE_MPI + helpString += "When using MPI, the processors parameter is set to the number of MPI processes running. \n"; +#endif + helpString += "The increment parameter allows you to specify how far you move each window while finding chimeric sequences, default is 10.\n"; + helpString += "The ksize parameter allows you to input kmersize, default is 7. \n"; + helpString += "The svg parameter allows you to specify whether or not you would like a svg file outputted for each query sequence, default is False.\n"; + helpString += "The name parameter allows you to enter a file containing names of sequences you would like .svg files for.\n"; + helpString += "You may enter multiple name files by separating their names with dashes. ie. fasta=abrecovery.svg.names-amzon.svg.names \n"; + helpString += "The chimera.check command should be in the following format: \n"; + helpString += "chimera.check(fasta=yourFastaFile, reference=yourTemplateFile, processors=yourProcessors, ksize=yourKmerSize) \n"; + helpString += "Example: chimera.check(fasta=AD.fasta, reference=core_set_aligned,imputed.fasta, processors=4, ksize=8) \n"; + helpString += "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFastaFile).\n"; + return helpString; } catch(exception& e) { - m->errorOut(e, "ChimeraCheckCommand", "getRequiredFiles"); + m->errorOut(e, "ChimeraCheckCommand", "getHelpString"); exit(1); } } //********************************************************************************************************************** ChimeraCheckCommand::ChimeraCheckCommand(){ try { + abort = true; calledHelp = true; + setParameters(); vector tempOutNames; outputTypes["chimera"] = tempOutNames; } @@ -58,15 +77,14 @@ ChimeraCheckCommand::ChimeraCheckCommand(){ //*************************************************************************************************************** ChimeraCheckCommand::ChimeraCheckCommand(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","processors","increment","template","ksize","svg", "name","outputdir","inputdir" }; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + vector myArray = setParameters(); OptionParser parser(option); map parameters = parser.getParameters(); @@ -86,65 +104,88 @@ ChimeraCheckCommand::ChimeraCheckCommand(string option) { string inputDir = validParameter.validFile(parameters, "inputdir", false); if (inputDir == "not found"){ inputDir = ""; } else { - it = parameters.find("template"); + it = parameters.find("reference"); //user has given a template file if(it != parameters.end()){ string path = m->hasPath(it->second); //if the user has not given a path then, add inputdir. else leave path alone. - if (path == "") { parameters["template"] = inputDir + it->second; } + if (path == "") { parameters["reference"] = inputDir + it->second; } } } //check for required parameters fastafile = validParameter.validFile(parameters, "fasta", false); - if (fastafile == "not found") { fastafile = ""; m->mothurOut("fasta is a required parameter for the chimera.check command."); m->mothurOutEndLine(); abort = true; } - else { + if (fastafile == "not found") { + //if there is a current fasta file, use it + string filename = m->getFastaFile(); + if (filename != "") { fastaFileNames.push_back(filename); m->mothurOut("Using " + filename + " as input file for the fasta parameter."); m->mothurOutEndLine(); } + else { m->mothurOut("You have no current fastafile and the fasta parameter is required."); m->mothurOutEndLine(); abort = true; } + }else { m->splitAtDash(fastafile, fastaFileNames); //go through files and make sure they are good, if not, then disregard them for (int i = 0; i < fastaFileNames.size(); i++) { - if (inputDir != "") { - string path = m->hasPath(fastaFileNames[i]); - //if the user has not given a path then, add inputdir. else leave path alone. - if (path == "") { fastaFileNames[i] = inputDir + fastaFileNames[i]; } - } - - int ableToOpen; - ifstream in; - ableToOpen = m->openInputFile(fastaFileNames[i], in, "noerror"); - - //if you can't open it, try default location - if (ableToOpen == 1) { - if (m->getDefaultPath() != "") { //default path is set - string tryPath = m->getDefaultPath() + m->getSimpleName(fastaFileNames[i]); - m->mothurOut("Unable to open " + fastaFileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine(); - ifstream in2; - ableToOpen = m->openInputFile(tryPath, in2, "noerror"); - in2.close(); - fastaFileNames[i] = tryPath; + bool ignore = false; + if (fastaFileNames[i] == "current") { + fastaFileNames[i] = m->getFastaFile(); + if (fastaFileNames[i] != "") { m->mothurOut("Using " + fastaFileNames[i] + " as input file for the fasta parameter where you had given current."); m->mothurOutEndLine(); } + else { + m->mothurOut("You have no current fastafile, ignoring current."); m->mothurOutEndLine(); ignore=true; + //erase from file list + fastaFileNames.erase(fastaFileNames.begin()+i); + i--; } } - //if you can't open it, try default location - if (ableToOpen == 1) { - if (m->getOutputDir() != "") { //default path is set - string tryPath = m->getOutputDir() + m->getSimpleName(fastaFileNames[i]); - m->mothurOut("Unable to open " + fastaFileNames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine(); - ifstream in2; - ableToOpen = m->openInputFile(tryPath, in2, "noerror"); - in2.close(); - fastaFileNames[i] = tryPath; - } - } + if (!ignore) { - in.close(); - if (ableToOpen == 1) { - m->mothurOut("Unable to open " + fastaFileNames[i] +". It will be disregarded."); m->mothurOutEndLine(); - //erase from file list - fastaFileNames.erase(fastaFileNames.begin()+i); - i--; + if (inputDir != "") { + string path = m->hasPath(fastaFileNames[i]); + //if the user has not given a path then, add inputdir. else leave path alone. + if (path == "") { fastaFileNames[i] = inputDir + fastaFileNames[i]; } + } + + int ableToOpen; + ifstream in; + + ableToOpen = m->openInputFile(fastaFileNames[i], in, "noerror"); + + //if you can't open it, try default location + if (ableToOpen == 1) { + if (m->getDefaultPath() != "") { //default path is set + string tryPath = m->getDefaultPath() + m->getSimpleName(fastaFileNames[i]); + m->mothurOut("Unable to open " + fastaFileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine(); + ifstream in2; + ableToOpen = m->openInputFile(tryPath, in2, "noerror"); + in2.close(); + fastaFileNames[i] = tryPath; + } + } + + //if you can't open it, try default location + if (ableToOpen == 1) { + if (m->getOutputDir() != "") { //default path is set + string tryPath = m->getOutputDir() + m->getSimpleName(fastaFileNames[i]); + m->mothurOut("Unable to open " + fastaFileNames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine(); + ifstream in2; + ableToOpen = m->openInputFile(tryPath, in2, "noerror"); + in2.close(); + fastaFileNames[i] = tryPath; + } + } + + in.close(); + + if (ableToOpen == 1) { + m->mothurOut("Unable to open " + fastaFileNames[i] +". It will be disregarded."); m->mothurOutEndLine(); + //erase from file list + fastaFileNames.erase(fastaFileNames.begin()+i); + i--; + }else { + m->setFastaFile(fastaFileNames[i]); + } } } @@ -155,9 +196,9 @@ ChimeraCheckCommand::ChimeraCheckCommand(string option) { //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 = ""; } - templatefile = validParameter.validFile(parameters, "template", true); + templatefile = validParameter.validFile(parameters, "reference", true); if (templatefile == "not open") { abort = true; } - else if (templatefile == "not found") { templatefile = ""; m->mothurOut("template is a required parameter for the chimera.check command."); m->mothurOutEndLine(); abort = true; } + else if (templatefile == "not found") { templatefile = ""; m->mothurOut("reference is a required parameter for the chimera.check command."); m->mothurOutEndLine(); abort = true; } namefile = validParameter.validFile(parameters, "name", false); if (namefile == "not found") { namefile = ""; } @@ -166,50 +207,67 @@ ChimeraCheckCommand::ChimeraCheckCommand(string option) { //go through files and make sure they are good, if not, then disregard them for (int i = 0; i < nameFileNames.size(); i++) { - if (inputDir != "") { - string path = m->hasPath(nameFileNames[i]); - //if the user has not given a path then, add inputdir. else leave path alone. - if (path == "") { nameFileNames[i] = inputDir + nameFileNames[i]; } - } - - int ableToOpen; - ifstream in; - ableToOpen = m->openInputFile(nameFileNames[i], in, "noerror"); - - //if you can't open it, try default location - if (ableToOpen == 1) { - if (m->getDefaultPath() != "") { //default path is set - string tryPath = m->getDefaultPath() + m->getSimpleName(nameFileNames[i]); - m->mothurOut("Unable to open " + nameFileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine(); - ifstream in2; - ableToOpen = m->openInputFile(tryPath, in2, "noerror"); - in2.close(); - nameFileNames[i] = tryPath; + bool ignore = false; + if (nameFileNames[i] == "current") { + nameFileNames[i] = m->getNameFile(); + if (nameFileNames[i] != "") { m->mothurOut("Using " + nameFileNames[i] + " as input file for the name parameter where you had given current."); m->mothurOutEndLine(); } + else { + m->mothurOut("You have no current namefile, ignoring current."); m->mothurOutEndLine(); ignore=true; + //erase from file list + nameFileNames.erase(nameFileNames.begin()+i); + i--; } } - //if you can't open it, try default location - if (ableToOpen == 1) { - if (m->getOutputDir() != "") { //default path is set - string tryPath = m->getOutputDir() + m->getSimpleName(nameFileNames[i]); - m->mothurOut("Unable to open " + nameFileNames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine(); - ifstream in2; - ableToOpen = m->openInputFile(tryPath, in2, "noerror"); - in2.close(); - nameFileNames[i] = tryPath; - } - } + if (!ignore) { - in.close(); + if (inputDir != "") { + string path = m->hasPath(nameFileNames[i]); + //if the user has not given a path then, add inputdir. else leave path alone. + if (path == "") { nameFileNames[i] = inputDir + nameFileNames[i]; } + } + + int ableToOpen; + ifstream in; + + ableToOpen = m->openInputFile(nameFileNames[i], in, "noerror"); - if (ableToOpen == 1) { - m->mothurOut("Unable to open " + nameFileNames[i] + ". It will be disregarded."); m->mothurOutEndLine(); - //erase from file list - nameFileNames.erase(nameFileNames.begin()+i); - i--; + //if you can't open it, try default location + if (ableToOpen == 1) { + if (m->getDefaultPath() != "") { //default path is set + string tryPath = m->getDefaultPath() + m->getSimpleName(nameFileNames[i]); + m->mothurOut("Unable to open " + nameFileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine(); + ifstream in2; + ableToOpen = m->openInputFile(tryPath, in2, "noerror"); + in2.close(); + nameFileNames[i] = tryPath; + } + } + + //if you can't open it, try default location + if (ableToOpen == 1) { + if (m->getOutputDir() != "") { //default path is set + string tryPath = m->getOutputDir() + m->getSimpleName(nameFileNames[i]); + m->mothurOut("Unable to open " + nameFileNames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine(); + ifstream in2; + ableToOpen = m->openInputFile(tryPath, in2, "noerror"); + in2.close(); + nameFileNames[i] = tryPath; + } + } + + in.close(); + + if (ableToOpen == 1) { + m->mothurOut("Unable to open " + nameFileNames[i] + ". It will be disregarded."); m->mothurOutEndLine(); + //erase from file list + nameFileNames.erase(nameFileNames.begin()+i); + i--; + }else { + m->setNameFile(nameFileNames[i]); + } } - } //make sure there is at least one valid file left @@ -221,7 +279,8 @@ ChimeraCheckCommand::ChimeraCheckCommand(string option) { } } - string temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found") { temp = "1"; } + string temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found"){ temp = m->getProcessors(); } + m->setProcessors(temp); convert(temp, processors); temp = validParameter.validFile(parameters, "ksize", false); if (temp == "not found") { temp = "7"; } @@ -240,47 +299,12 @@ ChimeraCheckCommand::ChimeraCheckCommand(string option) { exit(1); } } -//********************************************************************************************************************** - -void ChimeraCheckCommand::help(){ - try { - - m->mothurOut("The chimera.check command reads a fastafile and templatefile and outputs potentially chimeric sequences.\n"); - m->mothurOut("This command was created using the algorythms described in CHIMERA_CHECK version 2.7 written by Niels Larsen. \n"); - m->mothurOut("The chimera.check command parameters are fasta, template, processors, ksize, increment, svg and name.\n"); - m->mothurOut("The fasta parameter allows you to enter the fasta file containing your potentially chimeric sequences, and is required. \n"); - m->mothurOut("You may enter multiple fasta files by separating their names with dashes. ie. fasta=abrecovery.fasta-amzon.fasta \n"); - m->mothurOut("The template parameter allows you to enter a template file containing known non-chimeric sequences, and is required. \n"); - m->mothurOut("The processors parameter allows you to specify how many processors you would like to use. The default is 1. \n"); - #ifdef USE_MPI - m->mothurOut("When using MPI, the processors parameter is set to the number of MPI processes running. \n"); - #endif - m->mothurOut("The increment parameter allows you to specify how far you move each window while finding chimeric sequences, default is 10.\n"); - m->mothurOut("The ksize parameter allows you to input kmersize, default is 7. \n"); - m->mothurOut("The svg parameter allows you to specify whether or not you would like a svg file outputted for each query sequence, default is False.\n"); - m->mothurOut("The name parameter allows you to enter a file containing names of sequences you would like .svg files for.\n"); - m->mothurOut("You may enter multiple name files by separating their names with dashes. ie. fasta=abrecovery.svg.names-amzon.svg.names \n"); - m->mothurOut("The chimera.check command should be in the following format: \n"); - m->mothurOut("chimera.check(fasta=yourFastaFile, template=yourTemplateFile, processors=yourProcessors, ksize=yourKmerSize) \n"); - m->mothurOut("Example: chimera.check(fasta=AD.fasta, template=core_set_aligned,imputed.fasta, processors=4, ksize=8) \n"); - m->mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFastaFile).\n\n"); - } - catch(exception& e) { - m->errorOut(e, "ChimeraCheckCommand", "help"); - exit(1); - } -} - -//*************************************************************************************************************** - -ChimeraCheckCommand::~ChimeraCheckCommand(){ /* do nothing */ } - //*************************************************************************************************************** int ChimeraCheckCommand::execute(){ try{ - if (abort == true) { return 0; } + if (abort == true) { if (calledHelp) { return 0; } return 2; } for (int i = 0; i < fastaFileNames.size(); i++) { @@ -301,7 +325,7 @@ int ChimeraCheckCommand::execute(){ #ifdef USE_MPI - int pid, end, numSeqsPerProcessor; + int pid, numSeqsPerProcessor; int tag = 2001; vector MPIPos; @@ -572,7 +596,11 @@ int ChimeraCheckCommand::createProcesses(string outputFileName, string filename) out.close(); exit(0); - }else { m->mothurOut("unable to spawn the necessary processes."); m->mothurOutEndLine(); exit(0); } + }else { + m->mothurOut("[ERROR]: unable to spawn the necessary processes."); m->mothurOutEndLine(); + for (int i = 0; i < processIDS.size(); i++) { kill (processIDS[i], SIGINT); } + exit(0); + } } //force parent to wait until all the processes are done