X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=chimeraccodecommand.cpp;h=df4e67db118462e1115857331c7adcc4551a272c;hb=62c36830aae6dd6151898ec6e07df59c8aed79fe;hp=1f6a5a56a8ee7398a8f1b0b454986c28c1483fe7;hpb=8bc3e5b38c2317a1715f53be22fa96455868c281;p=mothur.git diff --git a/chimeraccodecommand.cpp b/chimeraccodecommand.cpp index 1f6a5a5..df4e67d 100644 --- a/chimeraccodecommand.cpp +++ b/chimeraccodecommand.cpp @@ -9,67 +9,83 @@ #include "chimeraccodecommand.h" #include "ccode.h" - //********************************************************************************************************************** -vector ChimeraCcodeCommand::getValidParameters(){ +vector ChimeraCcodeCommand::setParameters(){ try { - string AlignArray[] = {"fasta", "filter", "processors", "window", "template", "mask", "numwanted", "outputdir","inputdir" }; - 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 pfilter("filter", "Boolean", "", "F", "", "", "",false,false); parameters.push_back(pfilter); + CommandParameter pwindow("window", "Number", "", "0", "", "", "",false,false); parameters.push_back(pwindow); + CommandParameter pnumwanted("numwanted", "Number", "", "20", "", "", "",false,false); parameters.push_back(pnumwanted); + CommandParameter pmask("mask", "String", "", "", "", "", "",false,false); parameters.push_back(pmask); + 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, "ChimeraCcodeCommand", "getValidParameters"); - exit(1); - } -} -//********************************************************************************************************************** -ChimeraCcodeCommand::ChimeraCcodeCommand(){ - try { - vector tempOutNames; - outputTypes["chimera"] = tempOutNames; - outputTypes["mapinfo"] = tempOutNames; - outputTypes["accnos"] = tempOutNames; - } - catch(exception& e) { - m->errorOut(e, "ChimeraCcodeCommand", "ChimeraCcodeCommand"); + m->errorOut(e, "ChimeraCcodeCommand", "setParameters"); exit(1); } } //********************************************************************************************************************** -vector ChimeraCcodeCommand::getRequiredParameters(){ +string ChimeraCcodeCommand::getHelpString(){ try { - string AlignArray[] = {"template","fasta"}; - vector myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string))); - return myArray; + string helpString = ""; + helpString += "The chimera.ccode command reads a fastafile and referencefile and outputs potentially chimeric sequences.\n"; + helpString += "This command was created using the algorythms described in the 'Evaluating putative chimeric sequences from PCR-amplified products' paper by Juan M. Gonzalez, Johannes Zimmerman and Cesareo Saiz-Jimenez.\n"; + helpString += "The chimera.ccode command parameters are fasta, reference, filter, mask, processors, window and numwanted.\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 filter parameter allows you to specify if you would like to apply a vertical and 50% soft filter. \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 mask parameter allows you to specify a file containing one sequence you wish to use as a mask for the your sequences. \n"; + helpString += "The window parameter allows you to specify the window size for searching for chimeras. \n"; + helpString += "The numwanted parameter allows you to specify how many sequences you would each query sequence compared with.\n"; + helpString += "The chimera.ccode command should be in the following format: \n"; + helpString += "chimera.ccode(fasta=yourFastaFile, reference=yourTemplate) \n"; + helpString += "Example: chimera.ccode(fasta=AD.align, reference=core_set_aligned.imputed.fasta) \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, "ChimeraCcodeCommand", "getRequiredParameters"); + m->errorOut(e, "ChimeraCcodeCommand", "getHelpString"); exit(1); } } //********************************************************************************************************************** -vector ChimeraCcodeCommand::getRequiredFiles(){ +ChimeraCcodeCommand::ChimeraCcodeCommand(){ try { - vector myArray; - return myArray; + abort = true; calledHelp = true; + setParameters(); + vector tempOutNames; + outputTypes["chimera"] = tempOutNames; + outputTypes["mapinfo"] = tempOutNames; + outputTypes["accnos"] = tempOutNames; } catch(exception& e) { - m->errorOut(e, "ChimeraCcodeCommand", "getRequiredFiles"); + m->errorOut(e, "ChimeraCcodeCommand", "ChimeraCcodeCommand"); exit(1); } } //*************************************************************************************************************** ChimeraCcodeCommand::ChimeraCcodeCommand(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", "filter", "processors", "window", "template", "mask", "numwanted", "outputdir","inputdir" }; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + vector myArray = setParameters(); OptionParser parser(option); map parameters = parser.getParameters(); @@ -92,61 +108,84 @@ ChimeraCcodeCommand::ChimeraCcodeCommand(string option) { if (inputDir == "not found"){ inputDir = ""; } else { string path; - it = parameters.find("template"); + it = parameters.find("reference"); //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["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.ccode 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(); - ableToOpen = m->openInputFile(tryPath, in, "noerror"); - 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(); - ableToOpen = m->openInputFile(tryPath, in, "noerror"); - fastaFileNames[i] = tryPath; - } - } + if (!ignore) { - in.close(); + 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 (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 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--; + } } } @@ -157,9 +196,9 @@ ChimeraCcodeCommand::ChimeraCcodeCommand(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.ccode command."); m->mothurOutEndLine(); abort = true; } + else if (templatefile == "not found") { templatefile = ""; m->mothurOut("reference is a required parameter for the chimera.ccode command."); m->mothurOutEndLine(); abort = true; } maskfile = validParameter.validFile(parameters, "mask", false); if (maskfile == "not found") { maskfile = ""; } @@ -180,7 +219,8 @@ ChimeraCcodeCommand::ChimeraCcodeCommand(string option) { temp = validParameter.validFile(parameters, "filter", false); if (temp == "not found") { temp = "F"; } filter = m->isTrue(temp); - temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found") { temp = "1"; } + temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found"){ temp = m->getProcessors(); } + m->setProcessors(temp); convert(temp, processors); temp = validParameter.validFile(parameters, "window", false); if (temp == "not found") { temp = "0"; } @@ -196,46 +236,11 @@ ChimeraCcodeCommand::ChimeraCcodeCommand(string option) { exit(1); } } -//********************************************************************************************************************** - -void ChimeraCcodeCommand::help(){ - try { - - m->mothurOut("The chimera.ccode command reads a fastafile and templatefile and outputs potentially chimeric sequences.\n"); - m->mothurOut("This command was created using the algorythms described in the 'Evaluating putative chimeric sequences from PCR-amplified products' paper by Juan M. Gonzalez, Johannes Zimmerman and Cesareo Saiz-Jimenez.\n"); - m->mothurOut("The chimera.ccode command parameters are fasta, template, filter, mask, processors, window and numwanted.\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 filter parameter allows you to specify if you would like to apply a vertical and 50% soft filter. \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 mask parameter allows you to specify a file containing one sequence you wish to use as a mask for the your sequences. \n"); - m->mothurOut("The window parameter allows you to specify the window size for searching for chimeras. \n"); - m->mothurOut("The numwanted parameter allows you to specify how many sequences you would each query sequence compared with.\n"); - m->mothurOut("The chimera.ccode command should be in the following format: \n"); - m->mothurOut("chimera.ccode(fasta=yourFastaFile, template=yourTemplate) \n"); - m->mothurOut("Example: chimera.ccode(fasta=AD.align, template=core_set_aligned.imputed.fasta) \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, "ChimeraCcodeCommand", "help"); - exit(1); - } -} - //*************************************************************************************************************** - -ChimeraCcodeCommand::~ChimeraCcodeCommand(){ /* do nothing */ } - -//*************************************************************************************************************** - int ChimeraCcodeCommand::execute(){ try{ - if (abort == true) { return 0; } + if (abort == true) { if (calledHelp) { return 0; } return 2; } for (int s = 0; s < fastaFileNames.size(); s++) { @@ -268,7 +273,7 @@ int ChimeraCcodeCommand::execute(){ #ifdef USE_MPI - int pid, end, numSeqsPerProcessor; + int pid, numSeqsPerProcessor; int tag = 2001; vector MPIPos; @@ -299,7 +304,7 @@ int ChimeraCcodeCommand::execute(){ if (m->control_pressed) { MPI_File_close(&inMPI); MPI_File_close(&outMPI); MPI_File_close(&outMPIAccnos); for (int j = 0; j < outputNames.size(); j++) { remove(outputNames[j].c_str()); } outputTypes.clear(); delete chimera; return 0; } if (pid == 0) { //you are the root process - string outTemp = "For full window mapping info refer to " + mapInfo + "\n\n"; + string outTemp = "For full window mapping info refer to " + mapInfo + "\n"; //print header int length = outTemp.length(); @@ -430,6 +435,14 @@ int ChimeraCcodeCommand::execute(){ m->mothurOutEndLine(); m->mothurOut("It took " + toString(time(NULL) - start) + " secs to check " + toString(numSeqs) + " sequences."); 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); } + } + m->mothurOutEndLine(); m->mothurOut("Output File Names: "); m->mothurOutEndLine(); for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); } @@ -546,7 +559,7 @@ int ChimeraCcodeCommand::driverMPI(int start, int num, MPI_File& inMPI, MPI_File if (m->control_pressed) { delete candidateSeq; return 1; } //print results - bool isChimeric = chimera->print(outMPI, outAccMPI); + chimera->print(outMPI, outAccMPI); } } delete candidateSeq; @@ -593,7 +606,11 @@ int ChimeraCcodeCommand::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