X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=makegroupcommand.cpp;h=68b1e84d0e7e6eb811971128d14490832ad390ae;hb=541bab1dac00688b4c3a8c4a95ab464412663c50;hp=24c2de2e5de0499bae2ef1366987090fefa5de5f;hpb=17aafaea968f87e581297063b16695ad515bea53;p=mothur.git diff --git a/makegroupcommand.cpp b/makegroupcommand.cpp index 24c2de2..68b1e84 100644 --- a/makegroupcommand.cpp +++ b/makegroupcommand.cpp @@ -8,22 +8,87 @@ */ #include "makegroupcommand.h" +#include "sequence.hpp" + + +//********************************************************************************************************************** +vector MakeGroupCommand::setParameters(){ + try { + CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "none","group",false,true,true); parameters.push_back(pfasta); + CommandParameter pgroups("groups", "String", "", "", "", "", "","",false,false,true); parameters.push_back(pgroups); + CommandParameter poutput("output", "String", "", "", "", "", "","",false,false); parameters.push_back(poutput); + 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, "MakeGroupCommand", "setParameters"); + exit(1); + } +} +//********************************************************************************************************************** +string MakeGroupCommand::getHelpString(){ + try { + string helpString = ""; + helpString += "The make.group command reads a fasta file or series of fasta files and creates a groupfile.\n"; + helpString += "The make.group command parameters are fasta, groups and output. Fasta and group are required.\n"; + helpString += "The output parameter allows you to specify the name of groupfile created. \n"; + helpString += "The make.group command should be in the following format: \n"; + helpString += "make.group(fasta=yourFastaFiles, groups=yourGroups). \n"; + helpString += "Example make.group(fasta=seqs1.fasta-seq2.fasta-seqs3.fasta, groups=A-B-C)\n"; + helpString += "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFastaFiles).\n"; + return helpString; + } + catch(exception& e) { + m->errorOut(e, "MakeGroupCommand", "getHelpString"); + exit(1); + } +} +//********************************************************************************************************************** +string MakeGroupCommand::getOutputPattern(string type) { + try { + string pattern = ""; + + if (type == "group") { pattern = "[filename],groups"; } + else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; } + + return pattern; + } + catch(exception& e) { + m->errorOut(e, "MakeGroupCommand", "getOutputPattern"); + exit(1); + } +} +//********************************************************************************************************************** +MakeGroupCommand::MakeGroupCommand(){ + try { + abort = true; calledHelp = true; + setParameters(); + vector tempOutNames; + outputTypes["group"] = tempOutNames; + } + catch(exception& e) { + m->errorOut(e, "MakeGroupCommand", "MakeGroupCommand"); + exit(1); + } +} //********************************************************************************************************************** MakeGroupCommand::MakeGroupCommand(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 AlignArray[] = {"fasta","groups","outputdir","inputdir"}; - vector myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string))); + vector myArray = setParameters(); OptionParser parser(option); map parameters = parser.getParameters(); @@ -35,103 +100,158 @@ MakeGroupCommand::MakeGroupCommand(string option) { for (it = parameters.begin(); it != parameters.end(); it++) { if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; } } - - //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 = ""; } - + //initialize outputTypes + vector tempOutNames; + outputTypes["group"] = tempOutNames; + //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 = ""; } - fastaFileName = validParameter.validFile(parameters, "fasta", false); - if (fastaFileName == "not found") { m->mothurOut("fasta is a required parameter for the make.group command."); m->mothurOutEndLine(); abort = true; } - else { - splitAtDash(fastaFileName, fastaFileNames); + if (fastaFileName == "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(fastaFileName, 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 = 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 = openInputFile(fastaFileNames[i], in); - in.close(); - - if (ableToOpen == 1) { - m->mothurOut(fastaFileNames[i] + " will be disregarded."); m->mothurOutEndLine(); - //erase from file list - fastaFileNames.erase(fastaFileNames.begin()+i); - i--; + 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(); + filename += m->getRootName(m->getSimpleName(fastaFileNames[i])); + } + 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 (!ignore) { + 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]; } + } + + ifstream in; + int 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{ filename += m->getRootName(m->getSimpleName(fastaFileNames[i])); m->setFastaFile(fastaFileNames[i]); } + } } + //prevent giantic file name + map variables; + variables["[filename]"] = filename; + if (fastaFileNames.size() > 3) { variables["[filename]"] = outputDir + "merge"; } + filename = getOutputFileName("group",variables); + //make sure there is at least one valid file left if (fastaFileNames.size() == 0) { m->mothurOut("no valid files."); m->mothurOutEndLine(); abort = true; } } - + + //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 = ""; } + + output = validParameter.validFile(parameters, "output", false); + if (output == "not found") { output = ""; } + else{ filename = output; } + + groups = validParameter.validFile(parameters, "groups", false); + if (groups == "not found") { m->mothurOut("groups is a required parameter for the make.group command."); m->mothurOutEndLine(); abort = true; } + else { m->splitAtDash(groups, groupsNames); } + + if (groupsNames.size() != fastaFileNames.size()) { m->mothurOut("You do not have the same number of valid fastfile files as groups. This could be because we could not open a fastafile."); m->mothurOutEndLine(); abort = true; } } - } catch(exception& e) { m->errorOut(e, "MakeGroupCommand", "MakeGroupCommand"); exit(1); } } - -//********************************************************************************************************************** - -MakeGroupCommand::~MakeGroupCommand(){ } - -//********************************************************************************************************************** - -void MakeGroupCommand::help(){ - try { - m->mothurOut("The align.seqs command reads a file containing sequences and creates an alignment file and a report file.\n"); - m->mothurOut("The align.seqs command parameters are template, candidate, search, ksize, align, match, mismatch, gapopen and gapextend.\n"); - m->mothurOut("The template and candidate parameters are required. You may enter multiple fasta files by separating their names with dashes. ie. fasta=abrecovery.fasta-amzon.fasta \n"); - m->mothurOut("The search parameter allows you to specify the method to find most similar template. Your options are: suffix, kmer and blast. The default is kmer.\n"); - m->mothurOut("The align parameter allows you to specify the alignment method to use. Your options are: gotoh, needleman, blast and noalign. The default is needleman.\n"); - m->mothurOut("The ksize parameter allows you to specify the kmer size for finding most similar template to candidate. The default is 8.\n"); - m->mothurOut("The match parameter allows you to specify the bonus for having the same base. The default is 1.0.\n"); - m->mothurOut("The mistmatch parameter allows you to specify the penalty for having different bases. The default is -1.0.\n"); - m->mothurOut("The gapopen parameter allows you to specify the penalty for opening a gap in an alignment. The default is -2.0.\n"); - m->mothurOut("The gapextend parameter allows you to specify the penalty for extending a gap in an alignment. The default is -1.0.\n"); - m->mothurOut("The flip parameter is used to specify whether or not you want mothur to try the reverse complement if a sequence falls below the threshold. The default is false.\n"); - m->mothurOut("The threshold is used to specify a cutoff at which an alignment is deemed 'bad' and the reverse complement may be tried. The default threshold is 0.50, meaning 50% of the bases are removed in the alignment.\n"); - m->mothurOut("If the flip parameter is set to true the reverse complement of the sequence is aligned and the better alignment is reported.\n"); - m->mothurOut("The default for the threshold parameter is 0.50, meaning at least 50% of the bases must remain or the sequence is reported as potentially reversed.\n"); - m->mothurOut("The align.seqs command should be in the following format: \n"); - m->mothurOut("align.seqs(template=yourTemplateFile, candidate=yourCandidateFile, align=yourAlignmentMethod, search=yourSearchmethod, ksize=yourKmerSize, match=yourMatchBonus, mismatch=yourMismatchpenalty, gapopen=yourGapopenPenalty, gapextend=yourGapExtendPenalty) \n"); - m->mothurOut("Example align.seqs(candidate=candidate.fasta, template=core.filtered, align=kmer, search=gotoh, ksize=8, match=2.0, mismatch=3.0, gapopen=-2.0, gapextend=-1.0)\n"); - m->mothurOut("Note: No spaces between parameter labels (i.e. candidate), '=' and parameters (i.e.yourFastaFile).\n\n"); - } - catch(exception& e) { - m->errorOut(e, "MakeGroupCommand", "help"); - exit(1); - } -} - - //********************************************************************************************************************** int MakeGroupCommand::execute(){ try { - if (abort == true) { return 0; } + if (abort == true) { if (calledHelp) { return 0; } return 2; } + + if (outputDir == "") { outputDir = m->hasPath(fastaFileNames[0]); } + + filename = outputDir + filename; + + ofstream out; + m->openOutputFile(filename, out); + + for (int i = 0; i < fastaFileNames.size(); i++) { + + if (m->control_pressed) { outputTypes.clear(); out.close(); m->mothurRemove(filename); return 0; } + + ifstream in; + m->openInputFile(fastaFileNames[i], in); + + while (!in.eof()) { + + Sequence seq(in, "no align"); m->gobble(in); + + if (m->control_pressed) { outputTypes.clear(); in.close(); out.close(); m->mothurRemove(filename); return 0; } + + if (seq.getName() != "") { out << seq.getName() << '\t' << groupsNames[i] << endl; } + } + in.close(); + } + out.close(); m->mothurOutEndLine(); - m->mothurOut("Output File Names: "); m->mothurOutEndLine(); - //for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); } + m->mothurOut("Output File Names: " + filename); m->mothurOutEndLine(); outputNames.push_back(filename); outputTypes["group"].push_back(filename); m->mothurOutEndLine(); - + + //set group file as new current groupfile + string current = ""; + itTypes = outputTypes.find("group"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setGroupFile(current); } + } + return 0; } catch(exception& e) { @@ -139,4 +259,6 @@ int MakeGroupCommand::execute(){ exit(1); } } +//********************************************************************************************************************** +