X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=binsequencecommand.cpp;h=2117daff4f2558e26bcf0008666f87bee0180f4d;hb=e0ce7cbc93d7d2fbb753ca694182db092a0ea0e7;hp=08ae6b607a13e3406aa4fe42d8a1f5025a41bbc0;hpb=f37a59b81c339f574d97042ff6e364146feb457a;p=mothur.git diff --git a/binsequencecommand.cpp b/binsequencecommand.cpp index 08ae6b6..2117daf 100644 --- a/binsequencecommand.cpp +++ b/binsequencecommand.cpp @@ -9,44 +9,152 @@ #include "binsequencecommand.h" + +//********************************************************************************************************************** +vector BinSeqCommand::setParameters(){ + try { + CommandParameter plist("list", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(plist); + 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 pgroup("group", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(pgroup); + CommandParameter plabel("label", "String", "", "", "", "", "",false,false); parameters.push_back(plabel); + 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, "BinSeqCommand", "setParameters"); + exit(1); + } +} +//********************************************************************************************************************** +string BinSeqCommand::getHelpString(){ + try { + string helpString = ""; + helpString += "The bin.seqs command parameters are list, fasta, name, label and group. The fasta and list are required, unless you have a valid current list and fasta file.\n"; + helpString += "The label parameter allows you to select what distance levels you would like a output files created for, and are separated by dashes.\n"; + helpString += "The bin.seqs command should be in the following format: bin.seqs(fasta=yourFastaFile, name=yourNamesFile, group=yourGroupFile, label=yourLabels).\n"; + helpString += "Example bin.seqs(fasta=amazon.fasta, group=amazon.groups, name=amazon.names).\n"; + helpString += "The default value for label is all lines in your inputfile.\n"; + helpString += "The bin.seqs command outputs a .fasta file for each distance you specify appending the OTU number to each name.\n"; + helpString += "If you provide a groupfile, then it also appends the sequences group to the name.\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, "BinSeqCommand", "getHelpString"); + exit(1); + } +} +//********************************************************************************************************************** +BinSeqCommand::BinSeqCommand(){ + try { + abort = true; calledHelp = true; + setParameters(); + vector tempOutNames; + outputTypes["fasta"] = tempOutNames; + } + catch(exception& e) { + m->errorOut(e, "BinSeqCommand", "BinSeqCommand"); + exit(1); + } +} //********************************************************************************************************************** -BinSeqCommand::BinSeqCommand(string option){ +BinSeqCommand::BinSeqCommand(string option) { try { - globaldata = GlobalData::getInstance(); - abort = false; + abort = false; calledHelp = false; allLines = 1; labels.clear(); //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","label","name", "group"}; - vector myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string))); + vector myArray = setParameters(); 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++) { + for (it = parameters.begin(); it != parameters.end(); it++) { if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; } } - //make sure the user has already run the read.otu command - if (globaldata->getListFile() == "") { - mothurOut("You must read a listfile before running the bin.seqs command."); - mothurOutEndLine(); - abort = true; - } + //initialize outputTypes + vector tempOutNames; + outputTypes["fasta"] = 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 = ""; } + else { + string path; + 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; } + } + } + //check for required parameters fastafile = validParameter.validFile(parameters, "fasta", true); - if (fastafile == "not found") { mothurOut("fasta is a required parameter for the bin.seqs command."); mothurOutEndLine(); abort = true; } + if (fastafile == "not found") { //if there is a current phylip file, use it + fastafile = m->getFastaFile(); + if (fastafile != "") { m->mothurOut("Using " + fastafile + " as input file for the fasta parameter."); m->mothurOutEndLine(); } + else { m->mothurOut("You have no current fasta file and the fasta parameter is required."); m->mothurOutEndLine(); abort = true; } + } else if (fastafile == "not open") { abort = true; } + else { m->setFastaFile(fastafile); } + + listfile = validParameter.validFile(parameters, "list", true); + if (listfile == "not found") { + listfile = m->getListFile(); + if (listfile != "") { m->mothurOut("Using " + listfile + " as input file for the list parameter."); m->mothurOutEndLine(); } + else { m->mothurOut("You have no current list file and the list parameter is required."); m->mothurOutEndLine(); abort = true; } + } + else if (listfile == "not open") { listfile = ""; abort = true; } + else { m->setListFile(listfile); } + + //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 = ""; + outputDir += m->hasPath(listfile); //if user entered a file with a path then preserve it + } + //check for optional parameter and set defaults // ...at some point should added some additional type checking... @@ -54,101 +162,63 @@ BinSeqCommand::BinSeqCommand(string option){ label = validParameter.validFile(parameters, "label", false); if (label == "not found") { label = ""; } else { - if(label != "all") { splitAtDash(label, labels); allLines = 0; } + if(label != "all") { m->splitAtDash(label, labels); allLines = 0; } else { allLines = 1; } } - //if the user has not specified any labels use the ones from read.otu - if (label == "") { - allLines = globaldata->allLines; - labels = globaldata->labels; - } - namesfile = validParameter.validFile(parameters, "name", true); - if (namesfile == "not open") { abort = true; } + if (namesfile == "not open") { namesfile = ""; abort = true; } else if (namesfile == "not found") { namesfile = ""; } + else { m->setNameFile(namesfile); } groupfile = validParameter.validFile(parameters, "group", true); if (groupfile == "not open") { abort = true; } else if (groupfile == "not found") { groupfile = ""; } + else { m->setGroupFile(groupfile); } - if (abort == false) { -// openInputFile(fastafile, in); - fasta = new FastaMap(); - if (groupfile != "") { - groupMap = new GroupMap(groupfile); - groupMap->readMap(); - } + if (namesfile == ""){ + vector files; files.push_back(fastafile); + parser.getNameFile(files); } - + } } catch(exception& e) { - errorOut(e, "BinSeqCommand", "BinSeqCommand"); + m->errorOut(e, "BinSeqCommand", "BinSeqCommand"); exit(1); } } //********************************************************************************************************************** -void BinSeqCommand::help(){ - try { - mothurOut("The bin.seqs command can only be executed after a successful read.otu command of a listfile.\n"); - mothurOut("The bin.seqs command parameters are fasta, name, label and group. The fasta parameter is required.\n"); - mothurOut("The label parameter allows you to select what distance levels you would like a output files created for, and are separated by dashes.\n"); - mothurOut("The bin.seqs command should be in the following format: bin.seqs(fasta=yourFastaFile, name=yourNamesFile, group=yourGroupFile, label=yourLabels).\n"); - mothurOut("Example bin.seqs(fasta=amazon.fasta, group=amazon.groups, name=amazon.names).\n"); - mothurOut("The default value for label is all lines in your inputfile.\n"); - mothurOut("The bin.seqs command outputs a .fasta file for each distance you specify appending the OTU number to each name.\n"); - mothurOut("If you provide a groupfile, then it also appends the sequences group to the name.\n"); - mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFastaFile).\n\n"); - } - catch(exception& e) { - errorOut(e, "BinSeqCommand", "help"); - exit(1); - } -} - -//********************************************************************************************************************** - -BinSeqCommand::~BinSeqCommand(){ - //made new in execute - if (abort == false) { - delete input; globaldata->ginput = NULL; - delete read; - globaldata->gListVector = NULL; - delete fasta; - if (groupfile != "") { delete groupMap; globaldata->gGroupmap = NULL; } - } -} - +BinSeqCommand::~BinSeqCommand(){} //********************************************************************************************************************** int BinSeqCommand::execute(){ try { - if (abort == true) { return 0; } + if (abort == true) { if (calledHelp) { return 0; } return 2; } int error = 0; + fasta = new FastaMap(); + if (groupfile != "") { + groupMap = new GroupMap(groupfile); + groupMap->readMap(); + } + //read fastafile fasta->readFastaFile(fastafile); - - //set format to list so input can get listvector -// globaldata->setFormat("list"); - //if user gave a namesfile then use it if (namesfile != "") { readNamesFile(); } - //read list file - read = new ReadOTUFile(globaldata->getListFile()); - read->read(&*globaldata); - - input = globaldata->ginput; - list = globaldata->gListVector; + input = new InputData(listfile, "list"); + list = input->getListVector(); string lastLabel = list->getLabel(); + if (m->control_pressed) { delete input; delete fasta; if (groupfile != "") { delete groupMap; } return 0; } + //if the users enters label "0.06" and there is no "0.06" in their file use the next lowest label. set processedLabels; set userLabels = labels; @@ -156,24 +226,31 @@ int BinSeqCommand::execute(){ while((list != NULL) && ((allLines == 1) || (userLabels.size() != 0))) { + if(m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } delete input; delete fasta; if (groupfile != "") { delete groupMap; } return 0; } + if(allLines == 1 || labels.count(list->getLabel()) == 1){ error = process(list); - if (error == 1) { return 0; } + if (error == 1) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } delete input; delete fasta; if (groupfile != "") { delete groupMap; } return 0; } processedLabels.insert(list->getLabel()); userLabels.erase(list->getLabel()); } - if ((anyLabelsToProcess(list->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) { + if ((m->anyLabelsToProcess(list->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) { + string saveLabel = list->getLabel(); + delete list; list = input->getListVector(lastLabel); error = process(list); - if (error == 1) { return 0; } + if (error == 1) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } delete input; delete fasta; if (groupfile != "") { delete groupMap; } return 0; } processedLabels.insert(list->getLabel()); userLabels.erase(list->getLabel()); + + //restore real lastlabel to save below + list->setLabel(saveLabel); } lastLabel = list->getLabel(); @@ -182,17 +259,18 @@ int BinSeqCommand::execute(){ list = input->getListVector(); } - + if(m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } delete input; delete fasta; if (groupfile != "") { delete groupMap; } return 0; } + //output error messages about any remaining user labels set::iterator it; bool needToRun = false; for (it = userLabels.begin(); it != userLabels.end(); it++) { - mothurOut("Your file does not include the label " + *it); + m->mothurOut("Your file does not include the label " + *it); if (processedLabels.count(lastLabel) != 1) { - mothurOut(". I will use " + lastLabel + "."); mothurOutEndLine(); + m->mothurOut(". I will use " + lastLabel + "."); m->mothurOutEndLine(); needToRun = true; }else { - mothurOut(". Please refer to " + lastLabel + "."); mothurOutEndLine(); + m->mothurOut(". Please refer to " + lastLabel + "."); m->mothurOutEndLine(); } } @@ -202,15 +280,27 @@ int BinSeqCommand::execute(){ list = input->getListVector(lastLabel); error = process(list); - if (error == 1) { return 0; } + if (error == 1) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } delete input; delete fasta; if (groupfile != "") { delete groupMap; } return 0; } delete list; } + delete input; + delete fasta; + if (groupfile != "") { delete groupMap; } + + if(m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } + + m->mothurOutEndLine(); + m->mothurOut("Output File Names: "); m->mothurOutEndLine(); + for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); } + m->mothurOutEndLine(); + + return 0; } catch(exception& e) { - errorOut(e, "BinSeqCommand", "execute"); + m->errorOut(e, "BinSeqCommand", "execute"); exit(1); } } @@ -219,7 +309,7 @@ int BinSeqCommand::execute(){ void BinSeqCommand::readNamesFile() { try { vector dupNames; - openInputFile(namesfile, inNames); + m->openInputFile(namesfile, inNames); string name, names, sequence; @@ -230,7 +320,7 @@ void BinSeqCommand::readNamesFile() { dupNames.clear(); //parse names into vector - splitAtComma(names, dupNames); + m->splitAtComma(names, dupNames); //store names in fasta map sequence = fasta->getSequence(name); @@ -238,13 +328,13 @@ void BinSeqCommand::readNamesFile() { fasta->push_back(dupNames[i], sequence); } - gobble(inNames); + m->gobble(inNames); } inNames.close(); } catch(exception& e) { - errorOut(e, "BinSeqCommand", "readNamesFile"); + m->errorOut(e, "BinSeqCommand", "readNamesFile"); exit(1); } } @@ -253,14 +343,20 @@ void BinSeqCommand::readNamesFile() { int BinSeqCommand::process(ListVector* list) { try { string binnames, name, sequence; - string outputFileName = getRootName(globaldata->getListFile()) + list->getLabel() + ".fasta"; - openOutputFile(outputFileName, out); + + string outputFileName = outputDir + m->getRootName(m->getSimpleName(listfile)) + list->getLabel() + ".fasta"; + m->openOutputFile(outputFileName, out); + + //save to output list of output file names + outputNames.push_back(outputFileName); outputTypes["fasta"].push_back(outputFileName); - mothurOut(list->getLabel()); mothurOutEndLine(); + m->mothurOut(list->getLabel()); m->mothurOutEndLine(); //for each bin in the list vector for (int i = 0; i < list->size(); i++) { - + + if (m->control_pressed) { return 1; } + binnames = list->get(i); while (binnames.find_first_of(',') != -1) { name = binnames.substr(0,binnames.find_first_of(',')); @@ -271,24 +367,22 @@ int BinSeqCommand::process(ListVector* list) { if (sequence != "not found") { //if you don't have groups if (groupfile == "") { - name = name + "|" + toString(i+1); + name = name + "\t" + toString(i+1); out << ">" << name << endl; out << sequence << endl; }else {//if you do have groups string group = groupMap->getGroup(name); if (group == "not found") { - mothurOut(name + " is missing from your group file. Please correct. "); mothurOutEndLine(); - remove(outputFileName.c_str()); + m->mothurOut(name + " is missing from your group file. Please correct. "); m->mothurOutEndLine(); return 1; }else{ - name = name + "|" + group + "|" + toString(i+1); + name = name + "\t" + group + "\t" + toString(i+1); out << ">" << name << endl; out << sequence << endl; } } }else { - mothurOut(name + " is missing from your fasta or name file. Please correct. "); mothurOutEndLine(); - remove(outputFileName.c_str()); + m->mothurOut(name + " is missing from your fasta or name file. Please correct. "); m->mothurOutEndLine(); return 1; } @@ -299,24 +393,22 @@ int BinSeqCommand::process(ListVector* list) { if (sequence != "not found") { //if you don't have groups if (groupfile == "") { - binnames = binnames + "|" + toString(i+1); + binnames = binnames + "\t" + toString(i+1); out << ">" << binnames << endl; out << sequence << endl; }else {//if you do have groups string group = groupMap->getGroup(binnames); if (group == "not found") { - mothurOut(binnames + " is missing from your group file. Please correct. "); mothurOutEndLine(); - remove(outputFileName.c_str()); + m->mothurOut(binnames + " is missing from your group file. Please correct. "); m->mothurOutEndLine(); return 1; }else{ - binnames = binnames + "|" + group + "|" + toString(i+1); + binnames = binnames + "\t" + group + "\t" + toString(i+1); out << ">" << binnames << endl; out << sequence << endl; } } }else { - mothurOut(binnames + " is missing from your fasta or name file. Please correct. "); mothurOutEndLine(); - remove(outputFileName.c_str()); + m->mothurOut(binnames + " is missing from your fasta or name file. Please correct. "); m->mothurOutEndLine(); return 1; } } @@ -326,7 +418,7 @@ int BinSeqCommand::process(ListVector* list) { } catch(exception& e) { - errorOut(e, "BinSeqCommand", "process"); + m->errorOut(e, "BinSeqCommand", "process"); exit(1); } }