X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=binsequencecommand.cpp;h=6618eb6e5aa60109cf908786f4b50f7a06b02293;hb=96b36196d49a3d1f6bc49a26a9d2aa2da7ff876e;hp=7810ea9f793255e31e44c854a5a4c21639019c60;hpb=b22853b5cfbf5c47949ad2a084f2fad88b2e4be4;p=mothur.git diff --git a/binsequencecommand.cpp b/binsequencecommand.cpp index 7810ea9..6618eb6 100644 --- a/binsequencecommand.cpp +++ b/binsequencecommand.cpp @@ -10,46 +10,171 @@ #include "binsequencecommand.h" //********************************************************************************************************************** -BinSeqCommand::BinSeqCommand(){ +BinSeqCommand::BinSeqCommand(string option){ try { globaldata = GlobalData::getInstance(); - fastafile = globaldata->getFastaFile(); - namesfile = globaldata->getNameFile(); - openInputFile(fastafile, in); + abort = false; + allLines = 1; + labels.clear(); - fasta = new FastaMap(); + //allow user to run help + if(option == "help") { help(); abort = true; } + + else { + //valid paramters for this command + string AlignArray[] = {"fasta","label","name", "group","outputdir","inputdir"}; + vector myArray (AlignArray, AlignArray+(sizeof(AlignArray)/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 (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 = ""; + outputDir += hasPath(globaldata->getListFile()); //if user entered a file with a path then preserve it + } + + + //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; + } + + //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 = 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("name"); + //user has given a template file + if(it != parameters.end()){ + path = 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 = 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; } + else if (fastafile == "not open") { abort = true; } + + //check for optional parameter and set defaults + // ...at some point should added some additional type checking... + + label = validParameter.validFile(parameters, "label", false); + if (label == "not found") { label = ""; } + else { + if(label != "all") { 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; } + else if (namesfile == "not found") { namesfile = ""; } + + groupfile = validParameter.validFile(parameters, "group", true); + if (groupfile == "not open") { abort = true; } + else if (groupfile == "not found") { groupfile = ""; } + + if (abort == false) { +// openInputFile(fastafile, in); + fasta = new FastaMap(); + if (groupfile != "") { + groupMap = new GroupMap(groupfile); + + int error = groupMap->readMap(); + if (error == 1) { delete groupMap; abort = true; } + } + } + + } } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the BinSeqCommand class Function BinSeqCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + errorOut(e, "BinSeqCommand", "BinSeqCommand"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the BinSeqCommand class function BinSeqCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; +} +//********************************************************************************************************************** + +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(){ - delete input; - delete read; - delete fasta; - delete list; + //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; } + } } //********************************************************************************************************************** int BinSeqCommand::execute(){ try { - int count = 1; - string binnames, name, sequence; + if (abort == true) { return 0; } + + int error = 0; //read fastafile - fasta->readFastaFile(in); + fasta->readFastaFile(fastafile); + //set format to list so input can get listvector - globaldata->setFormat("list"); +// globaldata->setFormat("list"); //if user gave a namesfile then use it if (namesfile != "") { @@ -62,69 +187,77 @@ int BinSeqCommand::execute(){ input = globaldata->ginput; list = globaldata->gListVector; + string lastLabel = list->getLabel(); + + //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; + - while(list != NULL){ + while((list != NULL) && ((allLines == 1) || (userLabels.size() != 0))) { - if(globaldata->allLines == 1 || globaldata->lines.count(count) == 1 || globaldata->labels.count(list->getLabel()) == 1){ + if(allLines == 1 || labels.count(list->getLabel()) == 1){ - string outputFileName = getRootName(globaldata->getListFile()) + list->getLabel() + ".fasta"; - openOutputFile(outputFileName, out); - - cout << list->getLabel() << '\t' << count << endl; + error = process(list); + if (error == 1) { return 0; } + + processedLabels.insert(list->getLabel()); + userLabels.erase(list->getLabel()); + } + + if ((anyLabelsToProcess(list->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) { + string saveLabel = list->getLabel(); - //for each bin in the list vector - for (int i = 0; i < list->size(); i++) { - - binnames = list->get(i); - while (binnames.find_first_of(',') != -1) { - name = binnames.substr(0,binnames.find_first_of(',')); - binnames = binnames.substr(binnames.find_first_of(',')+1, binnames.length()); - - //do work for that name - sequence = fasta->getSequence(name); - if (sequence != "not found") { - name = name + "|" + toString(i+1); - out << ">" << name << endl; - out << sequence << endl; - }else { - cout << name << " is missing from your fasta or name file. Please correct. " << endl; - remove(outputFileName.c_str()); - return 0; - } - - } - - //get last name - sequence = fasta->getSequence(binnames); - if (sequence != "not found") { - name = binnames + '|' + toString(i+1); - out << ">" << name << endl; - out << sequence << endl; - }else { - cout << binnames << " is missing from your fasta or name file. Please correct. " << endl; - remove(outputFileName.c_str()); - return 0; - } - - } - out.close(); + delete list; + list = input->getListVector(lastLabel); + + error = process(list); + if (error == 1) { return 0; } + + processedLabels.insert(list->getLabel()); + userLabels.erase(list->getLabel()); + + //restore real lastlabel to save below + list->setLabel(saveLabel); } + lastLabel = list->getLabel(); + delete list; list = input->getListVector(); - count++; + } + + + //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); + if (processedLabels.count(lastLabel) != 1) { + mothurOut(". I will use " + lastLabel + "."); mothurOutEndLine(); + needToRun = true; + }else { + mothurOut(". Please refer to " + lastLabel + "."); mothurOutEndLine(); + } + } + + //run last label if you need to + if (needToRun == true) { + if (list != NULL) { delete list; } + list = input->getListVector(lastLabel); + + error = process(list); + if (error == 1) { return 0; } + + delete list; } return 0; } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the BinSeqCommand class Function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + errorOut(e, "BinSeqCommand", "execute"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the BinSeqCommand class function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } } //********************************************************************************************************************** @@ -156,15 +289,93 @@ void BinSeqCommand::readNamesFile() { } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the BinSeqCommand class Function readNamesFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + errorOut(e, "BinSeqCommand", "readNamesFile"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the BinSeqCommand class function readNamesFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } } //********************************************************************************************************************** +//return 1 if error, 0 otherwise +int BinSeqCommand::process(ListVector* list) { + try { + string binnames, name, sequence; + + string outputFileName = outputDir + getRootName(getSimpleName(globaldata->getListFile())) + list->getLabel() + ".fasta"; + openOutputFile(outputFileName, out); + + mothurOut(list->getLabel()); mothurOutEndLine(); + + //for each bin in the list vector + for (int i = 0; i < list->size(); i++) { + binnames = list->get(i); + while (binnames.find_first_of(',') != -1) { + name = binnames.substr(0,binnames.find_first_of(',')); + binnames = binnames.substr(binnames.find_first_of(',')+1, binnames.length()); + + //do work for that name + sequence = fasta->getSequence(name); + if (sequence != "not found") { + //if you don't have groups + if (groupfile == "") { + name = name + "|" + 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()); + return 1; + }else{ + name = name + "|" + group + "|" + 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()); + return 1; + } + + } + + //get last name + sequence = fasta->getSequence(binnames); + if (sequence != "not found") { + //if you don't have groups + if (groupfile == "") { + binnames = binnames + "|" + 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()); + return 1; + }else{ + binnames = binnames + "|" + group + "|" + 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()); + return 1; + } + } + + out.close(); + return 0; + + } + catch(exception& e) { + errorOut(e, "BinSeqCommand", "process"); + exit(1); + } +} +//**********************************************************************************************************************