X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=binsequencecommand.cpp;h=bf14d6b07b3b6ae64c20d3072abb3c3603a9e42c;hb=1e0359c041eedc99670c93d824a2cf7fa72577cc;hp=c21757850b858d4a53173619da911ffcab5d24a3;hpb=a8f5a612bba54ceb74e17efc027d3a7f5aa93c9a;p=mothur.git diff --git a/binsequencecommand.cpp b/binsequencecommand.cpp index c217578..bf14d6b 100644 --- a/binsequencecommand.cpp +++ b/binsequencecommand.cpp @@ -10,41 +10,207 @@ #include "binsequencecommand.h" //********************************************************************************************************************** -BinSeqCommand::BinSeqCommand(){ +vector BinSeqCommand::getValidParameters(){ + try { + string AlignArray[] = {"fasta","label","name", "group","outputdir","inputdir"}; + vector myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string))); + return myArray; + } + catch(exception& e) { + m->errorOut(e, "BinSeqCommand", "getValidParameters"); + exit(1); + } +} +//********************************************************************************************************************** +vector BinSeqCommand::getRequiredParameters(){ + try { + string AlignArray[] = {"fasta"}; + vector myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string))); + return myArray; + } + catch(exception& e) { + m->errorOut(e, "BinSeqCommand", "getRequiredParameters"); + exit(1); + } +} +//********************************************************************************************************************** +vector BinSeqCommand::getRequiredFiles(){ + try { + string AlignArray[] = {"list"}; + vector myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string))); + return myArray; + } + catch(exception& e) { + m->errorOut(e, "BinSeqCommand", "getRequiredFiles"); + exit(1); + } +} +//********************************************************************************************************************** +BinSeqCommand::BinSeqCommand(){ + try { + abort = true; + //initialize outputTypes + vector tempOutNames; + outputTypes["fasta"] = tempOutNames; + } + catch(exception& e) { + m->errorOut(e, "BinSeqCommand", "BinSeqCommand"); + exit(1); + } +} +//********************************************************************************************************************** +BinSeqCommand::BinSeqCommand(string option) { try { globaldata = GlobalData::getInstance(); - fastafile = globaldata->getFastaFile(); - namesfile = globaldata->getNameFile(); - groupfile = globaldata->getGroupFile(); - openInputFile(fastafile, in); + abort = false; + allLines = 1; + labels.clear(); - if (groupfile != "") { - //read in group map info. - groupMap = new GroupMap(groupfile); - groupMap->readMap(); - } + //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; - fasta = new FastaMap(); + //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; } + } + + //initialize outputTypes + vector tempOutNames; + outputTypes["fasta"] = tempOutNames; + + //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(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() == "") { + m->mothurOut("You must read a listfile before running the bin.seqs command."); + m->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 = 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("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") { m->mothurOut("fasta is a required parameter for the bin.seqs command."); m->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") { 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; } + 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) { +// m->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"; + m->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 { + m->mothurOut("The bin.seqs command can only be executed after a successful read.otu command of a listfile.\n"); + m->mothurOut("The bin.seqs command parameters are fasta, name, label and group. The fasta parameter is required.\n"); + m->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"); + m->mothurOut("The bin.seqs command should be in the following format: bin.seqs(fasta=yourFastaFile, name=yourNamesFile, group=yourGroupFile, label=yourLabels).\n"); + m->mothurOut("Example bin.seqs(fasta=amazon.fasta, group=amazon.groups, name=amazon.names).\n"); + m->mothurOut("The default value for label is all lines in your inputfile.\n"); + m->mothurOut("The bin.seqs command outputs a .fasta file for each distance you specify appending the OTU number to each name.\n"); + m->mothurOut("If you provide a groupfile, then it also appends the sequences group to the name.\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, "BinSeqCommand", "help"); exit(1); - } + } } //********************************************************************************************************************** BinSeqCommand::~BinSeqCommand(){ - delete input; - delete read; - delete fasta; - delete list; - if (groupfile != "") { - delete groupMap; + //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; } } } @@ -52,14 +218,16 @@ BinSeqCommand::~BinSeqCommand(){ int BinSeqCommand::execute(){ try { - int count = 1; + 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 != "") { @@ -72,80 +240,97 @@ int BinSeqCommand::execute(){ input = globaldata->ginput; list = globaldata->gListVector; - ListVector* lastList = list; + string lastLabel = list->getLabel(); + + if (m->control_pressed) { 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 = globaldata->labels; + set userLabels = labels; - while((list != NULL) && ((globaldata->allLines == 1) || (userLabels.size() != 0))) { + while((list != NULL) && ((allLines == 1) || (userLabels.size() != 0))) { + + if(m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } - if(globaldata->allLines == 1 || globaldata->lines.count(count) == 1 || globaldata->labels.count(list->getLabel()) == 1){ + if(allLines == 1 || labels.count(list->getLabel()) == 1){ - error = process(list, count); - if (error == 1) { return 0; } + error = process(list); + if (error == 1) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } processedLabels.insert(list->getLabel()); userLabels.erase(list->getLabel()); - } - if ((anyLabelsToProcess(list->getLabel(), userLabels, "") == true) && (processedLabels.count(lastList->getLabel()) != 1)) { + if ((m->anyLabelsToProcess(list->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) { + string saveLabel = list->getLabel(); - error = process(lastList, count); - if (error == 1) { return 0; } + delete list; + list = input->getListVector(lastLabel); + + error = process(list); + if (error == 1) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } - processedLabels.insert(lastList->getLabel()); - userLabels.erase(lastList->getLabel()); + processedLabels.insert(list->getLabel()); + userLabels.erase(list->getLabel()); + //restore real lastlabel to save below + list->setLabel(saveLabel); } - if (count != 1) { delete lastList; } - lastList = list; - + lastLabel = list->getLabel(); + + delete list; list = input->getListVector(); - count++; } - + if(m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } + //output error messages about any remaining user labels set::iterator it; bool needToRun = false; for (it = userLabels.begin(); it != userLabels.end(); it++) { - cout << "Your file does not include the label "<< *it; - if (processedLabels.count(lastList->getLabel()) != 1) { - cout << ". I will use " << lastList->getLabel() << "." << endl; + m->mothurOut("Your file does not include the label " + *it); + if (processedLabels.count(lastLabel) != 1) { + m->mothurOut(". I will use " + lastLabel + "."); m->mothurOutEndLine(); needToRun = true; }else { - cout << ". Please refer to " << lastList->getLabel() << "." << endl; + m->mothurOut(". Please refer to " + lastLabel + "."); m->mothurOutEndLine(); } } - //run last line if you need to + //run last label if you need to if (needToRun == true) { - error = process(lastList, count); - if (error == 1) { return 0; } + if (list != NULL) { delete list; } + list = input->getListVector(lastLabel); + + error = process(list); + if (error == 1) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } + + delete list; } - delete lastList; + if(m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } 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) { - cout << "Standard Error: " << e.what() << " has occurred in the BinSeqCommand class Function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->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); - } } //********************************************************************************************************************** void BinSeqCommand::readNamesFile() { try { vector dupNames; - openInputFile(namesfile, inNames); + m->openInputFile(namesfile, inNames); string name, names, sequence; @@ -156,7 +341,7 @@ 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); @@ -164,33 +349,35 @@ void BinSeqCommand::readNamesFile() { fasta->push_back(dupNames[i], sequence); } - gobble(inNames); + m->gobble(inNames); } inNames.close(); } 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"; + m->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, int count) { +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(globaldata->getListFile())) + list->getLabel() + ".fasta"; + m->openOutputFile(outputFileName, out); + + //save to output list of output file names + outputNames.push_back(outputFileName); outputTypes["fasta"].push_back(outputFileName); - cout << list->getLabel() << '\t' << count << endl; + 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(',')); @@ -207,8 +394,7 @@ int BinSeqCommand::process(ListVector* list, int count) { }else {//if you do have groups string group = groupMap->getGroup(name); if (group == "not found") { - cout << name << " is missing from your group file. Please correct. " << endl; - 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); @@ -217,8 +403,7 @@ int BinSeqCommand::process(ListVector* list, int count) { } } }else { - cout << name << " is missing from your fasta or name file. Please correct. " << endl; - remove(outputFileName.c_str()); + m->mothurOut(name + " is missing from your fasta or name file. Please correct. "); m->mothurOutEndLine(); return 1; } @@ -235,8 +420,7 @@ int BinSeqCommand::process(ListVector* list, int count) { }else {//if you do have groups string group = groupMap->getGroup(binnames); if (group == "not found") { - cout << binnames << " is missing from your group file. Please correct. " << endl; - 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); @@ -245,8 +429,7 @@ int BinSeqCommand::process(ListVector* list, int count) { } } }else { - cout << binnames << " is missing from your fasta or name file. Please correct. " << endl; - remove(outputFileName.c_str()); + m->mothurOut(binnames + " is missing from your fasta or name file. Please correct. "); m->mothurOutEndLine(); return 1; } } @@ -256,13 +439,9 @@ int BinSeqCommand::process(ListVector* list, int count) { } 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"; + m->errorOut(e, "BinSeqCommand", "process"); 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); - } } //**********************************************************************************************************************