X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=binsequencecommand.cpp;h=033cd52e9e323e1707f603f8c20aaf22f50d4ecc;hb=b447f829850ae054e42560c7c3ed71b14f3f40bb;hp=1627b42d7bec5090a708c77d7491b93fa3bc7cdd;hpb=02909d6cae9963ba00dc746969a370fa8ca934fc;p=mothur.git diff --git a/binsequencecommand.cpp b/binsequencecommand.cpp index 1627b42..033cd52 100644 --- a/binsequencecommand.cpp +++ b/binsequencecommand.cpp @@ -10,12 +10,11 @@ #include "binsequencecommand.h" //********************************************************************************************************************** -BinSeqCommand::BinSeqCommand(string option){ +BinSeqCommand::BinSeqCommand(string option) { try { globaldata = GlobalData::getInstance(); abort = false; allLines = 1; - lines.clear(); labels.clear(); //allow user to run help @@ -23,36 +22,72 @@ BinSeqCommand::BinSeqCommand(string option){ else { //valid paramters for this command - string AlignArray[] = {"fasta","line","label","name", "group"}; + 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 (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; } } + //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() == "") { cout << "You must read a listfile before running the bin.seqs command." << endl; abort = true; } + 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 = 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") { cout << "fasta is a required parameter for the bin.seqs command." << endl; abort = 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... - line = validParameter.validFile(parameters, "line", false); - if (line == "not found") { line = ""; } - else { - if(line != "all") { splitAtDash(line, lines); allLines = 0; } - else { allLines = 1; } - } label = validParameter.validFile(parameters, "label", false); if (label == "not found") { label = ""; } @@ -61,13 +96,10 @@ BinSeqCommand::BinSeqCommand(string option){ else { allLines = 1; } } - //make sure user did not use both the line and label parameters - if ((line != "") && (label != "")) { cout << "You cannot use both the line and label parameters at the same time. " << endl; abort = true; } - //if the user has not specified any line or labels use the ones from read.otu - else if ((line == "") && (label == "")) { + //if the user has not specified any labels use the ones from read.otu + if (label == "") { allLines = globaldata->allLines; labels = globaldata->labels; - lines = globaldata->lines; } namesfile = validParameter.validFile(parameters, "name", true); @@ -79,51 +111,43 @@ BinSeqCommand::BinSeqCommand(string option){ else if (groupfile == "not found") { groupfile = ""; } if (abort == false) { - openInputFile(fastafile, in); +// openInputFile(fastafile, in); fasta = new FastaMap(); if (groupfile != "") { groupMap = new GroupMap(groupfile); - groupMap->readMap(); + + 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"; - exit(1); - } } //********************************************************************************************************************** void BinSeqCommand::help(){ try { - cout << "The bin.seqs command can only be executed after a successful read.otu command of a listfile." << "\n"; - cout << "The bin.seqs command parameters are fasta, name, line, label and group. The fasta parameter is required, and you may not use line and label at the same time." << "\n"; - cout << "The line and label allow you to select what distance levels you would like a output files created for, and are separated by dashes." << "\n"; - cout << "The bin.seqs command should be in the following format: bin.seqs(fasta=yourFastaFile, name=yourNamesFile, group=yourGroupFile, line=yourLines, label=yourLabels)." << "\n"; - cout << "Example bin.seqs(fasta=amazon.fasta, group=amazon.groups, line=1-3-5, name=amazon.names)." << "\n"; - cout << "The default value for line and label are all lines in your inputfile." << "\n"; - cout << "The bin.seqs command outputs a .fasta file for each distance you specify appending the OTU number to each name." << "\n"; - cout << "If you provide a groupfile, then it also appends the sequences group to the name." << "\n"; - cout << "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFastaFile)." << "\n" << "\n"; + 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) { - cout << "Standard Error: " << e.what() << " has occurred in the BinSeqCommand class Function help. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "BinSeqCommand", "help"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the BinSeqCommand class function help. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } } - - //********************************************************************************************************************** BinSeqCommand::~BinSeqCommand(){ @@ -143,13 +167,11 @@ int BinSeqCommand::execute(){ try { if (abort == true) { return 0; } - int count = 1; int error = 0; //read fastafile - fasta->readFastaFile(in); + fasta->readFastaFile(fastafile); - in.close(); //set format to list so input can get listvector // globaldata->setFormat("list"); @@ -159,80 +181,97 @@ int BinSeqCommand::execute(){ readNamesFile(); } + //read list file read = new ReadOTUFile(globaldata->getListFile()); read->read(&*globaldata); 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 = labels; - set userLines = lines; - while((list != NULL) && ((allLines == 1) || (userLabels.size() != 0) || (userLines.size() != 0))) { + while((list != NULL) && ((allLines == 1) || (userLabels.size() != 0))) { - if(allLines == 1 || lines.count(count) == 1 || labels.count(list->getLabel()) == 1){ + if(m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } + + 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()); - userLines.erase(count); } - if ((anyLabelsToProcess(list->getLabel(), userLabels, "") == true) && (processedLabels.count(lastList->getLabel()) != 1)) { + if ((anyLabelsToProcess(list->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) { + string saveLabel = list->getLabel(); + + delete list; + list = input->getListVector(lastLabel); - error = process(lastList, 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(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); - } } //********************************************************************************************************************** @@ -264,27 +303,29 @@ 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"; + 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"; + + string outputFileName = outputDir + getRootName(getSimpleName(globaldata->getListFile())) + list->getLabel() + ".fasta"; openOutputFile(outputFileName, out); + + //save to output list of output file names + outputNames.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(',')); @@ -301,8 +342,7 @@ 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); @@ -311,8 +351,7 @@ 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; } @@ -329,8 +368,7 @@ 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); @@ -339,8 +377,7 @@ 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; } } @@ -350,13 +387,9 @@ 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); - } } //**********************************************************************************************************************