X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=binsequencecommand.cpp;h=7798a4d74f749eed04d4554c796776a58697b98b;hp=3f9378fbdb4650078cf27091326c0dc5e87c993a;hb=1a20e24ee786195ab0e1cccd4f5aede7a88f3f4e;hpb=1d898dc6edaf9e9f287fab53bf1f21fb29757a17 diff --git a/binsequencecommand.cpp b/binsequencecommand.cpp index 3f9378f..7798a4d 100644 --- a/binsequencecommand.cpp +++ b/binsequencecommand.cpp @@ -13,13 +13,14 @@ //********************************************************************************************************************** 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); + CommandParameter plist("list", "InputTypes", "", "", "none", "none", "none","",false,true,true); parameters.push_back(plist); + CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "none","fasta",false,true,true); parameters.push_back(pfasta); + CommandParameter pname("name", "InputTypes", "", "", "NameCount", "none", "none","",false,false,true); parameters.push_back(pname); + CommandParameter pcount("count", "InputTypes", "", "", "NameCount-CountGroup", "none", "none","",false,false,true); parameters.push_back(pcount); + CommandParameter pgroup("group", "InputTypes", "", "", "CountGroup", "none", "none","",false,false,true); 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); } @@ -34,7 +35,7 @@ vector BinSeqCommand::setParameters(){ 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 bin.seqs command parameters are list, fasta, name, count, 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"; @@ -50,6 +51,21 @@ string BinSeqCommand::getHelpString(){ } } //********************************************************************************************************************** +string BinSeqCommand::getOutputPattern(string type) { + try { + string pattern = ""; + + if (type == "fasta") { pattern = "[filename],[distance],fasta"; } //makes file like: amazon.0.03.fasta + else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; } + + return pattern; + } + catch(exception& e) { + m->errorOut(e, "BinSeqCommand", "getOutputPattern"); + exit(1); + } +} +//********************************************************************************************************************** BinSeqCommand::BinSeqCommand(){ try { abort = true; calledHelp = true; @@ -71,6 +87,7 @@ BinSeqCommand::BinSeqCommand(string option) { //allow user to run help if(option == "help") { help(); abort = true; calledHelp = true; } + else if(option == "citation") { citation(); abort = true; calledHelp = true;} else { vector myArray = setParameters(); @@ -126,6 +143,14 @@ BinSeqCommand::BinSeqCommand(string option) { //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["group"] = inputDir + it->second; } } + + it = parameters.find("count"); + //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["count"] = inputDir + it->second; } + } } @@ -137,6 +162,7 @@ BinSeqCommand::BinSeqCommand(string option) { 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") { @@ -145,6 +171,7 @@ BinSeqCommand::BinSeqCommand(string option) { 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"){ @@ -164,12 +191,34 @@ BinSeqCommand::BinSeqCommand(string option) { } 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); } + + countfile = validParameter.validFile(parameters, "count", true); + if (countfile == "not open") { countfile = ""; abort = true; } + else if (countfile == "not found") { countfile = ""; } + else { m->setCountTableFile(countfile); } + + if ((namesfile != "") && (countfile != "")) { + m->mothurOut("[ERROR]: you may only use one of the following: name or count."); m->mothurOutEndLine(); abort = true; + } + + if ((groupfile != "") && (countfile != "")) { + m->mothurOut("[ERROR]: you may only use one of the following: group or count."); m->mothurOutEndLine(); abort=true; + } + + if (countfile == "") { + if (namesfile == ""){ + vector files; files.push_back(fastafile); + parser.getNameFile(files); + } + } } } @@ -199,9 +248,8 @@ int BinSeqCommand::execute(){ fasta->readFastaFile(fastafile); //if user gave a namesfile then use it - if (namesfile != "") { - readNamesFile(); - } + if (namesfile != "") { readNamesFile(); } + if (countfile != "") { ct.readTable(countfile); } input = new InputData(listfile, "list"); list = input->getListVector(); @@ -216,12 +264,12 @@ int BinSeqCommand::execute(){ 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()); } delete input; delete fasta; if (groupfile != "") { delete groupMap; } return 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) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } delete input; delete fasta; if (groupfile != "") { delete groupMap; } 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()); @@ -234,7 +282,7 @@ int BinSeqCommand::execute(){ list = input->getListVector(lastLabel); error = process(list); - if (error == 1) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } delete input; delete fasta; if (groupfile != "") { delete groupMap; } 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()); @@ -249,7 +297,7 @@ int BinSeqCommand::execute(){ list = input->getListVector(); } - if(m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } delete input; delete fasta; if (groupfile != "") { delete groupMap; } return 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; } //output error messages about any remaining user labels set::iterator it; @@ -270,7 +318,7 @@ int BinSeqCommand::execute(){ list = input->getListVector(lastLabel); error = process(list); - if (error == 1) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } delete input; delete fasta; if (groupfile != "") { delete groupMap; } 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; } @@ -279,11 +327,14 @@ int BinSeqCommand::execute(){ delete fasta; if (groupfile != "") { delete groupMap; } - if(m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } - - 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; } + + //set align file as new current fastafile + string currentFasta = ""; + itTypes = outputTypes.find("fasta"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { currentFasta = (itTypes->second)[0]; m->setFastaFile(currentFasta); } + } m->mothurOutEndLine(); m->mothurOut("Output File Names: "); m->mothurOutEndLine(); @@ -336,79 +387,75 @@ void BinSeqCommand::readNamesFile() { //return 1 if error, 0 otherwise int BinSeqCommand::process(ListVector* list) { try { - string binnames, name, sequence; - - 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); - - 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(',')); - 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 + "\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") { - m->mothurOut(name + " is missing from your group file. Please correct. "); m->mothurOutEndLine(); - return 1; - }else{ - name = name + "\t" + group + "\t" + toString(i+1); - out << ">" << name << endl; - out << sequence << endl; - } - } - }else { - m->mothurOut(name + " is missing from your fasta or name file. Please correct. "); m->mothurOutEndLine(); - return 1; - } - - } - - //get last name - sequence = fasta->getSequence(binnames); - if (sequence != "not found") { - //if you don't have groups - if (groupfile == "") { - 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") { - m->mothurOut(binnames + " is missing from your group file. Please correct. "); m->mothurOutEndLine(); - return 1; - }else{ - binnames = binnames + "\t" + group + "\t" + toString(i+1); - out << ">" << binnames << endl; - out << sequence << endl; - } - } - }else { - m->mothurOut(binnames + " is missing from your fasta or name file. Please correct. "); m->mothurOutEndLine(); - return 1; - } - } - - out.close(); - return 0; + map variables; + variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(listfile)); + variables["[distance]"] = list->getLabel(); + string outputFileName = getOutputFileName("fasta", variables); + + m->openOutputFile(outputFileName, out); + outputNames.push_back(outputFileName); outputTypes["fasta"].push_back(outputFileName); + + 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; } + + string binnames = list->get(i); + vector names; + m->splitAtComma(binnames, names); + for (int j = 0; j < names.size(); j++) { + string name = names[j]; + + //do work for that name + string sequence = fasta->getSequence(name); + + if (countfile != "") { + if (sequence != "not found") { + if (ct.hasGroupInfo()) { + vector groups = ct.getGroups(name); + string groupInfo = ""; + for (int k = 0; k < groups.size()-1; k++) { + groupInfo += groups[k] + "-"; + } + if (groups.size() != 0) { groupInfo += groups[groups.size()-1]; } + else { groupInfo = "not found"; } + name = name + "\t" + groupInfo + "\t" + toString(i+1)+ "\tNumRep=" + toString(ct.getNumSeqs(name)); + out << ">" << name << endl; + out << sequence << endl; + }else { + name = name + "\t" + toString(i+1) + "\tNumRep=" + toString(ct.getNumSeqs(name)); + out << ">" << name << endl; + out << sequence << endl; + } + + }else { m->mothurOut(name + " is missing from your fasta. Does your list file contain all sequence names or just the uniques?"); m->mothurOutEndLine(); return 1; } + }else { + if (sequence != "not found") { + //if you don't have groups + if (groupfile == "") { + 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") { + m->mothurOut(name + " is missing from your group file. Please correct. "); m->mothurOutEndLine(); + return 1; + }else{ + name = name + "\t" + group + "\t" + toString(i+1); + out << ">" << name << endl; + out << sequence << endl; + } + } + }else { m->mothurOut(name + " is missing from your fasta or name file. Please correct. "); m->mothurOutEndLine(); return 1; } + } + } + } + + out.close(); + return 0; } catch(exception& e) {