X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=phylotypecommand.cpp;h=b21865abb54472b29473a76e2a9898939f7904c5;hp=c4f367a06d3e810afd954800ac637f29dc1818a1;hb=cf9987b67aa49777a4c91c2d21f96e58bf17aa82;hpb=260ae19c36cb11a53ddc5a75b5e507f8dd8b31d6 diff --git a/phylotypecommand.cpp b/phylotypecommand.cpp index c4f367a..b21865a 100644 --- a/phylotypecommand.cpp +++ b/phylotypecommand.cpp @@ -13,19 +13,90 @@ #include "rabundvector.hpp" #include "sabundvector.hpp" +//********************************************************************************************************************** +vector PhylotypeCommand::setParameters(){ + try { + CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "none", "none", "none","list-rabund-sabund",false,true,true); parameters.push_back(ptaxonomy); + CommandParameter pname("name", "InputTypes", "", "", "NameCount", "none", "ColumnName","rabund-sabund",false,false,true); parameters.push_back(pname); + CommandParameter pcount("count", "InputTypes", "", "", "NameCount", "none", "none","",false,false,true); parameters.push_back(pcount); + CommandParameter pcutoff("cutoff", "Number", "", "-1", "", "", "","",false,false,true); parameters.push_back(pcutoff); + 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, "PhylotypeCommand", "setParameters"); + exit(1); + } +} +//********************************************************************************************************************** +string PhylotypeCommand::getHelpString(){ + try { + string helpString = ""; + helpString += "The phylotype command reads a taxonomy file and outputs a .list, .rabund and .sabund file. \n"; + helpString += "The phylotype command parameter options are taxonomy, name, count, cutoff and label. The taxonomy parameter is required.\n"; + helpString += "The cutoff parameter allows you to specify the level you want to stop at. The default is the highest level in your taxonomy file. \n"; + helpString += "For example: taxonomy = Bacteria;Bacteroidetes-Chlorobi;Bacteroidetes; - cutoff=2, would truncate the taxonomy to Bacteria;Bacteroidetes-Chlorobi; \n"; + helpString += "For the cutoff parameter levels count up from the root of the phylotree. This enables you to look at the grouping down to a specific resolution, say the genus level.\n"; + helpString += "The label parameter allows you to specify which level you would like, and are separated by dashes. The default all levels in your taxonomy file. \n"; + helpString += "For the label parameter, levels count down from the root to keep the output similiar to mothur's other commands which report information from finer resolution to coarser resolutions.\n"; + helpString += "The phylotype command should be in the following format: \n"; + helpString += "phylotype(taxonomy=yourTaxonomyFile, cutoff=yourCutoff, label=yourLabels) \n"; + helpString += "Eaxample: phylotype(taxonomy=amazon.taxonomy, cutoff=5, label=1-3-5).\n"; + return helpString; + } + catch(exception& e) { + m->errorOut(e, "PhylotypeCommand", "getHelpString"); + exit(1); + } +} +//********************************************************************************************************************** +string PhylotypeCommand::getOutputPattern(string type) { + try { + string pattern = ""; + + if (type == "list") { pattern = "[filename],[clustertag],list-[filename],[clustertag],[tag2],list"; } + else if (type == "rabund") { pattern = "[filename],[clustertag],rabund"; } + else if (type == "sabund") { pattern = "[filename],[clustertag],sabund"; } + else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; } + + return pattern; + } + catch(exception& e) { + m->errorOut(e, "PhylotypeCommand", "getOutputPattern"); + exit(1); + } +} +//********************************************************************************************************************** +PhylotypeCommand::PhylotypeCommand(){ + try { + abort = true; calledHelp = true; + setParameters(); + vector tempOutNames; + outputTypes["list"] = tempOutNames; + outputTypes["sabund"] = tempOutNames; + outputTypes["rabund"] = tempOutNames; + } + catch(exception& e) { + m->errorOut(e, "PhylotypeCommand", "PhylotypeCommand"); + exit(1); + } +} /**********************************************************************************************************************/ PhylotypeCommand::PhylotypeCommand(string option) { try { - abort = false; + abort = false; calledHelp = false; //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[] = {"taxonomy","cutoff","label","name","outputdir","inputdir"}; - vector myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string))); + vector myArray = setParameters(); OptionParser parser(option); map parameters = parser.getParameters(); @@ -38,6 +109,12 @@ PhylotypeCommand::PhylotypeCommand(string option) { if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; } } + //initialize outputTypes + vector tempOutNames; + outputTypes["list"] = tempOutNames; + outputTypes["sabund"] = tempOutNames; + outputTypes["rabund"] = 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 = ""; } @@ -58,19 +135,36 @@ PhylotypeCommand::PhylotypeCommand(string option) { //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("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; } + } } taxonomyFileName = validParameter.validFile(parameters, "taxonomy", true); if (taxonomyFileName == "not found") { - m->mothurOut("taxonomy is a required parameter for the phylotype command."); - m->mothurOutEndLine(); - abort = true; - }else if (taxonomyFileName == "not open") { abort = true; } + taxonomyFileName = m->getTaxonomyFile(); + if (taxonomyFileName != "") { m->mothurOut("Using " + taxonomyFileName + " as input file for the taxonomy parameter."); m->mothurOutEndLine(); } + else { + m->mothurOut("No valid current files. taxonomy is a required parameter."); m->mothurOutEndLine(); + abort = true; + } + }else if (taxonomyFileName == "not open") { taxonomyFileName = ""; abort = true; } + else { m->setTaxonomyFile(taxonomyFileName); } namefile = validParameter.validFile(parameters, "name", true); - if (namefile == "not open") { abort = true; } + if (namefile == "not open") { namefile = ""; abort = true; } else if (namefile == "not found") { namefile = ""; } - else { readNamesFile(); } + else { readNamesFile(); m->setNameFile(namefile); } + + countfile = validParameter.validFile(parameters, "count", true); + if (countfile == "not open") { abort = true; countfile = ""; } + else if (countfile == "not found") { countfile = ""; } + else { m->setCountTableFile(countfile); } //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"){ @@ -78,9 +172,11 @@ PhylotypeCommand::PhylotypeCommand(string option) { outputDir += m->hasPath(taxonomyFileName); //if user entered a file with a path then preserve it } + if ((countfile != "") && (namefile != "")) { m->mothurOut("You must enter ONLY ONE of the following: count or name."); m->mothurOutEndLine(); abort = true; } + string temp = validParameter.validFile(parameters, "cutoff", false); if (temp == "not found") { temp = "-1"; } - convert(temp, cutoff); + m->mothurConvert(temp, cutoff); label = validParameter.validFile(parameters, "label", false); if (label == "not found") { label = ""; allLines = 1; } @@ -89,6 +185,12 @@ PhylotypeCommand::PhylotypeCommand(string option) { else { allLines = 1; } } + if (countfile == "") { + if (namefile == "") { + vector files; files.push_back(taxonomyFileName); + parser.getNameFile(files); + } + } } } catch(exception& e) { @@ -98,36 +200,10 @@ PhylotypeCommand::PhylotypeCommand(string option) { } /**********************************************************************************************************************/ -void PhylotypeCommand::help(){ - try { - m->mothurOut("The phylotype command reads a taxonomy file and outputs a .list, .rabund and .sabund file. \n"); - m->mothurOut("The phylotype command parameter options are taxonomy, cutoff and label. The taxonomy parameter is required.\n"); - m->mothurOut("The cutoff parameter allows you to specify the level you want to stop at. The default is the highest level in your taxonomy file. \n"); - m->mothurOut("For example: taxonomy = Bacteria;Bacteroidetes-Chlorobi;Bacteroidetes; - cutoff=2, would truncate the taxonomy to Bacteria;Bacteroidetes-Chlorobi; \n"); - m->mothurOut("For the cutoff parameter levels count up from the root of the phylotree. This enables you to look at the grouping down to a specific resolution, say the genus level.\n"); - m->mothurOut("The label parameter allows you to specify which level you would like, and are separated by dashes. The default all levels in your taxonomy file. \n"); - m->mothurOut("For the label parameter, levels count down from the root to keep the output similiar to mothur's other commands which report information from finer resolution to coarser resolutions.\n"); - m->mothurOut("The phylotype command should be in the following format: \n"); - m->mothurOut("phylotype(taxonomy=yourTaxonomyFile, cutoff=yourCutoff, label=yourLabels) \n"); - m->mothurOut("Eaxample: phylotype(taxonomy=amazon.taxonomy, cutoff=5, label=1-3-5).\n\n"); - } - catch(exception& e) { - m->errorOut(e, "PhylotypeCommand", "help"); - exit(1); - } -} -/**********************************************************************************************************************/ - -PhylotypeCommand::~PhylotypeCommand(){} - -/**********************************************************************************************************************/ - int PhylotypeCommand::execute(){ try { - if (abort == true) { return 0; } - - vector outputNames; + if (abort == true) { if (calledHelp) { return 0; } return 2; } //reads in taxonomy file and makes all the taxonomies the same length //by appending the last taxon to a given taxonomy as many times as needed to @@ -152,22 +228,27 @@ int PhylotypeCommand::execute(){ if (m->control_pressed) { delete tree; return 0; } - string fileroot = outputDir + m->getRootName(m->getSimpleName(taxonomyFileName)); - - ofstream outList; - string outputListFile = fileroot + "tx.list"; - m->openOutputFile(outputListFile, outList); - ofstream outSabund; - string outputSabundFile = fileroot + "tx.sabund"; - m->openOutputFile(outputSabundFile, outSabund); - ofstream outRabund; - string outputRabundFile = fileroot + "tx.rabund"; - m->openOutputFile(outputRabundFile, outRabund); - - outputNames.push_back(outputListFile); - outputNames.push_back(outputSabundFile); - outputNames.push_back(outputRabundFile); - + ofstream outList, outRabund, outSabund; + map variables; + string fileroot = outputDir + m->getRootName(m->getSimpleName(taxonomyFileName)); + variables["[filename]"] = fileroot; + variables["[clustertag]"] = "tx"; + string sabundFileName = getOutputFileName("sabund", variables); + string rabundFileName = getOutputFileName("rabund", variables); + if (countfile != "") { variables["[tag2]"] = "unique_list"; } + string listFileName = getOutputFileName("list", variables); + + if (countfile == "") { + m->openOutputFile(sabundFileName, outSabund); + m->openOutputFile(rabundFileName, outRabund); + outputNames.push_back(sabundFileName); outputTypes["sabund"].push_back(sabundFileName); + outputNames.push_back(rabundFileName); outputTypes["rabund"].push_back(rabundFileName); + + } + m->openOutputFile(listFileName, outList); + outputNames.push_back(listFileName); outputTypes["list"].push_back(listFileName); + + int count = 1; //start at leaves of tree and work towards root, processing the labels the user wants while((!done) && ((allLines == 1) || (labels.size() != 0))) { @@ -176,8 +257,8 @@ int PhylotypeCommand::execute(){ count++; if (m->control_pressed) { - outRabund.close(); outSabund.close(); outList.close(); - for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } + if (countfile == "") { outRabund.close(); outSabund.close(); } outList.close(); + for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } delete tree; return 0; } @@ -189,6 +270,7 @@ int PhylotypeCommand::execute(){ ListVector list; list.setLabel(level); + //go through nodes and build listvector for (itCurrent = currentNodes.begin(); itCurrent != currentNodes.end(); itCurrent++) { @@ -201,27 +283,35 @@ int PhylotypeCommand::execute(){ //make the names compatable with listvector string name = ""; for (int i = 0; i < names.size(); i++) { - if (namefile != "") { - map::iterator itNames = namemap.find(names[i]); //make sure this name is in namefile - - if (itNames != namemap.end()) { name += namemap[names[i]] + ","; } //you found it in namefile - else { m->mothurOut(names[i] + " is not in your namefile, please correct."); m->mothurOutEndLine(); exit(1); } - - }else{ name += names[i] + ","; } + + if (names[i] != "unknown") { + if (namefile != "") { + map::iterator itNames = namemap.find(names[i]); //make sure this name is in namefile + + if (itNames != namemap.end()) { name += namemap[names[i]] + ","; } //you found it in namefile + else { m->mothurOut("[ERROR]: " + names[i] + " is not in your namefile, please correct."); m->mothurOutEndLine(); m->control_pressed = true; } + + }else{ name += names[i] + ","; } + } } + + if (m->control_pressed) { break; } + name = name.substr(0, name.length()-1); //rip off extra ',' - //add bin to list vector - list.push_back(name); + if (name != "") { list.push_back(name); } //caused by unknown } //print listvector - list.print(outList); - //print rabund - list.getRAbundVector().print(outRabund); - //print sabund - list.getSAbundVector().print(outSabund); - + if (!m->printedListHeaders) { list.printHeaders(outList); } + list.print(outList); + + if (countfile == "") { + //print rabund + list.getRAbundVector().print(outRabund); + //print sabund + list.getSAbundVector().print(outSabund); + } labels.erase(level); }else { @@ -242,16 +332,37 @@ int PhylotypeCommand::execute(){ } outList.close(); - outSabund.close(); - outRabund.close(); + if (countfile == "") { + outSabund.close(); + outRabund.close(); + } delete tree; if (m->control_pressed) { - for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } + for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } + //set list file as new current listfile + string current = ""; + itTypes = outputTypes.find("list"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setListFile(current); } + } + + //set rabund file as new current rabundfile + itTypes = outputTypes.find("rabund"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setRabundFile(current); } + } + + //set sabund file as new current sabundfile + itTypes = outputTypes.find("sabund"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setSabundFile(current); } + } + m->mothurOutEndLine(); m->mothurOut("Output File Names: "); m->mothurOutEndLine(); for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); }