X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=collectcommand.cpp;h=89ab0a49a7592a86638d801aaaf0257f63a34379;hb=19fcbbdba99658f5eca244803280f9ee7f9f6607;hp=9ea55b2d6068dfda14450d82d247a428dcb9ca56;hpb=191ae1be0679d5cf4eda950b3b1bf26fb7dd503d;p=mothur.git diff --git a/collectcommand.cpp b/collectcommand.cpp index 9ea55b2..89ab0a4 100644 --- a/collectcommand.cpp +++ b/collectcommand.cpp @@ -34,46 +34,57 @@ #include "shen.h" #include "coverage.h" + //********************************************************************************************************************** -vector CollectCommand::getValidParameters(){ - try { - string AlignArray[] = {"freq","label","calc","abund","size","outputdir","inputdir"}; - vector myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string))); - return myArray; - } - catch(exception& e) { - m->errorOut(e, "CollectCommand", "getValidParameters"); - exit(1); - } -} -//********************************************************************************************************************** -vector CollectCommand::getRequiredParameters(){ +vector CollectCommand::setParameters(){ try { + CommandParameter plist("list", "InputTypes", "", "", "LRSS", "LRSS", "none",false,false); parameters.push_back(plist); + CommandParameter prabund("rabund", "InputTypes", "", "", "LRSS", "LRSS", "none",false,false); parameters.push_back(prabund); + CommandParameter psabund("sabund", "InputTypes", "", "", "LRSS", "LRSS", "none",false,false); parameters.push_back(psabund); + CommandParameter pshared("shared", "InputTypes", "", "", "LRSS", "LRSS", "none",false,false); parameters.push_back(pshared); + CommandParameter plabel("label", "String", "", "", "", "", "",false,false); parameters.push_back(plabel); + CommandParameter pfreq("freq", "Number", "", "100", "", "", "",false,false); parameters.push_back(pfreq); + CommandParameter pcalc("calc", "Multiple", "sobs-chao-nseqs-coverage-ace-jack-shannon-shannoneven-np_shannon-heip-smithwilson-simpson-simpsoneven-invsimpson-bootstrap-geometric-qstat-logseries-bergerparker-bstick-goodscoverage-efron-boneh-solow-shen", "sobs-chao-ace-jack-shannon-npshannon-simpson", "", "", "",true,false); parameters.push_back(pcalc); + CommandParameter pabund("abund", "Number", "", "10", "", "", "",false,false); parameters.push_back(pabund); + CommandParameter psize("size", "Number", "", "0", "", "", "",false,false); parameters.push_back(psize); + 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, "CollectCommand", "getRequiredParameters"); + m->errorOut(e, "CollectCommand", "setParameters"); exit(1); } } //********************************************************************************************************************** -vector CollectCommand::getRequiredFiles(){ +string CollectCommand::getHelpString(){ try { - string AlignArray[] = {"shared","list","rabund","sabund","or"}; - vector myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string))); - return myArray; + string helpString = ""; + ValidCalculators validCalculator; + helpString += "The collect.single command parameters are list, sabund, rabund, shared, label, freq, calc and abund. list, sabund, rabund or shared is required unless you have a valid current file. \n"; + helpString += "The collect.single command should be in the following format: \n"; + helpString += "The freq parameter is used indicate when to output your data, by default it is set to 100. But you can set it to a percentage of the number of sequence. For example freq=0.10, means 10%. \n"; + helpString += "collect.single(label=yourLabel, iters=yourIters, freq=yourFreq, calc=yourEstimators).\n"; + helpString += "Example collect(label=unique-.01-.03, iters=10000, freq=10, calc=sobs-chao-ace-jack).\n"; + helpString += "The default values for freq is 100, and calc are sobs-chao-ace-jack-shannon-npshannon-simpson.\n"; + helpString += validCalculator.printCalc("single"); + helpString += "The label parameter is used to analyze specific labels in your input.\n"; + helpString += "Note: No spaces between parameter labels (i.e. freq), '=' and parameters (i.e.yourFreq).\n"; + return helpString; } catch(exception& e) { - m->errorOut(e, "CollectCommand", "getRequiredFiles"); + m->errorOut(e, "CollectCommand", "getHelpString"); exit(1); } } //********************************************************************************************************************** CollectCommand::CollectCommand(){ try { - abort = true; - //initialize outputTypes + abort = true; calledHelp = true; + setParameters(); vector tempOutNames; outputTypes["sobs"] = tempOutNames; outputTypes["chao"] = tempOutNames; @@ -109,30 +120,27 @@ CollectCommand::CollectCommand(){ //********************************************************************************************************************** CollectCommand::CollectCommand(string option) { try { - globaldata = GlobalData::getInstance(); - abort = false; + abort = false; calledHelp = false; allLines = 1; - labels.clear(); - Estimators.clear(); //allow user to run help - if(option == "help") { validCalculator = new ValidCalculators(); help(); delete validCalculator; abort = true; } + if(option == "help") { help(); calledHelp = true; abort = true; } + else if(option == "citation") { citation(); abort = true; calledHelp = true;} else { - //valid paramters for this command - string Array[] = {"freq","label","calc","abund","size","outputdir","inputdir"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + vector myArray = setParameters(); OptionParser parser(option); map parameters = parser.getParameters(); + map::iterator it; ValidParameters validParameter; //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; } } - + //initialize outputTypes vector tempOutNames; outputTypes["sobs"] = tempOutNames; @@ -161,11 +169,92 @@ CollectCommand::CollectCommand(string option) { outputTypes["solow"] = tempOutNames; outputTypes["shen"] = 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 = ""; } + else { + string path; + it = parameters.find("shared"); + //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["shared"] = inputDir + it->second; } + } + + it = parameters.find("rabund"); + //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["rabund"] = inputDir + it->second; } + } + + it = parameters.find("sabund"); + //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["sabund"] = inputDir + it->second; } + } + + it = parameters.find("list"); + //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["list"] = inputDir + it->second; } + } + } + + //check for required parameters + listfile = validParameter.validFile(parameters, "list", true); + if (listfile == "not open") { listfile = ""; abort = true; } + else if (listfile == "not found") { listfile = ""; } + else { format = "list"; inputfile = listfile; m->setListFile(listfile); } + + sabundfile = validParameter.validFile(parameters, "sabund", true); + if (sabundfile == "not open") { sabundfile = ""; abort = true; } + else if (sabundfile == "not found") { sabundfile = ""; } + else { format = "sabund"; inputfile = sabundfile; m->setSabundFile(sabundfile); } + + rabundfile = validParameter.validFile(parameters, "rabund", true); + if (rabundfile == "not open") { rabundfile = ""; abort = true; } + else if (rabundfile == "not found") { rabundfile = ""; } + else { format = "rabund"; inputfile = rabundfile; m->setRabundFile(rabundfile); } + + sharedfile = validParameter.validFile(parameters, "shared", true); + if (sharedfile == "not open") { sharedfile = ""; abort = true; } + else if (sharedfile == "not found") { sharedfile = ""; } + else { format = "sharedfile"; inputfile = sharedfile; m->setSharedFile(sharedfile); } + + //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 = ""; } - //make sure the user has already run the read.otu command - if ((globaldata->getSharedFile() == "") && (globaldata->getListFile() == "") && (globaldata->getRabundFile() == "") && (globaldata->getSabundFile() == "")) { m->mothurOut("You must read a list, sabund, rabund or shared file before you can use the collect.single command."); m->mothurOutEndLine(); abort = true; } + if ((sharedfile == "") && (listfile == "") && (rabundfile == "") && (sabundfile == "")) { + //is there are current file available for any of these? + //give priority to shared, then list, then rabund, then sabund + //if there is a current shared file, use it + sharedfile = m->getSharedFile(); + if (sharedfile != "") { inputfile = sharedfile; format = "sharedfile"; m->mothurOut("Using " + sharedfile + " as input file for the shared parameter."); m->mothurOutEndLine(); } + else { + listfile = m->getListFile(); + if (listfile != "") { inputfile = listfile; format = "list"; m->mothurOut("Using " + listfile + " as input file for the list parameter."); m->mothurOutEndLine(); } + else { + rabundfile = m->getRabundFile(); + if (rabundfile != "") { inputfile = rabundfile; format = "rabund"; m->mothurOut("Using " + rabundfile + " as input file for the rabund parameter."); m->mothurOutEndLine(); } + else { + sabundfile = m->getSabundFile(); + if (sabundfile != "") { inputfile = sabundfile; format = "sabund"; m->mothurOut("Using " + sabundfile + " as input file for the sabund parameter."); m->mothurOutEndLine(); } + else { + m->mothurOut("No valid current files. You must provide a list, sabund, rabund or shared file before you can use the collect.single command."); m->mothurOutEndLine(); + abort = true; + } + } + } + } + } //check for optional parameter and set defaults // ...at some point should added some additional type checking... @@ -176,18 +265,18 @@ CollectCommand::CollectCommand(string option) { 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; - } - + //NOTE: if you add new calc options, don't forget to add them to the parameter initialize in setParameters or the gui won't be able to use them calc = validParameter.validFile(parameters, "calc", false); if (calc == "not found") { calc = "sobs-chao-ace-jack-shannon-npshannon-simpson"; } else { if (calc == "default") { calc = "sobs-chao-ace-jack-shannon-npshannon-simpson"; } } m->splitAtDash(calc, Estimators); + if (m->inUsersGroups("citation", Estimators)) { + ValidCalculators validCalc; validCalc.printCitations(Estimators); + //remove citation from list of calcs + for (int i = 0; i < Estimators.size(); i++) { if (Estimators[i] == "citation") { Estimators.erase(Estimators.begin()+i); break; } } + } string temp; temp = validParameter.validFile(parameters, "freq", false); if (temp == "not found") { temp = "100"; } @@ -208,57 +297,30 @@ CollectCommand::CollectCommand(string option) { } //********************************************************************************************************************** -void CollectCommand::help(){ - try { - m->mothurOut("The collect.single command can only be executed after a successful read.otu command. WITH ONE EXECEPTION. \n"); - m->mothurOut("The collect.single command can be executed after a successful cluster command. It will use the .list file from the output of the cluster.\n"); - m->mothurOut("The collect.single command parameters are label, freq, calc and abund. No parameters are required. \n"); - m->mothurOut("The collect.single command should be in the following format: \n"); - m->mothurOut("The freq parameter is used indicate when to output your data, by default it is set to 100. But you can set it to a percentage of the number of sequence. For example freq=0.10, means 10%. \n"); - m->mothurOut("collect.single(label=yourLabel, iters=yourIters, freq=yourFreq, calc=yourEstimators).\n"); - m->mothurOut("Example collect(label=unique-.01-.03, iters=10000, freq=10, calc=sobs-chao-ace-jack).\n"); - m->mothurOut("The default values for freq is 100, and calc are sobs-chao-ace-jack-shannon-npshannon-simpson.\n"); - validCalculator->printCalc("single", cout); - m->mothurOut("The label parameter is used to analyze specific labels in your input.\n"); - m->mothurOut("Note: No spaces between parameter labels (i.e. freq), '=' and parameters (i.e.yourFreq).\n\n"); - } - catch(exception& e) { - m->errorOut(e, "CollectCommand", "help"); - exit(1); - } -} - -//********************************************************************************************************************** - -CollectCommand::~CollectCommand(){} - -//********************************************************************************************************************** - int CollectCommand::execute(){ try { - if (abort == true) { return 0; } - - string hadShared = ""; - if ((globaldata->getFormat() != "sharedfile")) { inputFileNames.push_back(globaldata->inputFileName); } - else { hadShared = globaldata->getSharedFile(); inputFileNames = parseSharedFile(globaldata->getSharedFile()); globaldata->setFormat("rabund"); } + if (abort == true) { if (calledHelp) { return 0; } return 2; } + + if ((format != "sharedfile")) { inputFileNames.push_back(inputfile); } + else { inputFileNames = parseSharedFile(sharedfile); format = "rabund"; } for (int p = 0; p < inputFileNames.size(); p++) { - if (m->control_pressed) { outputTypes.clear(); for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } globaldata->Groups.clear(); if (hadShared != "") { globaldata->setSharedFile(hadShared); globaldata->setFormat("sharedfile"); } return 0; } + if (m->control_pressed) { outputTypes.clear(); for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } m->Groups.clear(); return 0; } if (outputDir == "") { outputDir += m->hasPath(inputFileNames[p]); } string fileNameRoot = outputDir + m->getRootName(m->getSimpleName(inputFileNames[p])); - globaldata->inputFileName = inputFileNames[p]; + //globaldata->inputFileName = inputFileNames[p]; if (inputFileNames.size() > 1) { m->mothurOutEndLine(); m->mothurOut("Processing group " + groups[p]); m->mothurOutEndLine(); m->mothurOutEndLine(); } - validCalculator = new ValidCalculators(); + ValidCalculators validCalculator; for (int i=0; iisValidCalculator("single", Estimators[i]) == true) { + if (validCalculator.isValidCalculator("single", Estimators[i]) == true) { if (Estimators[i] == "sobs") { cDisplays.push_back(new CollectDisplay(new Sobs(), new OneColumnFile(fileNameRoot+"sobs"))); outputNames.push_back(fileNameRoot+"sobs"); outputTypes["sobs"].push_back(fileNameRoot+"sobs"); @@ -339,14 +401,11 @@ int CollectCommand::execute(){ } //if the users entered no valid calculators don't execute command - if (cDisplays.size() == 0) { if (hadShared != "") { globaldata->setSharedFile(hadShared); globaldata->setFormat("sharedfile"); } return 0; } + if (cDisplays.size() == 0) { return 0; } - read = new ReadOTUFile(inputFileNames[p]); - read->read(&*globaldata); - - order = globaldata->gorder; + input = new InputData(inputFileNames[p], format); + order = input->getOrderVector(); string lastLabel = order->getLabel(); - input = globaldata->ginput; //if the users enters label "0.06" and there is no "0.06" in their file use the next lowest label. set processedLabels; @@ -354,13 +413,10 @@ int CollectCommand::execute(){ if (m->control_pressed) { for(int i=0;iginput = NULL; - delete read; - delete order; globaldata->gorder = NULL; - delete validCalculator; - globaldata->Groups.clear(); - if (hadShared != "") { globaldata->setSharedFile(hadShared); globaldata->setFormat("sharedfile"); } + for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } outputTypes.clear(); + delete input; + delete order; + m->Groups.clear(); return 0; } @@ -369,13 +425,10 @@ int CollectCommand::execute(){ if (m->control_pressed) { for(int i=0;iginput = NULL; - delete read; - delete order; globaldata->gorder = NULL; - delete validCalculator; - globaldata->Groups.clear(); - if (hadShared != "") { globaldata->setSharedFile(hadShared); globaldata->setFormat("sharedfile"); } + for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } outputTypes.clear(); + delete input; + delete order; + m->Groups.clear(); return 0; } @@ -421,12 +474,9 @@ int CollectCommand::execute(){ if (m->control_pressed) { for(int i=0;iginput = NULL; - delete read; - delete validCalculator; - globaldata->Groups.clear(); - if (hadShared != "") { globaldata->setSharedFile(hadShared); globaldata->setFormat("sharedfile"); } + for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } outputTypes.clear(); + delete input; + m->Groups.clear(); return 0; } @@ -456,13 +506,10 @@ int CollectCommand::execute(){ if (m->control_pressed) { for(int i=0;iginput = NULL; - delete read; - delete order; globaldata->gorder = NULL; - delete validCalculator; - globaldata->Groups.clear(); - if (hadShared != "") { globaldata->setSharedFile(hadShared); globaldata->setFormat("sharedfile"); } + for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } outputTypes.clear(); + delete input; + delete order; + m->Groups.clear(); return 0; } delete order; @@ -470,16 +517,10 @@ int CollectCommand::execute(){ for(int i=0;iginput = NULL; - delete read; - globaldata->gorder = NULL; - delete validCalculator; + delete input; } - //return to shared mode if you changed above - if (hadShared != "") { globaldata->setSharedFile(hadShared); globaldata->setFormat("sharedfile"); } - - if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } + if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } m->mothurOutEndLine(); m->mothurOut("Output File Names: "); m->mothurOutEndLine(); @@ -502,20 +543,15 @@ vector CollectCommand::parseSharedFile(string filename) { map filehandles; map::iterator it3; - - - //read first line - read = new ReadOTUFile(filename); - read->read(&*globaldata); - - input = globaldata->ginput; + + input = new InputData(filename, "sharedfile"); vector lookup = input->getSharedRAbundVectors(); string sharedFileRoot = m->getRootName(filename); //clears file before we start to write to it below for (int i=0; igetGroup() + ".rabund").c_str()); + m->mothurRemove((sharedFileRoot + lookup[i]->getGroup() + ".rabund")); filenames.push_back((sharedFileRoot + lookup[i]->getGroup() + ".rabund")); } @@ -543,9 +579,8 @@ vector CollectCommand::parseSharedFile(string filename) { for (it3 = filehandles.begin(); it3 != filehandles.end(); it3++) { delete it3->second; } - delete read; + delete input; - globaldata->ginput = NULL; return filenames; }