X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=getlistcountcommand.cpp;fp=getlistcountcommand.cpp;h=980c886cc0cb79f51f892ee13fe4dc2c3061b812;hb=0caf3fbabaa3ece404f8ce77f4c883dc5b1bf1dc;hp=0000000000000000000000000000000000000000;hpb=1b73ff67c83892a025e597dabd9df6fe7b58206a;p=mothur.git diff --git a/getlistcountcommand.cpp b/getlistcountcommand.cpp new file mode 100644 index 0000000..980c886 --- /dev/null +++ b/getlistcountcommand.cpp @@ -0,0 +1,270 @@ +/* + * getlistcountcommand.cpp + * Mothur + * + * Created by westcott on 10/12/09. + * Copyright 2009 Schloss Lab. All rights reserved. + * + */ + +#include "getlistcountcommand.h" + +//********************************************************************************************************************** +vector GetListCountCommand::setParameters(){ + try { + CommandParameter plist("list", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(plist); + CommandParameter plabel("label", "String", "", "", "", "", "",false,false); parameters.push_back(plabel); + CommandParameter parasort("sort", "Multiple", "name-otu", "otu", "", "", "",false,false); parameters.push_back(parasort); + 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, "GetListCountCommand", "setParameters"); + exit(1); + } +} +//********************************************************************************************************************** +string GetListCountCommand::getHelpString(){ + try { + string helpString = ""; + helpString += "The get.otulist command parameters are list, sort and label. list is required, unless you have a valid current list 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 sort parameter allows you to select how you want the output displayed. Options are otu and name.\n"; + helpString += "If otu is selected the output will be otu number followed by the list of names in that otu.\n"; + helpString += "If name is selected the output will be a sequence name followed by its otu number.\n"; + helpString += "The get.otulist command should be in the following format: get.otulist(list=yourlistFile, label=yourLabels).\n"; + helpString += "Example get.otulist(list=amazon.fn.list, label=0.10).\n"; + helpString += "The default value for label is all lines in your inputfile.\n"; + helpString += "The get.otulist command outputs a .otu file for each distance you specify listing the bin number and the names of the sequences in that bin.\n"; + helpString += "Note: No spaces between parameter labels (i.e. list), '=' and parameters (i.e.yourListFile).\n"; + return helpString; + } + catch(exception& e) { + m->errorOut(e, "GetListCountCommand", "getHelpString"); + exit(1); + } +} +//********************************************************************************************************************** +GetListCountCommand::GetListCountCommand(){ + try { + abort = true; calledHelp = true; + setParameters(); + vector tempOutNames; + outputTypes["otu"] = tempOutNames; + } + catch(exception& e) { + m->errorOut(e, "GetListCountCommand", "GetListCountCommand"); + exit(1); + } +} +//********************************************************************************************************************** +GetListCountCommand::GetListCountCommand(string option) { + try { + abort = false; calledHelp = false; + allLines = 1; + + //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(); + + OptionParser parser(option); + map parameters = parser.getParameters(); + + ValidParameters validParameter; + map::iterator it; + + //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["otu"] = 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("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; } + } + } + + //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 = ""; } + + //check for required parameters + listfile = validParameter.validFile(parameters, "list", true); + if (listfile == "not found") { + listfile = m->getListFile(); + if (listfile != "") { m->mothurOut("Using " + listfile + " as input file for the list parameter."); m->mothurOutEndLine(); } + else { m->mothurOut("You have no current list file and the list parameter is required."); m->mothurOutEndLine(); abort = true; } + } + else if (listfile == "not open") { abort = true; } + else { m->setListFile(listfile); } + + + //check for optional parameter and set defaults + // ...at some point should added some additional type checking... + sort = validParameter.validFile(parameters, "sort", false); if (sort == "not found") { sort = "otu"; } + if ((sort != "otu") && (sort != "name")) { m->mothurOut( sort + " is not a valid sort option. Options are otu and name. I will use otu."); m->mothurOutEndLine(); sort = "otu"; } + + label = validParameter.validFile(parameters, "label", false); + if (label == "not found") { label = ""; } + else { + if(label != "all") { m->splitAtDash(label, labels); allLines = 0; } + else { allLines = 1; } + } + } + } + catch(exception& e) { + m->errorOut(e, "GetListCountCommand", "GetListCountCommand"); + exit(1); + } +} +//********************************************************************************************************************** + +int GetListCountCommand::execute(){ + try { + if (abort == true) { if (calledHelp) { return 0; } return 2; } + + input = new InputData(listfile, "list"); + list = input->getListVector(); + string lastLabel = list->getLabel(); + + //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; + + if (m->control_pressed) { delete input; delete list; for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } + + while((list != NULL) && ((allLines == 1) || (userLabels.size() != 0))) { + + if(allLines == 1 || labels.count(list->getLabel()) == 1){ + + process(list); + + if (m->control_pressed) { delete input; delete list; for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } + + processedLabels.insert(list->getLabel()); + userLabels.erase(list->getLabel()); + } + + if ((m->anyLabelsToProcess(list->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) { + string saveLabel = list->getLabel(); + + delete list; + list = input->getListVector(lastLabel); + + process(list); + + if (m->control_pressed) { delete input; delete list; for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } + + + processedLabels.insert(list->getLabel()); + userLabels.erase(list->getLabel()); + + //restore real lastlabel to save below + list->setLabel(saveLabel); + } + + lastLabel = list->getLabel(); + + delete list; + list = input->getListVector(); + } + + + //output error messages about any remaining user labels + set::iterator it; + bool needToRun = false; + for (it = userLabels.begin(); it != userLabels.end(); it++) { + 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 { + m->mothurOut(". Please refer to " + lastLabel + "."); m->mothurOutEndLine(); + } + } + + //run last label if you need to + if (needToRun == true) { + if (list != NULL) { delete list; } + list = input->getListVector(lastLabel); + + process(list); + + if (m->control_pressed) { delete input; delete list; for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } + + delete list; + } + + delete input; + + 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) { + m->errorOut(e, "GetListCountCommand", "execute"); + exit(1); + } +} + +//********************************************************************************************************************** +//return 1 if error, 0 otherwise +void GetListCountCommand::process(ListVector* list) { + try { + string binnames; + if (outputDir == "") { outputDir += m->hasPath(listfile); } + string outputFileName = outputDir + m->getRootName(m->getSimpleName(listfile)) + list->getLabel() + ".otu"; + m->openOutputFile(outputFileName, out); + outputNames.push_back(outputFileName); outputTypes["otu"].push_back(outputFileName); + + m->mothurOut(list->getLabel()); m->mothurOutEndLine(); + + //for each bin in the list vector + for (int i = 0; i < list->getNumBins(); i++) { + if (m->control_pressed) { break; } + + binnames = list->get(i); + + if (sort == "otu") { + out << i+1 << '\t' << binnames << endl; + }else{ //sort = name + vector names; + m->splitAtComma(binnames, names); + + for (int j = 0; j < names.size(); j++) { + out << names[j] << '\t' << i+1 << endl; + } + } + } + + out.close(); + } + catch(exception& e) { + m->errorOut(e, "GetListCountCommand", "process"); + exit(1); + } +} +//********************************************************************************************************************** + +