X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=getgroupscommand.cpp;h=bb15a3f5a21e3c7785283cfc5d6eade2c1bda6ed;hb=250e3b11b1c9c1e1ad458ab6c7e71ac2e67e11d9;hp=7585c122eeb3a212fab404240f5b6f6568574634;hpb=5b72d1cf3fa48730e5bb70d59cced1e43e1fe424;p=mothur.git diff --git a/getgroupscommand.cpp b/getgroupscommand.cpp index 7585c12..bb15a3f 100644 --- a/getgroupscommand.cpp +++ b/getgroupscommand.cpp @@ -16,18 +16,18 @@ //********************************************************************************************************************** vector GetGroupsCommand::setParameters(){ try { - CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "FNGLT",false,false); parameters.push_back(pfasta); - CommandParameter pshared("shared", "InputTypes", "", "", "none", "sharedGroup", "none",false,false); parameters.push_back(pshared); - CommandParameter pname("name", "InputTypes", "", "", "NameCount", "none", "none",false,false); parameters.push_back(pname); - CommandParameter pcount("count", "InputTypes", "", "", "NameCount-CountGroup", "none", "none",false,false); parameters.push_back(pcount); - CommandParameter pgroup("group", "InputTypes", "", "", "CountGroup", "sharedGroup", "FNGLT",false,false); parameters.push_back(pgroup); - CommandParameter pdesign("design", "InputTypes", "", "", "none", "sharedGroup", "FNGLT",false,false); parameters.push_back(pdesign); - CommandParameter plist("list", "InputTypes", "", "", "none", "none", "FNGLT",false,false); parameters.push_back(plist); - CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "none", "none", "FNGLT",false,false); parameters.push_back(ptaxonomy); - CommandParameter paccnos("accnos", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(paccnos); - CommandParameter pgroups("groups", "String", "", "", "", "", "",false,false); parameters.push_back(pgroups); - CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir); - CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir); + CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "FNGLT","fasta",false,false, true); parameters.push_back(pfasta); + CommandParameter pshared("shared", "InputTypes", "", "", "none", "sharedGroup", "none","shared",false,false, true); parameters.push_back(pshared); + CommandParameter pname("name", "InputTypes", "", "", "NameCount", "none", "none","name",false,false, true); parameters.push_back(pname); + CommandParameter pcount("count", "InputTypes", "", "", "NameCount-CountGroup", "none", "none","count",false,false, true); parameters.push_back(pcount); + CommandParameter pgroup("group", "InputTypes", "", "", "CountGroup", "sharedGroup", "FNGLT","group",false,false, true); parameters.push_back(pgroup); + CommandParameter pdesign("design", "InputTypes", "", "", "none", "sharedGroup", "FNGLT","design",false,false, true); parameters.push_back(pdesign); + CommandParameter plist("list", "InputTypes", "", "", "none", "none", "FNGLT","list",false,false, true); parameters.push_back(plist); + CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "none", "none", "FNGLT","taxonomy",false,false, true); parameters.push_back(ptaxonomy); + CommandParameter paccnos("accnos", "InputTypes", "", "", "none", "none", "none","",false,false); parameters.push_back(paccnos); + CommandParameter pgroups("groups", "String", "", "", "", "", "","",false,false); parameters.push_back(pgroups); + 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); } @@ -59,33 +59,27 @@ string GetGroupsCommand::getHelpString(){ } } //********************************************************************************************************************** -string GetGroupsCommand::getOutputFileNameTag(string type, string inputName=""){ - try { - string outputFileName = ""; - map >::iterator it; +string GetGroupsCommand::getOutputPattern(string type) { + try { + string pattern = ""; - //is this a type this command creates - it = outputTypes.find(type); - if (it == outputTypes.end()) { m->mothurOut("[ERROR]: this command doesn't create a " + type + " output file.\n"); } - else { - if (type == "fasta") { outputFileName = "pick" + m->getExtension(inputName); } - else if (type == "taxonomy") { outputFileName = "pick" + m->getExtension(inputName); } - else if (type == "name") { outputFileName = "pick" + m->getExtension(inputName); } - else if (type == "group") { outputFileName = "pick" + m->getExtension(inputName); } - else if (type == "count") { outputFileName = "pick" + m->getExtension(inputName); } - else if (type == "list") { outputFileName = "pick" + m->getExtension(inputName); } - else if (type == "shared") { outputFileName = "pick" + m->getExtension(inputName); } - else if (type == "design") { outputFileName = "pick" + m->getExtension(inputName); } - else { m->mothurOut("[ERROR]: No definition for type " + type + " output file tag.\n"); m->control_pressed = true; } - } - return outputFileName; - } - catch(exception& e) { - m->errorOut(e, "GetGroupsCommand", "getOutputFileNameTag"); - exit(1); - } + if (type == "fasta") { pattern = "[filename],pick,[extension]"; } + else if (type == "taxonomy") { pattern = "[filename],pick,[extension]"; } + else if (type == "name") { pattern = "[filename],pick,[extension]"; } + else if (type == "group") { pattern = "[filename],pick,[extension]"; } + else if (type == "count") { pattern = "[filename],pick,[extension]"; } + else if (type == "list") { pattern = "[filename],[tag],pick,[extension]"; } + else if (type == "shared") { pattern = "[filename],[tag],pick,[extension]"; } + else if (type == "design") { pattern = "[filename],pick,[extension]"; } + else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; } + + return pattern; + } + catch(exception& e) { + m->errorOut(e, "GetGroupsCommand", "getOutputPattern"); + exit(1); + } } - //********************************************************************************************************************** GetGroupsCommand::GetGroupsCommand(){ try { @@ -376,7 +370,7 @@ int GetGroupsCommand::execute(){ m->mothurOut("\n[NOTE]: The count file should contain only unique names, so mothur assumes your fasta, list and taxonomy files also contain only uniques.\n\n"); } CountTable ct; - ct.readTable(countfile); + ct.readTable(countfile, true, false); if (!ct.hasGroupInfo()) { m->mothurOut("[ERROR]: your count file does not contain group info, aborting.\n"); return 0; } vector gNamesOfGroups = ct.getNamesOfGroups(); @@ -467,7 +461,10 @@ int GetGroupsCommand::readFasta(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(fastafile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(fastafile)) + getOutputFileNameTag("fasta", fastafile); + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(fastafile)); + variables["[extension]"] = m->getExtension(fastafile); + string outputFileName = getOutputFileName("fasta", variables); ofstream out; m->openOutputFile(outputFileName, out); @@ -530,12 +527,17 @@ int GetGroupsCommand::readShared(){ InputData input(sharedfile, "sharedfile"); vector lookup = input.getSharedRAbundVectors(); + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(sharedfile)); + variables["[extension]"] = m->getExtension(sharedfile); bool wroteSomething = false; while(lookup[0] != NULL) { - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(sharedfile)) + lookup[0]->getLabel() + "." + getOutputFileNameTag("shared", sharedfile); + variables["[tag]"] = lookup[0]->getLabel(); + string outputFileName = getOutputFileName("shared", variables); + ofstream out; m->openOutputFile(outputFileName, out); outputTypes["shared"].push_back(outputFileName); outputNames.push_back(outputFileName); @@ -580,10 +582,9 @@ int GetGroupsCommand::readList(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(listfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(listfile)) + getOutputFileNameTag("list", listfile); - - ofstream out; - m->openOutputFile(outputFileName, out); + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(listfile)); + variables["[extension]"] = m->getExtension(listfile); ifstream in; m->openInputFile(listfile, in); @@ -594,9 +595,19 @@ int GetGroupsCommand::readList(){ while(!in.eof()){ selectedCount = 0; - + //read in list vector ListVector list(in); + + variables["[tag]"] = list.getLabel(); + string outputFileName = getOutputFileName("list", variables); + + ofstream out; + m->openOutputFile(outputFileName, out); + outputTypes["list"].push_back(outputFileName); outputNames.push_back(outputFileName); + + vector binLabels = list.getLabels(); + vector newBinLabels; //make a new list vector ListVector newList; @@ -608,13 +619,14 @@ int GetGroupsCommand::readList(){ //parse out names that are in accnos file string binnames = list.get(i); + vector thisBinNames; + m->splitAtComma(binnames, thisBinNames); string newNames = ""; - while (binnames.find_first_of(',') != -1) { - string name = binnames.substr(0,binnames.find_first_of(',')); - binnames = binnames.substr(binnames.find_first_of(',')+1, binnames.length()); - - //if that name is in the .accnos file, add it + for (int j = 0; j < thisBinNames.size(); j++) { + string name = thisBinNames[j]; + + //if that name is in the .accnos file, add it if (names.count(name) != 0) { newNames += name + ","; selectedCount++; } else{ //if you are not in the accnos file check if you are a name that needs to be changed @@ -624,39 +636,30 @@ int GetGroupsCommand::readList(){ selectedCount++; } } - } - - //get last name - if (names.count(binnames) != 0) { newNames += binnames + ","; selectedCount++; } - else{ - //if you are not in the accnos file check if you are a name that needs to be changed - map::iterator it = uniqueToRedundant.find(binnames); - if (it != uniqueToRedundant.end()) { - newNames += it->second + ","; - selectedCount++; - } - } - + } + //if there are names in this bin add to new list if (newNames != "") { newNames = newNames.substr(0, newNames.length()-1); //rip off extra comma - newList.push_back(newNames); + newList.push_back(newNames); + newBinLabels.push_back(binLabels[i]); } } //print new listvector if (newList.getNumBins() != 0) { wroteSomething = true; + newList.setLabels(newBinLabels); + newList.printHeaders(out); newList.print(out); } m->gobble(in); + out.close(); } - in.close(); - out.close(); + in.close(); if (wroteSomething == false) { m->mothurOut("Your file does NOT contain sequences from the groups you wish to get."); m->mothurOutEndLine(); } - outputTypes["list"].push_back(outputFileName); outputNames.push_back(outputFileName); m->mothurOut("Selected " + toString(selectedCount) + " sequences from your list file."); m->mothurOutEndLine(); @@ -673,7 +676,10 @@ int GetGroupsCommand::readName(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(namefile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(namefile)) + getOutputFileNameTag("name", namefile); + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(namefile)); + variables["[extension]"] = m->getExtension(namefile); + string outputFileName = getOutputFileName("name", variables); ofstream out; m->openOutputFile(outputFileName, out); @@ -754,7 +760,10 @@ int GetGroupsCommand::readGroup(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(groupfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(groupfile)) + getOutputFileNameTag("group", groupfile); + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(groupfile)); + variables["[extension]"] = m->getExtension(groupfile); + string outputFileName = getOutputFileName("group", variables); ofstream out; m->openOutputFile(outputFileName, out); @@ -801,7 +810,10 @@ int GetGroupsCommand::readCount(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(countfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(countfile)) + getOutputFileNameTag("count", countfile); + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(countfile)); + variables["[extension]"] = m->getExtension(countfile); + string outputFileName = getOutputFileName("count", variables); ofstream out; m->openOutputFile(outputFileName, out); @@ -877,7 +889,10 @@ int GetGroupsCommand::readDesign(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(designfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(designfile)) + getOutputFileNameTag("design", designfile); + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(designfile)); + variables["[extension]"] = m->getExtension(designfile); + string outputFileName = getOutputFileName("design", variables); ofstream out; m->openOutputFile(outputFileName, out); @@ -927,7 +942,11 @@ int GetGroupsCommand::readTax(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(taxfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(taxfile)) + getOutputFileNameTag("taxonomy", taxfile); + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(taxfile)); + variables["[extension]"] = m->getExtension(taxfile); + string outputFileName = getOutputFileName("taxonomy", variables); + ofstream out; m->openOutputFile(outputFileName, out);