X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=getlineagecommand.cpp;h=b895cc4fc62bfb49346c96df7a0d6371dd2b4a50;hb=1a968f34ae2d2680eaf189a197d1a21b8dfd6c03;hp=1cd139b5213733e759a7a32a1fbdf8221d09dfb6;hpb=ea4f373c28543cd1002b0dd7dc6e55c526647d59;p=mothur.git diff --git a/getlineagecommand.cpp b/getlineagecommand.cpp index 1cd139b..b895cc4 100644 --- a/getlineagecommand.cpp +++ b/getlineagecommand.cpp @@ -10,21 +10,22 @@ #include "getlineagecommand.h" #include "sequence.hpp" #include "listvector.hpp" +#include "counttable.h" //********************************************************************************************************************** vector GetLineageCommand::setParameters(){ try { - CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pfasta); - CommandParameter pname("name", "InputTypes", "", "", "NameCount", "FNGLT", "none",false,false); parameters.push_back(pname); - CommandParameter pcount("count", "InputTypes", "", "", "NameCount-CountGroup", "FNGLT", "none",false,false); parameters.push_back(pcount); - CommandParameter pgroup("group", "InputTypes", "", "", "CountGroup", "FNGLT", "none",false,false); parameters.push_back(pgroup); - CommandParameter plist("list", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(plist); - CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "none", "FNGLT", "none",false,true); parameters.push_back(ptaxonomy); - CommandParameter palignreport("alignreport", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(palignreport); - CommandParameter ptaxon("taxon", "String", "", "", "", "", "",false,true); parameters.push_back(ptaxon); - CommandParameter pdups("dups", "Boolean", "", "T", "", "", "",false,false); parameters.push_back(pdups); - 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", "FNGLT", "none","fasta",false,false, true); parameters.push_back(pfasta); + CommandParameter pname("name", "InputTypes", "", "", "NameCount", "FNGLT", "none","name",false,false, true); parameters.push_back(pname); + CommandParameter pcount("count", "InputTypes", "", "", "NameCount-CountGroup", "FNGLT", "none","count",false,false, true); parameters.push_back(pcount); + CommandParameter pgroup("group", "InputTypes", "", "", "CountGroup", "FNGLT", "none","group",false,false, true); parameters.push_back(pgroup); + CommandParameter plist("list", "InputTypes", "", "", "none", "FNGLT", "none","list",false,false, true); parameters.push_back(plist); + CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "none", "FNGLT", "none","taxonomy",false,true, true); parameters.push_back(ptaxonomy); + CommandParameter palignreport("alignreport", "InputTypes", "", "", "none", "FNGLT", "none","alignreport",false,false); parameters.push_back(palignreport); + CommandParameter ptaxon("taxon", "String", "", "", "", "", "","",false,true, true); parameters.push_back(ptaxon); + CommandParameter pdups("dups", "Boolean", "", "T", "", "", "","",false,false); parameters.push_back(pdups); + 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); } @@ -59,30 +60,25 @@ string GetLineageCommand::getHelpString(){ } } //********************************************************************************************************************** -string GetLineageCommand::getOutputFileNameTag(string type, string inputName=""){ - try { - string outputFileName = ""; - map >::iterator it; +string GetLineageCommand::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 == "count") { outputFileName = "pick.count.table"; } - else if (type == "group") { outputFileName = "pick" + m->getExtension(inputName); } - else if (type == "list") { outputFileName = "pick" + m->getExtension(inputName); } - else if (type == "alignreport") { outputFileName = "pick.align.report"; } - 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, "GetLineageCommand", "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],pick,[extension]"; } + else if (type == "alignreport") { pattern = "[filename],pick.align.report"; } + else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; } + + return pattern; + } + catch(exception& e) { + m->errorOut(e, "GetLineageCommand", "getOutputPattern"); + exit(1); + } } //********************************************************************************************************************** GetLineageCommand::GetLineageCommand(){ @@ -361,7 +357,10 @@ int GetLineageCommand::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); @@ -408,7 +407,10 @@ int GetLineageCommand::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); @@ -438,6 +440,14 @@ int GetLineageCommand::readCount(){ } in.close(); out.close(); + + //check for groups that have been eliminated + CountTable ct; + if (ct.testGroups(outputFileName)) { + ct.readTable(outputFileName, true); + ct.printTable(outputFileName); + } + if (wroteSomething == false) { m->mothurOut("Your file contains does not contain any sequences from " + taxons + "."); m->mothurOutEndLine(); } outputTypes["count"].push_back(outputFileName); outputNames.push_back(outputFileName); @@ -454,7 +464,10 @@ int GetLineageCommand::readList(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(listfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(listfile)) + getOutputFileNameTag("list", listfile); + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(listfile)); + variables["[extension]"] = m->getExtension(listfile); + string outputFileName = getOutputFileName("list", variables); ofstream out; m->openOutputFile(outputFileName, out); @@ -526,7 +539,10 @@ int GetLineageCommand::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); @@ -612,7 +628,10 @@ int GetLineageCommand::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); @@ -659,7 +678,10 @@ int GetLineageCommand::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); @@ -691,15 +713,17 @@ int GetLineageCommand::readTax(){ in >> name; //read from first column in >> tax; //read from second column + string noQuotesTax = m->removeQuotes(tax); + for (int j = 0; j < listOfTaxons.size(); j++) { - string newtax = tax; + string newtax = noQuotesTax; //if the users file contains confidence scores we want to ignore them when searching for the taxons, unless the taxon has them if (!taxonsHasConfidence[j]) { - int hasConfidences = tax.find_first_of('('); + int hasConfidences = noQuotesTax.find_first_of('('); if (hasConfidences != string::npos) { - newtax = tax; + newtax = noQuotesTax; m->removeConfidences(newtax); } @@ -712,7 +736,7 @@ int GetLineageCommand::readTax(){ break; } }else{//if listOfTaxons[i] has them and you don't them remove taxons - int hasConfidences = tax.find_first_of('('); + int hasConfidences = noQuotesTax.find_first_of('('); if (hasConfidences == string::npos) { int pos = newtax.find(noConfidenceTaxons[j]); @@ -726,10 +750,10 @@ int GetLineageCommand::readTax(){ }else { //both have confidences so we want to make sure the users confidences are greater then or equal to the taxons //first remove confidences from both and see if the taxonomy exists - string noNewTax = tax; - int hasConfidences = tax.find_first_of('('); + string noNewTax = noQuotesTax; + int hasConfidences = noQuotesTax.find_first_of('('); if (hasConfidences != string::npos) { - noNewTax = tax; + noNewTax = noQuotesTax; m->removeConfidences(noNewTax); } @@ -803,20 +827,27 @@ int GetLineageCommand::readTax(){ /**************************************************************************************************/ vector< map > GetLineageCommand::getTaxons(string tax) { try { - + vector< map > t; string taxon = ""; int taxLength = tax.length(); + for(int i=0;iisNumeric1(confidenceScore)) { //its a confidence + newtaxon = taxon.substr(0, openParen); //rip off confidence + confidence = taxon.substr((openParen+1), (closeParen-openParen-1)); + }else { //its part of the taxon + newtaxon = taxon; + confidence = "0"; + } }else{ newtaxon = taxon; confidence = "0"; @@ -826,12 +857,13 @@ vector< map > GetLineageCommand::getTaxons(string tax) { map temp; temp[newtaxon] = con; + t.push_back(temp); - taxon = ""; } else{ taxon += tax[i]; + } } @@ -848,7 +880,11 @@ int GetLineageCommand::readAlign(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(alignfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(alignfile)) + getOutputFileNameTag("alignreport"); + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(alignfile)); + variables["[extension]"] = m->getExtension(alignfile); + string outputFileName = getOutputFileName("alignreport", variables); + ofstream out; m->openOutputFile(outputFileName, out);