X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=removeseqscommand.cpp;h=b1bc4fd508576c04126206b4e178798c088cb91d;hb=1a968f34ae2d2680eaf189a197d1a21b8dfd6c03;hp=1fb94462ac48fa13ac871c6b9d3cf4f3ae2ceff6;hpb=ea4f373c28543cd1002b0dd7dc6e55c526647d59;p=mothur.git diff --git a/removeseqscommand.cpp b/removeseqscommand.cpp index 1fb9446..b1bc4fd 100644 --- a/removeseqscommand.cpp +++ b/removeseqscommand.cpp @@ -10,22 +10,23 @@ #include "removeseqscommand.h" #include "sequence.hpp" #include "listvector.hpp" +#include "counttable.h" //********************************************************************************************************************** vector RemoveSeqsCommand::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,false); parameters.push_back(ptaxonomy); - CommandParameter palignreport("alignreport", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(palignreport); - CommandParameter pqfile("qfile", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pqfile); - CommandParameter paccnos("accnos", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(paccnos); - 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,false,true); parameters.push_back(ptaxonomy); + CommandParameter palignreport("alignreport", "InputTypes", "", "", "none", "FNGLT", "none","alignreport",false,false); parameters.push_back(palignreport); + CommandParameter pqfile("qfile", "InputTypes", "", "", "none", "FNGLT", "none","qfile",false,false); parameters.push_back(pqfile); + CommandParameter paccnos("accnos", "InputTypes", "", "", "none", "none", "none","",false,true,true); parameters.push_back(paccnos); + 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); } @@ -55,33 +56,27 @@ string RemoveSeqsCommand::getHelpString(){ } } //********************************************************************************************************************** -string RemoveSeqsCommand::getOutputFileNameTag(string type, string inputName=""){ - try { - string outputFileName = ""; - map >::iterator it; +string RemoveSeqsCommand::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 == "list") { outputFileName = "pick" + m->getExtension(inputName); } - else if (type == "qfile") { outputFileName = "pick" + m->getExtension(inputName); } - else if (type == "alignreport") { outputFileName = "pick.align.report"; } - else if (type == "count") { outputFileName = "pick.count.table"; } - 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, "RemoveSeqsCommand", "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 == "qfile") { 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, "GetSeqsCommand", "getOutputPattern"); + exit(1); + } } - //********************************************************************************************************************** RemoveSeqsCommand::RemoveSeqsCommand(){ try { @@ -389,7 +384,10 @@ int RemoveSeqsCommand::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); @@ -405,6 +403,12 @@ int RemoveSeqsCommand::readFasta(){ if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } Sequence currSeq(in); + + if (!dups) {//adjust name if needed + map::iterator it = uniqueMap.find(currSeq.getName()); + if (it != uniqueMap.end()) { currSeq.setName(it->second); } + } + name = currSeq.getName(); if (name != "") { @@ -412,7 +416,7 @@ int RemoveSeqsCommand::readFasta(){ if (names.count(name) == 0) { wroteSomething = true; - currSeq.printSequence(out); + currSeq.printSequence(out); }else { removedCount++; } } m->gobble(in); @@ -438,7 +442,10 @@ int RemoveSeqsCommand::readQual(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(qualfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(qualfile)) + getOutputFileNameTag("qfile", qualfile); + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(qualfile)); + variables["[extension]"] = m->getExtension(qualfile); + string outputFileName = getOutputFileName("qfile", variables); ofstream out; m->openOutputFile(outputFileName, out); @@ -462,7 +469,7 @@ int RemoveSeqsCommand::readQual(){ saveName = name.substr(1); while (!in.eof()) { char c = in.get(); - if (c == 10 || c == 13){ break; } + if (c == 10 || c == 13 || c == -1){ break; } else { name += c; } } m->gobble(in); @@ -476,6 +483,11 @@ int RemoveSeqsCommand::readQual(){ m->gobble(in); + if (!dups) {//adjust name if needed + map::iterator it = uniqueMap.find(saveName); + if (it != uniqueMap.end()) { name = ">" + it->second; saveName = it->second; } + } + if (names.count(saveName) == 0) { wroteSomething = true; @@ -507,7 +519,10 @@ int RemoveSeqsCommand::readCount(){ 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); @@ -538,6 +553,14 @@ int RemoveSeqsCommand::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 only sequences from the .accnos file."); m->mothurOutEndLine(); } outputTypes["count"].push_back(outputFileName); outputNames.push_back(outputFileName); @@ -556,7 +579,10 @@ int RemoveSeqsCommand::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); @@ -634,7 +660,10 @@ int RemoveSeqsCommand::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); @@ -686,6 +715,8 @@ int RemoveSeqsCommand::readName(){ wroteSomething = true; out << validSecond[0] << '\t'; + //we are changing the unique name in the fasta file + uniqueMap[firstCol] = validSecond[0]; //you know you have at least one valid second since first column is valid for (int i = 0; i < validSecond.size()-1; i++) { out << validSecond[i] << ','; } @@ -716,7 +747,10 @@ int RemoveSeqsCommand::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); @@ -762,7 +796,10 @@ int RemoveSeqsCommand::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); @@ -776,12 +813,18 @@ int RemoveSeqsCommand::readTax(){ while(!in.eof()){ if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } - in >> name; //read from first column + in >> name; m->gobble(in); //read from first column in >> tax; //read from second column + if (!dups) {//adjust name if needed + map::iterator it = uniqueMap.find(name); + if (it != uniqueMap.end()) { name = it->second; } + } + //if this name is in the accnos file if (names.count(name) == 0) { wroteSomething = true; + out << name << '\t' << tax << endl; }else { removedCount++; } @@ -808,7 +851,9 @@ int RemoveSeqsCommand::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)); + string outputFileName = getOutputFileName("alignreport", variables); ofstream out; m->openOutputFile(outputFileName, out); @@ -831,6 +876,11 @@ int RemoveSeqsCommand::readAlign(){ if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } in >> name; //read from first column + + if (!dups) {//adjust name if needed + map::iterator it = uniqueMap.find(name); + if (it != uniqueMap.end()) { name = it->second; } + } //if this name is in the accnos file if (names.count(name) == 0) {