X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=removeseqscommand.cpp;h=73873f3a4744eb0e9ce59a9b2640bf013f524852;hb=035f86272c776e1cccaa47021e26782e49cd41e7;hp=2abe9ef78a8c76354d377087fa7a23deb27b4d25;hpb=0caf3fbabaa3ece404f8ce77f4c883dc5b1bf1dc;p=mothur.git diff --git a/removeseqscommand.cpp b/removeseqscommand.cpp index 2abe9ef..73873f3 100644 --- a/removeseqscommand.cpp +++ b/removeseqscommand.cpp @@ -10,13 +10,15 @@ #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", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pname); - CommandParameter pgroup("group", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pgroup); + 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); @@ -39,9 +41,9 @@ vector RemoveSeqsCommand::setParameters(){ string RemoveSeqsCommand::getHelpString(){ try { string helpString = ""; - helpString += "The remove.seqs command reads an .accnos file and at least one of the following file types: fasta, name, group, list, taxonomy, quality or alignreport file.\n"; + helpString += "The remove.seqs command reads an .accnos file and at least one of the following file types: fasta, name, group, count, list, taxonomy, quality or alignreport file.\n"; helpString += "It outputs a file containing the sequences NOT in the .accnos file.\n"; - helpString += "The remove.seqs command parameters are accnos, fasta, name, group, list, taxonomy, qfile, alignreport and dups. You must provide accnos and at least one of the file parameters.\n"; + helpString += "The remove.seqs command parameters are accnos, fasta, name, group, count, list, taxonomy, qfile, alignreport and dups. You must provide accnos and at least one of the file parameters.\n"; helpString += "The dups parameter allows you to remove the entire line from a name file if you remove any name from the line. default=true. \n"; helpString += "The remove.seqs command should be in the following format: remove.seqs(accnos=yourAccnos, fasta=yourFasta).\n"; helpString += "Example remove.seqs(accnos=amazon.accnos, fasta=amazon.fasta).\n"; @@ -53,7 +55,33 @@ string RemoveSeqsCommand::getHelpString(){ exit(1); } } - +//********************************************************************************************************************** +string RemoveSeqsCommand::getOutputFileNameTag(string type, string inputName=""){ + try { + string outputFileName = ""; + map >::iterator it; + + //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); + } +} //********************************************************************************************************************** RemoveSeqsCommand::RemoveSeqsCommand(){ @@ -68,6 +96,7 @@ RemoveSeqsCommand::RemoveSeqsCommand(){ outputTypes["alignreport"] = tempOutNames; outputTypes["list"] = tempOutNames; outputTypes["qfile"] = tempOutNames; + outputTypes["count"] = tempOutNames; } catch(exception& e) { m->errorOut(e, "RemoveSeqsCommand", "RemoveSeqsCommand"); @@ -106,6 +135,7 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option) { outputTypes["alignreport"] = tempOutNames; outputTypes["list"] = tempOutNames; outputTypes["qfile"] = tempOutNames; + outputTypes["count"] = tempOutNames; //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 = ""; } @@ -178,6 +208,14 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option) { //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["qfile"] = inputDir + it->second; } } + + it = parameters.find("count"); + //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["count"] = inputDir + it->second; } + } } @@ -234,13 +272,28 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option) { else { temp = "false"; usedDups = ""; } } dups = m->isTrue(temp); - - if ((fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == "") && (taxfile == "") && (qualfile == "")) { m->mothurOut("You must provide at least one of the following: fasta, name, group, taxonomy, quality, alignreport or list."); m->mothurOutEndLine(); abort = true; } - - if ((fastafile != "") && (namefile == "")) { - vector files; files.push_back(fastafile); - parser.getNameFile(files); - } + + countfile = validParameter.validFile(parameters, "count", true); + if (countfile == "not open") { countfile = ""; abort = true; } + else if (countfile == "not found") { countfile = ""; } + else { m->setCountTableFile(countfile); } + + if ((namefile != "") && (countfile != "")) { + m->mothurOut("[ERROR]: you may only use one of the following: name or count."); m->mothurOutEndLine(); abort = true; + } + + if ((groupfile != "") && (countfile != "")) { + m->mothurOut("[ERROR]: you may only use one of the following: group or count."); m->mothurOutEndLine(); abort=true; + } + + if ((countfile == "") && (fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == "") && (taxfile == "") && (qualfile == "")) { m->mothurOut("You must provide at least one of the following: fasta, name, group, taxonomy, quality, alignreport or list."); m->mothurOutEndLine(); abort = true; } + + if (countfile == "") { + if ((fastafile != "") && (namefile == "")) { + vector files; files.push_back(fastafile); + parser.getNameFile(files); + } + } } } @@ -257,9 +310,15 @@ int RemoveSeqsCommand::execute(){ if (abort == true) { if (calledHelp) { return 0; } return 2; } //get names you want to keep - readAccnos(); + names = m->readAccnos(accnosfile); if (m->control_pressed) { return 0; } + + if (countfile != "") { + if ((fastafile != "") || (listfile != "") || (taxfile != "")) { + 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"); + } + } //read through the correct file and output lines you want to keep if (namefile != "") { readName(); } @@ -269,6 +328,7 @@ int RemoveSeqsCommand::execute(){ if (listfile != "") { readList(); } if (taxfile != "") { readTax(); } if (qualfile != "") { readQual(); } + if (countfile != "") { readCount(); } if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } @@ -308,7 +368,12 @@ int RemoveSeqsCommand::execute(){ itTypes = outputTypes.find("qfile"); if (itTypes != outputTypes.end()) { if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setQualFile(current); } - } + } + + itTypes = outputTypes.find("count"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setCountTableFile(current); } + } } return 0; @@ -325,7 +390,7 @@ int RemoveSeqsCommand::readFasta(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(fastafile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(fastafile)) + "pick" + m->getExtension(fastafile); + string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(fastafile)) + getOutputFileNameTag("fasta", fastafile); ofstream out; m->openOutputFile(outputFileName, out); @@ -374,7 +439,7 @@ int RemoveSeqsCommand::readQual(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(qualfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(qualfile)) + "pick" + m->getExtension(qualfile); + string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(qualfile)) + getOutputFileNameTag("qfile", qualfile); ofstream out; m->openOutputFile(outputFileName, out); @@ -438,12 +503,69 @@ int RemoveSeqsCommand::readQual(){ } } //********************************************************************************************************************** +int RemoveSeqsCommand::readCount(){ + try { + + string thisOutputDir = outputDir; + if (outputDir == "") { thisOutputDir += m->hasPath(countfile); } + string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(countfile)) + getOutputFileNameTag("count", countfile); + + ofstream out; + m->openOutputFile(outputFileName, out); + + ifstream in; + m->openInputFile(countfile, in); + + bool wroteSomething = false; + int removedCount = 0; + + string headers = m->getline(in); m->gobble(in); + out << headers << endl; + + string name, rest; int thisTotal; + while (!in.eof()) { + + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } + + in >> name; m->gobble(in); + in >> thisTotal; m->gobble(in); + rest = m->getline(in); m->gobble(in); + if (m->debug) { m->mothurOut("[DEBUG]: " + name + '\t' + rest + "\n"); } + + if (names.count(name) == 0) { + out << name << '\t' << thisTotal << '\t' << rest << endl; + wroteSomething = true; + }else { removedCount += thisTotal; } + } + in.close(); + out.close(); + + //check for groups that have been eliminated + CountTable ct; + if (ct.testGroups(outputFileName)) { + ct.readTable(outputFileName); + 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); + + m->mothurOut("Removed " + toString(removedCount) + " sequences from your count file."); m->mothurOutEndLine(); + + return 0; + } + catch(exception& e) { + m->errorOut(e, "RemoveSeqsCommand", "readCount"); + exit(1); + } +} +//********************************************************************************************************************** int RemoveSeqsCommand::readList(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(listfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(listfile)) + "pick" + m->getExtension(listfile); - + string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(listfile)) + getOutputFileNameTag("list", listfile); ofstream out; m->openOutputFile(outputFileName, out); @@ -521,8 +643,7 @@ int RemoveSeqsCommand::readName(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(namefile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(namefile)) + "pick" + m->getExtension(namefile); - + string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(namefile)) + getOutputFileNameTag("name", namefile); ofstream out; m->openOutputFile(outputFileName, out); @@ -604,8 +725,7 @@ int RemoveSeqsCommand::readGroup(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(groupfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(groupfile)) + "pick" + m->getExtension(groupfile); - + string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(groupfile)) + getOutputFileNameTag("group", groupfile); ofstream out; m->openOutputFile(outputFileName, out); @@ -651,7 +771,7 @@ int RemoveSeqsCommand::readTax(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(taxfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(taxfile)) + "pick" + m->getExtension(taxfile); + string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(taxfile)) + getOutputFileNameTag("taxonomy", taxfile); ofstream out; m->openOutputFile(outputFileName, out); @@ -697,7 +817,7 @@ int RemoveSeqsCommand::readAlign(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(alignfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(alignfile)) + "pick.align.report"; + string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(alignfile)) + getOutputFileNameTag("alignreport"); ofstream out; m->openOutputFile(outputFileName, out); @@ -764,29 +884,5 @@ int RemoveSeqsCommand::readAlign(){ } } //********************************************************************************************************************** -void RemoveSeqsCommand::readAccnos(){ - try { - - ifstream in; - m->openInputFile(accnosfile, in); - string name; - - while(!in.eof()){ - in >> name; - - names.insert(name); - - m->gobble(in); - } - in.close(); - - } - catch(exception& e) { - m->errorOut(e, "RemoveSeqsCommand", "readAccnos"); - exit(1); - } -} - -//**********************************************************************************************************************