X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=removeseqscommand.cpp;h=2abe9ef78a8c76354d377087fa7a23deb27b4d25;hb=e0ce7cbc93d7d2fbb753ca694182db092a0ea0e7;hp=0ab181b411738d38b769a0255baeaf5968308d35;hpb=c6e5f84783b39a558119835963dec3c4facb0154;p=mothur.git diff --git a/removeseqscommand.cpp b/removeseqscommand.cpp index 0ab181b..2abe9ef 100644 --- a/removeseqscommand.cpp +++ b/removeseqscommand.cpp @@ -12,18 +12,79 @@ #include "listvector.hpp" //********************************************************************************************************************** +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 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); + + vector myArray; + for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); } + return myArray; + } + catch(exception& e) { + m->errorOut(e, "RemoveSeqsCommand", "setParameters"); + exit(1); + } +} +//********************************************************************************************************************** +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 += "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 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"; + helpString += "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n"; + return helpString; + } + catch(exception& e) { + m->errorOut(e, "RemoveSeqsCommand", "getHelpString"); + exit(1); + } +} + +//********************************************************************************************************************** +RemoveSeqsCommand::RemoveSeqsCommand(){ + try { + abort = true; calledHelp = true; + setParameters(); + vector tempOutNames; + outputTypes["fasta"] = tempOutNames; + outputTypes["taxonomy"] = tempOutNames; + outputTypes["name"] = tempOutNames; + outputTypes["group"] = tempOutNames; + outputTypes["alignreport"] = tempOutNames; + outputTypes["list"] = tempOutNames; + outputTypes["qfile"] = tempOutNames; + } + catch(exception& e) { + m->errorOut(e, "RemoveSeqsCommand", "RemoveSeqsCommand"); + exit(1); + } +} +//********************************************************************************************************************** RemoveSeqsCommand::RemoveSeqsCommand(string option) { try { - abort = false; + abort = false; calledHelp = false; //allow user to run help - if(option == "help") { help(); abort = true; } + if(option == "help") { help(); abort = true; calledHelp = true; } + else if(option == "citation") { citation(); abort = true; calledHelp = true;} else { - //valid paramters for this command - string Array[] = {"fasta","name", "group", "alignreport", "accnos", "list","taxonomy","outputdir","inputdir", "dups" }; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + vector myArray = setParameters(); OptionParser parser(option); map parameters = parser.getParameters(); @@ -36,6 +97,16 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option) { if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; } } + //initialize outputTypes + vector tempOutNames; + outputTypes["fasta"] = tempOutNames; + outputTypes["taxonomy"] = tempOutNames; + outputTypes["name"] = tempOutNames; + outputTypes["group"] = tempOutNames; + outputTypes["alignreport"] = tempOutNames; + outputTypes["list"] = tempOutNames; + outputTypes["qfile"] = 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 = ""; } @@ -99,25 +170,43 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option) { //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["taxonomy"] = inputDir + it->second; } } + + it = parameters.find("qfile"); + //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["qfile"] = inputDir + it->second; } + } } //check for required parameters accnosfile = validParameter.validFile(parameters, "accnos", true); if (accnosfile == "not open") { abort = true; } - else if (accnosfile == "not found") { accnosfile = ""; m->mothurOut("You must provide an accnos file."); m->mothurOutEndLine(); abort = true; } + else if (accnosfile == "not found") { + accnosfile = m->getAccnosFile(); + if (accnosfile != "") { m->mothurOut("Using " + accnosfile + " as input file for the accnos parameter."); m->mothurOutEndLine(); } + else { + m->mothurOut("You have no valid accnos file and accnos is required."); m->mothurOutEndLine(); + abort = true; + } + }else { m->setAccnosFile(accnosfile); } fastafile = validParameter.validFile(parameters, "fasta", true); - if (fastafile == "not open") { abort = true; } + if (fastafile == "not open") { fastafile = ""; abort = true; } else if (fastafile == "not found") { fastafile = ""; } - + else { m->setFastaFile(fastafile); } + namefile = validParameter.validFile(parameters, "name", true); - if (namefile == "not open") { abort = true; } + if (namefile == "not open") { namefile = ""; abort = true; } else if (namefile == "not found") { namefile = ""; } - + else { m->setNameFile(namefile); } + groupfile = validParameter.validFile(parameters, "group", true); if (groupfile == "not open") { abort = true; } - else if (groupfile == "not found") { groupfile = ""; } + else if (groupfile == "not found") { groupfile = ""; } + else { m->setGroupFile(groupfile); } alignfile = validParameter.validFile(parameters, "alignreport", true); if (alignfile == "not open") { abort = true; } @@ -126,11 +215,17 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option) { listfile = validParameter.validFile(parameters, "list", true); if (listfile == "not open") { abort = true; } else if (listfile == "not found") { listfile = ""; } + else { m->setListFile(listfile); } taxfile = validParameter.validFile(parameters, "taxonomy", true); if (taxfile == "not open") { abort = true; } else if (taxfile == "not found") { taxfile = ""; } - + else { m->setTaxonomyFile(taxfile); } + + qualfile = validParameter.validFile(parameters, "qfile", true); + if (qualfile == "not open") { abort = true; } + else if (qualfile == "not found") { qualfile = ""; } + else { m->setQualFile(qualfile); } string usedDups = "true"; string temp = validParameter.validFile(parameters, "dups", false); @@ -140,9 +235,12 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option) { } dups = m->isTrue(temp); - if ((fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == "") && (taxfile == "")) { m->mothurOut("You must provide at least one of the following: fasta, name, group, taxonomy, alignreport or list."); m->mothurOutEndLine(); abort = true; } + 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 ((usedDups != "") && (namefile == "")) { m->mothurOut("You may only use dups with the name option."); m->mothurOutEndLine(); abort = true; } + if ((fastafile != "") && (namefile == "")) { + vector files; files.push_back(fastafile); + parser.getNameFile(files); + } } } @@ -153,28 +251,10 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option) { } //********************************************************************************************************************** -void RemoveSeqsCommand::help(){ - try { - m->mothurOut("The remove.seqs command reads an .accnos file and at least one of the following file types: fasta, name, group, list, taxonomy or alignreport file.\n"); - m->mothurOut("It outputs a file containing the sequences NOT in the .accnos file.\n"); - m->mothurOut("The remove.seqs command parameters are accnos, fasta, name, group, list, taxonomy, alignreport and dups. You must provide accnos and at least one of the file parameters.\n"); - m->mothurOut("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"); - m->mothurOut("The remove.seqs command should be in the following format: remove.seqs(accnos=yourAccnos, fasta=yourFasta).\n"); - m->mothurOut("Example remove.seqs(accnos=amazon.accnos, fasta=amazon.fasta).\n"); - m->mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n\n"); - } - catch(exception& e) { - m->errorOut(e, "RemoveSeqsCommand", "help"); - exit(1); - } -} - -//********************************************************************************************************************** - int RemoveSeqsCommand::execute(){ try { - if (abort == true) { return 0; } + if (abort == true) { if (calledHelp) { return 0; } return 2; } //get names you want to keep readAccnos(); @@ -188,14 +268,47 @@ int RemoveSeqsCommand::execute(){ if (alignfile != "") { readAlign(); } if (listfile != "") { readList(); } if (taxfile != "") { readTax(); } + if (qualfile != "") { readQual(); } - if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } - + if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } + if (outputNames.size() != 0) { 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(); + + //set fasta file as new current fastafile + string current = ""; + itTypes = outputTypes.find("fasta"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setFastaFile(current); } + } + + itTypes = outputTypes.find("name"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setNameFile(current); } + } + + itTypes = outputTypes.find("group"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setGroupFile(current); } + } + + itTypes = outputTypes.find("list"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setListFile(current); } + } + + itTypes = outputTypes.find("taxonomy"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setTaxonomyFile(current); } + } + + itTypes = outputTypes.find("qfile"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setQualFile(current); } + } } return 0; @@ -222,9 +335,10 @@ int RemoveSeqsCommand::readFasta(){ string name; bool wroteSomething = false; + int removedCount = 0; while(!in.eof()){ - if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } Sequence currSeq(in); name = currSeq.getName(); @@ -235,7 +349,7 @@ int RemoveSeqsCommand::readFasta(){ wroteSomething = true; currSeq.printSequence(out); - } + }else { removedCount++; } } m->gobble(in); } @@ -243,7 +357,9 @@ int RemoveSeqsCommand::readFasta(){ out.close(); if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); } - outputNames.push_back(outputFileName); + outputTypes["fasta"].push_back(outputFileName); outputNames.push_back(outputFileName); + + m->mothurOut("Removed " + toString(removedCount) + " sequences from your fasta file."); m->mothurOutEndLine(); return 0; @@ -254,6 +370,74 @@ int RemoveSeqsCommand::readFasta(){ } } //********************************************************************************************************************** +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); + ofstream out; + m->openOutputFile(outputFileName, out); + + + ifstream in; + m->openInputFile(qualfile, in); + string name; + + bool wroteSomething = false; + int removedCount = 0; + + + while(!in.eof()){ + string saveName = ""; + string name = ""; + string scores = ""; + + in >> name; + + if (name.length() != 0) { + saveName = name.substr(1); + while (!in.eof()) { + char c = in.get(); + if (c == 10 || c == 13){ break; } + else { name += c; } + } + m->gobble(in); + } + + while(in){ + char letter= in.get(); + if(letter == '>'){ in.putback(letter); break; } + else{ scores += letter; } + } + + m->gobble(in); + + if (names.count(saveName) == 0) { + wroteSomething = true; + + out << name << endl << scores; + }else { removedCount++; } + + m->gobble(in); + } + in.close(); + out.close(); + + + if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); } + outputNames.push_back(outputFileName); outputTypes["qfile"].push_back(outputFileName); + + m->mothurOut("Removed " + toString(removedCount) + " sequences from your quality file."); m->mothurOutEndLine(); + + return 0; + + } + catch(exception& e) { + m->errorOut(e, "RemoveSeqsCommand", "readQual"); + exit(1); + } +} +//********************************************************************************************************************** int RemoveSeqsCommand::readList(){ try { string thisOutputDir = outputDir; @@ -267,8 +451,12 @@ int RemoveSeqsCommand::readList(){ m->openInputFile(listfile, in); bool wroteSomething = false; + int removedCount = 0; while(!in.eof()){ + + removedCount = 0; + //read in list vector ListVector list(in); @@ -278,7 +466,7 @@ int RemoveSeqsCommand::readList(){ //for each bin for (int i = 0; i < list.getNumBins(); i++) { - if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } //parse out names that are in accnos file string binnames = list.get(i); @@ -290,10 +478,12 @@ int RemoveSeqsCommand::readList(){ //if that name is in the .accnos file, add it if (names.count(name) == 0) { newNames += name + ","; } + else { removedCount++; } } //get last name if (names.count(binnames) == 0) { newNames += binnames + ","; } + else { removedCount++; } //if there are names in this bin add to new list if (newNames != "") { @@ -314,8 +504,10 @@ int RemoveSeqsCommand::readList(){ out.close(); if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); } - outputNames.push_back(outputFileName); - + outputTypes["list"].push_back(outputFileName); outputNames.push_back(outputFileName); + + m->mothurOut("Removed " + toString(removedCount) + " sequences from your list file."); m->mothurOutEndLine(); + return 0; } @@ -339,24 +531,17 @@ int RemoveSeqsCommand::readName(){ string name, firstCol, secondCol; bool wroteSomething = false; + int removedCount = 0; while(!in.eof()){ - if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } - - in >> firstCol; + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } + + in >> firstCol; m->gobble(in); in >> secondCol; - + vector parsedNames; - //parse second column saving each name - while (secondCol.find_first_of(',') != -1) { - name = secondCol.substr(0,secondCol.find_first_of(',')); - secondCol = secondCol.substr(secondCol.find_first_of(',')+1, secondCol.length()); - parsedNames.push_back(name); - } + m->splitAtComma(secondCol, parsedNames); - //get name after last , - parsedNames.push_back(secondCol); - vector validSecond; validSecond.clear(); for (int i = 0; i < parsedNames.size(); i++) { if (names.count(parsedNames[i]) == 0) { @@ -366,8 +551,10 @@ int RemoveSeqsCommand::readName(){ if ((dups) && (validSecond.size() != parsedNames.size())) { //if dups is true and we want to get rid of anyone, get rid of everyone for (int i = 0; i < parsedNames.size(); i++) { names.insert(parsedNames[i]); } + removedCount += parsedNames.size(); }else { - //if the name in the first column is in the set then print it and any other names in second column also in set + removedCount += parsedNames.size()-validSecond.size(); + //if the name in the first column is in the set then print it and any other names in second column also in set if (names.count(firstCol) == 0) { wroteSomething = true; @@ -398,10 +585,12 @@ int RemoveSeqsCommand::readName(){ } in.close(); out.close(); - + if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); } - outputNames.push_back(outputFileName); - + outputTypes["name"].push_back(outputFileName); outputNames.push_back(outputFileName); + + m->mothurOut("Removed " + toString(removedCount) + " sequences from your name file."); m->mothurOutEndLine(); + return 0; } catch(exception& e) { @@ -425,9 +614,10 @@ int RemoveSeqsCommand::readGroup(){ string name, group; bool wroteSomething = false; + int removedCount = 0; while(!in.eof()){ - if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } in >> name; //read from first column in >> group; //read from second column @@ -436,7 +626,7 @@ int RemoveSeqsCommand::readGroup(){ if (names.count(name) == 0) { wroteSomething = true; out << name << '\t' << group << endl; - } + }else { removedCount++; } m->gobble(in); } @@ -444,7 +634,10 @@ int RemoveSeqsCommand::readGroup(){ out.close(); if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); } - outputNames.push_back(outputFileName); + outputTypes["group"].push_back(outputFileName); outputNames.push_back(outputFileName); + + m->mothurOut("Removed " + toString(removedCount) + " sequences from your group file."); m->mothurOutEndLine(); + return 0; } @@ -467,9 +660,10 @@ int RemoveSeqsCommand::readTax(){ string name, tax; bool wroteSomething = false; + int removedCount = 0; while(!in.eof()){ - if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } in >> name; //read from first column in >> tax; //read from second column @@ -478,7 +672,7 @@ int RemoveSeqsCommand::readTax(){ if (names.count(name) == 0) { wroteSomething = true; out << name << '\t' << tax << endl; - } + }else { removedCount++; } m->gobble(in); } @@ -486,7 +680,9 @@ int RemoveSeqsCommand::readTax(){ out.close(); if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); } - outputNames.push_back(outputFileName); + outputTypes["taxonomy"].push_back(outputFileName); outputNames.push_back(outputFileName); + + m->mothurOut("Removed " + toString(removedCount) + " sequences from your taxonomy file."); m->mothurOutEndLine(); return 0; } @@ -511,6 +707,7 @@ int RemoveSeqsCommand::readAlign(){ string name, junk; bool wroteSomething = false; + int removedCount = 0; //read column headers for (int i = 0; i < 16; i++) { @@ -520,7 +717,7 @@ int RemoveSeqsCommand::readAlign(){ out << endl; while(!in.eof()){ - if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } in >> name; //read from first column @@ -538,6 +735,7 @@ int RemoveSeqsCommand::readAlign(){ out << endl; }else {//still read just don't do anything with it + removedCount++; //read rest for (int i = 0; i < 15; i++) { @@ -552,7 +750,10 @@ int RemoveSeqsCommand::readAlign(){ out.close(); if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); } - outputNames.push_back(outputFileName); + outputTypes["alignreport"].push_back(outputFileName); outputNames.push_back(outputFileName); + + m->mothurOut("Removed " + toString(removedCount) + " sequences from your alignreport file."); m->mothurOutEndLine(); + return 0;