X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=removeseqscommand.cpp;h=c7af108325390221bd0313e4ad2a733dfd2e90d3;hp=a8f03e06b29c505d219a8a4f5770999586e182ae;hb=1a20e24ee786195ab0e1cccd4f5aede7a88f3f4e;hpb=315e38cf393c82be238da5b32574f225a020d25c diff --git a/removeseqscommand.cpp b/removeseqscommand.cpp index a8f03e0..c7af108 100644 --- a/removeseqscommand.cpp +++ b/removeseqscommand.cpp @@ -10,20 +10,104 @@ #include "removeseqscommand.h" #include "sequence.hpp" #include "listvector.hpp" +#include "counttable.h" //********************************************************************************************************************** - -RemoveSeqsCommand::RemoveSeqsCommand(string option){ +vector RemoveSeqsCommand::setParameters(){ + try { + 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); } + 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, 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, 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"; + 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); + } +} +//********************************************************************************************************************** +string RemoveSeqsCommand::getOutputPattern(string type) { + try { + string pattern = ""; + + 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 { - abort = false; + 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; + outputTypes["count"] = tempOutNames; + } + catch(exception& e) { + m->errorOut(e, "RemoveSeqsCommand", "RemoveSeqsCommand"); + exit(1); + } +} +//********************************************************************************************************************** +RemoveSeqsCommand::RemoveSeqsCommand(string option) { + try { + 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","outputdir","inputdir" }; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + vector myArray = setParameters(); OptionParser parser(option); map parameters = parser.getParameters(); @@ -36,6 +120,17 @@ 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; + 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 = ""; } @@ -47,7 +142,7 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option){ it = parameters.find("alignreport"); //user has given a template file if(it != parameters.end()){ - path = hasPath(it->second); + path = m->hasPath(it->second); //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["alignreport"] = inputDir + it->second; } } @@ -55,7 +150,7 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option){ it = parameters.find("fasta"); //user has given a template file if(it != parameters.end()){ - path = hasPath(it->second); + path = m->hasPath(it->second); //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["fasta"] = inputDir + it->second; } } @@ -63,7 +158,7 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option){ it = parameters.find("accnos"); //user has given a template file if(it != parameters.end()){ - path = hasPath(it->second); + path = m->hasPath(it->second); //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["accnos"] = inputDir + it->second; } } @@ -71,7 +166,7 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option){ it = parameters.find("list"); //user has given a template file if(it != parameters.end()){ - path = hasPath(it->second); + path = m->hasPath(it->second); //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["list"] = inputDir + it->second; } } @@ -79,7 +174,7 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option){ it = parameters.find("name"); //user has given a template file if(it != parameters.end()){ - path = hasPath(it->second); + path = m->hasPath(it->second); //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["name"] = inputDir + it->second; } } @@ -87,29 +182,63 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option){ it = parameters.find("group"); //user has given a template file if(it != parameters.end()){ - path = hasPath(it->second); + path = m->hasPath(it->second); //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["group"] = inputDir + it->second; } } + + it = parameters.find("taxonomy"); + //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["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; } + } + + 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; } + } } //check for required parameters accnosfile = validParameter.validFile(parameters, "accnos", true); if (accnosfile == "not open") { abort = true; } - else if (accnosfile == "not found") { accnosfile = ""; mothurOut("You must provide an accnos file."); 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; } @@ -118,80 +247,168 @@ 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); } - if ((fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == "")) { mothurOut("You must provide one of the following: fasta, name, group, alignreport or list."); mothurOutEndLine(); abort = true; } + taxfile = validParameter.validFile(parameters, "taxonomy", true); + if (taxfile == "not open") { abort = true; } + else if (taxfile == "not found") { taxfile = ""; } + else { m->setTaxonomyFile(taxfile); } - int okay = 2; - if (outputDir != "") { okay++; } + qualfile = validParameter.validFile(parameters, "qfile", true); + if (qualfile == "not open") { abort = true; } + else if (qualfile == "not found") { qualfile = ""; } + else { m->setQualFile(qualfile); } - if (parameters.size() > okay) { mothurOut("You may only enter one of the following: fasta, name, group, alignreport, or list."); mothurOutEndLine(); abort = true; } + string usedDups = "true"; + string temp = validParameter.validFile(parameters, "dups", false); + if (temp == "not found") { + if (namefile != "") { temp = "true"; } + else { temp = "false"; usedDups = ""; } + } + dups = m->isTrue(temp); + + 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); + } + } } } catch(exception& e) { - errorOut(e, "RemoveSeqsCommand", "RemoveSeqsCommand"); - exit(1); - } -} -//********************************************************************************************************************** - -void RemoveSeqsCommand::help(){ - try { - mothurOut("The remove.seqs command reads an .accnos file and one of the following file types: fasta, name, group, list or alignreport file.\n"); - mothurOut("It outputs a file containing the sequences NOT in the .accnos file.\n"); - mothurOut("The remove.seqs command parameters are accnos, fasta, name, group, list and alignreport. You must provide accnos and one of the other parameters.\n"); - mothurOut("The remove.seqs command should be in the following format: remove.seqs(accnos=yourAccnos, fasta=yourFasta).\n"); - mothurOut("Example remove.seqs(accnos=amazon.accnos, fasta=amazon.fasta).\n"); - mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n\n"); - } - catch(exception& e) { - errorOut(e, "RemoveSeqsCommand", "help"); + m->errorOut(e, "RemoveSeqsCommand", "RemoveSeqsCommand"); 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(); + 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(); } if (fastafile != "") { readFasta(); } - else if (namefile != "") { readName(); } - else if (groupfile != "") { readGroup(); } - else if (alignfile != "") { readAlign(); } - else if (listfile != "") { readList(); } + if (groupfile != "") { readGroup(); } + if (alignfile != "") { readAlign(); } + 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; } + + 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); } + } + + itTypes = outputTypes.find("count"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setCountTableFile(current); } + } + } return 0; } catch(exception& e) { - errorOut(e, "RemoveSeqsCommand", "execute"); + m->errorOut(e, "RemoveSeqsCommand", "execute"); exit(1); } } //********************************************************************************************************************** -void RemoveSeqsCommand::readFasta(){ +int RemoveSeqsCommand::readFasta(){ try { - if (outputDir == "") { outputDir += hasPath(fastafile); } - string outputFileName = getRootName(fastafile) + "pick" + getExtension(fastafile); + string thisOutputDir = outputDir; + if (outputDir == "") { thisOutputDir += m->hasPath(fastafile); } + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(fastafile)); + variables["[extension]"] = m->getExtension(fastafile); + string outputFileName = getOutputFileName("fasta", variables); + ofstream out; - openOutputFile(outputFileName, out); + m->openOutputFile(outputFileName, out); ifstream in; - openInputFile(fastafile, in); + m->openInputFile(fastafile, in); string name; bool wroteSomething = false; + int removedCount = 0; while(!in.eof()){ + 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 != "") { @@ -199,39 +416,186 @@ void RemoveSeqsCommand::readFasta(){ if (names.count(name) == 0) { wroteSomething = true; - currSeq.printSequence(out); - }else { names.erase(name); } + currSeq.printSequence(out); + }else { removedCount++; } } - gobble(in); + m->gobble(in); } in.close(); out.close(); - if (wroteSomething == false) { - mothurOut("Your file contains only sequences from the .accnos file."); mothurOutEndLine(); - remove(outputFileName.c_str()); + if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); } + outputTypes["fasta"].push_back(outputFileName); outputNames.push_back(outputFileName); + + m->mothurOut("Removed " + toString(removedCount) + " sequences from your fasta file."); m->mothurOutEndLine(); + + return 0; + + } + catch(exception& e) { + m->errorOut(e, "RemoveSeqsCommand", "readFasta"); + exit(1); + } +} +//********************************************************************************************************************** +int RemoveSeqsCommand::readQual(){ + try { + string thisOutputDir = outputDir; + if (outputDir == "") { thisOutputDir += m->hasPath(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); + + + 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 || c == -1){ 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 (!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; + + 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::readCount(){ + try { + + string thisOutputDir = outputDir; + if (outputDir == "") { thisOutputDir += m->hasPath(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); + + 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) { - errorOut(e, "RemoveSeqsCommand", "readFasta"); + m->errorOut(e, "RemoveSeqsCommand", "readCount"); exit(1); } } //********************************************************************************************************************** -void RemoveSeqsCommand::readList(){ +int RemoveSeqsCommand::readList(){ try { - if (outputDir == "") { outputDir += hasPath(listfile); } - string outputFileName = getRootName(listfile) + "pick" + getExtension(listfile); + string thisOutputDir = outputDir; + if (outputDir == "") { thisOutputDir += m->hasPath(listfile); } + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(listfile)); + variables["[extension]"] = m->getExtension(listfile); + string outputFileName = getOutputFileName("list", variables); ofstream out; - openOutputFile(outputFileName, out); + m->openOutputFile(outputFileName, out); ifstream in; - openInputFile(listfile, in); + m->openInputFile(listfile, in); bool wroteSomething = false; + int removedCount = 0; while(!in.eof()){ + + removedCount = 0; + //read in list vector ListVector list(in); @@ -241,6 +605,7 @@ void RemoveSeqsCommand::readList(){ //for each bin for (int i = 0; i < list.getNumBins(); i++) { + 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); @@ -252,13 +617,18 @@ void 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; } + if (names.count(binnames) == 0) { newNames += binnames + ","; } + else { removedCount++; } //if there are names in this bin add to new list - if (newNames != "") { newList.push_back(newNames); } + if (newNames != "") { + newNames = newNames.substr(0, newNames.length()-1); //rip off extra comma + newList.push_back(newNames); + } } //print new listvector @@ -267,54 +637,52 @@ void RemoveSeqsCommand::readList(){ newList.print(out); } - gobble(in); + m->gobble(in); } in.close(); out.close(); - if (wroteSomething == false) { - mothurOut("Your file contains only sequences from the .accnos file."); mothurOutEndLine(); - remove(outputFileName.c_str()); - } + if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); } + outputTypes["list"].push_back(outputFileName); outputNames.push_back(outputFileName); + + m->mothurOut("Removed " + toString(removedCount) + " sequences from your list file."); m->mothurOutEndLine(); + + return 0; } catch(exception& e) { - errorOut(e, "RemoveSeqsCommand", "readList"); + m->errorOut(e, "RemoveSeqsCommand", "readList"); exit(1); } } //********************************************************************************************************************** -void RemoveSeqsCommand::readName(){ +int RemoveSeqsCommand::readName(){ try { - if (outputDir == "") { outputDir += hasPath(namefile); } - string outputFileName = getRootName(namefile) + "pick" + getExtension(namefile); - + string thisOutputDir = outputDir; + if (outputDir == "") { thisOutputDir += m->hasPath(namefile); } + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(namefile)); + variables["[extension]"] = m->getExtension(namefile); + string outputFileName = getOutputFileName("name", variables); ofstream out; - openOutputFile(outputFileName, out); + m->openOutputFile(outputFileName, out); ifstream in; - openInputFile(namefile, in); + m->openInputFile(namefile, in); string name, firstCol, secondCol; bool wroteSomething = false; + int removedCount = 0; while(!in.eof()){ - - 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) { @@ -322,66 +690,80 @@ void RemoveSeqsCommand::readName(){ } } - //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; - - out << firstCol << '\t'; - - //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] << ','; } - out << validSecond[validSecond.size()-1] << endl; - - //make first name in set you come to first column and then add the remaining names to second column + 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 { - - //you want part of this row - if (validSecond.size() != 0) { - + 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; - out << validSecond[0] << '\t'; - + out << firstCol << '\t'; + //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] << ','; } out << validSecond[validSecond.size()-1] << endl; + + //make first name in set you come to first column and then add the remaining names to second column + }else { + + //you want part of this row + if (validSecond.size() != 0) { + + 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] << ','; } + out << validSecond[validSecond.size()-1] << endl; + } } } - - gobble(in); + m->gobble(in); } in.close(); out.close(); - if (wroteSomething == false) { - mothurOut("Your file contains only sequences from the .accnos file."); mothurOutEndLine(); - remove(outputFileName.c_str()); - } + if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); } + 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) { - errorOut(e, "RemoveSeqsCommand", "readName"); + m->errorOut(e, "RemoveSeqsCommand", "readName"); exit(1); } } //********************************************************************************************************************** -void RemoveSeqsCommand::readGroup(){ +int RemoveSeqsCommand::readGroup(){ try { - if (outputDir == "") { outputDir += hasPath(groupfile); } - string outputFileName = getRootName(groupfile) + "pick" + getExtension(groupfile); + string thisOutputDir = outputDir; + if (outputDir == "") { thisOutputDir += m->hasPath(groupfile); } + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(groupfile)); + variables["[extension]"] = m->getExtension(groupfile); + string outputFileName = getOutputFileName("group", variables); ofstream out; - openOutputFile(outputFileName, out); + m->openOutputFile(outputFileName, out); ifstream in; - openInputFile(groupfile, in); + m->openInputFile(groupfile, in); string name, group; bool wroteSomething = false; + int removedCount = 0; while(!in.eof()){ - + 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 @@ -389,39 +771,99 @@ void RemoveSeqsCommand::readGroup(){ if (names.count(name) == 0) { wroteSomething = true; out << name << '\t' << group << endl; - }else { names.erase(name); } + }else { removedCount++; } - gobble(in); + m->gobble(in); } in.close(); out.close(); - if (wroteSomething == false) { - mothurOut("Your file contains only sequences from the .accnos file."); mothurOutEndLine(); - remove(outputFileName.c_str()); - } + if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); } + outputTypes["group"].push_back(outputFileName); outputNames.push_back(outputFileName); + + m->mothurOut("Removed " + toString(removedCount) + " sequences from your group file."); m->mothurOutEndLine(); + + return 0; } catch(exception& e) { - errorOut(e, "RemoveSeqsCommand", "readGroup"); + m->errorOut(e, "RemoveSeqsCommand", "readGroup"); exit(1); } } +//********************************************************************************************************************** +int RemoveSeqsCommand::readTax(){ + try { + string thisOutputDir = outputDir; + if (outputDir == "") { thisOutputDir += m->hasPath(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); + ifstream in; + m->openInputFile(taxfile, in); + string name, tax; + + bool wroteSomething = false; + int removedCount = 0; + + while(!in.eof()){ + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } + + 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++; } + + m->gobble(in); + } + in.close(); + out.close(); + + if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); } + outputTypes["taxonomy"].push_back(outputFileName); outputNames.push_back(outputFileName); + + m->mothurOut("Removed " + toString(removedCount) + " sequences from your taxonomy file."); m->mothurOutEndLine(); + + return 0; + } + catch(exception& e) { + m->errorOut(e, "RemoveSeqsCommand", "readTax"); + exit(1); + } +} //********************************************************************************************************************** //alignreport file has a column header line then all other lines contain 16 columns. we just want the first column since that contains the name -void RemoveSeqsCommand::readAlign(){ +int RemoveSeqsCommand::readAlign(){ try { - if (outputDir == "") { outputDir += hasPath(alignfile); } - string outputFileName = getRootName(getRootName(alignfile)) + "pick.align.report"; + string thisOutputDir = outputDir; + if (outputDir == "") { thisOutputDir += m->hasPath(alignfile); } + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(alignfile)); + string outputFileName = getOutputFileName("alignreport", variables); + ofstream out; - openOutputFile(outputFileName, out); + m->openOutputFile(outputFileName, out); ifstream in; - openInputFile(alignfile, in); + m->openInputFile(alignfile, in); string name, junk; bool wroteSomething = false; + int removedCount = 0; //read column headers for (int i = 0; i < 16; i++) { @@ -431,8 +873,14 @@ void RemoveSeqsCommand::readAlign(){ out << endl; while(!in.eof()){ - + 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) { @@ -448,7 +896,7 @@ void RemoveSeqsCommand::readAlign(){ out << endl; }else {//still read just don't do anything with it - names.erase(name); + removedCount++; //read rest for (int i = 0; i < 15; i++) { @@ -457,46 +905,25 @@ void RemoveSeqsCommand::readAlign(){ } } - gobble(in); + m->gobble(in); } in.close(); out.close(); - if (wroteSomething == false) { - mothurOut("Your file contains only sequences from the .accnos file."); mothurOutEndLine(); - remove(outputFileName.c_str()); - } + if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); } + outputTypes["alignreport"].push_back(outputFileName); outputNames.push_back(outputFileName); - } - catch(exception& e) { - errorOut(e, "RemoveSeqsCommand", "readAlign"); - exit(1); - } -} -//********************************************************************************************************************** -void RemoveSeqsCommand::readAccnos(){ - try { + m->mothurOut("Removed " + toString(removedCount) + " sequences from your alignreport file."); m->mothurOutEndLine(); + - ifstream in; - openInputFile(accnosfile, in); - string name; + return 0; - while(!in.eof()){ - in >> name; - - names.insert(name); - - gobble(in); - } - in.close(); - } catch(exception& e) { - errorOut(e, "RemoveSeqsCommand", "readAccnos"); + m->errorOut(e, "RemoveSeqsCommand", "readAlign"); exit(1); } } - //**********************************************************************************************************************