X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=removeseqscommand.cpp;h=c7af108325390221bd0313e4ad2a733dfd2e90d3;hp=7e3b93918da6420a6a61c2943a779e89d52ea527;hb=1a20e24ee786195ab0e1cccd4f5aede7a88f3f4e;hpb=ca9ac1d80c62f57270b0dcd49410ebe08a8aecd6 diff --git a/removeseqscommand.cpp b/removeseqscommand.cpp index 7e3b939..c7af108 100644 --- a/removeseqscommand.cpp +++ b/removeseqscommand.cpp @@ -10,21 +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", "", "", "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); + 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); } @@ -39,13 +41,13 @@ 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"; - helpString += "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n\n"; + helpString += "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n"; return helpString; } catch(exception& e) { @@ -53,8 +55,28 @@ string 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 { @@ -68,6 +90,7 @@ RemoveSeqsCommand::RemoveSeqsCommand(){ outputTypes["alignreport"] = tempOutNames; outputTypes["list"] = tempOutNames; outputTypes["qfile"] = tempOutNames; + outputTypes["count"] = tempOutNames; } catch(exception& e) { m->errorOut(e, "RemoveSeqsCommand", "RemoveSeqsCommand"); @@ -81,6 +104,7 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option) { //allow user to run help if(option == "help") { help(); abort = true; calledHelp = true; } + else if(option == "citation") { citation(); abort = true; calledHelp = true;} else { vector myArray = setParameters(); @@ -105,6 +129,7 @@ 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 = ""; } @@ -177,6 +202,14 @@ 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; } + } } @@ -190,19 +223,22 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option) { 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; } @@ -211,15 +247,17 @@ 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); @@ -228,9 +266,28 @@ 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; } - + + 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); + } + } } } @@ -247,9 +304,15 @@ 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(); } @@ -259,11 +322,10 @@ 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++) { remove(outputNames[i].c_str()); } return 0; } - - m->mothurOut("Removed " + toString(names.size()) + " sequences."); m->mothurOutEndLine(); - + 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(); @@ -300,7 +362,12 @@ 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; @@ -317,7 +384,10 @@ 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); + 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); @@ -327,11 +397,18 @@ 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); + + 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 != "") { @@ -339,8 +416,8 @@ int RemoveSeqsCommand::readFasta(){ if (names.count(name) == 0) { wroteSomething = true; - currSeq.printSequence(out); - } + currSeq.printSequence(out); + }else { removedCount++; } } m->gobble(in); } @@ -350,6 +427,8 @@ int RemoveSeqsCommand::readFasta(){ 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; } @@ -363,7 +442,10 @@ 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); + 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); @@ -373,6 +455,7 @@ int RemoveSeqsCommand::readQual(){ string name; bool wroteSomething = false; + int removedCount = 0; while(!in.eof()){ @@ -386,7 +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); @@ -400,11 +483,16 @@ 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; out << name << endl << scores; - } + }else { removedCount++; } m->gobble(in); } @@ -415,6 +503,8 @@ int RemoveSeqsCommand::readQual(){ 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; } @@ -424,12 +514,75 @@ int RemoveSeqsCommand::readQual(){ } } //********************************************************************************************************************** +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) { + 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); - + 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); @@ -437,8 +590,12 @@ 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); @@ -448,7 +605,7 @@ 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); @@ -460,10 +617,12 @@ 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 != "") { @@ -485,7 +644,9 @@ int RemoveSeqsCommand::readList(){ 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; } @@ -499,8 +660,10 @@ 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); - + 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); @@ -509,10 +672,10 @@ 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; } + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } in >> firstCol; m->gobble(in); in >> secondCol; @@ -529,7 +692,9 @@ 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 { + 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) { @@ -550,6 +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] << ','; } @@ -565,6 +732,8 @@ int RemoveSeqsCommand::readName(){ 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) { @@ -578,8 +747,10 @@ 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); - + 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); @@ -588,9 +759,10 @@ 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 @@ -599,7 +771,7 @@ int RemoveSeqsCommand::readGroup(){ if (names.count(name) == 0) { wroteSomething = true; out << name << '\t' << group << endl; - } + }else { removedCount++; } m->gobble(in); } @@ -609,6 +781,9 @@ int RemoveSeqsCommand::readGroup(){ 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) { @@ -621,7 +796,10 @@ 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); + 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); @@ -630,18 +808,25 @@ 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 >> 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); } @@ -651,6 +836,8 @@ int RemoveSeqsCommand::readTax(){ 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) { @@ -664,7 +851,9 @@ int RemoveSeqsCommand::readAlign(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(alignfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(alignfile)) + "pick.align.report"; + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(alignfile)); + string outputFileName = getOutputFileName("alignreport", variables); ofstream out; m->openOutputFile(outputFileName, out); @@ -674,6 +863,7 @@ int RemoveSeqsCommand::readAlign(){ string name, junk; bool wroteSomething = false; + int removedCount = 0; //read column headers for (int i = 0; i < 16; i++) { @@ -683,9 +873,14 @@ 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 + + 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) { @@ -701,6 +896,7 @@ 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++) { @@ -717,6 +913,9 @@ int RemoveSeqsCommand::readAlign(){ 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); + m->mothurOut("Removed " + toString(removedCount) + " sequences from your alignreport file."); m->mothurOutEndLine(); + + return 0; } @@ -726,29 +925,5 @@ 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); - } -} - -//**********************************************************************************************************************