X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=removeseqscommand.cpp;h=0d53c1a95ed5b968d0a8281f1f3d612d7d4c2047;hb=f509429e06e545bde69c97cacc0eb436775bd329;hp=7e3b93918da6420a6a61c2943a779e89d52ea527;hpb=ca9ac1d80c62f57270b0dcd49410ebe08a8aecd6;p=mothur.git diff --git a/removeseqscommand.cpp b/removeseqscommand.cpp index 7e3b939..0d53c1a 100644 --- a/removeseqscommand.cpp +++ b/removeseqscommand.cpp @@ -45,7 +45,7 @@ string RemoveSeqsCommand::getHelpString(){ 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) { @@ -53,7 +53,32 @@ 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 { 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(){ @@ -81,6 +106,7 @@ 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(); @@ -190,19 +216,22 @@ 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 +240,17 @@ 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); @@ -231,6 +262,10 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option) { 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); + } } } @@ -247,7 +282,7 @@ 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; } @@ -260,10 +295,8 @@ int RemoveSeqsCommand::execute(){ 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; } - - 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(); @@ -317,7 +350,7 @@ 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); @@ -327,9 +360,10 @@ 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(); @@ -340,7 +374,7 @@ int RemoveSeqsCommand::readFasta(){ wroteSomething = true; currSeq.printSequence(out); - } + }else { removedCount++; } } m->gobble(in); } @@ -350,6 +384,8 @@ 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 +399,7 @@ 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); @@ -373,6 +409,7 @@ int RemoveSeqsCommand::readQual(){ string name; bool wroteSomething = false; + int removedCount = 0; while(!in.eof()){ @@ -404,7 +441,7 @@ int RemoveSeqsCommand::readQual(){ wroteSomething = true; out << name << endl << scores; - } + }else { removedCount++; } m->gobble(in); } @@ -415,6 +452,8 @@ 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; } @@ -428,8 +467,7 @@ 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); @@ -437,8 +475,12 @@ 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 +490,7 @@ 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 +502,12 @@ 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 +529,9 @@ 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 +545,7 @@ 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); @@ -509,10 +554,10 @@ 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 +574,9 @@ 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) { @@ -565,6 +612,8 @@ 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 +627,7 @@ 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); @@ -588,9 +636,10 @@ 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 +648,7 @@ int RemoveSeqsCommand::readGroup(){ if (names.count(name) == 0) { wroteSomething = true; out << name << '\t' << group << endl; - } + }else { removedCount++; } m->gobble(in); } @@ -609,6 +658,9 @@ 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 +673,7 @@ 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); @@ -630,9 +682,10 @@ 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 @@ -641,7 +694,7 @@ int RemoveSeqsCommand::readTax(){ if (names.count(name) == 0) { wroteSomething = true; out << name << '\t' << tax << endl; - } + }else { removedCount++; } m->gobble(in); } @@ -651,6 +704,8 @@ 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 +719,7 @@ 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); @@ -674,6 +729,7 @@ int RemoveSeqsCommand::readAlign(){ string name, junk; bool wroteSomething = false; + int removedCount = 0; //read column headers for (int i = 0; i < 16; i++) { @@ -683,7 +739,7 @@ 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 @@ -701,6 +757,7 @@ 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 +774,9 @@ 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 +786,5 @@ 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); - } -} - -//**********************************************************************************************************************