X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=removeseqscommand.cpp;h=384a360353abd1a801e80f1e580054d17deac67d;hb=89f19f9c6ab89c2f6c7c6921a328ae87bce6f8e3;hp=da6bc44297d474e75d9866c69ff3d790ae92052a;hpb=14edc148cb299c5624f72bb681375b704aa74f43;p=mothur.git diff --git a/removeseqscommand.cpp b/removeseqscommand.cpp index da6bc44..384a360 100644 --- a/removeseqscommand.cpp +++ b/removeseqscommand.cpp @@ -12,7 +12,60 @@ #include "listvector.hpp" //********************************************************************************************************************** - +vector RemoveSeqsCommand::getValidParameters(){ + try { + string Array[] = {"fasta","name", "group", "alignreport", "accnos", "qfile","list","taxonomy","outputdir","inputdir", "dups" }; + vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + return myArray; + } + catch(exception& e) { + m->errorOut(e, "RemoveSeqsCommand", "getValidParameters"); + exit(1); + } +} +//********************************************************************************************************************** +RemoveSeqsCommand::RemoveSeqsCommand(){ + try { + 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; + } + catch(exception& e) { + m->errorOut(e, "RemoveSeqsCommand", "RemoveSeqsCommand"); + exit(1); + } +} +//********************************************************************************************************************** +vector RemoveSeqsCommand::getRequiredParameters(){ + try { + string Array[] = {"accnos"}; + vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + return myArray; + } + catch(exception& e) { + m->errorOut(e, "RemoveSeqsCommand", "getRequiredParameters"); + exit(1); + } +} +//********************************************************************************************************************** +vector RemoveSeqsCommand::getRequiredFiles(){ + try { + vector myArray; + return myArray; + } + catch(exception& e) { + m->errorOut(e, "RemoveSeqsCommand", "getRequiredFiles"); + exit(1); + } +} +//********************************************************************************************************************** RemoveSeqsCommand::RemoveSeqsCommand(string option) { try { abort = false; @@ -22,7 +75,7 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option) { else { //valid paramters for this command - string Array[] = {"fasta","name", "group", "alignreport", "accnos", "list","taxonomy","outputdir","inputdir", "dups" }; + string Array[] = {"fasta","name", "group", "alignreport", "accnos", "qfile", "list","taxonomy","outputdir","inputdir", "dups" }; vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); OptionParser parser(option); @@ -36,6 +89,16 @@ 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 = ""; } @@ -47,7 +110,7 @@ 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 +118,7 @@ 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 +126,7 @@ 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 +134,7 @@ 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 +142,7 @@ 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; } } @@ -87,7 +150,7 @@ 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; } } @@ -95,10 +158,18 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option) { it = parameters.find("taxonomy"); //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["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; } + } } @@ -130,13 +201,21 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option) { taxfile = validParameter.validFile(parameters, "taxonomy", true); if (taxfile == "not open") { abort = true; } else if (taxfile == "not found") { taxfile = ""; } + + qualfile = validParameter.validFile(parameters, "qfile", true); + if (qualfile == "not open") { abort = true; } + else if (qualfile == "not found") { qualfile = ""; } string usedDups = "true"; - string temp = validParameter.validFile(parameters, "dups", false); if (temp == "not found") { temp = "false"; usedDups = ""; } - dups = isTrue(temp); + string temp = validParameter.validFile(parameters, "dups", false); + if (temp == "not found") { + if (namefile != "") { temp = "true"; } + else { temp = "false"; usedDups = ""; } + } + 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; } } @@ -151,10 +230,10 @@ 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("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"); 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=false. If dups=true, then remove.seqs outputs a new .accnos file containing all the sequences removed. \n"); + m->mothurOut("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"); + 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"); @@ -178,12 +257,13 @@ int RemoveSeqsCommand::execute(){ if (m->control_pressed) { return 0; } //read through the correct file and output lines you want to keep - if (fastafile != "") { readFasta(); } if (namefile != "") { readName(); } + if (fastafile != "") { readFasta(); } if (groupfile != "") { readGroup(); } 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; } @@ -206,13 +286,15 @@ int RemoveSeqsCommand::execute(){ //********************************************************************************************************************** int RemoveSeqsCommand::readFasta(){ try { - if (outputDir == "") { outputDir += hasPath(fastafile); } - string outputFileName = outputDir + getRootName(getSimpleName(fastafile)) + "pick" + getExtension(fastafile); + string thisOutputDir = outputDir; + if (outputDir == "") { thisOutputDir += m->hasPath(fastafile); } + string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(fastafile)) + "pick" + m->getExtension(fastafile); + ofstream out; - openOutputFile(outputFileName, out); + m->openOutputFile(outputFileName, out); ifstream in; - openInputFile(fastafile, in); + m->openInputFile(fastafile, in); string name; bool wroteSomething = false; @@ -231,15 +313,13 @@ int RemoveSeqsCommand::readFasta(){ currSeq.printSequence(out); } } - gobble(in); + m->gobble(in); } in.close(); out.close(); - if (wroteSomething == false) { - m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); - remove(outputFileName.c_str()); - }else { outputNames.push_back(outputFileName); } + 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); return 0; @@ -250,15 +330,82 @@ 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; + + + 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; + } + + 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); + + return 0; + + } + catch(exception& e) { + m->errorOut(e, "RemoveSeqsCommand", "readQual"); + exit(1); + } +} +//********************************************************************************************************************** int RemoveSeqsCommand::readList(){ try { - if (outputDir == "") { outputDir += hasPath(listfile); } - string outputFileName = outputDir + getRootName(getSimpleName(listfile)) + "pick" + getExtension(listfile); + string thisOutputDir = outputDir; + if (outputDir == "") { thisOutputDir += m->hasPath(listfile); } + string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(listfile)) + "pick" + m->getExtension(listfile); + ofstream out; - openOutputFile(outputFileName, out); + m->openOutputFile(outputFileName, out); ifstream in; - openInputFile(listfile, in); + m->openInputFile(listfile, in); bool wroteSomething = false; @@ -302,16 +449,14 @@ int RemoveSeqsCommand::readList(){ newList.print(out); } - gobble(in); + m->gobble(in); } in.close(); out.close(); - if (wroteSomething == false) { - m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); - remove(outputFileName.c_str()); - }else { outputNames.push_back(outputFileName); } - + 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); + return 0; } @@ -323,27 +468,23 @@ int RemoveSeqsCommand::readList(){ //********************************************************************************************************************** int RemoveSeqsCommand::readName(){ try { - if (outputDir == "") { outputDir += hasPath(namefile); } - string outputFileName = outputDir + getRootName(getSimpleName(namefile)) + "pick" + getExtension(namefile); - string outputFileName2 = outputDir + getRootName(getSimpleName(namefile)) + "dups.accnos"; + string thisOutputDir = outputDir; + if (outputDir == "") { thisOutputDir += m->hasPath(namefile); } + string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(namefile)) + "pick" + m->getExtension(namefile); - ofstream out2; - if (dups) { openOutputFile(outputFileName2, out2); } - bool wroteDups = false; - 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; while(!in.eof()){ - if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); if (dups) { out2.close(); remove(outputFileName2.c_str()); } return 0; } + if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } - in >> firstCol; + in >> firstCol; m->gobble(in); in >> secondCol; vector parsedNames; @@ -352,7 +493,6 @@ int RemoveSeqsCommand::readName(){ name = secondCol.substr(0,secondCol.find_first_of(',')); secondCol = secondCol.substr(secondCol.find_first_of(',')+1, secondCol.length()); parsedNames.push_back(name); - } //get name after last , @@ -365,9 +505,8 @@ int RemoveSeqsCommand::readName(){ } } - if ((dups) && (validSecond.size() != parsedNames.size())) { - wroteDups = true; - for (int i = 0; i < parsedNames.size(); i++) { out2 << parsedNames[i] << endl; } + 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]); } }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 if (names.count(firstCol) == 0) { @@ -396,21 +535,14 @@ int RemoveSeqsCommand::readName(){ } } } - gobble(in); + m->gobble(in); } in.close(); out.close(); - - if (dups) { out2.close(); } - if (wroteDups == false) { - remove(outputFileName2.c_str()); - }else { outputNames.push_back(outputFileName2); } - - if (wroteSomething == false) { - m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); - remove(outputFileName.c_str()); - }else { outputNames.push_back(outputFileName); } - + + 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); + return 0; } catch(exception& e) { @@ -422,13 +554,15 @@ int RemoveSeqsCommand::readName(){ //********************************************************************************************************************** int RemoveSeqsCommand::readGroup(){ try { - if (outputDir == "") { outputDir += hasPath(groupfile); } - string outputFileName = outputDir + getRootName(getSimpleName(groupfile)) + "pick" + getExtension(groupfile); + string thisOutputDir = outputDir; + if (outputDir == "") { thisOutputDir += m->hasPath(groupfile); } + string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(groupfile)) + "pick" + m->getExtension(groupfile); + ofstream out; - openOutputFile(outputFileName, out); + m->openOutputFile(outputFileName, out); ifstream in; - openInputFile(groupfile, in); + m->openInputFile(groupfile, in); string name, group; bool wroteSomething = false; @@ -445,15 +579,13 @@ int RemoveSeqsCommand::readGroup(){ out << name << '\t' << group << endl; } - gobble(in); + m->gobble(in); } in.close(); out.close(); - if (wroteSomething == false) { - m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); - remove(outputFileName.c_str()); - }else { outputNames.push_back(outputFileName); } + 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); return 0; } @@ -465,13 +597,14 @@ int RemoveSeqsCommand::readGroup(){ //********************************************************************************************************************** int RemoveSeqsCommand::readTax(){ try { - if (outputDir == "") { outputDir += hasPath(taxfile); } - string outputFileName = outputDir + getRootName(getSimpleName(taxfile)) + "pick" + getExtension(taxfile); + string thisOutputDir = outputDir; + if (outputDir == "") { thisOutputDir += m->hasPath(taxfile); } + string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(taxfile)) + "pick" + m->getExtension(taxfile); ofstream out; - openOutputFile(outputFileName, out); + m->openOutputFile(outputFileName, out); ifstream in; - openInputFile(taxfile, in); + m->openInputFile(taxfile, in); string name, tax; bool wroteSomething = false; @@ -488,15 +621,13 @@ int RemoveSeqsCommand::readTax(){ out << name << '\t' << tax << endl; } - gobble(in); + m->gobble(in); } in.close(); out.close(); - if (wroteSomething == false) { - m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); - remove(outputFileName.c_str()); - }else { outputNames.push_back(outputFileName); } + 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); return 0; } @@ -509,13 +640,15 @@ int RemoveSeqsCommand::readTax(){ //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 int RemoveSeqsCommand::readAlign(){ try { - if (outputDir == "") { outputDir += hasPath(alignfile); } - string outputFileName = outputDir + getRootName(getSimpleName(alignfile)) + "pick.align.report"; + string thisOutputDir = outputDir; + if (outputDir == "") { thisOutputDir += m->hasPath(alignfile); } + string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(alignfile)) + "pick.align.report"; + ofstream out; - openOutputFile(outputFileName, out); + m->openOutputFile(outputFileName, out); ifstream in; - openInputFile(alignfile, in); + m->openInputFile(alignfile, in); string name, junk; bool wroteSomething = false; @@ -554,15 +687,13 @@ int RemoveSeqsCommand::readAlign(){ } } - gobble(in); + m->gobble(in); } in.close(); out.close(); - if (wroteSomething == false) { - m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); - remove(outputFileName.c_str()); - }else { outputNames.push_back(outputFileName); } + 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); return 0; @@ -577,7 +708,7 @@ void RemoveSeqsCommand::readAccnos(){ try { ifstream in; - openInputFile(accnosfile, in); + m->openInputFile(accnosfile, in); string name; while(!in.eof()){ @@ -585,7 +716,7 @@ void RemoveSeqsCommand::readAccnos(){ names.insert(name); - gobble(in); + m->gobble(in); } in.close();