X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=removeseqscommand.cpp;h=81c42f6e426a2b59cb074a2d28cbed1c6e529c0b;hb=662c0b60d65f79f672ab199300b7ee4975233465;hp=0ab181b411738d38b769a0255baeaf5968308d35;hpb=c6e5f84783b39a558119835963dec3c4facb0154;p=mothur.git diff --git a/removeseqscommand.cpp b/removeseqscommand.cpp index 0ab181b..81c42f6 100644 --- a/removeseqscommand.cpp +++ b/removeseqscommand.cpp @@ -12,17 +12,69 @@ #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; calledHelp = true; + 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; + abort = false; calledHelp = false; //allow user to run help - if(option == "help") { help(); abort = true; } + if(option == "help") { help(); abort = true; calledHelp = true; } 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 +88,16 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option) { if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; } } + //initialize outputTypes + vector tempOutNames; + outputTypes["fasta"] = tempOutNames; + outputTypes["taxonomy"] = tempOutNames; + outputTypes["name"] = tempOutNames; + outputTypes["group"] = tempOutNames; + outputTypes["alignreport"] = tempOutNames; + outputTypes["list"] = tempOutNames; + outputTypes["qfile"] = tempOutNames; + //if the user changes the output directory command factory will send this info to us in the output parameter outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){ outputDir = ""; } @@ -99,6 +161,14 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option) { //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["taxonomy"] = inputDir + it->second; } } + + it = parameters.find("qfile"); + //user has given a template file + if(it != parameters.end()){ + path = m->hasPath(it->second); + //if the user has not given a path then, add inputdir. else leave path alone. + if (path == "") { parameters["qfile"] = inputDir + it->second; } + } } @@ -130,6 +200,10 @@ 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"; @@ -140,7 +214,7 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option) { } dups = m->isTrue(temp); - if ((fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == "") && (taxfile == "")) { m->mothurOut("You must provide at least one of the following: fasta, name, group, taxonomy, alignreport or list."); m->mothurOutEndLine(); abort = true; } + if ((fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == "") && (taxfile == "") && (qualfile == "")) { m->mothurOut("You must provide at least one of the following: fasta, name, group, taxonomy, quality, alignreport or list."); m->mothurOutEndLine(); abort = true; } if ((usedDups != "") && (namefile == "")) { m->mothurOut("You may only use dups with the name option."); m->mothurOutEndLine(); abort = true; } } @@ -155,9 +229,9 @@ 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 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"); @@ -174,7 +248,7 @@ void RemoveSeqsCommand::help(){ int RemoveSeqsCommand::execute(){ try { - if (abort == true) { return 0; } + if (abort == true) { if (calledHelp) { return 0; } return 2; } //get names you want to keep readAccnos(); @@ -188,9 +262,12 @@ int RemoveSeqsCommand::execute(){ if (alignfile != "") { readAlign(); } if (listfile != "") { readList(); } if (taxfile != "") { readTax(); } + if (qualfile != "") { readQual(); } if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } + m->mothurOut("Removed " + toString(names.size()) + " sequences."); m->mothurOutEndLine(); + if (outputNames.size() != 0) { m->mothurOutEndLine(); m->mothurOut("Output File Names: "); m->mothurOutEndLine(); @@ -243,7 +320,7 @@ int RemoveSeqsCommand::readFasta(){ out.close(); if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); } - outputNames.push_back(outputFileName); + outputTypes["fasta"].push_back(outputFileName); outputNames.push_back(outputFileName); return 0; @@ -254,6 +331,71 @@ 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 { string thisOutputDir = outputDir; @@ -314,7 +456,7 @@ int RemoveSeqsCommand::readList(){ out.close(); if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); } - outputNames.push_back(outputFileName); + outputTypes["list"].push_back(outputFileName); outputNames.push_back(outputFileName); return 0; @@ -343,7 +485,7 @@ int RemoveSeqsCommand::readName(){ while(!in.eof()){ 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; @@ -400,7 +542,7 @@ int RemoveSeqsCommand::readName(){ out.close(); if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); } - outputNames.push_back(outputFileName); + outputTypes["name"].push_back(outputFileName); outputNames.push_back(outputFileName); return 0; } @@ -444,7 +586,7 @@ int RemoveSeqsCommand::readGroup(){ out.close(); if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); } - outputNames.push_back(outputFileName); + outputTypes["group"].push_back(outputFileName); outputNames.push_back(outputFileName); return 0; } @@ -486,7 +628,7 @@ int RemoveSeqsCommand::readTax(){ out.close(); if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); } - outputNames.push_back(outputFileName); + outputTypes["taxonomy"].push_back(outputFileName); outputNames.push_back(outputFileName); return 0; } @@ -552,7 +694,7 @@ int RemoveSeqsCommand::readAlign(){ out.close(); if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); } - outputNames.push_back(outputFileName); + outputTypes["alignreport"].push_back(outputFileName); outputNames.push_back(outputFileName); return 0;