X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=getseqscommand.cpp;h=9f2b5060fcaa715f9a2fd3fc484ba585d6322da9;hb=fa08e82ec2dd48f73d051c210dad54a403308949;hp=315417a30586d290b2a692e04b2e0afacb1e6fb3;hpb=648ec37228eb16075ace911dd5a5773cdfe683da;p=mothur.git diff --git a/getseqscommand.cpp b/getseqscommand.cpp index 315417a..9f2b506 100644 --- a/getseqscommand.cpp +++ b/getseqscommand.cpp @@ -9,35 +9,186 @@ #include "getseqscommand.h" #include "sequence.hpp" +#include "listvector.hpp" //********************************************************************************************************************** - -GetSeqsCommand::GetSeqsCommand(string option){ +vector GetSeqsCommand::getValidParameters(){ + try { + string Array[] = {"fasta","name", "group", "qfile","alignreport", "accnos", "accnos2","dups", "list","taxonomy","outputdir","inputdir"}; + vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + return myArray; + } + catch(exception& e) { + m->errorOut(e, "GetSeqsCommand", "getValidParameters"); + exit(1); + } +} +//********************************************************************************************************************** +GetSeqsCommand::GetSeqsCommand(){ + 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; + outputTypes["accnosreport"] = tempOutNames; + } + catch(exception& e) { + m->errorOut(e, "GetSeqsCommand", "GetSeqsCommand"); + exit(1); + } +} +//********************************************************************************************************************** +vector GetSeqsCommand::getRequiredParameters(){ + try { + string Array[] = {"accnos"}; + vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + return myArray; + } + catch(exception& e) { + m->errorOut(e, "GetSeqsCommand", "getRequiredParameters"); + exit(1); + } +} +//********************************************************************************************************************** +vector GetSeqsCommand::getRequiredFiles(){ + try { + vector myArray; + return myArray; + } + catch(exception& e) { + m->errorOut(e, "GetSeqsCommand", "getRequiredFiles"); + exit(1); + } +} +//********************************************************************************************************************** +GetSeqsCommand::GetSeqsCommand(string option) { try { abort = false; - + //allow user to run help if(option == "help") { help(); abort = true; } else { //valid paramters for this command - string Array[] = {"fasta","name", "group", "alignreport", "accnos" }; + string Array[] = {"fasta","name", "group", "alignreport", "qfile", "accnos", "accnos2","dups", "list","taxonomy","outputdir","inputdir"}; vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); OptionParser parser(option); map parameters = parser.getParameters(); ValidParameters validParameter; + map::iterator it; //check to make sure all parameters are valid for command - for (map::iterator it = parameters.begin(); it != parameters.end(); it++) { + for (it = parameters.begin(); it != parameters.end(); it++) { 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["accnosreport"] = 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 = ""; } + + //if the user changes the input directory command factory will send this info to us in the output parameter + string inputDir = validParameter.validFile(parameters, "inputdir", false); + if (inputDir == "not found"){ inputDir = ""; } + else { + string path; + it = parameters.find("alignreport"); + //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["alignreport"] = inputDir + it->second; } + } + + it = parameters.find("fasta"); + //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["fasta"] = inputDir + it->second; } + } + + it = parameters.find("accnos"); + //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["accnos"] = inputDir + it->second; } + } + + it = parameters.find("accnos2"); + //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["accnos2"] = inputDir + it->second; } + } + + it = parameters.find("list"); + //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["list"] = inputDir + it->second; } + } + + it = parameters.find("name"); + //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["name"] = inputDir + it->second; } + } + + it = parameters.find("group"); + //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["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; } + } + } + + //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->mothurOut("You must provide an accnos file."); m->mothurOutEndLine(); abort = true; } + + if (accnosfile2 == "not found") { accnosfile2 = ""; } fastafile = validParameter.validFile(parameters, "fasta", true); if (fastafile == "not open") { abort = true; } @@ -55,14 +206,31 @@ GetSeqsCommand::GetSeqsCommand(string option){ if (alignfile == "not open") { abort = true; } else if (alignfile == "not found") { alignfile = ""; } - if ((fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "")) { mothurOut("You must provide one of the following: fasta, name, group, alignreport."); mothurOutEndLine(); abort = true; } + listfile = validParameter.validFile(parameters, "list", true); + if (listfile == "not open") { abort = true; } + else if (listfile == "not found") { listfile = ""; } + + taxfile = validParameter.validFile(parameters, "taxonomy", true); + if (taxfile == "not open") { abort = true; } + else if (taxfile == "not found") { taxfile = ""; } - if (parameters.size() > 2) { mothurOut("You may only enter one of the following: fasta, name, group, alignreport."); mothurOutEndLine(); abort = true; } + 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 = m->isTrue(temp); + + if ((fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == "") && (taxfile == "") && (qualfile == "") && (accnosfile2 == "")) { m->mothurOut("You must provide one of the following: fasta, name, group, alignreport, taxonomy, quality or listfile."); m->mothurOutEndLine(); abort = true; } + + if ((usedDups != "") && (namefile == "")) { m->mothurOut("You may only use dups with the name option."); m->mothurOutEndLine(); abort = true; } + } } catch(exception& e) { - errorOut(e, "GetSeqsCommand", "GetSeqsCommand"); + m->errorOut(e, "GetSeqsCommand", "GetSeqsCommand"); exit(1); } } @@ -70,15 +238,16 @@ GetSeqsCommand::GetSeqsCommand(string option){ void GetSeqsCommand::help(){ try { - mothurOut("The get.seqs command reads an .accnos file and one of the following file types: fasta, name, group or alignreport file.\n"); - mothurOut("It outputs a file containing only the sequences in the .accnos file.\n"); - mothurOut("The get.seqs command parameters are accnos, fasta, name, group and alignreport. You must provide accnos and one of the other parameters.\n"); - mothurOut("The get.seqs command should be in the following format: get.seqs(accnos=yourAccnos, fasta=yourFasta).\n"); - mothurOut("Example get.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"); + m->mothurOut("The get.seqs command reads an .accnos file and any of the following file types: fasta, name, group, list, taxonomy, quality or alignreport file.\n"); + m->mothurOut("It outputs a file containing only the sequences in the .accnos file.\n"); + m->mothurOut("The get.seqs command parameters are accnos, fasta, name, group, list, taxonomy, qfile, alignreport and dups. You must provide accnos and at least one of the other parameters.\n"); + m->mothurOut("The dups parameter allows you to add the entire line from a name file if you add any name from the line. default=false. \n"); + m->mothurOut("The get.seqs command should be in the following format: get.seqs(accnos=yourAccnos, fasta=yourFasta).\n"); + m->mothurOut("Example get.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"); } catch(exception& e) { - errorOut(e, "GetSeqsCommand", "help"); + m->errorOut(e, "GetSeqsCommand", "help"); exit(1); } } @@ -93,84 +262,249 @@ int GetSeqsCommand::execute(){ //get names you want to keep readAccnos(); + if (m->control_pressed) { return 0; } + //read through the correct file and output lines you want to keep - if (fastafile != "") { readFasta(); } - else if (namefile != "") { readName(); } - else if (groupfile != "") { readGroup(); } - else if (alignfile != "") { readAlign(); } + if (namefile != "") { readName(); } + if (fastafile != "") { readFasta(); } + if (groupfile != "") { readGroup(); } + if (alignfile != "") { readAlign(); } + if (listfile != "") { readList(); } + if (taxfile != "") { readTax(); } + if (qualfile != "") { readQual(); } + if (accnosfile2 != "") { compareAccnos(); } + + if (m->control_pressed) { outputTypes.clear(); for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } + + m->mothurOut("Selected " + toString(names.size()) + " sequences."); m->mothurOutEndLine(); + + 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(); + } return 0; } catch(exception& e) { - errorOut(e, "GetSeqsCommand", "execute"); + m->errorOut(e, "GetSeqsCommand", "execute"); exit(1); } } //********************************************************************************************************************** -void GetSeqsCommand::readFasta(){ +int GetSeqsCommand::readFasta(){ try { - string outputFileName = getRootName(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; while(!in.eof()){ + + if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } + Sequence currSeq(in); name = currSeq.getName(); if (name != "") { //if this name is in the accnos file - if (names.count(name) == 1) { + if (names.count(name) != 0) { wroteSomething = true; currSeq.printSequence(out); - - names.erase(name); } } - gobble(in); + m->gobble(in); } in.close(); out.close(); - if (wroteSomething == false) { - mothurOut("Your file does not contain any sequence from the .accnos file."); mothurOutEndLine(); - remove(outputFileName.c_str()); - } + + if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); } + outputNames.push_back(outputFileName); outputTypes["fasta"].push_back(outputFileName); + + return 0; } catch(exception& e) { - errorOut(e, "GetSeqsCommand", "readFasta"); + m->errorOut(e, "GetSeqsCommand", "readFasta"); + exit(1); + } +} +//********************************************************************************************************************** +int GetSeqsCommand::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 does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); } + outputNames.push_back(outputFileName); outputTypes["qfile"].push_back(outputFileName); + + return 0; + + } + catch(exception& e) { + m->errorOut(e, "GetSeqsCommand", "readQual"); exit(1); } } +//********************************************************************************************************************** +int GetSeqsCommand::readList(){ + try { + string thisOutputDir = outputDir; + if (outputDir == "") { thisOutputDir += m->hasPath(listfile); } + string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(listfile)) + "pick" + m->getExtension(listfile); + ofstream out; + m->openOutputFile(outputFileName, out); + + ifstream in; + m->openInputFile(listfile, in); + + bool wroteSomething = false; + + while(!in.eof()){ + + if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } + + //read in list vector + ListVector list(in); + + //make a new list vector + ListVector newList; + newList.setLabel(list.getLabel()); + + //for each bin + for (int i = 0; i < list.getNumBins(); i++) { + + //parse out names that are in accnos file + string binnames = list.get(i); + + string newNames = ""; + while (binnames.find_first_of(',') != -1) { + string name = binnames.substr(0,binnames.find_first_of(',')); + binnames = binnames.substr(binnames.find_first_of(',')+1, binnames.length()); + + //if that name is in the .accnos file, add it + if (names.count(name) != 0) { newNames += name + ","; } + } + + //get last name + if (names.count(binnames) != 0) { newNames += binnames + ","; } + + //if there are names in this bin add to new list + if (newNames != "") { + newNames = newNames.substr(0, newNames.length()-1); //rip off extra comma + newList.push_back(newNames); + } + } + + //print new listvector + if (newList.getNumBins() != 0) { + wroteSomething = true; + newList.print(out); + } + + m->gobble(in); + } + in.close(); + out.close(); + + if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); } + outputNames.push_back(outputFileName); outputTypes["list"].push_back(outputFileName); + + return 0; + } + catch(exception& e) { + m->errorOut(e, "GetSeqsCommand", "readList"); + exit(1); + } +} //********************************************************************************************************************** -void GetSeqsCommand::readName(){ +int GetSeqsCommand::readName(){ try { - - string outputFileName = getRootName(namefile) + "pick" + getExtension(namefile); + string thisOutputDir = outputDir; + if (outputDir == "") { thisOutputDir += m->hasPath(namefile); } + string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(namefile)) + "pick" + m->getExtension(namefile); 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()); return 0; } in >> firstCol; - in >> secondCol; + in >> secondCol; + + string hold = ""; + if (dups) { hold = secondCol; } vector parsedNames; //parse second column saving each name @@ -185,111 +519,165 @@ void GetSeqsCommand::readName(){ vector validSecond; for (int i = 0; i < parsedNames.size(); i++) { - if (names.count(parsedNames[i]) == 1) { + if (names.count(parsedNames[i]) != 0) { validSecond.push_back(parsedNames[i]); } } - - //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) == 1) { - + if ((dups) && (validSecond.size() != 0)) { //dups = true and we want to add someone, then add everyone + for (int i = 0; i < parsedNames.size(); i++) { names.insert(parsedNames[i]); } + out << firstCol << '\t' << hold << endl; 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 }else { - //you want part of this row - if (validSecond.size() != 0) { + //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'; + + //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 does not contain any sequence from the .accnos file."); mothurOutEndLine(); - remove(outputFileName.c_str()); - } + if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); } + outputNames.push_back(outputFileName); outputTypes["name"].push_back(outputFileName); + + return 0; } catch(exception& e) { - errorOut(e, "GetSeqsCommand", "readName"); + m->errorOut(e, "GetSeqsCommand", "readName"); exit(1); } } //********************************************************************************************************************** -void GetSeqsCommand::readGroup(){ +int GetSeqsCommand::readGroup(){ try { - - string outputFileName = getRootName(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; while(!in.eof()){ + if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } + + in >> name; //read from first column in >> group; //read from second column //if this name is in the accnos file - if (names.count(name) == 1) { + if (names.count(name) != 0) { wroteSomething = true; out << name << '\t' << group << endl; - - names.erase(name); } - gobble(in); + m->gobble(in); } in.close(); out.close(); - if (wroteSomething == false) { - mothurOut("Your file does not contain any sequence from the .accnos file."); mothurOutEndLine(); - remove(outputFileName.c_str()); - } + if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); } + outputNames.push_back(outputFileName); outputTypes["group"].push_back(outputFileName); + + return 0; } catch(exception& e) { - errorOut(e, "GetSeqsCommand", "readGroup"); + m->errorOut(e, "GetSeqsCommand", "readGroup"); exit(1); } } +//********************************************************************************************************************** +int GetSeqsCommand::readTax(){ + try { + string thisOutputDir = outputDir; + if (outputDir == "") { thisOutputDir += m->hasPath(taxfile); } + string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(taxfile)) + "pick" + m->getExtension(taxfile); + ofstream out; + m->openOutputFile(outputFileName, out); + + ifstream in; + m->openInputFile(taxfile, in); + string name, tax; + + bool wroteSomething = false; + + while(!in.eof()){ + + if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } + + in >> name; //read from first column + in >> tax; //read from second column + + //if this name is in the accnos file + if (names.count(name) != 0) { + wroteSomething = true; + + out << name << '\t' << tax << endl; + } + + m->gobble(in); + } + in.close(); + out.close(); + + if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); } + outputNames.push_back(outputFileName); outputTypes["taxonomy"].push_back(outputFileName); + + return 0; + } + catch(exception& e) { + m->errorOut(e, "GetSeqsCommand", "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 GetSeqsCommand::readAlign(){ +int GetSeqsCommand::readAlign(){ try { - string outputFileName = getRootName(getRootName(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; @@ -302,11 +690,14 @@ void GetSeqsCommand::readAlign(){ out << endl; while(!in.eof()){ + + if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } + in >> name; //read from first column //if this name is in the accnos file - if (names.count(name) == 1) { + if (names.count(name) != 0) { wroteSomething = true; out << name << '\t'; @@ -318,8 +709,6 @@ void GetSeqsCommand::readAlign(){ } out << endl; - names.erase(name); - }else {//still read just don't do anything with it //read rest for (int i = 0; i < 15; i++) { @@ -328,29 +717,29 @@ void GetSeqsCommand::readAlign(){ } } - gobble(in); + m->gobble(in); } in.close(); out.close(); - if (wroteSomething == false) { - mothurOut("Your file does not contain any sequence from the .accnos file."); mothurOutEndLine(); - remove(outputFileName.c_str()); - } + if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); } + outputNames.push_back(outputFileName); outputTypes["alignreport"].push_back(outputFileName); + + return 0; } catch(exception& e) { - errorOut(e, "GetSeqsCommand", "readAlign"); + m->errorOut(e, "GetSeqsCommand", "readAlign"); exit(1); } } //********************************************************************************************************************** -void GetSeqsCommand::readAccnos(){ +int GetSeqsCommand::readAccnos(){ try { ifstream in; - openInputFile(accnosfile, in); + m->openInputFile(accnosfile, in); string name; while(!in.eof()){ @@ -358,16 +747,115 @@ void GetSeqsCommand::readAccnos(){ names.insert(name); - gobble(in); + m->gobble(in); + } + in.close(); + + return 0; + + } + catch(exception& e) { + m->errorOut(e, "GetSeqsCommand", "readAccnos"); + exit(1); + } +} +//********************************************************************************************************************** + +int GetSeqsCommand::compareAccnos(){ + try { + + string thisOutputDir = outputDir; + if (outputDir == "") { thisOutputDir += m->hasPath(accnosfile); } + string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(accnosfile)) + "accnos.report"; + ofstream out; + m->openOutputFile(outputFileName, out); + + ifstream in; + m->openInputFile(accnosfile2, in); + string name; + + set namesAccnos2; + set namesDups; + set namesAccnos = names; + + map nameCount; + + if (namefile != "") { + ifstream inName; + m->openInputFile(namefile, inName); + + + while(!inName.eof()){ + + if (m->control_pressed) { inName.close(); return 0; } + + string thisname, repnames; + + inName >> thisname; m->gobble(inName); //read from first column + inName >> repnames; //read from second column + + int num = m->getNumNames(repnames); + nameCount[thisname] = num; + + m->gobble(inName); + } + inName.close(); + } + + while(!in.eof()){ + in >> name; + + if (namesAccnos.count(name) == 0){ //name unique to accnos2 + namesAccnos2.insert(name); + }else { //you are in both so erase + namesAccnos.erase(name); + namesDups.insert(name); + } + + m->gobble(in); + } + in.close(); + + out << "Names in both files : " + toString(namesDups.size()) << endl; + m->mothurOut("Names in both files : " + toString(namesDups.size())); m->mothurOutEndLine(); + + for (set::iterator it = namesDups.begin(); it != namesDups.end(); it++) { + out << (*it); + if (namefile != "") { out << '\t' << nameCount[(*it)]; } + out << endl; + } + + out << "Names unique to " + accnosfile + " : " + toString(namesAccnos.size()) << endl; + m->mothurOut("Names unique to " + accnosfile + " : " + toString(namesAccnos.size())); m->mothurOutEndLine(); + + for (set::iterator it = namesAccnos.begin(); it != namesAccnos.end(); it++) { + out << (*it); + if (namefile != "") { out << '\t' << nameCount[(*it)]; } + out << endl; + } + + out << "Names unique to " + accnosfile2 + " : " + toString(namesAccnos2.size()) << endl; + m->mothurOut("Names unique to " + accnosfile2 + " : " + toString(namesAccnos2.size())); m->mothurOutEndLine(); + + for (set::iterator it = namesAccnos2.begin(); it != namesAccnos2.end(); it++) { + out << (*it); + if (namefile != "") { out << '\t' << nameCount[(*it)]; } + out << endl; } - in.close(); + out.close(); + + outputNames.push_back(outputFileName); outputTypes["accnosreport"].push_back(outputFileName); + + return 0; + } catch(exception& e) { - errorOut(e, "GetSeqsCommand", "readAccnos"); + m->errorOut(e, "GetSeqsCommand", "readAccnos"); exit(1); } } + //**********************************************************************************************************************