X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=getseqscommand.cpp;h=e7226ceca0b1e959040fbea6d78818ba23731a6e;hb=260ae19c36cb11a53ddc5a75b5e507f8dd8b31d6;hp=f40c89b3fb3eff837729bc203055d11ef1a3c5a5;hpb=17a6a53298a907c005fa93fb82af9e533adcda09;p=mothur.git diff --git a/getseqscommand.cpp b/getseqscommand.cpp index f40c89b..e7226ce 100644 --- a/getseqscommand.cpp +++ b/getseqscommand.cpp @@ -22,7 +22,7 @@ GetSeqsCommand::GetSeqsCommand(string option) { else { //valid paramters for this command - string Array[] = {"fasta","name", "group", "alignreport", "accnos", "list","outputdir","inputdir"}; + string Array[] = {"fasta","name", "group", "alignreport", "accnos", "dups", "list","taxonomy","outputdir","inputdir"}; vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); OptionParser parser(option); @@ -47,7 +47,7 @@ GetSeqsCommand::GetSeqsCommand(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 +55,7 @@ GetSeqsCommand::GetSeqsCommand(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 +63,7 @@ GetSeqsCommand::GetSeqsCommand(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 +71,7 @@ GetSeqsCommand::GetSeqsCommand(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 +79,7 @@ GetSeqsCommand::GetSeqsCommand(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; } } @@ -87,10 +87,18 @@ GetSeqsCommand::GetSeqsCommand(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; } } + + 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; } + } } @@ -119,12 +127,18 @@ GetSeqsCommand::GetSeqsCommand(string option) { if (listfile == "not open") { abort = true; } else if (listfile == "not found") { listfile = ""; } - if ((fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == "")) { m->mothurOut("You must provide one of the following: fasta, name, group, alignreport or listfile."); m->mothurOutEndLine(); abort = true; } + taxfile = validParameter.validFile(parameters, "taxonomy", true); + if (taxfile == "not open") { abort = true; } + else if (taxfile == "not found") { taxfile = ""; } - int okay = 2; - if (outputDir != "") { okay++; } + string usedDups = "true"; + string temp = validParameter.validFile(parameters, "dups", false); if (temp == "not found") { temp = "false"; usedDups = ""; } + dups = m->isTrue(temp); - if (parameters.size() > okay) { m->mothurOut("You may only enter one of the following: fasta, name, group, alignreport or listfile."); m->mothurOutEndLine(); abort = true; } + if ((fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == "") && (taxfile == "")) { m->mothurOut("You must provide one of the following: fasta, name, group, alignreport, taxonomy or listfile."); m->mothurOutEndLine(); abort = true; } + + if ((usedDups != "") && (namefile == "")) { m->mothurOut("You may only use dups with the name option."); m->mothurOutEndLine(); abort = true; } + } } @@ -137,9 +151,10 @@ GetSeqsCommand::GetSeqsCommand(string option) { void GetSeqsCommand::help(){ try { - m->mothurOut("The get.seqs command reads an .accnos file and one of the following file types: fasta, name, group, list or alignreport file.\n"); + m->mothurOut("The get.seqs command reads an .accnos file and any of the following file types: fasta, name, group, list, taxonomy 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 and alignreport. You must provide accnos and one of the other parameters.\n"); + m->mothurOut("The get.seqs command parameters are accnos, fasta, name, group, list, taxonomy, 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"); @@ -163,13 +178,14 @@ int GetSeqsCommand::execute(){ if (m->control_pressed) { return 0; } //read through the correct file and output lines you want to keep + if (namefile != "") { readName(); } if (fastafile != "") { readFasta(); } - else if (namefile != "") { readName(); } - else if (groupfile != "") { readGroup(); } - else if (alignfile != "") { readAlign(); } - else if (listfile != "") { readList(); } + if (groupfile != "") { readGroup(); } + if (alignfile != "") { readAlign(); } + if (listfile != "") { readList(); } + if (taxfile != "") { readTax(); } - if (m->control_pressed) { return 0; } + if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } if (outputNames.size() != 0) { m->mothurOutEndLine(); @@ -190,14 +206,14 @@ int GetSeqsCommand::execute(){ //********************************************************************************************************************** int GetSeqsCommand::readFasta(){ try { - if (outputDir == "") { outputDir += hasPath(fastafile); } - string outputFileName = outputDir + getRootName(getSimpleName(fastafile)) + "pick" + getExtension(fastafile); + if (outputDir == "") { outputDir += m->hasPath(fastafile); } + string outputFileName = outputDir + 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; @@ -211,23 +227,19 @@ int GetSeqsCommand::readFasta(){ 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) { - m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); - remove(outputFileName.c_str()); - }else { outputNames.push_back(outputFileName); } + if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); } + outputNames.push_back(outputFileName); return 0; @@ -240,13 +252,13 @@ int GetSeqsCommand::readFasta(){ //********************************************************************************************************************** int GetSeqsCommand::readList(){ try { - if (outputDir == "") { outputDir += hasPath(listfile); } - string outputFileName = outputDir + getRootName(getSimpleName(listfile)) + "pick" + getExtension(listfile); + if (outputDir == "") { outputDir += m->hasPath(listfile); } + string outputFileName = outputDir + 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; @@ -273,11 +285,11 @@ int GetSeqsCommand::readList(){ binnames = binnames.substr(binnames.find_first_of(',')+1, binnames.length()); //if that name is in the .accnos file, add it - if (names.count(name) == 1) { newNames += name + ","; } + if (names.count(name) != 0) { newNames += name + ","; } } //get last name - if (names.count(binnames) == 1) { newNames += binnames + ","; } + if (names.count(binnames) != 0) { newNames += binnames + ","; } //if there are names in this bin add to new list if (newNames != "") { @@ -292,15 +304,13 @@ int GetSeqsCommand::readList(){ newList.print(out); } - gobble(in); + 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(); - remove(outputFileName.c_str()); - }else { outputNames.push_back(outputFileName); } + if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); } + outputNames.push_back(outputFileName); return 0; @@ -313,14 +323,14 @@ int GetSeqsCommand::readList(){ //********************************************************************************************************************** int GetSeqsCommand::readName(){ try { - if (outputDir == "") { outputDir += hasPath(namefile); } - string outputFileName = outputDir + getRootName(getSimpleName(namefile)) + "pick" + getExtension(namefile); + if (outputDir == "") { outputDir += m->hasPath(namefile); } + string outputFileName = outputDir + 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; @@ -331,7 +341,10 @@ int GetSeqsCommand::readName(){ 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 @@ -346,48 +359,50 @@ int 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) { - m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); - remove(outputFileName.c_str()); - }else { outputNames.push_back(outputFileName); } + if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); } + outputNames.push_back(outputFileName); return 0; @@ -401,14 +416,14 @@ int GetSeqsCommand::readName(){ //********************************************************************************************************************** int GetSeqsCommand::readGroup(){ try { - if (outputDir == "") { outputDir += hasPath(groupfile); } - string outputFileName = outputDir + getRootName(getSimpleName(groupfile)) + "pick" + getExtension(groupfile); + if (outputDir == "") { outputDir += m->hasPath(groupfile); } + string outputFileName = outputDir + 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; @@ -422,23 +437,19 @@ int GetSeqsCommand::readGroup(){ 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) { - m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); - remove(outputFileName.c_str()); - }else { outputNames.push_back(outputFileName); } + if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); } + outputNames.push_back(outputFileName); return 0; @@ -448,19 +459,62 @@ int GetSeqsCommand::readGroup(){ exit(1); } } +//********************************************************************************************************************** +int GetSeqsCommand::readTax(){ + try { + if (outputDir == "") { outputDir += m->hasPath(taxfile); } + string outputFileName = outputDir + 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); + + 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 int GetSeqsCommand::readAlign(){ try { - if (outputDir == "") { outputDir += hasPath(alignfile); } - string outputFileName = outputDir + getRootName(getSimpleName(alignfile)) + "pick.align.report"; + if (outputDir == "") { outputDir += m->hasPath(alignfile); } + string outputFileName = outputDir + 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; @@ -480,7 +534,7 @@ int GetSeqsCommand::readAlign(){ 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'; @@ -492,8 +546,6 @@ int 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++) { @@ -502,15 +554,13 @@ int GetSeqsCommand::readAlign(){ } } - gobble(in); + 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(); - remove(outputFileName.c_str()); - }else { outputNames.push_back(outputFileName); } + if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); } + outputNames.push_back(outputFileName); return 0; @@ -526,7 +576,7 @@ int GetSeqsCommand::readAccnos(){ try { ifstream in; - openInputFile(accnosfile, in); + m->openInputFile(accnosfile, in); string name; while(!in.eof()){ @@ -534,7 +584,7 @@ int GetSeqsCommand::readAccnos(){ names.insert(name); - gobble(in); + m->gobble(in); } in.close();