X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=removeseqscommand.cpp;h=f1804ed8b826d00b4993a708804733335bb1b194;hb=134a9c1275862a6b3ea10a2c0f11965c0a535854;hp=07e946b78eb8d7d56c7d09a91fd2fb90fc8564a5;hpb=17a6a53298a907c005fa93fb82af9e533adcda09;p=mothur.git diff --git a/removeseqscommand.cpp b/removeseqscommand.cpp index 07e946b..f1804ed 100644 --- a/removeseqscommand.cpp +++ b/removeseqscommand.cpp @@ -12,7 +12,59 @@ #include "listvector.hpp" //********************************************************************************************************************** - +vector RemoveSeqsCommand::getValidParameters(){ + try { + string Array[] = {"fasta","name", "group", "alignreport", "accnos", "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; + } + 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 +74,7 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option) { else { //valid paramters for this command - string Array[] = {"fasta","name", "group", "alignreport", "accnos", "list","outputdir","inputdir", "dups" }; + string Array[] = {"fasta","name", "group", "alignreport", "accnos", "list","taxonomy","outputdir","inputdir", "dups" }; vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); OptionParser parser(option); @@ -36,6 +88,15 @@ 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; + //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 +108,7 @@ 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 +116,7 @@ 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 +124,7 @@ 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 +132,7 @@ 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 +140,7 @@ 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; } } @@ -87,10 +148,18 @@ 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; } } + + 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; } + } } @@ -119,19 +188,22 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option) { if (listfile == "not open") { abort = true; } else if (listfile == "not found") { listfile = ""; } - string usedDups = "true"; - string temp = validParameter.validFile(parameters, "dups", false); if (temp == "not found") { temp = "false"; usedDups = ""; } - dups = isTrue(temp); - - if ((fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == "")) { m->mothurOut("You must provide one of the following: fasta, name, group, alignreport or list."); 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++; } - if (usedDups != "") { okay++; } + string usedDups = "true"; + string temp = validParameter.validFile(parameters, "dups", false); + if (temp == "not found") { + if (namefile != "") { temp = "true"; } + else { temp = "false"; usedDups = ""; } + } + dups = m->isTrue(temp); - if ((usedDups != "") && (namefile == "")) { m->mothurOut("You may only use dups with the name option."); m->mothurOutEndLine(); abort = true; } + 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 (parameters.size() > okay) { m->mothurOut("You may only enter one of the following: fasta, name, group, 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; } } } @@ -144,10 +216,10 @@ RemoveSeqsCommand::RemoveSeqsCommand(string option) { void RemoveSeqsCommand::help(){ try { - m->mothurOut("The remove.seqs command reads an .accnos file and one of the following file types: fasta, name, group, list 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 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, alignreport and dups. You must provide accnos and 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, 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"); @@ -171,11 +243,12 @@ int RemoveSeqsCommand::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) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } @@ -198,13 +271,15 @@ int RemoveSeqsCommand::execute(){ //********************************************************************************************************************** int RemoveSeqsCommand::readFasta(){ try { - if (outputDir == "") { outputDir += hasPath(fastafile); } - 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; @@ -221,17 +296,15 @@ int RemoveSeqsCommand::readFasta(){ wroteSomething = true; currSeq.printSequence(out); - }else { names.erase(name); } + } } - 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); return 0; @@ -244,13 +317,15 @@ int RemoveSeqsCommand::readFasta(){ //********************************************************************************************************************** int RemoveSeqsCommand::readList(){ try { - if (outputDir == "") { outputDir += hasPath(listfile); } - string outputFileName = getRootName(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; @@ -294,16 +369,14 @@ 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); + return 0; } @@ -315,27 +388,23 @@ int RemoveSeqsCommand::readList(){ //********************************************************************************************************************** int RemoveSeqsCommand::readName(){ try { - if (outputDir == "") { outputDir += hasPath(namefile); } - string outputFileName = getRootName(namefile) + "pick" + getExtension(namefile); - string outputFileName2 = getRootName(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; @@ -344,7 +413,6 @@ 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 , @@ -357,9 +425,8 @@ 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) { @@ -388,21 +455,14 @@ 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); + return 0; } catch(exception& e) { @@ -414,13 +474,15 @@ int RemoveSeqsCommand::readName(){ //********************************************************************************************************************** int RemoveSeqsCommand::readGroup(){ try { - if (outputDir == "") { outputDir += hasPath(groupfile); } - 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; @@ -435,17 +497,15 @@ int RemoveSeqsCommand::readGroup(){ if (names.count(name) == 0) { wroteSomething = true; out << name << '\t' << group << endl; - }else { names.erase(name); } + } - 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); return 0; } @@ -454,18 +514,61 @@ int RemoveSeqsCommand::readGroup(){ exit(1); } } +//********************************************************************************************************************** +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); + 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 contains only sequences from the .accnos file."); m->mothurOutEndLine(); } + outputTypes["taxonomy"].push_back(outputFileName); + + return 0; + } + catch(exception& e) { + m->errorOut(e, "RemoveSeqsCommand", "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 RemoveSeqsCommand::readAlign(){ try { - if (outputDir == "") { outputDir += hasPath(alignfile); } - 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; @@ -496,7 +599,6 @@ int RemoveSeqsCommand::readAlign(){ out << endl; }else {//still read just don't do anything with it - names.erase(name); //read rest for (int i = 0; i < 15; i++) { @@ -505,15 +607,13 @@ 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); return 0; @@ -528,7 +628,7 @@ void RemoveSeqsCommand::readAccnos(){ try { ifstream in; - openInputFile(accnosfile, in); + m->openInputFile(accnosfile, in); string name; while(!in.eof()){ @@ -536,7 +636,7 @@ void RemoveSeqsCommand::readAccnos(){ names.insert(name); - gobble(in); + m->gobble(in); } in.close();