X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=getseqscommand.cpp;h=9bf188db3d25fa4ac16b82973a2802c3b1e6ad75;hb=5cbb9328400eabc6689da26738aceee394666dfa;hp=68d0d2b4e4a8f9addeb39d4ee853d12aef61592f;hpb=348de0f8b17d84ede77081dcf67bd6ef43496677;p=mothur.git diff --git a/getseqscommand.cpp b/getseqscommand.cpp index 68d0d2b..9bf188d 100644 --- a/getseqscommand.cpp +++ b/getseqscommand.cpp @@ -12,21 +12,54 @@ #include "listvector.hpp" //********************************************************************************************************************** -vector GetSeqsCommand::getValidParameters(){ +vector GetSeqsCommand::setParameters(){ try { - string Array[] = {"fasta","name", "group", "qfile","alignreport", "accnos", "accnos2","dups", "list","taxonomy","outputdir","inputdir"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pfasta); + CommandParameter pname("name", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pname); + CommandParameter pgroup("group", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pgroup); + CommandParameter plist("list", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(plist); + CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(ptaxonomy); + CommandParameter palignreport("alignreport", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(palignreport); + CommandParameter pqfile("qfile", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pqfile); + CommandParameter paccnos("accnos", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(paccnos); + CommandParameter pdups("dups", "Boolean", "", "T", "", "", "",false,false); parameters.push_back(pdups); + CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir); + CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir); + CommandParameter paccnos2("accnos2", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(paccnos2); + + vector myArray; + for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); } return myArray; } catch(exception& e) { - m->errorOut(e, "GetSeqsCommand", "getValidParameters"); + m->errorOut(e, "GetSeqsCommand", "setParameters"); + exit(1); + } +} +//********************************************************************************************************************** +string GetSeqsCommand::getHelpString(){ + try { + string helpString = ""; + helpString += "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"; + helpString += "It outputs a file containing only the sequences in the .accnos file.\n"; + helpString += "The get.seqs command parameters are accnos, fasta, name, group, list, taxonomy, qfile, alignreport and dups. You must provide accnos unless you have a valid current accnos file, and at least one of the other parameters.\n"; + helpString += "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"; + helpString += "The get.seqs command should be in the following format: get.seqs(accnos=yourAccnos, fasta=yourFasta).\n"; + helpString += "Example get.seqs(accnos=amazon.accnos, fasta=amazon.fasta).\n"; + helpString += "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n"; + return helpString; + } + catch(exception& e) { + m->errorOut(e, "GetSeqsCommand", "getHelpString"); exit(1); } } + //********************************************************************************************************************** GetSeqsCommand::GetSeqsCommand(){ try { - abort = true; calledHelp = true; + abort = true; calledHelp = true; + setParameters(); vector tempOutNames; outputTypes["fasta"] = tempOutNames; outputTypes["taxonomy"] = tempOutNames; @@ -43,40 +76,16 @@ GetSeqsCommand::GetSeqsCommand(){ } } //********************************************************************************************************************** -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; calledHelp = false; //allow user to run help if(option == "help") { help(); abort = true; calledHelp = true; } + else if(option == "citation") { citation(); abort = true; calledHelp = true;} else { - //valid paramters for this command - string Array[] = {"fasta","name", "group", "alignreport", "qfile", "accnos", "accnos2","dups", "list","taxonomy","outputdir","inputdir"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + vector myArray = setParameters(); OptionParser parser(option); map parameters = parser.getParameters(); @@ -185,21 +194,31 @@ GetSeqsCommand::GetSeqsCommand(string option) { //check for required parameters accnosfile = validParameter.validFile(parameters, "accnos", true); if (accnosfile == "not open") { abort = true; } - else if (accnosfile == "not found") { accnosfile = ""; m->mothurOut("You must provide an accnos file."); m->mothurOutEndLine(); abort = true; } + else if (accnosfile == "not found") { + accnosfile = m->getAccnosFile(); + if (accnosfile != "") { m->mothurOut("Using " + accnosfile + " as input file for the accnos parameter."); m->mothurOutEndLine(); } + else { + m->mothurOut("You have no valid accnos file and accnos is required."); m->mothurOutEndLine(); + abort = true; + } + }else { m->setAccnosFile(accnosfile); } if (accnosfile2 == "not found") { accnosfile2 = ""; } fastafile = validParameter.validFile(parameters, "fasta", true); - if (fastafile == "not open") { abort = true; } - else if (fastafile == "not found") { fastafile = ""; } + if (fastafile == "not open") { fastafile = ""; abort = true; } + else if (fastafile == "not found") { fastafile = ""; } + else { m->setFastaFile(fastafile); } namefile = validParameter.validFile(parameters, "name", true); - if (namefile == "not open") { abort = true; } + if (namefile == "not open") { namefile = ""; abort = true; } else if (namefile == "not found") { namefile = ""; } + else { m->setNameFile(namefile); } groupfile = validParameter.validFile(parameters, "group", true); if (groupfile == "not open") { abort = true; } else if (groupfile == "not found") { groupfile = ""; } + else { m->setGroupFile(groupfile); } alignfile = validParameter.validFile(parameters, "alignreport", true); if (alignfile == "not open") { abort = true; } @@ -208,23 +227,33 @@ GetSeqsCommand::GetSeqsCommand(string option) { listfile = validParameter.validFile(parameters, "list", true); if (listfile == "not open") { abort = true; } else if (listfile == "not found") { listfile = ""; } + else { m->setListFile(listfile); } taxfile = validParameter.validFile(parameters, "taxonomy", true); - if (taxfile == "not open") { abort = true; } + if (taxfile == "not open") { taxfile = ""; abort = true; } else if (taxfile == "not found") { taxfile = ""; } + else { m->setTaxonomyFile(taxfile); } qualfile = validParameter.validFile(parameters, "qfile", true); if (qualfile == "not open") { abort = true; } else if (qualfile == "not found") { qualfile = ""; } + else { m->setQualFile(qualfile); } + + accnosfile2 = validParameter.validFile(parameters, "accnos2", true); + if (accnosfile2 == "not open") { abort = true; } + else if (accnosfile2 == "not found") { accnosfile2 = ""; } + string usedDups = "true"; - string temp = validParameter.validFile(parameters, "dups", false); if (temp == "not found") { temp = "false"; usedDups = ""; } + string temp = validParameter.validFile(parameters, "dups", false); if (temp == "not found") { temp = "true"; 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; } - + if ((namefile == "") && ((fastafile != "") || (taxfile != ""))){ + vector files; files.push_back(fastafile); files.push_back(taxfile); + parser.getNameFile(files); + } } } @@ -235,24 +264,6 @@ GetSeqsCommand::GetSeqsCommand(string option) { } //********************************************************************************************************************** -void GetSeqsCommand::help(){ - try { - 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) { - m->errorOut(e, "GetSeqsCommand", "help"); - exit(1); - } -} - -//********************************************************************************************************************** - int GetSeqsCommand::execute(){ try { @@ -273,9 +284,8 @@ int GetSeqsCommand::execute(){ 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; } + if (m->control_pressed) { outputTypes.clear(); for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } - m->mothurOut("Selected " + toString(names.size()) + " sequences."); m->mothurOutEndLine(); if (outputNames.size() != 0) { m->mothurOutEndLine(); @@ -341,10 +351,11 @@ int GetSeqsCommand::readFasta(){ string name; bool wroteSomething = false; + int selectedCount = 0; while(!in.eof()){ - if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } Sequence currSeq(in); name = currSeq.getName(); @@ -355,6 +366,7 @@ int GetSeqsCommand::readFasta(){ wroteSomething = true; currSeq.printSequence(out); + selectedCount++; } } m->gobble(in); @@ -366,6 +378,8 @@ int GetSeqsCommand::readFasta(){ 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); + m->mothurOut("Selected " + toString(selectedCount) + " sequences from your fasta file."); m->mothurOutEndLine(); + return 0; } @@ -389,6 +403,7 @@ int GetSeqsCommand::readQual(){ string name; bool wroteSomething = false; + int selectedCount = 0; while(!in.eof()){ @@ -420,6 +435,7 @@ int GetSeqsCommand::readQual(){ wroteSomething = true; out << name << endl << scores; + selectedCount++; } m->gobble(in); @@ -431,6 +447,9 @@ int GetSeqsCommand::readQual(){ 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); + m->mothurOut("Selected " + toString(selectedCount) + " sequences from your quality file."); m->mothurOutEndLine(); + + return 0; } @@ -452,10 +471,13 @@ int GetSeqsCommand::readList(){ m->openInputFile(listfile, in); bool wroteSomething = false; + int selectedCount = 0; while(!in.eof()){ - if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } + selectedCount = 0; + + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } //read in list vector ListVector list(in); @@ -476,11 +498,11 @@ 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) != 0) { newNames += name + ","; } + if (names.count(name) != 0) { newNames += name + ","; selectedCount++; } } //get last name - if (names.count(binnames) != 0) { newNames += binnames + ","; } + if (names.count(binnames) != 0) { newNames += binnames + ","; selectedCount++; } //if there are names in this bin add to new list if (newNames != "") { @@ -503,6 +525,8 @@ int GetSeqsCommand::readList(){ 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); + m->mothurOut("Selected " + toString(selectedCount) + " sequences from your list file."); m->mothurOutEndLine(); + return 0; } @@ -526,11 +550,11 @@ int GetSeqsCommand::readName(){ string name, firstCol, secondCol; bool wroteSomething = false; - + int selectedCount = 0; while(!in.eof()){ - if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } in >> firstCol; in >> secondCol; @@ -539,15 +563,7 @@ int GetSeqsCommand::readName(){ if (dups) { hold = secondCol; } vector parsedNames; - //parse second column saving each name - while (secondCol.find_first_of(',') != -1) { - 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 , - parsedNames.push_back(secondCol); + m->splitAtComma(secondCol, parsedNames); vector validSecond; for (int i = 0; i < parsedNames.size(); i++) { @@ -560,7 +576,10 @@ int GetSeqsCommand::readName(){ for (int i = 0; i < parsedNames.size(); i++) { names.insert(parsedNames[i]); } out << firstCol << '\t' << hold << endl; wroteSomething = true; + selectedCount += parsedNames.size(); }else { + selectedCount += validSecond.size(); + //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) { @@ -596,6 +615,8 @@ int GetSeqsCommand::readName(){ 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); + m->mothurOut("Selected " + toString(selectedCount) + " sequences from your name file."); m->mothurOutEndLine(); + return 0; } @@ -620,10 +641,11 @@ int GetSeqsCommand::readGroup(){ string name, group; bool wroteSomething = false; + int selectedCount = 0; while(!in.eof()){ - if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } in >> name; //read from first column @@ -634,6 +656,7 @@ int GetSeqsCommand::readGroup(){ wroteSomething = true; out << name << '\t' << group << endl; + selectedCount++; } m->gobble(in); @@ -644,6 +667,9 @@ int GetSeqsCommand::readGroup(){ 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); + m->mothurOut("Selected " + toString(selectedCount) + " sequences from your group file."); m->mothurOutEndLine(); + + return 0; } @@ -666,10 +692,11 @@ int GetSeqsCommand::readTax(){ string name, tax; bool wroteSomething = false; + int selectedCount = 0; while(!in.eof()){ - if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } in >> name; //read from first column in >> tax; //read from second column @@ -679,6 +706,7 @@ int GetSeqsCommand::readTax(){ wroteSomething = true; out << name << '\t' << tax << endl; + selectedCount++; } m->gobble(in); @@ -688,6 +716,8 @@ int GetSeqsCommand::readTax(){ 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); + + m->mothurOut("Selected " + toString(selectedCount) + " sequences from your taxonomy file."); m->mothurOutEndLine(); return 0; @@ -713,6 +743,7 @@ int GetSeqsCommand::readAlign(){ string name, junk; bool wroteSomething = false; + int selectedCount = 0; //read column headers for (int i = 0; i < 16; i++) { @@ -723,7 +754,7 @@ int GetSeqsCommand::readAlign(){ while(!in.eof()){ - if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } in >> name; //read from first column @@ -731,6 +762,7 @@ int GetSeqsCommand::readAlign(){ //if this name is in the accnos file if (names.count(name) != 0) { wroteSomething = true; + selectedCount++; out << name << '\t'; @@ -757,6 +789,8 @@ int GetSeqsCommand::readAlign(){ 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); + m->mothurOut("Selected " + toString(selectedCount) + " sequences from your alignreport file."); m->mothurOutEndLine(); + return 0; } @@ -838,7 +872,15 @@ int GetSeqsCommand::compareAccnos(){ in >> name; if (namesAccnos.count(name) == 0){ //name unique to accnos2 - namesAccnos2.insert(name); + int pos = name.find_last_of('_'); + string tempName = name; + if (pos != string::npos) { tempName = tempName.substr(pos+1); cout << tempName << endl; } + if (namesAccnos.count(tempName) == 0){ + namesAccnos2.insert(name); + }else { //you are in both so erase + namesAccnos.erase(name); + namesDups.insert(name); + } }else { //you are in both so erase namesAccnos.erase(name); namesDups.insert(name);