X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=getseqscommand.cpp;h=84fe0acab9abc0ec603df10896be1c0fe1e7f47c;hb=4c302368ef34f0d897afefc7853edf86fb45b9f3;hp=d40dcc6a30d20080770ac806855295f98ed83df3;hpb=de67504f85e091a3049ef4c5df8e77f7dcb1d814;p=mothur.git diff --git a/getseqscommand.cpp b/getseqscommand.cpp index d40dcc6..84fe0ac 100644 --- a/getseqscommand.cpp +++ b/getseqscommand.cpp @@ -12,22 +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; - //initialize outputTypes + abort = true; calledHelp = true; + setParameters(); vector tempOutNames; outputTypes["fasta"] = tempOutNames; outputTypes["taxonomy"] = tempOutNames; @@ -44,40 +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; + abort = false; calledHelp = false; //allow user to run help - if(option == "help") { help(); abort = true; } + 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(); @@ -186,22 +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); } - accnosfile2 = validParameter.validFile(parameters, "accnos2", true); - if (accnosfile2 == "not open") { abort = true; } + 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; } @@ -210,23 +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); + } } } @@ -237,28 +264,10 @@ 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 { - if (abort == true) { return 0; } + if (abort == true) { if (calledHelp) { return 0; } return 2; } //get names you want to keep readAccnos(); @@ -274,16 +283,50 @@ int GetSeqsCommand::execute(){ if (taxfile != "") { readTax(); } if (qualfile != "") { readQual(); } if (accnosfile2 != "") { compareAccnos(); } + + if (m->debug) { runSanityCheck(); } - 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(); m->mothurOut("Output File Names: "); m->mothurOutEndLine(); for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); } m->mothurOutEndLine(); + + //set fasta file as new current fastafile + string current = ""; + itTypes = outputTypes.find("fasta"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setFastaFile(current); } + } + + itTypes = outputTypes.find("name"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setNameFile(current); } + } + + itTypes = outputTypes.find("group"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setGroupFile(current); } + } + + itTypes = outputTypes.find("list"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setListFile(current); } + } + + itTypes = outputTypes.find("taxonomy"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setTaxonomyFile(current); } + } + + itTypes = outputTypes.find("qfile"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setQualFile(current); } + } + } return 0; @@ -310,10 +353,13 @@ int GetSeqsCommand::readFasta(){ string name; bool wroteSomething = false; + int selectedCount = 0; + + if (m->debug) { set temp; sanity["fasta"] = temp; } 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(); @@ -324,6 +370,9 @@ int GetSeqsCommand::readFasta(){ wroteSomething = true; currSeq.printSequence(out); + selectedCount++; + + if (m->debug) { sanity["fasta"].insert(name); } } } m->gobble(in); @@ -335,6 +384,8 @@ 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; } @@ -358,7 +409,9 @@ int GetSeqsCommand::readQual(){ string name; bool wroteSomething = false; + int selectedCount = 0; + if (m->debug) { set temp; sanity["qual"] = temp; } while(!in.eof()){ string saveName = ""; @@ -389,6 +442,8 @@ int GetSeqsCommand::readQual(){ wroteSomething = true; out << name << endl << scores; + selectedCount++; + if (m->debug) { sanity["qual"].insert(name); } } m->gobble(in); @@ -400,6 +455,9 @@ 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; } @@ -421,10 +479,15 @@ int GetSeqsCommand::readList(){ m->openInputFile(listfile, in); bool wroteSomething = false; + int selectedCount = 0; + + if (m->debug) { set temp; sanity["list"] = temp; } 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); @@ -445,11 +508,11 @@ 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++; if (m->debug) { sanity["list"].insert(name); } } } //get last name - if (names.count(binnames) != 0) { newNames += binnames + ","; } + if (names.count(binnames) != 0) { newNames += binnames + ","; selectedCount++; if (m->debug) { sanity["list"].insert(binnames); } } //if there are names in this bin add to new list if (newNames != "") { @@ -472,6 +535,8 @@ 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; } @@ -495,11 +560,14 @@ int GetSeqsCommand::readName(){ string name, firstCol, secondCol; bool wroteSomething = false; - + int selectedCount = 0; + + if (m->debug) { set temp; sanity["name"] = temp; } + if (m->debug) { set temp; sanity["dupname"] = temp; } 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; @@ -508,28 +576,25 @@ 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++) { if (names.count(parsedNames[i]) != 0) { validSecond.push_back(parsedNames[i]); + if (m->debug) { sanity["dupname"].insert(parsedNames[i]); } } } 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]); } + for (int i = 0; i < parsedNames.size(); i++) { names.insert(parsedNames[i]); if (m->debug) { sanity["dupname"].insert(parsedNames[i]); } } out << firstCol << '\t' << hold << endl; wroteSomething = true; + selectedCount += parsedNames.size(); + if (m->debug) { sanity["name"].insert(firstCol); } }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) { @@ -540,6 +605,8 @@ int GetSeqsCommand::readName(){ //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; + + if (m->debug) { sanity["name"].insert(firstCol); } //make first name in set you come to first column and then add the remaining names to second column @@ -554,6 +621,8 @@ int GetSeqsCommand::readName(){ //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; + + if (m->debug) { sanity["name"].insert(validSecond[0]); } } } } @@ -565,6 +634,8 @@ 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; } @@ -589,10 +660,13 @@ int GetSeqsCommand::readGroup(){ string name, group; bool wroteSomething = false; + int selectedCount = 0; + + if (m->debug) { set temp; sanity["group"] = temp; } 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 @@ -603,6 +677,9 @@ int GetSeqsCommand::readGroup(){ wroteSomething = true; out << name << '\t' << group << endl; + selectedCount++; + + if (m->debug) { sanity["group"].insert(name); } } m->gobble(in); @@ -613,6 +690,9 @@ 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; } @@ -635,10 +715,13 @@ int GetSeqsCommand::readTax(){ string name, tax; bool wroteSomething = false; + int selectedCount = 0; + + if (m->debug) { set temp; sanity["tax"] = temp; } 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 @@ -648,6 +731,9 @@ int GetSeqsCommand::readTax(){ wroteSomething = true; out << name << '\t' << tax << endl; + selectedCount++; + + if (m->debug) { sanity["tax"].insert(name); } } m->gobble(in); @@ -657,6 +743,8 @@ 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; @@ -682,6 +770,7 @@ int GetSeqsCommand::readAlign(){ string name, junk; bool wroteSomething = false; + int selectedCount = 0; //read column headers for (int i = 0; i < 16; i++) { @@ -692,7 +781,7 @@ 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 @@ -700,6 +789,7 @@ int GetSeqsCommand::readAlign(){ //if this name is in the accnos file if (names.count(name) != 0) { wroteSomething = true; + selectedCount++; out << name << '\t'; @@ -726,6 +816,8 @@ 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; } @@ -761,6 +853,99 @@ int GetSeqsCommand::readAccnos(){ } } //********************************************************************************************************************** +//just looking at common mistakes. +int GetSeqsCommand::runSanityCheck(){ + try { + string thisOutputDir = outputDir; + if (outputDir == "") { thisOutputDir += m->hasPath(fastafile); } + string filename = outputDir + "get.seqs.debug.report"; + + ofstream out; + m->openOutputFile(filename, out); + + + //compare fasta, name, qual and taxonomy if given to make sure they contain the same seqs + if (fastafile != "") { + if (namefile != "") { //compare with fasta + if (sanity["fasta"] != sanity["name"]) { //create mismatch file + createMisMatchFile(out, fastafile, namefile, sanity["fasta"], sanity["name"]); + } + } + if (qualfile != "") { + if (sanity["fasta"] != sanity["qual"]) { //create mismatch file + createMisMatchFile(out, fastafile, qualfile, sanity["fasta"], sanity["qual"]); + } + } + if (taxfile != "") { + if (sanity["fasta"] != sanity["tax"]) { //create mismatch file + createMisMatchFile(out, fastafile, taxfile, sanity["fasta"], sanity["tax"]); + } + } + } + + //compare dupnames, groups and list if given to make sure they match + if (namefile != "") { + if (groupfile != "") { + if (sanity["dupname"] != sanity["group"]) { //create mismatch file + createMisMatchFile(out, namefile, groupfile, sanity["dupname"], sanity["group"]); + } + } + if (listfile != "") { + if (sanity["dupname"] != sanity["list"]) { //create mismatch file + createMisMatchFile(out, namefile, listfile, sanity["dupname"], sanity["list"]); + } + } + }else{ + + if ((groupfile != "") && (fastafile != "")) { + if (sanity["fasta"] != sanity["group"]) { //create mismatch file + createMisMatchFile(out, fastafile, groupfile, sanity["fasta"], sanity["group"]); + } + } + } + + out.close(); + + if (m->isBlank(filename)) { m->mothurRemove(filename); } + else { m->mothurOut("\n[DEBUG]: " + filename + " contains the file mismatches.\n");outputNames.push_back(filename); outputTypes["debug"].push_back(filename); } + + return 0; + } + catch(exception& e) { + m->errorOut(e, "GetSeqsCommand", "runSanityCheck"); + exit(1); + } +} +//********************************************************************************************************************** +//just looking at common mistakes. +int GetSeqsCommand::createMisMatchFile(ofstream& out, string filename1, string filename2, set set1, set set2){ + try { + out << "****************************************" << endl << endl; + out << "Names unique to " << filename1 << ":\n"; + + //remove names in set1 that are also in set2 + for (set::iterator it = set1.begin(); it != set1.end();) { + string name = *it; + + if (set2.count(name) == 0) { out << name << endl; } //name unique to set1 + else { set2.erase(name); } //you are in both so erase + set1.erase(it++); + } + + out << "\nNames unique to " << filename2 << ":\n"; + //output results + for (set::iterator it = set2.begin(); it != set2.end(); it++) { out << *it << endl; } + + out << "****************************************" << endl << endl; + + return 0; + } + catch(exception& e) { + m->errorOut(e, "GetSeqsCommand", "runSanityCheck"); + exit(1); + } +} +//********************************************************************************************************************** int GetSeqsCommand::compareAccnos(){ try { @@ -779,11 +964,43 @@ int GetSeqsCommand::compareAccnos(){ 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); + 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); @@ -797,21 +1014,27 @@ int GetSeqsCommand::compareAccnos(){ m->mothurOut("Names in both files : " + toString(namesDups.size())); m->mothurOutEndLine(); for (set::iterator it = namesDups.begin(); it != namesDups.end(); it++) { - out << (*it) << endl; + 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) << endl; + 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) << endl; + out << (*it); + if (namefile != "") { out << '\t' << nameCount[(*it)]; } + out << endl; } out.close();