X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=getseqscommand.cpp;h=84fe0acab9abc0ec603df10896be1c0fe1e7f47c;hb=2c97dd48b8e27ee0a6a86c7a082f4c504c3357c6;hp=ffe49b48810d7916e5324efd9480c87e8322ec92;hpb=8742edef7a51b82834289e570d336f5a81ba1f2b;p=mothur.git diff --git a/getseqscommand.cpp b/getseqscommand.cpp index ffe49b4..84fe0ac 100644 --- a/getseqscommand.cpp +++ b/getseqscommand.cpp @@ -206,12 +206,12 @@ GetSeqsCommand::GetSeqsCommand(string option) { if (accnosfile2 == "not found") { accnosfile2 = ""; } fastafile = validParameter.validFile(parameters, "fasta", true); - if (fastafile == "not open") { abort = true; } + 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); } @@ -230,7 +230,7 @@ GetSeqsCommand::GetSeqsCommand(string option) { 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); } @@ -249,6 +249,11 @@ GetSeqsCommand::GetSeqsCommand(string option) { 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 ((namefile == "") && ((fastafile != "") || (taxfile != ""))){ + vector files; files.push_back(fastafile); files.push_back(taxfile); + parser.getNameFile(files); + } } } @@ -278,6 +283,8 @@ 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++) { m->mothurRemove(outputNames[i]); } return 0; } @@ -347,6 +354,8 @@ int GetSeqsCommand::readFasta(){ bool wroteSomething = false; int selectedCount = 0; + + if (m->debug) { set temp; sanity["fasta"] = temp; } while(!in.eof()){ @@ -362,6 +371,8 @@ int GetSeqsCommand::readFasta(){ currSeq.printSequence(out); selectedCount++; + + if (m->debug) { sanity["fasta"].insert(name); } } } m->gobble(in); @@ -400,6 +411,7 @@ int GetSeqsCommand::readQual(){ bool wroteSomething = false; int selectedCount = 0; + if (m->debug) { set temp; sanity["qual"] = temp; } while(!in.eof()){ string saveName = ""; @@ -431,6 +443,7 @@ int GetSeqsCommand::readQual(){ out << name << endl << scores; selectedCount++; + if (m->debug) { sanity["qual"].insert(name); } } m->gobble(in); @@ -467,6 +480,8 @@ int GetSeqsCommand::readList(){ bool wroteSomething = false; int selectedCount = 0; + + if (m->debug) { set temp; sanity["list"] = temp; } while(!in.eof()){ @@ -493,11 +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 + ","; selectedCount++; } + 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 + ","; selectedCount++; } + 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 != "") { @@ -546,6 +561,9 @@ int GetSeqsCommand::readName(){ 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()){ @@ -564,14 +582,16 @@ int GetSeqsCommand::readName(){ 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(); @@ -585,6 +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 @@ -599,6 +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]); } } } } @@ -637,6 +661,8 @@ int GetSeqsCommand::readGroup(){ bool wroteSomething = false; int selectedCount = 0; + + if (m->debug) { set temp; sanity["group"] = temp; } while(!in.eof()){ @@ -652,6 +678,8 @@ int GetSeqsCommand::readGroup(){ out << name << '\t' << group << endl; selectedCount++; + + if (m->debug) { sanity["group"].insert(name); } } m->gobble(in); @@ -688,6 +716,8 @@ int GetSeqsCommand::readTax(){ bool wroteSomething = false; int selectedCount = 0; + + if (m->debug) { set temp; sanity["tax"] = temp; } while(!in.eof()){ @@ -702,6 +732,8 @@ int GetSeqsCommand::readTax(){ out << name << '\t' << tax << endl; selectedCount++; + + if (m->debug) { sanity["tax"].insert(name); } } m->gobble(in); @@ -821,6 +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 {