X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=getseqscommand.cpp;h=84fe0acab9abc0ec603df10896be1c0fe1e7f47c;hb=42d411d3362186465347aeabdd3155bd3259671e;hp=ad9698b695815cc77459cc85d2cca1ec7cd24f67;hpb=e150b0b0664caec517485ee6d69dcdade6dcae77;p=mothur.git diff --git a/getseqscommand.cpp b/getseqscommand.cpp index ad9698b..84fe0ac 100644 --- a/getseqscommand.cpp +++ b/getseqscommand.cpp @@ -25,7 +25,8 @@ vector GetSeqsCommand::setParameters(){ 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; @@ -200,21 +201,24 @@ GetSeqsCommand::GetSeqsCommand(string option) { 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; } @@ -223,20 +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 = "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 ((namefile == "") && ((fastafile != "") || (taxfile != ""))){ + vector files; files.push_back(fastafile); files.push_back(taxfile); + parser.getNameFile(files); + } } } @@ -266,10 +283,11 @@ 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(); @@ -335,10 +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(); @@ -349,6 +370,9 @@ int GetSeqsCommand::readFasta(){ wroteSomething = true; currSeq.printSequence(out); + selectedCount++; + + if (m->debug) { sanity["fasta"].insert(name); } } } m->gobble(in); @@ -360,6 +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; } @@ -383,7 +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 = ""; @@ -414,6 +442,8 @@ int GetSeqsCommand::readQual(){ wroteSomething = true; out << name << endl << scores; + selectedCount++; + if (m->debug) { sanity["qual"].insert(name); } } m->gobble(in); @@ -425,6 +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; } @@ -446,10 +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); @@ -470,11 +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 != "") { @@ -497,6 +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; } @@ -520,11 +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; @@ -539,14 +582,19 @@ 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(); + //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) { @@ -557,6 +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 @@ -571,6 +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]); } } } } @@ -582,6 +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; } @@ -606,10 +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 @@ -620,6 +677,9 @@ int GetSeqsCommand::readGroup(){ wroteSomething = true; out << name << '\t' << group << endl; + selectedCount++; + + if (m->debug) { sanity["group"].insert(name); } } m->gobble(in); @@ -630,6 +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; } @@ -652,10 +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 @@ -665,6 +731,9 @@ int GetSeqsCommand::readTax(){ wroteSomething = true; out << name << '\t' << tax << endl; + selectedCount++; + + if (m->debug) { sanity["tax"].insert(name); } } m->gobble(in); @@ -674,6 +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; @@ -699,6 +770,7 @@ int GetSeqsCommand::readAlign(){ string name, junk; bool wroteSomething = false; + int selectedCount = 0; //read column headers for (int i = 0; i < 16; i++) { @@ -709,7 +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 @@ -717,6 +789,7 @@ int GetSeqsCommand::readAlign(){ //if this name is in the accnos file if (names.count(name) != 0) { wroteSomething = true; + selectedCount++; out << name << '\t'; @@ -743,6 +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; } @@ -778,6 +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 { @@ -824,7 +992,15 @@ 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);