X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=getseqscommand.cpp;h=a4697ca3fded8c34ec5320630a588e243601373d;hb=f06fdb807822f8e06db003ed809c87250905cfc8;hp=9fbfb932e4cafd672374b0a31dc7d250151b095a;hpb=89f19f9c6ab89c2f6c7c6921a328ae87bce6f8e3;p=mothur.git diff --git a/getseqscommand.cpp b/getseqscommand.cpp index 9fbfb93..a4697ca 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", "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; @@ -36,6 +68,7 @@ GetSeqsCommand::GetSeqsCommand(){ outputTypes["alignreport"] = tempOutNames; outputTypes["list"] = tempOutNames; outputTypes["qfile"] = tempOutNames; + outputTypes["accnosreport"] = tempOutNames; } catch(exception& e) { m->errorOut(e, "GetSeqsCommand", "GetSeqsCommand"); @@ -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; + 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", "dups", "list","taxonomy","outputdir","inputdir"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + vector myArray = setParameters(); OptionParser parser(option); map parameters = parser.getParameters(); @@ -98,6 +107,7 @@ GetSeqsCommand::GetSeqsCommand(string option) { outputTypes["alignreport"] = tempOutNames; outputTypes["list"] = tempOutNames; outputTypes["qfile"] = tempOutNames; + outputTypes["accnosreport"] = 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 = ""; } @@ -131,6 +141,14 @@ GetSeqsCommand::GetSeqsCommand(string option) { if (path == "") { parameters["accnos"] = inputDir + it->second; } } + it = parameters.find("accnos2"); + //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["accnos2"] = inputDir + it->second; } + } + it = parameters.find("list"); //user has given a template file if(it != parameters.end()){ @@ -176,7 +194,16 @@ 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; + } + } + + if (accnosfile2 == "not found") { accnosfile2 = ""; } fastafile = validParameter.validFile(parameters, "fasta", true); if (fastafile == "not open") { abort = true; } @@ -206,14 +233,16 @@ GetSeqsCommand::GetSeqsCommand(string option) { if (qualfile == "not open") { abort = true; } else if (qualfile == "not found") { 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 == "")) { 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 ((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; } } } @@ -224,28 +253,10 @@ 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(); @@ -253,21 +264,57 @@ int GetSeqsCommand::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(); } - if (groupfile != "") { readGroup(); } - if (alignfile != "") { readAlign(); } - if (listfile != "") { readList(); } - if (taxfile != "") { readTax(); } - if (qualfile != "") { readQual(); } + if (namefile != "") { readName(); } + if (fastafile != "") { readFasta(); } + if (groupfile != "") { readGroup(); } + if (alignfile != "") { readAlign(); } + if (listfile != "") { readList(); } + if (taxfile != "") { readTax(); } + 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; } + 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; @@ -492,15 +539,7 @@ 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++) { @@ -744,6 +783,111 @@ int GetSeqsCommand::readAccnos(){ exit(1); } } +//********************************************************************************************************************** + +int GetSeqsCommand::compareAccnos(){ + try { + + string thisOutputDir = outputDir; + if (outputDir == "") { thisOutputDir += m->hasPath(accnosfile); } + string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(accnosfile)) + "accnos.report"; + ofstream out; + m->openOutputFile(outputFileName, out); + + ifstream in; + m->openInputFile(accnosfile2, in); + string name; + + set namesAccnos2; + 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 + 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); + } + + m->gobble(in); + } + in.close(); + + out << "Names in both files : " + toString(namesDups.size()) << endl; + m->mothurOut("Names in both files : " + toString(namesDups.size())); m->mothurOutEndLine(); + + for (set::iterator it = namesDups.begin(); it != namesDups.end(); it++) { + 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); + 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); + if (namefile != "") { out << '\t' << nameCount[(*it)]; } + out << endl; + } + + out.close(); + + outputNames.push_back(outputFileName); outputTypes["accnosreport"].push_back(outputFileName); + + return 0; + + } + catch(exception& e) { + m->errorOut(e, "GetSeqsCommand", "readAccnos"); + exit(1); + } +} + //**********************************************************************************************************************