X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;ds=sidebyside;f=sffinfocommand.cpp;h=8c50247c6845867ff9f99f62760d81300d433779;hb=d945488119ad368b180537f36ed40298ff170f39;hp=2caad96df797bc2d5dca067a4ae2b3f4a4ebed5c;hpb=d0954e27635712cdbd8b86e3c4510670803a2665;p=mothur.git diff --git a/sffinfocommand.cpp b/sffinfocommand.cpp index 2caad96..8c50247 100644 --- a/sffinfocommand.cpp +++ b/sffinfocommand.cpp @@ -11,21 +11,57 @@ #include "endiannessmacros.h" //********************************************************************************************************************** -vector SffInfoCommand::getValidParameters(){ - try { - string Array[] = {"sff","qfile","fasta","flow","trim","accnos","sfftxt","outputdir","inputdir", "outputdir"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); +vector SffInfoCommand::setParameters(){ + try { + CommandParameter psff("sff", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(psff); + CommandParameter paccnos("accnos", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(paccnos); + CommandParameter psfftxt("sfftxt", "String", "", "", "", "", "",false,false); parameters.push_back(psfftxt); + CommandParameter pflow("flow", "Boolean", "", "F", "", "", "",false,false); parameters.push_back(pflow); + CommandParameter ptrim("trim", "Boolean", "", "T", "", "", "",false,false); parameters.push_back(ptrim); + CommandParameter pfasta("fasta", "Boolean", "", "T", "", "", "",false,false); parameters.push_back(pfasta); + CommandParameter pqfile("name", "Boolean", "", "T", "", "", "",false,false); parameters.push_back(pqfile); + CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir); + CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir); + + vector myArray; + for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); } return myArray; } catch(exception& e) { - m->errorOut(e, "SffInfoCommand", "getValidParameters"); + m->errorOut(e, "SffInfoCommand", "setParameters"); + exit(1); + } +} +//********************************************************************************************************************** +string SffInfoCommand::getHelpString(){ + try { + string helpString = ""; + helpString += "The sffinfo command reads a sff file and extracts the sequence data, or you can use it to parse a sfftxt file.\n"; + helpString += "The sffinfo command parameters are sff, fasta, qfile, accnos, flow, sfftxt, and trim. sff is required. \n"; + helpString += "The sff parameter allows you to enter the sff file you would like to extract data from. You may enter multiple files by separating them by -'s.\n"; + helpString += "The fasta parameter allows you to indicate if you would like a fasta formatted file generated. Default=True. \n"; + helpString += "The qfile parameter allows you to indicate if you would like a quality file generated. Default=True. \n"; + helpString += "The flow parameter allows you to indicate if you would like a flowgram file generated. Default=False. \n"; + helpString += "The sfftxt parameter allows you to indicate if you would like a sff.txt file generated. Default=False. \n"; + helpString += "If you want to parse an existing sfftxt file into flow, fasta and quality file, enter the file name using the sfftxt parameter. \n"; + helpString += "The trim parameter allows you to indicate if you would like a sequences and quality scores trimmed to the clipQualLeft and clipQualRight values. Default=True. \n"; + helpString += "The accnos parameter allows you to provide a accnos file containing the names of the sequences you would like extracted. You may enter multiple files by separating them by -'s. \n"; + helpString += "Example sffinfo(sff=mySffFile.sff, trim=F).\n"; + helpString += "Note: No spaces between parameter labels (i.e. sff), '=' and parameters (i.e.yourSffFileName).\n"; + return helpString; + } + catch(exception& e) { + m->errorOut(e, "SffInfoCommand", "getHelpString"); exit(1); } } + + //********************************************************************************************************************** SffInfoCommand::SffInfoCommand(){ try { abort = true; calledHelp = true; + setParameters(); vector tempOutNames; outputTypes["fasta"] = tempOutNames; outputTypes["flow"] = tempOutNames; @@ -38,29 +74,6 @@ SffInfoCommand::SffInfoCommand(){ } } //********************************************************************************************************************** -vector SffInfoCommand::getRequiredParameters(){ - try { - string Array[] = {"sff", "sfftxt", "or"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); - return myArray; - } - catch(exception& e) { - m->errorOut(e, "SffInfoCommand", "getRequiredParameters"); - exit(1); - } -} -//********************************************************************************************************************** -vector SffInfoCommand::getRequiredFiles(){ - try { - vector myArray; - return myArray; - } - catch(exception& e) { - m->errorOut(e, "SffInfoCommand", "getRequiredFiles"); - exit(1); - } -} -//********************************************************************************************************************** SffInfoCommand::SffInfoCommand(string option) { try { @@ -72,8 +85,7 @@ SffInfoCommand::SffInfoCommand(string option) { else { //valid paramters for this command - string Array[] = {"sff","qfile","fasta","flow","trim","accnos","sfftxt","outputdir","inputdir", "outputdir"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + vector myArray = setParameters(); OptionParser parser(option); map parameters = parser.getParameters(); @@ -104,46 +116,60 @@ SffInfoCommand::SffInfoCommand(string option) { //go through files and make sure they are good, if not, then disregard them for (int i = 0; i < filenames.size(); i++) { - if (inputDir != "") { - string path = m->hasPath(filenames[i]); - //if the user has not given a path then, add inputdir. else leave path alone. - if (path == "") { filenames[i] = inputDir + filenames[i]; } - } - - ifstream in; - int ableToOpen = m->openInputFile(filenames[i], in, "noerror"); - - //if you can't open it, try default location - if (ableToOpen == 1) { - if (m->getDefaultPath() != "") { //default path is set - string tryPath = m->getDefaultPath() + m->getSimpleName(filenames[i]); - m->mothurOut("Unable to open " + filenames[i] + ". Trying default " + tryPath); m->mothurOutEndLine(); - ifstream in2; - ableToOpen = m->openInputFile(tryPath, in2, "noerror"); - in2.close(); - filenames[i] = tryPath; + bool ignore = false; + if (filenames[i] == "current") { + filenames[i] = m->getSFFFile(); + if (filenames[i] != "") { m->mothurOut("Using " + filenames[i] + " as input file for the sff parameter where you had given current."); m->mothurOutEndLine(); } + else { + m->mothurOut("You have no current sfffile, ignoring current."); m->mothurOutEndLine(); ignore=true; + //erase from file list + filenames.erase(filenames.begin()+i); + i--; } } - //if you can't open it, try default location - if (ableToOpen == 1) { - if (m->getOutputDir() != "") { //default path is set - string tryPath = m->getOutputDir() + m->getSimpleName(filenames[i]); - m->mothurOut("Unable to open " + filenames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine(); - ifstream in2; - ableToOpen = m->openInputFile(tryPath, in2, "noerror"); - in2.close(); - filenames[i] = tryPath; + if (!ignore) { + if (inputDir != "") { + string path = m->hasPath(filenames[i]); + //if the user has not given a path then, add inputdir. else leave path alone. + if (path == "") { filenames[i] = inputDir + filenames[i]; } } - } - - in.close(); + + ifstream in; + int ableToOpen = m->openInputFile(filenames[i], in, "noerror"); - if (ableToOpen == 1) { - m->mothurOut("Unable to open " + filenames[i] + ". It will be disregarded."); m->mothurOutEndLine(); - //erase from file list - filenames.erase(filenames.begin()+i); - i--; + //if you can't open it, try default location + if (ableToOpen == 1) { + if (m->getDefaultPath() != "") { //default path is set + string tryPath = m->getDefaultPath() + m->getSimpleName(filenames[i]); + m->mothurOut("Unable to open " + filenames[i] + ". Trying default " + tryPath); m->mothurOutEndLine(); + ifstream in2; + ableToOpen = m->openInputFile(tryPath, in2, "noerror"); + in2.close(); + filenames[i] = tryPath; + } + } + + //if you can't open it, try default location + if (ableToOpen == 1) { + if (m->getOutputDir() != "") { //default path is set + string tryPath = m->getOutputDir() + m->getSimpleName(filenames[i]); + m->mothurOut("Unable to open " + filenames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine(); + ifstream in2; + ableToOpen = m->openInputFile(tryPath, in2, "noerror"); + in2.close(); + filenames[i] = tryPath; + } + } + + in.close(); + + if (ableToOpen == 1) { + m->mothurOut("Unable to open " + filenames[i] + ". It will be disregarded."); m->mothurOutEndLine(); + //erase from file list + filenames.erase(filenames.begin()+i); + i--; + } } } @@ -159,44 +185,59 @@ SffInfoCommand::SffInfoCommand(string option) { //go through files and make sure they are good, if not, then disregard them for (int i = 0; i < accnosFileNames.size(); i++) { - if (inputDir != "") { - string path = m->hasPath(accnosFileNames[i]); - //if the user has not given a path then, add inputdir. else leave path alone. - if (path == "") { accnosFileNames[i] = inputDir + accnosFileNames[i]; } - } - - ifstream in; - int ableToOpen = m->openInputFile(accnosFileNames[i], in, "noerror"); - - //if you can't open it, try default location - if (ableToOpen == 1) { - if (m->getDefaultPath() != "") { //default path is set - string tryPath = m->getDefaultPath() + m->getSimpleName(accnosFileNames[i]); - m->mothurOut("Unable to open " + accnosFileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine(); - ifstream in2; - ableToOpen = m->openInputFile(tryPath, in2, "noerror"); - in2.close(); - accnosFileNames[i] = tryPath; + bool ignore = false; + if (accnosFileNames[i] == "current") { + accnosFileNames[i] = m->getAccnosFile(); + if (accnosFileNames[i] != "") { m->mothurOut("Using " + accnosFileNames[i] + " as input file for the accnos parameter where you had given current."); m->mothurOutEndLine(); } + else { + m->mothurOut("You have no current accnosfile, ignoring current."); m->mothurOutEndLine(); ignore=true; + //erase from file list + accnosFileNames.erase(accnosFileNames.begin()+i); + i--; } } - //if you can't open it, try default location - if (ableToOpen == 1) { - if (m->getOutputDir() != "") { //default path is set - string tryPath = m->getOutputDir() + m->getSimpleName(accnosFileNames[i]); - m->mothurOut("Unable to open " + accnosFileNames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine(); - ifstream in2; - ableToOpen = m->openInputFile(tryPath, in2, "noerror"); - in2.close(); - accnosFileNames[i] = tryPath; + + if (!ignore) { + + if (inputDir != "") { + string path = m->hasPath(accnosFileNames[i]); + //if the user has not given a path then, add inputdir. else leave path alone. + if (path == "") { accnosFileNames[i] = inputDir + accnosFileNames[i]; } } - } - in.close(); + + ifstream in; + int ableToOpen = m->openInputFile(accnosFileNames[i], in, "noerror"); - if (ableToOpen == 1) { - m->mothurOut("Unable to open " + accnosFileNames[i] + ". It will be disregarded."); m->mothurOutEndLine(); - //erase from file list - accnosFileNames.erase(accnosFileNames.begin()+i); - i--; + //if you can't open it, try default location + if (ableToOpen == 1) { + if (m->getDefaultPath() != "") { //default path is set + string tryPath = m->getDefaultPath() + m->getSimpleName(accnosFileNames[i]); + m->mothurOut("Unable to open " + accnosFileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine(); + ifstream in2; + ableToOpen = m->openInputFile(tryPath, in2, "noerror"); + in2.close(); + accnosFileNames[i] = tryPath; + } + } + //if you can't open it, try default location + if (ableToOpen == 1) { + if (m->getOutputDir() != "") { //default path is set + string tryPath = m->getOutputDir() + m->getSimpleName(accnosFileNames[i]); + m->mothurOut("Unable to open " + accnosFileNames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine(); + ifstream in2; + ableToOpen = m->openInputFile(tryPath, in2, "noerror"); + in2.close(); + accnosFileNames[i] = tryPath; + } + } + in.close(); + + if (ableToOpen == 1) { + m->mothurOut("Unable to open " + accnosFileNames[i] + ". It will be disregarded."); m->mothurOutEndLine(); + //erase from file list + accnosFileNames.erase(accnosFileNames.begin()+i); + i--; + } } } @@ -240,7 +281,12 @@ SffInfoCommand::SffInfoCommand(string option) { else if (sfftxtFilename == "not open") { sfftxtFilename = ""; } } - if ((sfftxtFilename == "") && (filenames.size() == 0)) { m->mothurOut("[ERROR]: you must provide a valid sff or sfftxt file."); m->mothurOutEndLine(); abort=true; } + if ((sfftxtFilename == "") && (filenames.size() == 0)) { + //if there is a current fasta file, use it + string filename = m->getSFFFile(); + if (filename != "") { filenames.push_back(filename); m->mothurOut("Using " + filename + " as input file for the sff parameter."); m->mothurOutEndLine(); } + else { m->mothurOut("[ERROR]: you must provide a valid sff or sfftxt file."); m->mothurOutEndLine(); abort=true; } + } } } catch(exception& e) { @@ -248,32 +294,6 @@ SffInfoCommand::SffInfoCommand(string option) { exit(1); } } -//********************************************************************************************************************** - -void SffInfoCommand::help(){ - try { - m->mothurOut("The sffinfo command reads a sff file and extracts the sequence data, or you can use it to parse a sfftxt file..\n"); - m->mothurOut("The sffinfo command parameters are sff, fasta, qfile, accnos, flow, sfftxt, and trim. sff is required. \n"); - m->mothurOut("The sff parameter allows you to enter the sff file you would like to extract data from. You may enter multiple files by separating them by -'s.\n"); - m->mothurOut("The fasta parameter allows you to indicate if you would like a fasta formatted file generated. Default=True. \n"); - m->mothurOut("The qfile parameter allows you to indicate if you would like a quality file generated. Default=True. \n"); - m->mothurOut("The flow parameter allows you to indicate if you would like a flowgram file generated. Default=False. \n"); - m->mothurOut("The sfftxt parameter allows you to indicate if you would like a sff.txt file generated. Default=False. \n"); - m->mothurOut("If you want to parse an existing sfftxt file into flow, fasta and quality file, enter the file name using the sfftxt parameter. \n"); - m->mothurOut("The trim parameter allows you to indicate if you would like a sequences and quality scores trimmed to the clipQualLeft and clipQualRight values. Default=True. \n"); - m->mothurOut("The accnos parameter allows you to provide a accnos file containing the names of the sequences you would like extracted. You may enter multiple files by separating them by -'s. \n"); - m->mothurOut("Example sffinfo(sff=mySffFile.sff, trim=F).\n"); - m->mothurOut("Note: No spaces between parameter labels (i.e. sff), '=' and parameters (i.e.yourSffFileName).\n\n"); - } - catch(exception& e) { - m->errorOut(e, "SffInfoCommand", "help"); - exit(1); - } -} -//********************************************************************************************************************** - -SffInfoCommand::~SffInfoCommand(){} - //********************************************************************************************************************** int SffInfoCommand::execute(){ try { @@ -310,7 +330,12 @@ int SffInfoCommand::execute(){ itTypes = outputTypes.find("qfile"); if (itTypes != outputTypes.end()) { if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setQualFile(current); } - } + } + + itTypes = outputTypes.find("flow"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setFlowFile(current); } + } //report output filenames m->mothurOutEndLine(); @@ -356,8 +381,9 @@ int SffInfoCommand::extractSffInfo(string input, string accnos){ CommonHeader header; readCommonHeader(in, header); - + int count = 0; + mycount = 0; //check magic number and version if (header.magicNumber != 779314790) { m->mothurOut("Magic Number is not correct, not a valid .sff file"); m->mothurOutEndLine(); return count; } @@ -392,6 +418,7 @@ int SffInfoCommand::extractSffInfo(string input, string accnos){ } count++; + mycount++; //report progress if((count+1) % 10000 == 0){ m->mothurOut(toString(count+1)); m->mothurOutEndLine(); } @@ -788,6 +815,7 @@ int SffInfoCommand::printQualSeqData(ofstream& out, seqRead& read, Header& heade if (trim) { if(header.clipQualRight < header.clipQualLeft){ + out << ">" << header.name << " xy=" << header.xy << endl; out << "0\t0\t0\t0"; } else if((header.clipQualRight != 0) && ((header.clipQualRight-header.clipQualLeft) >= 0)){