X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=filterseqscommand.cpp;h=82c73f3d439c1d3cc154c8dac67398075134a1e8;hb=8dd3c225255d7084e3aff8740aa4f1f1cabb367a;hp=6fd4e04a0e562e5ee44fd0a05fc7df9b1bfae3d4;hpb=c69e2e9749626cfbf1d6cb0125ae94f869e00b18;p=mothur.git diff --git a/filterseqscommand.cpp b/filterseqscommand.cpp index 6fd4e04..82c73f3 100644 --- a/filterseqscommand.cpp +++ b/filterseqscommand.cpp @@ -10,51 +10,63 @@ #include "filterseqscommand.h" #include "sequence.hpp" + //********************************************************************************************************************** -vector FilterSeqsCommand::getValidParameters(){ +vector FilterSeqsCommand::setParameters(){ try { - string Array[] = {"fasta", "trump", "soft", "hard", "vertical", "outputdir","inputdir", "processors"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(pfasta); + CommandParameter phard("hard", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(phard); + CommandParameter ptrump("trump", "String", "", "*", "", "", "",false,false); parameters.push_back(ptrump); + CommandParameter psoft("soft", "Number", "", "0", "", "", "",false,false); parameters.push_back(psoft); + CommandParameter pvertical("vertical", "Boolean", "", "T", "", "", "",false,false); parameters.push_back(pvertical); + CommandParameter pprocessors("processors", "Number", "", "1", "", "", "",false,false); parameters.push_back(pprocessors); + 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, "FilterSeqsCommand", "getValidParameters"); + m->errorOut(e, "FilterSeqsCommand", "setParameters"); exit(1); } } //********************************************************************************************************************** -FilterSeqsCommand::FilterSeqsCommand(){ +string FilterSeqsCommand::getHelpString(){ try { - abort = true; calledHelp = true; - vector tempOutNames; - outputTypes["fasta"] = tempOutNames; - outputTypes["filter"] = tempOutNames; + string helpString = ""; + helpString += "The filter.seqs command reads a file containing sequences and creates a .filter and .filter.fasta file.\n"; + helpString += "The filter.seqs command parameters are fasta, trump, soft, hard, processors and vertical. \n"; + helpString += "The fasta parameter is required, unless you have a valid current fasta file. You may enter several fasta files to build the filter from and filter, by separating their names with -'s.\n"; + helpString += "For example: fasta=abrecovery.fasta-amazon.fasta \n"; + helpString += "The trump option will remove a column if the trump character is found at that position in any sequence of the alignment. Default=*, meaning no trump. \n"; + helpString += "A soft mask removes any column where the dominant base (i.e. A, T, G, C, or U) does not occur in at least a designated percentage of sequences. Default=0.\n"; + helpString += "The hard parameter allows you to enter a file containing the filter you want to use.\n"; + helpString += "The vertical parameter removes columns where all sequences contain a gap character. The default is T.\n"; + helpString += "The processors parameter allows you to specify the number of processors to use. The default is 1.\n"; + helpString += "The filter.seqs command should be in the following format: \n"; + helpString += "filter.seqs(fasta=yourFastaFile, trump=yourTrump) \n"; + helpString += "Example filter.seqs(fasta=abrecovery.fasta, trump=.).\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, "FilterSeqsCommand", "FilterSeqsCommand"); + m->errorOut(e, "FilterSeqsCommand", "getHelpString"); exit(1); } } //********************************************************************************************************************** -vector FilterSeqsCommand::getRequiredParameters(){ - try { - string Array[] = {"fasta"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); - return myArray; - } - catch(exception& e) { - m->errorOut(e, "FilterSeqsCommand", "getRequiredParameters"); - exit(1); - } -} -//********************************************************************************************************************** -vector FilterSeqsCommand::getRequiredFiles(){ +FilterSeqsCommand::FilterSeqsCommand(){ try { - vector myArray; - return myArray; + abort = true; calledHelp = true; + setParameters(); + vector tempOutNames; + outputTypes["fasta"] = tempOutNames; + outputTypes["filter"] = tempOutNames; } catch(exception& e) { - m->errorOut(e, "FilterSeqsCommand", "getRequiredFiles"); + m->errorOut(e, "FilterSeqsCommand", "FilterSeqsCommand"); exit(1); } } @@ -66,11 +78,10 @@ FilterSeqsCommand::FilterSeqsCommand(string option) { //allow user to run help 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", "trump", "soft", "hard", "vertical", "outputdir","inputdir", "processors"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + vector myArray = setParameters(); OptionParser parser(option); map parameters = parser.getParameters(); @@ -112,57 +123,77 @@ FilterSeqsCommand::FilterSeqsCommand(string option) { //check for required parameters fasta = validParameter.validFile(parameters, "fasta", false); - if (fasta == "not found") { m->mothurOut("fasta is a required parameter for the filter.seqs command."); m->mothurOutEndLine(); abort = true; } + if (fasta == "not found") { + fasta = m->getFastaFile(); + if (fasta != "") { fastafileNames.push_back(fasta); m->mothurOut("Using " + fasta + " as input file for the fasta parameter."); m->mothurOutEndLine(); } + else { m->mothurOut("You have no current fastafile and the fasta parameter is required."); m->mothurOutEndLine(); abort = true; } + } else { m->splitAtDash(fasta, fastafileNames); //go through files and make sure they are good, if not, then disregard them for (int i = 0; i < fastafileNames.size(); i++) { - if (inputDir != "") { - string path = m->hasPath(fastafileNames[i]); - //if the user has not given a path then, add inputdir. else leave path alone. - if (path == "") { fastafileNames[i] = inputDir + fastafileNames[i]; } - } - - ifstream in; - int ableToOpen = m->openInputFile(fastafileNames[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(fastafileNames[i]); - m->mothurOut("Unable to open " + fastafileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine(); - ifstream in2; - ableToOpen = m->openInputFile(tryPath, in2, "noerror"); - in2.close(); - fastafileNames[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(fastafileNames[i]); - m->mothurOut("Unable to open " + fastafileNames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine(); - ifstream in2; - ableToOpen = m->openInputFile(tryPath, in2, "noerror"); - in2.close(); - fastafileNames[i] = tryPath; + bool ignore = false; + if (fastafileNames[i] == "current") { + fastafileNames[i] = m->getFastaFile(); + if (fastafileNames[i] != "") { m->mothurOut("Using " + fastafileNames[i] + " as input file for the fasta parameter where you had given current."); m->mothurOutEndLine(); } + else { + m->mothurOut("You have no current fastafile, ignoring current."); m->mothurOutEndLine(); ignore=true; + //erase from file list + fastafileNames.erase(fastafileNames.begin()+i); + i--; } } - in.close(); + if (!ignore) { + if (inputDir != "") { + string path = m->hasPath(fastafileNames[i]); + //if the user has not given a path then, add inputdir. else leave path alone. + if (path == "") { fastafileNames[i] = inputDir + fastafileNames[i]; } + } + + ifstream in; + int ableToOpen = m->openInputFile(fastafileNames[i], in, "noerror"); - if (ableToOpen == 1) { - m->mothurOut("Unable to open " + fastafileNames[i] + ". It will be disregarded."); m->mothurOutEndLine(); - //erase from file list - fastafileNames.erase(fastafileNames.begin()+i); - i--; - }else{ - string simpleName = m->getSimpleName(fastafileNames[i]); - filterFileName += simpleName.substr(0, simpleName.find_first_of('.')); + //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(fastafileNames[i]); + m->mothurOut("Unable to open " + fastafileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine(); + ifstream in2; + ableToOpen = m->openInputFile(tryPath, in2, "noerror"); + in2.close(); + fastafileNames[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(fastafileNames[i]); + m->mothurOut("Unable to open " + fastafileNames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine(); + ifstream in2; + ableToOpen = m->openInputFile(tryPath, in2, "noerror"); + in2.close(); + fastafileNames[i] = tryPath; + } + } + + in.close(); + + if (ableToOpen == 1) { + m->mothurOut("Unable to open " + fastafileNames[i] + ". It will be disregarded."); m->mothurOutEndLine(); + //erase from file list + fastafileNames.erase(fastafileNames.begin()+i); + i--; + }else{ + string simpleName = m->getSimpleName(fastafileNames[i]); + filterFileName += simpleName.substr(0, simpleName.find_first_of('.')); + m->setFastaFile(fastafileNames[i]); + } + in.close(); } - in.close(); } //make sure there is at least one valid file left @@ -189,8 +220,9 @@ FilterSeqsCommand::FilterSeqsCommand(string option) { temp = validParameter.validFile(parameters, "soft", false); if (temp == "not found") { soft = 0; } else { soft = (float)atoi(temp.c_str()) / 100.0; } - temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found"){ temp = "1"; } - convert(temp, processors); + temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found"){ temp = m->getProcessors(); } + m->setProcessors(temp); + m->mothurConvert(temp, processors); vertical = validParameter.validFile(parameters, "vertical", false); if (vertical == "not found") { @@ -207,33 +239,6 @@ FilterSeqsCommand::FilterSeqsCommand(string option) { exit(1); } } - -//********************************************************************************************************************** - -void FilterSeqsCommand::help(){ - try { - - m->mothurOut("The filter.seqs command reads a file containing sequences and creates a .filter and .filter.fasta file.\n"); - m->mothurOut("The filter.seqs command parameters are fasta, trump, soft, hard, processors and vertical. \n"); - m->mothurOut("The fasta parameter is required. You may enter several fasta files to build the filter from and filter, by separating their names with -'s.\n"); - m->mothurOut("For example: fasta=abrecovery.fasta-amazon.fasta \n"); - m->mothurOut("The trump parameter .... The default is ...\n"); - m->mothurOut("The soft parameter .... The default is ....\n"); - m->mothurOut("The hard parameter allows you to enter a file containing the filter you want to use.\n"); - m->mothurOut("The vertical parameter removes columns where all sequences contain a gap character. The default is T.\n"); - m->mothurOut("The processors parameter allows you to specify the number of processors to use. The default is 1.\n"); - m->mothurOut("The filter.seqs command should be in the following format: \n"); - m->mothurOut("filter.seqs(fasta=yourFastaFile, trump=yourTrump) \n"); - m->mothurOut("Example filter.seqs(fasta=abrecovery.fasta, trump=.).\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, "FilterSeqsCommand", "help"); - exit(1); - } -} - /**************************************************************************************/ int FilterSeqsCommand::execute() { @@ -293,7 +298,7 @@ int FilterSeqsCommand::execute() { if(filter[i] == '1'){ filteredLength++; } } - 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->mothurOutEndLine(); @@ -302,6 +307,12 @@ int FilterSeqsCommand::execute() { m->mothurOut("Length of the original alignment: " + toString(alignmentLength)); m->mothurOutEndLine(); m->mothurOut("Number of sequences used to construct filter: " + toString(numSeqs)); 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); } + } m->mothurOutEndLine(); m->mothurOut("Output File Names: "); m->mothurOutEndLine(); @@ -330,7 +341,7 @@ int FilterSeqsCommand::filterSequences() { #ifdef USE_MPI int pid, numSeqsPerProcessor, num; int tag = 2001; - vectorMPIPos; + vectorMPIPos; MPI_Status status; MPI_Comm_size(MPI_COMM_WORLD, &processors); //set processors to the number of mpi processes running @@ -409,12 +420,14 @@ int FilterSeqsCommand::filterSequences() { MPI_Barrier(MPI_COMM_WORLD); //make everyone wait - just in case #else - vector positions = m->divideFile(fastafileNames[s], processors); - + + #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) + vector positions = m->divideFile(fastafileNames[s], processors); + for (int i = 0; i < (positions.size()-1); i++) { lines.push_back(new linePair(positions[i], positions[(i+1)])); } - #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) + if(processors == 1){ int numFastaSeqs = driverRunFilter(filter, filteredFasta, fastafileNames[s], lines[0]); numSeqs += numFastaSeqs; @@ -427,12 +440,13 @@ int FilterSeqsCommand::filterSequences() { //append fasta files for(int i=1;iappendFiles((fastafileNames[s] + toString(processIDS[i]) + ".temp"), filteredFasta); - remove((fastafileNames[s] + toString(processIDS[i]) + ".temp").c_str()); + m->mothurRemove((fastafileNames[s] + toString(processIDS[i]) + ".temp")); } } if (m->control_pressed) { return 1; } #else + lines.push_back(new linePair(0, 1000)); int numFastaSeqs = driverRunFilter(filter, filteredFasta, fastafileNames[s], lines[0]); numSeqs += numFastaSeqs; @@ -451,7 +465,7 @@ int FilterSeqsCommand::filterSequences() { } #ifdef USE_MPI /**************************************************************************************/ -int FilterSeqsCommand::driverMPIRun(int start, int num, MPI_File& inMPI, MPI_File& outMPI, vector& MPIPos) { +int FilterSeqsCommand::driverMPIRun(int start, int num, MPI_File& inMPI, MPI_File& outMPI, vector& MPIPos) { try { string outputString = ""; int count = 0; @@ -557,7 +571,7 @@ int FilterSeqsCommand::driverRunFilter(string F, string outputFilename, string i } #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) - unsigned long int pos = in.tellg(); + unsigned long long pos = in.tellg(); if ((pos == -1) || (pos >= filePos->end)) { break; } #else if (in.eof()) { break; } @@ -626,7 +640,7 @@ int FilterSeqsCommand::createProcessesRunFilter(string F, string filename) { string tempFile = filename + toString(processIDS[i]) + ".num.temp"; m->openInputFile(tempFile, in); if (!in.eof()) { int tempNum = 0; in >> tempNum; num += tempNum; } - in.close(); remove(tempFile.c_str()); + in.close(); m->mothurRemove(tempFile); } @@ -665,7 +679,7 @@ string FilterSeqsCommand::createFilter() { #ifdef USE_MPI int pid, numSeqsPerProcessor, num; int tag = 2001; - vector MPIPos; + vector MPIPos; MPI_Status status; MPI_File inMPI; @@ -725,12 +739,14 @@ string FilterSeqsCommand::createFilter() { MPI_Barrier(MPI_COMM_WORLD); //make everyone wait - just in case #else - vector positions = m->divideFile(fastafileNames[s], processors); - for (int i = 0; i < (positions.size()-1); i++) { - lines.push_back(new linePair(positions[i], positions[(i+1)])); - } + #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) + vector positions = m->divideFile(fastafileNames[s], processors); + for (int i = 0; i < (positions.size()-1); i++) { + lines.push_back(new linePair(positions[i], positions[(i+1)])); + } + if(processors == 1){ int numFastaSeqs = driverCreateFilter(F, fastafileNames[s], lines[0]); numSeqs += numFastaSeqs; @@ -741,6 +757,7 @@ string FilterSeqsCommand::createFilter() { if (m->control_pressed) { return filterString; } #else + lines.push_back(new linePair(0, 1000)); int numFastaSeqs = driverCreateFilter(F, fastafileNames[s], lines[0]); numSeqs += numFastaSeqs; if (m->control_pressed) { return filterString; } @@ -866,7 +883,7 @@ int FilterSeqsCommand::driverCreateFilter(Filters& F, string filename, linePair* } #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) - unsigned long int pos = in.tellg(); + unsigned long long pos = in.tellg(); if ((pos == -1) || (pos >= filePos->end)) { break; } #else if (in.eof()) { break; } @@ -888,7 +905,7 @@ int FilterSeqsCommand::driverCreateFilter(Filters& F, string filename, linePair* } #ifdef USE_MPI /**************************************************************************************/ -int FilterSeqsCommand::MPICreateFilter(int start, int num, Filters& F, MPI_File& inMPI, vector& MPIPos) { +int FilterSeqsCommand::MPICreateFilter(int start, int num, Filters& F, MPI_File& inMPI, vector& MPIPos) { try { MPI_Status status; @@ -1013,7 +1030,7 @@ int FilterSeqsCommand::createProcessesCreateFilter(Filters& F, string filename) for (int k = 0; k < alignmentLength; k++) { in >> temp; F.gap[k] += temp; } m->gobble(in); in.close(); - remove(tempFilename.c_str()); + m->mothurRemove(tempFilename); } return num;