X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=chimeraccodecommand.cpp;h=223ddb23c1bec61748ce62217001dfac04b565ac;hb=e6c4a7223199d800d496356604eb34dfe273673d;hp=8ea91e53abe27cb75641bfc54c7ed293d2b17a65;hpb=284fd95c611ccc3b1a7875c4dacfca06d1f50ed6;p=mothur.git diff --git a/chimeraccodecommand.cpp b/chimeraccodecommand.cpp index 8ea91e5..223ddb2 100644 --- a/chimeraccodecommand.cpp +++ b/chimeraccodecommand.cpp @@ -10,8 +10,55 @@ #include "chimeraccodecommand.h" #include "ccode.h" +//********************************************************************************************************************** +vector ChimeraCcodeCommand::getValidParameters(){ + try { + string AlignArray[] = {"fasta", "filter", "processors", "window", "template", "mask", "numwanted", "outputdir","inputdir" }; + vector myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string))); + return myArray; + } + catch(exception& e) { + m->errorOut(e, "ChimeraCcodeCommand", "getValidParameters"); + exit(1); + } +} +//********************************************************************************************************************** +ChimeraCcodeCommand::ChimeraCcodeCommand(){ + try { + vector tempOutNames; + outputTypes["chimera"] = tempOutNames; + outputTypes["mapinfo"] = tempOutNames; + outputTypes["accnos"] = tempOutNames; + } + catch(exception& e) { + m->errorOut(e, "ChimeraCcodeCommand", "ChimeraCcodeCommand"); + exit(1); + } +} +//********************************************************************************************************************** +vector ChimeraCcodeCommand::getRequiredParameters(){ + try { + string AlignArray[] = {"template","fasta"}; + vector myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string))); + return myArray; + } + catch(exception& e) { + m->errorOut(e, "ChimeraCcodeCommand", "getRequiredParameters"); + exit(1); + } +} +//********************************************************************************************************************** +vector ChimeraCcodeCommand::getRequiredFiles(){ + try { + vector myArray; + return myArray; + } + catch(exception& e) { + m->errorOut(e, "ChimeraCcodeCommand", "getRequiredFiles"); + exit(1); + } +} //*************************************************************************************************************** - ChimeraCcodeCommand::ChimeraCcodeCommand(string option) { try { abort = false; @@ -21,7 +68,7 @@ ChimeraCcodeCommand::ChimeraCcodeCommand(string option) { else { //valid paramters for this command - string Array[] = {"fasta", "filter", "processors", "window", "template", "mask", "numwanted", "outputdir","inputdir", }; + string Array[] = {"fasta", "filter", "processors", "window", "template", "mask", "numwanted", "outputdir","inputdir" }; vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); OptionParser parser(option); @@ -35,6 +82,11 @@ ChimeraCcodeCommand::ChimeraCcodeCommand(string option) { if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; } } + vector tempOutNames; + outputTypes["chimera"] = tempOutNames; + outputTypes["mapinfo"] = tempOutNames; + outputTypes["accnos"] = tempOutNames; + //if the user changes the input directory command factory will send this info to us in the output parameter string inputDir = validParameter.validFile(parameters, "inputdir", false); if (inputDir == "not found"){ inputDir = ""; } @@ -43,7 +95,7 @@ ChimeraCcodeCommand::ChimeraCcodeCommand(string option) { it = parameters.find("template"); //user has given a template file if(it != parameters.end()){ - path = hasPath(it->second); + path = m->hasPath(it->second); //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["template"] = inputDir + it->second; } } @@ -53,12 +105,12 @@ ChimeraCcodeCommand::ChimeraCcodeCommand(string option) { fastafile = validParameter.validFile(parameters, "fasta", false); if (fastafile == "not found") { fastafile = ""; m->mothurOut("fasta is a required parameter for the chimera.ccode command."); m->mothurOutEndLine(); abort = true; } else { - splitAtDash(fastafile, fastaFileNames); + m->splitAtDash(fastafile, 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 = hasPath(fastaFileNames[i]); + 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]; } } @@ -66,17 +118,32 @@ ChimeraCcodeCommand::ChimeraCcodeCommand(string option) { int ableToOpen; ifstream in; - ableToOpen = openInputFile(fastaFileNames[i], in, "noerror"); + 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() + getSimpleName(fastaFileNames[i]); + string tryPath = m->getDefaultPath() + m->getSimpleName(fastaFileNames[i]); m->mothurOut("Unable to open " + fastaFileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine(); - ableToOpen = openInputFile(tryPath, in, "noerror"); + 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) { @@ -92,10 +159,7 @@ ChimeraCcodeCommand::ChimeraCcodeCommand(string option) { } //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 = ""; - outputDir += hasPath(fastafile); //if user entered a file with a path then preserve it - } + outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){ outputDir = ""; } templatefile = validParameter.validFile(parameters, "template", true); if (templatefile == "not open") { abort = true; } @@ -105,20 +169,20 @@ ChimeraCcodeCommand::ChimeraCcodeCommand(string option) { if (maskfile == "not found") { maskfile = ""; } else if (maskfile != "default") { if (inputDir != "") { - string path = hasPath(maskfile); + string path = m->hasPath(maskfile); //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { maskfile = inputDir + maskfile; } } ifstream in; - int ableToOpen = openInputFile(maskfile, in); + int ableToOpen = m->openInputFile(maskfile, in); if (ableToOpen == 1) { abort = true; } in.close(); } string temp; temp = validParameter.validFile(parameters, "filter", false); if (temp == "not found") { temp = "F"; } - filter = isTrue(temp); + filter = m->isTrue(temp); temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found") { temp = "1"; } convert(temp, processors); @@ -192,22 +256,23 @@ int ChimeraCcodeCommand::execute(){ if (chimera->getUnaligned()) { m->mothurOut("Your template sequences are different lengths, please correct."); m->mothurOutEndLine(); delete chimera; return 0; } templateSeqsLength = chimera->getLength(); + if (outputDir == "") { outputDir = m->hasPath(fastaFileNames[s]); }//if user entered a file with a path then preserve it string outputFileName, accnosFileName; if (maskfile != "") { - outputFileName = outputDir + getRootName(getSimpleName(fastaFileNames[s])) + maskfile + ".ccode.chimeras"; - accnosFileName = outputDir + getRootName(getSimpleName(fastaFileNames[s])) + maskfile + ".ccode.accnos"; + outputFileName = outputDir + m->getRootName(m->getSimpleName(fastaFileNames[s])) + maskfile + ".ccode.chimeras"; + accnosFileName = outputDir + m->getRootName(m->getSimpleName(fastaFileNames[s])) + maskfile + ".ccode.accnos"; }else { - outputFileName = outputDir + getRootName(getSimpleName(fastaFileNames[s])) + "ccode.chimeras"; - accnosFileName = outputDir + getRootName(getSimpleName(fastaFileNames[s])) + "ccode.accnos"; + outputFileName = outputDir + m->getRootName(m->getSimpleName(fastaFileNames[s])) + "ccode.chimeras"; + accnosFileName = outputDir + m->getRootName(m->getSimpleName(fastaFileNames[s])) + "ccode.accnos"; } - string mapInfo = outputDir + getRootName(getSimpleName(fastaFileNames[s])) + "mapinfo"; + string mapInfo = outputDir + m->getRootName(m->getSimpleName(fastaFileNames[s])) + "mapinfo"; - if (m->control_pressed) { delete chimera; for (int j = 0; j < outputNames.size(); j++) { remove(outputNames[j].c_str()); } return 0; } + if (m->control_pressed) { delete chimera; for (int j = 0; j < outputNames.size(); j++) { remove(outputNames[j].c_str()); } outputTypes.clear(); return 0; } #ifdef USE_MPI - int pid, end, numSeqsPerProcessor; + int pid, numSeqsPerProcessor; int tag = 2001; vector MPIPos; @@ -235,7 +300,7 @@ int ChimeraCcodeCommand::execute(){ MPI_File_open(MPI_COMM_WORLD, outFilename, outMode, MPI_INFO_NULL, &outMPI); MPI_File_open(MPI_COMM_WORLD, outAccnosFilename, outMode, MPI_INFO_NULL, &outMPIAccnos); - if (m->control_pressed) { MPI_File_close(&inMPI); MPI_File_close(&outMPI); MPI_File_close(&outMPIAccnos); for (int j = 0; j < outputNames.size(); j++) { remove(outputNames[j].c_str()); } delete chimera; return 0; } + if (m->control_pressed) { MPI_File_close(&inMPI); MPI_File_close(&outMPI); MPI_File_close(&outMPIAccnos); for (int j = 0; j < outputNames.size(); j++) { remove(outputNames[j].c_str()); } outputTypes.clear(); delete chimera; return 0; } if (pid == 0) { //you are the root process string outTemp = "For full window mapping info refer to " + mapInfo + "\n\n"; @@ -248,7 +313,7 @@ int ChimeraCcodeCommand::execute(){ MPI_File_write_shared(outMPI, buf2, length, MPI_CHAR, &status); delete buf2; - MPIPos = setFilePosFasta(fastaFileNames[s], numSeqs); //fills MPIPos, returns numSeqs + MPIPos = m->setFilePosFasta(fastaFileNames[s], numSeqs); //fills MPIPos, returns numSeqs //send file positions to all processes for(int i = 1; i < processors; i++) { @@ -265,7 +330,7 @@ int ChimeraCcodeCommand::execute(){ //align your part driverMPI(startIndex, numSeqsPerProcessor, inMPI, outMPI, outMPIAccnos, MPIPos); - if (m->control_pressed) { MPI_File_close(&inMPI); MPI_File_close(&outMPI); MPI_File_close(&outMPIAccnos); remove(outputFileName.c_str()); remove(accnosFileName.c_str()); for (int j = 0; j < outputNames.size(); j++) { remove(outputNames[j].c_str()); } delete chimera; return 0; } + if (m->control_pressed) { MPI_File_close(&inMPI); MPI_File_close(&outMPI); MPI_File_close(&outMPIAccnos); remove(outputFileName.c_str()); remove(accnosFileName.c_str()); for (int j = 0; j < outputNames.size(); j++) { remove(outputNames[j].c_str()); } outputTypes.clear(); delete chimera; return 0; } }else{ //you are a child process MPI_Recv(&numSeqs, 1, MPI_INT, 0, tag, MPI_COMM_WORLD, &status); @@ -281,7 +346,7 @@ int ChimeraCcodeCommand::execute(){ //align your part driverMPI(startIndex, numSeqsPerProcessor, inMPI, outMPI, outMPIAccnos, MPIPos); - if (m->control_pressed) { MPI_File_close(&inMPI); MPI_File_close(&outMPI); MPI_File_close(&outMPIAccnos); for (int j = 0; j < outputNames.size(); j++) { remove(outputNames[j].c_str()); } delete chimera; return 0; } + if (m->control_pressed) { MPI_File_close(&inMPI); MPI_File_close(&outMPI); MPI_File_close(&outMPIAccnos); for (int j = 0; j < outputNames.size(); j++) { remove(outputNames[j].c_str()); } outputTypes.clear(); delete chimera; return 0; } } //close files @@ -293,14 +358,14 @@ int ChimeraCcodeCommand::execute(){ #else ofstream outHeader; - string tempHeader = outputDir + getRootName(getSimpleName(fastaFileNames[s])) + maskfile + "ccode.chimeras.tempHeader"; - openOutputFile(tempHeader, outHeader); + string tempHeader = outputDir + m->getRootName(m->getSimpleName(fastaFileNames[s])) + maskfile + "ccode.chimeras.tempHeader"; + m->openOutputFile(tempHeader, outHeader); outHeader << "For full window mapping info refer to " << mapInfo << endl << endl; outHeader.close(); - vector positions = divideFile(fastaFileNames[s], processors); + 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)])); @@ -312,7 +377,7 @@ int ChimeraCcodeCommand::execute(){ numSeqs = driver(lines[0], outputFileName, fastaFileNames[s], accnosFileName); - if (m->control_pressed) { remove(outputFileName.c_str()); remove(tempHeader.c_str()); remove(accnosFileName.c_str()); for (int j = 0; j < outputNames.size(); j++) { remove(outputNames[j].c_str()); } for (int i = 0; i < lines.size(); i++) { delete lines[i]; } lines.clear(); delete chimera; return 0; } + if (m->control_pressed) { remove(outputFileName.c_str()); remove(tempHeader.c_str()); remove(accnosFileName.c_str()); for (int j = 0; j < outputNames.size(); j++) { remove(outputNames[j].c_str()); } for (int i = 0; i < lines.size(); i++) { delete lines[i]; } outputTypes.clear(); lines.clear(); delete chimera; return 0; } }else{ processIDS.resize(0); @@ -324,20 +389,20 @@ int ChimeraCcodeCommand::execute(){ //append output files for(int i=1;iappendFiles((outputFileName + toString(processIDS[i]) + ".temp"), outputFileName); remove((outputFileName + toString(processIDS[i]) + ".temp").c_str()); } //append output files for(int i=1;iappendFiles((accnosFileName + toString(processIDS[i]) + ".temp"), accnosFileName); remove((accnosFileName + toString(processIDS[i]) + ".temp").c_str()); } if (m->control_pressed) { remove(outputFileName.c_str()); remove(accnosFileName.c_str()); - for (int j = 0; j < outputNames.size(); j++) { remove(outputNames[j].c_str()); } + for (int j = 0; j < outputNames.size(); j++) { remove(outputNames[j].c_str()); } outputTypes.clear(); for (int i = 0; i < lines.size(); i++) { delete lines[i]; } lines.clear(); delete chimera; return 0; @@ -348,11 +413,11 @@ int ChimeraCcodeCommand::execute(){ #else numSeqs = driver(lines[0], outputFileName, fastaFileNames[s], accnosFileName); - if (m->control_pressed) { remove(outputFileName.c_str()); remove(tempHeader.c_str()); remove(accnosFileName.c_str()); for (int j = 0; j < outputNames.size(); j++) { remove(outputNames[j].c_str()); } for (int i = 0; i < lines.size(); i++) { delete lines[i]; } lines.clear(); delete chimera; return 0; } + if (m->control_pressed) { remove(outputFileName.c_str()); remove(tempHeader.c_str()); remove(accnosFileName.c_str()); for (int j = 0; j < outputNames.size(); j++) { remove(outputNames[j].c_str()); } for (int i = 0; i < lines.size(); i++) { delete lines[i]; } outputTypes.clear(); lines.clear(); delete chimera; return 0; } #endif - appendFiles(outputFileName, tempHeader); + m->appendFiles(outputFileName, tempHeader); remove(outputFileName.c_str()); rename(tempHeader.c_str(), outputFileName.c_str()); @@ -360,10 +425,10 @@ int ChimeraCcodeCommand::execute(){ delete chimera; - outputNames.push_back(outputFileName); - outputNames.push_back(mapInfo); - outputNames.push_back(accnosFileName); - + outputNames.push_back(outputFileName); outputTypes["chimera"].push_back(outputFileName); + outputNames.push_back(mapInfo); outputTypes["mapinfo"].push_back(mapInfo); + outputNames.push_back(accnosFileName); outputTypes["accnos"].push_back(accnosFileName); + for (int i = 0; i < lines.size(); i++) { delete lines[i]; } lines.clear(); m->mothurOutEndLine(); m->mothurOut("It took " + toString(time(NULL) - start) + " secs to check " + toString(numSeqs) + " sequences."); m->mothurOutEndLine(); @@ -387,13 +452,13 @@ int ChimeraCcodeCommand::execute(){ int ChimeraCcodeCommand::driver(linePair* filePos, string outputFName, string filename, string accnos){ try { ofstream out; - openOutputFile(outputFName, out); + m->openOutputFile(outputFName, out); ofstream out2; - openOutputFile(accnos, out2); + m->openOutputFile(accnos, out2); ifstream inFASTA; - openInputFile(filename, inFASTA); + m->openInputFile(filename, inFASTA); inFASTA.seekg(filePos->start); @@ -404,7 +469,7 @@ int ChimeraCcodeCommand::driver(linePair* filePos, string outputFName, string fi if (m->control_pressed) { return 1; } - Sequence* candidateSeq = new Sequence(inFASTA); gobble(inFASTA); + Sequence* candidateSeq = new Sequence(inFASTA); m->gobble(inFASTA); if (candidateSeq->getName() != "") { //incase there is a commented sequence at the end of a file @@ -423,8 +488,12 @@ int ChimeraCcodeCommand::driver(linePair* filePos, string outputFName, string fi } delete candidateSeq; - unsigned long int pos = inFASTA.tellg(); - if ((pos == -1) || (pos >= filePos->end)) { break; } + #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) + unsigned long int pos = inFASTA.tellg(); + if ((pos == -1) || (pos >= filePos->end)) { break; } + #else + if (inFASTA.eof()) { break; } + #endif //report progress if((count) % 100 == 0){ m->mothurOut("Processing sequence: " + toString(count)); m->mothurOutEndLine(); } @@ -468,7 +537,7 @@ int ChimeraCcodeCommand::driverMPI(int start, int num, MPI_File& inMPI, MPI_File istringstream iss (tempBuf,istringstream::in); delete buf4; - Sequence* candidateSeq = new Sequence(iss); gobble(iss); + Sequence* candidateSeq = new Sequence(iss); m->gobble(iss); if (candidateSeq->getName() != "") { //incase there is a commented sequence at the end of a file @@ -481,7 +550,7 @@ int ChimeraCcodeCommand::driverMPI(int start, int num, MPI_File& inMPI, MPI_File if (m->control_pressed) { delete candidateSeq; return 1; } //print results - bool isChimeric = chimera->print(outMPI, outAccMPI); + chimera->print(outMPI, outAccMPI); } } delete candidateSeq; @@ -522,13 +591,17 @@ int ChimeraCcodeCommand::createProcesses(string outputFileName, string filename, //pass numSeqs to parent ofstream out; - string tempFile = toString(getpid()) + ".temp"; - openOutputFile(tempFile, out); + string tempFile = outputFileName + toString(getpid()) + ".num.temp"; + m->openOutputFile(tempFile, out); out << num << endl; out.close(); exit(0); - }else { m->mothurOut("unable to spawn the necessary processes."); m->mothurOutEndLine(); exit(0); } + }else { + m->mothurOut("[ERROR]: unable to spawn the necessary processes."); m->mothurOutEndLine(); + for (int i = 0; i < processIDS.size(); i++) { kill (processIDS[i], SIGINT); } + exit(0); + } } //force parent to wait until all the processes are done @@ -539,8 +612,8 @@ int ChimeraCcodeCommand::createProcesses(string outputFileName, string filename, for (int i = 0; i < processIDS.size(); i++) { ifstream in; - string tempFile = toString(processIDS[i]) + ".temp"; - openInputFile(tempFile, in); + string tempFile = outputFileName + 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()); }