X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=seqsummarycommand.cpp;h=2f3638d2ae8bfc9f051c60520c3bf9429afc9a45;hb=92de7f976371d41441ad41f02ca83af8b43cef5c;hp=7d074c4e05d441d350d552d2eb3796007191943a;hpb=8bc3e5b38c2317a1715f53be22fa96455868c281;p=mothur.git diff --git a/seqsummarycommand.cpp b/seqsummarycommand.cpp index 7d074c4..2f3638d 100644 --- a/seqsummarycommand.cpp +++ b/seqsummarycommand.cpp @@ -11,49 +11,50 @@ #include "sequence.hpp" //********************************************************************************************************************** -vector SeqSummaryCommand::getValidParameters(){ +vector SeqSummaryCommand::setParameters(){ try { - string Array[] = {"fasta","processors","outputdir","inputdir"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(pfasta); + CommandParameter pname("name", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(pname); + 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, "SeqSummaryCommand", "getValidParameters"); - exit(1); - } -} -//********************************************************************************************************************** -SeqSummaryCommand::SeqSummaryCommand(){ - try { - //initialize outputTypes - vector tempOutNames; - outputTypes["summary"] = tempOutNames; - } - catch(exception& e) { - m->errorOut(e, "SeqSummaryCommand", "SeqSummaryCommand"); + m->errorOut(e, "SeqSummaryCommand", "setParameters"); exit(1); } } //********************************************************************************************************************** -vector SeqSummaryCommand::getRequiredParameters(){ +string SeqSummaryCommand::getHelpString(){ try { - string Array[] = {"fasta"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); - return myArray; + string helpString = ""; + helpString += "The summary.seqs command reads a fastafile and summarizes the sequences.\n"; + helpString += "The summary.seqs command parameters are fasta, name and processors, fasta is required, unless you have a valid current fasta file.\n"; + helpString += "The name parameter allows you to enter a name file associated with your fasta file. \n"; + helpString += "The summary.seqs command should be in the following format: \n"; + helpString += "summary.seqs(fasta=yourFastaFile, processors=2) \n"; + helpString += "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFastaFile).\n"; + return helpString; } catch(exception& e) { - m->errorOut(e, "SeqSummaryCommand", "getRequiredParameters"); + m->errorOut(e, "SeqSummaryCommand", "getHelpString"); exit(1); } } + //********************************************************************************************************************** -vector SeqSummaryCommand::getRequiredFiles(){ +SeqSummaryCommand::SeqSummaryCommand(){ try { - vector myArray; - return myArray; + abort = true; calledHelp = true; + setParameters(); + vector tempOutNames; + outputTypes["summary"] = tempOutNames; } catch(exception& e) { - m->errorOut(e, "SeqSummaryCommand", "getRequiredFiles"); + m->errorOut(e, "SeqSummaryCommand", "SeqSummaryCommand"); exit(1); } } @@ -61,15 +62,13 @@ vector SeqSummaryCommand::getRequiredFiles(){ SeqSummaryCommand::SeqSummaryCommand(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 { - //valid paramters for this command - string Array[] = {"fasta","processors","outputdir","inputdir"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + vector myArray = setParameters(); OptionParser parser(option); map parameters = parser.getParameters(); @@ -94,6 +93,14 @@ SeqSummaryCommand::SeqSummaryCommand(string option) { //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["fasta"] = inputDir + it->second; } } + + it = parameters.find("name"); + //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["name"] = inputDir + it->second; } + } } //initialize outputTypes @@ -103,7 +110,15 @@ SeqSummaryCommand::SeqSummaryCommand(string option) { //check for required parameters fastafile = validParameter.validFile(parameters, "fasta", true); if (fastafile == "not open") { abort = true; } - else if (fastafile == "not found") { fastafile = ""; m->mothurOut("fasta is a required parameter for the summary.seqs command."); m->mothurOutEndLine(); abort = true; } + else if (fastafile == "not found") { + fastafile = m->getFastaFile(); + if (fastafile != "") { m->mothurOut("Using " + fastafile + " 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; } + } + + namefile = validParameter.validFile(parameters, "name", true); + if (namefile == "not open") { namefile = ""; abort = true; } + else if (namefile == "not found") { namefile = ""; } //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"){ @@ -111,8 +126,9 @@ SeqSummaryCommand::SeqSummaryCommand(string option) { outputDir += m->hasPath(fastafile); //if user entered a file with a path then preserve it } - string temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found"){ temp = "1"; } - convert(temp, processors); + string temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found"){ temp = m->getProcessors(); } + m->setProcessors(temp); + convert(temp, processors); } @@ -122,32 +138,15 @@ SeqSummaryCommand::SeqSummaryCommand(string option) { exit(1); } } -//********************************************************************************************************************** - -void SeqSummaryCommand::help(){ - try { - m->mothurOut("The summary.seqs command reads a fastafile and summarizes the sequences.\n"); - m->mothurOut("The summary.seqs command parameters are fasta and processors, fasta is required.\n"); - m->mothurOut("The summary.seqs command should be in the following format: \n"); - m->mothurOut("summary.seqs(fasta=yourFastaFile, processors=2) \n"); - m->mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFastaFile).\n\n"); - } - catch(exception& e) { - m->errorOut(e, "SeqSummaryCommand", "help"); - exit(1); - } -} - -//*************************************************************************************************************** - -SeqSummaryCommand::~SeqSummaryCommand(){ /* do nothing */ } - //*************************************************************************************************************** int SeqSummaryCommand::execute(){ try{ - if (abort == true) { return 0; } + if (abort == true) { if (calledHelp) { return 0; } return 2; } + + //set current fasta to fastafile + m->setFastaFile(fastafile); string summaryFile = outputDir + m->getSimpleName(fastafile) + ".summary"; @@ -158,6 +157,10 @@ int SeqSummaryCommand::execute(){ vector seqLength; vector ambigBases; vector longHomoPolymer; + + if (namefile != "") { nameMap = m->readNames(namefile); } + + if (m->control_pressed) { return 0; } #ifdef USE_MPI int pid, numSeqsPerProcessor; @@ -186,7 +189,7 @@ int SeqSummaryCommand::execute(){ if (pid == 0) { //you are the root process //print header - string outputString = "seqname\tstart\tend\tnbases\tambigs\tpolymer\n"; + string outputString = "seqname\tstart\tend\tnbases\tambigs\tpolymer\tnumSeqs\n"; int length = outputString.length(); char* buf2 = new char[length]; memcpy(buf2, outputString.c_str(), length); @@ -311,13 +314,14 @@ int SeqSummaryCommand::execute(){ sort(seqLength.begin(), seqLength.end()); sort(ambigBases.begin(), ambigBases.end()); sort(longHomoPolymer.begin(), longHomoPolymer.end()); - - int ptile0_25 = int(numSeqs * 0.025); - int ptile25 = int(numSeqs * 0.250); - int ptile50 = int(numSeqs * 0.500); - int ptile75 = int(numSeqs * 0.750); - int ptile97_5 = int(numSeqs * 0.975); - int ptile100 = numSeqs - 1; + int size = startPosition.size(); + + int ptile0_25 = int(size * 0.025); + int ptile25 = int(size * 0.250); + int ptile50 = int(size * 0.500); + int ptile75 = int(size * 0.750); + int ptile97_5 = int(size * 0.975); + int ptile100 = size - 1; //to compensate for blank sequences that would result in startPosition and endPostion equalling -1 if (startPosition[0] == -1) { startPosition[0] = 0; } @@ -334,7 +338,8 @@ int SeqSummaryCommand::execute(){ m->mothurOut("75%-tile:\t" + toString(startPosition[ptile75]) + "\t" + toString(endPosition[ptile75]) + "\t" + toString(seqLength[ptile75]) + "\t" + toString(ambigBases[ptile75]) + "\t" + toString(longHomoPolymer[ptile75])); m->mothurOutEndLine(); m->mothurOut("97.5%-tile:\t" + toString(startPosition[ptile97_5]) + "\t" + toString(endPosition[ptile97_5]) + "\t" + toString(seqLength[ptile97_5]) + "\t" + toString(ambigBases[ptile97_5]) + "\t" + toString(longHomoPolymer[ptile97_5])); m->mothurOutEndLine(); m->mothurOut("Maximum:\t" + toString(startPosition[ptile100]) + "\t" + toString(endPosition[ptile100]) + "\t" + toString(seqLength[ptile100]) + "\t" + toString(ambigBases[ptile100]) + "\t" + toString(longHomoPolymer[ptile100])); m->mothurOutEndLine(); - m->mothurOut("# of Seqs:\t" + toString(numSeqs)); m->mothurOutEndLine(); + if (namefile == "") { m->mothurOut("# of Seqs:\t" + toString(numSeqs)); m->mothurOutEndLine(); } + else { m->mothurOut("# of unique seqs:\t" + toString(numSeqs)); m->mothurOutEndLine(); m->mothurOut("total # of seqs:\t" + toString(startPosition.size())); m->mothurOutEndLine(); } if (m->control_pressed) { remove(summaryFile.c_str()); return 0; } @@ -363,7 +368,7 @@ int SeqSummaryCommand::driverCreateSummary(vector& startPosition, vectorstart == 0) { - outSummary << "seqname\tstart\tend\tnbases\tambigs\tpolymer" << endl; + outSummary << "seqname\tstart\tend\tnbases\tambigs\tpolymer\tnumSeqs" << endl; } ifstream in; @@ -381,17 +386,30 @@ int SeqSummaryCommand::driverCreateSummary(vector& startPosition, vectorgobble(in); if (current.getName() != "") { - startPosition.push_back(current.getStartPos()); - endPosition.push_back(current.getEndPos()); - seqLength.push_back(current.getNumBases()); - ambigBases.push_back(current.getAmbigBases()); - longHomoPolymer.push_back(current.getLongHomoPolymer()); + int num = 1; + if (namefile != "") { + //make sure this sequence is in the namefile, else error + map::iterator it = nameMap.find(current.getName()); + + if (it == nameMap.end()) { m->mothurOut("[ERROR]: " + current.getName() + " is not in your namefile, please correct."); m->mothurOutEndLine(); m->control_pressed = true; } + else { num = it->second; } + } + + //for each sequence this sequence represents + for (int i = 0; i < num; i++) { + startPosition.push_back(current.getStartPos()); + endPosition.push_back(current.getEndPos()); + seqLength.push_back(current.getNumBases()); + ambigBases.push_back(current.getAmbigBases()); + longHomoPolymer.push_back(current.getLongHomoPolymer()); + } + + count++; outSummary << current.getName() << '\t'; outSummary << current.getStartPos() << '\t' << current.getEndPos() << '\t'; outSummary << current.getNumBases() << '\t' << current.getAmbigBases() << '\t'; - outSummary << current.getLongHomoPolymer() << endl; - count++; + outSummary << current.getLongHomoPolymer() << '\t' << num << endl; } #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) @@ -425,7 +443,6 @@ int SeqSummaryCommand::MPICreateSummary(int start, int num, vector& startPo MPI_Status status; MPI_Comm_rank(MPI_COMM_WORLD, &pid); - for(int i=0;icontrol_pressed) { return 0; } @@ -444,14 +461,27 @@ int SeqSummaryCommand::MPICreateSummary(int start, int num, vector& startPo Sequence current(iss); if (current.getName() != "") { - startPosition.push_back(current.getStartPos()); - endPosition.push_back(current.getEndPos()); - seqLength.push_back(current.getNumBases()); - ambigBases.push_back(current.getAmbigBases()); - longHomoPolymer.push_back(current.getLongHomoPolymer()); + + int num = 1; + if (namefile != "") { + //make sure this sequence is in the namefile, else error + map::iterator it = nameMap.find(current.getName()); + + if (it == nameMap.end()) { cout << "[ERROR]: " << current.getName() << " is not in your namefile, please correct." << endl; m->control_pressed = true; } + else { num = it->second; } + } + + //for each sequence this sequence represents + for (int i = 0; i < num; i++) { + startPosition.push_back(current.getStartPos()); + endPosition.push_back(current.getEndPos()); + seqLength.push_back(current.getNumBases()); + ambigBases.push_back(current.getAmbigBases()); + longHomoPolymer.push_back(current.getLongHomoPolymer()); + } string outputString = current.getName() + "\t" + toString(current.getStartPos()) + "\t" + toString(current.getEndPos()) + "\t"; - outputString += toString(current.getNumBases()) + "\t" + toString(current.getAmbigBases()) + "\t" + toString(current.getLongHomoPolymer()) + "\n"; + outputString += toString(current.getNumBases()) + "\t" + toString(current.getAmbigBases()) + "\t" + toString(current.getLongHomoPolymer()) + "\t" + toString(num) + "\n"; //output to file length = outputString.length(); @@ -495,6 +525,7 @@ int SeqSummaryCommand::createProcessesCreateSummary(vector& startPosition, m->openOutputFile(tempFile, out); out << num << endl; + out << startPosition.size() << endl; for (int k = 0; k < startPosition.size(); k++) { out << startPosition[k] << '\t'; } out << endl; for (int k = 0; k < endPosition.size(); k++) { out << endPosition[k] << '\t'; } out << endl; for (int k = 0; k < seqLength.size(); k++) { out << seqLength[k] << '\t'; } out << endl; @@ -504,7 +535,11 @@ int SeqSummaryCommand::createProcessesCreateSummary(vector& startPosition, 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 @@ -521,6 +556,7 @@ int SeqSummaryCommand::createProcessesCreateSummary(vector& startPosition, int temp, tempNum; in >> tempNum; m->gobble(in); num += tempNum; + in >> tempNum; m->gobble(in); for (int k = 0; k < tempNum; k++) { in >> temp; startPosition.push_back(temp); } m->gobble(in); for (int k = 0; k < tempNum; k++) { in >> temp; endPosition.push_back(temp); } m->gobble(in); for (int k = 0; k < tempNum; k++) { in >> temp; seqLength.push_back(temp); } m->gobble(in); @@ -539,6 +575,7 @@ int SeqSummaryCommand::createProcessesCreateSummary(vector& startPosition, exit(1); } } -//*************************************************************************************************************** +/**********************************************************************************************************************/ +