X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=clearcutcommand.cpp;h=1b0a532cace0792297ce3162a03c7a382b66b282;hp=f8d389c60d81654f944e6b892ef7ad19a6d91859;hb=b206f634aae1b4ce13978d203247fb64757d5482;hpb=5a86e9e5a5a9e061e17b3ae64fb8881f14e53b8a diff --git a/clearcutcommand.cpp b/clearcutcommand.cpp index f8d389c..1b0a532 100644 --- a/clearcutcommand.cpp +++ b/clearcutcommand.cpp @@ -8,21 +8,125 @@ */ #include "clearcutcommand.h" -#include "globaldata.hpp" +#ifdef __cplusplus +extern "C" { +#endif +#include "clearcut.h" +#ifdef __cplusplus +} +#endif +//********************************************************************************************************************** +vector ClearcutCommand::setParameters(){ + try { + CommandParameter pphylip("phylip", "InputTypes", "", "", "FastaPhylip", "FastaPhylip", "none","tree",false,false,true); parameters.push_back(pphylip); + CommandParameter pfasta("fasta", "InputTypes", "", "", "FastaPhylip", "FastaPhylip", "none","tree",false,false,true); parameters.push_back(pfasta); + CommandParameter pverbose("verbose", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(pverbose); + CommandParameter pquiet("quiet", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(pquiet); + CommandParameter pversion("version", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(pversion); + CommandParameter pseed("seed", "String", "", "", "*", "", "","",false,false); parameters.push_back(pseed); + CommandParameter pnorandom("norandom", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(pnorandom); + CommandParameter pshuffle("shuffle", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(pshuffle); + CommandParameter pneighbor("neighbor", "Boolean", "", "T", "", "", "","",false,false); parameters.push_back(pneighbor); + CommandParameter pexpblen("expblen", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(pexpblen); + CommandParameter pexpdist("expdist", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(pexpdist); + CommandParameter pDNA("DNA", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(pDNA); + CommandParameter pprotein("protein", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(pprotein); + CommandParameter pjukes("jukes", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(pjukes); + CommandParameter pkimura("kimura", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(pkimura); + CommandParameter pstdout("stdout", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(pstdout); + CommandParameter pntrees("ntrees", "Number", "", "1", "", "", "","",false,false); parameters.push_back(pntrees); + CommandParameter pmatrixout("matrixout", "String", "", "", "", "", "","",false,false); parameters.push_back(pmatrixout); + 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, "ClearcutCommand", "setParameters"); + exit(1); + } +} +//********************************************************************************************************************** +string ClearcutCommand::getHelpString(){ + try { + string helpString = ""; + helpString += "The clearcut command interfaces mothur with the clearcut program written by Initiative for Bioinformatics and Evolutionary Studies (IBEST) at the University of Idaho.\n"; + helpString += "For more information about clearcut refer to http://bioinformatics.hungry.com/clearcut/ \n"; + helpString += "The clearcut command parameters are phylip, fasta, version, verbose, quiet, seed, norandom, shuffle, neighbor, expblen, expdist, ntrees, matrixout, stdout, kimura, jukes, protein, DNA. \n"; + helpString += "The phylip parameter allows you to enter your phylip formatted distance matrix. \n"; + helpString += "The fasta parameter allows you to enter your aligned fasta file, if you enter a fastafile you specify if the sequences are DNA or protein using the DNA or protein parameters. \n"; + + helpString += "The version parameter prints out the version of clearcut you are using, default=F. \n"; + helpString += "The verbose parameter prints out more output from clearcut, default=F. \n"; + helpString += "The quiet parameter turns on silent operation mode, default=F. \n"; + helpString += "The seed parameter allows you to explicitly set the PRNG seed to a specific value. \n"; + helpString += "The norandom parameter allows you to attempt joins deterministically, default=F. \n"; + helpString += "The shuffle parameter allows you to randomly shuffle the distance matrix, default=F. \n"; + helpString += "The neighbor parameter allows you to use traditional Neighbor-Joining algorithm, default=T. \n"; + + helpString += "The DNA parameter allows you to indicate your fasta file contains DNA sequences, default=F. \n"; + helpString += "The protein parameter allows you to indicate your fasta file contains protein sequences, default=F. \n"; + + helpString += "The stdout parameter outputs your tree to STDOUT, default=F. \n"; + helpString += "The matrixout parameter allows you to specify a filename to output a distance matrix to. \n"; + helpString += "The ntrees parameter allows you to specify the number of output trees, default=1. \n"; + helpString += "The expblen parameter allows you to use exponential notation for branch lengths, default=F. \n"; + helpString += "The expdist parameter allows you to use exponential notation for distance outputs, default=F. \n"; + + helpString += "The clearcut command should be in the following format: \n"; + helpString += "clearcut(phylip=yourDistanceFile) \n"; + helpString += "Example: clearcut(phylip=abrecovery.phylip.dist) \n"; + return helpString; + } + catch(exception& e) { + m->errorOut(e, "ClearcutCommand", "getHelpString"); + exit(1); + } +} +//********************************************************************************************************************** +string ClearcutCommand::getOutputPattern(string type) { + try { + string pattern = ""; + + if (type == "matrixout") { pattern = "[filename],"; } + else if (type == "tree") { pattern = "[filename],tre"; } + else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; } + + return pattern; + } + catch(exception& e) { + m->errorOut(e, "ClearcutCommand", "getOutputPattern"); + exit(1); + } +} +//********************************************************************************************************************** +ClearcutCommand::ClearcutCommand(){ + try { + abort = true; calledHelp = true; + setParameters(); + vector tempOutNames; + outputTypes["tree"] = tempOutNames; + outputTypes["matrixout"] = tempOutNames; + } + catch(exception& e) { + m->errorOut(e, "ClearcutCommand", "ClearcutCommand"); + exit(1); + } +} /**************************************************************************************/ ClearcutCommand::ClearcutCommand(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","phylip","version","verbose","quiet","seed","norandom","shuffle","neighbor","expblen", - "expdist","ntrees","matrixout","stdout","kimura","jukes","protein","DNA","stdin","outputdir","inputdir"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + vector myArray = setParameters(); OptionParser parser(option); map parameters = parser.getParameters(); @@ -35,6 +139,11 @@ ClearcutCommand::ClearcutCommand(string option) { if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; } } + //initialize outputTypes + vector tempOutNames; + outputTypes["tree"] = tempOutNames; + outputTypes["matrixout"] = 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 +152,7 @@ ClearcutCommand::ClearcutCommand(string option) { it = parameters.find("fasta"); //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["fasta"] = inputDir + it->second; } } @@ -51,7 +160,7 @@ ClearcutCommand::ClearcutCommand(string option) { it = parameters.find("phylip"); //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["phylip"] = inputDir + it->second; } } @@ -61,68 +170,78 @@ ClearcutCommand::ClearcutCommand(string option) { fastafile = validParameter.validFile(parameters, "fasta", true); if (fastafile == "not open") { fastafile = ""; abort = true; } else if (fastafile == "not found") { fastafile = ""; } - else { inputFile = fastafile; } + else { inputFile = fastafile; m->setFastaFile(fastafile); } phylipfile = validParameter.validFile(parameters, "phylip", true); if (phylipfile == "not open") { phylipfile = ""; abort = true; } else if (phylipfile == "not found") { phylipfile = ""; } - else { inputFile = phylipfile; } + else { inputFile = phylipfile; m->setPhylipFile(phylipfile); } - if ((phylipfile == "") && (fastafile == "")) { m->mothurOut("You must provide either a phylip formatted distance matrix or an aligned fasta file."); m->mothurOutEndLine(); abort=true; } + if ((phylipfile == "") && (fastafile == "")) { + //is there are current file available for either of these? + //give priority to phylip, then fasta + phylipfile = m->getPhylipFile(); + if (phylipfile != "") { inputFile = phylipfile; m->mothurOut("Using " + phylipfile + " as input file for the phylip parameter."); m->mothurOutEndLine(); } + else { + fastafile = m->getFastaFile(); + if (fastafile != "") { inputFile = fastafile; m->mothurOut("Using " + fastafile + " as input file for the fasta parameter."); m->mothurOutEndLine(); } + else { + m->mothurOut("No valid current files. You must provide a phylip or fasta file before you can use the clearcut command."); m->mothurOutEndLine(); + abort = true; + } + } + } if ((phylipfile != "") && (fastafile != "")) { m->mothurOut("You must provide either a phylip formatted distance matrix or an aligned fasta file, not BOTH."); m->mothurOutEndLine(); abort=true; } //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 = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){ outputDir = m->hasPath(inputFile); } string temp; temp = validParameter.validFile(parameters, "version", false); if (temp == "not found"){ temp = "F"; } - version = isTrue(temp); + version = m->isTrue(temp); temp = validParameter.validFile(parameters, "verbose", false); if (temp == "not found"){ temp = "F"; } - verbose = isTrue(temp); + verbose = m->isTrue(temp); temp = validParameter.validFile(parameters, "quiet", false); if (temp == "not found"){ temp = "F"; } - quiet = isTrue(temp); + quiet = m->isTrue(temp); seed = validParameter.validFile(parameters, "seed", false); if (seed == "not found"){ seed = "*"; } temp = validParameter.validFile(parameters, "norandom", false); if (temp == "not found"){ temp = "F"; } - norandom = isTrue(temp); + norandom = m->isTrue(temp); temp = validParameter.validFile(parameters, "shuffle", false); if (temp == "not found"){ temp = "F"; } - shuffle = isTrue(temp); + shuffle = m->isTrue(temp); - temp = validParameter.validFile(parameters, "neighbor", false); if (temp == "not found"){ temp = "F"; } - neighbor = isTrue(temp); - - temp = validParameter.validFile(parameters, "stdin", false); if (temp == "not found"){ temp = "F"; } - stdin = isTrue(temp); + temp = validParameter.validFile(parameters, "neighbor", false); if (temp == "not found"){ temp = "T"; } + neighbor = m->isTrue(temp); temp = validParameter.validFile(parameters, "DNA", false); if (temp == "not found"){ temp = "F"; } - DNA = isTrue(temp); + DNA = m->isTrue(temp); temp = validParameter.validFile(parameters, "protein", false); if (temp == "not found"){ temp = "F"; } - protein = isTrue(temp); + protein = m->isTrue(temp); temp = validParameter.validFile(parameters, "jukes", false); if (temp == "not found"){ temp = "F"; } - jukes = isTrue(temp); + jukes = m->isTrue(temp); temp = validParameter.validFile(parameters, "kimura", false); if (temp == "not found"){ temp = "F"; } - kimura = isTrue(temp); + kimura = m->isTrue(temp); temp = validParameter.validFile(parameters, "stdout", false); if (temp == "not found"){ temp = "F"; } - stdout = isTrue(temp); + stdoutWanted = m->isTrue(temp); matrixout = validParameter.validFile(parameters, "matrixout", false); if (matrixout == "not found"){ matrixout = ""; } ntrees = validParameter.validFile(parameters, "ntrees", false); if (ntrees == "not found"){ ntrees = "1"; } temp = validParameter.validFile(parameters, "expblen", false); if (temp == "not found"){ temp = "F"; } - expblen = isTrue(temp); + expblen = m->isTrue(temp); temp = validParameter.validFile(parameters, "expdist", false); if (temp == "not found"){ temp = "F"; } - expdist = isTrue(temp); + expdist = m->isTrue(temp); if ((fastafile != "") && ((!DNA) && (!protein))) { m->mothurOut("You must specify the type of sequences you are using: DNA or protein"); m->mothurOutEndLine(); abort=true; } } @@ -133,96 +252,102 @@ ClearcutCommand::ClearcutCommand(string option) { exit(1); } } -//********************************************************************************************************************** - -void ClearcutCommand::help(){ - try { - m->mothurOut("The clearcut command interfaces mothur with the clearcut program written by Initiative for Bioinformatics and Evolutionary Studies (IBEST) at the University of Idaho.\n"); - m->mothurOut("For more information about clearcut refer to http://bioinformatics.hungry.com/clearcut/ \n"); - m->mothurOut("The clearcut executable must be in a folder called clearcut in the same folder as your mothur executable, similar to mothur's requirements for using blast. \n"); - m->mothurOut("The clearcut command parameters are phylip, fasta, version, verbose, quiet, seed, norandom, shuffle, neighbor, expblen, expdist, ntrees, matrixout, stdout, kimura, jukes, protein, DNA, stdin. \n"); - m->mothurOut("The phylip parameter allows you to enter your phylip formatted distance matrix. \n"); - m->mothurOut("The fasta parameter allows you to enter your aligned fasta file, if you enter a fastafile you specify if the sequences are DNA or protein using the DNA or protein parameters. \n"); - - m->mothurOut("The version parameter prints out the version of clearcut you are using, default=F. \n"); - m->mothurOut("The verbose parameter prints out more output from clearcut, default=F. \n"); - m->mothurOut("The quiet parameter turns on silent operation mode, default=F. \n"); - m->mothurOut("The seed parameter allows you to explicitly set the PRNG seed to a specific value. \n"); - m->mothurOut("The norandom parameter allows you to attempt joins deterministically, default=F. \n"); - m->mothurOut("The shuffle parameter allows you to randomly shuffle the distance matrix, default=F. \n"); - m->mothurOut("The neighbor parameter allows you to use traditional Neighbor-Joining algorithm, default=F. \n"); - - m->mothurOut("The stdin parameter reads input from STDIN, default=F. \n"); - m->mothurOut("The DNA parameter allows you to indicate your fasta file contains DNA sequences, default=F. \n"); - m->mothurOut("The protein parameter allows you to indicate your fasta file contains protein sequences, default=F. \n"); - - m->mothurOut("The stdout parameter outputs your tree to STDOUT, default=F. \n"); - m->mothurOut("The matrixout parameter allows you to specify a filename to output a distance matrix to. \n"); - m->mothurOut("The ntrees parameter allows you to specify the number of output trees, default=1. \n"); - m->mothurOut("The expblen parameter allows you to use exponential notation for branch lengths, default=F. \n"); - m->mothurOut("The expdist parameter allows you to use exponential notation for distance outputs, default=F. \n"); - - m->mothurOut("The clearcut command should be in the following format: \n"); - m->mothurOut("clearcut(phylip=yourDistanceFile) \n"); - m->mothurOut("Example: clearcut(phylip=abrecovery.phylip.dist) \n"); - } - catch(exception& e) { - m->errorOut(e, "ClearcutCommand", "help"); - exit(1); - } -} - /**************************************************************************************/ int ClearcutCommand::execute() { try { - if (abort == true) { return 0; } - + if (abort == true) { if (calledHelp) { return 0; } return 2; } + //prepare filename - string outputName = outputDir + getRootName(getSimpleName(inputFile)) + "tre"; + map variables; + variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(inputFile)); + string outputName = getOutputFileName("tree", variables); + outputNames.push_back(outputName); outputTypes["tree"].push_back(outputName); - //get location of clearcut - GlobalData* globaldata = GlobalData::getInstance(); - string path = globaldata->argv; - path = path.substr(0, (path.find_last_of('m'))); - - string clearcutCommand = path + "clearcut/clearcut "; + vector cPara; + char* tempClearcut = new char[9]; + *tempClearcut = '\0'; strncat(tempClearcut, "clearcut", 8); + cPara.push_back(tempClearcut); + //you gave us a distance matrix - if (phylipfile != "") { clearcutCommand += "--distance "; } + if (phylipfile != "") { char* temp = new char[11]; *temp = '\0'; strncat(temp, "--distance", 10); cPara.push_back(temp); } //you gave us a fastafile - if (fastafile != "") { clearcutCommand += "--alignment "; } - - if (version) { clearcutCommand += "--version "; } - if (verbose) { clearcutCommand += "--verbose "; } - if (quiet) { clearcutCommand += "--quiet "; } - if (seed != "*") { clearcutCommand += "--seed=" + seed + " "; } - if (norandom) { clearcutCommand += "--norandom "; } - if (shuffle) { clearcutCommand += "--shuffle "; } - if (neighbor) { clearcutCommand += "--neighbor "; } - - if (stdin) { clearcutCommand += "--stdin "; } - else { clearcutCommand += "--in=" + inputFile + " "; } - if (stdout) { clearcutCommand += "--stdout "; } - else { clearcutCommand += "--out=" + outputName + " "; } - - if (DNA) { clearcutCommand += "--DNA "; } - if (protein) { clearcutCommand += "--protein "; } - if (jukes) { clearcutCommand += "--jukes "; } - if (kimura) { clearcutCommand += "--kimura "; } - if (matrixout != "") { clearcutCommand += "--matrixout=" + matrixout + " "; } - if (ntrees != "1") { clearcutCommand += "--ntrees=" + ntrees + " "; } - if (expblen) { clearcutCommand += "--expblen "; } - if (expdist) { clearcutCommand += "--expdist "; } - - //run clearcut - system(clearcutCommand.c_str()); - - if (!stdout) { + if (fastafile != "") { char* temp = new char[12]; *temp = '\0'; strncat(temp, "--alignment", 11); cPara.push_back(temp); } + + if (version) { char* temp = new char[10]; *temp = '\0'; strncat(temp, "--version", 9); cPara.push_back(temp); } + if (verbose) { char* temp = new char[10]; *temp = '\0'; strncat(temp, "--verbose", 9); cPara.push_back(temp); } + if (quiet) { char* temp = new char[8]; *temp = '\0'; strncat(temp, "--quiet", 7); cPara.push_back(temp); } + if (seed != "*") { + string tempSeed = "--seed=" + seed; + char* temp = new char[tempSeed.length()+1]; + *temp = '\0'; strncat(temp, tempSeed.c_str(), tempSeed.length()); + cPara.push_back(temp); + } + if (norandom) { char* temp = new char[11]; *temp = '\0'; strncat(temp, "--norandom", 10); cPara.push_back(temp); } + if (shuffle) { char* temp = new char[10]; *temp = '\0'; strncat(temp, "--shuffle", 9); cPara.push_back(temp); } + if (neighbor) { char* temp = new char[11]; *temp = '\0'; strncat(temp, "--neighbor", 10); cPara.push_back(temp); } + + string tempIn = "--in=" + inputFile; + char* tempI = new char[tempIn.length()+1]; + *tempI = '\0'; strncat(tempI, tempIn.c_str(), tempIn.length()); + cPara.push_back(tempI); + + if (stdoutWanted) { char* temp = new char[9]; *temp = '\0'; strncat(temp, "--stdout", 8); cPara.push_back(temp); } + else{ + string tempOut = "--out=" + outputName; + char* temp = new char[tempOut.length()+1]; + *temp = '\0'; strncat(temp, tempOut.c_str(), tempOut.length()); + cPara.push_back(temp); + } + + if (DNA) { char* temp = new char[6]; *temp = '\0'; strncat(temp, "--DNA", 5); cPara.push_back(temp); } + if (protein) { char* temp = new char[10]; *temp = '\0'; strncat(temp, "--protein", 9); cPara.push_back(temp); } + if (jukes) { char* temp = new char[8]; *temp = '\0'; strncat(temp, "--jukes", 7); cPara.push_back(temp); } + if (kimura) { char* temp = new char[9]; *temp = '\0'; strncat(temp, "--kimura", 8); cPara.push_back(temp); } + if (matrixout != "") { + string tempMatrix = "--matrixout=" + outputDir + matrixout; + char* temp = new char[tempMatrix.length()+1]; + *temp = '\0'; strncat(temp, tempMatrix.c_str(), tempMatrix.length()); + cPara.push_back(temp); + outputNames.push_back((outputDir + matrixout)); + outputTypes["matrixout"].push_back((outputDir + matrixout)); + } + + if (ntrees != "1") { + string tempNtrees = "--ntrees=" + ntrees; + char* temp = new char[tempNtrees.length()+1]; + *temp = '\0'; strncat(temp, tempNtrees.c_str(), tempNtrees.length()); + cPara.push_back(temp); + } + + if (expblen) { char* temp = new char[10]; *temp = '\0'; strncat(temp, "--expblen", 9); cPara.push_back(temp); } + if (expdist) { char* temp = new char[10]; *temp = '\0'; strncat(temp, "--expdist", 9); cPara.push_back(temp); } + + char** clearcutParameters; + clearcutParameters = new char*[cPara.size()]; + for (int i = 0; i < cPara.size(); i++) { clearcutParameters[i] = cPara[i]; } + int numArgs = cPara.size(); + + clearcut_main(numArgs, clearcutParameters); + + //free memory + for(int i = 0; i < cPara.size(); i++) { delete[] cPara[i]; } + delete[] clearcutParameters; + + if (!stdoutWanted) { + + //set first tree file as new current treefile + string currentTree = ""; + itTypes = outputTypes.find("tree"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { currentTree = (itTypes->second)[0]; m->setTreeFile(currentTree); } + } + m->mothurOutEndLine(); m->mothurOut("Output File Names: "); m->mothurOutEndLine(); - m->mothurOut(outputName); m->mothurOutEndLine(); + for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); } m->mothurOutEndLine(); }