X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=readdistcommand.cpp;h=8bf6996333b246814a28009d309ab8f3b6bf8718;hb=a6cf29fa4dac0909c7582cb1094151d34093ee76;hp=31d8308414755601166268f6088dd7142f7dfaad;hpb=0470f6d037aacb3563c3f7010708120a4a67d4e6;p=mothur.git diff --git a/readdistcommand.cpp b/readdistcommand.cpp index 31d8308..8bf6996 100644 --- a/readdistcommand.cpp +++ b/readdistcommand.cpp @@ -12,91 +12,139 @@ #include "readcolumn.h" #include "readmatrix.hpp" -ReadDistCommand::ReadDistCommand(string option){ +//********************************************************************************************************************** +ReadDistCommand::ReadDistCommand(string option) { try { - globaldata = GlobalData::getInstance(); - 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[] = {"phylip","column", "name","cutoff","precision", "group"}; + /*//valid paramters for this command + string Array[] = {"phylip", "column", "name", "cutoff", "precision", "group","outputdir","inputdir","sim"}; vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); - parser = new OptionParser(); - parser->parse(option, parameters); delete parser; + OptionParser parser(option); + map parameters = parser.getParameters(); - ValidParameters* validParameter = new ValidParameters(); + ValidParameters validParameter; + map::iterator it; //check to make sure all parameters are valid for command for (it = parameters.begin(); it != parameters.end(); it++) { - if (validParameter->isValidParameter(it->first, myArray, it->second) != true) { abort = true; } + if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; } } globaldata->newRead(); + //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 = ""; } + else { + string path; + it = parameters.find("phylip"); + //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["phylip"] = inputDir + it->second; } + } + + it = parameters.find("column"); + //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["column"] = 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; } + } + + it = parameters.find("group"); + //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["group"] = inputDir + it->second; } + } + } + + //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 = ""; } + //check for required parameters - phylipfile = validParameter->validFile(parameters, "phylip", true); + phylipfile = validParameter.validFile(parameters, "phylip", true); if (phylipfile == "not open") { abort = true; } else if (phylipfile == "not found") { phylipfile = ""; } else { globaldata->setPhylipFile(phylipfile); globaldata->setFormat("phylip"); } - columnfile = validParameter->validFile(parameters, "column", true); + columnfile = validParameter.validFile(parameters, "column", true); if (columnfile == "not open") { abort = true; } else if (columnfile == "not found") { columnfile = ""; } else { globaldata->setColumnFile(columnfile); globaldata->setFormat("column"); } - groupfile = validParameter->validFile(parameters, "group", true); + groupfile = validParameter.validFile(parameters, "group", true); if (groupfile == "not open") { abort = true; } else if (groupfile == "not found") { groupfile = ""; } else { globaldata->setGroupFile(groupfile); - groupMap = new GroupMap(groupfile); - groupMap->readMap(); + //groupMap = new GroupMap(groupfile); + //groupMap->readMap(); } - - namefile = validParameter->validFile(parameters, "name", true); + + namefile = validParameter.validFile(parameters, "name", true); if (namefile == "not open") { abort = true; } else if (namefile == "not found") { namefile = ""; } else { globaldata->setNameFile(namefile); } - //you are doing a list and group shared - if ((phylipfile != "") && (groupfile != "")) { globaldata->setFormat("matrix"); } + if ((phylipfile != "") && (groupfile != "")) { + globaldata->setFormat("matrix"); } - if ((phylipfile == "") && (columnfile == "")) { cout << "When executing a read.dist command you must enter a phylip or a column." << endl; abort = true; } - else if ((phylipfile != "") && (columnfile != "")) { cout << "When executing a read.dist command you must enter ONLY ONE of the following: phylip or column." << endl; abort = true; } + if ((phylipfile == "") && (columnfile == "")) { m->mothurOut("When executing a read.dist command you must enter a phylip or a column."); m->mothurOutEndLine(); abort = true; } + else if ((phylipfile != "") && (columnfile != "")) { m->mothurOut("When executing a read.dist command you must enter ONLY ONE of the following: phylip or column."); m->mothurOutEndLine(); abort = true; } if (columnfile != "") { if (namefile == "") { cout << "You need to provide a namefile if you are going to use the column format." << endl; abort = true; } } - + //check for optional parameter and set defaults // ...at some point should added some additional type checking... //get user cutoff and precision or use defaults string temp; - temp = validParameter->validFile(parameters, "precision", false); if (temp == "not found") { temp = "100"; } - convert(temp, precision); + temp = validParameter.validFile(parameters, "precision", false); if (temp == "not found") { temp = "100"; } + m->mothurConvert(temp, precision); + + temp = validParameter.validFile(parameters, "sim", false); if (temp == "not found") { temp = "F"; } + sim = m->isTrue(temp); + globaldata->sim = sim; - temp = validParameter->validFile(parameters, "cutoff", false); if (temp == "not found") { temp = "10"; } + temp = validParameter.validFile(parameters, "cutoff", false); if (temp == "not found") { temp = "10"; } convert(temp, cutoff); - cutoff += (5 / (precision * 10.0)); - - delete validParameter; + cutoff += (5 / (precision * 10.0)); if (abort == false) { - filename = globaldata->inputFileName; + distFileName = globaldata->inputFileName; format = globaldata->getFormat(); - if (format == "column") { read = new ReadColumnMatrix(filename); } - else if (format == "phylip") { read = new ReadPhylipMatrix(filename); } + if (format == "column") { read = new ReadColumnMatrix(distFileName); } + else if (format == "phylip") { read = new ReadPhylipMatrix(distFileName); } else if (format == "matrix") { groupMap = new GroupMap(groupfile); - groupMap->readMap(); - if (globaldata->gGroupmap != NULL) { delete globaldata->gGroupmap; } - globaldata->gGroupmap = groupMap; + int error = groupMap->readMap(); + if (error == 1) { delete groupMap; abort = true; } + else { + if (globaldata->gGroupmap != NULL) { delete globaldata->gGroupmap; } + globaldata->gGroupmap = groupMap; + } } if (format != "matrix" ) { @@ -104,85 +152,107 @@ ReadDistCommand::ReadDistCommand(string option){ if(namefile != ""){ nameMap = new NameAssignment(namefile); - nameMap->readMap(1,2); + nameMap->readMap(); }else{ nameMap = NULL; } } } - +*/ } } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the ReadDistCommand class Function ReadDistCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the ReadDistCommand class function ReadDistCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "ReadDistCommand", "ReadDistCommand"); exit(1); } } -//********************************************************************************************************************** - -void ReadDistCommand::help(){ - try { - cout << "The read.dist command parameter options are phylip or column, group, name, cutoff and precision" << "\n"; - cout << "The read.dist command can be used in two ways. The first is to read a phylip or column and run the cluster command" << "\n"; - cout << "For this use the read.dist command should be in the following format: " << "\n"; - cout << "read.dist(phylip=yourDistFile, name=yourNameFile, cutoff=yourCutoff, precision=yourPrecision) " << "\n"; - cout << "The phylip or column parameter is required, but only one may be used. If you use a column file the name filename is required. " << "\n"; - cout << "If you do not provide a cutoff value 10.00 is assumed. If you do not provide a precision value then 100 is assumed." << "\n"; - cout << "The second way to use the read.dist command is to read a phylip or column and a group, so you can use the libshuff command." << "\n"; - cout << "For this use the read.dist command should be in the following format: " << "\n"; - cout << "read.dist(phylip=yourPhylipfile, group=yourGroupFile). The cutoff and precision parameters are not valid with this use. " << "\n"; - cout << "Note: No spaces between parameter labels (i.e. phylip), '=' and parameters (i.e.yourPhylipfile)." << "\n" << "\n"; - } - catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the ReadDistCommand class Function help. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the ReadDistCommand class function help. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } -} - -//********************************************************************************************************************** -ReadDistCommand::~ReadDistCommand(){ - delete read; - delete nameMap; -} - //********************************************************************************************************************** int ReadDistCommand::execute(){ try { - if (abort == true) { return 0; } + if (abort == true) { if (calledHelp) { return 0; } return 2; } + m->mothurOut(getHelpString()); m->mothurOutEndLine(); +/* + time_t start = time(NULL); + size_t numDists = 0; if (format == "matrix") { ifstream in; - openInputFile(filename, in); + m->openInputFile(distFileName, in); matrix = new FullMatrix(in); //reads the matrix file + in.close(); + + if (m->control_pressed) { delete groupMap; delete matrix; return 0; } + + //if files don't match... + if (matrix->getNumSeqs() < groupMap->getNumSeqs()) { + m->mothurOut("Your distance file contains " + toString(matrix->getNumSeqs()) + " sequences, and your group file contains " + toString(groupMap->getNumSeqs()) + " sequences."); m->mothurOutEndLine(); + //create new group file + if(outputDir == "") { outputDir += m->hasPath(groupfile); } + + string newGroupFile = outputDir + m->getRootName(m->getSimpleName(groupfile)) + "editted.groups"; + outputNames.push_back(newGroupFile); + ofstream outGroups; + m->openOutputFile(newGroupFile, outGroups); + + for (int i = 0; i < matrix->getNumSeqs(); i++) { + if (m->control_pressed) { delete groupMap; delete matrix; outGroups.close(); m->mothurRemove(newGroupFile); return 0; } + + Names temp = matrix->getRowInfo(i); + outGroups << temp.seqName << '\t' << temp.groupName << endl; + } + outGroups.close(); + + m->mothurOut(newGroupFile + " is a new group file containing only the sequence that are in your distance file. I will read this file instead."); m->mothurOutEndLine(); + + //read new groupfile + delete groupMap; groupMap = NULL; + groupfile = newGroupFile; + globaldata->setGroupFile(groupfile); + + groupMap = new GroupMap(groupfile); + groupMap->readMap(); + + if (m->control_pressed) { delete groupMap; delete matrix; m->mothurRemove(newGroupFile); return 0; } + + globaldata->gGroupmap = groupMap; + } + //memory leak prevention - //if (globaldata->gMatrix != NULL) { delete globaldata->gMatrix; } + if (globaldata->gMatrix != NULL) { delete globaldata->gMatrix; } globaldata->gMatrix = matrix; //save matrix for coverage commands - }else { + numDists = matrix->getSizes()[1]; + } else { read->read(nameMap); //to prevent memory leak - if (globaldata->gListVector != NULL) { delete globaldata->gListVector; } + + if (m->control_pressed) { return 0; } + + if (globaldata->gListVector != NULL) { delete globaldata->gListVector; } globaldata->gListVector = read->getListVector(); + if (globaldata->gSparseMatrix != NULL) { delete globaldata->gSparseMatrix; } globaldata->gSparseMatrix = read->getMatrix(); + numDists = globaldata->gSparseMatrix->getNNodes(); } + + if (m->control_pressed) { return 0; } + + if (outputNames.size() != 0) { + m->mothurOutEndLine(); + m->mothurOut("Output File Name: "); m->mothurOutEndLine(); + for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); } + m->mothurOutEndLine(); + } + + m->mothurOut("It took " + toString(time(NULL) - start) + " secs to read "); m->mothurOutEndLine(); + */ return 0; + } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the ReadDistCommand class Function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the ReadDistCommand class function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "ReadDistCommand", "execute"); exit(1); } }