X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=readdistcommand.cpp;h=9cb2046139ba7d275aa31cb1e9024bf9a729cbf2;hb=315e38cf393c82be238da5b32574f225a020d25c;hp=6d38f4e4d55cde380570dd53aaa847f96600550f;hpb=cd10743907df223b7dd5b3a3deb20fde758b8ed7;p=mothur.git diff --git a/readdistcommand.cpp b/readdistcommand.cpp index 6d38f4e..9cb2046 100644 --- a/readdistcommand.cpp +++ b/readdistcommand.cpp @@ -8,82 +8,283 @@ */ #include "readdistcommand.h" +#include "readphylip.h" +#include "readcolumn.h" +#include "readmatrix.hpp" -ReadDistCommand::ReadDistCommand(){ +ReadDistCommand::ReadDistCommand(string option){ try { globaldata = GlobalData::getInstance(); + abort = false; - filename = globaldata->inputFileName; - format = globaldata->getFormat(); + //allow user to run help + if(option == "help") { help(); abort = true; } - if (format == "column") { read = new ReadColumnMatrix(filename); } - else if (format == "phylip") { read = new ReadPhylipMatrix(filename); } - else if (format == "matrix") { - groupMap = new GroupMap(globaldata->getGroupFile()); - groupMap->readMap(); - if (globaldata->gGroupmap != NULL) { delete globaldata->gGroupmap; } - globaldata->gGroupmap = groupMap; - } + else { + //valid paramters for this command + string Array[] = {"phylip", "column", "name", "cutoff", "precision", "group","outputdir","inputdir"}; + vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + + OptionParser parser(option); + map parameters = parser.getParameters(); + + ValidParameters validParameter; + map::iterator it; - if (format != "matrix" ) { - if(globaldata->getPrecision() != ""){ - convert(globaldata->getPrecision(), precision); + //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; } + } + + 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 = 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 = 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 = 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 = 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); + 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); + 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); + if (groupfile == "not open") { abort = true; } + else if (groupfile == "not found") { groupfile = ""; } + else { + globaldata->setGroupFile(groupfile); + //groupMap = new GroupMap(groupfile); + //groupMap->readMap(); } + + 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 == "") && (columnfile == "")) { mothurOut("When executing a read.dist command you must enter a phylip or a column."); mothurOutEndLine(); abort = true; } + else if ((phylipfile != "") && (columnfile != "")) { mothurOut("When executing a read.dist command you must enter ONLY ONE of the following: phylip or column."); mothurOutEndLine(); abort = true; } - if(globaldata->getCutOff() != ""){ - convert(globaldata->getCutOff(), cutoff); - cutoff += (5 / (precision * 10.0)); + if (columnfile != "") { + if (namefile == "") { cout << "You need to provide a namefile if you are going to use the column format." << endl; abort = true; } } - read->setCutoff(cutoff); + + //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, "cutoff", false); if (temp == "not found") { temp = "10"; } + convert(temp, cutoff); + cutoff += (5 / (precision * 10.0)); + + if (abort == false) { + distFileName = globaldata->inputFileName; + format = globaldata->getFormat(); + + if (format == "column") { read = new ReadColumnMatrix(distFileName); } + else if (format == "phylip") { read = new ReadPhylipMatrix(distFileName); } + else if (format == "matrix") { + groupMap = new GroupMap(groupfile); + 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" ) { + read->setCutoff(cutoff); - if(globaldata->getNameFile() != ""){ - nameMap = new NameAssignment(globaldata->getNameFile()); - nameMap->readMap(1,2); - } - else{ - nameMap = NULL; + if(namefile != ""){ + nameMap = new NameAssignment(namefile); + 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"; + errorOut(e, "ReadDistCommand", "ReadDistCommand"); 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"; +} +//********************************************************************************************************************** + +void ReadDistCommand::help(){ + try { + mothurOut("The read.dist command parameter options are phylip or column, group, name, cutoff and precision\n"); + mothurOut("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"); + mothurOut("For this use the read.dist command should be in the following format: \n"); + mothurOut("read.dist(phylip=yourDistFile, name=yourNameFile, cutoff=yourCutoff, precision=yourPrecision) \n"); + mothurOut("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"); + mothurOut("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"); + mothurOut("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"); + mothurOut("For this use the read.dist command should be in the following format: \n"); + mothurOut("read.dist(phylip=yourPhylipfile, group=yourGroupFile). The cutoff and precision parameters are not valid with this use. \n"); + mothurOut("Note: No spaces between parameter labels (i.e. phylip), '=' and parameters (i.e.yourPhylipfile).\n\n"); + } + catch(exception& e) { + errorOut(e, "ReadDistCommand", "help"); exit(1); } } //********************************************************************************************************************** + ReadDistCommand::~ReadDistCommand(){ - delete read; - delete nameMap; + if (abort == false) { + if (format != "matrix") { + delete read; + delete nameMap; + } + } } //********************************************************************************************************************** int ReadDistCommand::execute(){ try { + if (abort == true) { return 0; } + + time_t start = time(NULL); + size_t numDists = 0; + if (format == "matrix") { ifstream in; - openInputFile(filename, in); + openInputFile(distFileName, in); matrix = new FullMatrix(in); //reads the matrix file + in.close(); + + //if files don't match... + if (matrix->getNumSeqs() < groupMap->getNumSeqs()) { + mothurOut("Your distance file contains " + toString(matrix->getNumSeqs()) + " sequences, and your group file contains " + toString(groupMap->getNumSeqs()) + " sequences."); mothurOutEndLine(); + //create new group file + if(outputDir == "") { outputDir += hasPath(groupfile); } + + string newGroupFile = outputDir + getRootName(getSimpleName(groupfile)) + "editted.groups"; + ofstream outGroups; + openOutputFile(newGroupFile, outGroups); + + for (int i = 0; i < matrix->getNumSeqs(); i++) { + Names temp = matrix->getRowInfo(i); + outGroups << temp.seqName << '\t' << temp.groupName << endl; + } + outGroups.close(); + + mothurOut(newGroupFile + " is a new group file containing only the sequence that are in your distance file. I will read this file instead."); mothurOutEndLine(); + + //read new groupfile + delete groupMap; groupMap = NULL; + groupfile = newGroupFile; + globaldata->setGroupFile(groupfile); + + groupMap = new GroupMap(groupfile); + groupMap->readMap(); + + globaldata->gGroupmap = groupMap; + } + + //memory leak prevention + 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; } globaldata->gListVector = read->getListVector(); + + if (globaldata->gSparseMatrix != NULL) { delete globaldata->gSparseMatrix; } globaldata->gSparseMatrix = read->getMatrix(); + numDists = globaldata->gSparseMatrix->getNNodes(); + //cout << "matrix contains " << numDists << " distances." << endl; + + /* int lines = cutoff / (1.0/precision); + vector dist_cutoff(lines+1,0); + for (int i = 0; i <= lines;i++) { + dist_cutoff[i] = (i + 0.5) / precision; + } + vector dist_count(lines+1,0); + list::iterator currentCell; + SparseMatrix* smatrix = globaldata->gSparseMatrix; + for (currentCell = smatrix->begin(); currentCell != smatrix->end(); currentCell++) { + for (int i = 0; i <= lines;i++) { + if (currentCell->dist < dist_cutoff[i]) { + dist_count[i]++; + break; + } + } + } +*/ + // string dist_string = "Dist:"; + // string count_string = "Count: "; + //for (int i = 0; i <= lines;i++) { + //dist_string = dist_string.append("\t").append(toString(dist_cutoff[i])); + // count_string = count_string.append("\t").append(toString(dist_count[i])); + // } + //mothurOut(dist_string); mothurOutEndLine(); mothurOut(count_string); mothurOutEndLine(); } + mothurOut("It took " + toString(time(NULL) - start) + " secs to read "); 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"; + errorOut(e, "ReadDistCommand", "execute"); exit(1); } }