X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=readtreecommand.cpp;h=edfdf3b77e0d85ff51afce83323d0204ab987a66;hb=8bc3e5b38c2317a1715f53be22fa96455868c281;hp=b030542ef8f7e5933f2bf32c4c6bf6ba9e051ee0;hpb=cd37904452dc95b183ff313ff05720c562902487;p=mothur.git diff --git a/readtreecommand.cpp b/readtreecommand.cpp index b030542..edfdf3b 100644 --- a/readtreecommand.cpp +++ b/readtreecommand.cpp @@ -10,41 +10,121 @@ #include "readtreecommand.h" //********************************************************************************************************************** -ReadTreeCommand::ReadTreeCommand(string option){ +vector ReadTreeCommand::getValidParameters(){ + try { + string Array[] = {"tree","group","name","outputdir","inputdir"}; + vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + return myArray; + } + catch(exception& e) { + m->errorOut(e, "ReadTreeCommand", "getValidParameters"); + exit(1); + } +} +//********************************************************************************************************************** +vector ReadTreeCommand::getRequiredParameters(){ + try { + string Array[] = {"tree"}; + vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + return myArray; + } + catch(exception& e) { + m->errorOut(e, "ReadTreeCommand", "getRequiredParameters"); + exit(1); + } +} +//********************************************************************************************************************** +vector ReadTreeCommand::getRequiredFiles(){ + try { + vector myArray; + return myArray; + } + catch(exception& e) { + m->errorOut(e, "ReadTreeCommand", "getRequiredFiles"); + exit(1); + } +} +//********************************************************************************************************************** +ReadTreeCommand::ReadTreeCommand(string option) { try { globaldata = GlobalData::getInstance(); abort = false; - + //allow user to run help if(option == "help") { help(); abort = true; } else { //valid paramters for this command - string Array[] = {"tree","group"}; + string Array[] = {"tree","group","name","outputdir","inputdir"}; vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); OptionParser parser(option); map parameters = parser.getParameters(); ValidParameters validParameter; + map::iterator it; //check to make sure all parameters are valid for command - for (map::iterator it = parameters.begin(); it != parameters.end(); it++) { + 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("tree"); + //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["tree"] = 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; } + } + + 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; } + } + + } + + //check for required parameters treefile = validParameter.validFile(parameters, "tree", true); if (treefile == "not open") { abort = true; } - else if (treefile == "not found") { treefile = ""; cout << "tree is a required parameter for the read.tree command." << endl; abort = true; } -// else { globaldata->setTreeFile(treefile); globaldata->setFormat("tree"); } + else if (treefile == "not found") { treefile = ""; m->mothurOut("tree is a required parameter for the read.tree command."); m->mothurOutEndLine(); abort = true; } + else { globaldata->setTreeFile(treefile); globaldata->setFormat("tree"); } groupfile = validParameter.validFile(parameters, "group", true); if (groupfile == "not open") { abort = true; } - else if (groupfile == "not found") { groupfile = ""; cout << "group is a required parameter for the read.tree command." << endl; abort = true; } - else { + else if (groupfile == "not found") { + groupfile = ""; + + m->mothurOut("You have not provided a group file. I am assumming all sequence are from the same group."); m->mothurOutEndLine(); + + if (treefile != "") { Tree* tree = new Tree(treefile); delete tree; } //extracts names from tree to make faked out groupmap + + globaldata->setGroupFile(groupfile); + //read in group map info. + treeMap = new TreeMap(); + for (int i = 0; i < globaldata->Treenames.size(); i++) { treeMap->addSeq(globaldata->Treenames[i], "Group1"); } + globaldata->gTreemap = treeMap; + + }else { globaldata->setGroupFile(groupfile); //read in group map info. treeMap = new TreeMap(groupfile); @@ -52,6 +132,11 @@ ReadTreeCommand::ReadTreeCommand(string option){ globaldata->gTreemap = treeMap; } + namefile = validParameter.validFile(parameters, "name", true); + if (namefile == "not open") { abort = true; } + else if (namefile == "not found") { namefile = ""; } + else { readNamesFile(); } + if (abort == false) { filename = treefile; read = new ReadNewickTree(filename); @@ -60,11 +145,7 @@ ReadTreeCommand::ReadTreeCommand(string option){ } } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the ReadTreeCommand class Function ReadTreeCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } - catch(...) { - cout << "An unknown error has occurred in the ReadTreeCommand class function ReadTreeCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "ReadTreeCommand", "ReadTreeCommand"); exit(1); } } @@ -72,26 +153,24 @@ ReadTreeCommand::ReadTreeCommand(string option){ void ReadTreeCommand::help(){ try { - cout << "The read.tree command must be run before you execute a unifrac.weighted, unifrac.unweighted. " << "\n"; - cout << "It also must be run before using the parsimony command, unless you are using the randomtree parameter." << "\n"; - cout << "The read.tree command should be in the following format: read.tree(tree=yourTreeFile, group=yourGroupFile)." << "\n"; - cout << "The tree and group parameters are both required." << "\n"; - cout << "Note: No spaces between parameter labels (i.e. tree), '=' and parameters (i.e.yourTreefile)." << "\n" << "\n"; + m->mothurOut("The read.tree command must be run before you execute a unifrac.weighted, unifrac.unweighted. \n"); + m->mothurOut("It also must be run before using the parsimony command, unless you are using the randomtree parameter.\n"); + m->mothurOut("The read.tree command parameters are tree, group and name.\n"); + m->mothurOut("The read.tree command should be in the following format: read.tree(tree=yourTreeFile, group=yourGroupFile).\n"); + m->mothurOut("The tree and group parameters are both required, if no group file is given then one group is assumed.\n"); + m->mothurOut("The name parameter allows you to enter a namefile.\n"); + m->mothurOut("Note: No spaces between parameter labels (i.e. tree), '=' and parameters (i.e.yourTreefile).\n\n"); } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the ReadTreeCommand class Function help. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "ReadTreeCommand", "help"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the ReadTreeCommand class function help. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; - exit(1); - } } //********************************************************************************************************************** ReadTreeCommand::~ReadTreeCommand(){ - delete read; + if (abort == false) { delete read; } } //********************************************************************************************************************** @@ -105,17 +184,33 @@ int ReadTreeCommand::execute(){ readOk = read->read(); - if (readOk != 0) { cout << "Read Terminated." << endl; globaldata->gTree.clear(); delete globaldata->gTreemap; return 0; } + if (readOk != 0) { m->mothurOut("Read Terminated."); m->mothurOutEndLine(); globaldata->gTree.clear(); delete globaldata->gTreemap; return 0; } vector T = globaldata->gTree; - + //assemble users trees for (int i = 0; i < T.size(); i++) { + if (m->control_pressed) { + for (int i = 0; i < T.size(); i++) { delete T[i]; } + globaldata->gTree.clear(); + delete globaldata->gTreemap; + return 0; + } + T[i]->assembleTree(); } - //output any names that are in names file but not in tree - if (globaldata->Treenames.size() < treeMap->getNumSeqs()) { + + //if you provide a namefile we will use the numNames in the namefile as long as the number of unique match the tree names size. + int numNamesInTree; + if (namefile != "") { + if (numUniquesInName == globaldata->Treenames.size()) { numNamesInTree = nameMap.size(); } + else { numNamesInTree = globaldata->Treenames.size(); } + }else { numNamesInTree = globaldata->Treenames.size(); } + + + //output any names that are in group file but not in tree + if (numNamesInTree < treeMap->getNumSeqs()) { for (int i = 0; i < treeMap->namesOfSeqs.size(); i++) { //is that name in the tree? int count = 0; @@ -124,21 +219,70 @@ int ReadTreeCommand::execute(){ count++; } + if (m->control_pressed) { + for (int i = 0; i < T.size(); i++) { delete T[i]; } + globaldata->gTree.clear(); + delete globaldata->gTreemap; + return 0; + } + //then you did not find it so report it if (count == globaldata->Treenames.size()) { - cout << treeMap->namesOfSeqs[i] << " is in your namefile and not in your tree. It will be disregarded." << endl; + //if it is in your namefile then don't remove + map::iterator it = nameMap.find(treeMap->namesOfSeqs[i]); + + if (it == nameMap.end()) { + m->mothurOut(treeMap->namesOfSeqs[i] + " is in your groupfile and not in your tree. It will be disregarded."); m->mothurOutEndLine(); + treeMap->removeSeq(treeMap->namesOfSeqs[i]); + i--; //need this because removeSeq removes name from namesOfSeqs + } } } + + globaldata->gTreemap = treeMap; } - + return 0; } catch(exception& e) { - cout << "Standard Error: " << e.what() << " has occurred in the ReadTreeCommand class Function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; + m->errorOut(e, "ReadTreeCommand", "execute"); exit(1); } - catch(...) { - cout << "An unknown error has occurred in the ReadTreeCommand class function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n"; +} +/*****************************************************************/ +int ReadTreeCommand::readNamesFile() { + try { + globaldata->names.clear(); + numUniquesInName = 0; + + ifstream in; + m->openInputFile(namefile, in); + + string first, second; + map::iterator itNames; + + while(!in.eof()) { + in >> first >> second; m->gobble(in); + + numUniquesInName++; + + itNames = globaldata->names.find(first); + if (itNames == globaldata->names.end()) { + globaldata->names[first] = second; + + //we need a list of names in your namefile to use above when removing extra seqs above so we don't remove them + vector dupNames; + m->splitAtComma(second, dupNames); + + for (int i = 0; i < dupNames.size(); i++) { nameMap[dupNames[i]] = dupNames[i]; if ((groupfile == "") && (i != 0)) { globaldata->gTreemap->addSeq(dupNames[i], "Group1"); } } + }else { m->mothurOut(first + " has already been seen in namefile, disregarding names file."); m->mothurOutEndLine(); in.close(); globaldata->names.clear(); namefile = ""; return 1; } + } + in.close(); + + return 0; + } + catch(exception& e) { + m->errorOut(e, "ReadTreeCommand", "readNamesFile"); exit(1); } }