X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=sharedcommand.cpp;h=2b4d56ec44591400f977e365f6501e89170c9f02;hb=643cdf74ccd4fc2d565168716fb5645917dee834;hp=91bb8e19604d3d9446016c4b9eaf82f566172c0a;hpb=762b3e4c83e1e8e8392c1199b6482d36ee89e50f;p=mothur.git diff --git a/sharedcommand.cpp b/sharedcommand.cpp index 91bb8e1..2b4d56e 100644 --- a/sharedcommand.cpp +++ b/sharedcommand.cpp @@ -12,50 +12,203 @@ //sorts lowest to highest inline bool compareSharedRabunds(SharedRAbundVector* left, SharedRAbundVector* right){ return (left->getGroup() < right->getGroup()); -} +} //********************************************************************************************************************** - -SharedCommand::SharedCommand(string o) : outputDir(o) { +vector SharedCommand::setParameters(){ try { - globaldata = GlobalData::getInstance(); - - //getting output filename - filename = globaldata->inputFileName; - if (outputDir == "") { outputDir += hasPath(filename); } - - filename = outputDir + getRootName(getSimpleName(filename)); - filename = filename + "shared"; - - openOutputFile(filename, out); - pickedGroups = false; - - groupMap = globaldata->gGroupmap; + CommandParameter plist("list", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(plist); + CommandParameter pgroup("group", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(pgroup); + CommandParameter pordergroup("ordergroup", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(pordergroup); + CommandParameter plabel("label", "String", "", "", "", "", "",false,false); parameters.push_back(plabel); + CommandParameter pgroups("groups", "String", "", "", "", "", "",false,false); parameters.push_back(pgroups); + 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, "SharedCommand", "setParameters"); + exit(1); + } +} +//********************************************************************************************************************** +string SharedCommand::getHelpString(){ + try { + string helpString = ""; + helpString += "The make.shared command reads a list and group file and creates a shared file, as well as a rabund file for each group.\n"; + helpString += "The make.shared command parameters are list, group, ordergroup, groups and label. list and group are required unless a current file is available.\n"; + helpString += "The groups parameter allows you to indicate which groups you want to include, group names should be separated by dashes. ex. groups=A-B-C. Default is all groups in your groupfile.\n"; + helpString += "The label parameter allows you to indicate which labels you want to include, label names should be separated by dashes. Default is all labels in your list file.\n"; + helpString += "The ordergroup parameter allows you to indicate the order of the groups in the sharedfile, by default the groups are listed alphabetically.\n"; + return helpString; + } + catch(exception& e) { + m->errorOut(e, "SharedCommand", "getHelpString"); + exit(1); + } +} +//********************************************************************************************************************** +SharedCommand::SharedCommand(){ + try { + abort = true; calledHelp = true; + setParameters(); + //initialize outputTypes + vector tempOutNames; + outputTypes["rabund"] = tempOutNames; + outputTypes["shared"] = tempOutNames; + } + catch(exception& e) { + m->errorOut(e, "SharedCommand", "SharedCommand"); + exit(1); + } +} +//********************************************************************************************************************** +SharedCommand::SharedCommand(string option) { + try { + abort = false; calledHelp = false; + allLines = 1; - //if hte user has not specified any groups then use them all - if (globaldata->Groups.size() == 0) { - groups = groupMap->namesOfGroups; - }else{ //they have specified groups - groups = globaldata->Groups; - pickedGroups = true; - } + //allow user to run help + if(option == "help") { help(); abort = true; calledHelp = true; } - //fill filehandles with neccessary ofstreams - int i; - ofstream* temp; - for (i=0; i myArray = setParameters(); + + OptionParser parser(option); + map parameters = parser.getParameters(); + + 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 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("list"); + //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["list"] = 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("ordergroup"); + //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["ordergroup"] = 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 + listfile = validParameter.validFile(parameters, "list", true); + if (listfile == "not open") { listfile = ""; abort = true; } + else if (listfile == "not found") { + listfile = m->getListFile(); + if (listfile != "") { m->mothurOut("Using " + listfile + " as input file for the list parameter."); m->mothurOutEndLine(); } + else { m->mothurOut("You have no current list file and the list parameter is required."); m->mothurOutEndLine(); abort = true; } + } + + ordergroupfile = validParameter.validFile(parameters, "ordergroup", true); + if (ordergroupfile == "not open") { abort = true; } + else if (ordergroupfile == "not found") { ordergroupfile = ""; } + + groupfile = validParameter.validFile(parameters, "group", true); + if (groupfile == "not open") { abort = true; } + else if (groupfile == "not found") { + groupfile = m->getGroupFile(); + if (groupfile != "") { + m->mothurOut("Using " + groupfile + " as input file for the group parameter."); m->mothurOutEndLine(); + groupMap = new GroupMap(groupfile); + + int error = groupMap->readMap(); + if (error == 1) { abort = true; } + m->namesOfGroups = groupMap->namesOfGroups; + } + else { m->mothurOut("You have no current group file and the group parameter is required."); m->mothurOutEndLine(); abort = true; } + }else { + groupMap = new GroupMap(groupfile); + + int error = groupMap->readMap(); + if (error == 1) { abort = true; } + m->namesOfGroups = groupMap->namesOfGroups; + m->setGroupFile(groupfile); + } + + string groups = validParameter.validFile(parameters, "groups", false); + if (groups == "not found") { groups = ""; } + else { + m->splitAtDash(groups, Groups); + m->Groups = Groups; + } + + //check for optional parameter and set defaults + // ...at some point should added some additional type checking... + string label = validParameter.validFile(parameters, "label", false); + if (label == "not found") { label = ""; } + else { + if(label != "all") { m->splitAtDash(label, labels); allLines = 0; } + else { allLines = 1; } + } + + //getting output filename + filename = listfile; + if (outputDir == "") { outputDir += m->hasPath(filename); } + + filename = outputDir + m->getRootName(m->getSimpleName(filename)); + filename = filename + "shared"; + outputTypes["shared"].push_back(filename); + + m->openOutputFile(filename, out); + pickedGroups = false; + + //if hte user has not specified any groups then use them all + if (Groups.size() == 0) { + Groups = groupMap->namesOfGroups; m->Groups = Groups; + } + + //fill filehandles with neccessary ofstreams + int i; + ofstream* temp; + for (i=0; igetRootName(m->getSimpleName(listfile)); + + //clears file before we start to write to it below + for (int i=0; igetListFile())); - - //clears file before we start to write to it below - for (int i=0; ierrorOut(e, "SharedCommand", "SharedCommand"); @@ -67,29 +220,29 @@ SharedCommand::SharedCommand(string o) : outputDir(o) { int SharedCommand::execute(){ try { + if (abort == true) { if (calledHelp) { return 0; } return 2; } + //lookup.clear(); string errorOff = "no error"; //errorOff = ""; - //read in listfile - read = new ReadOTUFile(globaldata->inputFileName); - read->read(&*globaldata); - delete read; - - input = globaldata->ginput; - SharedList = globaldata->gSharedList; + //if user provided an order file containing the order the shared file should be in read it + if (ordergroupfile != "") { readOrderFile(); } + + input = new InputData(listfile, "shared"); + SharedList = input->getSharedListVector(); string lastLabel = SharedList->getLabel(); vector lookup; if (m->control_pressed) { - delete input; delete SharedList; globaldata->ginput = NULL; globaldata->gSharedList = NULL; + delete input; delete SharedList; delete groupMap; for (it3 = filehandles.begin(); it3 != filehandles.end(); it3++) { delete it3->second; } out.close(); remove(filename.c_str()); - for (int i=0; iGroups.size() == 0) && (SharedList->getNumSeqs() != groupMap->getNumSeqs())) { //if the user has not specified any groups and their files don't match exit with error + if ((m->Groups.size() == 0) && (SharedList->getNumSeqs() != groupMap->getNumSeqs())) { //if the user has not specified any groups and their files don't match exit with error m->mothurOut("Your group file contains " + toString(groupMap->getNumSeqs()) + " sequences and list file contains " + toString(SharedList->getNumSeqs()) + " sequences. Please correct."); m->mothurOutEndLine(); out.close(); @@ -101,30 +254,30 @@ int SharedCommand::execute(){ for (it3 = filehandles.begin(); it3 != filehandles.end(); it3++) { delete it3->second; } - delete input; - globaldata->ginput = NULL; - delete SharedList; - globaldata->gSharedList = NULL; + + delete input; delete SharedList; delete groupMap; - return 1; + return 0; } //if user has specified groups make new groupfile for them - if (globaldata->Groups.size() != 0) { //make new group file + if (m->Groups.size() != 0) { //make new group file string groups = ""; - for (int i = 0; i < globaldata->Groups.size(); i++) { - groups += globaldata->Groups[i] + "."; - } + if (m->Groups.size() < 4) { + for (int i = 0; i < m->Groups.size(); i++) { + groups += m->Groups[i] + "."; + } + }else { groups = "merge"; } - string newGroupFile = outputDir + getRootName(getSimpleName(globaldata->inputFileName)) + groups + "groups"; + string newGroupFile = outputDir + m->getRootName(m->getSimpleName(listfile)) + groups + "groups"; ofstream outGroups; - openOutputFile(newGroupFile, outGroups); + m->openOutputFile(newGroupFile, outGroups); vector names = groupMap->getNamesSeqs(); string groupName; for (int i = 0; i < names.size(); i++) { groupName = groupMap->getGroup(names[i]); - if (isValidGroup(groupName, globaldata->Groups)) { + if (isValidGroup(groupName, m->Groups)) { outGroups << names[i] << '\t' << groupName << endl; } } @@ -133,18 +286,18 @@ int SharedCommand::execute(){ //if the users enters label "0.06" and there is no "0.06" in their file use the next lowest label. set processedLabels; - set userLabels = globaldata->labels; + set userLabels = labels; - while((SharedList != NULL) && ((globaldata->allLines == 1) || (userLabels.size() != 0))) { + while((SharedList != NULL) && ((allLines == 1) || (userLabels.size() != 0))) { if (m->control_pressed) { - delete input; delete SharedList; globaldata->ginput = NULL; globaldata->gSharedList = NULL; + delete input; delete SharedList; delete groupMap; for (it3 = filehandles.begin(); it3 != filehandles.end(); it3++) { delete it3->second; } out.close(); remove(filename.c_str()); - for (int i=0; iallLines == 1 || globaldata->labels.count(SharedList->getLabel()) == 1){ + if(allLines == 1 || labels.count(SharedList->getLabel()) == 1){ lookup = SharedList->getSharedRAbundVector(); @@ -154,12 +307,12 @@ int SharedCommand::execute(){ } if (m->control_pressed) { - delete input; delete SharedList; globaldata->ginput = NULL; globaldata->gSharedList = NULL; + delete input; delete SharedList; delete groupMap; for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } for (it3 = filehandles.begin(); it3 != filehandles.end(); it3++) { delete it3->second; } out.close(); remove(filename.c_str()); - for (int i=0; igetLabel()); } - if ((anyLabelsToProcess(SharedList->getLabel(), userLabels, errorOff) == true) && (processedLabels.count(lastLabel) != 1)) { + if ((m->anyLabelsToProcess(SharedList->getLabel(), userLabels, errorOff) == true) && (processedLabels.count(lastLabel) != 1)) { string saveLabel = SharedList->getLabel(); delete SharedList; @@ -183,12 +336,12 @@ int SharedCommand::execute(){ if (m->control_pressed) { - delete input; delete SharedList; globaldata->ginput = NULL; globaldata->gSharedList = NULL; + delete input; delete SharedList; delete groupMap; for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } for (it3 = filehandles.begin(); it3 != filehandles.end(); it3++) { delete it3->second; } out.close(); remove(filename.c_str()); - for (int i=0; icontrol_pressed) { - delete input; globaldata->ginput = NULL; + delete input; delete groupMap; for (it3 = filehandles.begin(); it3 != filehandles.end(); it3++) { delete it3->second; } out.close(); remove(filename.c_str()); - for (int i=0; igSharedList = NULL; - out.close(); for (it3 = filehandles.begin(); it3 != filehandles.end(); it3++) { delete it3->second; } - - //change format to shared to speed up commands - globaldata->setFormat("sharedfile"); - globaldata->setListFile(""); - globaldata->setGroupFile(""); - globaldata->setSharedFile(filename); + delete input; delete groupMap; if (m->control_pressed) { - delete input; globaldata->ginput = NULL; remove(filename.c_str()); - for (int i=0; isecond).size() != 0) { current = (itTypes->second)[0]; m->setRabundFile(current); } + } + + itTypes = outputTypes.find("shared"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setSharedFile(current); } + } + m->mothurOutEndLine(); m->mothurOut("Output File Names: "); m->mothurOutEndLine(); for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); } @@ -280,18 +437,53 @@ int SharedCommand::execute(){ void SharedCommand::printSharedData(vector thislookup) { try { - sort(thislookup.begin(), thislookup.end(), compareSharedRabunds); + if (order.size() == 0) { //user has not specified an order so do aplabetically + sort(thislookup.begin(), thislookup.end(), compareSharedRabunds); + + m->Groups.clear(); + + //initialize bin values + for (int i = 0; i < thislookup.size(); i++) { + out << thislookup[i]->getLabel() << '\t' << thislookup[i]->getGroup() << '\t'; + thislookup[i]->print(out); + + m->Groups.push_back(thislookup[i]->getGroup()); + + RAbundVector rav = thislookup[i]->getRAbundVector(); + m->openOutputFileAppend(fileroot + thislookup[i]->getGroup() + ".rabund", *(filehandles[thislookup[i]->getGroup()])); + rav.print(*(filehandles[thislookup[i]->getGroup()])); + (*(filehandles[thislookup[i]->getGroup()])).close(); + } + }else{ + //create a map from groupName to each sharedrabund + map myMap; + map::iterator myIt; + + for (int i = 0; i < thislookup.size(); i++) { + myMap[thislookup[i]->getGroup()] = thislookup[i]; + } + + m->Groups.clear(); + + //loop through ordered list and print the rabund + for (int i = 0; i < order.size(); i++) { + myIt = myMap.find(order[i]); + + if(myIt != myMap.end()) { //we found it + out << (myIt->second)->getLabel() << '\t' << (myIt->second)->getGroup() << '\t'; + (myIt->second)->print(out); + + m->Groups.push_back((myIt->second)->getGroup()); + + RAbundVector rav = (myIt->second)->getRAbundVector(); + m->openOutputFileAppend(fileroot + (myIt->second)->getGroup() + ".rabund", *(filehandles[(myIt->second)->getGroup()])); + rav.print(*(filehandles[(myIt->second)->getGroup()])); + (*(filehandles[(myIt->second)->getGroup()])).close(); + }else{ + m->mothurOut("Can't find shared info for " + order[i] + ", skipping."); m->mothurOutEndLine(); + } + } - //initialize bin values - for (int i = 0; i < thislookup.size(); i++) { -//cout << "in printData " << thislookup[i]->getLabel() << '\t' << thislookup[i]->getGroup() << endl; - out << thislookup[i]->getLabel() << '\t' << thislookup[i]->getGroup() << '\t'; - thislookup[i]->print(out); - - RAbundVector rav = thislookup[i]->getRAbundVector(); - openOutputFileAppend(fileroot + thislookup[i]->getGroup() + ".rabund", *(filehandles[thislookup[i]->getGroup()])); - rav.print(*(filehandles[thislookup[i]->getGroup()])); - (*(filehandles[thislookup[i]->getGroup()])).close(); } } @@ -346,14 +538,14 @@ int SharedCommand::eliminateZeroOTUS(vector& thislookup) { int SharedCommand::createMisMatchFile() { try { ofstream outMisMatch; - string outputMisMatchName = outputDir + getRootName(getSimpleName(globaldata->inputFileName)); + string outputMisMatchName = outputDir + m->getRootName(m->getSimpleName(listfile)); //you have sequences in your list file that are not in your group file if (SharedList->getNumSeqs() > groupMap->getNumSeqs()) { outputMisMatchName += "missing.group"; m->mothurOut("For a list of names that are in your list file and not in your group file, please refer to " + outputMisMatchName + "."); m->mothurOutEndLine(); - openOutputFile(outputMisMatchName, outMisMatch); + m->openOutputFile(outputMisMatchName, outMisMatch); map listNames; map::iterator itList; @@ -427,7 +619,7 @@ int SharedCommand::createMisMatchFile() { map::iterator itMatch; - openOutputFile(outputMisMatchName, outMisMatch); + m->openOutputFile(outputMisMatchName, outMisMatch); //loop through names in seqNames and if they aren't in namesIn list output them for (int i = 0; i < seqNames.size(); i++) { @@ -458,7 +650,32 @@ SharedCommand::~SharedCommand(){ } - +//********************************************************************************************************************** +int SharedCommand::readOrderFile() { + try { + //remove old names + order.clear(); + + ifstream in; + m->openInputFile(ordergroupfile, in); + string thisGroup; + + while(!in.eof()){ + in >> thisGroup; m->gobble(in); + + order.push_back(thisGroup); + + if (m->control_pressed) { order.clear(); break; } + } + in.close(); + + return 0; + } + catch(exception& e) { + m->errorOut(e, "SharedCommand", "readOrderFile"); + exit(1); + } +} //********************************************************************************************************************** bool SharedCommand::isValidGroup(string groupname, vector groups) {