X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=collectcommand.cpp;h=88be43b9a283b3313eacb6093ffe4f496c6bc452;hb=7a8fc1115b3871107c09a4b9b307b1f2ab7d3fcf;hp=ea2d558544514e7f35e291033c23e20aca930a6a;hpb=72ebb6fa35b45b149812d47c2b1cb8acaca64659;p=mothur.git diff --git a/collectcommand.cpp b/collectcommand.cpp index ea2d558..88be43b 100644 --- a/collectcommand.cpp +++ b/collectcommand.cpp @@ -31,7 +31,7 @@ //********************************************************************************************************************** -CollectCommand::CollectCommand(string option){ +CollectCommand::CollectCommand(string option) { try { globaldata = GlobalData::getInstance(); abort = false; @@ -40,11 +40,11 @@ CollectCommand::CollectCommand(string option){ Estimators.clear(); //allow user to run help - if(option == "help") { validCalculator = new ValidCalculators(); help(); abort = true; } + if(option == "help") { validCalculator = new ValidCalculators(); help(); delete validCalculator; abort = true; } else { //valid paramters for this command - string Array[] = {"freq","label","calc","abund","size"}; + string Array[] = {"freq","label","calc","abund","size","outputdir","inputdir"}; vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); OptionParser parser(option); @@ -57,8 +57,11 @@ CollectCommand::CollectCommand(string option){ if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { 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 = ""; } + //make sure the user has already run the read.otu command - if ((globaldata->getListFile() == "") && (globaldata->getRabundFile() == "") && (globaldata->getSabundFile() == "")) { mothurOut("You must read a list, sabund or rabund before you can use the collect.single command."); mothurOutEndLine(); abort = true; } + if ((globaldata->getSharedFile() == "") && (globaldata->getListFile() == "") && (globaldata->getRabundFile() == "") && (globaldata->getSabundFile() == "")) { m->mothurOut("You must read a list, sabund, rabund or shared file before you can use the collect.single command."); m->mothurOutEndLine(); abort = true; } //check for optional parameter and set defaults // ...at some point should added some additional type checking... @@ -91,63 +94,11 @@ CollectCommand::CollectCommand(string option){ temp = validParameter.validFile(parameters, "size", false); if (temp == "not found") { temp = "0"; } convert(temp, size); - - if (abort == false) { - string fileNameRoot = getRootName(globaldata->inputFileName); - int i; - validCalculator = new ValidCalculators(); - - for (i=0; iisValidCalculator("single", Estimators[i]) == true) { - if (Estimators[i] == "sobs") { - cDisplays.push_back(new CollectDisplay(new Sobs(), new OneColumnFile(fileNameRoot+"sobs"))); - }else if (Estimators[i] == "chao") { - cDisplays.push_back(new CollectDisplay(new Chao1(), new ThreeColumnFile(fileNameRoot+"chao"))); - }else if (Estimators[i] == "nseqs") { - cDisplays.push_back(new CollectDisplay(new NSeqs(), new OneColumnFile(fileNameRoot+"nseqs"))); - }else if (Estimators[i] == "coverage") { - cDisplays.push_back(new CollectDisplay(new Coverage(), new OneColumnFile(fileNameRoot+"coverage"))); - }else if (Estimators[i] == "ace") { - cDisplays.push_back(new CollectDisplay(new Ace(abund), new ThreeColumnFile(fileNameRoot+"ace"))); - }else if (Estimators[i] == "jack") { - cDisplays.push_back(new CollectDisplay(new Jackknife(), new ThreeColumnFile(fileNameRoot+"jack"))); - }else if (Estimators[i] == "shannon") { - cDisplays.push_back(new CollectDisplay(new Shannon(), new ThreeColumnFile(fileNameRoot+"shannon"))); - }else if (Estimators[i] == "npshannon") { - cDisplays.push_back(new CollectDisplay(new NPShannon(), new OneColumnFile(fileNameRoot+"np_shannon"))); - }else if (Estimators[i] == "simpson") { - cDisplays.push_back(new CollectDisplay(new Simpson(), new ThreeColumnFile(fileNameRoot+"simpson"))); - }else if (Estimators[i] == "bootstrap") { - cDisplays.push_back(new CollectDisplay(new Bootstrap(), new OneColumnFile(fileNameRoot+"bootstrap"))); - }else if (Estimators[i] == "geometric") { - cDisplays.push_back(new CollectDisplay(new Geom(), new OneColumnFile(fileNameRoot+"geometric"))); - }else if (Estimators[i] == "qstat") { - cDisplays.push_back(new CollectDisplay(new QStat(), new OneColumnFile(fileNameRoot+"qstat"))); - }else if (Estimators[i] == "logseries") { - cDisplays.push_back(new CollectDisplay(new LogSD(), new OneColumnFile(fileNameRoot+"logseries"))); - }else if (Estimators[i] == "bergerparker") { - cDisplays.push_back(new CollectDisplay(new BergerParker(), new OneColumnFile(fileNameRoot+"bergerparker"))); - }else if (Estimators[i] == "bstick") { - cDisplays.push_back(new CollectDisplay(new BStick(), new ThreeColumnFile(fileNameRoot+"bstick"))); - }else if (Estimators[i] == "goodscoverage") { - cDisplays.push_back(new CollectDisplay(new GoodsCoverage(), new OneColumnFile(fileNameRoot+"goodscoverage"))); - }else if (Estimators[i] == "efron") { - cDisplays.push_back(new CollectDisplay(new Efron(size), new OneColumnFile(fileNameRoot+"efron"))); - }else if (Estimators[i] == "boneh") { - cDisplays.push_back(new CollectDisplay(new Boneh(size), new OneColumnFile(fileNameRoot+"boneh"))); - }else if (Estimators[i] == "solow") { - cDisplays.push_back(new CollectDisplay(new Solow(size), new OneColumnFile(fileNameRoot+"solow"))); - }else if (Estimators[i] == "shen") { - cDisplays.push_back(new CollectDisplay(new Shen(size, abund), new OneColumnFile(fileNameRoot+"shen"))); - } - } - } - } } } catch(exception& e) { - errorOut(e, "CollectCommand", "CollectCommand"); + m->errorOut(e, "CollectCommand", "CollectCommand"); exit(1); } } @@ -155,34 +106,27 @@ CollectCommand::CollectCommand(string option){ void CollectCommand::help(){ try { - mothurOut("The collect.single command can only be executed after a successful read.otu command. WITH ONE EXECEPTION. \n"); - mothurOut("The collect.single command can be executed after a successful cluster command. It will use the .list file from the output of the cluster.\n"); - mothurOut("The collect.single command parameters are label, freq, calc and abund. No parameters are required. \n"); - mothurOut("The collect.single command should be in the following format: \n"); - mothurOut("collect.single(label=yourLabel, iters=yourIters, freq=yourFreq, calc=yourEstimators).\n"); - mothurOut("Example collect(label=unique-.01-.03, iters=10000, freq=10, calc=sobs-chao-ace-jack).\n"); - mothurOut("The default values for freq is 100, and calc are sobs-chao-ace-jack-shannon-npshannon-simpson.\n"); + m->mothurOut("The collect.single command can only be executed after a successful read.otu command. WITH ONE EXECEPTION. \n"); + m->mothurOut("The collect.single command can be executed after a successful cluster command. It will use the .list file from the output of the cluster.\n"); + m->mothurOut("The collect.single command parameters are label, freq, calc and abund. No parameters are required. \n"); + m->mothurOut("The collect.single command should be in the following format: \n"); + m->mothurOut("The freq parameter is used indicate when to output your data, by default it is set to 100. But you can set it to a percentage of the number of sequence. For example freq=0.10, means 10%. \n"); + m->mothurOut("collect.single(label=yourLabel, iters=yourIters, freq=yourFreq, calc=yourEstimators).\n"); + m->mothurOut("Example collect(label=unique-.01-.03, iters=10000, freq=10, calc=sobs-chao-ace-jack).\n"); + m->mothurOut("The default values for freq is 100, and calc are sobs-chao-ace-jack-shannon-npshannon-simpson.\n"); validCalculator->printCalc("single", cout); - mothurOut("The label parameter is used to analyze specific labels in your input.\n"); - mothurOut("Note: No spaces between parameter labels (i.e. freq), '=' and parameters (i.e.yourFreq).\n\n"); + m->mothurOut("The label parameter is used to analyze specific labels in your input.\n"); + m->mothurOut("Note: No spaces between parameter labels (i.e. freq), '=' and parameters (i.e.yourFreq).\n\n"); } catch(exception& e) { - errorOut(e, "CollectCommand", "help"); + m->errorOut(e, "CollectCommand", "help"); exit(1); } } //********************************************************************************************************************** -CollectCommand::~CollectCommand(){ - if (abort == false) { - //delete order; - delete input; globaldata->ginput = NULL; - delete read; - delete validCalculator; - globaldata->gorder = NULL; - } -} +CollectCommand::~CollectCommand(){} //********************************************************************************************************************** @@ -191,93 +135,299 @@ int CollectCommand::execute(){ if (abort == true) { return 0; } - //if the users entered no valid calculators don't execute command - if (cDisplays.size() == 0) { return 0; } - - read = new ReadOTUFile(globaldata->inputFileName); - read->read(&*globaldata); + vector outputNames; - order = globaldata->gorder; - string lastLabel = order->getLabel(); - input = globaldata->ginput; + if ((globaldata->getFormat() != "sharedfile")) { inputFileNames.push_back(globaldata->inputFileName); } + else { inputFileNames = parseSharedFile(globaldata->getSharedFile()); globaldata->setFormat("rabund"); } + + for (int p = 0; p < inputFileNames.size(); p++) { + + if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } globaldata->Groups.clear(); return 0; } + + if (outputDir == "") { outputDir += hasPath(inputFileNames[p]); } + string fileNameRoot = outputDir + getRootName(getSimpleName(inputFileNames[p])); + globaldata->inputFileName = inputFileNames[p]; - //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 = labels; + if (inputFileNames.size() > 1) { + m->mothurOutEndLine(); m->mothurOut("Processing group " + groups[p]); m->mothurOutEndLine(); m->mothurOutEndLine(); + } - while((order != NULL) && ((allLines == 1) || (userLabels.size() != 0))) { + validCalculator = new ValidCalculators(); + + for (int i=0; iisValidCalculator("single", Estimators[i]) == true) { + if (Estimators[i] == "sobs") { + cDisplays.push_back(new CollectDisplay(new Sobs(), new OneColumnFile(fileNameRoot+"sobs"))); + outputNames.push_back(fileNameRoot+"sobs"); + }else if (Estimators[i] == "chao") { + cDisplays.push_back(new CollectDisplay(new Chao1(), new ThreeColumnFile(fileNameRoot+"chao"))); + outputNames.push_back(fileNameRoot+"chao"); + }else if (Estimators[i] == "nseqs") { + cDisplays.push_back(new CollectDisplay(new NSeqs(), new OneColumnFile(fileNameRoot+"nseqs"))); + outputNames.push_back(fileNameRoot+"nseqs"); + }else if (Estimators[i] == "coverage") { + cDisplays.push_back(new CollectDisplay(new Coverage(), new OneColumnFile(fileNameRoot+"coverage"))); + outputNames.push_back(fileNameRoot+"coverage"); + }else if (Estimators[i] == "ace") { + cDisplays.push_back(new CollectDisplay(new Ace(abund), new ThreeColumnFile(fileNameRoot+"ace"))); + outputNames.push_back(fileNameRoot+"ace"); + }else if (Estimators[i] == "jack") { + cDisplays.push_back(new CollectDisplay(new Jackknife(), new ThreeColumnFile(fileNameRoot+"jack"))); + outputNames.push_back(fileNameRoot+"jack"); + }else if (Estimators[i] == "shannon") { + cDisplays.push_back(new CollectDisplay(new Shannon(), new ThreeColumnFile(fileNameRoot+"shannon"))); + outputNames.push_back(fileNameRoot+"shannon"); + }else if (Estimators[i] == "npshannon") { + cDisplays.push_back(new CollectDisplay(new NPShannon(), new OneColumnFile(fileNameRoot+"np_shannon"))); + outputNames.push_back(fileNameRoot+"np_shannon"); + }else if (Estimators[i] == "simpson") { + cDisplays.push_back(new CollectDisplay(new Simpson(), new ThreeColumnFile(fileNameRoot+"simpson"))); + outputNames.push_back(fileNameRoot+"simpson"); + }else if (Estimators[i] == "bootstrap") { + cDisplays.push_back(new CollectDisplay(new Bootstrap(), new OneColumnFile(fileNameRoot+"bootstrap"))); + outputNames.push_back(fileNameRoot+"bootstrap"); + }else if (Estimators[i] == "geometric") { + cDisplays.push_back(new CollectDisplay(new Geom(), new OneColumnFile(fileNameRoot+"geometric"))); + outputNames.push_back(fileNameRoot+"geometric"); + }else if (Estimators[i] == "qstat") { + cDisplays.push_back(new CollectDisplay(new QStat(), new OneColumnFile(fileNameRoot+"qstat"))); + outputNames.push_back(fileNameRoot+"qstat"); + }else if (Estimators[i] == "logseries") { + cDisplays.push_back(new CollectDisplay(new LogSD(), new OneColumnFile(fileNameRoot+"logseries"))); + outputNames.push_back(fileNameRoot+"logseries"); + }else if (Estimators[i] == "bergerparker") { + cDisplays.push_back(new CollectDisplay(new BergerParker(), new OneColumnFile(fileNameRoot+"bergerparker"))); + outputNames.push_back(fileNameRoot+"bergerparker"); + }else if (Estimators[i] == "bstick") { + cDisplays.push_back(new CollectDisplay(new BStick(), new ThreeColumnFile(fileNameRoot+"bstick"))); + outputNames.push_back(fileNameRoot+"bstick"); + }else if (Estimators[i] == "goodscoverage") { + cDisplays.push_back(new CollectDisplay(new GoodsCoverage(), new OneColumnFile(fileNameRoot+"goodscoverage"))); + outputNames.push_back(fileNameRoot+"goodscoverage"); + }else if (Estimators[i] == "efron") { + cDisplays.push_back(new CollectDisplay(new Efron(size), new OneColumnFile(fileNameRoot+"efron"))); + outputNames.push_back(fileNameRoot+"efron"); + }else if (Estimators[i] == "boneh") { + cDisplays.push_back(new CollectDisplay(new Boneh(size), new OneColumnFile(fileNameRoot+"boneh"))); + outputNames.push_back(fileNameRoot+"boneh"); + }else if (Estimators[i] == "solow") { + cDisplays.push_back(new CollectDisplay(new Solow(size), new OneColumnFile(fileNameRoot+"solow"))); + outputNames.push_back(fileNameRoot+"solow"); + }else if (Estimators[i] == "shen") { + cDisplays.push_back(new CollectDisplay(new Shen(size, abund), new OneColumnFile(fileNameRoot+"shen"))); + outputNames.push_back(fileNameRoot+"shen"); + } + } + } - if(allLines == 1 || labels.count(order->getLabel()) == 1){ - - cCurve = new Collect(order, cDisplays); - cCurve->getCurve(freq); - delete cCurve; + //if the users entered no valid calculators don't execute command + if (cDisplays.size() == 0) { return 0; } - mothurOut(order->getLabel()); mothurOutEndLine(); - processedLabels.insert(order->getLabel()); - userLabels.erase(order->getLabel()); + read = new ReadOTUFile(inputFileNames[p]); + read->read(&*globaldata); + + order = globaldata->gorder; + string lastLabel = order->getLabel(); + input = globaldata->ginput; + //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 = labels; + if (m->control_pressed) { + for(int i=0;iginput = NULL; + delete read; + delete order; globaldata->gorder = NULL; + delete validCalculator; + globaldata->Groups.clear(); + return 0; } - //you have a label the user want that is smaller than this label and the last label has not already been processed - if ((anyLabelsToProcess(order->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) { - string saveLabel = order->getLabel(); + + + while((order != NULL) && ((allLines == 1) || (userLabels.size() != 0))) { + + if (m->control_pressed) { + for(int i=0;iginput = NULL; + delete read; + delete order; globaldata->gorder = NULL; + delete validCalculator; + globaldata->Groups.clear(); + return 0; + } + - delete order; + if(allLines == 1 || labels.count(order->getLabel()) == 1){ + + m->mothurOut(order->getLabel()); m->mothurOutEndLine(); + cCurve = new Collect(order, cDisplays); + cCurve->getCurve(freq); + delete cCurve; + + processedLabels.insert(order->getLabel()); + userLabels.erase(order->getLabel()); + + + } + //you have a label the user want that is smaller than this label and the last label has not already been processed + if ((anyLabelsToProcess(order->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) { + string saveLabel = order->getLabel(); + + delete order; + order = (input->getOrderVector(lastLabel)); + + m->mothurOut(order->getLabel()); m->mothurOutEndLine(); + cCurve = new Collect(order, cDisplays); + cCurve->getCurve(freq); + delete cCurve; + + + processedLabels.insert(order->getLabel()); + userLabels.erase(order->getLabel()); + + //restore real lastlabel to save below + order->setLabel(saveLabel); + } + + lastLabel = order->getLabel(); + + delete order; + order = (input->getOrderVector()); + } + + + if (m->control_pressed) { + for(int i=0;iginput = NULL; + delete read; + delete validCalculator; + globaldata->Groups.clear(); + return 0; + } + + //output error messages about any remaining user labels + set::iterator it; + bool needToRun = false; + for (it = userLabels.begin(); it != userLabels.end(); it++) { + m->mothurOut("Your file does not include the label " + *it); + if (processedLabels.count(lastLabel) != 1) { + m->mothurOut(". I will use " + lastLabel + "."); m->mothurOutEndLine(); + needToRun = true; + }else { + m->mothurOut(". Please refer to " + lastLabel + "."); m->mothurOutEndLine(); + } + } + + //run last label if you need to + if (needToRun == true) { + if (order != NULL) { delete order; } order = (input->getOrderVector(lastLabel)); + m->mothurOut(order->getLabel()); m->mothurOutEndLine(); + cCurve = new Collect(order, cDisplays); cCurve->getCurve(freq); delete cCurve; - - mothurOut(order->getLabel()); mothurOutEndLine(); - processedLabels.insert(order->getLabel()); - userLabels.erase(order->getLabel()); - //restore real lastlabel to save below - order->setLabel(saveLabel); + if (m->control_pressed) { + for(int i=0;iginput = NULL; + delete read; + delete order; globaldata->gorder = NULL; + delete validCalculator; + globaldata->Groups.clear(); + return 0; + } + delete order; } - lastLabel = order->getLabel(); - - delete order; - order = (input->getOrderVector()); + for(int i=0;iginput = NULL; + delete read; + globaldata->gorder = NULL; + delete validCalculator; } - //output error messages about any remaining user labels - set::iterator it; - bool needToRun = false; - for (it = userLabels.begin(); it != userLabels.end(); it++) { - mothurOut("Your file does not include the label " + *it); - if (processedLabels.count(lastLabel) != 1) { - mothurOut(". I will use " + lastLabel + "."); mothurOutEndLine(); - needToRun = true; - }else { - mothurOut(". Please refer to " + lastLabel + "."); mothurOutEndLine(); - } - } + if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } + + m->mothurOutEndLine(); + m->mothurOut("Output File Names: "); m->mothurOutEndLine(); + for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); } + m->mothurOutEndLine(); + - //run last label if you need to - if (needToRun == true) { - if (order != NULL) { delete order; } - order = (input->getOrderVector(lastLabel)); - - mothurOut(order->getLabel()); mothurOutEndLine(); + return 0; + } + catch(exception& e) { + m->errorOut(e, "CollectCommand", "execute"); + exit(1); + } +} + +//********************************************************************************************************************** +vector CollectCommand::parseSharedFile(string filename) { + try { + vector filenames; + + map filehandles; + map::iterator it3; + + + //read first line + read = new ReadOTUFile(filename); + read->read(&*globaldata); - cCurve = new Collect(order, cDisplays); - cCurve->getCurve(freq); - delete cCurve; - delete order; + input = globaldata->ginput; + vector lookup = input->getSharedRAbundVectors(); + + string sharedFileRoot = getRootName(filename); + + //clears file before we start to write to it below + for (int i=0; igetGroup() + ".rabund").c_str()); + filenames.push_back((sharedFileRoot + lookup[i]->getGroup() + ".rabund")); + } + + ofstream* temp; + for (int i=0; igetGroup()] = temp; + groups.push_back(lookup[i]->getGroup()); } + + while(lookup[0] != NULL) { + for (int i = 0; i < lookup.size(); i++) { + RAbundVector rav = lookup[i]->getRAbundVector(); + openOutputFileAppend(sharedFileRoot + lookup[i]->getGroup() + ".rabund", *(filehandles[lookup[i]->getGroup()])); + rav.print(*(filehandles[lookup[i]->getGroup()])); + (*(filehandles[lookup[i]->getGroup()])).close(); + } - for(int i=0;igetSharedRAbundVectors(); + } + + //free memory + for (it3 = filehandles.begin(); it3 != filehandles.end(); it3++) { + delete it3->second; + } + delete read; + delete input; + globaldata->ginput = NULL; + + return filenames; } catch(exception& e) { - errorOut(e, "CollectCommand", "execute"); + m->errorOut(e, "CollectCommand", "parseSharedFile"); exit(1); } } - //********************************************************************************************************************** +