X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=removegroupscommand.cpp;h=05b1170bf4501ebd3131a616fdcd58a9b49e59f2;hb=49d2b7459c5027557564b21e9487dadafbbbdc96;hp=2c98e814220432e2d27cf82499235a3fe3e928bb;hpb=5694c92fbf646fe01abc87bde2af59e14a9a56b6;p=mothur.git diff --git a/removegroupscommand.cpp b/removegroupscommand.cpp index 2c98e81..05b1170 100644 --- a/removegroupscommand.cpp +++ b/removegroupscommand.cpp @@ -11,71 +11,108 @@ #include "sequence.hpp" #include "listvector.hpp" #include "sharedutilities.h" +#include "inputdata.h" //********************************************************************************************************************** -vector RemoveGroupsCommand::getValidParameters(){ +vector RemoveGroupsCommand::setParameters(){ try { - string Array[] = {"fasta","name", "group", "accnos", "groups","list","taxonomy","outputdir","inputdir" }; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "FNGLT",false,false); parameters.push_back(pfasta); + CommandParameter pshared("shared", "InputTypes", "", "", "none", "sharedGroup", "none",false,false); parameters.push_back(pshared); + CommandParameter pname("name", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(pname); + CommandParameter pgroup("group", "InputTypes", "", "", "none", "sharedGroup", "FNGLT",false,false); parameters.push_back(pgroup); + CommandParameter pdesign("design", "InputTypes", "", "", "none", "sharedGroup", "FNGLT",false,false); parameters.push_back(pdesign); + CommandParameter plist("list", "InputTypes", "", "", "none", "none", "FNGLT",false,false); parameters.push_back(plist); + CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "none", "none", "FNGLT",false,false); parameters.push_back(ptaxonomy); + CommandParameter paccnos("accnos", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(paccnos); + 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, "RemoveGroupsCommand", "getValidParameters"); + m->errorOut(e, "RemoveGroupsCommand", "setParameters"); exit(1); } } //********************************************************************************************************************** -RemoveGroupsCommand::RemoveGroupsCommand(){ +string RemoveGroupsCommand::getHelpString(){ try { - abort = true; - //initialize outputTypes - vector tempOutNames; - outputTypes["fasta"] = tempOutNames; - outputTypes["taxonomy"] = tempOutNames; - outputTypes["name"] = tempOutNames; - outputTypes["group"] = tempOutNames; - outputTypes["list"] = tempOutNames; + string helpString = ""; + helpString += "The remove.groups command removes sequences from a specfic group or set of groups from the following file types: fasta, name, group, list, taxonomy, design or sharedfile.\n"; + helpString += "It outputs a file containing the sequences NOT in the those specified groups, or with a sharedfile eliminates the groups you selected.\n"; + helpString += "The remove.groups command parameters are accnos, fasta, name, group, list, taxonomy, shared, design and groups. The group parameter is required, unless you have a current group file or are using a sharedfile.\n"; + helpString += "You must also provide an accnos containing the list of groups to remove or set the groups parameter to the groups you wish to remove.\n"; + helpString += "The groups parameter allows you to specify which of the groups in your groupfile you would like removed. You can separate group names with dashes.\n"; + helpString += "The remove.groups command should be in the following format: remove.groups(accnos=yourAccnos, fasta=yourFasta, group=yourGroupFile).\n"; + helpString += "Example remove.groups(accnos=amazon.accnos, fasta=amazon.fasta, group=amazon.groups).\n"; + helpString += "or remove.groups(groups=pasture, fasta=amazon.fasta, amazon.groups).\n"; + helpString += "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n"; + return helpString; } catch(exception& e) { - m->errorOut(e, "RemoveGroupsCommand", "RemoveGroupsCommand"); + m->errorOut(e, "RemoveGroupsCommand", "getHelpString"); exit(1); } } //********************************************************************************************************************** -vector RemoveGroupsCommand::getRequiredParameters(){ +string RemoveGroupsCommand::getOutputFileNameTag(string type, string inputName=""){ try { - string Array[] = {"group"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); - return myArray; + string outputFileName = ""; + map >::iterator it; + + //is this a type this command creates + it = outputTypes.find(type); + if (it == outputTypes.end()) { m->mothurOut("[ERROR]: this command doesn't create a " + type + " output file.\n"); } + else { + if (type == "fasta") { outputFileName = "pick" + m->getExtension(inputName); } + else if (type == "taxonomy") { outputFileName = "pick" + m->getExtension(inputName); } + else if (type == "name") { outputFileName = "pick" + m->getExtension(inputName); } + else if (type == "group") { outputFileName = "pick" + m->getExtension(inputName); } + else if (type == "list") { outputFileName = "pick" + m->getExtension(inputName); } + else if (type == "shared") { outputFileName = "pick" + m->getExtension(inputName); } + else if (type == "design") { outputFileName = "pick" + m->getExtension(inputName); } + else { m->mothurOut("[ERROR]: No definition for type " + type + " output file tag.\n"); m->control_pressed = true; } + } + return outputFileName; } catch(exception& e) { - m->errorOut(e, "RemoveGroupsCommand", "getRequiredParameters"); + m->errorOut(e, "RemoveGroupsCommand", "getOutputFileNameTag"); exit(1); } } //********************************************************************************************************************** -vector RemoveGroupsCommand::getRequiredFiles(){ +RemoveGroupsCommand::RemoveGroupsCommand(){ try { - vector myArray; - return myArray; + abort = true; calledHelp = true; + setParameters(); + vector tempOutNames; + outputTypes["fasta"] = tempOutNames; + outputTypes["taxonomy"] = tempOutNames; + outputTypes["name"] = tempOutNames; + outputTypes["group"] = tempOutNames; + outputTypes["list"] = tempOutNames; + outputTypes["shared"] = tempOutNames; + outputTypes["design"] = tempOutNames; } catch(exception& e) { - m->errorOut(e, "RemoveGroupsCommand", "getRequiredFiles"); + m->errorOut(e, "RemoveGroupsCommand", "RemoveGroupsCommand"); exit(1); } } //********************************************************************************************************************** RemoveGroupsCommand::RemoveGroupsCommand(string option) { try { - 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[] = {"fasta","name", "group", "accnos", "groups", "list","taxonomy","outputdir","inputdir" }; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + vector myArray = setParameters(); OptionParser parser(option); map parameters = parser.getParameters(); @@ -95,6 +132,8 @@ RemoveGroupsCommand::RemoveGroupsCommand(string option) { outputTypes["name"] = tempOutNames; outputTypes["group"] = tempOutNames; outputTypes["list"] = tempOutNames; + outputTypes["shared"] = tempOutNames; + outputTypes["design"] = tempOutNames; //if the user changes the output directory command factory will send this info to us in the output parameter @@ -152,43 +191,119 @@ RemoveGroupsCommand::RemoveGroupsCommand(string option) { //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["taxonomy"] = inputDir + it->second; } } + + it = parameters.find("shared"); + //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["shared"] = inputDir + it->second; } + } + + it = parameters.find("design"); + //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["design"] = inputDir + it->second; } + } } //check for required parameters accnosfile = validParameter.validFile(parameters, "accnos", true); - if (accnosfile == "not open") { abort = true; } + if (accnosfile == "not open") { accnosfile = ""; abort = true; } else if (accnosfile == "not found") { accnosfile = ""; } + else { m->setAccnosFile(accnosfile); } fastafile = validParameter.validFile(parameters, "fasta", true); - if (fastafile == "not open") { abort = true; } + if (fastafile == "not open") { fastafile = ""; abort = true; } else if (fastafile == "not found") { fastafile = ""; } + else { m->setFastaFile(fastafile); } namefile = validParameter.validFile(parameters, "name", true); - if (namefile == "not open") { abort = true; } + if (namefile == "not open") { namefile = ""; abort = true; } else if (namefile == "not found") { namefile = ""; } + else { m->setNameFile(namefile); } groupfile = validParameter.validFile(parameters, "group", true); - if (groupfile == "not open") { abort = true; } - else if (groupfile == "not found") { groupfile = ""; m->mothurOut("You must provide a group file."); m->mothurOutEndLine(); abort = true; } + if (groupfile == "not open") { groupfile = ""; abort = true; } + else if (groupfile == "not found") { groupfile = ""; } + else { m->setGroupFile(groupfile); } listfile = validParameter.validFile(parameters, "list", true); - if (listfile == "not open") { abort = true; } + if (listfile == "not open") { listfile = ""; abort = true; } else if (listfile == "not found") { listfile = ""; } + else { m->setListFile(listfile); } taxfile = validParameter.validFile(parameters, "taxonomy", true); - if (taxfile == "not open") { abort = true; } + if (taxfile == "not open") { taxfile = ""; abort = true; } else if (taxfile == "not found") { taxfile = ""; } + else { m->setTaxonomyFile(taxfile); } + + designfile = validParameter.validFile(parameters, "design", true); + if (designfile == "not open") { designfile = ""; abort = true; } + else if (designfile == "not found") { designfile = ""; } + else { m->setDesignFile(designfile); } groups = validParameter.validFile(parameters, "groups", false); if (groups == "not found") { groups = ""; } else { m->splitAtDash(groups, Groups); + m->setGroups(Groups); + } + + sharedfile = validParameter.validFile(parameters, "shared", true); + if (sharedfile == "not open") { sharedfile = ""; abort = true; } + else if (sharedfile == "not found") { sharedfile = ""; } + else { m->setSharedFile(sharedfile); } + + groupfile = validParameter.validFile(parameters, "group", true); + if (groupfile == "not open") { groupfile = ""; abort = true; } + else if (groupfile == "not found") { groupfile = ""; } + else { m->setGroupFile(groupfile); } + + if ((sharedfile == "") && (groupfile == "") && (designfile == "")) { + //is there are current file available for any of these? + if ((namefile != "") || (fastafile != "") || (listfile != "") || (taxfile != "")) { + //give priority to group, then shared + groupfile = m->getGroupFile(); + if (groupfile != "") { m->mothurOut("Using " + groupfile + " as input file for the group parameter."); m->mothurOutEndLine(); } + else { + sharedfile = m->getSharedFile(); + if (sharedfile != "") { m->mothurOut("Using " + sharedfile + " as input file for the shared parameter."); m->mothurOutEndLine(); } + else { + m->mothurOut("You have no current groupfile or sharedfile and one is required."); m->mothurOutEndLine(); abort = true; + } + } + }else { + //give priority to shared, then group + sharedfile = m->getSharedFile(); + if (sharedfile != "") { m->mothurOut("Using " + sharedfile + " as input file for the shared parameter."); m->mothurOutEndLine(); } + else { + groupfile = m->getGroupFile(); + if (groupfile != "") { m->mothurOut("Using " + groupfile + " as input file for the group parameter."); m->mothurOutEndLine(); } + else { + designfile = m->getDesignFile(); + if (designfile != "") { m->mothurOut("Using " + designfile + " as input file for the design parameter."); m->mothurOutEndLine(); } + else { + m->mothurOut("You have no current groupfile or sharedfile or designfile and one is required."); m->mothurOutEndLine(); abort = true; + } + } + } + } } - if ((accnosfile == "") && (Groups.size() == 0)) { m->mothurOut("You must provide an accnos file or specify groups using the groups parameter."); m->mothurOutEndLine(); abort = true; } + if ((accnosfile == "") && (Groups.size() == 0)) { m->mothurOut("You must provide an accnos file containing group names or specify groups using the groups parameter."); m->mothurOutEndLine(); abort = true; } + + if ((fastafile == "") && (namefile == "") && (groupfile == "") && (sharedfile == "") && (designfile == "") && (listfile == "") && (taxfile == "")) { m->mothurOut("You must provide at least one of the following: fasta, name, taxonomy, group, shared, design or list."); m->mothurOutEndLine(); abort = true; } + if ((groupfile == "") && ((namefile != "") || (fastafile != "") || (listfile != "") || (taxfile != ""))) { m->mothurOut("If using a fasta, name, taxonomy, group or list, then you must provide a group file."); m->mothurOutEndLine(); abort = true; } - if ((fastafile == "") && (namefile == "") && (groupfile == "") && (listfile == "") && (taxfile == "")) { m->mothurOut("You must provide at least one of the following: fasta, name, taxonomy, group or list."); m->mothurOutEndLine(); abort = true; } + if ((namefile == "") && ((fastafile != "") || (taxfile != ""))){ + vector files; files.push_back(fastafile); files.push_back(taxfile); + parser.getNameFile(files); + } + } } @@ -199,47 +314,32 @@ RemoveGroupsCommand::RemoveGroupsCommand(string option) { } //********************************************************************************************************************** -void RemoveGroupsCommand::help(){ - try { - m->mothurOut("The remove.groups command removes sequences from a specfic group or set of groups from the following file types: fasta, name, group, list, taxonomy.\n"); - m->mothurOut("It outputs a file containing the sequences NOT in the those specified groups.\n"); - m->mothurOut("The remove.groups command parameters are accnos, fasta, name, group, list, taxonomy and groups. The group parameter is required.\n"); - m->mothurOut("You must also provide an accnos containing the list of groups to remove or set the groups parameter to the groups you wish to remove.\n"); - m->mothurOut("The groups parameter allows you to specify which of the groups in your groupfile you would like removed. You can separate group names with dashes.\n"); - m->mothurOut("The remove.groups command should be in the following format: remove.groups(accnos=yourAccnos, fasta=yourFasta, group=yourGroupFile).\n"); - m->mothurOut("Example remove.seqs(accnos=amazon.accnos, fasta=amazon.fasta, group=amazon.groups).\n"); - m->mothurOut("or remove.seqs(groups=pasture, fasta=amazon.fasta, amazon.groups).\n"); - m->mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n\n"); - } - catch(exception& e) { - m->errorOut(e, "RemoveGroupsCommand", "help"); - exit(1); - } -} - -//********************************************************************************************************************** - int RemoveGroupsCommand::execute(){ try { - if (abort == true) { return 0; } - - groupMap = new GroupMap(groupfile); - groupMap->readMap(); + if (abort == true) { if (calledHelp) { return 0; } return 2; } //get groups you want to remove - if (accnosfile != "") { readAccnos(); } - - //make sure groups are valid - //takes care of user setting groupNames that are invalid or setting groups=all - SharedUtil* util = new SharedUtil(); - util->setGroups(Groups, groupMap->namesOfGroups); - delete util; + if (accnosfile != "") { m->readAccnos(accnosfile, Groups); m->setGroups(Groups); } - //fill names with names of sequences that are from the groups we want to remove - fillNames(); - - if (m->control_pressed) { delete groupMap; return 0; } + if (groupfile != "") { + groupMap = new GroupMap(groupfile); + groupMap->readMap(); + + //make sure groups are valid + //takes care of user setting groupNames that are invalid or setting groups=all + SharedUtil* util = new SharedUtil(); + vector namesGroups = groupMap->getNamesOfGroups(); + util->setGroups(Groups, namesGroups); + delete util; + + //fill names with names of sequences that are from the groups we want to remove + fillNames(); + + delete groupMap; + } + + if (m->control_pressed) { return 0; } //read through the correct file and output lines you want to keep if (namefile != "") { readName(); } @@ -247,18 +347,53 @@ int RemoveGroupsCommand::execute(){ if (groupfile != "") { readGroup(); } if (listfile != "") { readList(); } if (taxfile != "") { readTax(); } + if (sharedfile != "") { readShared(); } + if (designfile != "") { readDesign(); } - if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } - - m->mothurOut("Removed " + toString(names.size()) + " sequences. From the groups: "); m->mothurOutEndLine(); - for (int i = 0; i < Groups.size(); i++) { m->mothurOut(Groups[i]); m->mothurOutEndLine(); } - m->mothurOutEndLine(); - + if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } + if (outputNames.size() != 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(); + + //set fasta file as new current fastafile + string current = ""; + itTypes = outputTypes.find("fasta"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setFastaFile(current); } + } + + itTypes = outputTypes.find("name"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setNameFile(current); } + } + + itTypes = outputTypes.find("group"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setGroupFile(current); } + } + + itTypes = outputTypes.find("list"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setListFile(current); } + } + + itTypes = outputTypes.find("taxonomy"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setTaxonomyFile(current); } + } + + itTypes = outputTypes.find("shared"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setSharedFile(current); } + } + + itTypes = outputTypes.find("design"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setDesignFile(current); } + } } return 0; @@ -275,7 +410,7 @@ int RemoveGroupsCommand::readFasta(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(fastafile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(fastafile)) + "pick" + m->getExtension(fastafile); + string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(fastafile)) + getOutputFileNameTag("fasta", fastafile); ofstream out; m->openOutputFile(outputFileName, out); @@ -285,9 +420,10 @@ int RemoveGroupsCommand::readFasta(){ string name; bool wroteSomething = false; + int removedCount = 0; while(!in.eof()){ - if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } Sequence currSeq(in); name = currSeq.getName(); @@ -296,8 +432,15 @@ int RemoveGroupsCommand::readFasta(){ //if this name is in the accnos file if (names.count(name) == 0) { wroteSomething = true; - - currSeq.printSequence(out); + currSeq.printSequence(out); + }else { + //if you are not in the accnos file check if you are a name that needs to be changed + map::iterator it = uniqueToRedundant.find(name); + if (it != uniqueToRedundant.end()) { + wroteSomething = true; + currSeq.setName(it->second); + currSeq.printSequence(out); + }else { removedCount++; } } } m->gobble(in); @@ -308,6 +451,8 @@ int RemoveGroupsCommand::readFasta(){ if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the groups you wish to remove."); m->mothurOutEndLine(); } outputTypes["fasta"].push_back(outputFileName); outputNames.push_back(outputFileName); + m->mothurOut("Removed " + toString(removedCount) + " sequences from your fasta file."); m->mothurOutEndLine(); + return 0; } @@ -316,13 +461,96 @@ int RemoveGroupsCommand::readFasta(){ exit(1); } } +//********************************************************************************************************************** +int RemoveGroupsCommand::readShared(){ + try { + string thisOutputDir = outputDir; + if (outputDir == "") { thisOutputDir += m->hasPath(sharedfile); } + + //get group names from sharedfile so we can set Groups to the groupNames we want to keep + //that way we can take advantage of the reads in inputdata and sharedRabundVector + InputData* tempInput = new InputData(sharedfile, "sharedfile"); + vector lookup = tempInput->getSharedRAbundVectors(); + + //save m->Groups + vector allGroupsNames = m->getAllGroups(); + vector mothurOutGroups = m->getGroups(); + + vector groupsToKeep; + for (int i = 0; i < allGroupsNames.size(); i++) { + if (!m->inUsersGroups(allGroupsNames[i], m->getGroups())) { + groupsToKeep.push_back(allGroupsNames[i]); + } + } + + if (allGroupsNames.size() == groupsToKeep.size()) { m->mothurOut("Your file does not contain any groups you wish to remove."); m->mothurOutEndLine(); m->setGroups(mothurOutGroups); delete tempInput; for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } return 0; } + + //reset read + for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } + delete tempInput; + m->setGroups(groupsToKeep); + m->clearAllGroups(); + m->saveNextLabel = ""; + m->printedHeaders = false; + m->currentBinLabels.clear(); + m->binLabelsInFile.clear(); + + InputData input(sharedfile, "sharedfile"); + lookup = input.getSharedRAbundVectors(); + bool wroteSomething = false; + + while(lookup[0] != NULL) { + + string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(sharedfile)) + lookup[0]->getLabel() + "." + getOutputFileNameTag("shared", sharedfile); + ofstream out; + m->openOutputFile(outputFileName, out); + outputTypes["shared"].push_back(outputFileName); outputNames.push_back(outputFileName); + + if (m->control_pressed) { out.close(); m->mothurRemove(outputFileName); for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } return 0; } + + lookup[0]->printHeaders(out); + + for (int i = 0; i < lookup.size(); i++) { + out << lookup[i]->getLabel() << '\t' << lookup[i]->getGroup() << '\t'; + lookup[i]->print(out); + wroteSomething = true; + + } + + //get next line to process + //prevent memory leak + for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } + lookup = input.getSharedRAbundVectors(); + + out.close(); + } + + + m->setGroups(mothurOutGroups); + + if (wroteSomething == false) { m->mothurOut("Your file contains only the groups you wish to remove."); m->mothurOutEndLine(); } + + string groupsString = ""; + for (int i = 0; i < Groups.size()-1; i++) { groupsString += Groups[i] + ", "; } + groupsString += Groups[Groups.size()-1]; + + m->mothurOut("Removed groups: " + groupsString + " from your shared file."); m->mothurOutEndLine(); + + return 0; + + } + catch(exception& e) { + m->errorOut(e, "RemoveGroupsCommand", "readShared"); + exit(1); + } +} //********************************************************************************************************************** int RemoveGroupsCommand::readList(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(listfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(listfile)) + "pick" + m->getExtension(listfile); + string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(listfile)) + getOutputFileNameTag("list", listfile); ofstream out; m->openOutputFile(outputFileName, out); @@ -331,8 +559,12 @@ int RemoveGroupsCommand::readList(){ m->openInputFile(listfile, in); bool wroteSomething = false; + int removedCount = 0; while(!in.eof()){ + + removedCount = 0; + //read in list vector ListVector list(in); @@ -342,7 +574,7 @@ int RemoveGroupsCommand::readList(){ //for each bin for (int i = 0; i < list.getNumBins(); i++) { - if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } //parse out names that are in accnos file string binnames = list.get(i); @@ -354,10 +586,23 @@ int RemoveGroupsCommand::readList(){ //if that name is in the .accnos file, add it if (names.count(name) == 0) { newNames += name + ","; } + else { + //if you are not in the accnos file check if you are a name that needs to be changed + map::iterator it = uniqueToRedundant.find(name); + if (it != uniqueToRedundant.end()) { + newNames += it->second + ","; + }else { removedCount++; } + } } //get last name if (names.count(binnames) == 0) { newNames += binnames + ","; } + else { //if you are not in the accnos file check if you are a name that needs to be changed + map::iterator it = uniqueToRedundant.find(binnames); + if (it != uniqueToRedundant.end()) { + newNames += it->second + ","; + }else { removedCount++; } + } //if there are names in this bin add to new list if (newNames != "") { @@ -380,6 +625,8 @@ int RemoveGroupsCommand::readList(){ if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the groups you wish to remove."); m->mothurOutEndLine(); } outputTypes["list"].push_back(outputFileName); outputNames.push_back(outputFileName); + m->mothurOut("Removed " + toString(removedCount) + " sequences from your list file."); m->mothurOutEndLine(); + return 0; } @@ -393,8 +640,7 @@ int RemoveGroupsCommand::readName(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(namefile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(namefile)) + "pick" + m->getExtension(namefile); - + string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(namefile)) + getOutputFileNameTag("name", namefile); ofstream out; m->openOutputFile(outputFileName, out); @@ -403,9 +649,10 @@ int RemoveGroupsCommand::readName(){ string name, firstCol, secondCol; bool wroteSomething = false; + int removedCount = 0; while(!in.eof()){ - if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } in >> firstCol; m->gobble(in); in >> secondCol; @@ -420,6 +667,7 @@ int RemoveGroupsCommand::readName(){ } } + removedCount += parsedNames.size()-validSecond.size(); //if the name in the first column is in the set then print it and any other names in second column also in set if (names.count(firstCol) == 0) { @@ -445,6 +693,7 @@ int RemoveGroupsCommand::readName(){ //you know you have at least one valid second since first column is valid for (int i = 0; i < validSecond.size()-1; i++) { out << validSecond[i] << ','; } out << validSecond[validSecond.size()-1] << endl; + uniqueToRedundant[firstCol] = validSecond[0]; } } @@ -456,6 +705,8 @@ int RemoveGroupsCommand::readName(){ if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the groups you wish to remove."); m->mothurOutEndLine(); } outputTypes["name"].push_back(outputFileName); outputNames.push_back(outputFileName); + m->mothurOut("Removed " + toString(removedCount) + " sequences from your name file."); m->mothurOutEndLine(); + return 0; } catch(exception& e) { @@ -469,8 +720,7 @@ int RemoveGroupsCommand::readGroup(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(groupfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(groupfile)) + "pick" + m->getExtension(groupfile); - + string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(groupfile)) + getOutputFileNameTag("group", groupfile); ofstream out; m->openOutputFile(outputFileName, out); @@ -479,9 +729,10 @@ int RemoveGroupsCommand::readGroup(){ string name, group; bool wroteSomething = false; + int removedCount = 0; while(!in.eof()){ - if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } in >> name; //read from first column in >> group; //read from second column @@ -490,7 +741,7 @@ int RemoveGroupsCommand::readGroup(){ if (names.count(name) == 0) { wroteSomething = true; out << name << '\t' << group << endl; - } + }else { removedCount++; } m->gobble(in); } @@ -500,6 +751,9 @@ int RemoveGroupsCommand::readGroup(){ if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the groups you wish to remove."); m->mothurOutEndLine(); } outputTypes["group"].push_back(outputFileName); outputNames.push_back(outputFileName); + m->mothurOut("Removed " + toString(removedCount) + " sequences from your group file."); m->mothurOutEndLine(); + + return 0; } catch(exception& e) { @@ -508,68 +762,100 @@ int RemoveGroupsCommand::readGroup(){ } } //********************************************************************************************************************** -int RemoveGroupsCommand::readTax(){ +int RemoveGroupsCommand::readDesign(){ try { string thisOutputDir = outputDir; - if (outputDir == "") { thisOutputDir += m->hasPath(taxfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(taxfile)) + "pick" + m->getExtension(taxfile); + if (outputDir == "") { thisOutputDir += m->hasPath(designfile); } + string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(designfile)) + getOutputFileNameTag("design", designfile); + ofstream out; m->openOutputFile(outputFileName, out); ifstream in; - m->openInputFile(taxfile, in); - string name, tax; + m->openInputFile(designfile, in); + string name, group; bool wroteSomething = false; + int removedCount = 0; while(!in.eof()){ - if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } in >> name; //read from first column - in >> tax; //read from second column + in >> group; //read from second column //if this name is in the accnos file - if (names.count(name) == 0) { + if (!(m->inUsersGroups(name, Groups))) { wroteSomething = true; - out << name << '\t' << tax << endl; - } + out << name << '\t' << group << endl; + }else { removedCount++; } m->gobble(in); } in.close(); out.close(); - if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the groups you wish to remove."); m->mothurOutEndLine(); } - outputTypes["taxonomy"].push_back(outputFileName); outputNames.push_back(outputFileName); + if (wroteSomething == false) { m->mothurOut("Your file contains only groups from the groups you wish to remove."); m->mothurOutEndLine(); } + outputTypes["design"].push_back(outputFileName); outputNames.push_back(outputFileName); + + m->mothurOut("Removed " + toString(removedCount) + " groups from your design file."); m->mothurOutEndLine(); + return 0; } catch(exception& e) { - m->errorOut(e, "RemoveGroupsCommand", "readTax"); + m->errorOut(e, "RemoveGroupsCommand", "readDesign"); exit(1); } } + //********************************************************************************************************************** -void RemoveGroupsCommand::readAccnos(){ +int RemoveGroupsCommand::readTax(){ try { - Groups.clear(); + string thisOutputDir = outputDir; + if (outputDir == "") { thisOutputDir += m->hasPath(taxfile); } + string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(taxfile)) + getOutputFileNameTag("taxonomy", taxfile); + ofstream out; + m->openOutputFile(outputFileName, out); ifstream in; - m->openInputFile(accnosfile, in); - string name; + m->openInputFile(taxfile, in); + string name, tax; + + bool wroteSomething = false; + int removedCount = 0; while(!in.eof()){ - in >> name; + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } + + in >> name; //read from first column + in >> tax; //read from second column - Groups.push_back(name); + //if this name is in the accnos file + if (names.count(name) == 0) { + wroteSomething = true; + out << name << '\t' << tax << endl; + }else { //if you are not in the accnos file check if you are a name that needs to be changed + map::iterator it = uniqueToRedundant.find(name); + if (it != uniqueToRedundant.end()) { + wroteSomething = true; + out << it->second << '\t' << tax << endl; + }else { removedCount++; } } m->gobble(in); } - in.close(); + in.close(); + out.close(); + + if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the groups you wish to remove."); m->mothurOutEndLine(); } + outputTypes["taxonomy"].push_back(outputFileName); outputNames.push_back(outputFileName); + + m->mothurOut("Removed " + toString(removedCount) + " sequences from your taxonomy file."); m->mothurOutEndLine(); + return 0; } catch(exception& e) { - m->errorOut(e, "RemoveGroupsCommand", "readAccnos"); + m->errorOut(e, "RemoveGroupsCommand", "readTax"); exit(1); } }