X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=getgroupscommand.cpp;h=fe6f571669bf820d1a153ef3f44327611666b8a1;hb=957d67f7d8bbadfd2930de061e89fd9b149270fd;hp=d3470f16ad990d7285e51e534ad059666a03d097;hpb=8742edef7a51b82834289e570d336f5a81ba1f2b;p=mothur.git diff --git a/getgroupscommand.cpp b/getgroupscommand.cpp index d3470f1..fe6f571 100644 --- a/getgroupscommand.cpp +++ b/getgroupscommand.cpp @@ -16,12 +16,13 @@ //********************************************************************************************************************** vector GetGroupsCommand::setParameters(){ try { - CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pfasta); - CommandParameter pshared("shared", "InputTypes", "", "", "none", "FNGLT-sharedGroup", "none",false,false); parameters.push_back(pshared); - CommandParameter pname("name", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pname); - CommandParameter pgroup("group", "InputTypes", "", "", "none", "FNGLT-sharedGroup", "none",false,false); parameters.push_back(pgroup); - CommandParameter plist("list", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(plist); - CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(ptaxonomy); + 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); @@ -40,9 +41,9 @@ vector GetGroupsCommand::setParameters(){ string GetGroupsCommand::getHelpString(){ try { string helpString = ""; - helpString += "The get.groups command selects sequences from a specfic group or set of groups from the following file types: fasta, name, group, list, taxonomy or shared file.\n"; + helpString += "The get.groups command selects sequences from a specfic group or set of groups from the following file types: fasta, name, group, list, taxonomy, design or shared file.\n"; helpString += "It outputs a file containing the sequences in the those specified groups, or a sharedfile containing only those groups.\n"; - helpString += "The get.groups command parameters are accnos, fasta, name, group, list, taxonomy, shared and groups. The group parameter is required, unless you have a current group file, or are using a shared file.\n"; + helpString += "The get.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 shared file.\n"; helpString += "You must also provide an accnos containing the list of groups to get or set the groups parameter to the groups you wish to select.\n"; helpString += "The groups parameter allows you to specify which of the groups in your groupfile you would like. You can separate group names with dashes.\n"; helpString += "The get.groups command should be in the following format: get.groups(accnos=yourAccnos, fasta=yourFasta, group=yourGroupFile).\n"; @@ -56,6 +57,33 @@ string GetGroupsCommand::getHelpString(){ exit(1); } } +//********************************************************************************************************************** +string GetGroupsCommand::getOutputFileNameTag(string type, string inputName=""){ + try { + 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, "GetGroupsCommand", "getOutputFileNameTag"); + exit(1); + } +} + //********************************************************************************************************************** GetGroupsCommand::GetGroupsCommand(){ try { @@ -68,6 +96,7 @@ GetGroupsCommand::GetGroupsCommand(){ outputTypes["group"] = tempOutNames; outputTypes["list"] = tempOutNames; outputTypes["shared"] = tempOutNames; + outputTypes["design"] = tempOutNames; } catch(exception& e) { m->errorOut(e, "GetGroupsCommand", "GetGroupsCommand"); @@ -105,6 +134,7 @@ GetGroupsCommand::GetGroupsCommand(string option) { 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 @@ -170,6 +200,14 @@ GetGroupsCommand::GetGroupsCommand(string option) { //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; } + } } @@ -180,22 +218,27 @@ GetGroupsCommand::GetGroupsCommand(string option) { 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") { 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; } 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); } @@ -203,7 +246,7 @@ GetGroupsCommand::GetGroupsCommand(string option) { if (groups == "not found") { groups = ""; } else { m->splitAtDash(groups, Groups); - m->Groups = Groups; + m->setGroups(Groups); } sharedfile = validParameter.validFile(parameters, "shared", true); @@ -214,9 +257,14 @@ GetGroupsCommand::GetGroupsCommand(string option) { 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 == "")) { + else { m->setGroupFile(groupfile); } + + designfile = validParameter.validFile(parameters, "design", true); + if (designfile == "not open") { designfile = ""; abort = true; } + else if (designfile == "not found") { designfile = ""; } + else { m->setDesignFile(designfile); } + + 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 @@ -237,7 +285,11 @@ GetGroupsCommand::GetGroupsCommand(string option) { groupfile = m->getGroupFile(); if (groupfile != "") { m->mothurOut("Using " + groupfile + " as input file for the group parameter."); m->mothurOutEndLine(); } else { - m->mothurOut("You have no current groupfile or sharedfile and one is required."); m->mothurOutEndLine(); abort = true; + 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; + } } } } @@ -245,9 +297,13 @@ GetGroupsCommand::GetGroupsCommand(string option) { 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 ((fastafile == "") && (namefile == "") && (groupfile == "") && (sharedfile == "") && (listfile == "") && (taxfile == "")) { m->mothurOut("You must provide at least one of the following: fasta, name, taxonomy, group, shared or list."); m->mothurOutEndLine(); abort = true; } + if ((fastafile == "") && (namefile == "") && (groupfile == "") && (designfile == "") && (sharedfile == "") && (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 ((namefile == "") && ((fastafile != "") || (taxfile != ""))){ + vector files; files.push_back(fastafile); files.push_back(taxfile); + parser.getNameFile(files); + } } } @@ -264,7 +320,7 @@ int GetGroupsCommand::execute(){ if (abort == true) { if (calledHelp) { return 0; } return 2; } //get groups you want to remove - if (accnosfile != "") { readAccnos(); } + if (accnosfile != "") { m->readAccnos(accnosfile, Groups); m->setGroups(Groups); } if (groupfile != "") { groupMap = new GroupMap(groupfile); @@ -273,7 +329,9 @@ int GetGroupsCommand::execute(){ //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); + vector gNamesOfGroups = groupMap->getNamesOfGroups(); + util->setGroups(Groups, gNamesOfGroups); + groupMap->setNamesOfGroups(gNamesOfGroups); delete util; //fill names with names of sequences that are from the groups we want to remove @@ -291,6 +349,7 @@ int GetGroupsCommand::execute(){ if (listfile != "") { readList(); } if (taxfile != "") { readTax(); } if (sharedfile != "") { readShared(); } + if (designfile != "") { readDesign(); } if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } @@ -332,6 +391,11 @@ int GetGroupsCommand::execute(){ 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; @@ -348,7 +412,7 @@ int GetGroupsCommand::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); @@ -373,6 +437,15 @@ int GetGroupsCommand::readFasta(){ currSeq.printSequence(out); selectedCount++; + }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); + selectedCount++; + } } } m->gobble(in); @@ -407,7 +480,7 @@ int GetGroupsCommand::readShared(){ while(lookup[0] != NULL) { - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(sharedfile)) + lookup[0]->getLabel() + ".pick" + m->getExtension(sharedfile); + 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); @@ -452,7 +525,7 @@ int GetGroupsCommand::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); @@ -488,10 +561,26 @@ int GetGroupsCommand::readList(){ //if that name is in the .accnos file, add it if (names.count(name) != 0) { newNames += name + ","; selectedCount++; } + 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 + ","; + selectedCount++; + } + } } //get last name if (names.count(binnames) != 0) { newNames += binnames + ","; selectedCount++; } + 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 + ","; + selectedCount++; + } + } //if there are names in this bin add to new list if (newNames != "") { @@ -529,7 +618,7 @@ int GetGroupsCommand::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); @@ -583,6 +672,7 @@ int GetGroupsCommand::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]; } } @@ -609,7 +699,7 @@ int GetGroupsCommand::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); @@ -652,30 +742,33 @@ int GetGroupsCommand::readGroup(){ } } //********************************************************************************************************************** -int GetGroupsCommand::readTax(){ +int GetGroupsCommand::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 selectedCount = 0; while(!in.eof()){ 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; + selectedCount++; } m->gobble(in); @@ -683,39 +776,67 @@ int GetGroupsCommand::readTax(){ in.close(); out.close(); - if (wroteSomething == false) { m->mothurOut("Your file does NOT contain sequences from the groups you wish to get."); m->mothurOutEndLine(); } - outputTypes["taxonomy"].push_back(outputFileName); outputNames.push_back(outputFileName); + if (wroteSomething == false) { m->mothurOut("Your file does NOT contain groups from the groups you wish to get."); m->mothurOutEndLine(); } + outputTypes["design"].push_back(outputFileName); outputNames.push_back(outputFileName); + + m->mothurOut("Selected " + toString(selectedCount) + " groups from your design file."); m->mothurOutEndLine(); + return 0; } catch(exception& e) { - m->errorOut(e, "GetGroupsCommand", "readTax"); + m->errorOut(e, "GetGroupsCommand", "readDesign"); exit(1); } } + + //********************************************************************************************************************** -void GetGroupsCommand::readAccnos(){ +int GetGroupsCommand::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; 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; + } + } m->gobble(in); } - in.close(); + in.close(); + out.close(); - m->Groups = Groups; + if (wroteSomething == false) { m->mothurOut("Your file does NOT contain sequences from the groups you wish to get."); m->mothurOutEndLine(); } + outputTypes["taxonomy"].push_back(outputFileName); outputNames.push_back(outputFileName); + return 0; } catch(exception& e) { - m->errorOut(e, "GetGroupsCommand", "readAccnos"); + m->errorOut(e, "GetGroupsCommand", "readTax"); exit(1); } }