X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=getgroupscommand.cpp;h=bb15a3f5a21e3c7785283cfc5d6eade2c1bda6ed;hp=1832f96aed8122020b5ddf0ad5881275e3cc6481;hb=cf9987b67aa49777a4c91c2d21f96e58bf17aa82;hpb=5694c92fbf646fe01abc87bde2af59e14a9a56b6 diff --git a/getgroupscommand.cpp b/getgroupscommand.cpp index 1832f96..bb15a3f 100644 --- a/getgroupscommand.cpp +++ b/getgroupscommand.cpp @@ -11,71 +11,106 @@ #include "sequence.hpp" #include "listvector.hpp" #include "sharedutilities.h" +#include "inputdata.h" //********************************************************************************************************************** -vector GetGroupsCommand::getValidParameters(){ +vector GetGroupsCommand::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","fasta",false,false, true); parameters.push_back(pfasta); + CommandParameter pshared("shared", "InputTypes", "", "", "none", "sharedGroup", "none","shared",false,false, true); parameters.push_back(pshared); + CommandParameter pname("name", "InputTypes", "", "", "NameCount", "none", "none","name",false,false, true); parameters.push_back(pname); + CommandParameter pcount("count", "InputTypes", "", "", "NameCount-CountGroup", "none", "none","count",false,false, true); parameters.push_back(pcount); + CommandParameter pgroup("group", "InputTypes", "", "", "CountGroup", "sharedGroup", "FNGLT","group",false,false, true); parameters.push_back(pgroup); + CommandParameter pdesign("design", "InputTypes", "", "", "none", "sharedGroup", "FNGLT","design",false,false, true); parameters.push_back(pdesign); + CommandParameter plist("list", "InputTypes", "", "", "none", "none", "FNGLT","list",false,false, true); parameters.push_back(plist); + CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "none", "none", "FNGLT","taxonomy",false,false, true); 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, "GetGroupsCommand", "getValidParameters"); + m->errorOut(e, "GetGroupsCommand", "setParameters"); exit(1); } } //********************************************************************************************************************** -GetGroupsCommand::GetGroupsCommand(){ +string GetGroupsCommand::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 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, design and groups. The group or count parameter is required, unless you have a current group or count 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"; + helpString += "Example get.groups(accnos=amazon.accnos, fasta=amazon.fasta, group=amazon.groups).\n"; + helpString += "or get.groups(groups=pasture, fasta=amazon.fasta, group=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, "GetGroupsCommand", "GetGroupsCommand"); + m->errorOut(e, "GetGroupsCommand", "getHelpString"); exit(1); } } //********************************************************************************************************************** -vector GetGroupsCommand::getRequiredParameters(){ - try { - string Array[] = {"group"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); - return myArray; - } - catch(exception& e) { - m->errorOut(e, "GetGroupsCommand", "getRequiredParameters"); - exit(1); - } +string GetGroupsCommand::getOutputPattern(string type) { + try { + string pattern = ""; + + if (type == "fasta") { pattern = "[filename],pick,[extension]"; } + else if (type == "taxonomy") { pattern = "[filename],pick,[extension]"; } + else if (type == "name") { pattern = "[filename],pick,[extension]"; } + else if (type == "group") { pattern = "[filename],pick,[extension]"; } + else if (type == "count") { pattern = "[filename],pick,[extension]"; } + else if (type == "list") { pattern = "[filename],[tag],pick,[extension]"; } + else if (type == "shared") { pattern = "[filename],[tag],pick,[extension]"; } + else if (type == "design") { pattern = "[filename],pick,[extension]"; } + else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; } + + return pattern; + } + catch(exception& e) { + m->errorOut(e, "GetGroupsCommand", "getOutputPattern"); + exit(1); + } } //********************************************************************************************************************** -vector GetGroupsCommand::getRequiredFiles(){ +GetGroupsCommand::GetGroupsCommand(){ 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; + outputTypes["count"] = tempOutNames; } catch(exception& e) { - m->errorOut(e, "GetGroupsCommand", "getRequiredFiles"); + m->errorOut(e, "GetGroupsCommand", "GetGroupsCommand"); exit(1); } } //********************************************************************************************************************** GetGroupsCommand::GetGroupsCommand(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 +130,9 @@ GetGroupsCommand::GetGroupsCommand(string option) { outputTypes["name"] = tempOutNames; outputTypes["group"] = tempOutNames; outputTypes["list"] = tempOutNames; + outputTypes["shared"] = tempOutNames; + outputTypes["design"] = tempOutNames; + outputTypes["count"] = tempOutNames; //if the user changes the output directory command factory will send this info to us in the output parameter @@ -152,43 +190,146 @@ GetGroupsCommand::GetGroupsCommand(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; } + } + + it = parameters.find("count"); + //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["count"] = inputDir + it->second; } + } } //check for required parameters accnosfile = validParameter.validFile(parameters, "accnos", true); if (accnosfile == "not open") { abort = true; } - else if (accnosfile == "not found") { accnosfile = ""; } + else if (accnosfile == "not found") { accnosfile = ""; } + else { m->setAccnosFile(accnosfile); } fastafile = validParameter.validFile(parameters, "fasta", true); - if (fastafile == "not open") { abort = true; } - else if (fastafile == "not found") { fastafile = ""; } + 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 = ""; } - - 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; } + else { m->setNameFile(namefile); } 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); } groups = validParameter.validFile(parameters, "groups", false); if (groups == "not found") { groups = ""; } - else { + 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); } + + designfile = validParameter.validFile(parameters, "design", true); + if (designfile == "not open") { designfile = ""; abort = true; } + else if (designfile == "not found") { designfile = ""; } + else { m->setDesignFile(designfile); } + + countfile = validParameter.validFile(parameters, "count", true); + if (countfile == "not open") { countfile = ""; abort = true; } + else if (countfile == "not found") { countfile = ""; } + else { m->setCountTableFile(countfile); } + + if ((namefile != "") && (countfile != "")) { + m->mothurOut("[ERROR]: you may only use one of the following: name or count."); m->mothurOutEndLine(); abort = true; + } + + if ((groupfile != "") && (countfile != "")) { + m->mothurOut("[ERROR]: you may only use one of the following: group or count."); m->mothurOutEndLine(); abort=true; + } + + + if ((sharedfile == "") && (groupfile == "") && (designfile == "") && (countfile == "")) { + //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 { + countfile = m->getCountTableFile(); + if (countfile != "") { m->mothurOut("Using " + countfile + " as input file for the count parameter."); m->mothurOutEndLine(); } + else { + m->mothurOut("You have no current groupfile, countfile 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 { + countfile = m->getCountTableFile(); + if (countfile != "") { m->mothurOut("Using " + countfile + " as input file for the count parameter."); m->mothurOutEndLine(); } + else { + m->mothurOut("You have no current groupfile, designfile, countfile or sharedfile 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 ((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 ((fastafile == "") && (namefile == "") && (countfile == "") && (groupfile == "") && (designfile == "") && (sharedfile == "") && (listfile == "") && (taxfile == "")) { m->mothurOut("You must provide at least one of the following: fasta, name, taxonomy, group, shared, design, count or list."); m->mothurOutEndLine(); abort = true; } + if (((groupfile == "") && (countfile == "")) && ((namefile != "") || (fastafile != "") || (listfile != "") || (taxfile != ""))) { m->mothurOut("If using a fasta, name, taxonomy, group or list, then you must provide a group or count file."); m->mothurOutEndLine(); abort = true; } + + if (countfile == "") { + if ((namefile == "") && ((fastafile != "") || (taxfile != ""))){ + vector files; files.push_back(fastafile); files.push_back(taxfile); + parser.getNameFile(files); + } + } } } @@ -199,66 +340,111 @@ GetGroupsCommand::GetGroupsCommand(string option) { } //********************************************************************************************************************** -void GetGroupsCommand::help(){ - try { - m->mothurOut("The get.groups command selects 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 in the those specified groups.\n"); - m->mothurOut("The get.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 get or set the groups parameter to the groups you wish to select.\n"); - m->mothurOut("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"); - m->mothurOut("The get.groups command should be in the following format: get.groups(accnos=yourAccnos, fasta=yourFasta, group=yourGroupFile).\n"); - m->mothurOut("Example get.seqs(accnos=amazon.accnos, fasta=amazon.fasta, group=amazon.groups).\n"); - m->mothurOut("or get.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, "GetGroupsCommand", "help"); - exit(1); - } -} - -//********************************************************************************************************************** - int GetGroupsCommand::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; - - //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 (accnosfile != "") { m->readAccnos(accnosfile, Groups); m->setGroups(Groups); } + + 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 gNamesOfGroups = groupMap->getNamesOfGroups(); + util->setGroups(Groups, gNamesOfGroups); + m->setGroups(Groups); + groupMap->setNamesOfGroups(gNamesOfGroups); + delete util; + + //fill names with names of sequences that are from the groups we want to remove + fillNames(); + + delete groupMap; + }else if (countfile != ""){ + if ((fastafile != "") || (listfile != "") || (taxfile != "")) { + m->mothurOut("\n[NOTE]: The count file should contain only unique names, so mothur assumes your fasta, list and taxonomy files also contain only uniques.\n\n"); + } + CountTable ct; + ct.readTable(countfile, true, false); + if (!ct.hasGroupInfo()) { m->mothurOut("[ERROR]: your count file does not contain group info, aborting.\n"); return 0; } + + vector gNamesOfGroups = ct.getNamesOfGroups(); + SharedUtil util; + util.setGroups(Groups, gNamesOfGroups); + m->setGroups(Groups); + for (int i = 0; i < Groups.size(); i++) { + vector thisGroupsSeqs = ct.getNamesOfSeqs(Groups[i]); + for (int j = 0; j < thisGroupsSeqs.size(); j++) { names.insert(thisGroupsSeqs[j]); } + } + } + + if (m->control_pressed) { return 0; } //read through the correct file and output lines you want to keep if (namefile != "") { readName(); } if (fastafile != "") { readFasta(); } if (groupfile != "") { readGroup(); } + if (countfile != "") { readCount(); } 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; } + if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } - m->mothurOut("Selected " + 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 (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); } + } + + itTypes = outputTypes.find("count"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setCountTableFile(current); } + } } return 0; @@ -275,7 +461,10 @@ 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); + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(fastafile)); + variables["[extension]"] = m->getExtension(fastafile); + string outputFileName = getOutputFileName("fasta", variables); ofstream out; m->openOutputFile(outputFileName, out); @@ -285,9 +474,10 @@ int GetGroupsCommand::readFasta(){ string name; bool wroteSomething = false; + int selectedCount = 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(); @@ -298,6 +488,16 @@ int GetGroupsCommand::readFasta(){ wroteSomething = true; 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); @@ -308,6 +508,9 @@ int GetGroupsCommand::readFasta(){ if (wroteSomething == false) { m->mothurOut("Your file does NOT contain sequences from the groups you wish to get."); m->mothurOutEndLine(); } outputTypes["fasta"].push_back(outputFileName); outputNames.push_back(outputFileName); + m->mothurOut("Selected " + toString(selectedCount) + " sequences from your fasta file."); m->mothurOutEndLine(); + + return 0; } @@ -316,25 +519,95 @@ int GetGroupsCommand::readFasta(){ exit(1); } } - +//********************************************************************************************************************** +int GetGroupsCommand::readShared(){ + try { + string thisOutputDir = outputDir; + if (outputDir == "") { thisOutputDir += m->hasPath(sharedfile); } + + InputData input(sharedfile, "sharedfile"); + vector lookup = input.getSharedRAbundVectors(); + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(sharedfile)); + variables["[extension]"] = m->getExtension(sharedfile); + + bool wroteSomething = false; + + while(lookup[0] != NULL) { + + variables["[tag]"] = lookup[0]->getLabel(); + string outputFileName = getOutputFileName("shared", variables); + + 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(); + } + + 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("Selected groups: " + groupsString + " from your shared file."); m->mothurOutEndLine(); + + return 0; + + } + catch(exception& e) { + m->errorOut(e, "GetGroupsCommand", "readShared"); + exit(1); + } +} //********************************************************************************************************************** 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); - - ofstream out; - m->openOutputFile(outputFileName, out); + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(listfile)); + variables["[extension]"] = m->getExtension(listfile); ifstream in; m->openInputFile(listfile, in); bool wroteSomething = false; + int selectedCount = 0; while(!in.eof()){ + + selectedCount = 0; + //read in list vector ListVector list(in); + + variables["[tag]"] = list.getLabel(); + string outputFileName = getOutputFileName("list", variables); + + ofstream out; + m->openOutputFile(outputFileName, out); + outputTypes["list"].push_back(outputFileName); outputNames.push_back(outputFileName); + + vector binLabels = list.getLabels(); + vector newBinLabels; //make a new list vector ListVector newList; @@ -342,43 +615,53 @@ int GetGroupsCommand::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); + vector thisBinNames; + m->splitAtComma(binnames, thisBinNames); string newNames = ""; - while (binnames.find_first_of(',') != -1) { - string name = binnames.substr(0,binnames.find_first_of(',')); - binnames = binnames.substr(binnames.find_first_of(',')+1, binnames.length()); - - //if that name is in the .accnos file, add it - if (names.count(name) != 0) { newNames += name + ","; } - } - - //get last name - if (names.count(binnames) != 0) { newNames += binnames + ","; } - + for (int j = 0; j < thisBinNames.size(); j++) { + string name = thisBinNames[j]; + + //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++; + } + } + } + //if there are names in this bin add to new list if (newNames != "") { newNames = newNames.substr(0, newNames.length()-1); //rip off extra comma - newList.push_back(newNames); + newList.push_back(newNames); + newBinLabels.push_back(binLabels[i]); } } //print new listvector if (newList.getNumBins() != 0) { wroteSomething = true; + newList.setLabels(newBinLabels); + newList.printHeaders(out); newList.print(out); } m->gobble(in); + out.close(); } - in.close(); - out.close(); + in.close(); if (wroteSomething == false) { m->mothurOut("Your file does NOT contain sequences from the groups you wish to get."); m->mothurOutEndLine(); } - outputTypes["list"].push_back(outputFileName); outputNames.push_back(outputFileName); + + m->mothurOut("Selected " + toString(selectedCount) + " sequences from your list file."); m->mothurOutEndLine(); return 0; @@ -393,7 +676,10 @@ 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); + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(namefile)); + variables["[extension]"] = m->getExtension(namefile); + string outputFileName = getOutputFileName("name", variables); ofstream out; m->openOutputFile(outputFileName, out); @@ -403,9 +689,10 @@ int GetGroupsCommand::readName(){ string name, firstCol, secondCol; bool wroteSomething = false; + int selectedCount = 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 +707,8 @@ int GetGroupsCommand::readName(){ } } + selectedCount += 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) { @@ -444,6 +733,7 @@ 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]; } } @@ -455,6 +745,8 @@ int GetGroupsCommand::readName(){ if (wroteSomething == false) { m->mothurOut("Your file does NOT contain sequences from the groups you wish to get."); m->mothurOutEndLine(); } outputTypes["name"].push_back(outputFileName); outputNames.push_back(outputFileName); + m->mothurOut("Selected " + toString(selectedCount) + " sequences from your name file."); m->mothurOutEndLine(); + return 0; } catch(exception& e) { @@ -468,7 +760,10 @@ 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); + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(groupfile)); + variables["[extension]"] = m->getExtension(groupfile); + string outputFileName = getOutputFileName("group", variables); ofstream out; m->openOutputFile(outputFileName, out); @@ -478,9 +773,10 @@ int GetGroupsCommand::readGroup(){ string name, group; bool wroteSomething = false; + int selectedCount = 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 @@ -489,6 +785,7 @@ int GetGroupsCommand::readGroup(){ if (names.count(name) != 0) { wroteSomething = true; out << name << '\t' << group << endl; + selectedCount++; } m->gobble(in); @@ -499,6 +796,8 @@ int GetGroupsCommand::readGroup(){ if (wroteSomething == false) { m->mothurOut("Your file does NOT contain sequences from the groups you wish to get."); m->mothurOutEndLine(); } outputTypes["group"].push_back(outputFileName); outputNames.push_back(outputFileName); + m->mothurOut("Selected " + toString(selectedCount) + " sequences from your group file."); m->mothurOutEndLine(); + return 0; } catch(exception& e) { @@ -507,30 +806,115 @@ int GetGroupsCommand::readGroup(){ } } //********************************************************************************************************************** -int GetGroupsCommand::readTax(){ +int GetGroupsCommand::readCount(){ 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(countfile); } + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(countfile)); + variables["[extension]"] = m->getExtension(countfile); + string outputFileName = getOutputFileName("count", variables); + ofstream out; m->openOutputFile(outputFileName, out); ifstream in; - m->openInputFile(taxfile, in); - string name, tax; + m->openInputFile(countfile, in); bool wroteSomething = false; + int selectedCount = 0; + + string headers = m->getline(in); m->gobble(in); + vector columnHeaders = m->splitWhiteSpace(headers); + + vector groups; + map originalGroupIndexes; + map GroupIndexes; + set indexOfGroupsChosen; + for (int i = 2; i < columnHeaders.size(); i++) { groups.push_back(columnHeaders[i]); originalGroupIndexes[i-2] = columnHeaders[i]; } + //sort groups to keep consistent with how we store the groups in groupmap + sort(groups.begin(), groups.end()); + for (int i = 0; i < groups.size(); i++) { GroupIndexes[groups[i]] = i; } + sort(Groups.begin(), Groups.end()); + out << "Representative_Sequence\ttotal\t"; + for (int i = 0; i < Groups.size(); i++) { out << Groups[i] << '\t'; indexOfGroupsChosen.insert(GroupIndexes[Groups[i]]); } + out << endl; + + string name; int oldTotal; + while (!in.eof()) { + + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } + + in >> name; m->gobble(in); in >> oldTotal; m->gobble(in); + if (m->debug) { m->mothurOut("[DEBUG]: " + name + '\t' + toString(oldTotal) + "\n"); } + + if (names.count(name) != 0) { + //if group info, then read it + vector selectedCounts; int thisTotal = 0; int temp; + for (int i = 0; i < groups.size(); i++) { + int thisIndex = GroupIndexes[originalGroupIndexes[i]]; + in >> temp; m->gobble(in); + if (indexOfGroupsChosen.count(thisIndex) != 0) { //we want this group + selectedCounts.push_back(temp); thisTotal += temp; + } + } + + out << name << '\t' << thisTotal << '\t'; + for (int i = 0; i < selectedCounts.size(); i++) { out << selectedCounts[i] << '\t'; } + out << endl; + + wroteSomething = true; + selectedCount+= thisTotal; + }else { m->getline(in); } + + m->gobble(in); + } + 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["count"].push_back(outputFileName); outputNames.push_back(outputFileName); + + m->mothurOut("Selected " + toString(selectedCount) + " sequences from your count file."); m->mothurOutEndLine(); + + return 0; + } + catch(exception& e) { + m->errorOut(e, "GetGroupsCommand", "readCount"); + exit(1); + } +} +//********************************************************************************************************************** +int GetGroupsCommand::readDesign(){ + try { + string thisOutputDir = outputDir; + if (outputDir == "") { thisOutputDir += m->hasPath(designfile); } + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(designfile)); + variables["[extension]"] = m->getExtension(designfile); + string outputFileName = getOutputFileName("design", variables); + + ofstream out; + m->openOutputFile(outputFileName, out); + + ifstream in; + m->openInputFile(designfile, in); + string name, group; + + bool wroteSomething = false; + int selectedCount = 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; + selectedCount++; } m->gobble(in); @@ -538,37 +922,71 @@ 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); } + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(taxfile)); + variables["[extension]"] = m->getExtension(taxfile); + string outputFileName = getOutputFileName("taxonomy", variables); + + 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(); + + 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); } }