X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=getsharedotucommand.cpp;h=5ae8da588ba4a6d36b6658527d8cd12e208c50c4;hb=8159f34321e2c771638059b59a986caca9f3ab60;hp=492195d702286af6cc82d919311aae7a59260596;hpb=260ae19c36cb11a53ddc5a75b5e507f8dd8b31d6;p=mothur.git diff --git a/getsharedotucommand.cpp b/getsharedotucommand.cpp index 492195d..5ae8da5 100644 --- a/getsharedotucommand.cpp +++ b/getsharedotucommand.cpp @@ -8,25 +8,102 @@ */ #include "getsharedotucommand.h" +#include "sharedutilities.h" //********************************************************************************************************************** +vector GetSharedOTUCommand::setParameters(){ + try { + CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "FNGLT", "none","fasta",false,false); parameters.push_back(pfasta); + CommandParameter pgroup("group", "InputTypes", "", "", "none", "FNGLT", "none","sharedseq",false,true,true); parameters.push_back(pgroup); + CommandParameter plist("list", "InputTypes", "", "", "none", "FNGLT", "none","sharedseq",false,true,true); parameters.push_back(plist); + CommandParameter poutput("output", "Multiple", "accnos-default", "default", "", "", "","",false,false); parameters.push_back(poutput); + CommandParameter plabel("label", "String", "", "", "", "", "","",false,false); parameters.push_back(plabel); + CommandParameter punique("unique", "String", "", "", "", "", "","",false,false,true); parameters.push_back(punique); + CommandParameter pshared("shared", "String", "", "", "", "", "","",false,false,true); parameters.push_back(pshared); + 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, "GetSharedOTUCommand", "setParameters"); + exit(1); + } +} +//********************************************************************************************************************** +string GetSharedOTUCommand::getHelpString(){ + try { + string helpString = ""; + helpString += "The get.sharedseqs command parameters are list, group, label, unique, shared, output and fasta. The list and group parameters are required, unless you have valid current files.\n"; + helpString += "The label parameter allows you to select what distance levels you would like output files for, and are separated by dashes.\n"; + helpString += "The unique and shared parameters allow you to select groups you would like to know the shared info for, and are separated by dashes.\n"; + helpString += "If you enter your groups under the unique parameter mothur will return the otus that contain ONLY sequences from those groups.\n"; + helpString += "If you enter your groups under the shared parameter mothur will return the otus that contain sequences from those groups and may also contain sequences from other groups.\n"; + helpString += "If you do not enter any groups then the get.sharedseqs command will return sequences that are unique to all groups in your group file.\n"; + helpString += "The fasta parameter allows you to input a fasta file and outputs a fasta file for each distance level containing only the sequences that are in OTUs shared by the groups specified.\n"; + helpString += "The output parameter allows you to output the list of names without the group and bin number added. \n"; + helpString += "With this option you can use the names file as an input in get.seqs and remove.seqs commands. To do this enter output=accnos. \n"; + helpString += "The get.sharedseqs command outputs a .names file for each distance level containing a list of sequences in the OTUs shared by the groups specified.\n"; + helpString += "The get.sharedseqs command should be in the following format: get.sharedseqs(list=yourListFile, group=yourGroupFile, label=yourLabels, unique=yourGroups, fasta=yourFastafile, output=yourOutput).\n"; + helpString += "Example get.sharedseqs(list=amazon.fn.list, label=unique-0.01, group= amazon.groups, unique=forest-pasture, fasta=amazon.fasta, output=accnos).\n"; + helpString += "The output to the screen is the distance and the number of otus at that distance for the groups you specified.\n"; + helpString += "The default value for label is all labels in your inputfile. The default for groups is all groups in your file.\n"; + helpString += "Note: No spaces between parameter labels (i.e. label), '=' and parameters (i.e.yourLabel).\n"; + return helpString; + } + catch(exception& e) { + m->errorOut(e, "GetSharedOTUCommand", "getHelpString"); + exit(1); + } +} +//********************************************************************************************************************** +string GetSharedOTUCommand::getOutputPattern(string type) { + try { + string pattern = ""; + if (type == "fasta") { pattern = "[filename],[distance],[group],shared.fasta"; } + else if (type == "accnos") { pattern = "[filename],[distance],[group],accnos"; } + else if (type == "sharedseqs") { pattern = "[filename],[distance],[group],shared.seqs"; } + else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; } + + return pattern; + } + catch(exception& e) { + m->errorOut(e, "GetSharedOTUCommand", "getOutputPattern"); + exit(1); + } +} +//********************************************************************************************************************** +GetSharedOTUCommand::GetSharedOTUCommand(){ + try { + abort = true; calledHelp = true; + setParameters(); + vector tempOutNames; + outputTypes["fasta"] = tempOutNames; + outputTypes["accnos"] = tempOutNames; + outputTypes["sharedseqs"] = tempOutNames; + } + catch(exception& e) { + m->errorOut(e, "GetSharedOTUCommand", "GetSharedOTUCommand"); + exit(1); + } +} +//********************************************************************************************************************** GetSharedOTUCommand::GetSharedOTUCommand(string option) { try { - globaldata = GlobalData::getInstance(); - abort = false; + abort = false; calledHelp = false; unique = true; allLines = 1; - labels.clear(); //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[] = {"label","unique","shared","fasta","list","group","output","outputdir","inputdir"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + vector myArray = setParameters(); OptionParser parser(option); map parameters = parser.getParameters(); @@ -39,6 +116,12 @@ GetSharedOTUCommand::GetSharedOTUCommand(string option) { if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; } } + //initialize outputTypes + vector tempOutNames; + outputTypes["fasta"] = tempOutNames; + outputTypes["accnos"] = tempOutNames; + outputTypes["sharedseqs"] = tempOutNames; + //if the user changes the output directory command factory will send this info to us in the output parameter outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){ outputDir = ""; } @@ -76,12 +159,25 @@ GetSharedOTUCommand::GetSharedOTUCommand(string option) { //check for required parameters listfile = validParameter.validFile(parameters, "list", true); if (listfile == "not open") { abort = true; } - else if (listfile == "not found") { listfile = ""; } - else { globaldata->setListFile(listfile); globaldata->setFormat("list"); } + else if (listfile == "not found") { + listfile = m->getListFile(); + if (listfile != "") { format = "list"; m->mothurOut("Using " + listfile + " as input file for the list parameter."); m->mothurOutEndLine(); } + else { + m->mothurOut("No valid current list file. You must provide a list file."); m->mothurOutEndLine(); + abort = true; + } + }else { format = "list"; m->setListFile(listfile); } groupfile = validParameter.validFile(parameters, "group", true); if (groupfile == "not open") { abort = true; } - else if (groupfile == "not found") { groupfile = ""; } + else if (groupfile == "not found") { + groupfile = m->getGroupFile(); + if (groupfile != "") { m->mothurOut("Using " + groupfile + " as input file for the group parameter."); m->mothurOutEndLine(); } + else { + m->mothurOut("No valid current group file. You must provide a group file."); m->mothurOutEndLine(); + abort = true; + } + }else { m->setGroupFile(groupfile); } if ((listfile == "") || (groupfile == "")) { m->mothurOut("The list and group parameters are required."); m->mothurOutEndLine(); abort = true; } @@ -96,13 +192,14 @@ GetSharedOTUCommand::GetSharedOTUCommand(string option) { output = validParameter.validFile(parameters, "output", false); if (output == "not found") { output = ""; } + else if (output == "default") { output = ""; } groups = validParameter.validFile(parameters, "unique", false); if (groups == "not found") { groups = ""; } else { userGroups = "unique." + groups; m->splitAtDash(groups, Groups); - globaldata->Groups = Groups; + m->setGroups(Groups); } @@ -111,14 +208,14 @@ GetSharedOTUCommand::GetSharedOTUCommand(string option) { else { userGroups = groups; m->splitAtDash(groups, Groups); - globaldata->Groups = Groups; + m->setGroups(Groups); unique = false; } fastafile = validParameter.validFile(parameters, "fasta", true); if (fastafile == "not open") { abort = true; } else if (fastafile == "not found") { fastafile = ""; } - + else { m->setFastaFile(fastafile); } } } @@ -129,40 +226,10 @@ GetSharedOTUCommand::GetSharedOTUCommand(string option) { } //********************************************************************************************************************** -void GetSharedOTUCommand::help(){ - try { - m->mothurOut("The get.sharedseqs command parameters are list, group, label, unique, shared, output and fasta. The list and group parameters are required.\n"); - m->mothurOut("The label parameter allows you to select what distance levels you would like output files for, and are separated by dashes.\n"); - m->mothurOut("The unique and shared parameters allow you to select groups you would like to know the shared info for, and are separated by dashes.\n"); - m->mothurOut("If you enter your groups under the unique parameter mothur will return the otus that contain ONLY sequences from those groups.\n"); - m->mothurOut("If you enter your groups under the shared parameter mothur will return the otus that contain sequences from those groups and may also contain sequences from other groups.\n"); - m->mothurOut("If you do not enter any groups then the get.sharedseqs command will return sequences that are unique to all groups in your group file.\n"); - m->mothurOut("The fasta parameter allows you to input a fasta file and outputs a fasta file for each distance level containing only the sequences that are in OTUs shared by the groups specified.\n"); - m->mothurOut("The output parameter allows you to output the list of names without the group and bin number added. \n"); - m->mothurOut("With this option you can use the names file as an input in get.seqs and remove.seqs commands. To do this enter output=accnos. \n"); - m->mothurOut("The get.sharedseqs command outputs a .names file for each distance level containing a list of sequences in the OTUs shared by the groups specified.\n"); - m->mothurOut("The get.sharedseqs command should be in the following format: get.sabund(label=yourLabels, groups=yourGroups, fasta=yourFastafile, output=yourOutput).\n"); - m->mothurOut("Example get.sharedseqs(list=amazon.fn.list, label=unique-0.01, group=forest-pasture, fasta=amazon.fasta, output=accnos).\n"); - m->mothurOut("The output to the screen is the distance and the number of otus at that distance for the groups you specified.\n"); - m->mothurOut("The default value for label is all labels in your inputfile. The default for groups is all groups in your file.\n"); - m->mothurOut("Note: No spaces between parameter labels (i.e. label), '=' and parameters (i.e.yourLabel).\n\n"); - } - catch(exception& e) { - m->errorOut(e, "GetSharedOTUCommand", "help"); - exit(1); - } -} - -//********************************************************************************************************************** - -GetSharedOTUCommand::~GetSharedOTUCommand(){} - -//********************************************************************************************************************** - int GetSharedOTUCommand::execute(){ try { - if (abort == true) { return 0; } + if (abort == true) { if (calledHelp) { return 0; } return 2; } groupMap = new GroupMap(groupfile); int error = groupMap->readMap(); @@ -170,15 +237,19 @@ int GetSharedOTUCommand::execute(){ if (m->control_pressed) { delete groupMap; return 0; } - globaldata->gGroupmap = groupMap; - if (Groups.size() == 0) { - Groups = groupMap->namesOfGroups; + Groups = groupMap->getNamesOfGroups(); //make string for outputfile name userGroups = "unique."; for(int i = 0; i < Groups.size(); i++) { userGroups += Groups[i] + "-"; } userGroups = userGroups.substr(0, userGroups.length()-1); + }else{ + //sanity check for group names + SharedUtil util; + vector namesOfGroups = groupMap->getNamesOfGroups(); + util.setGroups(Groups, namesOfGroups); + groupMap->setNamesOfGroups(namesOfGroups); } //put groups in map to find easier @@ -191,7 +262,7 @@ int GetSharedOTUCommand::execute(){ m->openInputFile(fastafile, inFasta); while(!inFasta.eof()) { - if (m->control_pressed) { inFasta.close(); delete groupMap; return 0; } + if (m->control_pressed) { outputTypes.clear(); inFasta.close(); delete groupMap; return 0; } Sequence seq(inFasta); m->gobble(inFasta); if (seq.getName() != "") { seqs.push_back(seq); } @@ -214,7 +285,7 @@ int GetSharedOTUCommand::execute(){ if (m->control_pressed) { if (lastlist != NULL) { delete lastlist; } - for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } + for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } outputTypes.clear(); delete groupMap; return 0; } @@ -273,11 +344,25 @@ int GetSharedOTUCommand::execute(){ //reset groups parameter - globaldata->Groups.clear(); + m->clearGroups(); if (lastlist != NULL) { delete lastlist; } - if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } delete groupMap; return 0; } + if (m->control_pressed) { outputTypes.clear(); for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } delete groupMap; return 0; } + + //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); } + } + + if (output == "accnos") { + itTypes = outputTypes.find("accnos"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setAccnosFile(current); } + } + } m->mothurOutEndLine(); m->mothurOut("Output File Names: "); m->mothurOutEndLine(); @@ -303,11 +388,13 @@ int GetSharedOTUCommand::process(ListVector* shared) { string outputFileNames; if (outputDir == "") { outputDir += m->hasPath(listfile); } - if (output != "accnos") { - outputFileNames = outputDir + m->getRootName(m->getSimpleName(listfile)) + shared->getLabel() + userGroups + ".shared.seqs"; - }else { - outputFileNames = outputDir + m->getRootName(m->getSimpleName(listfile)) + shared->getLabel() + userGroups + ".accnos"; - } + map variables; + variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(listfile)); + variables["[distance]"] = shared->getLabel(); + variables["[group]"] = userGroups; + if (output != "accnos") { outputFileNames = getOutputFileName("sharedseqs", variables); } + else { outputFileNames = getOutputFileName("accnos", variables); } + m->openOutputFile(outputFileNames, outNames); bool wroteSomething = false; @@ -315,7 +402,7 @@ int GetSharedOTUCommand::process(ListVector* shared) { //go through each bin, find out if shared for (int i = 0; i < shared->getNumBins(); i++) { - if (m->control_pressed) { outNames.close(); remove(outputFileNames.c_str()); return 0; } + if (m->control_pressed) { outNames.close(); m->mothurRemove(outputFileNames); return 0; } bool uniqueOTU = true; @@ -326,10 +413,11 @@ int GetSharedOTUCommand::process(ListVector* shared) { vector namesOfSeqsInThisBin; - string names = shared->get(i); - while ((names.find_first_of(',') != -1)) { - string name = names.substr(0,names.find_first_of(',')); - names = names.substr(names.find_first_of(',')+1, names.length()); + string names = shared->get(i); + vector binNames; + m->splitAtComma(names, binNames); + for(int j = 0; j < binNames.size(); j++) { + string name = binNames[j]; //find group string seqGroup = groupMap->getGroup(name); @@ -345,20 +433,6 @@ int GetSharedOTUCommand::process(ListVector* shared) { else { atLeastOne[seqGroup]++; } } - //get last name - string seqGroup = groupMap->getGroup(names); - if (output != "accnos") { - namesOfSeqsInThisBin.push_back((names + "|" + seqGroup + "|" + toString(i+1))); - }else { namesOfSeqsInThisBin.push_back(names); } - - if (seqGroup == "not found") { m->mothurOut(names + " is not in your groupfile. Please correct."); m->mothurOutEndLine(); exit(1); } - - //is this seq in one of hte groups we care about - it = groupFinder.find(seqGroup); - if (it == groupFinder.end()) { uniqueOTU = false; } //you have a sequence from a group you don't want - else { atLeastOne[seqGroup]++; } - - //make sure you have at least one seq from each group you want bool sharedByAll = true; map::iterator it2; @@ -393,7 +467,7 @@ int GetSharedOTUCommand::process(ListVector* shared) { outNames.close(); if (!wroteSomething) { - remove(outputFileNames.c_str()); + m->mothurRemove(outputFileNames); string outputString = "\t" + toString(num) + " - No otus shared by groups"; string groupString = ""; @@ -406,15 +480,18 @@ int GetSharedOTUCommand::process(ListVector* shared) { }else { m->mothurOut("\t" + toString(num)); m->mothurOutEndLine(); outputNames.push_back(outputFileNames); + if (output != "accnos") { outputTypes["sharedseqs"].push_back(outputFileNames); } + else { outputTypes["accnos"].push_back(outputFileNames); } } //if fasta file provided output new fasta file if ((fastafile != "") && wroteSomething) { if (outputDir == "") { outputDir += m->hasPath(fastafile); } - string outputFileFasta = outputDir + m->getRootName(m->getSimpleName(fastafile)) + shared->getLabel() + userGroups + ".shared.fasta"; + variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(fastafile)); + string outputFileFasta = getOutputFileName("fasta", variables); ofstream outFasta; m->openOutputFile(outputFileFasta, outFasta); - outputNames.push_back(outputFileFasta); + outputNames.push_back(outputFileFasta); outputTypes["fasta"].push_back(outputFileFasta); for (int k = 0; k < seqs.size(); k++) { if (m->control_pressed) { outFasta.close(); return 0; }