X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=splitabundcommand.cpp;h=580493b60a1e4d449a71b8689635e8ced4dea397;hp=891fb979e3aa533a53453628f2701e790161fbcc;hb=615301e57c25e241356a9c2380648d117709458d;hpb=83b5acbe3d6087a6cd73e80dde4b923387a01d01 diff --git a/splitabundcommand.cpp b/splitabundcommand.cpp index 891fb97..580493b 100644 --- a/splitabundcommand.cpp +++ b/splitabundcommand.cpp @@ -8,20 +8,106 @@ */ #include "splitabundcommand.h" +#include "sharedutilities.h" +//********************************************************************************************************************** +vector SplitAbundCommand::setParameters(){ + try { + CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "none","fasta",false,true,true); parameters.push_back(pfasta); + CommandParameter pname("name", "InputTypes", "", "", "NameCount", "FNGLT", "none","name",false,false,true); parameters.push_back(pname); + CommandParameter pcount("count", "InputTypes", "", "", "NameCount-CountGroup", "none", "none","count",false,false); parameters.push_back(pcount); + CommandParameter pgroup("group", "InputTypes", "", "", "CountGroup", "none", "none","group",false,false); parameters.push_back(pgroup); + CommandParameter plist("list", "InputTypes", "", "", "none", "FNGLT", "none","list",false,false,true); parameters.push_back(plist); + CommandParameter plabel("label", "String", "", "", "", "", "","",false,false); parameters.push_back(plabel); + CommandParameter pcutoff("cutoff", "Number", "", "0", "", "", "","",false,true); parameters.push_back(pcutoff); + CommandParameter pgroups("groups", "String", "", "", "", "", "","",false,false); parameters.push_back(pgroups); + CommandParameter paccnos("accnos", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(paccnos); + 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, "SplitAbundCommand", "setParameters"); + exit(1); + } +} +//********************************************************************************************************************** +string SplitAbundCommand::getHelpString(){ + try { + string helpString = ""; + helpString += "The split.abund command reads a fasta file and a list or a names file splits the sequences into rare and abundant groups. \n"; + helpString += "The split.abund command parameters are fasta, list, name, count, cutoff, group, label, groups, cutoff and accnos.\n"; + helpString += "The fasta and a list or name or count parameter are required, and you must provide a cutoff value.\n"; + helpString += "The cutoff parameter is used to qualify what is abundant and rare.\n"; + helpString += "The group parameter allows you to parse a group file into rare and abundant groups.\n"; + helpString += "The label parameter is used to read specific labels in your listfile you want to use.\n"; + helpString += "The accnos parameter allows you to output a .rare.accnos and .abund.accnos files to use with the get.seqs and remove.seqs commands.\n"; + helpString += "The groups parameter allows you to parse the files into rare and abundant files by group. \n"; + helpString += "For example if you set groups=A-B-C, you will get a .A.abund, .A.rare, .B.abund, .B.rare, .C.abund, .C.rare files. \n"; + helpString += "If you want .abund and .rare files for all groups, set groups=all. \n"; + helpString += "The split.abund command should be used in the following format: split.abund(fasta=yourFasta, list=yourListFile, group=yourGroupFile, label=yourLabels, cutoff=yourCutoff).\n"; + helpString += "Example: split.abund(fasta=abrecovery.fasta, list=abrecovery.fn.list, group=abrecovery.groups, label=0.03, cutoff=2).\n"; + helpString += "Note: No spaces between parameter labels (i.e. list), '=' and parameters (i.e.yourListfile).\n"; + return helpString; + } + catch(exception& e) { + m->errorOut(e, "SplitAbundCommand", "getHelpString"); + exit(1); + } +} + +//********************************************************************************************************************** +string SplitAbundCommand::getOutputPattern(string type) { + try { + string pattern = ""; + + if (type == "fasta") { pattern = "[filename],[tag],[tag2],fasta-[filename],[tag],[group],[tag2],fasta"; } + else if (type == "list") { pattern = "[filename],[tag],[tag2],list-[filename],[group],[tag],[tag2],list"; } + else if (type == "name") { pattern = "[filename],[tag],names-[filename],[group],[tag],names"; } + else if (type == "count") { pattern = "[filename],[tag],[tag2],count_table-[filename],[tag],count_table"; } + else if (type == "group") { pattern = "[filename],[tag],[tag2],groups-[filename],[tag],[group],[tag2],groups"; } + else if (type == "accnos") { pattern = "[filename],[tag],[tag2],accnos-[filename],[tag],[group],[tag2],accnos"; } + else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; } + + return pattern; + } + catch(exception& e) { + m->errorOut(e, "SplitAbundCommand", "getOutputPattern"); + exit(1); + } +} +//********************************************************************************************************************** +SplitAbundCommand::SplitAbundCommand(){ + try { + abort = true; calledHelp = true; + setParameters(); + vector tempOutNames; + outputTypes["list"] = tempOutNames; + outputTypes["name"] = tempOutNames; + outputTypes["count"] = tempOutNames; + outputTypes["accnos"] = tempOutNames; + outputTypes["group"] = tempOutNames; + outputTypes["fasta"] = tempOutNames; + } + catch(exception& e) { + m->errorOut(e, "SplitAbundCommand", "SplitAbundCommand"); + exit(1); + } +} //********************************************************************************************************************** SplitAbundCommand::SplitAbundCommand(string option) { try { - abort = false; + abort = false; calledHelp = false; allLines = 1; //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[] = {"name","group","list","label","accnos","groups","fasta","cutoff","outputdir","inputdir"}; // - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + vector myArray = setParameters(); OptionParser parser(option); map parameters = parser.getParameters(); @@ -33,7 +119,16 @@ SplitAbundCommand::SplitAbundCommand(string option) { for (it = parameters.begin(); it != parameters.end(); it++) { if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; } } - + + //initialize outputTypes + vector tempOutNames; + outputTypes["list"] = tempOutNames; + outputTypes["name"] = tempOutNames; + outputTypes["accnos"] = tempOutNames; + outputTypes["group"] = tempOutNames; + outputTypes["fasta"] = tempOutNames; + outputTypes["count"] = tempOutNames; + //if the user changes the input directory command factory will send this info to us in the output parameter string inputDir = validParameter.validFile(parameters, "inputdir", false); if (inputDir == "not found"){ inputDir = ""; } @@ -42,7 +137,7 @@ SplitAbundCommand::SplitAbundCommand(string option) { it = parameters.find("list"); //user has given a template file if(it != parameters.end()){ - path = hasPath(it->second); + path = m->hasPath(it->second); //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["list"] = inputDir + it->second; } } @@ -50,7 +145,7 @@ SplitAbundCommand::SplitAbundCommand(string option) { it = parameters.find("group"); //user has given a template file if(it != parameters.end()){ - path = hasPath(it->second); + path = m->hasPath(it->second); //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["group"] = inputDir + it->second; } } @@ -58,7 +153,7 @@ SplitAbundCommand::SplitAbundCommand(string option) { it = parameters.find("fasta"); //user has given a template file if(it != parameters.end()){ - path = hasPath(it->second); + path = m->hasPath(it->second); //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["fasta"] = inputDir + it->second; } } @@ -66,11 +161,18 @@ SplitAbundCommand::SplitAbundCommand(string option) { it = parameters.find("name"); //user has given a template file if(it != parameters.end()){ - path = hasPath(it->second); + path = m->hasPath(it->second); //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["name"] = 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; } + } } @@ -81,59 +183,87 @@ SplitAbundCommand::SplitAbundCommand(string option) { listfile = validParameter.validFile(parameters, "list", true); if (listfile == "not open") { abort = true; } else if (listfile == "not found") { listfile = ""; } - else{ inputFile = listfile; } + else{ inputFile = listfile; m->setListFile(listfile); } namefile = validParameter.validFile(parameters, "name", true); if (namefile == "not open") { abort = true; } else if (namefile == "not found") { namefile = ""; } - else{ inputFile = namefile; } + else{ inputFile = namefile; m->setNameFile(namefile); } fastafile = validParameter.validFile(parameters, "fasta", true); if (fastafile == "not open") { abort = true; } - else if (fastafile == "not found") { fastafile = ""; m->mothurOut("fasta is a required parameter for the split.abund command. "); m->mothurOutEndLine(); abort = true; } + else if (fastafile == "not found") { + fastafile = m->getFastaFile(); + if (fastafile != "") { m->mothurOut("Using " + fastafile + " as input file for the fasta parameter."); m->mothurOutEndLine(); } + else { m->mothurOut("You have no current fastafile and the fasta parameter is required."); m->mothurOutEndLine(); abort = true; } + }else { m->setFastaFile(fastafile); } groupfile = validParameter.validFile(parameters, "group", true); if (groupfile == "not open") { groupfile = ""; abort = true; } else if (groupfile == "not found") { groupfile = ""; } else { - groupMap = new GroupMap(groupfile); - - int error = groupMap->readMap(); + int error = groupMap.readMap(groupfile); if (error == 1) { abort = true; } - + m->setGroupFile(groupfile); } + countfile = validParameter.validFile(parameters, "count", true); + if (countfile == "not open") { countfile = ""; abort = true; } + else if (countfile == "not found") { countfile = ""; } + else { + m->setCountTableFile(countfile); + ct.readTable(countfile, true); + } + + 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; + } + groups = validParameter.validFile(parameters, "groups", false); if (groups == "not found") { groups = ""; } - else if (groups == "all") { - if (groupfile != "") { Groups = groupMap->namesOfGroups; } - else { m->mothurOut("You cannot select groups without a valid groupfile, I will disregard your groups selection. "); m->mothurOutEndLine(); groups = ""; } - }else { - splitAtDash(groups, Groups); - } + else { m->splitAtDash(groups, Groups); } - if ((groupfile == "") && (groups != "")) { m->mothurOut("You cannot select groups without a valid groupfile, I will disregard your groups selection. "); m->mothurOutEndLine(); groups = ""; Groups.clear(); } + if (((groupfile == "") && (countfile == ""))&& (groups != "")) { m->mothurOut("You cannot select groups without a valid group or count file, I will disregard your groups selection. "); m->mothurOutEndLine(); groups = ""; Groups.clear(); } + if (countfile != "") { + if (!ct.hasGroupInfo()) { m->mothurOut("You cannot pick groups without group info in your count file; I will disregard your groups selection."); m->mothurOutEndLine(); groups = ""; Groups.clear(); } + } + //do you have all files needed - if ((listfile == "") && (namefile == "")) { m->mothurOut("You must either a listfile or a namefile for the split.abund command. "); m->mothurOutEndLine(); abort = true; } - + if ((listfile == "") && (namefile == "") && (countfile == "")) { + namefile = m->getNameFile(); + if (namefile != "") { m->mothurOut("Using " + namefile + " as input file for the name parameter."); m->mothurOutEndLine(); } + else { + listfile = m->getListFile(); + if (listfile != "") { m->mothurOut("Using " + listfile + " as input file for the list 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 list, count or namefile and one is required."); m->mothurOutEndLine(); abort = true; } + } + } + } + //check for optional parameter and set defaults // ...at some point should added some additional type checking... label = validParameter.validFile(parameters, "label", false); if (label == "not found") { label = ""; allLines = 1; } else { - if(label != "all") { splitAtDash(label, labels); allLines = 0; } + if(label != "all") { m->splitAtDash(label, labels); allLines = 0; } else { allLines = 1; } } string temp = validParameter.validFile(parameters, "accnos", false); if (temp == "not found") { temp = "F"; } - accnos = isTrue(temp); + accnos = m->isTrue(temp); temp = validParameter.validFile(parameters, "cutoff", false); if (temp == "not found") { temp = "0"; } - convert(temp, cutoff); + m->mothurConvert(temp, cutoff); if (cutoff == 0) { m->mothurOut("You must provide a cutoff to qualify what is abundant for the split.abund command. "); m->mothurOutEndLine(); abort = true; } - } } @@ -143,76 +273,41 @@ SplitAbundCommand::SplitAbundCommand(string option) { } } //********************************************************************************************************************** -void SplitAbundCommand::help(){ - try { - m->mothurOut("The split.abund command reads a fasta file and a list or a names file splits the sequences into rare and abundant groups. \n"); - m->mothurOut("The split.abund command parameters are fasta, list, name, cutoff, group, label, groups, cutoff and accnos.\n"); - m->mothurOut("The fasta and a list or name parameter are required, and you must provide a cutoff value.\n"); - m->mothurOut("The cutoff parameter is used to qualify what is abundant and rare.\n"); - m->mothurOut("The group parameter allows you to parse a group file into rare and abundant groups.\n"); - m->mothurOut("The label parameter is used to read specific labels in your listfile you want to use.\n"); - m->mothurOut("The accnos parameter allows you to output a .rare.accnos and .abund.accnos files to use with the get.seqs and remove.seqs commands.\n"); - m->mothurOut("The groups parameter allows you to parse the files into rare and abundant files by group. \n"); - m->mothurOut("For example if you set groups=A-B-C, you will get a .A.abund, .A.rare, .B.abund, .B.rare, .C.abund, .C.rare files. \n"); - m->mothurOut("If you want .abund and .rare files for all groups, set groups=all. \n"); - m->mothurOut("The split.abund command should be used in the following format: split.abund(fasta=yourFasta, list=yourListFile, group=yourGroupFile, label=yourLabels, cutoff=yourCutoff).\n"); - m->mothurOut("Example: split.abund(fasta=abrecovery.fasta, list=abrecovery.fn.list, group=abrecovery.groups, label=0.03, cutoff=2).\n"); - m->mothurOut("Note: No spaces between parameter labels (i.e. list), '=' and parameters (i.e.yourListfile).\n\n"); - - } - catch(exception& e) { - m->errorOut(e, "SplitAbundCommand", "help"); - exit(1); - } -} -//********************************************************************************************************************** -SplitAbundCommand::~SplitAbundCommand(){ - if (groupfile != "") { delete groupMap; } -} +SplitAbundCommand::~SplitAbundCommand(){} //********************************************************************************************************************** int SplitAbundCommand::execute(){ try { - if (abort == true) { return 0; } + if (abort == true) { if (calledHelp) { return 0; } return 2; } + + if (Groups.size() != 0) { + vector allGroups; + if (countfile != "") { allGroups = ct.getNamesOfGroups(); } + else { allGroups = groupMap.getNamesOfGroups(); } + SharedUtil util; + util.setGroups(Groups, allGroups); + } if (listfile != "") { //you are using a listfile to determine abundance - if (outputDir == "") { outputDir = hasPath(listfile); } - - //remove old files so you can append later.... - string fileroot = outputDir + getRootName(getSimpleName(listfile)); - if (Groups.size() == 0) { - remove((fileroot + "rare.list").c_str()); - remove((fileroot + "abund.list").c_str()); - - wroteListFile["rare"] = false; - wroteListFile["abund"] = false; - }else{ - for (int i=0; ihasPath(listfile); } //if the users enters label "0.06" and there is no "0.06" in their file use the next lowest label. set processedLabels; set userLabels = labels; - input = new InputData(listfile, "list"); - list = input->getListVector(); + InputData input(listfile, "list"); + ListVector* list = input.getListVector(); string lastLabel = list->getLabel(); //do you have a namefile or do we need to similate one? if (namefile != "") { readNamesFile(); } else { createNameMap(list); } - if (m->control_pressed) { delete input; delete list; for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } + if (m->control_pressed) { delete list; for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } while((list != NULL) && ((allLines == 1) || (userLabels.size() != 0))) { - if (m->control_pressed) { delete input; delete list; for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } + if (m->control_pressed) { delete list; for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } if(allLines == 1 || labels.count(list->getLabel()) == 1){ @@ -223,11 +318,11 @@ int SplitAbundCommand::execute(){ userLabels.erase(list->getLabel()); } - if ((anyLabelsToProcess(list->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) { + if ((m->anyLabelsToProcess(list->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) { string saveLabel = list->getLabel(); delete list; - list = input->getListVector(lastLabel); //get new list vector to process + list = input.getListVector(lastLabel); //get new list vector to process m->mothurOut(list->getLabel()); m->mothurOutEndLine(); splitList(list); @@ -243,10 +338,10 @@ int SplitAbundCommand::execute(){ lastLabel = list->getLabel(); delete list; - list = input->getListVector(); //get new list vector to process + list = input.getListVector(); //get new list vector to process } - if (m->control_pressed) { delete input; 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; } //output error messages about any remaining user labels set::iterator it; @@ -262,12 +357,12 @@ int SplitAbundCommand::execute(){ } - if (m->control_pressed) { delete input; 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; } //run last label if you need to if (needToRun == true) { if (list != NULL) { delete list; } - list = input->getListVector(lastLabel); //get new list vector to process + list = input.getListVector(lastLabel); //get new list vector to process m->mothurOut(list->getLabel()); m->mothurOutEndLine(); splitList(list); @@ -275,25 +370,10 @@ int SplitAbundCommand::execute(){ delete list; } - delete input; - - for (map::iterator itBool = wroteListFile.begin(); itBool != wroteListFile.end(); itBool++) { - string filename = fileroot + itBool->first; - if ((itBool->first == "rare") || (itBool->first == "abund")) { - filename = fileroot + itBool->first + ".list"; - } - if (itBool->second) { //we wrote to this file - outputNames.push_back(filename); - }else{ - remove(filename.c_str()); - } - } - - 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; } - }else { //you are using the namefile to determine abundance - if (outputDir == "") { outputDir = hasPath(namefile); } + }else if (namefile != "") { //you are using the namefile to determine abundance + if (outputDir == "") { outputDir = m->hasPath(namefile); } splitNames(); writeNames(); @@ -302,8 +382,47 @@ int SplitAbundCommand::execute(){ if (groupfile != "") { parseGroup(tag); } if (accnos) { writeAccnos(tag); } if (fastafile != "") { parseFasta(tag); } + }else { + //split by countfile + string tag = ""; + splitCount(); + + if (accnos) { writeAccnos(tag); } + if (fastafile != "") { parseFasta(tag); } + } + + //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("accnos"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setAccnosFile(current); } + } + + itTypes = outputTypes.find("count"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setCountTableFile(current); } + } + m->mothurOutEndLine(); m->mothurOut("Output File Names: "); m->mothurOutEndLine(); for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); } @@ -323,29 +442,40 @@ int SplitAbundCommand::splitList(ListVector* thisList) { abundNames.clear(); //get rareNames and abundNames + int numRareBins = 0; for (int i = 0; i < thisList->getNumBins(); i++) { if (m->control_pressed) { return 0; } string bin = thisList->get(i); vector names; - splitAtComma(bin, names); //parses bin into individual sequence names + m->splitAtComma(bin, names); //parses bin into individual sequence names int size = names.size(); - + + //if countfile is not blank we assume the list file is unique, otherwise we assume it includes all seqs + if (countfile != "") { + size = 0; + for (int j = 0; j < names.size(); j++) { size += ct.getNumSeqs(names[j]); } + } + if (size <= cutoff) { + numRareBins++; for (int j = 0; j < names.size(); j++) { rareNames.insert(names[j]); } }else{ for (int j = 0; j < names.size(); j++) { abundNames.insert(names[j]); } } }//end for - writeList(thisList); - string tag = thisList->getLabel() + "."; + string tag = thisList->getLabel(); + + writeList(thisList, tag, numRareBins); + if (groupfile != "") { parseGroup(tag); } if (accnos) { writeAccnos(tag); } if (fastafile != "") { parseFasta(tag); } - + if (countfile != "") { parseCount(tag); } + return 0; } @@ -355,61 +485,61 @@ int SplitAbundCommand::splitList(ListVector* thisList) { } } /**********************************************************************************************************************/ -int SplitAbundCommand::writeList(ListVector* thisList) { +int SplitAbundCommand::writeList(ListVector* thisList, string tag, int numRareBins) { try { map filehandles; if (Groups.size() == 0) { - SAbundVector* sabund = new SAbundVector(); - *sabund = thisList->getSAbundVector(); - - //find out how many bins are rare and how many are abundant so you can process the list vector one bin at a time - // and don't have to store the bins until you are done with the whole vector, this save alot of space. - int numRareBins = 0; - for (int i = 0; i <= sabund->getMaxRank(); i++) { - if (i > cutoff) { break; } - numRareBins += sabund->get(i); - } int numAbundBins = thisList->getNumBins() - numRareBins; - delete sabund; ofstream aout; ofstream rout; - if (rareNames.size() != 0) { - string rare = outputDir + getRootName(getSimpleName(listfile)) + "rare.list"; - wroteListFile["rare"] = true; - openOutputFileAppend(rare, rout); - rout << thisList->getLabel() << '\t' << numRareBins << '\t'; - } - - if (abundNames.size() != 0) { - string abund = outputDir + getRootName(getSimpleName(listfile)) + "abund.list"; - wroteListFile["abund"] = true; - openOutputFileAppend(abund, aout); - aout << thisList->getLabel() << '\t' << numAbundBins << '\t'; - } + map variables; + variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(listfile)); + variables["[tag]"] = tag; + variables["[tag2]"] = "rare"; + string rare = getOutputFileName("list",variables); + m->openOutputFile(rare, rout); + outputNames.push_back(rare); outputTypes["list"].push_back(rare); + + variables["[tag2]"] = "abund"; + string abund = getOutputFileName("list",variables); + m->openOutputFile(abund, aout); + outputNames.push_back(abund); outputTypes["list"].push_back(abund); + + if (rareNames.size() != 0) { rout << thisList->getLabel() << '\t' << numRareBins << '\t'; } + if (abundNames.size() != 0) { aout << thisList->getLabel() << '\t' << numAbundBins << '\t'; } for (int i = 0; i < thisList->getNumBins(); i++) { if (m->control_pressed) { break; } - string bin = list->get(i); - - int size = getNumNames(bin); + string bin = thisList->get(i); + vector names; + m->splitAtComma(bin, names); + + int size = names.size(); + if (countfile != "") { + size = 0; + for (int j = 0; j < names.size(); j++) { size += ct.getNumSeqs(names[j]); } + } if (size <= cutoff) { rout << bin << '\t'; } else { aout << bin << '\t'; } } - if (rareNames.size() != 0) { rout << endl; rout.close(); } - if (abundNames.size() != 0) { aout << endl; aout.close(); } - + if (rareNames.size() != 0) { rout << endl; } + if (abundNames.size() != 0) { aout << endl; } + + rout.close(); + aout.close(); + }else{ //parse names by abundance and group - string fileroot = outputDir + getRootName(getSimpleName(listfile)); + string fileroot = outputDir + m->getRootName(m->getSimpleName(listfile)); ofstream* temp; ofstream* temp2; - map wroteFile; + //map wroteFile; map filehandles; map::iterator it3; @@ -419,8 +549,18 @@ int SplitAbundCommand::writeList(ListVector* thisList) { temp2 = new ofstream; filehandles[Groups[i]+".abund"] = temp2; - openOutputFileAppend(fileroot + Groups[i] + ".rare.list", *(filehandles[Groups[i]+".rare"])); - openOutputFileAppend(fileroot + Groups[i] + ".abund.list", *(filehandles[Groups[i]+".abund"])); + map variables; + variables["[filename]"] = fileroot; + variables["[tag]"] = tag; + variables["[tag2]"] = "rare"; + variables["[group]"] = Groups[i]; + string rareGroupFileName = getOutputFileName("list",variables); + variables["[tag2]"] = "abund"; + string abundGroupFileName = getOutputFileName("list",variables); + m->openOutputFile(rareGroupFileName, *(filehandles[Groups[i]+".rare"])); + m->openOutputFile(abundGroupFileName, *(filehandles[Groups[i]+".abund"])); + outputNames.push_back(rareGroupFileName); outputTypes["list"].push_back(rareGroupFileName); + outputNames.push_back(abundGroupFileName); outputTypes["list"].push_back(abundGroupFileName); } map groupVector; @@ -436,10 +576,10 @@ int SplitAbundCommand::writeList(ListVector* thisList) { if (m->control_pressed) { break; } map groupBins; - string bin = list->get(i); + string bin = thisList->get(i); vector names; - splitAtComma(bin, names); //parses bin into individual sequence names + m->splitAtComma(bin, names); //parses bin into individual sequence names //parse bin into list of sequences in each group for (int j = 0; j < names.size(); j++) { @@ -450,19 +590,34 @@ int SplitAbundCommand::writeList(ListVector* thisList) { rareAbund = ".abund"; } - string group = groupMap->getGroup(names[j]); - - if (inUsersGroups(group, Groups)) { //only add if this is in a group we want - itGroup = groupBins.find(group+rareAbund); - if(itGroup == groupBins.end()) { - groupBins[group+rareAbund] = names[j]; //add first name - groupNumBins[group+rareAbund]++; - }else{ //add another name - groupBins[group+rareAbund] += "," + names[j]; - } - }else if(group == "not found") { - m->mothurOut(names[j] + " is not in your groupfile. Ignoring."); m->mothurOutEndLine(); - } + if (countfile == "") { + string group = groupMap.getGroup(names[j]); + + if (m->inUsersGroups(group, Groups)) { //only add if this is in a group we want + itGroup = groupBins.find(group+rareAbund); + if(itGroup == groupBins.end()) { + groupBins[group+rareAbund] = names[j]; //add first name + groupNumBins[group+rareAbund]++; + }else{ //add another name + groupBins[group+rareAbund] += "," + names[j]; + } + }else if(group == "not found") { + m->mothurOut(names[j] + " is not in your groupfile. Ignoring."); m->mothurOutEndLine(); + } + }else { + vector thisSeqsGroups = ct.getGroups(names[j]); + for (int k = 0; k < thisSeqsGroups.size(); k++) { + if (m->inUsersGroups(thisSeqsGroups[k], Groups)) { //only add if this is in a group we want + itGroup = groupBins.find(thisSeqsGroups[k]+rareAbund); + if(itGroup == groupBins.end()) { + groupBins[thisSeqsGroups[k]+rareAbund] = names[j]; //add first name + groupNumBins[thisSeqsGroups[k]+rareAbund]++; + }else{ //add another name + groupBins[thisSeqsGroups[k]+rareAbund] += "," + names[j]; + } + } + } + } } @@ -474,7 +629,6 @@ int SplitAbundCommand::writeList(ListVector* thisList) { //end list vector for (it3 = filehandles.begin(); it3 != filehandles.end(); it3++) { (*(filehandles[it3->first])) << thisList->getLabel() << '\t' << groupNumBins[it3->first] << '\t' << groupVector[it3->first] << endl; // label numBins listvector for that group - wroteListFile[it3->first] = true; (*(filehandles[it3->first])).close(); delete it3->second; } @@ -489,6 +643,37 @@ int SplitAbundCommand::writeList(ListVector* thisList) { } } /**********************************************************************************************************************/ +int SplitAbundCommand::splitCount() { //countfile + try { + rareNames.clear(); + abundNames.clear(); + + vector allNames = ct.getNamesOfSeqs(); + for (int i = 0; i < allNames.size(); i++) { + + if (m->control_pressed) { return 0; } + + int size = ct.getNumSeqs(allNames[i]); + nameMap[allNames[i]] = allNames[i]; + + if (size <= cutoff) { + rareNames.insert(allNames[i]); + }else{ + abundNames.insert(allNames[i]); + } + } + + //write out split count files + parseCount(""); + + return 0; + } + catch(exception& e) { + m->errorOut(e, "SplitAbundCommand", "splitCount"); + exit(1); + } +} +/**********************************************************************************************************************/ int SplitAbundCommand::splitNames() { //namefile try { @@ -497,17 +682,17 @@ int SplitAbundCommand::splitNames() { //namefile //open input file ifstream in; - openInputFile(namefile, in); + m->openInputFile(namefile, in); while (!in.eof()) { if (m->control_pressed) { break; } string firstCol, secondCol; - in >> firstCol >> secondCol; gobble(in); + in >> firstCol >> secondCol; m->gobble(in); nameMap[firstCol] = secondCol; - int size = getNumNames(secondCol); + int size = m->getNumNames(secondCol); if (size <= cutoff) { rareNames.insert(firstCol); @@ -530,13 +715,13 @@ int SplitAbundCommand::readNamesFile() { try { //open input file ifstream in; - openInputFile(namefile, in); + m->openInputFile(namefile, in); while (!in.eof()) { if (m->control_pressed) { break; } string firstCol, secondCol; - in >> firstCol >> secondCol; gobble(in); + in >> firstCol >> secondCol; m->gobble(in); nameMap[firstCol] = secondCol; } @@ -561,7 +746,7 @@ int SplitAbundCommand::createNameMap(ListVector* thisList) { string bin = thisList->get(i); vector names; - splitAtComma(bin, names); //parses bin into individual sequence names + m->splitAtComma(bin, names); //parses bin into individual sequence names for (int j = 0; j < names.size(); j++) { nameMap[names[j]] = names[j]; } }//end for @@ -575,6 +760,122 @@ int SplitAbundCommand::createNameMap(ListVector* thisList) { } } /**********************************************************************************************************************/ +int SplitAbundCommand::parseCount(string tag) { //namefile + try { + + map filehandles; + + if (Groups.size() == 0) { + map variables; + variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(countfile)); + variables["[tag]"] = tag; + variables["[tag2]"] = "rare"; + string rare = getOutputFileName("count",variables); + outputNames.push_back(rare); outputTypes["count"].push_back(rare); + variables["[tag2]"] = "abund"; + string abund = getOutputFileName("count",variables); + outputNames.push_back(abund); outputTypes["count"].push_back(abund); + + CountTable rareTable; + CountTable abundTable; + if (ct.hasGroupInfo()) { + vector ctGroups = ct.getNamesOfGroups(); + for (int i = 0; i < ctGroups.size(); i++) { rareTable.addGroup(ctGroups[i]); abundTable.addGroup(ctGroups[i]); } + } + + if (rareNames.size() != 0) { + for (set::iterator itRare = rareNames.begin(); itRare != rareNames.end(); itRare++) { + if (ct.hasGroupInfo()) { + vector groupCounts = ct.getGroupCounts(*itRare); + rareTable.push_back(*itRare, groupCounts); + }else { + int groupCounts = ct.getNumSeqs(*itRare); + rareTable.push_back(*itRare, groupCounts); + } + } + if (rareTable.hasGroupInfo()) { + vector ctGroups = rareTable.getNamesOfGroups(); + for (int i = 0; i < ctGroups.size(); i++) { + if (rareTable.getGroupCount(ctGroups[i]) == 0) { rareTable.removeGroup(ctGroups[i]); } + } + } + rareTable.printTable(rare); + } + + + if (abundNames.size() != 0) { + for (set::iterator itAbund = abundNames.begin(); itAbund != abundNames.end(); itAbund++) { + if (ct.hasGroupInfo()) { + vector groupCounts = ct.getGroupCounts(*itAbund); + abundTable.push_back(*itAbund, groupCounts); + }else { + int groupCounts = ct.getNumSeqs(*itAbund); + abundTable.push_back(*itAbund, groupCounts); + } + } + if (abundTable.hasGroupInfo()) { + vector ctGroups = abundTable.getNamesOfGroups(); + for (int i = 0; i < ctGroups.size(); i++) { + if (abundTable.getGroupCount(ctGroups[i]) == 0) { abundTable.removeGroup(ctGroups[i]); } + } + } + abundTable.printTable(abund); + } + + }else{ //parse names by abundance and group + map countTableMap; + map::iterator it3; + + for (int i=0; iaddGroup(Groups[i]); + countTableMap[Groups[i]+".rare"] = rareCt; + CountTable* abundCt = new CountTable(); + abundCt->addGroup(Groups[i]); + countTableMap[Groups[i]+".abund"] = abundCt; + } + + vector allNames = ct.getNamesOfSeqs(); + for (int i = 0; i < allNames.size(); i++) { + string rareAbund; + if (rareNames.count(allNames[i]) != 0) { //you are a rare name + rareAbund = ".rare"; + }else{ //you are a abund name + rareAbund = ".abund"; + } + + vector thisSeqsGroups = ct.getGroups(allNames[i]); + for (int j = 0; j < thisSeqsGroups.size(); j++) { + if (m->inUsersGroups(thisSeqsGroups[j], Groups)) { //only add if this is in a group we want + int num = ct.getGroupCount(allNames[i], thisSeqsGroups[j]); + vector nums; nums.push_back(num); + countTableMap[thisSeqsGroups[j]+rareAbund]->push_back(allNames[i], nums); + } + } + } + + + for (it3 = countTableMap.begin(); it3 != countTableMap.end(); it3++) { + string fileroot = outputDir + m->getRootName(m->getSimpleName(countfile)); + map variables; + variables["[filename]"] = fileroot; + variables["[tag]"] = it3->first; + string filename = getOutputFileName("count",variables); + outputNames.push_back(filename); outputTypes["count"].push_back(filename); + (it3->second)->printTable(filename); + delete it3->second; + } + } + + return 0; + + } + catch(exception& e) { + m->errorOut(e, "SplitAbundCommand", "parseCount"); + exit(1); + } +} +/**********************************************************************************************************************/ int SplitAbundCommand::writeNames() { //namefile try { @@ -584,33 +885,36 @@ int SplitAbundCommand::writeNames() { //namefile ofstream aout; ofstream rout; + map variables; + variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(namefile)); + variables["[tag]"] = "rare"; + string rare = getOutputFileName("name", variables); + m->openOutputFile(rare, rout); + outputNames.push_back(rare); outputTypes["name"].push_back(rare); + + variables["[tag]"] = "abund"; + string abund = getOutputFileName("name", variables); + m->openOutputFile(abund, aout); + outputNames.push_back(abund); outputTypes["name"].push_back(abund); + if (rareNames.size() != 0) { - string rare = outputDir + getRootName(getSimpleName(namefile)) + "rare.names"; - openOutputFile(rare, rout); - outputNames.push_back(rare); - for (set::iterator itRare = rareNames.begin(); itRare != rareNames.end(); itRare++) { rout << (*itRare) << '\t' << nameMap[(*itRare)] << endl; } - rout.close(); } + rout.close(); if (abundNames.size() != 0) { - string abund = outputDir + getRootName(getSimpleName(namefile)) + "abund.names"; - openOutputFile(abund, aout); - outputNames.push_back(abund); - for (set::iterator itAbund = abundNames.begin(); itAbund != abundNames.end(); itAbund++) { aout << (*itAbund) << '\t' << nameMap[(*itAbund)] << endl; } - aout.close(); } - + aout.close(); + }else{ //parse names by abundance and group - string fileroot = outputDir + getRootName(getSimpleName(namefile)); + string fileroot = outputDir + m->getRootName(m->getSimpleName(namefile)); ofstream* temp; ofstream* temp2; - map wroteFile; map filehandles; map::iterator it3; @@ -620,16 +924,20 @@ int SplitAbundCommand::writeNames() { //namefile temp2 = new ofstream; filehandles[Groups[i]+".abund"] = temp2; - openOutputFile(fileroot + Groups[i] + ".rare.names", *(filehandles[Groups[i]+".rare"])); - openOutputFile(fileroot + Groups[i] + ".abund.names", *(filehandles[Groups[i]+".abund"])); - - wroteFile[Groups[i] + ".rare"] = false; - wroteFile[Groups[i] + ".abund"] = false; + map variables; + variables["[filename]"] = fileroot; + variables["[tag]"] = "rare"; + variables["[group]"] = Groups[i]; + string rareGroupFileName = getOutputFileName("name",variables); + variables["[tag]"] = "abund"; + string abundGroupFileName = getOutputFileName("name",variables); + m->openOutputFile(rareGroupFileName, *(filehandles[Groups[i]+".rare"])); + m->openOutputFile(abundGroupFileName, *(filehandles[Groups[i]+".abund"])); } for (map::iterator itName = nameMap.begin(); itName != nameMap.end(); itName++) { vector names; - splitAtComma(itName->second, names); //parses bin into individual sequence names + m->splitAtComma(itName->second, names); //parses bin into individual sequence names string rareAbund; if (rareNames.count(itName->first) != 0) { //you are a rare name @@ -642,9 +950,9 @@ int SplitAbundCommand::writeNames() { //namefile map::iterator itout; for (int i = 0; i < names.size(); i++) { - string group = groupMap->getGroup(names[i]); + string group = groupMap.getGroup(names[i]); - if (inUsersGroups(group, Groups)) { //only add if this is in a group we want + if (m->inUsersGroups(group, Groups)) { //only add if this is in a group we want itout = outputStrings.find(group+rareAbund); if (itout == outputStrings.end()) { outputStrings[group+rareAbund] = names[i] + '\t' + names[i]; @@ -654,17 +962,16 @@ int SplitAbundCommand::writeNames() { //namefile } } - for (itout = outputStrings.begin(); itout != outputStrings.end(); itout++) { - *(filehandles[itout->first]) << itout->second << endl; - wroteFile[itout->first] = true; - } + for (itout = outputStrings.begin(); itout != outputStrings.end(); itout++) { *(filehandles[itout->first]) << itout->second << endl; } } for (it3 = filehandles.begin(); it3 != filehandles.end(); it3++) { (*(filehandles[it3->first])).close(); - if (wroteFile[it3->first] == true) { outputNames.push_back(fileroot + it3->first + ".names"); } - else { remove((it3->first).c_str()); } + map variables; + variables["[filename]"] = fileroot; + variables["[tag]"] = it3->first; + outputNames.push_back(getOutputFileName("name",variables)); outputTypes["name"].push_back(getOutputFileName("name",variables)); delete it3->second; } } @@ -688,32 +995,33 @@ int SplitAbundCommand::writeAccnos(string tag) { ofstream aout; ofstream rout; - if (rareNames.size() != 0) { - string rare = outputDir + getRootName(getSimpleName(inputFile)) + tag + "rare.accnos"; - openOutputFile(rare, rout); - outputNames.push_back(rare); - - for (set::iterator itRare = rareNames.begin(); itRare != rareNames.end(); itRare++) { - rout << (*itRare) << endl; - } - rout.close(); + map variables; + variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(inputFile)); + variables["[tag]"] = tag; + variables["[tag2]"] = "rare"; + string rare = getOutputFileName("accnos",variables); + m->openOutputFile(rare, rout); + outputNames.push_back(rare); outputTypes["accnos"].push_back(rare); + + for (set::iterator itRare = rareNames.begin(); itRare != rareNames.end(); itRare++) { + rout << (*itRare) << endl; } + rout.close(); + + variables["[tag2]"] = "abund"; + string abund = getOutputFileName("accnos",variables); + m->openOutputFile(abund, aout); + outputNames.push_back(abund); outputTypes["accnos"].push_back(abund); - if (abundNames.size() != 0) { - string abund = outputDir + getRootName(getSimpleName(inputFile)) + tag + "abund.accnos"; - openOutputFile(abund, aout); - outputNames.push_back(abund); - - for (set::iterator itAbund = abundNames.begin(); itAbund != abundNames.end(); itAbund++) { - aout << (*itAbund) << endl; - } - aout.close(); + for (set::iterator itAbund = abundNames.begin(); itAbund != abundNames.end(); itAbund++) { + aout << (*itAbund) << endl; } + aout.close(); + }else{ //parse names by abundance and group - string fileroot = outputDir + getRootName(getSimpleName(inputFile)); + string fileroot = outputDir + m->getRootName(m->getSimpleName(inputFile)); ofstream* temp; ofstream* temp2; - map wroteFile; map filehandles; map::iterator it3; @@ -723,38 +1031,42 @@ int SplitAbundCommand::writeAccnos(string tag) { temp2 = new ofstream; filehandles[Groups[i]+".abund"] = temp2; - openOutputFile(fileroot + tag + Groups[i] + ".rare.accnos", *(filehandles[Groups[i]+".rare"])); - openOutputFile(fileroot + tag + Groups[i] + ".abund.accnos", *(filehandles[Groups[i]+".abund"])); - - wroteFile[Groups[i] + ".rare"] = false; - wroteFile[Groups[i] + ".abund"] = false; + map variables; + variables["[filename]"] = fileroot; + variables["[tag]"] = tag; + variables["[tag2]"] = "rare"; + variables["[group]"] = Groups[i]; + m->openOutputFile(getOutputFileName("accnos",variables), *(filehandles[Groups[i]+".rare"])); + variables["[tag2]"] = "abund"; + m->openOutputFile(getOutputFileName("accnos",variables), *(filehandles[Groups[i]+".abund"])); } //write rare for (set::iterator itRare = rareNames.begin(); itRare != rareNames.end(); itRare++) { - string group = groupMap->getGroup(*itRare); + string group = groupMap.getGroup(*itRare); - if (inUsersGroups(group, Groups)) { //only add if this is in a group we want + if (m->inUsersGroups(group, Groups)) { //only add if this is in a group we want *(filehandles[group+".rare"]) << *itRare << endl; - wroteFile[group+".rare"] = true; } } //write abund for (set::iterator itAbund = abundNames.begin(); itAbund != abundNames.end(); itAbund++) { - string group = groupMap->getGroup(*itAbund); + string group = groupMap.getGroup(*itAbund); - if (inUsersGroups(group, Groups)) { //only add if this is in a group we want + if (m->inUsersGroups(group, Groups)) { //only add if this is in a group we want *(filehandles[group+".abund"]) << *itAbund << endl; - wroteFile[group+".abund"] = true; } } //close files for (it3 = filehandles.begin(); it3 != filehandles.end(); it3++) { (*(filehandles[it3->first])).close(); - if (wroteFile[it3->first] == true) { outputNames.push_back(fileroot + tag + it3->first + ".accnos"); } - else { remove((fileroot + tag + it3->first + ".accnos").c_str()); } + map variables; + variables["[filename]"] = fileroot; + variables["[tag]"] = tag; + variables["[tag2]"] = it3->first; + outputNames.push_back(getOutputFileName("accnos",variables)); outputTypes["accnos"].push_back(getOutputFileName("accnos",variables)); delete it3->second; } } @@ -777,26 +1089,27 @@ int SplitAbundCommand::parseGroup(string tag) { //namefile ofstream aout; ofstream rout; - if (rareNames.size() != 0) { - string rare = outputDir + getRootName(getSimpleName(groupfile)) + tag + "rare.groups"; - openOutputFile(rare, rout); - outputNames.push_back(rare); - } + map variables; + variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(groupfile)); + variables["[tag]"] = tag; + variables["[tag2]"] = "rare"; + string rare = getOutputFileName("group",variables); + m->openOutputFile(rare, rout); + outputNames.push_back(rare); outputTypes["group"].push_back(rare); + + variables["[tag2]"] = "abund"; + string abund = getOutputFileName("group",variables); +; + m->openOutputFile(abund, aout); + outputNames.push_back(abund); outputTypes["group"].push_back(abund); - if (abundNames.size() != 0) { - string abund = outputDir + getRootName(getSimpleName(groupfile)) + tag + "abund.groups"; - openOutputFile(abund, aout); - outputNames.push_back(abund); - } - - for (map::iterator itName = nameMap.begin(); itName != nameMap.end(); itName++) { vector names; - splitAtComma(itName->second, names); //parses bin into individual sequence names + m->splitAtComma(itName->second, names); //parses bin into individual sequence names for (int i = 0; i < names.size(); i++) { - string group = groupMap->getGroup(names[i]); + string group = groupMap.getGroup(names[i]); if (group == "not found") { m->mothurOut(names[i] + " is not in your groupfile, ignoring, please correct."); m->mothurOutEndLine(); @@ -810,14 +1123,13 @@ int SplitAbundCommand::parseGroup(string tag) { //namefile } } - if (rareNames.size() != 0) { rout.close(); } - if (abundNames.size() != 0) { aout.close(); } + rout.close(); + aout.close(); }else{ //parse names by abundance and group - string fileroot = outputDir + getRootName(getSimpleName(groupfile)); + string fileroot = outputDir + m->getRootName(m->getSimpleName(groupfile)); ofstream* temp; ofstream* temp2; - map wroteFile; map filehandles; map::iterator it3; @@ -827,16 +1139,19 @@ int SplitAbundCommand::parseGroup(string tag) { //namefile temp2 = new ofstream; filehandles[Groups[i]+".abund"] = temp2; - openOutputFile(fileroot + tag + Groups[i] + ".rare.groups", *(filehandles[Groups[i]+".rare"])); - openOutputFile(fileroot + tag + Groups[i] + ".abund.groups", *(filehandles[Groups[i]+".abund"])); - - wroteFile[Groups[i] + ".rare"] = false; - wroteFile[Groups[i] + ".abund"] = false; + map variables; + variables["[filename]"] = fileroot; + variables["[tag]"] = tag; + variables["[tag2]"] = "rare"; + variables["[group]"] = Groups[i]; + m->openOutputFile(getOutputFileName("group",variables), *(filehandles[Groups[i]+".rare"])); + variables["[tag2]"] = "abund"; + m->openOutputFile(getOutputFileName("group",variables), *(filehandles[Groups[i]+".abund"])); } for (map::iterator itName = nameMap.begin(); itName != nameMap.end(); itName++) { vector names; - splitAtComma(itName->second, names); //parses bin into individual sequence names + m->splitAtComma(itName->second, names); //parses bin into individual sequence names string rareAbund; if (rareNames.count(itName->first) != 0) { //you are a rare name @@ -847,19 +1162,21 @@ int SplitAbundCommand::parseGroup(string tag) { //namefile for (int i = 0; i < names.size(); i++) { - string group = groupMap->getGroup(names[i]); + string group = groupMap.getGroup(names[i]); - if (inUsersGroups(group, Groups)) { //only add if this is in a group we want + if (m->inUsersGroups(group, Groups)) { //only add if this is in a group we want *(filehandles[group+rareAbund]) << names[i] << '\t' << group << endl; - wroteFile[group+rareAbund] = true; } } } for (it3 = filehandles.begin(); it3 != filehandles.end(); it3++) { (*(filehandles[it3->first])).close(); - if (wroteFile[it3->first] == true) { outputNames.push_back(fileroot + tag + it3->first + ".groups"); } - else { remove((fileroot + tag + it3->first + ".groups").c_str()); } + map variables; + variables["[filename]"] = fileroot; + variables["[tag]"] = tag; + variables["[tag2]"] = it3->first; + outputNames.push_back(getOutputFileName("group",variables)); outputTypes["group"].push_back(getOutputFileName("group",variables)); delete it3->second; } } @@ -882,27 +1199,27 @@ int SplitAbundCommand::parseFasta(string tag) { //namefile ofstream aout; ofstream rout; - if (rareNames.size() != 0) { - string rare = outputDir + getRootName(getSimpleName(fastafile)) + tag + "rare.fasta"; - openOutputFile(rare, rout); - outputNames.push_back(rare); - } - - if (abundNames.size() != 0) { - string abund = outputDir + getRootName(getSimpleName(fastafile)) + tag + "abund.fasta"; - openOutputFile(abund, aout); - outputNames.push_back(abund); - } - - + map variables; + variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(fastafile)); + variables["[tag]"] = tag; + variables["[tag2]"] = "rare"; + string rare = getOutputFileName("fasta",variables); + m->openOutputFile(rare, rout); + outputNames.push_back(rare); outputTypes["fasta"].push_back(rare); + + variables["[tag2]"] = "abund"; + string abund = getOutputFileName("fasta",variables); + m->openOutputFile(abund, aout); + outputNames.push_back(abund); outputTypes["fasta"].push_back(abund); + //open input file ifstream in; - openInputFile(fastafile, in); + m->openInputFile(fastafile, in); while (!in.eof()) { if (m->control_pressed) { break; } - Sequence seq(in); gobble(in); + Sequence seq(in); m->gobble(in); if (seq.getName() != "") { @@ -911,7 +1228,7 @@ int SplitAbundCommand::parseFasta(string tag) { //namefile itNames = nameMap.find(seq.getName()); if (itNames == nameMap.end()) { - m->mothurOut(seq.getName() + " is not in your namesfile, ignoring."); m->mothurOutEndLine(); + m->mothurOut(seq.getName() + " is not in your names or list file, ignoring."); m->mothurOutEndLine(); }else{ if (rareNames.count(seq.getName()) != 0) { //you are a rare name seq.printSequence(rout); @@ -922,14 +1239,13 @@ int SplitAbundCommand::parseFasta(string tag) { //namefile } } in.close(); - if (rareNames.size() != 0) { rout.close(); } - if (abundNames.size() != 0) { aout.close(); } + rout.close(); + aout.close(); }else{ //parse names by abundance and group - string fileroot = outputDir + getRootName(getSimpleName(fastafile)); + string fileroot = outputDir + m->getRootName(m->getSimpleName(fastafile)); ofstream* temp; ofstream* temp2; - map wroteFile; map filehandles; map::iterator it3; @@ -939,30 +1255,33 @@ int SplitAbundCommand::parseFasta(string tag) { //namefile temp2 = new ofstream; filehandles[Groups[i]+".abund"] = temp2; - openOutputFile(fileroot + tag + Groups[i] + ".rare.fasta", *(filehandles[Groups[i]+".rare"])); - openOutputFile(fileroot + tag + Groups[i] + ".abund.fasta", *(filehandles[Groups[i]+".abund"])); - - wroteFile[Groups[i] + ".rare"] = false; - wroteFile[Groups[i] + ".abund"] = false; + map variables; + variables["[filename]"] = fileroot; + variables["[tag]"] = tag; + variables["[tag2]"] = "rare"; + variables["[group]"] = Groups[i]; + m->openOutputFile(getOutputFileName("fasta",variables), *(filehandles[Groups[i]+".rare"])); + variables["[tag2]"] = "abund"; + m->openOutputFile(getOutputFileName("fasta",variables), *(filehandles[Groups[i]+".abund"])); } //open input file ifstream in; - openInputFile(fastafile, in); + m->openInputFile(fastafile, in); while (!in.eof()) { if (m->control_pressed) { break; } - Sequence seq(in); gobble(in); + Sequence seq(in); m->gobble(in); if (seq.getName() != "") { map::iterator itNames = nameMap.find(seq.getName()); if (itNames == nameMap.end()) { - m->mothurOut(seq.getName() + " is not in your namesfile, ignoring."); m->mothurOutEndLine(); + m->mothurOut(seq.getName() + " is not in your names or list file, ignoring."); m->mothurOutEndLine(); }else{ vector names; - splitAtComma(itNames->second, names); //parses bin into individual sequence names + m->splitAtComma(itNames->second, names); //parses bin into individual sequence names string rareAbund; if (rareNames.count(itNames->first) != 0) { //you are a rare name @@ -970,18 +1289,25 @@ int SplitAbundCommand::parseFasta(string tag) { //namefile }else{ //you are a abund name rareAbund = ".abund"; } - - for (int i = 0; i < names.size(); i++) { - - string group = groupMap->getGroup(seq.getName()); - - if (inUsersGroups(group, Groups)) { //only add if this is in a group we want - seq.printSequence(*(filehandles[group+rareAbund])); - wroteFile[group+rareAbund] = true; - }else if(group == "not found") { - m->mothurOut(seq.getName() + " is not in your groupfile. Ignoring."); m->mothurOutEndLine(); - } - } + + if (countfile == "") { + for (int i = 0; i < names.size(); i++) { + string group = groupMap.getGroup(seq.getName()); + + if (m->inUsersGroups(group, Groups)) { //only add if this is in a group we want + seq.printSequence(*(filehandles[group+rareAbund])); + }else if(group == "not found") { + m->mothurOut(seq.getName() + " is not in your groupfile. Ignoring."); m->mothurOutEndLine(); + } + } + }else { + vector thisSeqsGroups = ct.getGroups(names[0]); //we only need names[0], because there is no namefile + for (int i = 0; i < thisSeqsGroups.size(); i++) { + if (m->inUsersGroups(thisSeqsGroups[i], Groups)) { //only add if this is in a group we want + seq.printSequence(*(filehandles[thisSeqsGroups[i]+rareAbund])); + } + } + } } } } @@ -989,8 +1315,11 @@ int SplitAbundCommand::parseFasta(string tag) { //namefile for (it3 = filehandles.begin(); it3 != filehandles.end(); it3++) { (*(filehandles[it3->first])).close(); - if (wroteFile[it3->first] == true) { outputNames.push_back(fileroot + tag + it3->first + ".fasta"); } - else { remove((fileroot + tag + it3->first + ".fasta").c_str()); } + map variables; + variables["[filename]"] = fileroot; + variables["[tag]"] = tag; + variables["[tag2]"] = it3->first; + outputNames.push_back(getOutputFileName("fasta",variables)); outputTypes["fasta"].push_back(getOutputFileName("fasta",variables)); delete it3->second; } }