X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=splitabundcommand.cpp;h=580493b60a1e4d449a71b8689635e8ced4dea397;hp=140f37909039c4eb44580c745d1886a1534d78d9;hb=615301e57c25e241356a9c2380648d117709458d;hpb=55386dddad84cc1140d736cabaf4dd0ae16f2e01 diff --git a/splitabundcommand.cpp b/splitabundcommand.cpp index 140f379..580493b 100644 --- a/splitabundcommand.cpp +++ b/splitabundcommand.cpp @@ -8,20 +8,22 @@ */ #include "splitabundcommand.h" +#include "sharedutilities.h" //********************************************************************************************************************** vector SplitAbundCommand::setParameters(){ try { - CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(pfasta); - CommandParameter pname("name", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pname); - CommandParameter pgroup("group", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(pgroup); - CommandParameter plist("list", "InputTypes", "", "", "none", "FNGLT", "none",false,false); 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); + 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); } @@ -37,8 +39,8 @@ 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, cutoff, group, label, groups, cutoff and accnos.\n"; - helpString += "The fasta and a list or name parameter are required, and you must provide a cutoff value.\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"; @@ -57,6 +59,26 @@ string SplitAbundCommand::getHelpString(){ } } +//********************************************************************************************************************** +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 { @@ -65,6 +87,7 @@ SplitAbundCommand::SplitAbundCommand(){ vector tempOutNames; outputTypes["list"] = tempOutNames; outputTypes["name"] = tempOutNames; + outputTypes["count"] = tempOutNames; outputTypes["accnos"] = tempOutNames; outputTypes["group"] = tempOutNames; outputTypes["fasta"] = tempOutNames; @@ -103,7 +126,8 @@ SplitAbundCommand::SplitAbundCommand(string option) { outputTypes["name"] = tempOutNames; outputTypes["accnos"] = tempOutNames; outputTypes["group"] = tempOutNames; - outputTypes["fasta"] = 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); @@ -142,6 +166,13 @@ SplitAbundCommand::SplitAbundCommand(string option) { 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; } + } } @@ -171,35 +202,52 @@ SplitAbundCommand::SplitAbundCommand(string option) { 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->getNamesOfGroups(); } - else { m->mothurOut("You cannot select groups without a valid groupfile, I will disregard your groups selection. "); m->mothurOutEndLine(); groups = ""; } - }else { - m->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 == "")) { + 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 { m->mothurOut("You have no current list or namefile and the list or name parameter is required."); m->mothurOutEndLine(); abort = true; } + 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); @@ -213,10 +261,9 @@ SplitAbundCommand::SplitAbundCommand(string option) { 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; } - } } @@ -226,14 +273,20 @@ SplitAbundCommand::SplitAbundCommand(string option) { } } //********************************************************************************************************************** -SplitAbundCommand::~SplitAbundCommand(){ - if (groupfile != "") { delete groupMap; } -} +SplitAbundCommand::~SplitAbundCommand(){} //********************************************************************************************************************** int SplitAbundCommand::execute(){ try { 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 = m->hasPath(listfile); } @@ -242,19 +295,19 @@ int SplitAbundCommand::execute(){ 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++) { m->mothurRemove(outputNames[i]); } 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++) { m->mothurRemove(outputNames[i]); } 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){ @@ -269,7 +322,7 @@ int SplitAbundCommand::execute(){ 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); @@ -285,10 +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++) { m->mothurRemove(outputNames[i]); } 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; @@ -304,12 +357,12 @@ int SplitAbundCommand::execute(){ } - if (m->control_pressed) { delete input; for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } 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); @@ -317,11 +370,9 @@ int SplitAbundCommand::execute(){ delete list; } - delete input; - 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 + }else if (namefile != "") { //you are using the namefile to determine abundance if (outputDir == "") { outputDir = m->hasPath(namefile); } splitNames(); @@ -331,7 +382,14 @@ 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 = ""; @@ -359,6 +417,11 @@ int SplitAbundCommand::execute(){ 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(); @@ -379,6 +442,7 @@ 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; } @@ -387,8 +451,15 @@ int SplitAbundCommand::splitList(ListVector* thisList) { vector 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]); } @@ -396,14 +467,15 @@ int SplitAbundCommand::splitList(ListVector* thisList) { }//end for - string tag = thisList->getLabel() + "."; - - writeList(thisList, tag); - + 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; } @@ -413,33 +485,27 @@ int SplitAbundCommand::splitList(ListVector* thisList) { } } /**********************************************************************************************************************/ -int SplitAbundCommand::writeList(ListVector* thisList, string tag) { +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; - string rare = outputDir + m->getRootName(m->getSimpleName(listfile)) + tag + "rare.list"; + 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); - string abund = outputDir + m->getRootName(m->getSimpleName(listfile)) + tag + "abund.list"; + variables["[tag2]"] = "abund"; + string abund = getOutputFileName("list",variables); m->openOutputFile(abund, aout); outputNames.push_back(abund); outputTypes["list"].push_back(abund); @@ -449,9 +515,15 @@ int SplitAbundCommand::writeList(ListVector* thisList, string tag) { for (int i = 0; i < thisList->getNumBins(); i++) { if (m->control_pressed) { break; } - string bin = list->get(i); - - int size = m->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'; } @@ -477,10 +549,18 @@ int SplitAbundCommand::writeList(ListVector* thisList, string tag) { temp2 = new ofstream; filehandles[Groups[i]+".abund"] = temp2; - m->openOutputFile(fileroot + Groups[i] + tag + ".rare.list", *(filehandles[Groups[i]+".rare"])); - m->openOutputFile(fileroot + Groups[i] + tag + ".abund.list", *(filehandles[Groups[i]+".abund"])); - outputNames.push_back(fileroot + Groups[i] + tag + ".rare.list"); outputTypes["list"].push_back(fileroot + Groups[i] + tag + ".rare.list"); - outputNames.push_back(fileroot + Groups[i] + tag + ".abund.list"); outputTypes["list"].push_back(fileroot + Groups[i] + tag + ".abund.list"); + 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; @@ -496,7 +576,7 @@ int SplitAbundCommand::writeList(ListVector* thisList, string tag) { if (m->control_pressed) { break; } map groupBins; - string bin = list->get(i); + string bin = thisList->get(i); vector names; m->splitAtComma(bin, names); //parses bin into individual sequence names @@ -510,19 +590,34 @@ int SplitAbundCommand::writeList(ListVector* thisList, string tag) { rareAbund = ".abund"; } - 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(); - } + 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]; + } + } + } + } } @@ -548,6 +643,37 @@ int SplitAbundCommand::writeList(ListVector* thisList, string tag) { } } /**********************************************************************************************************************/ +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 { @@ -634,6 +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 { @@ -643,11 +885,15 @@ int SplitAbundCommand::writeNames() { //namefile ofstream aout; ofstream rout; - string rare = outputDir + m->getRootName(m->getSimpleName(namefile)) + "rare.names"; + 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); - string abund = outputDir + m->getRootName(m->getSimpleName(namefile)) + "abund.names"; + variables["[tag]"] = "abund"; + string abund = getOutputFileName("name", variables); m->openOutputFile(abund, aout); outputNames.push_back(abund); outputTypes["name"].push_back(abund); @@ -678,8 +924,15 @@ int SplitAbundCommand::writeNames() { //namefile temp2 = new ofstream; filehandles[Groups[i]+".abund"] = temp2; - m->openOutputFile(fileroot + Groups[i] + ".rare.names", *(filehandles[Groups[i]+".rare"])); - m->openOutputFile(fileroot + Groups[i] + ".abund.names", *(filehandles[Groups[i]+".abund"])); + 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++) { @@ -697,7 +950,7 @@ 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 (m->inUsersGroups(group, Groups)) { //only add if this is in a group we want itout = outputStrings.find(group+rareAbund); @@ -715,7 +968,10 @@ int SplitAbundCommand::writeNames() { //namefile for (it3 = filehandles.begin(); it3 != filehandles.end(); it3++) { (*(filehandles[it3->first])).close(); - outputNames.push_back(fileroot + it3->first + ".names"); outputTypes["name"].push_back(fileroot + it3->first + ".names"); + 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; } } @@ -739,8 +995,11 @@ int SplitAbundCommand::writeAccnos(string tag) { ofstream aout; ofstream rout; - - string rare = outputDir + m->getRootName(m->getSimpleName(inputFile)) + tag + "rare.accnos"; + 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); @@ -749,7 +1008,8 @@ int SplitAbundCommand::writeAccnos(string tag) { } rout.close(); - string abund = outputDir + m->getRootName(m->getSimpleName(inputFile)) + tag + "abund.accnos"; + variables["[tag2]"] = "abund"; + string abund = getOutputFileName("accnos",variables); m->openOutputFile(abund, aout); outputNames.push_back(abund); outputTypes["accnos"].push_back(abund); @@ -771,13 +1031,19 @@ int SplitAbundCommand::writeAccnos(string tag) { temp2 = new ofstream; filehandles[Groups[i]+".abund"] = temp2; - m->openOutputFile(fileroot + tag + Groups[i] + ".rare.accnos", *(filehandles[Groups[i]+".rare"])); - m->openOutputFile(fileroot + tag + Groups[i] + ".abund.accnos", *(filehandles[Groups[i]+".abund"])); + 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 (m->inUsersGroups(group, Groups)) { //only add if this is in a group we want *(filehandles[group+".rare"]) << *itRare << endl; @@ -786,7 +1052,7 @@ int SplitAbundCommand::writeAccnos(string tag) { //write abund for (set::iterator itAbund = abundNames.begin(); itAbund != abundNames.end(); itAbund++) { - string group = groupMap->getGroup(*itAbund); + string group = groupMap.getGroup(*itAbund); if (m->inUsersGroups(group, Groups)) { //only add if this is in a group we want *(filehandles[group+".abund"]) << *itAbund << endl; @@ -796,7 +1062,11 @@ int SplitAbundCommand::writeAccnos(string tag) { //close files for (it3 = filehandles.begin(); it3 != filehandles.end(); it3++) { (*(filehandles[it3->first])).close(); - outputNames.push_back(fileroot + tag + it3->first + ".accnos"); outputTypes["accnos"].push_back(fileroot + tag + it3->first + ".accnos"); + 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; } } @@ -819,11 +1089,17 @@ int SplitAbundCommand::parseGroup(string tag) { //namefile ofstream aout; ofstream rout; - string rare = outputDir + m->getRootName(m->getSimpleName(groupfile)) + tag + "rare.groups"; + 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); - string abund = outputDir + m->getRootName(m->getSimpleName(groupfile)) + tag + "abund.groups"; + variables["[tag2]"] = "abund"; + string abund = getOutputFileName("group",variables); +; m->openOutputFile(abund, aout); outputNames.push_back(abund); outputTypes["group"].push_back(abund); @@ -833,7 +1109,7 @@ 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 (group == "not found") { m->mothurOut(names[i] + " is not in your groupfile, ignoring, please correct."); m->mothurOutEndLine(); @@ -863,8 +1139,14 @@ int SplitAbundCommand::parseGroup(string tag) { //namefile temp2 = new ofstream; filehandles[Groups[i]+".abund"] = temp2; - m->openOutputFile(fileroot + tag + Groups[i] + ".rare.groups", *(filehandles[Groups[i]+".rare"])); - m->openOutputFile(fileroot + tag + Groups[i] + ".abund.groups", *(filehandles[Groups[i]+".abund"])); + 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++) { @@ -880,7 +1162,7 @@ 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 (m->inUsersGroups(group, Groups)) { //only add if this is in a group we want *(filehandles[group+rareAbund]) << names[i] << '\t' << group << endl; @@ -890,7 +1172,11 @@ int SplitAbundCommand::parseGroup(string tag) { //namefile for (it3 = filehandles.begin(); it3 != filehandles.end(); it3++) { (*(filehandles[it3->first])).close(); - outputNames.push_back(fileroot + tag + it3->first + ".groups"); outputTypes["group"].push_back(fileroot + tag + it3->first + ".groups"); + 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; } } @@ -913,11 +1199,16 @@ int SplitAbundCommand::parseFasta(string tag) { //namefile ofstream aout; ofstream rout; - string rare = outputDir + m->getRootName(m->getSimpleName(fastafile)) + tag + "rare.fasta"; + 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); - string abund = outputDir + m->getRootName(m->getSimpleName(fastafile)) + tag + "abund.fasta"; + variables["[tag2]"] = "abund"; + string abund = getOutputFileName("fasta",variables); m->openOutputFile(abund, aout); outputNames.push_back(abund); outputTypes["fasta"].push_back(abund); @@ -937,7 +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); @@ -964,8 +1255,14 @@ int SplitAbundCommand::parseFasta(string tag) { //namefile temp2 = new ofstream; filehandles[Groups[i]+".abund"] = temp2; - m->openOutputFile(fileroot + tag + Groups[i] + ".rare.fasta", *(filehandles[Groups[i]+".rare"])); - m->openOutputFile(fileroot + tag + Groups[i] + ".abund.fasta", *(filehandles[Groups[i]+".abund"])); + 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 @@ -981,7 +1278,7 @@ int SplitAbundCommand::parseFasta(string tag) { //namefile 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; m->splitAtComma(itNames->second, names); //parses bin into individual sequence names @@ -992,17 +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 (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(); - } - } + + 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])); + } + } + } } } } @@ -1010,7 +1315,11 @@ int SplitAbundCommand::parseFasta(string tag) { //namefile for (it3 = filehandles.begin(); it3 != filehandles.end(); it3++) { (*(filehandles[it3->first])).close(); - outputNames.push_back(fileroot + tag + it3->first + ".fasta"); outputTypes["fasta"].push_back(fileroot + tag + it3->first + ".fasta"); + 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; } }