X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=removelineagecommand.cpp;h=ef1e77e01755f57acbaa4581c36a3e66d376c198;hb=a4f05f09c250323132a4b9427f41a3ededaec634;hp=557622db59b1f5480a87fda36050e98cfb9439a9;hpb=8bc3e5b38c2317a1715f53be22fa96455868c281;p=mothur.git diff --git a/removelineagecommand.cpp b/removelineagecommand.cpp index 557622d..ef1e77e 100644 --- a/removelineagecommand.cpp +++ b/removelineagecommand.cpp @@ -26,7 +26,7 @@ vector RemoveLineageCommand::getValidParameters(){ //********************************************************************************************************************** RemoveLineageCommand::RemoveLineageCommand(){ try { - //initialize outputTypes + abort = true; calledHelp = true; vector tempOutNames; outputTypes["fasta"] = tempOutNames; outputTypes["taxonomy"] = tempOutNames; @@ -66,10 +66,10 @@ vector RemoveLineageCommand::getRequiredFiles(){ //********************************************************************************************************************** RemoveLineageCommand::RemoveLineageCommand(string option) { try { - abort = false; + abort = false; calledHelp = false; //allow user to run help - if(option == "help") { help(); abort = true; } + if(option == "help") { help(); abort = true; calledHelp = true; } else { //valid paramters for this command @@ -180,7 +180,11 @@ RemoveLineageCommand::RemoveLineageCommand(string option) { else if (taxfile == "not found") { taxfile = ""; m->mothurOut("The taxonomy parameter is required for the get.lineage command."); m->mothurOutEndLine(); abort = true; } string usedDups = "true"; - string temp = validParameter.validFile(parameters, "dups", false); if (temp == "not found") { temp = "false"; usedDups = ""; } + string temp = validParameter.validFile(parameters, "dups", false); + if (temp == "not found") { + if (namefile != "") { temp = "true"; } + else { temp = "false"; usedDups = ""; } + } dups = m->isTrue(temp); taxons = validParameter.validFile(parameters, "taxon", false); @@ -213,6 +217,8 @@ void RemoveLineageCommand::help(){ m->mothurOut("The remove.lineage command parameters are taxon, fasta, name, group, list, taxonomy, alignreport and dups. You must provide taxonomy and taxon.\n"); m->mothurOut("The dups parameter allows you to add the entire line from a name file if you add any name from the line. default=false. \n"); m->mothurOut("The taxon parameter allows you to select the taxons you would like to remove.\n"); + m->mothurOut("You may enter your taxons with confidence scores, doing so will remove only those sequences that belong to the taxonomy and whose cofidence scores fall below the scores you give.\n"); + m->mothurOut("If they belong to the taxonomy and have confidences above those you provide the sequence will not be removed.\n"); m->mothurOut("The remove.lineage command should be in the following format: remove.lineage(taxonomy=yourTaxonomyFile, taxon=yourTaxons).\n"); m->mothurOut("Example remove.lineage(taxonomy=amazon.silva.taxonomy, taxon=Bacteria;Firmicutes;Bacilli;Lactobacillales;).\n"); m->mothurOut("Note: If you are running mothur in script mode you must wrap the taxon in ' characters so mothur will ignore the ; in the taxon.\n"); @@ -230,7 +236,7 @@ void RemoveLineageCommand::help(){ int RemoveLineageCommand::execute(){ try { - if (abort == true) { return 0; } + if (abort == true) { if (calledHelp) { return 0; } return 2; } if (m->control_pressed) { return 0; } @@ -250,6 +256,33 @@ int RemoveLineageCommand::execute(){ m->mothurOut("Output File Names: "); m->mothurOutEndLine(); for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); } m->mothurOutEndLine(); + + //set fasta file as new current fastafile + string current = ""; + itTypes = outputTypes.find("fasta"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setFastaFile(current); } + } + + itTypes = outputTypes.find("name"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setNameFile(current); } + } + + itTypes = outputTypes.find("group"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setGroupFile(current); } + } + + itTypes = outputTypes.find("list"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setListFile(current); } + } + + itTypes = outputTypes.find("taxonomy"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setTaxonomyFile(current); } + } } return 0; @@ -297,7 +330,7 @@ int RemoveLineageCommand::readFasta(){ out.close(); if (wroteSomething == false) { m->mothurOut("Your fasta file contains only sequences from " + taxons + "."); m->mothurOutEndLine(); } - outputTypes["fasta"].push_back(outputFileName); + outputNames.push_back(outputFileName); outputTypes["fasta"].push_back(outputFileName); return 0; @@ -368,7 +401,7 @@ int RemoveLineageCommand::readList(){ out.close(); if (wroteSomething == false) { m->mothurOut("Your list file contains only sequences from " + taxons + "."); m->mothurOutEndLine(); } - outputTypes["list"].push_back(outputFileName); + outputNames.push_back(outputFileName); outputTypes["list"].push_back(outputFileName); return 0; @@ -454,7 +487,7 @@ int RemoveLineageCommand::readName(){ out.close(); if (wroteSomething == false) { m->mothurOut("Your name file contains only sequences from " + taxons + "."); m->mothurOutEndLine(); } - outputTypes["name"].push_back(outputFileName); + outputNames.push_back(outputFileName); outputTypes["name"].push_back(outputFileName); return 0; } @@ -498,7 +531,7 @@ int RemoveLineageCommand::readGroup(){ out.close(); if (wroteSomething == false) { m->mothurOut("Your group file contains only sequences from " + taxons + "."); m->mothurOutEndLine(); } - outputTypes["group"].push_back(outputFileName); + outputNames.push_back(outputFileName); outputTypes["group"].push_back(outputFileName); return 0; } @@ -522,6 +555,17 @@ int RemoveLineageCommand::readTax(){ bool wroteSomething = false; + bool taxonsHasConfidence = false; + vector< map > searchTaxons; + string noConfidenceTaxons = taxons; + int hasConPos = taxons.find_first_of('('); + if (hasConPos != string::npos) { + taxonsHasConfidence = true; + searchTaxons = getTaxons(taxons); + noConfidenceTaxons = removeConfidences(taxons); + } + + while(!in.eof()){ if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } @@ -531,20 +575,99 @@ int RemoveLineageCommand::readTax(){ string newtax = tax; - //if the users file contains confidence scores we want to ignore them when searching for the taxons - int hasConfidences = tax.find_first_of('('); - if (hasConfidences != string::npos) { - newtax = removeConfidences(tax); + //if the users file contains confidence scores we want to ignore them when searching for the taxons, unless the taxon has them + if (!taxonsHasConfidence) { + + int hasConfidences = tax.find_first_of('('); + if (hasConfidences != string::npos) { + newtax = removeConfidences(tax); + } + + int pos = newtax.find(taxons); + + if (pos == string::npos) { + wroteSomething = true; + out << name << '\t' << tax << endl; + }else{ //this sequence contains the taxon the user wants to remove + names.insert(name); + } + + }else{//if taxons has them and you don't them remove taxons + int hasConfidences = tax.find_first_of('('); + if (hasConfidences == string::npos) { + + int pos = newtax.find(noConfidenceTaxons); + + if (pos == string::npos) { + wroteSomething = true; + out << name << '\t' << tax << endl; + }else{ //this sequence contains the taxon the user wants to remove + names.insert(name); + } + }else { //both have confidences so we want to make sure the users confidences are greater then or equal to the taxons + //first remove confidences from both and see if the taxonomy exists + + string noNewTax = tax; + int hasConfidences = tax.find_first_of('('); + if (hasConfidences != string::npos) { + noNewTax = removeConfidences(tax); + } + + int pos = noNewTax.find(noConfidenceTaxons); + + if (pos != string::npos) { //if yes, then are the confidences okay + + bool remove = false; + vector< map > usersTaxon = getTaxons(newtax); + + //the usersTaxon is most likely longer than the searchTaxons, and searchTaxon[0] may relate to userTaxon[4] + //we want to "line them up", so we will find the the index where the searchstring starts + int index = 0; + for (int i = 0; i < usersTaxon.size(); i++) { + + if (usersTaxon[i].begin()->first == searchTaxons[0].begin()->first) { + index = i; + int spot = 0; + bool goodspot = true; + //is this really the start, or are we dealing with a taxon of the same name? + while ((spot < searchTaxons.size()) && ((i+spot) < usersTaxon.size())) { + if (usersTaxon[i+spot].begin()->first != searchTaxons[spot].begin()->first) { goodspot = false; break; } + else { spot++; } + } + + if (goodspot) { break; } + } + } + + for (int i = 0; i < searchTaxons.size(); i++) { + + if ((i+index) < usersTaxon.size()) { //just in case, should never be false + if (usersTaxon[i+index].begin()->second < searchTaxons[i].begin()->second) { //is the users cutoff less than the search taxons + remove = true; + break; + } + }else { + remove = true; + break; + } + } + + //passed the test so remove you + if (remove) { + names.insert(name); + }else { + wroteSomething = true; + out << name << '\t' << tax << endl; + } + }else { + wroteSomething = true; + out << name << '\t' << tax << endl; + } + } } - int pos = newtax.find(taxons); - if (pos == string::npos) { - wroteSomething = true; - out << name << '\t' << tax << endl; - }else{ //this sequence contains the taxon the user wants to remove - names.insert(name); - } + m->gobble(in); } @@ -552,7 +675,7 @@ int RemoveLineageCommand::readTax(){ out.close(); if (!wroteSomething) { m->mothurOut("Your taxonomy file contains only sequences from " + taxons + "."); m->mothurOutEndLine(); } - outputTypes["taxonomy"].push_back(outputFileName); + outputNames.push_back(outputFileName); outputTypes["taxonomy"].push_back(outputFileName); return 0; @@ -563,6 +686,48 @@ int RemoveLineageCommand::readTax(){ } } /**************************************************************************************************/ +vector< map > RemoveLineageCommand::getTaxons(string tax) { + try { + + vector< map > t; + string taxon = ""; + int taxLength = tax.length(); + for(int i=0;i temp; + temp[newtaxon] = con; + t.push_back(temp); + + taxon = ""; + } + else{ + taxon += tax[i]; + } + } + + return t; + } + catch(exception& e) { + m->errorOut(e, "RemoveLineageCommand", "getTaxons"); + exit(1); + } +} +/**************************************************************************************************/ string RemoveLineageCommand::removeConfidences(string tax) { try { @@ -642,7 +807,7 @@ int RemoveLineageCommand::readAlign(){ out.close(); if (wroteSomething == false) { m->mothurOut("Your align file contains only sequences from " + taxons + "."); m->mothurOutEndLine(); } - outputTypes["alignreport"].push_back(outputFileName); + outputNames.push_back(outputFileName); outputTypes["alignreport"].push_back(outputFileName); return 0;