X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=getlineagecommand.cpp;h=25a68be75c950de1ebad3afe6955cf308ad0ce0b;hp=1cd139b5213733e759a7a32a1fbdf8221d09dfb6;hb=d3e27ba055f6765044b885cded5302d9cece161a;hpb=ea4f373c28543cd1002b0dd7dc6e55c526647d59 diff --git a/getlineagecommand.cpp b/getlineagecommand.cpp index 1cd139b..25a68be 100644 --- a/getlineagecommand.cpp +++ b/getlineagecommand.cpp @@ -10,21 +10,26 @@ #include "getlineagecommand.h" #include "sequence.hpp" #include "listvector.hpp" +#include "counttable.h" +#include "inputdata.h" //********************************************************************************************************************** vector GetLineageCommand::setParameters(){ try { - CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pfasta); - CommandParameter pname("name", "InputTypes", "", "", "NameCount", "FNGLT", "none",false,false); parameters.push_back(pname); - CommandParameter pcount("count", "InputTypes", "", "", "NameCount-CountGroup", "FNGLT", "none",false,false); parameters.push_back(pcount); - CommandParameter pgroup("group", "InputTypes", "", "", "CountGroup", "FNGLT", "none",false,false); parameters.push_back(pgroup); - CommandParameter plist("list", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(plist); - CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "none", "FNGLT", "none",false,true); parameters.push_back(ptaxonomy); - CommandParameter palignreport("alignreport", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(palignreport); - CommandParameter ptaxon("taxon", "String", "", "", "", "", "",false,true); parameters.push_back(ptaxon); - CommandParameter pdups("dups", "Boolean", "", "T", "", "", "",false,false); parameters.push_back(pdups); - 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", "FNGLT", "none","fasta",false,false, 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", "FNGLT", "none","count",false,false, true); parameters.push_back(pcount); + CommandParameter pgroup("group", "InputTypes", "", "", "CountGroup", "FNGLT", "none","group",false,false, true); parameters.push_back(pgroup); + CommandParameter plist("list", "InputTypes", "", "", "none", "FNGLT", "none","list",false,false, true); parameters.push_back(plist); + CommandParameter pshared("shared", "InputTypes", "", "", "none", "FNGLT", "none","shared",false,false, true); parameters.push_back(pshared); + CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "tax", "FNGLT", "none","taxonomy",false,false, true); parameters.push_back(ptaxonomy); + CommandParameter pconstaxonomy("constaxonomy", "InputTypes", "", "", "tax", "FNGLT", "none","constaxonomy",false,false, true); parameters.push_back(pconstaxonomy); + CommandParameter palignreport("alignreport", "InputTypes", "", "", "none", "FNGLT", "none","alignreport",false,false); parameters.push_back(palignreport); + CommandParameter plabel("label", "String", "", "", "", "", "","",false,false); parameters.push_back(plabel); + CommandParameter ptaxon("taxon", "String", "", "", "", "", "","",false,true, true); parameters.push_back(ptaxon); + CommandParameter pdups("dups", "Boolean", "", "T", "", "", "","",false,false); parameters.push_back(pdups); + 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); } @@ -39,13 +44,14 @@ vector GetLineageCommand::setParameters(){ string GetLineageCommand::getHelpString(){ try { string helpString = ""; - helpString += "The get.lineage command reads a taxonomy file and any of the following file types: fasta, name, group, count, list or alignreport file.\n"; + helpString += "The get.lineage command reads a taxonomy or constaxonomy file and any of the following file types: fasta, name, group, count, list, shared or alignreport file. The constaxonomy can only be used with a shared or list file.\n"; helpString += "It outputs a file containing only the sequences from the taxonomy file that are from the taxon requested.\n"; - helpString += "The get.lineage command parameters are taxon, fasta, name, group, count, list, taxonomy, alignreport and dups. You must provide taxonomy unless you have a valid current taxonomy file.\n"; + helpString += "The get.lineage command parameters are taxon, fasta, name, group, count, list, shared, taxonomy, alignreport, label and dups. You must provide taxonomy or constaxonomy unless you have a valid current taxonomy file.\n"; helpString += "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"; helpString += "The taxon parameter allows you to select the taxons you would like to get and is required.\n"; helpString += "You may enter your taxons with confidence scores, doing so will get only those sequences that belong to the taxonomy and whose cofidence scores is above the scores you give.\n"; helpString += "If they belong to the taxonomy and have confidences below those you provide the sequence will not be selected.\n"; + helpString += "The label parameter is used to analyze specific labels in your input. \n"; helpString += "The get.lineage command should be in the following format: get.lineage(taxonomy=yourTaxonomyFile, taxon=yourTaxons).\n"; helpString += "Example get.lineage(taxonomy=amazon.silva.taxonomy, taxon=Bacteria;Firmicutes;Bacilli;Lactobacillales;).\n"; helpString += "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"; @@ -59,30 +65,27 @@ string GetLineageCommand::getHelpString(){ } } //********************************************************************************************************************** -string GetLineageCommand::getOutputFileNameTag(string type, string inputName=""){ - try { - string outputFileName = ""; - map >::iterator it; +string GetLineageCommand::getOutputPattern(string type) { + try { + string pattern = ""; - //is this a type this command creates - it = outputTypes.find(type); - if (it == outputTypes.end()) { m->mothurOut("[ERROR]: this command doesn't create a " + type + " output file.\n"); } - else { - if (type == "fasta") { outputFileName = "pick" + m->getExtension(inputName); } - else if (type == "taxonomy") { outputFileName = "pick" + m->getExtension(inputName); } - else if (type == "name") { outputFileName = "pick" + m->getExtension(inputName); } - else if (type == "count") { outputFileName = "pick.count.table"; } - else if (type == "group") { outputFileName = "pick" + m->getExtension(inputName); } - else if (type == "list") { outputFileName = "pick" + m->getExtension(inputName); } - else if (type == "alignreport") { outputFileName = "pick.align.report"; } - else { m->mothurOut("[ERROR]: No definition for type " + type + " output file tag.\n"); m->control_pressed = true; } - } - return outputFileName; - } - catch(exception& e) { - m->errorOut(e, "GetLineageCommand", "getOutputFileNameTag"); - exit(1); - } + if (type == "fasta") { pattern = "[filename],pick,[extension]"; } + else if (type == "taxonomy") { pattern = "[filename],pick,[extension]"; } + else if (type == "constaxonomy") { pattern = "[filename],pick,[extension]"; } + else if (type == "name") { pattern = "[filename],pick,[extension]"; } + else if (type == "group") { pattern = "[filename],pick,[extension]"; } + else if (type == "count") { pattern = "[filename],pick,[extension]"; } + else if (type == "list") { pattern = "[filename],pick,[extension]-[filename],[distance],pick,[extension]"; } + else if (type == "shared") { pattern = "[filename],[distance],pick,[extension]"; } + else if (type == "alignreport") { pattern = "[filename],pick.align.report"; } + else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; } + + return pattern; + } + catch(exception& e) { + m->errorOut(e, "GetLineageCommand", "getOutputPattern"); + exit(1); + } } //********************************************************************************************************************** GetLineageCommand::GetLineageCommand(){ @@ -97,6 +100,8 @@ GetLineageCommand::GetLineageCommand(){ outputTypes["alignreport"] = tempOutNames; outputTypes["list"] = tempOutNames; outputTypes["count"] = tempOutNames; + outputTypes["constaxonomy"] = tempOutNames; + outputTypes["shared"] = tempOutNames; } catch(exception& e) { m->errorOut(e, "GetLineageCommand", "GetLineageCommand"); @@ -135,6 +140,8 @@ GetLineageCommand::GetLineageCommand(string option) { outputTypes["alignreport"] = tempOutNames; outputTypes["list"] = tempOutNames; outputTypes["count"] = tempOutNames; + outputTypes["constaxonomy"] = tempOutNames; + outputTypes["shared"] = tempOutNames; //if the user changes the output directory command factory will send this info to us in the output parameter outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){ outputDir = ""; } @@ -199,6 +206,22 @@ GetLineageCommand::GetLineageCommand(string option) { //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["count"] = inputDir + it->second; } } + + it = parameters.find("constaxonomy"); + //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["constaxonomy"] = inputDir + it->second; } + } + + it = parameters.find("shared"); + //user has given a template file + if(it != parameters.end()){ + path = m->hasPath(it->second); + //if the user has not given a path then, add inputdir. else leave path alone. + if (path == "") { parameters["shared"] = inputDir + it->second; } + } } @@ -229,12 +252,26 @@ GetLineageCommand::GetLineageCommand(string option) { taxfile = validParameter.validFile(parameters, "taxonomy", true); if (taxfile == "not open") { taxfile = ""; abort = true; } - else if (taxfile == "not found") { - taxfile = m->getTaxonomyFile(); - if (taxfile != "") { m->mothurOut("Using " + taxfile + " as input file for the taxonomy parameter."); m->mothurOutEndLine(); } - else { m->mothurOut("You have no current taxonomy file and the taxonomy parameter is required."); m->mothurOutEndLine(); abort = true; } - }else { m->setTaxonomyFile(taxfile); } - + else if (taxfile == "not found") { taxfile = ""; } + else { m->setTaxonomyFile(taxfile); } + + sharedfile = validParameter.validFile(parameters, "shared", true); + if (sharedfile == "not open") { sharedfile = ""; abort = true; } + else if (sharedfile == "not found") { sharedfile = ""; } + else { m->setSharedFile(sharedfile); } + + + constaxonomy = validParameter.validFile(parameters, "constaxonomy", true); + if (constaxonomy == "not open") { constaxonomy = ""; abort = true; } + else if (constaxonomy == "not found") { constaxonomy = ""; } + + if ((constaxonomy == "") && (taxfile == "")) { + taxfile = m->getTaxonomyFile(); + if (taxfile != "") { m->mothurOut("Using " + taxfile + " as input file for the taxonomy parameter."); m->mothurOutEndLine(); } + else { + m->mothurOut("You have no current taxonomy file and did not provide a constaxonomy file. The taxonomy or constaxonomy parameter is required."); m->mothurOutEndLine(); abort = true; } + } + string usedDups = "true"; string temp = validParameter.validFile(parameters, "dups", false); if (temp == "not found") { @@ -265,8 +302,25 @@ GetLineageCommand::GetLineageCommand(string option) { } m->splitAtChar(taxons, listOfTaxons, '-'); - if ((fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == "") && (taxfile == "") && (countfile == "")) { m->mothurOut("You must provide one of the following: fasta, name, group, count, alignreport, taxonomy or listfile."); m->mothurOutEndLine(); abort = true; } - + if ((fastafile == "") && (constaxonomy == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == "") && (taxfile == "") && (countfile == "")) { m->mothurOut("You must provide one of the following: fasta, name, group, count, alignreport, taxonomy, constaxonomy, shared or listfile."); m->mothurOutEndLine(); abort = true; } + + if ((constaxonomy != "") && ((fastafile != "") || (namefile != "") || (groupfile != "") || (alignfile != "") || (taxfile != "") || (countfile != ""))) { + m->mothurOut("[ERROR]: can only use constaxonomy file with a list or shared file, aborting.\n"); abort = true; + } + + if ((constaxonomy != "") && (taxfile != "")) { + m->mothurOut("[ERROR]: Choose only one: taxonomy or constaxonomy, aborting.\n"); abort = true; + } + + if ((sharedfile != "") && (taxfile != "")) { + m->mothurOut("[ERROR]: sharedfile can only be used with constaxonomy file, aborting.\n"); abort = true; + } + + if ((sharedfile != "") || (listfile != "")) { + label = validParameter.validFile(parameters, "label", false); + if (label == "not found") { label = ""; m->mothurOut("You did not provide a label, I will use the first label in your inputfile."); m->mothurOutEndLine(); label=""; } + } + if (countfile == "") { if ((namefile == "") && ((fastafile != "") || (taxfile != ""))){ vector files; files.push_back(fastafile); files.push_back(taxfile); @@ -297,14 +351,21 @@ int GetLineageCommand::execute(){ } //read through the correct file and output lines you want to keep - if (taxfile != "") { readTax(); } //fills the set of names to get - if (namefile != "") { readName(); } - if (fastafile != "") { readFasta(); } - if (countfile != "") { readCount(); } - if (groupfile != "") { readGroup(); } - if (alignfile != "") { readAlign(); } - if (listfile != "") { readList(); } - + if (taxfile != "") { + readTax(); //fills the set of names to get + if (namefile != "") { readName(); } + if (fastafile != "") { readFasta(); } + if (countfile != "") { readCount(); } + if (groupfile != "") { readGroup(); } + if (alignfile != "") { readAlign(); } + if (listfile != "") { readList(); } + + }else { + readConsTax(); + if (listfile != "") { readConsList(); } + if (sharedfile != "") { readShared(); } + } + if (m->control_pressed) { outputTypes.clear(); for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } @@ -335,6 +396,11 @@ int GetLineageCommand::execute(){ if (itTypes != outputTypes.end()) { if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setListFile(current); } } + + itTypes = outputTypes.find("shared"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setSharedFile(current); } + } itTypes = outputTypes.find("taxonomy"); if (itTypes != outputTypes.end()) { @@ -361,7 +427,10 @@ int GetLineageCommand::readFasta(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(fastafile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(fastafile)) + getOutputFileNameTag("fasta", fastafile); + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(fastafile)); + variables["[extension]"] = m->getExtension(fastafile); + string outputFileName = getOutputFileName("fasta", variables); ofstream out; m->openOutputFile(outputFileName, out); @@ -408,7 +477,10 @@ int GetLineageCommand::readCount(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(countfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(countfile)) + getOutputFileNameTag("count", countfile); + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(countfile)); + variables["[extension]"] = m->getExtension(countfile); + string outputFileName = getOutputFileName("count", variables); ofstream out; m->openOutputFile(outputFileName, out); @@ -438,6 +510,14 @@ int GetLineageCommand::readCount(){ } in.close(); out.close(); + + //check for groups that have been eliminated + CountTable ct; + if (ct.testGroups(outputFileName)) { + ct.readTable(outputFileName, true); + ct.printTable(outputFileName); + } + if (wroteSomething == false) { m->mothurOut("Your file contains does not contain any sequences from " + taxons + "."); m->mothurOutEndLine(); } outputTypes["count"].push_back(outputFileName); outputNames.push_back(outputFileName); @@ -454,7 +534,10 @@ int GetLineageCommand::readList(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(listfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(listfile)) + getOutputFileNameTag("list", listfile); + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(listfile)); + variables["[extension]"] = m->getExtension(listfile); + string outputFileName = getOutputFileName("list", variables); ofstream out; m->openOutputFile(outputFileName, out); @@ -479,18 +562,16 @@ int GetLineageCommand::readList(){ //parse out names that are in accnos file string binnames = list.get(i); + vector bnames; + m->splitAtComma(binnames, bnames); string newNames = ""; - while (binnames.find_first_of(',') != -1) { - string name = binnames.substr(0,binnames.find_first_of(',')); - binnames = binnames.substr(binnames.find_first_of(',')+1, binnames.length()); - + for (int j = 0; j < bnames.size(); j++) { + string name = bnames[j]; //if that name is in the .accnos file, add it if (names.count(name) != 0) { newNames += name + ","; } } - - //get last name - if (names.count(binnames) != 0) { newNames += binnames + ","; } + //if there are names in this bin add to new list if (newNames != "") { @@ -521,12 +602,301 @@ int GetLineageCommand::readList(){ exit(1); } } +//********************************************************************************************************************** +int GetLineageCommand::readConsList(){ + try { + getListVector(); + + if (m->control_pressed) { delete list; return 0;} + + ListVector newList; + newList.setLabel(list->getLabel()); + int selectedCount = 0; + bool wroteSomething = false; + string snumBins = toString(list->getNumBins()); + + for (int i = 0; i < list->getNumBins(); i++) { + + if (m->control_pressed) { delete list; return 0;} + + //create a label for this otu + string otuLabel = "Otu"; + string sbinNumber = toString(i+1); + if (sbinNumber.length() < snumBins.length()) { + int diff = snumBins.length() - sbinNumber.length(); + for (int h = 0; h < diff; h++) { otuLabel += "0"; } + } + otuLabel += sbinNumber; + + if (names.count(otuLabel) != 0) { + selectedCount++; + newList.push_back(list->get(i)); + } + } + + string thisOutputDir = outputDir; + if (outputDir == "") { thisOutputDir += m->hasPath(listfile); } + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(listfile)); + variables["[extension]"] = m->getExtension(listfile); + variables["[distance]"] = list->getLabel(); + string outputFileName = getOutputFileName("list", variables); + ofstream out; + m->openOutputFile(outputFileName, out); + + delete list; + //print new listvector + if (newList.getNumBins() != 0) { + wroteSomething = true; + newList.print(out); + } + out.close(); + + if (wroteSomething == false) { m->mothurOut("Your file does not contain OTUs from " + taxons + "."); m->mothurOutEndLine(); } + outputNames.push_back(outputFileName); outputTypes["list"].push_back(outputFileName); + + m->mothurOut("Selected " + toString(selectedCount) + " OTUs from your list file."); m->mothurOutEndLine(); + + return 0; + + } + catch(exception& e) { + m->errorOut(e, "GetLineageCommand", "readConsList"); + exit(1); + } +} +//********************************************************************************************************************** +int GetLineageCommand::getListVector(){ + try { + InputData input(listfile, "list"); + list = input.getListVector(); + string lastLabel = list->getLabel(); + + if (label == "") { label = lastLabel; return 0; } + + //if the users enters label "0.06" and there is no "0.06" in their file use the next lowest label. + set labels; labels.insert(label); + set processedLabels; + set userLabels = labels; + + //as long as you are not at the end of the file or done wih the lines you want + while((list != NULL) && (userLabels.size() != 0)) { + if (m->control_pressed) { return 0; } + + if(labels.count(list->getLabel()) == 1){ + processedLabels.insert(list->getLabel()); + userLabels.erase(list->getLabel()); + break; + } + + if ((m->anyLabelsToProcess(list->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) { + string saveLabel = list->getLabel(); + + delete list; + list = input.getListVector(lastLabel); + + processedLabels.insert(list->getLabel()); + userLabels.erase(list->getLabel()); + + //restore real lastlabel to save below + list->setLabel(saveLabel); + break; + } + + lastLabel = list->getLabel(); + + //get next line to process + //prevent memory leak + delete list; + list = input.getListVector(); + } + + + if (m->control_pressed) { return 0; } + + //output error messages about any remaining user labels + set::iterator it; + bool needToRun = false; + for (it = userLabels.begin(); it != userLabels.end(); it++) { + m->mothurOut("Your file does not include the label " + *it); + if (processedLabels.count(lastLabel) != 1) { + m->mothurOut(". I will use " + lastLabel + "."); m->mothurOutEndLine(); + needToRun = true; + }else { + m->mothurOut(". Please refer to " + lastLabel + "."); m->mothurOutEndLine(); + } + } + + //run last label if you need to + if (needToRun == true) { + delete list; + list = input.getListVector(lastLabel); + } + + return 0; + } + catch(exception& e) { + m->errorOut(e, "GetLineageCommand", "getListVector"); + exit(1); + } +} + +//********************************************************************************************************************** +int GetLineageCommand::readShared(){ + try { + + getShared(); + + if (m->control_pressed) { for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } return 0; } + + vector newLabels; + + //create new "filtered" lookup + vector newLookup; + for (int i = 0; i < lookup.size(); i++) { + SharedRAbundVector* temp = new SharedRAbundVector(); + temp->setLabel(lookup[i]->getLabel()); + temp->setGroup(lookup[i]->getGroup()); + newLookup.push_back(temp); + } + + bool wroteSomething = false; + int numSelected = 0; + for (int i = 0; i < lookup[0]->getNumBins(); i++) { + + if (m->control_pressed) { for (int j = 0; j < newLookup.size(); j++) { delete newLookup[j]; } for (int j = 0; j < lookup.size(); j++) { delete lookup[j]; } return 0; } + + //is this otu on the list + if (names.count(m->currentBinLabels[i]) != 0) { + numSelected++; wroteSomething = true; + newLabels.push_back(m->currentBinLabels[i]); + for (int j = 0; j < newLookup.size(); j++) { //add this OTU to the new lookup + newLookup[j]->push_back(lookup[j]->getAbundance(i), lookup[j]->getGroup()); + } + } + } + + string thisOutputDir = outputDir; + if (outputDir == "") { thisOutputDir += m->hasPath(sharedfile); } + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(sharedfile)); + variables["[extension]"] = m->getExtension(sharedfile); + variables["[distance]"] = lookup[0]->getLabel(); + string outputFileName = getOutputFileName("shared", variables); + ofstream out; + m->openOutputFile(outputFileName, out); + outputTypes["shared"].push_back(outputFileName); outputNames.push_back(outputFileName); + + for (int j = 0; j < lookup.size(); j++) { delete lookup[j]; } + + m->currentBinLabels = newLabels; + + newLookup[0]->printHeaders(out); + + for (int i = 0; i < newLookup.size(); i++) { + out << newLookup[i]->getLabel() << '\t' << newLookup[i]->getGroup() << '\t'; + newLookup[i]->print(out); + } + out.close(); + + for (int j = 0; j < newLookup.size(); j++) { delete newLookup[j]; } + + if (wroteSomething == false) { m->mothurOut("Your file does not contain OTUs from " + taxons + "."); m->mothurOutEndLine(); } + + m->mothurOut("Selected " + toString(numSelected) + " OTUs from your shared file."); m->mothurOutEndLine(); + + return 0; + } + catch(exception& e) { + m->errorOut(e, "GetLineageCommand", "readShared"); + exit(1); + } +} +//********************************************************************************************************************** +int GetLineageCommand::getShared(){ + try { + InputData input(sharedfile, "sharedfile"); + lookup = input.getSharedRAbundVectors(); + string lastLabel = lookup[0]->getLabel(); + + if (label == "") { label = lastLabel; return 0; } + + //if the users enters label "0.06" and there is no "0.06" in their file use the next lowest label. + set labels; labels.insert(label); + set processedLabels; + set userLabels = labels; + + //as long as you are not at the end of the file or done wih the lines you want + while((lookup[0] != NULL) && (userLabels.size() != 0)) { + if (m->control_pressed) { return 0; } + + if(labels.count(lookup[0]->getLabel()) == 1){ + processedLabels.insert(lookup[0]->getLabel()); + userLabels.erase(lookup[0]->getLabel()); + break; + } + + if ((m->anyLabelsToProcess(lookup[0]->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) { + string saveLabel = lookup[0]->getLabel(); + + for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } + lookup = input.getSharedRAbundVectors(lastLabel); + + processedLabels.insert(lookup[0]->getLabel()); + userLabels.erase(lookup[0]->getLabel()); + + //restore real lastlabel to save below + lookup[0]->setLabel(saveLabel); + break; + } + + lastLabel = lookup[0]->getLabel(); + + //get next line to process + //prevent memory leak + for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } + lookup = input.getSharedRAbundVectors(); + } + + + if (m->control_pressed) { return 0; } + + //output error messages about any remaining user labels + set::iterator it; + bool needToRun = false; + for (it = userLabels.begin(); it != userLabels.end(); it++) { + m->mothurOut("Your file does not include the label " + *it); + if (processedLabels.count(lastLabel) != 1) { + m->mothurOut(". I will use " + lastLabel + "."); m->mothurOutEndLine(); + needToRun = true; + }else { + m->mothurOut(". Please refer to " + lastLabel + "."); m->mothurOutEndLine(); + } + } + + //run last label if you need to + if (needToRun == true) { + for (int i = 0; i < lookup.size(); i++) { if (lookup[i] != NULL) { delete lookup[i]; } } + lookup = input.getSharedRAbundVectors(lastLabel); + } + + return 0; + } + catch(exception& e) { + m->errorOut(e, "GetLineageCommand", "getShared"); + exit(1); + } +} + //********************************************************************************************************************** int GetLineageCommand::readName(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(namefile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(namefile)) + getOutputFileNameTag("name", namefile); + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(namefile)); + variables["[extension]"] = m->getExtension(namefile); + string outputFileName = getOutputFileName("name", variables); ofstream out; m->openOutputFile(outputFileName, out); @@ -612,7 +982,10 @@ int GetLineageCommand::readGroup(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(groupfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(groupfile)) + getOutputFileNameTag("group", groupfile); + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(groupfile)); + variables["[extension]"] = m->getExtension(groupfile); + string outputFileName = getOutputFileName("group", variables); ofstream out; m->openOutputFile(outputFileName, out); @@ -659,7 +1032,10 @@ int GetLineageCommand::readTax(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(taxfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(taxfile)) + getOutputFileNameTag("taxonomy", taxfile); + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(taxfile)); + variables["[extension]"] = m->getExtension(taxfile); + string outputFileName = getOutputFileName("taxonomy", variables); ofstream out; m->openOutputFile(outputFileName, out); @@ -691,15 +1067,17 @@ int GetLineageCommand::readTax(){ in >> name; //read from first column in >> tax; //read from second column + string noQuotesTax = m->removeQuotes(tax); + for (int j = 0; j < listOfTaxons.size(); j++) { - string newtax = tax; + string newtax = noQuotesTax; //if the users file contains confidence scores we want to ignore them when searching for the taxons, unless the taxon has them if (!taxonsHasConfidence[j]) { - int hasConfidences = tax.find_first_of('('); + int hasConfidences = noQuotesTax.find_first_of('('); if (hasConfidences != string::npos) { - newtax = tax; + newtax = noQuotesTax; m->removeConfidences(newtax); } @@ -712,7 +1090,7 @@ int GetLineageCommand::readTax(){ break; } }else{//if listOfTaxons[i] has them and you don't them remove taxons - int hasConfidences = tax.find_first_of('('); + int hasConfidences = noQuotesTax.find_first_of('('); if (hasConfidences == string::npos) { int pos = newtax.find(noConfidenceTaxons[j]); @@ -726,10 +1104,10 @@ int GetLineageCommand::readTax(){ }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('('); + string noNewTax = noQuotesTax; + int hasConfidences = noQuotesTax.find_first_of('('); if (hasConfidences != string::npos) { - noNewTax = tax; + noNewTax = noQuotesTax; m->removeConfidences(noNewTax); } @@ -800,23 +1178,185 @@ int GetLineageCommand::readTax(){ exit(1); } } +//********************************************************************************************************************** +int GetLineageCommand::readConsTax(){ + try { + string thisOutputDir = outputDir; + if (outputDir == "") { thisOutputDir += m->hasPath(constaxonomy); } + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(constaxonomy)); + variables["[extension]"] = m->getExtension(constaxonomy); + string outputFileName = getOutputFileName("constaxonomy", variables); + ofstream out; + m->openOutputFile(outputFileName, out); + + ifstream in; + m->openInputFile(constaxonomy, in); + string otuLabel, tax; + int numReps; + + //read headers + string headers = m->getline(in); + out << headers << endl; + + //bool wroteSomething = false; + vector taxonsHasConfidence; taxonsHasConfidence.resize(listOfTaxons.size(), false); + vector< vector< map > > searchTaxons; searchTaxons.resize(listOfTaxons.size()); + vector noConfidenceTaxons; noConfidenceTaxons.resize(listOfTaxons.size(), ""); + + for (int i = 0; i < listOfTaxons.size(); i++) { + noConfidenceTaxons[i] = listOfTaxons[i]; + int hasConPos = listOfTaxons[i].find_first_of('('); + if (hasConPos != string::npos) { + taxonsHasConfidence[i] = true; + searchTaxons[i] = getTaxons(listOfTaxons[i]); + noConfidenceTaxons[i] = listOfTaxons[i]; + m->removeConfidences(noConfidenceTaxons[i]); + } + } + + + while(!in.eof()){ + + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } + + in >> otuLabel; m->gobble(in); + in >> numReps; m->gobble(in); + in >> tax; m->gobble(in); + + string noQuotesTax = m->removeQuotes(tax); + + for (int j = 0; j < listOfTaxons.size(); j++) { + + string newtax = noQuotesTax; + + //if the users file contains confidence scores we want to ignore them when searching for the taxons, unless the taxon has them + if (!taxonsHasConfidence[j]) { + int hasConfidences = noQuotesTax.find_first_of('('); + if (hasConfidences != string::npos) { + newtax = noQuotesTax; + m->removeConfidences(newtax); + } + + int pos = newtax.find(noConfidenceTaxons[j]); + + if (pos != string::npos) { //this sequence contains the taxon the user wants + names.insert(otuLabel); + out << otuLabel << '\t' << numReps << '\t' << tax << endl; + //since you belong to at least one of the taxons we want you are included so no need to search for other + break; + } + }else{//if listOfTaxons[i] has them and you don't them remove taxons + int hasConfidences = noQuotesTax.find_first_of('('); + if (hasConfidences == string::npos) { + + int pos = newtax.find(noConfidenceTaxons[j]); + + if (pos != string::npos) { //this sequence contains the taxon the user wants + names.insert(otuLabel); + out << otuLabel << '\t' << numReps << '\t' << tax << endl; + //since you belong to at least one of the taxons we want you are included so no need to search for other + break; + } + }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 = noQuotesTax; + int hasConfidences = noQuotesTax.find_first_of('('); + if (hasConfidences != string::npos) { + noNewTax = noQuotesTax; + m->removeConfidences(noNewTax); + } + + int pos = noNewTax.find(noConfidenceTaxons[j]); + + if (pos != string::npos) { //if yes, then are the confidences okay + + bool good = true; + 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[j][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[j].size()) && ((i+spot) < usersTaxon.size())) { + if (usersTaxon[i+spot].begin()->first != searchTaxons[j][spot].begin()->first) { goodspot = false; break; } + else { spot++; } + } + + if (goodspot) { break; } + } + } + + for (int i = 0; i < searchTaxons[j].size(); i++) { + + if ((i+index) < usersTaxon.size()) { //just in case, should never be false + if (usersTaxon[i+index].begin()->second < searchTaxons[j][i].begin()->second) { //is the users cutoff less than the search taxons + good = false; + break; + } + }else { + good = false; + break; + } + } + + //passed the test so add you + if (good) { + names.insert(otuLabel); + out << otuLabel << '\t' << numReps << '\t' << tax << endl; + break; + } + } + } + } + + } + } + in.close(); + out.close(); + + if (names.size() == 0) { m->mothurOut("Your taxonomy file does not contain any OTUs from " + taxons + "."); m->mothurOutEndLine(); } + outputNames.push_back(outputFileName); outputTypes["constaxonomy"].push_back(outputFileName); + + return 0; + + } + catch(exception& e) { + m->errorOut(e, "GetLineageCommand", "readConsTax"); + exit(1); + } +} /**************************************************************************************************/ vector< map > GetLineageCommand::getTaxons(string tax) { try { - + vector< map > t; string taxon = ""; int taxLength = tax.length(); + for(int i=0;iisNumeric1(confidenceScore)) { //its a confidence + newtaxon = taxon.substr(0, openParen); //rip off confidence + confidence = taxon.substr((openParen+1), (closeParen-openParen-1)); + }else { //its part of the taxon + newtaxon = taxon; + confidence = "0"; + } }else{ newtaxon = taxon; confidence = "0"; @@ -826,12 +1366,13 @@ vector< map > GetLineageCommand::getTaxons(string tax) { map temp; temp[newtaxon] = con; + t.push_back(temp); - taxon = ""; } else{ taxon += tax[i]; + } } @@ -848,7 +1389,11 @@ int GetLineageCommand::readAlign(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(alignfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(alignfile)) + getOutputFileNameTag("alignreport"); + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(alignfile)); + variables["[extension]"] = m->getExtension(alignfile); + string outputFileName = getOutputFileName("alignreport", variables); + ofstream out; m->openOutputFile(outputFileName, out);