X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=getseqscommand.cpp;h=7f0f3ddb51da8496c292367b5dfc728b3915d53f;hp=ccabafb6d19c008eb6957a35e79b5cd0623021d0;hb=499f4ac6e321f9f03d4c3aa25c3b6880892c8b83;hpb=f687723a8357916e86a05116978e6869b039ce36 diff --git a/getseqscommand.cpp b/getseqscommand.cpp index ccabafb..7f0f3dd 100644 --- a/getseqscommand.cpp +++ b/getseqscommand.cpp @@ -10,22 +10,24 @@ #include "getseqscommand.h" #include "sequence.hpp" #include "listvector.hpp" +#include "counttable.h" //********************************************************************************************************************** vector GetSeqsCommand::setParameters(){ try { - CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pfasta); - CommandParameter pname("name", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pname); - CommandParameter pgroup("group", "InputTypes", "", "", "none", "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,false); parameters.push_back(ptaxonomy); - CommandParameter palignreport("alignreport", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(palignreport); - CommandParameter pqfile("qfile", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pqfile); - CommandParameter paccnos("accnos", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(paccnos); - 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 paccnos2("accnos2", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(paccnos2); + 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 ptaxonomy("taxonomy", "InputTypes", "", "", "none", "FNGLT", "none","taxonomy",false,false,true); parameters.push_back(ptaxonomy); + CommandParameter palignreport("alignreport", "InputTypes", "", "", "none", "FNGLT", "none","alignreport",false,false); parameters.push_back(palignreport); + CommandParameter pqfile("qfile", "InputTypes", "", "", "none", "FNGLT", "none","qfile",false,false); parameters.push_back(pqfile); + CommandParameter paccnos("accnos", "InputTypes", "", "", "none", "none", "none","",false,true,true); parameters.push_back(paccnos); + 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 paccnos2("accnos2", "InputTypes", "", "", "none", "none", "none","",false,false); parameters.push_back(paccnos2); vector myArray; for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); } @@ -40,10 +42,10 @@ vector GetSeqsCommand::setParameters(){ string GetSeqsCommand::getHelpString(){ try { string helpString = ""; - helpString += "The get.seqs command reads an .accnos file and any of the following file types: fasta, name, group, list, taxonomy, quality or alignreport file.\n"; + helpString += "The get.seqs command reads an .accnos file and any of the following file types: fasta, name, group, count, list, taxonomy, quality or alignreport file.\n"; helpString += "It outputs a file containing only the sequences in the .accnos file.\n"; helpString += "The get.seqs command parameters are accnos, fasta, name, group, list, taxonomy, qfile, alignreport and dups. You must provide accnos unless you have a valid current accnos file, and at least one of the other parameters.\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 dups parameter allows you to add the entire line from a name file if you add any name from the line. default=true. \n"; helpString += "The get.seqs command should be in the following format: get.seqs(accnos=yourAccnos, fasta=yourFasta).\n"; helpString += "Example get.seqs(accnos=amazon.accnos, fasta=amazon.fasta).\n"; helpString += "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n"; @@ -68,6 +70,7 @@ GetSeqsCommand::GetSeqsCommand(){ outputTypes["alignreport"] = tempOutNames; outputTypes["list"] = tempOutNames; outputTypes["qfile"] = tempOutNames; + outputTypes["count"] = tempOutNames; outputTypes["accnosreport"] = tempOutNames; } catch(exception& e) { @@ -76,31 +79,27 @@ GetSeqsCommand::GetSeqsCommand(){ } } //********************************************************************************************************************** -string GetSeqsCommand::getOutputFileNameTag(string type, string inputName=""){ - try { - string outputFileName = ""; - map >::iterator it; +string GetSeqsCommand::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 == "group") { outputFileName = "pick" + m->getExtension(inputName); } - else if (type == "list") { outputFileName = "pick" + m->getExtension(inputName); } - else if (type == "qfile") { outputFileName = "pick" + m->getExtension(inputName); } - else if (type == "accnosreport"){ outputFileName = "accnos.report"; } - 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, "GetSeqsCommand", "getOutputFileNameTag"); - exit(1); - } + if (type == "fasta") { pattern = "[filename],pick,[extension]"; } + else if (type == "taxonomy") { 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],[distance],pick,[extension]"; } + else if (type == "qfile") { pattern = "[filename],pick,[extension]"; } + else if (type == "accnosreport") { pattern = "[filename],pick.accnos.report"; } + 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, "GetSeqsCommand", "getOutputPattern"); + exit(1); + } } //********************************************************************************************************************** GetSeqsCommand::GetSeqsCommand(string option) { @@ -135,6 +134,7 @@ GetSeqsCommand::GetSeqsCommand(string option) { outputTypes["list"] = tempOutNames; outputTypes["qfile"] = tempOutNames; outputTypes["accnosreport"] = tempOutNames; + outputTypes["count"] = 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 = ""; } @@ -215,6 +215,14 @@ GetSeqsCommand::GetSeqsCommand(string option) { //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["qfile"] = 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; } + } } @@ -270,17 +278,32 @@ GetSeqsCommand::GetSeqsCommand(string option) { if (accnosfile2 == "not open") { abort = true; } else if (accnosfile2 == "not found") { accnosfile2 = ""; } + countfile = validParameter.validFile(parameters, "count", true); + if (countfile == "not open") { countfile = ""; abort = true; } + else if (countfile == "not found") { countfile = ""; } + else { m->setCountTableFile(countfile); } + + 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; + } + string usedDups = "true"; string temp = validParameter.validFile(parameters, "dups", false); if (temp == "not found") { temp = "true"; usedDups = ""; } dups = m->isTrue(temp); - if ((fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == "") && (taxfile == "") && (qualfile == "") && (accnosfile2 == "")) { m->mothurOut("You must provide one of the following: fasta, name, group, alignreport, taxonomy, quality or listfile."); m->mothurOutEndLine(); abort = true; } - - if ((namefile == "") && ((fastafile != "") || (taxfile != ""))){ - vector files; files.push_back(fastafile); files.push_back(taxfile); - parser.getNameFile(files); - } + if ((fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == "") && (taxfile == "") && (qualfile == "") && (accnosfile2 == "") && (countfile == "")) { m->mothurOut("You must provide one of the following: fasta, name, group, count, alignreport, taxonomy, quality or listfile."); m->mothurOutEndLine(); abort = true; } + + if (countfile == "") { + if ((namefile == "") && ((fastafile != "") || (taxfile != ""))){ + vector files; files.push_back(fastafile); files.push_back(taxfile); + parser.getNameFile(files); + } + } } } @@ -300,11 +323,18 @@ int GetSeqsCommand::execute(){ names = m->readAccnos(accnosfile); if (m->control_pressed) { return 0; } + + if (countfile != "") { + if ((fastafile != "") || (listfile != "") || (taxfile != "")) { + m->mothurOut("\n[NOTE]: The count file should contain only unique names, so mothur assumes your fasta, list and taxonomy files also contain only uniques.\n\n"); + } + } //read through the correct file and output lines you want to keep if (namefile != "") { readName(); } if (fastafile != "") { readFasta(); } if (groupfile != "") { readGroup(); } + if (countfile != "") { readCount(); } if (alignfile != "") { readAlign(); } if (listfile != "") { readList(); } if (taxfile != "") { readTax(); } @@ -354,6 +384,10 @@ int GetSeqsCommand::execute(){ if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setQualFile(current); } } + itTypes = outputTypes.find("count"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setCountTableFile(current); } + } } return 0; @@ -370,7 +404,10 @@ int GetSeqsCommand::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); @@ -390,7 +427,14 @@ int GetSeqsCommand::readFasta(){ Sequence currSeq(in); name = currSeq.getName(); + + if (!dups) {//adjust name if needed + map::iterator it = uniqueMap.find(name); + if (it != uniqueMap.end()) { currSeq.setName(it->second); } + } + name = currSeq.getName(); + if (name != "") { //if this name is in the accnos file if (names.count(name) != 0) { @@ -426,7 +470,10 @@ int GetSeqsCommand::readQual(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(qualfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(qualfile)) + getOutputFileNameTag("qfile", qualfile); + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(qualfile)); + variables["[extension]"] = m->getExtension(qualfile); + string outputFileName = getOutputFileName("qfile", variables); ofstream out; m->openOutputFile(outputFileName, out); @@ -445,13 +492,18 @@ int GetSeqsCommand::readQual(){ string name = ""; string scores = ""; - in >> name; + in >> name; + + if (!dups) {//adjust name if needed + map::iterator it = uniqueMap.find(name); + if (it != uniqueMap.end()) { name = it->second; } + } if (name.length() != 0) { saveName = name.substr(1); while (!in.eof()) { char c = in.get(); - if (c == 10 || c == 13){ break; } + if (c == 10 || c == 13 || c == -1){ break; } else { name += c; } } m->gobble(in); @@ -494,14 +546,75 @@ int GetSeqsCommand::readQual(){ } } //********************************************************************************************************************** -int GetSeqsCommand::readList(){ +int GetSeqsCommand::readCount(){ try { string thisOutputDir = outputDir; - if (outputDir == "") { thisOutputDir += m->hasPath(listfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(listfile)) + getOutputFileNameTag("list", listfile); + if (outputDir == "") { thisOutputDir += m->hasPath(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); + ifstream in; + m->openInputFile(countfile, in); + + bool wroteSomething = false; + int selectedCount = 0; + + string headers = m->getline(in); m->gobble(in); + out << headers << endl; + + string name, rest; int thisTotal; + while (!in.eof()) { + + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } + + in >> name; m->gobble(in); + in >> thisTotal; m->gobble(in); + rest = m->getline(in); m->gobble(in); + if (m->debug) { m->mothurOut("[DEBUG]: " + name + '\t' + rest + "\n"); } + + if (names.count(name) != 0) { + out << name << '\t' << thisTotal << '\t' << rest << endl; + wroteSomething = true; + selectedCount+= thisTotal; + } + } + in.close(); + out.close(); + + //check for groups that have been eliminated + CountTable ct; + if (ct.testGroups(outputFileName)) { + ct.readTable(outputFileName, true, false); + ct.printTable(outputFileName); + } + + if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); } + outputTypes["count"].push_back(outputFileName); outputNames.push_back(outputFileName); + + m->mothurOut("Selected " + toString(selectedCount) + " sequences from your count file."); m->mothurOutEndLine(); + + return 0; + } + catch(exception& e) { + m->errorOut(e, "GetSeqsCommand", "readCount"); + exit(1); + } +} + +//********************************************************************************************************************** +int GetSeqsCommand::readList(){ + try { + string thisOutputDir = outputDir; + if (outputDir == "") { thisOutputDir += m->hasPath(listfile); } + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(listfile)); + variables["[extension]"] = m->getExtension(listfile); + ifstream in; m->openInputFile(listfile, in); @@ -513,8 +626,6 @@ int GetSeqsCommand::readList(){ while(!in.eof()){ selectedCount = 0; - - if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } //read in list vector ListVector list(in); @@ -522,45 +633,57 @@ int GetSeqsCommand::readList(){ //make a new list vector ListVector newList; newList.setLabel(list.getLabel()); + + variables["[distance]"] = list.getLabel(); + string outputFileName = getOutputFileName("list", variables); + + ofstream out; + m->openOutputFile(outputFileName, out); + outputTypes["list"].push_back(outputFileName); outputNames.push_back(outputFileName); + + vector binLabels = list.getLabels(); + vector newBinLabels; + + if (m->control_pressed) { in.close(); out.close(); return 0; } //for each bin for (int i = 0; i < list.getNumBins(); i++) { //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 i = 0; i < bnames.size(); i++) { + string name = bnames[i]; //if that name is in the .accnos file, add it if (names.count(name) != 0) { newNames += name + ","; selectedCount++; if (m->debug) { sanity["list"].insert(name); } } } - //get last name - if (names.count(binnames) != 0) { newNames += binnames + ","; selectedCount++; if (m->debug) { sanity["list"].insert(binnames); } } - //if there are names in this bin add to new list if (newNames != "") { newNames = newNames.substr(0, newNames.length()-1); //rip off extra comma - newList.push_back(newNames); + newList.push_back(newNames); + newBinLabels.push_back(binLabels[i]); } } //print new listvector if (newList.getNumBins() != 0) { wroteSomething = true; + newList.setLabels(newBinLabels); + newList.printHeaders(out); newList.print(out); } m->gobble(in); + out.close(); } in.close(); - out.close(); + if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); } - outputNames.push_back(outputFileName); outputTypes["list"].push_back(outputFileName); m->mothurOut("Selected " + toString(selectedCount) + " sequences from your list file."); m->mothurOutEndLine(); @@ -577,7 +700,10 @@ int GetSeqsCommand::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); @@ -596,7 +722,7 @@ int GetSeqsCommand::readName(){ if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } - in >> firstCol; + in >> firstCol; m->gobble(in); in >> secondCol; string hold = ""; @@ -620,6 +746,7 @@ int GetSeqsCommand::readName(){ selectedCount += parsedNames.size(); if (m->debug) { sanity["name"].insert(firstCol); } }else { + selectedCount += validSecond.size(); //if the name in the first column is in the set then print it and any other names in second column also in set @@ -638,12 +765,15 @@ int GetSeqsCommand::readName(){ //make first name in set you come to first column and then add the remaining names to second column }else { + //you want part of this row if (validSecond.size() != 0) { wroteSomething = true; out << validSecond[0] << '\t'; + //we are changing the unique name in the fasta file + uniqueMap[firstCol] = validSecond[0]; //you know you have at least one valid second since first column is valid for (int i = 0; i < validSecond.size()-1; i++) { out << validSecond[i] << ','; } @@ -677,7 +807,10 @@ int GetSeqsCommand::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); @@ -698,6 +831,7 @@ int GetSeqsCommand::readGroup(){ in >> name; //read from first column in >> group; //read from second column + //if this name is in the accnos file if (names.count(name) != 0) { @@ -733,7 +867,10 @@ int GetSeqsCommand::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); @@ -752,6 +889,11 @@ int GetSeqsCommand::readTax(){ in >> name; //read from first column in >> tax; //read from second column + + if (!dups) {//adjust name if needed + map::iterator it = uniqueMap.find(name); + if (it != uniqueMap.end()) { name = it->second; } + } //if this name is in the accnos file if (names.count(name) != 0) { @@ -787,7 +929,9 @@ int GetSeqsCommand::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)); + string outputFileName = getOutputFileName("alignreport", variables); ofstream out; m->openOutputFile(outputFileName, out); @@ -812,6 +956,11 @@ int GetSeqsCommand::readAlign(){ in >> name; //read from first column + + if (!dups) {//adjust name if needed + map::iterator it = uniqueMap.find(name); + if (it != uniqueMap.end()) { name = it->second; } + } //if this name is in the accnos file if (names.count(name) != 0) { @@ -953,7 +1102,10 @@ int GetSeqsCommand::compareAccnos(){ string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(accnosfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(accnosfile)) + getOutputFileNameTag("accnosreport"); + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(accnosfile)); + string outputFileName = getOutputFileName("accnosreport", variables); + ofstream out; m->openOutputFile(outputFileName, out);