X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=sortseqscommand.cpp;h=d844452e1f72376535bc6edb57c36d3e2c808474;hp=ee7bf7304c0a952fb29064aa87e0cf3892b98808;hb=b206f634aae1b4ce13978d203247fb64757d5482;hpb=49d2b7459c5027557564b21e9487dadafbbbdc96 diff --git a/sortseqscommand.cpp b/sortseqscommand.cpp index ee7bf73..d844452 100644 --- a/sortseqscommand.cpp +++ b/sortseqscommand.cpp @@ -13,16 +13,17 @@ //********************************************************************************************************************** vector SortSeqsCommand::setParameters(){ try { - CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pfasta); - CommandParameter pflow("flow", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pflow); - 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 ptaxonomy("taxonomy", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(ptaxonomy); - CommandParameter pqfile("qfile", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pqfile); - CommandParameter plarge("large", "Boolean", "", "F", "", "", "",false,false); parameters.push_back(plarge); - CommandParameter paccnos("accnos", "InputTypes", "", "", "none", "none", "none",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", "FNGLT", "none","fasta",false,false); parameters.push_back(pfasta); + CommandParameter pflow("flow", "InputTypes", "", "", "none", "FNGLT", "none","flow",false,false); parameters.push_back(pflow); + CommandParameter pname("name", "InputTypes", "", "", "NameCount", "FNGLT", "none","name",false,false); parameters.push_back(pname); + CommandParameter pcount("count", "InputTypes", "", "", "NameCount-CountGroup", "FNGLT", "none","count",false,false); parameters.push_back(pcount); + CommandParameter pgroup("group", "InputTypes", "", "", "CountGroup", "FNGLT", "none","group",false,false); parameters.push_back(pgroup); + CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "none", "FNGLT", "none","taxonomy",false,false); parameters.push_back(ptaxonomy); + CommandParameter pqfile("qfile", "InputTypes", "", "", "none", "FNGLT", "none","qfile",false,false); parameters.push_back(pqfile); + CommandParameter plarge("large", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(plarge); + CommandParameter paccnos("accnos", "InputTypes", "", "", "none", "none", "none","",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 +38,8 @@ vector SortSeqsCommand::setParameters(){ string SortSeqsCommand::getHelpString(){ try { string helpString = ""; - helpString += "The sort.seqs command puts the sequences in the same order for the following file types: accnos fasta, name, group, taxonomy, flow or quality file.\n"; - helpString += "The sort.seqs command parameters are accnos, fasta, name, group, taxonomy, flow, qfile and large.\n"; + helpString += "The sort.seqs command puts the sequences in the same order for the following file types: accnos fasta, name, group, count, taxonomy, flow or quality file.\n"; + helpString += "The sort.seqs command parameters are accnos, fasta, name, group, count, taxonomy, flow, qfile and large.\n"; helpString += "The accnos file allows you to specify the order you want the files in. If none is provided, mothur will use the order of the first file it reads.\n"; helpString += "The large parameters is used to indicate your files are too large to fit in RAM.\n"; helpString += "The sort.seqs command should be in the following format: sort.seqs(fasta=yourFasta).\n"; @@ -51,33 +52,27 @@ string SortSeqsCommand::getHelpString(){ exit(1); } } - //********************************************************************************************************************** -string SortSeqsCommand::getOutputFileNameTag(string type, string inputName=""){ - try { - string outputFileName = ""; - map >::iterator it; +string SortSeqsCommand::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 = "sorted" + m->getExtension(inputName); } - else if (type == "taxonomy") { outputFileName = "sorted" + m->getExtension(inputName); } - else if (type == "name") { outputFileName = "sorted" + m->getExtension(inputName); } - else if (type == "group") { outputFileName = "sorted" + m->getExtension(inputName); } - else if (type == "flow") { outputFileName = "sorted" + m->getExtension(inputName); } - else if (type == "qfile") { outputFileName = "sorted" + m->getExtension(inputName); } - 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, "SortSeqsCommand", "getOutputFileNameTag"); - exit(1); - } + if (type == "fasta") { pattern = "[filename],sorted,[extension]"; } + else if (type == "taxonomy") { pattern = "[filename],sorted,[extension]"; } + else if (type == "name") { pattern = "[filename],sorted,[extension]"; } + else if (type == "group") { pattern = "[filename],sorted,[extension]"; } + else if (type == "count") { pattern = "[filename],sorted,[extension]"; } + else if (type == "flow") { pattern = "[filename],sorted,[extension]"; } + else if (type == "qfile") { pattern = "[filename],sorted,[extension]"; } + else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; } + + return pattern; + } + catch(exception& e) { + m->errorOut(e, "SortSeqsCommand", "getOutputPattern"); + exit(1); + } } - //********************************************************************************************************************** SortSeqsCommand::SortSeqsCommand(){ try { @@ -87,6 +82,7 @@ SortSeqsCommand::SortSeqsCommand(){ outputTypes["fasta"] = tempOutNames; outputTypes["taxonomy"] = tempOutNames; outputTypes["name"] = tempOutNames; + outputTypes["count"] = tempOutNames; outputTypes["group"] = tempOutNames; outputTypes["qfile"] = tempOutNames; outputTypes["flow"] = tempOutNames; @@ -127,6 +123,7 @@ SortSeqsCommand::SortSeqsCommand(string option) { outputTypes["group"] = tempOutNames; outputTypes["qfile"] = tempOutNames; outputTypes["flow"] = 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 = ""; } @@ -191,6 +188,14 @@ SortSeqsCommand::SortSeqsCommand(string option) { //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["flow"] = 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; } + } } @@ -229,16 +234,31 @@ SortSeqsCommand::SortSeqsCommand(string option) { if (qualfile == "not open") { abort = true; } else if (qualfile == "not found") { qualfile = ""; } else { m->setQualFile(qualfile); } + + 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 temp = validParameter.validFile(parameters, "large", false); if (temp == "not found") { temp = "f"; } large = m->isTrue(temp); - if ((fastafile == "") && (namefile == "") && (groupfile == "") && (taxfile == "") && (flowfile == "") && (qualfile == "")) { m->mothurOut("You must provide at least one of the following: fasta, name, group, taxonomy, flow or quality."); m->mothurOutEndLine(); abort = true; } + if ((fastafile == "") && (namefile == "") && (countfile == "") && (groupfile == "") && (taxfile == "") && (flowfile == "") && (qualfile == "")) { m->mothurOut("You must provide at least one of the following: fasta, name, group, count, taxonomy, flow or quality."); m->mothurOutEndLine(); abort = true; } - if ((fastafile != "") && (namefile == "")) { - vector files; files.push_back(fastafile); - parser.getNameFile(files); - } + if (countfile == "") { + if ((fastafile != "") && (namefile == "")) { + vector files; files.push_back(fastafile); + parser.getNameFile(files); + } + } } } @@ -267,6 +287,7 @@ int SortSeqsCommand::execute(){ if (qualfile != "") { readQual(); } if (namefile != "") { readName(); } if (groupfile != "") { readGroup(); } + if (countfile != "") { readCount(); } if (taxfile != "") { readTax(); } if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } @@ -308,7 +329,12 @@ int SortSeqsCommand::execute(){ itTypes = outputTypes.find("flow"); if (itTypes != outputTypes.end()) { if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setFlowFile(current); } - } + } + + itTypes = outputTypes.find("count"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setCountTableFile(current); } + } } return 0; @@ -325,7 +351,10 @@ int SortSeqsCommand::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); outputTypes["fasta"].push_back(outputFileName); outputNames.push_back(outputFileName); ofstream out; @@ -498,7 +527,10 @@ int SortSeqsCommand::readFlow(){ try { string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir += m->hasPath(flowfile); } - string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(flowfile)) + getOutputFileNameTag("flow", flowfile); + map variables; + variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(flowfile)); + variables["[extension]"] = m->getExtension(flowfile); + string outputFileName = getOutputFileName("flow", variables); outputTypes["flow"].push_back(outputFileName); outputNames.push_back(outputFileName); ofstream out; @@ -676,7 +708,10 @@ int SortSeqsCommand::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); outputTypes["qfile"].push_back(outputFileName); outputNames.push_back(outputFileName); ofstream out; @@ -856,7 +891,10 @@ int SortSeqsCommand::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); outputTypes["name"].push_back(outputFileName); outputNames.push_back(outputFileName); ofstream out; @@ -927,13 +965,100 @@ int SortSeqsCommand::readName(){ exit(1); } } - +//********************************************************************************************************************** +int SortSeqsCommand::readCount(){ + try { + string thisOutputDir = outputDir; + 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); + outputTypes["count"].push_back(outputFileName); outputNames.push_back(outputFileName); + + ofstream out; + m->openOutputFile(outputFileName, out); + + ifstream in; + m->openInputFile(countfile, in); + string firstCol, rest; + + if (names.size() != 0) {//this is not the first file we are reading so we need to use the order we already have + + vector seqs; seqs.resize(names.size(), ""); + + string headers = m->getline(in); m->gobble(in); + + while(!in.eof()){ + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } + + in >> firstCol; m->gobble(in); + rest = m->getline(in); m->gobble(in); + + if (firstCol != "") { + map::iterator it = names.find(firstCol); + if (it != names.end()) { //we found it, so put it in the vector in the right place. + seqs[it->second] = firstCol + '\t' + rest; + }else { //if we cant find it then add it to the end + names[firstCol] = seqs.size(); + seqs.push_back((firstCol + '\t' + rest)); + m->mothurOut(firstCol + " was not in the contained the file which determined the order, adding it to the end.\n"); + } + } + } + in.close(); + + int count = 0; + out << headers << endl; + for (int i = 0; i < seqs.size(); i++) { + if (seqs[i] != "") { out << seqs[i] << endl; count++; } + } + out.close(); + + m->mothurOut("Ordered " + toString(count) + " sequences from " + countfile + ".\n"); + + }else { //read in file to fill names + int count = 0; + + string headers = m->getline(in); m->gobble(in); + out << headers << endl; + + while(!in.eof()){ + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } + + in >> firstCol; m->gobble(in); + rest = m->getline(in); m->gobble(in); + + if (firstCol != "") { + //if this name is in the accnos file + names[firstCol] = count; + count++; + out << firstCol << '\t' << rest << endl; + } + m->gobble(in); + } + in.close(); + out.close(); + + m->mothurOut("\nUsing " + countfile + " to determine the order. It contains " + toString(count) + " representative sequences.\n"); + } + + return 0; + } + catch(exception& e) { + m->errorOut(e, "SortSeqsCommand", "readCount"); + exit(1); + } +} //********************************************************************************************************************** int SortSeqsCommand::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); outputTypes["group"].push_back(outputFileName); outputNames.push_back(outputFileName); ofstream out; @@ -1009,7 +1134,11 @@ int SortSeqsCommand::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); + outputTypes["taxonomy"].push_back(outputFileName); outputNames.push_back(outputFileName); ofstream out;