X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=getseqscommand.cpp;h=7f0f3ddb51da8496c292367b5dfc728b3915d53f;hp=779ea912ebebbe58ec22e65723899c4ea566b85f;hb=499f4ac6e321f9f03d4c3aa25c3b6880892c8b83;hpb=deba0af0ccdcb6005ed5b2b82649b137c63fbdf7 diff --git a/getseqscommand.cpp b/getseqscommand.cpp index 779ea91..7f0f3dd 100644 --- a/getseqscommand.cpp +++ b/getseqscommand.cpp @@ -45,7 +45,7 @@ string GetSeqsCommand::getHelpString(){ 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"; @@ -88,7 +88,7 @@ string GetSeqsCommand::getOutputPattern(string type) { 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]"; } + 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"; } @@ -427,7 +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) { @@ -485,13 +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); @@ -577,7 +589,7 @@ int GetSeqsCommand::readCount(){ //check for groups that have been eliminated CountTable ct; if (ct.testGroups(outputFileName)) { - ct.readTable(outputFileName); + ct.readTable(outputFileName, true, false); ct.printTable(outputFileName); } @@ -602,9 +614,6 @@ int GetSeqsCommand::readList(){ 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); ifstream in; m->openInputFile(listfile, in); @@ -617,8 +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); @@ -626,6 +633,18 @@ 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++) { @@ -645,23 +664,26 @@ int GetSeqsCommand::readList(){ //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(); @@ -700,7 +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 = ""; @@ -724,6 +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 @@ -742,12 +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] << ','; } @@ -805,6 +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) { @@ -862,6 +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) { @@ -924,6 +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) {