5 * Created by Sarah Westcott on 7/8/09.
6 * Copyright 2009 Schloss Lab UMASS Amherst. All rights reserved.
10 #include "getseqscommand.h"
11 #include "sequence.hpp"
12 #include "listvector.hpp"
13 #include "counttable.h"
15 //**********************************************************************************************************************
16 vector<string> GetSeqsCommand::setParameters(){
18 CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "FNGLT", "none","fasta",false,false,true); parameters.push_back(pfasta);
19 CommandParameter pname("name", "InputTypes", "", "", "NameCount", "FNGLT", "none","name",false,false,true); parameters.push_back(pname);
20 CommandParameter pcount("count", "InputTypes", "", "", "NameCount-CountGroup", "FNGLT", "none","count",false,false,true); parameters.push_back(pcount);
21 CommandParameter pgroup("group", "InputTypes", "", "", "CountGroup", "FNGLT", "none","group",false,false,true); parameters.push_back(pgroup);
22 CommandParameter plist("list", "InputTypes", "", "", "none", "FNGLT", "none","list",false,false,true); parameters.push_back(plist);
23 CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "none", "FNGLT", "none","taxonomy",false,false,true); parameters.push_back(ptaxonomy);
24 CommandParameter palignreport("alignreport", "InputTypes", "", "", "none", "FNGLT", "none","alignreport",false,false); parameters.push_back(palignreport);
25 CommandParameter pqfile("qfile", "InputTypes", "", "", "none", "FNGLT", "none","qfile",false,false); parameters.push_back(pqfile);
26 CommandParameter paccnos("accnos", "InputTypes", "", "", "none", "none", "none","",false,true,true); parameters.push_back(paccnos);
27 CommandParameter pdups("dups", "Boolean", "", "T", "", "", "","",false,false); parameters.push_back(pdups);
28 CommandParameter pinputdir("inputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(pinputdir);
29 CommandParameter poutputdir("outputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(poutputdir);
30 CommandParameter paccnos2("accnos2", "InputTypes", "", "", "none", "none", "none","",false,false); parameters.push_back(paccnos2);
32 vector<string> myArray;
33 for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); }
37 m->errorOut(e, "GetSeqsCommand", "setParameters");
41 //**********************************************************************************************************************
42 string GetSeqsCommand::getHelpString(){
44 string helpString = "";
45 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";
46 helpString += "It outputs a file containing only the sequences in the .accnos file.\n";
47 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";
48 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";
49 helpString += "The get.seqs command should be in the following format: get.seqs(accnos=yourAccnos, fasta=yourFasta).\n";
50 helpString += "Example get.seqs(accnos=amazon.accnos, fasta=amazon.fasta).\n";
51 helpString += "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n";
55 m->errorOut(e, "GetSeqsCommand", "getHelpString");
60 //**********************************************************************************************************************
61 GetSeqsCommand::GetSeqsCommand(){
63 abort = true; calledHelp = true;
65 vector<string> tempOutNames;
66 outputTypes["fasta"] = tempOutNames;
67 outputTypes["taxonomy"] = tempOutNames;
68 outputTypes["name"] = tempOutNames;
69 outputTypes["group"] = tempOutNames;
70 outputTypes["alignreport"] = tempOutNames;
71 outputTypes["list"] = tempOutNames;
72 outputTypes["qfile"] = tempOutNames;
73 outputTypes["count"] = tempOutNames;
74 outputTypes["accnosreport"] = tempOutNames;
77 m->errorOut(e, "GetSeqsCommand", "GetSeqsCommand");
81 //**********************************************************************************************************************
82 string GetSeqsCommand::getOutputPattern(string type) {
86 if (type == "fasta") { pattern = "[filename],pick,[extension]"; }
87 else if (type == "taxonomy") { pattern = "[filename],pick,[extension]"; }
88 else if (type == "name") { pattern = "[filename],pick,[extension]"; }
89 else if (type == "group") { pattern = "[filename],pick,[extension]"; }
90 else if (type == "count") { pattern = "[filename],pick,[extension]"; }
91 else if (type == "list") { pattern = "[filename],pick,[extension]"; }
92 else if (type == "qfile") { pattern = "[filename],pick,[extension]"; }
93 else if (type == "accnosreport") { pattern = "[filename],pick.accnos.report"; }
94 else if (type == "alignreport") { pattern = "[filename],pick.align.report"; }
95 else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; }
100 m->errorOut(e, "GetSeqsCommand", "getOutputPattern");
104 //**********************************************************************************************************************
105 GetSeqsCommand::GetSeqsCommand(string option) {
107 abort = false; calledHelp = false;
109 //allow user to run help
110 if(option == "help") { help(); abort = true; calledHelp = true; }
111 else if(option == "citation") { citation(); abort = true; calledHelp = true;}
114 vector<string> myArray = setParameters();
116 OptionParser parser(option);
117 map<string,string> parameters = parser.getParameters();
119 ValidParameters validParameter;
120 map<string,string>::iterator it;
122 //check to make sure all parameters are valid for command
123 for (it = parameters.begin(); it != parameters.end(); it++) {
124 if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; }
127 //initialize outputTypes
128 vector<string> tempOutNames;
129 outputTypes["fasta"] = tempOutNames;
130 outputTypes["taxonomy"] = tempOutNames;
131 outputTypes["name"] = tempOutNames;
132 outputTypes["group"] = tempOutNames;
133 outputTypes["alignreport"] = tempOutNames;
134 outputTypes["list"] = tempOutNames;
135 outputTypes["qfile"] = tempOutNames;
136 outputTypes["accnosreport"] = tempOutNames;
137 outputTypes["count"] = tempOutNames;
139 //if the user changes the output directory command factory will send this info to us in the output parameter
140 outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){ outputDir = ""; }
142 //if the user changes the input directory command factory will send this info to us in the output parameter
143 string inputDir = validParameter.validFile(parameters, "inputdir", false);
144 if (inputDir == "not found"){ inputDir = ""; }
147 it = parameters.find("alignreport");
148 //user has given a template file
149 if(it != parameters.end()){
150 path = m->hasPath(it->second);
151 //if the user has not given a path then, add inputdir. else leave path alone.
152 if (path == "") { parameters["alignreport"] = inputDir + it->second; }
155 it = parameters.find("fasta");
156 //user has given a template file
157 if(it != parameters.end()){
158 path = m->hasPath(it->second);
159 //if the user has not given a path then, add inputdir. else leave path alone.
160 if (path == "") { parameters["fasta"] = inputDir + it->second; }
163 it = parameters.find("accnos");
164 //user has given a template file
165 if(it != parameters.end()){
166 path = m->hasPath(it->second);
167 //if the user has not given a path then, add inputdir. else leave path alone.
168 if (path == "") { parameters["accnos"] = inputDir + it->second; }
171 it = parameters.find("accnos2");
172 //user has given a template file
173 if(it != parameters.end()){
174 path = m->hasPath(it->second);
175 //if the user has not given a path then, add inputdir. else leave path alone.
176 if (path == "") { parameters["accnos2"] = inputDir + it->second; }
179 it = parameters.find("list");
180 //user has given a template file
181 if(it != parameters.end()){
182 path = m->hasPath(it->second);
183 //if the user has not given a path then, add inputdir. else leave path alone.
184 if (path == "") { parameters["list"] = inputDir + it->second; }
187 it = parameters.find("name");
188 //user has given a template file
189 if(it != parameters.end()){
190 path = m->hasPath(it->second);
191 //if the user has not given a path then, add inputdir. else leave path alone.
192 if (path == "") { parameters["name"] = inputDir + it->second; }
195 it = parameters.find("group");
196 //user has given a template file
197 if(it != parameters.end()){
198 path = m->hasPath(it->second);
199 //if the user has not given a path then, add inputdir. else leave path alone.
200 if (path == "") { parameters["group"] = inputDir + it->second; }
203 it = parameters.find("taxonomy");
204 //user has given a template file
205 if(it != parameters.end()){
206 path = m->hasPath(it->second);
207 //if the user has not given a path then, add inputdir. else leave path alone.
208 if (path == "") { parameters["taxonomy"] = inputDir + it->second; }
211 it = parameters.find("qfile");
212 //user has given a template file
213 if(it != parameters.end()){
214 path = m->hasPath(it->second);
215 //if the user has not given a path then, add inputdir. else leave path alone.
216 if (path == "") { parameters["qfile"] = inputDir + it->second; }
219 it = parameters.find("count");
220 //user has given a template file
221 if(it != parameters.end()){
222 path = m->hasPath(it->second);
223 //if the user has not given a path then, add inputdir. else leave path alone.
224 if (path == "") { parameters["count"] = inputDir + it->second; }
229 //check for required parameters
230 accnosfile = validParameter.validFile(parameters, "accnos", true);
231 if (accnosfile == "not open") { abort = true; }
232 else if (accnosfile == "not found") {
233 accnosfile = m->getAccnosFile();
234 if (accnosfile != "") { m->mothurOut("Using " + accnosfile + " as input file for the accnos parameter."); m->mothurOutEndLine(); }
236 m->mothurOut("You have no valid accnos file and accnos is required."); m->mothurOutEndLine();
239 }else { m->setAccnosFile(accnosfile); }
241 if (accnosfile2 == "not found") { accnosfile2 = ""; }
243 fastafile = validParameter.validFile(parameters, "fasta", true);
244 if (fastafile == "not open") { fastafile = ""; abort = true; }
245 else if (fastafile == "not found") { fastafile = ""; }
246 else { m->setFastaFile(fastafile); }
248 namefile = validParameter.validFile(parameters, "name", true);
249 if (namefile == "not open") { namefile = ""; abort = true; }
250 else if (namefile == "not found") { namefile = ""; }
251 else { m->setNameFile(namefile); }
253 groupfile = validParameter.validFile(parameters, "group", true);
254 if (groupfile == "not open") { abort = true; }
255 else if (groupfile == "not found") { groupfile = ""; }
256 else { m->setGroupFile(groupfile); }
258 alignfile = validParameter.validFile(parameters, "alignreport", true);
259 if (alignfile == "not open") { abort = true; }
260 else if (alignfile == "not found") { alignfile = ""; }
262 listfile = validParameter.validFile(parameters, "list", true);
263 if (listfile == "not open") { abort = true; }
264 else if (listfile == "not found") { listfile = ""; }
265 else { m->setListFile(listfile); }
267 taxfile = validParameter.validFile(parameters, "taxonomy", true);
268 if (taxfile == "not open") { taxfile = ""; abort = true; }
269 else if (taxfile == "not found") { taxfile = ""; }
270 else { m->setTaxonomyFile(taxfile); }
272 qualfile = validParameter.validFile(parameters, "qfile", true);
273 if (qualfile == "not open") { abort = true; }
274 else if (qualfile == "not found") { qualfile = ""; }
275 else { m->setQualFile(qualfile); }
277 accnosfile2 = validParameter.validFile(parameters, "accnos2", true);
278 if (accnosfile2 == "not open") { abort = true; }
279 else if (accnosfile2 == "not found") { accnosfile2 = ""; }
281 countfile = validParameter.validFile(parameters, "count", true);
282 if (countfile == "not open") { countfile = ""; abort = true; }
283 else if (countfile == "not found") { countfile = ""; }
284 else { m->setCountTableFile(countfile); }
286 if ((namefile != "") && (countfile != "")) {
287 m->mothurOut("[ERROR]: you may only use one of the following: name or count."); m->mothurOutEndLine(); abort = true;
290 if ((groupfile != "") && (countfile != "")) {
291 m->mothurOut("[ERROR]: you may only use one of the following: group or count."); m->mothurOutEndLine(); abort=true;
295 string usedDups = "true";
296 string temp = validParameter.validFile(parameters, "dups", false); if (temp == "not found") { temp = "true"; usedDups = ""; }
297 dups = m->isTrue(temp);
299 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; }
301 if (countfile == "") {
302 if ((namefile == "") && ((fastafile != "") || (taxfile != ""))){
303 vector<string> files; files.push_back(fastafile); files.push_back(taxfile);
304 parser.getNameFile(files);
310 catch(exception& e) {
311 m->errorOut(e, "GetSeqsCommand", "GetSeqsCommand");
315 //**********************************************************************************************************************
317 int GetSeqsCommand::execute(){
320 if (abort == true) { if (calledHelp) { return 0; } return 2; }
322 //get names you want to keep
323 names = m->readAccnos(accnosfile);
325 if (m->control_pressed) { return 0; }
327 if (countfile != "") {
328 if ((fastafile != "") || (listfile != "") || (taxfile != "")) {
329 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");
333 //read through the correct file and output lines you want to keep
334 if (namefile != "") { readName(); }
335 if (fastafile != "") { readFasta(); }
336 if (groupfile != "") { readGroup(); }
337 if (countfile != "") { readCount(); }
338 if (alignfile != "") { readAlign(); }
339 if (listfile != "") { readList(); }
340 if (taxfile != "") { readTax(); }
341 if (qualfile != "") { readQual(); }
342 if (accnosfile2 != "") { compareAccnos(); }
344 if (m->debug) { runSanityCheck(); }
346 if (m->control_pressed) { outputTypes.clear(); for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
349 if (outputNames.size() != 0) {
350 m->mothurOutEndLine();
351 m->mothurOut("Output File Names: "); m->mothurOutEndLine();
352 for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); }
353 m->mothurOutEndLine();
355 //set fasta file as new current fastafile
357 itTypes = outputTypes.find("fasta");
358 if (itTypes != outputTypes.end()) {
359 if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setFastaFile(current); }
362 itTypes = outputTypes.find("name");
363 if (itTypes != outputTypes.end()) {
364 if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setNameFile(current); }
367 itTypes = outputTypes.find("group");
368 if (itTypes != outputTypes.end()) {
369 if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setGroupFile(current); }
372 itTypes = outputTypes.find("list");
373 if (itTypes != outputTypes.end()) {
374 if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setListFile(current); }
377 itTypes = outputTypes.find("taxonomy");
378 if (itTypes != outputTypes.end()) {
379 if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setTaxonomyFile(current); }
382 itTypes = outputTypes.find("qfile");
383 if (itTypes != outputTypes.end()) {
384 if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setQualFile(current); }
387 itTypes = outputTypes.find("count");
388 if (itTypes != outputTypes.end()) {
389 if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setCountTableFile(current); }
396 catch(exception& e) {
397 m->errorOut(e, "GetSeqsCommand", "execute");
402 //**********************************************************************************************************************
403 int GetSeqsCommand::readFasta(){
405 string thisOutputDir = outputDir;
406 if (outputDir == "") { thisOutputDir += m->hasPath(fastafile); }
407 map<string, string> variables;
408 variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(fastafile));
409 variables["[extension]"] = m->getExtension(fastafile);
410 string outputFileName = getOutputFileName("fasta", variables);
412 m->openOutputFile(outputFileName, out);
416 m->openInputFile(fastafile, in);
419 bool wroteSomething = false;
420 int selectedCount = 0;
422 if (m->debug) { set<string> temp; sanity["fasta"] = temp; }
426 if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; }
428 Sequence currSeq(in);
429 name = currSeq.getName();
431 if (!dups) {//adjust name if needed
432 map<string, string>::iterator it = uniqueMap.find(name);
433 if (it != uniqueMap.end()) { name = it->second; }
437 //if this name is in the accnos file
438 if (names.count(name) != 0) {
439 wroteSomething = true;
441 currSeq.printSequence(out);
444 if (m->debug) { sanity["fasta"].insert(name); }
453 if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); }
454 outputNames.push_back(outputFileName); outputTypes["fasta"].push_back(outputFileName);
456 m->mothurOut("Selected " + toString(selectedCount) + " sequences from your fasta file."); m->mothurOutEndLine();
461 catch(exception& e) {
462 m->errorOut(e, "GetSeqsCommand", "readFasta");
466 //**********************************************************************************************************************
467 int GetSeqsCommand::readQual(){
469 string thisOutputDir = outputDir;
470 if (outputDir == "") { thisOutputDir += m->hasPath(qualfile); }
471 map<string, string> variables;
472 variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(qualfile));
473 variables["[extension]"] = m->getExtension(qualfile);
474 string outputFileName = getOutputFileName("qfile", variables);
476 m->openOutputFile(outputFileName, out);
480 m->openInputFile(qualfile, in);
483 bool wroteSomething = false;
484 int selectedCount = 0;
486 if (m->debug) { set<string> temp; sanity["qual"] = temp; }
489 string saveName = "";
495 if (!dups) {//adjust name if needed
496 map<string, string>::iterator it = uniqueMap.find(name);
497 if (it != uniqueMap.end()) { name = it->second; }
500 if (name.length() != 0) {
501 saveName = name.substr(1);
504 if (c == 10 || c == 13 || c == -1){ break; }
511 char letter= in.get();
512 if(letter == '>'){ in.putback(letter); break; }
513 else{ scores += letter; }
518 if (names.count(saveName) != 0) {
519 wroteSomething = true;
521 out << name << endl << scores;
523 if (m->debug) { sanity["qual"].insert(name); }
532 if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); }
533 outputNames.push_back(outputFileName); outputTypes["qfile"].push_back(outputFileName);
535 m->mothurOut("Selected " + toString(selectedCount) + " sequences from your quality file."); m->mothurOutEndLine();
541 catch(exception& e) {
542 m->errorOut(e, "GetSeqsCommand", "readQual");
546 //**********************************************************************************************************************
547 int GetSeqsCommand::readCount(){
549 string thisOutputDir = outputDir;
550 if (outputDir == "") { thisOutputDir += m->hasPath(countfile); }
551 map<string, string> variables;
552 variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(countfile));
553 variables["[extension]"] = m->getExtension(countfile);
554 string outputFileName = getOutputFileName("count", variables);
557 m->openOutputFile(outputFileName, out);
560 m->openInputFile(countfile, in);
562 bool wroteSomething = false;
563 int selectedCount = 0;
565 string headers = m->getline(in); m->gobble(in);
566 out << headers << endl;
568 string name, rest; int thisTotal;
571 if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; }
573 in >> name; m->gobble(in);
574 in >> thisTotal; m->gobble(in);
575 rest = m->getline(in); m->gobble(in);
576 if (m->debug) { m->mothurOut("[DEBUG]: " + name + '\t' + rest + "\n"); }
578 if (names.count(name) != 0) {
579 out << name << '\t' << thisTotal << '\t' << rest << endl;
580 wroteSomething = true;
581 selectedCount+= thisTotal;
587 //check for groups that have been eliminated
589 if (ct.testGroups(outputFileName)) {
590 ct.readTable(outputFileName, true);
591 ct.printTable(outputFileName);
594 if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); }
595 outputTypes["count"].push_back(outputFileName); outputNames.push_back(outputFileName);
597 m->mothurOut("Selected " + toString(selectedCount) + " sequences from your count file."); m->mothurOutEndLine();
601 catch(exception& e) {
602 m->errorOut(e, "GetSeqsCommand", "readCount");
607 //**********************************************************************************************************************
608 int GetSeqsCommand::readList(){
610 string thisOutputDir = outputDir;
611 if (outputDir == "") { thisOutputDir += m->hasPath(listfile); }
612 map<string, string> variables;
613 variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(listfile));
614 variables["[extension]"] = m->getExtension(listfile);
615 string outputFileName = getOutputFileName("list", variables);
617 m->openOutputFile(outputFileName, out);
620 m->openInputFile(listfile, in);
622 bool wroteSomething = false;
623 int selectedCount = 0;
625 if (m->debug) { set<string> temp; sanity["list"] = temp; }
631 if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; }
633 //read in list vector
636 //make a new list vector
638 newList.setLabel(list.getLabel());
641 for (int i = 0; i < list.getNumBins(); i++) {
643 //parse out names that are in accnos file
644 string binnames = list.get(i);
645 vector<string> bnames;
646 m->splitAtComma(binnames, bnames);
648 string newNames = "";
649 for (int i = 0; i < bnames.size(); i++) {
650 string name = bnames[i];
651 //if that name is in the .accnos file, add it
652 if (names.count(name) != 0) { newNames += name + ","; selectedCount++; if (m->debug) { sanity["list"].insert(name); } }
655 //if there are names in this bin add to new list
656 if (newNames != "") {
657 newNames = newNames.substr(0, newNames.length()-1); //rip off extra comma
658 newList.push_back(newNames);
662 //print new listvector
663 if (newList.getNumBins() != 0) {
664 wroteSomething = true;
673 if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); }
674 outputNames.push_back(outputFileName); outputTypes["list"].push_back(outputFileName);
676 m->mothurOut("Selected " + toString(selectedCount) + " sequences from your list file."); m->mothurOutEndLine();
681 catch(exception& e) {
682 m->errorOut(e, "GetSeqsCommand", "readList");
686 //**********************************************************************************************************************
687 int GetSeqsCommand::readName(){
689 string thisOutputDir = outputDir;
690 if (outputDir == "") { thisOutputDir += m->hasPath(namefile); }
691 map<string, string> variables;
692 variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(namefile));
693 variables["[extension]"] = m->getExtension(namefile);
694 string outputFileName = getOutputFileName("name", variables);
696 m->openOutputFile(outputFileName, out);
700 m->openInputFile(namefile, in);
701 string name, firstCol, secondCol;
703 bool wroteSomething = false;
704 int selectedCount = 0;
706 if (m->debug) { set<string> temp; sanity["name"] = temp; }
707 if (m->debug) { set<string> temp; sanity["dupname"] = temp; }
711 if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; }
717 if (dups) { hold = secondCol; }
719 vector<string> parsedNames;
720 m->splitAtComma(secondCol, parsedNames);
722 vector<string> validSecond;
723 for (int i = 0; i < parsedNames.size(); i++) {
724 if (names.count(parsedNames[i]) != 0) {
725 validSecond.push_back(parsedNames[i]);
726 if (m->debug) { sanity["dupname"].insert(parsedNames[i]); }
730 if ((dups) && (validSecond.size() != 0)) { //dups = true and we want to add someone, then add everyone
731 for (int i = 0; i < parsedNames.size(); i++) { names.insert(parsedNames[i]); if (m->debug) { sanity["dupname"].insert(parsedNames[i]); } }
732 out << firstCol << '\t' << hold << endl;
733 wroteSomething = true;
734 selectedCount += parsedNames.size();
735 if (m->debug) { sanity["name"].insert(firstCol); }
737 selectedCount += validSecond.size();
739 //if the name in the first column is in the set then print it and any other names in second column also in set
740 if (names.count(firstCol) != 0) {
742 wroteSomething = true;
744 out << firstCol << '\t';
746 //you know you have at least one valid second since first column is valid
747 for (int i = 0; i < validSecond.size()-1; i++) { out << validSecond[i] << ','; }
748 out << validSecond[validSecond.size()-1] << endl;
750 if (m->debug) { sanity["name"].insert(firstCol); }
753 //make first name in set you come to first column and then add the remaining names to second column
755 //you want part of this row
756 if (validSecond.size() != 0) {
758 wroteSomething = true;
760 out << validSecond[0] << '\t';
761 //we are changing the unique name in the fasta file
762 uniqueMap[firstCol] = validSecond[0];
764 //you know you have at least one valid second since first column is valid
765 for (int i = 0; i < validSecond.size()-1; i++) { out << validSecond[i] << ','; }
766 out << validSecond[validSecond.size()-1] << endl;
768 if (m->debug) { sanity["name"].insert(validSecond[0]); }
777 if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); }
778 outputNames.push_back(outputFileName); outputTypes["name"].push_back(outputFileName);
780 m->mothurOut("Selected " + toString(selectedCount) + " sequences from your name file."); m->mothurOutEndLine();
785 catch(exception& e) {
786 m->errorOut(e, "GetSeqsCommand", "readName");
791 //**********************************************************************************************************************
792 int GetSeqsCommand::readGroup(){
794 string thisOutputDir = outputDir;
795 if (outputDir == "") { thisOutputDir += m->hasPath(groupfile); }
796 map<string, string> variables;
797 variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(groupfile));
798 variables["[extension]"] = m->getExtension(groupfile);
799 string outputFileName = getOutputFileName("group", variables);
801 m->openOutputFile(outputFileName, out);
805 m->openInputFile(groupfile, in);
808 bool wroteSomething = false;
809 int selectedCount = 0;
811 if (m->debug) { set<string> temp; sanity["group"] = temp; }
815 if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; }
818 in >> name; //read from first column
819 in >> group; //read from second column
822 //if this name is in the accnos file
823 if (names.count(name) != 0) {
824 wroteSomething = true;
826 out << name << '\t' << group << endl;
829 if (m->debug) { sanity["group"].insert(name); }
837 if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); }
838 outputNames.push_back(outputFileName); outputTypes["group"].push_back(outputFileName);
840 m->mothurOut("Selected " + toString(selectedCount) + " sequences from your group file."); m->mothurOutEndLine();
846 catch(exception& e) {
847 m->errorOut(e, "GetSeqsCommand", "readGroup");
851 //**********************************************************************************************************************
852 int GetSeqsCommand::readTax(){
854 string thisOutputDir = outputDir;
855 if (outputDir == "") { thisOutputDir += m->hasPath(taxfile); }
856 map<string, string> variables;
857 variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(taxfile));
858 variables["[extension]"] = m->getExtension(taxfile);
859 string outputFileName = getOutputFileName("taxonomy", variables);
861 m->openOutputFile(outputFileName, out);
864 m->openInputFile(taxfile, in);
867 bool wroteSomething = false;
868 int selectedCount = 0;
870 if (m->debug) { set<string> temp; sanity["tax"] = temp; }
874 if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; }
876 in >> name; //read from first column
877 in >> tax; //read from second column
879 if (!dups) {//adjust name if needed
880 map<string, string>::iterator it = uniqueMap.find(name);
881 if (it != uniqueMap.end()) { name = it->second; }
884 //if this name is in the accnos file
885 if (names.count(name) != 0) {
886 wroteSomething = true;
888 out << name << '\t' << tax << endl;
891 if (m->debug) { sanity["tax"].insert(name); }
899 if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); }
900 outputNames.push_back(outputFileName); outputTypes["taxonomy"].push_back(outputFileName);
902 m->mothurOut("Selected " + toString(selectedCount) + " sequences from your taxonomy file."); m->mothurOutEndLine();
907 catch(exception& e) {
908 m->errorOut(e, "GetSeqsCommand", "readTax");
912 //**********************************************************************************************************************
913 //alignreport file has a column header line then all other lines contain 16 columns. we just want the first column since that contains the name
914 int GetSeqsCommand::readAlign(){
916 string thisOutputDir = outputDir;
917 if (outputDir == "") { thisOutputDir += m->hasPath(alignfile); }
918 map<string, string> variables;
919 variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(alignfile));
920 string outputFileName = getOutputFileName("alignreport", variables);
922 m->openOutputFile(outputFileName, out);
926 m->openInputFile(alignfile, in);
929 bool wroteSomething = false;
930 int selectedCount = 0;
932 //read column headers
933 for (int i = 0; i < 16; i++) {
934 if (!in.eof()) { in >> junk; out << junk << '\t'; }
941 if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; }
944 in >> name; //read from first column
946 if (!dups) {//adjust name if needed
947 map<string, string>::iterator it = uniqueMap.find(name);
948 if (it != uniqueMap.end()) { name = it->second; }
951 //if this name is in the accnos file
952 if (names.count(name) != 0) {
953 wroteSomething = true;
959 for (int i = 0; i < 15; i++) {
960 if (!in.eof()) { in >> junk; out << junk << '\t'; }
965 }else {//still read just don't do anything with it
967 for (int i = 0; i < 15; i++) {
968 if (!in.eof()) { in >> junk; }
978 if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); }
979 outputNames.push_back(outputFileName); outputTypes["alignreport"].push_back(outputFileName);
981 m->mothurOut("Selected " + toString(selectedCount) + " sequences from your alignreport file."); m->mothurOutEndLine();
986 catch(exception& e) {
987 m->errorOut(e, "GetSeqsCommand", "readAlign");
991 //**********************************************************************************************************************
992 //just looking at common mistakes.
993 int GetSeqsCommand::runSanityCheck(){
995 string thisOutputDir = outputDir;
996 if (outputDir == "") { thisOutputDir += m->hasPath(fastafile); }
997 string filename = outputDir + "get.seqs.debug.report";
1000 m->openOutputFile(filename, out);
1003 //compare fasta, name, qual and taxonomy if given to make sure they contain the same seqs
1004 if (fastafile != "") {
1005 if (namefile != "") { //compare with fasta
1006 if (sanity["fasta"] != sanity["name"]) { //create mismatch file
1007 createMisMatchFile(out, fastafile, namefile, sanity["fasta"], sanity["name"]);
1010 if (qualfile != "") {
1011 if (sanity["fasta"] != sanity["qual"]) { //create mismatch file
1012 createMisMatchFile(out, fastafile, qualfile, sanity["fasta"], sanity["qual"]);
1015 if (taxfile != "") {
1016 if (sanity["fasta"] != sanity["tax"]) { //create mismatch file
1017 createMisMatchFile(out, fastafile, taxfile, sanity["fasta"], sanity["tax"]);
1022 //compare dupnames, groups and list if given to make sure they match
1023 if (namefile != "") {
1024 if (groupfile != "") {
1025 if (sanity["dupname"] != sanity["group"]) { //create mismatch file
1026 createMisMatchFile(out, namefile, groupfile, sanity["dupname"], sanity["group"]);
1029 if (listfile != "") {
1030 if (sanity["dupname"] != sanity["list"]) { //create mismatch file
1031 createMisMatchFile(out, namefile, listfile, sanity["dupname"], sanity["list"]);
1036 if ((groupfile != "") && (fastafile != "")) {
1037 if (sanity["fasta"] != sanity["group"]) { //create mismatch file
1038 createMisMatchFile(out, fastafile, groupfile, sanity["fasta"], sanity["group"]);
1045 if (m->isBlank(filename)) { m->mothurRemove(filename); }
1046 else { m->mothurOut("\n[DEBUG]: " + filename + " contains the file mismatches.\n");outputNames.push_back(filename); outputTypes["debug"].push_back(filename); }
1050 catch(exception& e) {
1051 m->errorOut(e, "GetSeqsCommand", "runSanityCheck");
1055 //**********************************************************************************************************************
1056 //just looking at common mistakes.
1057 int GetSeqsCommand::createMisMatchFile(ofstream& out, string filename1, string filename2, set<string> set1, set<string> set2){
1059 out << "****************************************" << endl << endl;
1060 out << "Names unique to " << filename1 << ":\n";
1062 //remove names in set1 that are also in set2
1063 for (set<string>::iterator it = set1.begin(); it != set1.end();) {
1066 if (set2.count(name) == 0) { out << name << endl; } //name unique to set1
1067 else { set2.erase(name); } //you are in both so erase
1071 out << "\nNames unique to " << filename2 << ":\n";
1073 for (set<string>::iterator it = set2.begin(); it != set2.end(); it++) { out << *it << endl; }
1075 out << "****************************************" << endl << endl;
1079 catch(exception& e) {
1080 m->errorOut(e, "GetSeqsCommand", "runSanityCheck");
1084 //**********************************************************************************************************************
1086 int GetSeqsCommand::compareAccnos(){
1089 string thisOutputDir = outputDir;
1090 if (outputDir == "") { thisOutputDir += m->hasPath(accnosfile); }
1091 map<string, string> variables;
1092 variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(accnosfile));
1093 string outputFileName = getOutputFileName("accnosreport", variables);
1096 m->openOutputFile(outputFileName, out);
1099 m->openInputFile(accnosfile2, in);
1102 set<string> namesAccnos2;
1103 set<string> namesDups;
1104 set<string> namesAccnos = names;
1106 map<string, int> nameCount;
1108 if (namefile != "") {
1110 m->openInputFile(namefile, inName);
1113 while(!inName.eof()){
1115 if (m->control_pressed) { inName.close(); return 0; }
1117 string thisname, repnames;
1119 inName >> thisname; m->gobble(inName); //read from first column
1120 inName >> repnames; //read from second column
1122 int num = m->getNumNames(repnames);
1123 nameCount[thisname] = num;
1133 if (namesAccnos.count(name) == 0){ //name unique to accnos2
1134 int pos = name.find_last_of('_');
1135 string tempName = name;
1136 if (pos != string::npos) { tempName = tempName.substr(pos+1); cout << tempName << endl; }
1137 if (namesAccnos.count(tempName) == 0){
1138 namesAccnos2.insert(name);
1139 }else { //you are in both so erase
1140 namesAccnos.erase(name);
1141 namesDups.insert(name);
1143 }else { //you are in both so erase
1144 namesAccnos.erase(name);
1145 namesDups.insert(name);
1152 out << "Names in both files : " + toString(namesDups.size()) << endl;
1153 m->mothurOut("Names in both files : " + toString(namesDups.size())); m->mothurOutEndLine();
1155 for (set<string>::iterator it = namesDups.begin(); it != namesDups.end(); it++) {
1157 if (namefile != "") { out << '\t' << nameCount[(*it)]; }
1161 out << "Names unique to " + accnosfile + " : " + toString(namesAccnos.size()) << endl;
1162 m->mothurOut("Names unique to " + accnosfile + " : " + toString(namesAccnos.size())); m->mothurOutEndLine();
1164 for (set<string>::iterator it = namesAccnos.begin(); it != namesAccnos.end(); it++) {
1166 if (namefile != "") { out << '\t' << nameCount[(*it)]; }
1170 out << "Names unique to " + accnosfile2 + " : " + toString(namesAccnos2.size()) << endl;
1171 m->mothurOut("Names unique to " + accnosfile2 + " : " + toString(namesAccnos2.size())); m->mothurOutEndLine();
1173 for (set<string>::iterator it = namesAccnos2.begin(); it != namesAccnos2.end(); it++) {
1175 if (namefile != "") { out << '\t' << nameCount[(*it)]; }
1181 outputNames.push_back(outputFileName); outputTypes["accnosreport"].push_back(outputFileName);
1186 catch(exception& e) {
1187 m->errorOut(e, "GetSeqsCommand", "compareAccnos");
1193 //**********************************************************************************************************************