2 * removeseqscommand.cpp
5 * Created by Sarah Westcott on 7/8/09.
6 * Copyright 2009 Schloss Lab UMASS Amherst. All rights reserved.
10 #include "removeseqscommand.h"
11 #include "sequence.hpp"
12 #include "listvector.hpp"
14 //**********************************************************************************************************************
15 vector<string> RemoveSeqsCommand::setParameters(){
17 CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pfasta);
18 CommandParameter pname("name", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pname);
19 CommandParameter pgroup("group", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pgroup);
20 CommandParameter plist("list", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(plist);
21 CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(ptaxonomy);
22 CommandParameter palignreport("alignreport", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(palignreport);
23 CommandParameter pqfile("qfile", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pqfile);
24 CommandParameter paccnos("accnos", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(paccnos);
25 CommandParameter pdups("dups", "Boolean", "", "T", "", "", "",false,false); parameters.push_back(pdups);
26 CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir);
27 CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir);
29 vector<string> myArray;
30 for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); }
34 m->errorOut(e, "RemoveSeqsCommand", "setParameters");
38 //**********************************************************************************************************************
39 string RemoveSeqsCommand::getHelpString(){
41 string helpString = "";
42 helpString += "The remove.seqs command reads an .accnos file and at least one of the following file types: fasta, name, group, list, taxonomy, quality or alignreport file.\n";
43 helpString += "It outputs a file containing the sequences NOT in the .accnos file.\n";
44 helpString += "The remove.seqs command parameters are accnos, fasta, name, group, list, taxonomy, qfile, alignreport and dups. You must provide accnos and at least one of the file parameters.\n";
45 helpString += "The dups parameter allows you to remove the entire line from a name file if you remove any name from the line. default=true. \n";
46 helpString += "The remove.seqs command should be in the following format: remove.seqs(accnos=yourAccnos, fasta=yourFasta).\n";
47 helpString += "Example remove.seqs(accnos=amazon.accnos, fasta=amazon.fasta).\n";
48 helpString += "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n";
52 m->errorOut(e, "RemoveSeqsCommand", "getHelpString");
58 //**********************************************************************************************************************
59 RemoveSeqsCommand::RemoveSeqsCommand(){
61 abort = true; calledHelp = true;
63 vector<string> tempOutNames;
64 outputTypes["fasta"] = tempOutNames;
65 outputTypes["taxonomy"] = tempOutNames;
66 outputTypes["name"] = tempOutNames;
67 outputTypes["group"] = tempOutNames;
68 outputTypes["alignreport"] = tempOutNames;
69 outputTypes["list"] = tempOutNames;
70 outputTypes["qfile"] = tempOutNames;
73 m->errorOut(e, "RemoveSeqsCommand", "RemoveSeqsCommand");
77 //**********************************************************************************************************************
78 RemoveSeqsCommand::RemoveSeqsCommand(string option) {
80 abort = false; calledHelp = false;
82 //allow user to run help
83 if(option == "help") { help(); abort = true; calledHelp = true; }
84 else if(option == "citation") { citation(); abort = true; calledHelp = true;}
87 vector<string> myArray = setParameters();
89 OptionParser parser(option);
90 map<string,string> parameters = parser.getParameters();
92 ValidParameters validParameter;
93 map<string,string>::iterator it;
95 //check to make sure all parameters are valid for command
96 for (it = parameters.begin(); it != parameters.end(); it++) {
97 if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; }
100 //initialize outputTypes
101 vector<string> tempOutNames;
102 outputTypes["fasta"] = tempOutNames;
103 outputTypes["taxonomy"] = tempOutNames;
104 outputTypes["name"] = tempOutNames;
105 outputTypes["group"] = tempOutNames;
106 outputTypes["alignreport"] = tempOutNames;
107 outputTypes["list"] = tempOutNames;
108 outputTypes["qfile"] = tempOutNames;
110 //if the user changes the output directory command factory will send this info to us in the output parameter
111 outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){ outputDir = ""; }
113 //if the user changes the input directory command factory will send this info to us in the output parameter
114 string inputDir = validParameter.validFile(parameters, "inputdir", false);
115 if (inputDir == "not found"){ inputDir = ""; }
118 it = parameters.find("alignreport");
119 //user has given a template file
120 if(it != parameters.end()){
121 path = m->hasPath(it->second);
122 //if the user has not given a path then, add inputdir. else leave path alone.
123 if (path == "") { parameters["alignreport"] = inputDir + it->second; }
126 it = parameters.find("fasta");
127 //user has given a template file
128 if(it != parameters.end()){
129 path = m->hasPath(it->second);
130 //if the user has not given a path then, add inputdir. else leave path alone.
131 if (path == "") { parameters["fasta"] = inputDir + it->second; }
134 it = parameters.find("accnos");
135 //user has given a template file
136 if(it != parameters.end()){
137 path = m->hasPath(it->second);
138 //if the user has not given a path then, add inputdir. else leave path alone.
139 if (path == "") { parameters["accnos"] = inputDir + it->second; }
142 it = parameters.find("list");
143 //user has given a template file
144 if(it != parameters.end()){
145 path = m->hasPath(it->second);
146 //if the user has not given a path then, add inputdir. else leave path alone.
147 if (path == "") { parameters["list"] = inputDir + it->second; }
150 it = parameters.find("name");
151 //user has given a template file
152 if(it != parameters.end()){
153 path = m->hasPath(it->second);
154 //if the user has not given a path then, add inputdir. else leave path alone.
155 if (path == "") { parameters["name"] = inputDir + it->second; }
158 it = parameters.find("group");
159 //user has given a template file
160 if(it != parameters.end()){
161 path = m->hasPath(it->second);
162 //if the user has not given a path then, add inputdir. else leave path alone.
163 if (path == "") { parameters["group"] = inputDir + it->second; }
166 it = parameters.find("taxonomy");
167 //user has given a template file
168 if(it != parameters.end()){
169 path = m->hasPath(it->second);
170 //if the user has not given a path then, add inputdir. else leave path alone.
171 if (path == "") { parameters["taxonomy"] = inputDir + it->second; }
174 it = parameters.find("qfile");
175 //user has given a template file
176 if(it != parameters.end()){
177 path = m->hasPath(it->second);
178 //if the user has not given a path then, add inputdir. else leave path alone.
179 if (path == "") { parameters["qfile"] = inputDir + it->second; }
184 //check for required parameters
185 accnosfile = validParameter.validFile(parameters, "accnos", true);
186 if (accnosfile == "not open") { abort = true; }
187 else if (accnosfile == "not found") {
188 accnosfile = m->getAccnosFile();
189 if (accnosfile != "") { m->mothurOut("Using " + accnosfile + " as input file for the accnos parameter."); m->mothurOutEndLine(); }
191 m->mothurOut("You have no valid accnos file and accnos is required."); m->mothurOutEndLine();
194 }else { m->setAccnosFile(accnosfile); }
196 fastafile = validParameter.validFile(parameters, "fasta", true);
197 if (fastafile == "not open") { abort = true; }
198 else if (fastafile == "not found") { fastafile = ""; }
199 else { m->setFastaFile(fastafile); }
201 namefile = validParameter.validFile(parameters, "name", true);
202 if (namefile == "not open") { abort = true; }
203 else if (namefile == "not found") { namefile = ""; }
204 else { m->setNameFile(namefile); }
206 groupfile = validParameter.validFile(parameters, "group", true);
207 if (groupfile == "not open") { abort = true; }
208 else if (groupfile == "not found") { groupfile = ""; }
209 else { m->setGroupFile(groupfile); }
211 alignfile = validParameter.validFile(parameters, "alignreport", true);
212 if (alignfile == "not open") { abort = true; }
213 else if (alignfile == "not found") { alignfile = ""; }
215 listfile = validParameter.validFile(parameters, "list", true);
216 if (listfile == "not open") { abort = true; }
217 else if (listfile == "not found") { listfile = ""; }
218 else { m->setListFile(listfile); }
220 taxfile = validParameter.validFile(parameters, "taxonomy", true);
221 if (taxfile == "not open") { abort = true; }
222 else if (taxfile == "not found") { taxfile = ""; }
223 else { m->setTaxonomyFile(taxfile); }
225 qualfile = validParameter.validFile(parameters, "qfile", true);
226 if (qualfile == "not open") { abort = true; }
227 else if (qualfile == "not found") { qualfile = ""; }
228 else { m->setQualFile(qualfile); }
230 string usedDups = "true";
231 string temp = validParameter.validFile(parameters, "dups", false);
232 if (temp == "not found") {
233 if (namefile != "") { temp = "true"; }
234 else { temp = "false"; usedDups = ""; }
236 dups = m->isTrue(temp);
238 if ((fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == "") && (taxfile == "") && (qualfile == "")) { m->mothurOut("You must provide at least one of the following: fasta, name, group, taxonomy, quality, alignreport or list."); m->mothurOutEndLine(); abort = true; }
243 catch(exception& e) {
244 m->errorOut(e, "RemoveSeqsCommand", "RemoveSeqsCommand");
248 //**********************************************************************************************************************
250 int RemoveSeqsCommand::execute(){
253 if (abort == true) { if (calledHelp) { return 0; } return 2; }
255 //get names you want to keep
258 if (m->control_pressed) { return 0; }
260 //read through the correct file and output lines you want to keep
261 if (namefile != "") { readName(); }
262 if (fastafile != "") { readFasta(); }
263 if (groupfile != "") { readGroup(); }
264 if (alignfile != "") { readAlign(); }
265 if (listfile != "") { readList(); }
266 if (taxfile != "") { readTax(); }
267 if (qualfile != "") { readQual(); }
269 if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
271 if (outputNames.size() != 0) {
272 m->mothurOutEndLine();
273 m->mothurOut("Output File Names: "); m->mothurOutEndLine();
274 for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); }
275 m->mothurOutEndLine();
277 //set fasta file as new current fastafile
279 itTypes = outputTypes.find("fasta");
280 if (itTypes != outputTypes.end()) {
281 if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setFastaFile(current); }
284 itTypes = outputTypes.find("name");
285 if (itTypes != outputTypes.end()) {
286 if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setNameFile(current); }
289 itTypes = outputTypes.find("group");
290 if (itTypes != outputTypes.end()) {
291 if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setGroupFile(current); }
294 itTypes = outputTypes.find("list");
295 if (itTypes != outputTypes.end()) {
296 if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setListFile(current); }
299 itTypes = outputTypes.find("taxonomy");
300 if (itTypes != outputTypes.end()) {
301 if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setTaxonomyFile(current); }
304 itTypes = outputTypes.find("qfile");
305 if (itTypes != outputTypes.end()) {
306 if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setQualFile(current); }
313 catch(exception& e) {
314 m->errorOut(e, "RemoveSeqsCommand", "execute");
319 //**********************************************************************************************************************
320 int RemoveSeqsCommand::readFasta(){
322 string thisOutputDir = outputDir;
323 if (outputDir == "") { thisOutputDir += m->hasPath(fastafile); }
324 string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(fastafile)) + "pick" + m->getExtension(fastafile);
327 m->openOutputFile(outputFileName, out);
330 m->openInputFile(fastafile, in);
333 bool wroteSomething = false;
334 int removedCount = 0;
337 if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; }
339 Sequence currSeq(in);
340 name = currSeq.getName();
343 //if this name is in the accnos file
344 if (names.count(name) == 0) {
345 wroteSomething = true;
347 currSeq.printSequence(out);
348 }else { removedCount++; }
355 if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); }
356 outputTypes["fasta"].push_back(outputFileName); outputNames.push_back(outputFileName);
358 m->mothurOut("Removed " + toString(removedCount) + " sequences from your fasta file."); m->mothurOutEndLine();
363 catch(exception& e) {
364 m->errorOut(e, "RemoveSeqsCommand", "readFasta");
368 //**********************************************************************************************************************
369 int RemoveSeqsCommand::readQual(){
371 string thisOutputDir = outputDir;
372 if (outputDir == "") { thisOutputDir += m->hasPath(qualfile); }
373 string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(qualfile)) + "pick" + m->getExtension(qualfile);
375 m->openOutputFile(outputFileName, out);
379 m->openInputFile(qualfile, in);
382 bool wroteSomething = false;
383 int removedCount = 0;
387 string saveName = "";
393 if (name.length() != 0) {
394 saveName = name.substr(1);
397 if (c == 10 || c == 13){ break; }
404 char letter= in.get();
405 if(letter == '>'){ in.putback(letter); break; }
406 else{ scores += letter; }
411 if (names.count(saveName) == 0) {
412 wroteSomething = true;
414 out << name << endl << scores;
415 }else { removedCount++; }
423 if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); }
424 outputNames.push_back(outputFileName); outputTypes["qfile"].push_back(outputFileName);
426 m->mothurOut("Removed " + toString(removedCount) + " sequences from your quality file."); m->mothurOutEndLine();
431 catch(exception& e) {
432 m->errorOut(e, "RemoveSeqsCommand", "readQual");
436 //**********************************************************************************************************************
437 int RemoveSeqsCommand::readList(){
439 string thisOutputDir = outputDir;
440 if (outputDir == "") { thisOutputDir += m->hasPath(listfile); }
441 string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(listfile)) + "pick" + m->getExtension(listfile);
444 m->openOutputFile(outputFileName, out);
447 m->openInputFile(listfile, in);
449 bool wroteSomething = false;
450 int removedCount = 0;
453 //read in list vector
456 //make a new list vector
458 newList.setLabel(list.getLabel());
461 for (int i = 0; i < list.getNumBins(); i++) {
462 if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; }
464 //parse out names that are in accnos file
465 string binnames = list.get(i);
467 string newNames = "";
468 while (binnames.find_first_of(',') != -1) {
469 string name = binnames.substr(0,binnames.find_first_of(','));
470 binnames = binnames.substr(binnames.find_first_of(',')+1, binnames.length());
472 //if that name is in the .accnos file, add it
473 if (names.count(name) == 0) { newNames += name + ","; }
474 else { removedCount++; }
478 if (names.count(binnames) == 0) { newNames += binnames + ","; }
479 else { removedCount++; }
481 //if there are names in this bin add to new list
482 if (newNames != "") {
483 newNames = newNames.substr(0, newNames.length()-1); //rip off extra comma
484 newList.push_back(newNames);
488 //print new listvector
489 if (newList.getNumBins() != 0) {
490 wroteSomething = true;
499 if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); }
500 outputTypes["list"].push_back(outputFileName); outputNames.push_back(outputFileName);
502 m->mothurOut("Removed " + toString(removedCount) + " sequences from your list file."); m->mothurOutEndLine();
507 catch(exception& e) {
508 m->errorOut(e, "RemoveSeqsCommand", "readList");
512 //**********************************************************************************************************************
513 int RemoveSeqsCommand::readName(){
515 string thisOutputDir = outputDir;
516 if (outputDir == "") { thisOutputDir += m->hasPath(namefile); }
517 string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(namefile)) + "pick" + m->getExtension(namefile);
520 m->openOutputFile(outputFileName, out);
523 m->openInputFile(namefile, in);
524 string name, firstCol, secondCol;
526 bool wroteSomething = false;
527 int removedCount = 0;
530 if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; }
532 in >> firstCol; m->gobble(in);
535 vector<string> parsedNames;
536 m->splitAtComma(secondCol, parsedNames);
538 vector<string> validSecond; validSecond.clear();
539 for (int i = 0; i < parsedNames.size(); i++) {
540 if (names.count(parsedNames[i]) == 0) {
541 validSecond.push_back(parsedNames[i]);
545 if ((dups) && (validSecond.size() != parsedNames.size())) { //if dups is true and we want to get rid of anyone, get rid of everyone
546 for (int i = 0; i < parsedNames.size(); i++) { names.insert(parsedNames[i]); }
547 removedCount += parsedNames.size();
549 removedCount += parsedNames.size()-validSecond.size();
550 //if the name in the first column is in the set then print it and any other names in second column also in set
551 if (names.count(firstCol) == 0) {
553 wroteSomething = true;
555 out << firstCol << '\t';
557 //you know you have at least one valid second since first column is valid
558 for (int i = 0; i < validSecond.size()-1; i++) { out << validSecond[i] << ','; }
559 out << validSecond[validSecond.size()-1] << endl;
561 //make first name in set you come to first column and then add the remaining names to second column
564 //you want part of this row
565 if (validSecond.size() != 0) {
567 wroteSomething = true;
569 out << validSecond[0] << '\t';
571 //you know you have at least one valid second since first column is valid
572 for (int i = 0; i < validSecond.size()-1; i++) { out << validSecond[i] << ','; }
573 out << validSecond[validSecond.size()-1] << endl;
582 if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); }
583 outputTypes["name"].push_back(outputFileName); outputNames.push_back(outputFileName);
585 m->mothurOut("Removed " + toString(removedCount) + " sequences from your name file."); m->mothurOutEndLine();
589 catch(exception& e) {
590 m->errorOut(e, "RemoveSeqsCommand", "readName");
595 //**********************************************************************************************************************
596 int RemoveSeqsCommand::readGroup(){
598 string thisOutputDir = outputDir;
599 if (outputDir == "") { thisOutputDir += m->hasPath(groupfile); }
600 string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(groupfile)) + "pick" + m->getExtension(groupfile);
603 m->openOutputFile(outputFileName, out);
606 m->openInputFile(groupfile, in);
609 bool wroteSomething = false;
610 int removedCount = 0;
613 if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; }
615 in >> name; //read from first column
616 in >> group; //read from second column
618 //if this name is in the accnos file
619 if (names.count(name) == 0) {
620 wroteSomething = true;
621 out << name << '\t' << group << endl;
622 }else { removedCount++; }
629 if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); }
630 outputTypes["group"].push_back(outputFileName); outputNames.push_back(outputFileName);
632 m->mothurOut("Removed " + toString(removedCount) + " sequences from your group file."); m->mothurOutEndLine();
637 catch(exception& e) {
638 m->errorOut(e, "RemoveSeqsCommand", "readGroup");
642 //**********************************************************************************************************************
643 int RemoveSeqsCommand::readTax(){
645 string thisOutputDir = outputDir;
646 if (outputDir == "") { thisOutputDir += m->hasPath(taxfile); }
647 string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(taxfile)) + "pick" + m->getExtension(taxfile);
649 m->openOutputFile(outputFileName, out);
652 m->openInputFile(taxfile, in);
655 bool wroteSomething = false;
656 int removedCount = 0;
659 if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; }
661 in >> name; //read from first column
662 in >> tax; //read from second column
664 //if this name is in the accnos file
665 if (names.count(name) == 0) {
666 wroteSomething = true;
667 out << name << '\t' << tax << endl;
668 }else { removedCount++; }
675 if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); }
676 outputTypes["taxonomy"].push_back(outputFileName); outputNames.push_back(outputFileName);
678 m->mothurOut("Removed " + toString(removedCount) + " sequences from your taxonomy file."); m->mothurOutEndLine();
682 catch(exception& e) {
683 m->errorOut(e, "RemoveSeqsCommand", "readTax");
687 //**********************************************************************************************************************
688 //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
689 int RemoveSeqsCommand::readAlign(){
691 string thisOutputDir = outputDir;
692 if (outputDir == "") { thisOutputDir += m->hasPath(alignfile); }
693 string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(alignfile)) + "pick.align.report";
696 m->openOutputFile(outputFileName, out);
699 m->openInputFile(alignfile, in);
702 bool wroteSomething = false;
703 int removedCount = 0;
705 //read column headers
706 for (int i = 0; i < 16; i++) {
707 if (!in.eof()) { in >> junk; out << junk << '\t'; }
713 if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; }
715 in >> name; //read from first column
717 //if this name is in the accnos file
718 if (names.count(name) == 0) {
719 wroteSomething = true;
724 for (int i = 0; i < 15; i++) {
725 if (!in.eof()) { in >> junk; out << junk << '\t'; }
730 }else {//still read just don't do anything with it
734 for (int i = 0; i < 15; i++) {
735 if (!in.eof()) { in >> junk; }
745 if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the .accnos file."); m->mothurOutEndLine(); }
746 outputTypes["alignreport"].push_back(outputFileName); outputNames.push_back(outputFileName);
748 m->mothurOut("Removed " + toString(removedCount) + " sequences from your alignreport file."); m->mothurOutEndLine();
754 catch(exception& e) {
755 m->errorOut(e, "RemoveSeqsCommand", "readAlign");
759 //**********************************************************************************************************************
760 void RemoveSeqsCommand::readAccnos(){
764 m->openInputFile(accnosfile, in);
777 catch(exception& e) {
778 m->errorOut(e, "RemoveSeqsCommand", "readAccnos");
783 //**********************************************************************************************************************