2 * removegroupscommand.cpp
5 * Created by westcott on 11/10/10.
6 * Copyright 2010 Schloss Lab. All rights reserved.
10 #include "removegroupscommand.h"
11 #include "sequence.hpp"
12 #include "listvector.hpp"
13 #include "sharedutilities.h"
14 #include "inputdata.h"
16 //**********************************************************************************************************************
17 vector<string> RemoveGroupsCommand::setParameters(){
19 CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "FNGLT",false,false); parameters.push_back(pfasta);
20 CommandParameter pshared("shared", "InputTypes", "", "", "none", "sharedGroup", "none",false,false); parameters.push_back(pshared);
21 CommandParameter pname("name", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(pname);
22 CommandParameter pgroup("group", "InputTypes", "", "", "none", "sharedGroup", "FNGLT",false,false); parameters.push_back(pgroup);
23 CommandParameter plist("list", "InputTypes", "", "", "none", "none", "FNGLT",false,false); parameters.push_back(plist);
24 CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "none", "none", "FNGLT",false,false); parameters.push_back(ptaxonomy);
25 CommandParameter paccnos("accnos", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(paccnos);
26 CommandParameter pgroups("groups", "String", "", "", "", "", "",false,false); parameters.push_back(pgroups);
27 CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir);
28 CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir);
30 vector<string> myArray;
31 for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); }
35 m->errorOut(e, "RemoveGroupsCommand", "setParameters");
39 //**********************************************************************************************************************
40 string RemoveGroupsCommand::getHelpString(){
42 string helpString = "";
43 helpString += "The remove.groups command removes sequences from a specfic group or set of groups from the following file types: fasta, name, group, list, taxonomy or sharedfile.\n";
44 helpString += "It outputs a file containing the sequences NOT in the those specified groups, or with a sharedfile eliminates the groups you selected.\n";
45 helpString += "The remove.groups command parameters are accnos, fasta, name, group, list, taxonomy, shared and groups. The group parameter is required, unless you have a current group file or are using a sharedfile.\n";
46 helpString += "You must also provide an accnos containing the list of groups to remove or set the groups parameter to the groups you wish to remove.\n";
47 helpString += "The groups parameter allows you to specify which of the groups in your groupfile you would like removed. You can separate group names with dashes.\n";
48 helpString += "The remove.groups command should be in the following format: remove.groups(accnos=yourAccnos, fasta=yourFasta, group=yourGroupFile).\n";
49 helpString += "Example remove.groups(accnos=amazon.accnos, fasta=amazon.fasta, group=amazon.groups).\n";
50 helpString += "or remove.groups(groups=pasture, fasta=amazon.fasta, amazon.groups).\n";
51 helpString += "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n";
55 m->errorOut(e, "RemoveGroupsCommand", "getHelpString");
60 //**********************************************************************************************************************
61 RemoveGroupsCommand::RemoveGroupsCommand(){
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["list"] = tempOutNames;
71 outputTypes["shared"] = tempOutNames;
74 m->errorOut(e, "RemoveGroupsCommand", "RemoveGroupsCommand");
78 //**********************************************************************************************************************
79 RemoveGroupsCommand::RemoveGroupsCommand(string option) {
81 abort = false; calledHelp = false;
83 //allow user to run help
84 if(option == "help") { help(); abort = true; calledHelp = true; }
85 else if(option == "citation") { citation(); abort = true; calledHelp = true;}
88 vector<string> myArray = setParameters();
90 OptionParser parser(option);
91 map<string,string> parameters = parser.getParameters();
93 ValidParameters validParameter;
94 map<string,string>::iterator it;
96 //check to make sure all parameters are valid for command
97 for (it = parameters.begin(); it != parameters.end(); it++) {
98 if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; }
101 //initialize outputTypes
102 vector<string> tempOutNames;
103 outputTypes["fasta"] = tempOutNames;
104 outputTypes["taxonomy"] = tempOutNames;
105 outputTypes["name"] = tempOutNames;
106 outputTypes["group"] = tempOutNames;
107 outputTypes["list"] = tempOutNames;
108 outputTypes["shared"] = tempOutNames;
111 //if the user changes the output directory command factory will send this info to us in the output parameter
112 outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){ outputDir = ""; }
114 //if the user changes the input directory command factory will send this info to us in the output parameter
115 string inputDir = validParameter.validFile(parameters, "inputdir", false);
116 if (inputDir == "not found"){ inputDir = ""; }
119 it = parameters.find("fasta");
120 //user has given a template file
121 if(it != parameters.end()){
122 path = m->hasPath(it->second);
123 //if the user has not given a path then, add inputdir. else leave path alone.
124 if (path == "") { parameters["fasta"] = inputDir + it->second; }
127 it = parameters.find("accnos");
128 //user has given a template file
129 if(it != parameters.end()){
130 path = m->hasPath(it->second);
131 //if the user has not given a path then, add inputdir. else leave path alone.
132 if (path == "") { parameters["accnos"] = inputDir + it->second; }
135 it = parameters.find("list");
136 //user has given a template file
137 if(it != parameters.end()){
138 path = m->hasPath(it->second);
139 //if the user has not given a path then, add inputdir. else leave path alone.
140 if (path == "") { parameters["list"] = inputDir + it->second; }
143 it = parameters.find("name");
144 //user has given a template file
145 if(it != parameters.end()){
146 path = m->hasPath(it->second);
147 //if the user has not given a path then, add inputdir. else leave path alone.
148 if (path == "") { parameters["name"] = inputDir + it->second; }
151 it = parameters.find("group");
152 //user has given a template file
153 if(it != parameters.end()){
154 path = m->hasPath(it->second);
155 //if the user has not given a path then, add inputdir. else leave path alone.
156 if (path == "") { parameters["group"] = inputDir + it->second; }
159 it = parameters.find("taxonomy");
160 //user has given a template file
161 if(it != parameters.end()){
162 path = m->hasPath(it->second);
163 //if the user has not given a path then, add inputdir. else leave path alone.
164 if (path == "") { parameters["taxonomy"] = inputDir + it->second; }
167 it = parameters.find("shared");
168 //user has given a template file
169 if(it != parameters.end()){
170 path = m->hasPath(it->second);
171 //if the user has not given a path then, add inputdir. else leave path alone.
172 if (path == "") { parameters["shared"] = inputDir + it->second; }
177 //check for required parameters
178 accnosfile = validParameter.validFile(parameters, "accnos", true);
179 if (accnosfile == "not open") { accnosfile = ""; abort = true; }
180 else if (accnosfile == "not found") { accnosfile = ""; }
181 else { m->setAccnosFile(accnosfile); }
183 fastafile = validParameter.validFile(parameters, "fasta", true);
184 if (fastafile == "not open") { fastafile = ""; abort = true; }
185 else if (fastafile == "not found") { fastafile = ""; }
186 else { m->setFastaFile(fastafile); }
188 namefile = validParameter.validFile(parameters, "name", true);
189 if (namefile == "not open") { namefile = ""; abort = true; }
190 else if (namefile == "not found") { namefile = ""; }
191 else { m->setNameFile(namefile); }
193 groupfile = validParameter.validFile(parameters, "group", true);
194 if (groupfile == "not open") { groupfile = ""; abort = true; }
195 else if (groupfile == "not found") { groupfile = ""; }
196 else { m->setGroupFile(groupfile); }
198 listfile = validParameter.validFile(parameters, "list", true);
199 if (listfile == "not open") { listfile = ""; abort = true; }
200 else if (listfile == "not found") { listfile = ""; }
201 else { m->setListFile(listfile); }
203 taxfile = validParameter.validFile(parameters, "taxonomy", true);
204 if (taxfile == "not open") { taxfile = ""; abort = true; }
205 else if (taxfile == "not found") { taxfile = ""; }
206 else { m->setTaxonomyFile(taxfile); }
208 groups = validParameter.validFile(parameters, "groups", false);
209 if (groups == "not found") { groups = ""; }
211 m->splitAtDash(groups, Groups);
212 m->setGroups(Groups);
215 sharedfile = validParameter.validFile(parameters, "shared", true);
216 if (sharedfile == "not open") { sharedfile = ""; abort = true; }
217 else if (sharedfile == "not found") { sharedfile = ""; }
218 else { m->setSharedFile(sharedfile); }
220 groupfile = validParameter.validFile(parameters, "group", true);
221 if (groupfile == "not open") { groupfile = ""; abort = true; }
222 else if (groupfile == "not found") { groupfile = ""; }
223 else { m->setGroupFile(groupfile); }
225 if ((sharedfile == "") && (groupfile == "")) {
226 //is there are current file available for any of these?
227 if ((namefile != "") || (fastafile != "") || (listfile != "") || (taxfile != "")) {
228 //give priority to group, then shared
229 groupfile = m->getGroupFile();
230 if (groupfile != "") { m->mothurOut("Using " + groupfile + " as input file for the group parameter."); m->mothurOutEndLine(); }
232 sharedfile = m->getSharedFile();
233 if (sharedfile != "") { m->mothurOut("Using " + sharedfile + " as input file for the shared parameter."); m->mothurOutEndLine(); }
235 m->mothurOut("You have no current groupfile or sharedfile and one is required."); m->mothurOutEndLine(); abort = true;
239 //give priority to shared, then group
240 sharedfile = m->getSharedFile();
241 if (sharedfile != "") { m->mothurOut("Using " + sharedfile + " as input file for the shared parameter."); m->mothurOutEndLine(); }
243 groupfile = m->getGroupFile();
244 if (groupfile != "") { m->mothurOut("Using " + groupfile + " as input file for the group parameter."); m->mothurOutEndLine(); }
246 m->mothurOut("You have no current groupfile or sharedfile and one is required."); m->mothurOutEndLine(); abort = true;
252 if ((accnosfile == "") && (Groups.size() == 0)) { m->mothurOut("You must provide an accnos file containing group names or specify groups using the groups parameter."); m->mothurOutEndLine(); abort = true; }
254 if ((fastafile == "") && (namefile == "") && (groupfile == "") && (sharedfile == "") && (listfile == "") && (taxfile == "")) { m->mothurOut("You must provide at least one of the following: fasta, name, taxonomy, group, shared or list."); m->mothurOutEndLine(); abort = true; }
255 if ((groupfile == "") && ((namefile != "") || (fastafile != "") || (listfile != "") || (taxfile != ""))) { m->mothurOut("If using a fasta, name, taxonomy, group or list, then you must provide a group file."); m->mothurOutEndLine(); abort = true; }
257 if ((namefile == "") && ((fastafile != "") || (taxfile != ""))){
258 vector<string> files; files.push_back(fastafile); files.push_back(taxfile);
259 parser.getNameFile(files);
265 catch(exception& e) {
266 m->errorOut(e, "RemoveGroupsCommand", "RemoveGroupsCommand");
270 //**********************************************************************************************************************
272 int RemoveGroupsCommand::execute(){
275 if (abort == true) { if (calledHelp) { return 0; } return 2; }
277 //get groups you want to remove
278 if (accnosfile != "") { readAccnos(); }
280 if (groupfile != "") {
281 groupMap = new GroupMap(groupfile);
284 //make sure groups are valid
285 //takes care of user setting groupNames that are invalid or setting groups=all
286 SharedUtil* util = new SharedUtil();
287 vector<string> namesGroups = groupMap->getNamesOfGroups();
288 util->setGroups(Groups, namesGroups);
291 //fill names with names of sequences that are from the groups we want to remove
297 if (m->control_pressed) { return 0; }
299 //read through the correct file and output lines you want to keep
300 if (namefile != "") { readName(); }
301 if (fastafile != "") { readFasta(); }
302 if (groupfile != "") { readGroup(); }
303 if (listfile != "") { readList(); }
304 if (taxfile != "") { readTax(); }
305 if (sharedfile != "") { readShared(); }
307 if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
309 if (outputNames.size() != 0) {
310 m->mothurOutEndLine();
311 m->mothurOut("Output File names: "); m->mothurOutEndLine();
312 for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); }
313 m->mothurOutEndLine();
315 //set fasta file as new current fastafile
317 itTypes = outputTypes.find("fasta");
318 if (itTypes != outputTypes.end()) {
319 if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setFastaFile(current); }
322 itTypes = outputTypes.find("name");
323 if (itTypes != outputTypes.end()) {
324 if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setNameFile(current); }
327 itTypes = outputTypes.find("group");
328 if (itTypes != outputTypes.end()) {
329 if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setGroupFile(current); }
332 itTypes = outputTypes.find("list");
333 if (itTypes != outputTypes.end()) {
334 if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setListFile(current); }
337 itTypes = outputTypes.find("taxonomy");
338 if (itTypes != outputTypes.end()) {
339 if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setTaxonomyFile(current); }
342 itTypes = outputTypes.find("shared");
343 if (itTypes != outputTypes.end()) {
344 if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setSharedFile(current); }
351 catch(exception& e) {
352 m->errorOut(e, "RemoveGroupsCommand", "execute");
357 //**********************************************************************************************************************
358 int RemoveGroupsCommand::readFasta(){
360 string thisOutputDir = outputDir;
361 if (outputDir == "") { thisOutputDir += m->hasPath(fastafile); }
362 string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(fastafile)) + "pick" + m->getExtension(fastafile);
365 m->openOutputFile(outputFileName, out);
368 m->openInputFile(fastafile, in);
371 bool wroteSomething = false;
372 int removedCount = 0;
375 if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; }
377 Sequence currSeq(in);
378 name = currSeq.getName();
381 //if this name is in the accnos file
382 if (names.count(name) == 0) {
383 wroteSomething = true;
384 currSeq.printSequence(out);
386 //if you are not in the accnos file check if you are a name that needs to be changed
387 map<string, string>::iterator it = uniqueToRedundant.find(name);
388 if (it != uniqueToRedundant.end()) {
389 wroteSomething = true;
390 currSeq.setName(it->second);
391 currSeq.printSequence(out);
392 }else { removedCount++; }
400 if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the groups you wish to remove."); m->mothurOutEndLine(); }
401 outputTypes["fasta"].push_back(outputFileName); outputNames.push_back(outputFileName);
403 m->mothurOut("Removed " + toString(removedCount) + " sequences from your fasta file."); m->mothurOutEndLine();
408 catch(exception& e) {
409 m->errorOut(e, "RemoveGroupsCommand", "readFasta");
413 //**********************************************************************************************************************
414 int RemoveGroupsCommand::readShared(){
416 string thisOutputDir = outputDir;
417 if (outputDir == "") { thisOutputDir += m->hasPath(sharedfile); }
419 //get group names from sharedfile so we can set Groups to the groupNames we want to keep
420 //that way we can take advantage of the reads in inputdata and sharedRabundVector
421 InputData* tempInput = new InputData(sharedfile, "sharedfile");
422 vector<SharedRAbundVector*> lookup = tempInput->getSharedRAbundVectors();
425 vector<string> allGroupsNames = m->getAllGroups();
426 vector<string> mothurOutGroups = m->getGroups();
428 vector<string> groupsToKeep;
429 for (int i = 0; i < allGroupsNames.size(); i++) {
430 if (!m->inUsersGroups(allGroupsNames[i], m->getGroups())) {
431 groupsToKeep.push_back(allGroupsNames[i]);
435 if (allGroupsNames.size() == groupsToKeep.size()) { m->mothurOut("Your file does not contain any groups you wish to remove."); m->mothurOutEndLine(); m->setGroups(mothurOutGroups); delete tempInput; for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } return 0; }
438 for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; }
440 m->setGroups(groupsToKeep);
443 m->saveNextLabel = "";
444 m->printedHeaders = false;
445 m->currentBinLabels.clear();
446 m->binLabelsInFile.clear();
448 InputData input(sharedfile, "sharedfile");
449 lookup = input.getSharedRAbundVectors();
451 bool wroteSomething = false;
453 while(lookup[0] != NULL) {
455 string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(sharedfile)) + lookup[0]->getLabel() + ".pick" + m->getExtension(sharedfile);
457 m->openOutputFile(outputFileName, out);
458 outputTypes["shared"].push_back(outputFileName); outputNames.push_back(outputFileName);
460 if (m->control_pressed) { out.close(); m->mothurRemove(outputFileName); for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } return 0; }
462 lookup[0]->printHeaders(out);
464 for (int i = 0; i < lookup.size(); i++) {
465 out << lookup[i]->getLabel() << '\t' << lookup[i]->getGroup() << '\t';
466 lookup[i]->print(out);
467 wroteSomething = true;
471 //get next line to process
472 //prevent memory leak
473 for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; }
474 lookup = input.getSharedRAbundVectors();
480 m->setGroups(mothurOutGroups);
482 if (wroteSomething == false) { m->mothurOut("Your file contains only the groups you wish to remove."); m->mothurOutEndLine(); }
484 string groupsString = "";
485 for (int i = 0; i < Groups.size()-1; i++) { groupsString += Groups[i] + ", "; }
486 groupsString += Groups[Groups.size()-1];
488 m->mothurOut("Removed groups: " + groupsString + " from your shared file."); m->mothurOutEndLine();
493 catch(exception& e) {
494 m->errorOut(e, "RemoveGroupsCommand", "readShared");
498 //**********************************************************************************************************************
499 int RemoveGroupsCommand::readList(){
501 string thisOutputDir = outputDir;
502 if (outputDir == "") { thisOutputDir += m->hasPath(listfile); }
503 string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(listfile)) + "pick" + m->getExtension(listfile);
506 m->openOutputFile(outputFileName, out);
509 m->openInputFile(listfile, in);
511 bool wroteSomething = false;
512 int removedCount = 0;
518 //read in list vector
521 //make a new list vector
523 newList.setLabel(list.getLabel());
526 for (int i = 0; i < list.getNumBins(); i++) {
527 if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; }
529 //parse out names that are in accnos file
530 string binnames = list.get(i);
532 string newNames = "";
533 while (binnames.find_first_of(',') != -1) {
534 string name = binnames.substr(0,binnames.find_first_of(','));
535 binnames = binnames.substr(binnames.find_first_of(',')+1, binnames.length());
537 //if that name is in the .accnos file, add it
538 if (names.count(name) == 0) { newNames += name + ","; }
540 //if you are not in the accnos file check if you are a name that needs to be changed
541 map<string, string>::iterator it = uniqueToRedundant.find(name);
542 if (it != uniqueToRedundant.end()) {
543 newNames += it->second + ",";
544 }else { removedCount++; }
549 if (names.count(binnames) == 0) { newNames += binnames + ","; }
550 else { //if you are not in the accnos file check if you are a name that needs to be changed
551 map<string, string>::iterator it = uniqueToRedundant.find(binnames);
552 if (it != uniqueToRedundant.end()) {
553 newNames += it->second + ",";
554 }else { removedCount++; }
557 //if there are names in this bin add to new list
558 if (newNames != "") {
559 newNames = newNames.substr(0, newNames.length()-1); //rip off extra comma
560 newList.push_back(newNames);
564 //print new listvector
565 if (newList.getNumBins() != 0) {
566 wroteSomething = true;
575 if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the groups you wish to remove."); m->mothurOutEndLine(); }
576 outputTypes["list"].push_back(outputFileName); outputNames.push_back(outputFileName);
578 m->mothurOut("Removed " + toString(removedCount) + " sequences from your list file."); m->mothurOutEndLine();
583 catch(exception& e) {
584 m->errorOut(e, "RemoveGroupsCommand", "readList");
588 //**********************************************************************************************************************
589 int RemoveGroupsCommand::readName(){
591 string thisOutputDir = outputDir;
592 if (outputDir == "") { thisOutputDir += m->hasPath(namefile); }
593 string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(namefile)) + "pick" + m->getExtension(namefile);
596 m->openOutputFile(outputFileName, out);
599 m->openInputFile(namefile, in);
600 string name, firstCol, secondCol;
602 bool wroteSomething = false;
603 int removedCount = 0;
606 if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; }
608 in >> firstCol; m->gobble(in);
611 vector<string> parsedNames;
612 m->splitAtComma(secondCol, parsedNames);
614 vector<string> validSecond; validSecond.clear();
615 for (int i = 0; i < parsedNames.size(); i++) {
616 if (names.count(parsedNames[i]) == 0) {
617 validSecond.push_back(parsedNames[i]);
621 removedCount += parsedNames.size()-validSecond.size();
623 //if the name in the first column is in the set then print it and any other names in second column also in set
624 if (names.count(firstCol) == 0) {
626 wroteSomething = true;
628 out << firstCol << '\t';
630 //you know you have at least one valid second since first column is valid
631 for (int i = 0; i < validSecond.size()-1; i++) { out << validSecond[i] << ','; }
632 out << validSecond[validSecond.size()-1] << endl;
634 //make first name in set you come to first column and then add the remaining names to second column
637 //you want part of this row
638 if (validSecond.size() != 0) {
640 wroteSomething = true;
642 out << validSecond[0] << '\t';
644 //you know you have at least one valid second since first column is valid
645 for (int i = 0; i < validSecond.size()-1; i++) { out << validSecond[i] << ','; }
646 out << validSecond[validSecond.size()-1] << endl;
647 uniqueToRedundant[firstCol] = validSecond[0];
656 if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the groups you wish to remove."); m->mothurOutEndLine(); }
657 outputTypes["name"].push_back(outputFileName); outputNames.push_back(outputFileName);
659 m->mothurOut("Removed " + toString(removedCount) + " sequences from your name file."); m->mothurOutEndLine();
663 catch(exception& e) {
664 m->errorOut(e, "RemoveGroupsCommand", "readName");
669 //**********************************************************************************************************************
670 int RemoveGroupsCommand::readGroup(){
672 string thisOutputDir = outputDir;
673 if (outputDir == "") { thisOutputDir += m->hasPath(groupfile); }
674 string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(groupfile)) + "pick" + m->getExtension(groupfile);
677 m->openOutputFile(outputFileName, out);
680 m->openInputFile(groupfile, in);
683 bool wroteSomething = false;
684 int removedCount = 0;
687 if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; }
689 in >> name; //read from first column
690 in >> group; //read from second column
692 //if this name is in the accnos file
693 if (names.count(name) == 0) {
694 wroteSomething = true;
695 out << name << '\t' << group << endl;
696 }else { removedCount++; }
703 if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the groups you wish to remove."); m->mothurOutEndLine(); }
704 outputTypes["group"].push_back(outputFileName); outputNames.push_back(outputFileName);
706 m->mothurOut("Removed " + toString(removedCount) + " sequences from your group file."); m->mothurOutEndLine();
711 catch(exception& e) {
712 m->errorOut(e, "RemoveGroupsCommand", "readGroup");
716 //**********************************************************************************************************************
717 int RemoveGroupsCommand::readTax(){
719 string thisOutputDir = outputDir;
720 if (outputDir == "") { thisOutputDir += m->hasPath(taxfile); }
721 string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(taxfile)) + "pick" + m->getExtension(taxfile);
723 m->openOutputFile(outputFileName, out);
726 m->openInputFile(taxfile, in);
729 bool wroteSomething = false;
730 int removedCount = 0;
733 if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; }
735 in >> name; //read from first column
736 in >> tax; //read from second column
738 //if this name is in the accnos file
739 if (names.count(name) == 0) {
740 wroteSomething = true;
741 out << name << '\t' << tax << endl;
742 }else { //if you are not in the accnos file check if you are a name that needs to be changed
743 map<string, string>::iterator it = uniqueToRedundant.find(name);
744 if (it != uniqueToRedundant.end()) {
745 wroteSomething = true;
746 out << it->second << '\t' << tax << endl;
747 }else { removedCount++; } }
754 if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the groups you wish to remove."); m->mothurOutEndLine(); }
755 outputTypes["taxonomy"].push_back(outputFileName); outputNames.push_back(outputFileName);
757 m->mothurOut("Removed " + toString(removedCount) + " sequences from your taxonomy file."); m->mothurOutEndLine();
761 catch(exception& e) {
762 m->errorOut(e, "RemoveGroupsCommand", "readTax");
766 //**********************************************************************************************************************
767 void RemoveGroupsCommand::readAccnos(){
772 m->openInputFile(accnosfile, in);
778 Groups.push_back(name);
784 m->setGroups(Groups);
787 catch(exception& e) {
788 m->errorOut(e, "RemoveGroupsCommand", "readAccnos");
792 //**********************************************************************************************************************
793 int RemoveGroupsCommand::fillNames(){
795 vector<string> seqs = groupMap->getNamesSeqs();
797 for (int i = 0; i < seqs.size(); i++) {
799 if (m->control_pressed) { return 0; }
801 string group = groupMap->getGroup(seqs[i]);
803 if (m->inUsersGroups(group, Groups)) {
804 names.insert(seqs[i]);
810 catch(exception& e) {
811 m->errorOut(e, "RemoveGroupsCommand", "fillNames");
816 //**********************************************************************************************************************