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", "FNGLT", "none",false,false); parameters.push_back(pfasta);
20 CommandParameter pshared("shared", "InputTypes", "", "", "none", "FNGLT-sharedGroup", "none",false,false); parameters.push_back(pshared);
21 CommandParameter pname("name", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pname);
22 CommandParameter pgroup("group", "InputTypes", "", "", "none", "FNGLT-sharedGroup", "none",false,false); parameters.push_back(pgroup);
23 CommandParameter plist("list", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(plist);
24 CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "none", "FNGLT", "none",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") { abort = true; }
195 else if (groupfile == "not found") {
196 //if there is a current group file, use it
197 groupfile = m->getGroupFile();
198 if (groupfile != "") { m->mothurOut("Using " + groupfile + " as input file for the group parameter."); m->mothurOutEndLine(); }
199 else { m->mothurOut("You have no current groupfile and the group parameter is required."); m->mothurOutEndLine(); abort = true; }
200 }else { m->setGroupFile(groupfile); }
202 listfile = validParameter.validFile(parameters, "list", true);
203 if (listfile == "not open") { listfile = ""; abort = true; }
204 else if (listfile == "not found") { listfile = ""; }
205 else { m->setListFile(listfile); }
207 taxfile = validParameter.validFile(parameters, "taxonomy", true);
208 if (taxfile == "not open") { taxfile = ""; abort = true; }
209 else if (taxfile == "not found") { taxfile = ""; }
210 else { m->setTaxonomyFile(taxfile); }
212 groups = validParameter.validFile(parameters, "groups", false);
213 if (groups == "not found") { groups = ""; }
215 m->splitAtDash(groups, Groups);
216 m->setGroups(Groups);
219 sharedfile = validParameter.validFile(parameters, "shared", true);
220 if (sharedfile == "not open") { sharedfile = ""; abort = true; }
221 else if (sharedfile == "not found") { sharedfile = ""; }
222 else { m->setSharedFile(sharedfile); }
224 groupfile = validParameter.validFile(parameters, "group", true);
225 if (groupfile == "not open") { groupfile = ""; abort = true; }
226 else if (groupfile == "not found") { groupfile = ""; }
227 else { m->setGroupFile(groupfile); }
229 if ((sharedfile == "") && (groupfile == "")) {
230 //is there are current file available for any of these?
231 if ((namefile != "") || (fastafile != "") || (listfile != "") || (taxfile != "")) {
232 //give priority to group, then shared
233 groupfile = m->getGroupFile();
234 if (groupfile != "") { m->mothurOut("Using " + groupfile + " as input file for the group parameter."); m->mothurOutEndLine(); }
236 sharedfile = m->getSharedFile();
237 if (sharedfile != "") { m->mothurOut("Using " + sharedfile + " as input file for the shared parameter."); m->mothurOutEndLine(); }
239 m->mothurOut("You have no current groupfile or sharedfile and one is required."); m->mothurOutEndLine(); abort = true;
243 //give priority to shared, then group
244 sharedfile = m->getSharedFile();
245 if (sharedfile != "") { m->mothurOut("Using " + sharedfile + " as input file for the shared parameter."); m->mothurOutEndLine(); }
247 groupfile = m->getGroupFile();
248 if (groupfile != "") { m->mothurOut("Using " + groupfile + " as input file for the group parameter."); m->mothurOutEndLine(); }
250 m->mothurOut("You have no current groupfile or sharedfile and one is required."); m->mothurOutEndLine(); abort = true;
256 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; }
258 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; }
259 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; }
263 catch(exception& e) {
264 m->errorOut(e, "RemoveGroupsCommand", "RemoveGroupsCommand");
268 //**********************************************************************************************************************
270 int RemoveGroupsCommand::execute(){
273 if (abort == true) { if (calledHelp) { return 0; } return 2; }
275 //get groups you want to remove
276 if (accnosfile != "") { readAccnos(); }
278 if (groupfile != "") {
279 groupMap = new GroupMap(groupfile);
282 //make sure groups are valid
283 //takes care of user setting groupNames that are invalid or setting groups=all
284 SharedUtil* util = new SharedUtil();
285 vector<string> namesGroups = groupMap->getNamesOfGroups();
286 util->setGroups(Groups, namesGroups);
289 //fill names with names of sequences that are from the groups we want to remove
295 if (m->control_pressed) { return 0; }
297 //read through the correct file and output lines you want to keep
298 if (namefile != "") { readName(); }
299 if (fastafile != "") { readFasta(); }
300 if (groupfile != "") { readGroup(); }
301 if (listfile != "") { readList(); }
302 if (taxfile != "") { readTax(); }
303 if (sharedfile != "") { readShared(); }
305 if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
307 if (outputNames.size() != 0) {
308 m->mothurOutEndLine();
309 m->mothurOut("Output File names: "); m->mothurOutEndLine();
310 for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); }
311 m->mothurOutEndLine();
313 //set fasta file as new current fastafile
315 itTypes = outputTypes.find("fasta");
316 if (itTypes != outputTypes.end()) {
317 if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setFastaFile(current); }
320 itTypes = outputTypes.find("name");
321 if (itTypes != outputTypes.end()) {
322 if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setNameFile(current); }
325 itTypes = outputTypes.find("group");
326 if (itTypes != outputTypes.end()) {
327 if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setGroupFile(current); }
330 itTypes = outputTypes.find("list");
331 if (itTypes != outputTypes.end()) {
332 if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setListFile(current); }
335 itTypes = outputTypes.find("taxonomy");
336 if (itTypes != outputTypes.end()) {
337 if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setTaxonomyFile(current); }
340 itTypes = outputTypes.find("shared");
341 if (itTypes != outputTypes.end()) {
342 if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setSharedFile(current); }
349 catch(exception& e) {
350 m->errorOut(e, "RemoveGroupsCommand", "execute");
355 //**********************************************************************************************************************
356 int RemoveGroupsCommand::readFasta(){
358 string thisOutputDir = outputDir;
359 if (outputDir == "") { thisOutputDir += m->hasPath(fastafile); }
360 string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(fastafile)) + "pick" + m->getExtension(fastafile);
363 m->openOutputFile(outputFileName, out);
366 m->openInputFile(fastafile, in);
369 bool wroteSomething = false;
370 int removedCount = 0;
373 if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; }
375 Sequence currSeq(in);
376 name = currSeq.getName();
379 //if this name is in the accnos file
380 if (names.count(name) == 0) {
381 wroteSomething = true;
382 currSeq.printSequence(out);
384 //if you are not in the accnos file check if you are a name that needs to be changed
385 map<string, string>::iterator it = uniqueToRedundant.find(name);
386 if (it != uniqueToRedundant.end()) {
387 wroteSomething = true;
388 currSeq.setName(it->second);
389 currSeq.printSequence(out);
390 }else { removedCount++; }
398 if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the groups you wish to remove."); m->mothurOutEndLine(); }
399 outputTypes["fasta"].push_back(outputFileName); outputNames.push_back(outputFileName);
401 m->mothurOut("Removed " + toString(removedCount) + " sequences from your fasta file."); m->mothurOutEndLine();
406 catch(exception& e) {
407 m->errorOut(e, "RemoveGroupsCommand", "readFasta");
411 //**********************************************************************************************************************
412 int RemoveGroupsCommand::readShared(){
414 string thisOutputDir = outputDir;
415 if (outputDir == "") { thisOutputDir += m->hasPath(sharedfile); }
417 //get group names from sharedfile so we can set Groups to the groupNames we want to keep
418 //that way we can take advantage of the reads in inputdata and sharedRabundVector
419 InputData* tempInput = new InputData(sharedfile, "sharedfile");
420 vector<SharedRAbundVector*> lookup = tempInput->getSharedRAbundVectors();
423 vector<string> allGroupsNames = m->getAllGroups();
424 vector<string> mothurOutGroups = m->getGroups();
426 vector<string> groupsToKeep;
427 for (int i = 0; i < allGroupsNames.size(); i++) {
428 if (!m->inUsersGroups(allGroupsNames[i], m->getGroups())) {
429 groupsToKeep.push_back(allGroupsNames[i]);
433 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; }
436 for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; }
438 m->setGroups(groupsToKeep);
441 m->saveNextLabel = "";
442 m->printedHeaders = false;
443 m->currentBinLabels.clear();
444 m->binLabelsInFile.clear();
446 InputData input(sharedfile, "sharedfile");
447 lookup = input.getSharedRAbundVectors();
449 bool wroteSomething = false;
451 while(lookup[0] != NULL) {
453 string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(sharedfile)) + lookup[0]->getLabel() + ".pick" + m->getExtension(sharedfile);
455 m->openOutputFile(outputFileName, out);
456 outputTypes["shared"].push_back(outputFileName); outputNames.push_back(outputFileName);
458 if (m->control_pressed) { out.close(); m->mothurRemove(outputFileName); for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } return 0; }
460 lookup[0]->printHeaders(out);
462 for (int i = 0; i < lookup.size(); i++) {
463 out << lookup[i]->getLabel() << '\t' << lookup[i]->getGroup() << '\t';
464 lookup[i]->print(out);
465 wroteSomething = true;
469 //get next line to process
470 //prevent memory leak
471 for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; }
472 lookup = input.getSharedRAbundVectors();
478 m->setGroups(mothurOutGroups);
480 if (wroteSomething == false) { m->mothurOut("Your file contains only the groups you wish to remove."); m->mothurOutEndLine(); }
482 string groupsString = "";
483 for (int i = 0; i < Groups.size()-1; i++) { groupsString += Groups[i] + ", "; }
484 groupsString += Groups[Groups.size()-1];
486 m->mothurOut("Removed groups: " + groupsString + " from your shared file."); m->mothurOutEndLine();
491 catch(exception& e) {
492 m->errorOut(e, "RemoveGroupsCommand", "readShared");
496 //**********************************************************************************************************************
497 int RemoveGroupsCommand::readList(){
499 string thisOutputDir = outputDir;
500 if (outputDir == "") { thisOutputDir += m->hasPath(listfile); }
501 string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(listfile)) + "pick" + m->getExtension(listfile);
504 m->openOutputFile(outputFileName, out);
507 m->openInputFile(listfile, in);
509 bool wroteSomething = false;
510 int removedCount = 0;
516 //read in list vector
519 //make a new list vector
521 newList.setLabel(list.getLabel());
524 for (int i = 0; i < list.getNumBins(); i++) {
525 if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; }
527 //parse out names that are in accnos file
528 string binnames = list.get(i);
530 string newNames = "";
531 while (binnames.find_first_of(',') != -1) {
532 string name = binnames.substr(0,binnames.find_first_of(','));
533 binnames = binnames.substr(binnames.find_first_of(',')+1, binnames.length());
535 //if that name is in the .accnos file, add it
536 if (names.count(name) == 0) { newNames += name + ","; }
538 //if you are not in the accnos file check if you are a name that needs to be changed
539 map<string, string>::iterator it = uniqueToRedundant.find(name);
540 if (it != uniqueToRedundant.end()) {
541 newNames += it->second + ",";
542 }else { removedCount++; }
547 if (names.count(binnames) == 0) { newNames += binnames + ","; }
548 else { //if you are not in the accnos file check if you are a name that needs to be changed
549 map<string, string>::iterator it = uniqueToRedundant.find(binnames);
550 if (it != uniqueToRedundant.end()) {
551 newNames += it->second + ",";
552 }else { removedCount++; }
555 //if there are names in this bin add to new list
556 if (newNames != "") {
557 newNames = newNames.substr(0, newNames.length()-1); //rip off extra comma
558 newList.push_back(newNames);
562 //print new listvector
563 if (newList.getNumBins() != 0) {
564 wroteSomething = true;
573 if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the groups you wish to remove."); m->mothurOutEndLine(); }
574 outputTypes["list"].push_back(outputFileName); outputNames.push_back(outputFileName);
576 m->mothurOut("Removed " + toString(removedCount) + " sequences from your list file."); m->mothurOutEndLine();
581 catch(exception& e) {
582 m->errorOut(e, "RemoveGroupsCommand", "readList");
586 //**********************************************************************************************************************
587 int RemoveGroupsCommand::readName(){
589 string thisOutputDir = outputDir;
590 if (outputDir == "") { thisOutputDir += m->hasPath(namefile); }
591 string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(namefile)) + "pick" + m->getExtension(namefile);
594 m->openOutputFile(outputFileName, out);
597 m->openInputFile(namefile, in);
598 string name, firstCol, secondCol;
600 bool wroteSomething = false;
601 int removedCount = 0;
604 if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; }
606 in >> firstCol; m->gobble(in);
609 vector<string> parsedNames;
610 m->splitAtComma(secondCol, parsedNames);
612 vector<string> validSecond; validSecond.clear();
613 for (int i = 0; i < parsedNames.size(); i++) {
614 if (names.count(parsedNames[i]) == 0) {
615 validSecond.push_back(parsedNames[i]);
619 removedCount += parsedNames.size()-validSecond.size();
621 //if the name in the first column is in the set then print it and any other names in second column also in set
622 if (names.count(firstCol) == 0) {
624 wroteSomething = true;
626 out << firstCol << '\t';
628 //you know you have at least one valid second since first column is valid
629 for (int i = 0; i < validSecond.size()-1; i++) { out << validSecond[i] << ','; }
630 out << validSecond[validSecond.size()-1] << endl;
632 //make first name in set you come to first column and then add the remaining names to second column
635 //you want part of this row
636 if (validSecond.size() != 0) {
638 wroteSomething = true;
640 out << validSecond[0] << '\t';
642 //you know you have at least one valid second since first column is valid
643 for (int i = 0; i < validSecond.size()-1; i++) { out << validSecond[i] << ','; }
644 out << validSecond[validSecond.size()-1] << endl;
645 uniqueToRedundant[firstCol] = validSecond[0];
654 if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the groups you wish to remove."); m->mothurOutEndLine(); }
655 outputTypes["name"].push_back(outputFileName); outputNames.push_back(outputFileName);
657 m->mothurOut("Removed " + toString(removedCount) + " sequences from your name file."); m->mothurOutEndLine();
661 catch(exception& e) {
662 m->errorOut(e, "RemoveGroupsCommand", "readName");
667 //**********************************************************************************************************************
668 int RemoveGroupsCommand::readGroup(){
670 string thisOutputDir = outputDir;
671 if (outputDir == "") { thisOutputDir += m->hasPath(groupfile); }
672 string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(groupfile)) + "pick" + m->getExtension(groupfile);
675 m->openOutputFile(outputFileName, out);
678 m->openInputFile(groupfile, in);
681 bool wroteSomething = false;
682 int removedCount = 0;
685 if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; }
687 in >> name; //read from first column
688 in >> group; //read from second column
690 //if this name is in the accnos file
691 if (names.count(name) == 0) {
692 wroteSomething = true;
693 out << name << '\t' << group << endl;
694 }else { removedCount++; }
701 if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the groups you wish to remove."); m->mothurOutEndLine(); }
702 outputTypes["group"].push_back(outputFileName); outputNames.push_back(outputFileName);
704 m->mothurOut("Removed " + toString(removedCount) + " sequences from your group file."); m->mothurOutEndLine();
709 catch(exception& e) {
710 m->errorOut(e, "RemoveGroupsCommand", "readGroup");
714 //**********************************************************************************************************************
715 int RemoveGroupsCommand::readTax(){
717 string thisOutputDir = outputDir;
718 if (outputDir == "") { thisOutputDir += m->hasPath(taxfile); }
719 string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(taxfile)) + "pick" + m->getExtension(taxfile);
721 m->openOutputFile(outputFileName, out);
724 m->openInputFile(taxfile, in);
727 bool wroteSomething = false;
728 int removedCount = 0;
731 if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; }
733 in >> name; //read from first column
734 in >> tax; //read from second column
736 //if this name is in the accnos file
737 if (names.count(name) == 0) {
738 wroteSomething = true;
739 out << name << '\t' << tax << endl;
740 }else { //if you are not in the accnos file check if you are a name that needs to be changed
741 map<string, string>::iterator it = uniqueToRedundant.find(name);
742 if (it != uniqueToRedundant.end()) {
743 wroteSomething = true;
744 out << it->second << '\t' << tax << endl;
745 }else { removedCount++; } }
752 if (wroteSomething == false) { m->mothurOut("Your file contains only sequences from the groups you wish to remove."); m->mothurOutEndLine(); }
753 outputTypes["taxonomy"].push_back(outputFileName); outputNames.push_back(outputFileName);
755 m->mothurOut("Removed " + toString(removedCount) + " sequences from your taxonomy file."); m->mothurOutEndLine();
759 catch(exception& e) {
760 m->errorOut(e, "RemoveGroupsCommand", "readTax");
764 //**********************************************************************************************************************
765 void RemoveGroupsCommand::readAccnos(){
770 m->openInputFile(accnosfile, in);
776 Groups.push_back(name);
782 m->setGroups(Groups);
785 catch(exception& e) {
786 m->errorOut(e, "RemoveGroupsCommand", "readAccnos");
790 //**********************************************************************************************************************
791 int RemoveGroupsCommand::fillNames(){
793 vector<string> seqs = groupMap->getNamesSeqs();
795 for (int i = 0; i < seqs.size(); i++) {
797 if (m->control_pressed) { return 0; }
799 string group = groupMap->getGroup(seqs[i]);
801 if (m->inUsersGroups(group, Groups)) {
802 names.insert(seqs[i]);
808 catch(exception& e) {
809 m->errorOut(e, "RemoveGroupsCommand", "fillNames");
814 //**********************************************************************************************************************