2 * removelineagecommand.cpp
5 * Created by westcott on 9/24/10.
6 * Copyright 2010 Schloss Lab. All rights reserved.
10 #include "removelineagecommand.h"
11 #include "sequence.hpp"
12 #include "listvector.hpp"
14 //**********************************************************************************************************************
15 vector<string> RemoveLineageCommand::getValidParameters(){
17 string Array[] = {"fasta","name", "group", "alignreport", "taxon", "dups", "list","taxonomy","outputdir","inputdir"};
18 vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
22 m->errorOut(e, "RemoveLineageCommand", "getValidParameters");
26 //**********************************************************************************************************************
27 RemoveLineageCommand::RemoveLineageCommand(){
30 //initialize outputTypes
31 vector<string> tempOutNames;
32 outputTypes["fasta"] = tempOutNames;
33 outputTypes["taxonomy"] = tempOutNames;
34 outputTypes["name"] = tempOutNames;
35 outputTypes["group"] = tempOutNames;
36 outputTypes["alignreport"] = tempOutNames;
37 outputTypes["list"] = tempOutNames;
40 m->errorOut(e, "RemoveLineageCommand", "RemoveLineageCommand");
44 //**********************************************************************************************************************
45 vector<string> RemoveLineageCommand::getRequiredParameters(){
47 string Array[] = {"taxonomy"};
48 vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
52 m->errorOut(e, "RemoveLineageCommand", "getRequiredParameters");
56 //**********************************************************************************************************************
57 vector<string> RemoveLineageCommand::getRequiredFiles(){
59 vector<string> myArray;
63 m->errorOut(e, "RemoveLineageCommand", "getRequiredFiles");
67 //**********************************************************************************************************************
68 RemoveLineageCommand::RemoveLineageCommand(string option) {
72 //allow user to run help
73 if(option == "help") { help(); abort = true; }
76 //valid paramters for this command
77 string Array[] = {"fasta","name", "group", "alignreport", "taxon", "dups", "list","taxonomy","outputdir","inputdir"};
78 vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
80 OptionParser parser(option);
81 map<string,string> parameters = parser.getParameters();
83 ValidParameters validParameter;
84 map<string,string>::iterator it;
86 //check to make sure all parameters are valid for command
87 for (it = parameters.begin(); it != parameters.end(); it++) {
88 if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; }
91 //initialize outputTypes
92 vector<string> tempOutNames;
93 outputTypes["fasta"] = tempOutNames;
94 outputTypes["taxonomy"] = tempOutNames;
95 outputTypes["name"] = tempOutNames;
96 outputTypes["group"] = tempOutNames;
97 outputTypes["alignreport"] = tempOutNames;
98 outputTypes["list"] = tempOutNames;
100 //if the user changes the output directory command factory will send this info to us in the output parameter
101 outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){ outputDir = ""; }
103 //if the user changes the input directory command factory will send this info to us in the output parameter
104 string inputDir = validParameter.validFile(parameters, "inputdir", false);
105 if (inputDir == "not found"){ inputDir = ""; }
108 it = parameters.find("alignreport");
109 //user has given a template file
110 if(it != parameters.end()){
111 path = m->hasPath(it->second);
112 //if the user has not given a path then, add inputdir. else leave path alone.
113 if (path == "") { parameters["alignreport"] = inputDir + it->second; }
116 it = parameters.find("fasta");
117 //user has given a template file
118 if(it != parameters.end()){
119 path = m->hasPath(it->second);
120 //if the user has not given a path then, add inputdir. else leave path alone.
121 if (path == "") { parameters["fasta"] = inputDir + it->second; }
124 it = parameters.find("list");
125 //user has given a template file
126 if(it != parameters.end()){
127 path = m->hasPath(it->second);
128 //if the user has not given a path then, add inputdir. else leave path alone.
129 if (path == "") { parameters["list"] = inputDir + it->second; }
132 it = parameters.find("name");
133 //user has given a template file
134 if(it != parameters.end()){
135 path = m->hasPath(it->second);
136 //if the user has not given a path then, add inputdir. else leave path alone.
137 if (path == "") { parameters["name"] = inputDir + it->second; }
140 it = parameters.find("group");
141 //user has given a template file
142 if(it != parameters.end()){
143 path = m->hasPath(it->second);
144 //if the user has not given a path then, add inputdir. else leave path alone.
145 if (path == "") { parameters["group"] = inputDir + it->second; }
148 it = parameters.find("taxonomy");
149 //user has given a template file
150 if(it != parameters.end()){
151 path = m->hasPath(it->second);
152 //if the user has not given a path then, add inputdir. else leave path alone.
153 if (path == "") { parameters["taxonomy"] = inputDir + it->second; }
158 //check for required parameters
159 fastafile = validParameter.validFile(parameters, "fasta", true);
160 if (fastafile == "not open") { abort = true; }
161 else if (fastafile == "not found") { fastafile = ""; }
163 namefile = validParameter.validFile(parameters, "name", true);
164 if (namefile == "not open") { abort = true; }
165 else if (namefile == "not found") { namefile = ""; }
167 groupfile = validParameter.validFile(parameters, "group", true);
168 if (groupfile == "not open") { abort = true; }
169 else if (groupfile == "not found") { groupfile = ""; }
171 alignfile = validParameter.validFile(parameters, "alignreport", true);
172 if (alignfile == "not open") { abort = true; }
173 else if (alignfile == "not found") { alignfile = ""; }
175 listfile = validParameter.validFile(parameters, "list", true);
176 if (listfile == "not open") { abort = true; }
177 else if (listfile == "not found") { listfile = ""; }
179 taxfile = validParameter.validFile(parameters, "taxonomy", true);
180 if (taxfile == "not open") { abort = true; }
181 else if (taxfile == "not found") { taxfile = ""; m->mothurOut("The taxonomy parameter is required for the get.lineage command."); m->mothurOutEndLine(); abort = true; }
183 string usedDups = "true";
184 string temp = validParameter.validFile(parameters, "dups", false);
185 if (temp == "not found") {
186 if (namefile != "") { temp = "true"; }
187 else { temp = "false"; usedDups = ""; }
189 dups = m->isTrue(temp);
191 taxons = validParameter.validFile(parameters, "taxon", false);
192 if (taxons == "not found") { taxons = ""; m->mothurOut("No taxons given, please correct."); m->mothurOutEndLine(); abort = true; }
195 if (taxons[0] == '\'') { taxons = taxons.substr(1); }
196 if (taxons[(taxons.length()-1)] == '\'') { taxons = taxons.substr(0, (taxons.length()-1)); }
200 if ((fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == "") && (taxfile == "")) { m->mothurOut("You must provide one of the following: fasta, name, group, alignreport, taxonomy or listfile."); m->mothurOutEndLine(); abort = true; }
202 if ((usedDups != "") && (namefile == "")) { m->mothurOut("You may only use dups with the name option."); m->mothurOutEndLine(); abort = true; }
207 catch(exception& e) {
208 m->errorOut(e, "RemoveLineageCommand", "RemoveLineageCommand");
212 //**********************************************************************************************************************
214 void RemoveLineageCommand::help(){
216 m->mothurOut("The remove.lineage command reads a taxonomy file and any of the following file types: fasta, name, group, list or alignreport file.\n");
217 m->mothurOut("It outputs a file containing only the sequences from the taxonomy file that are not from the taxon you requested to be removed.\n");
218 m->mothurOut("The remove.lineage command parameters are taxon, fasta, name, group, list, taxonomy, alignreport and dups. You must provide taxonomy and taxon.\n");
219 m->mothurOut("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");
220 m->mothurOut("The taxon parameter allows you to select the taxons you would like to remove.\n");
221 m->mothurOut("The remove.lineage command should be in the following format: remove.lineage(taxonomy=yourTaxonomyFile, taxon=yourTaxons).\n");
222 m->mothurOut("Example remove.lineage(taxonomy=amazon.silva.taxonomy, taxon=Bacteria;Firmicutes;Bacilli;Lactobacillales;).\n");
223 m->mothurOut("Note: If you are running mothur in script mode you must wrap the taxon in ' characters so mothur will ignore the ; in the taxon.\n");
224 m->mothurOut("Example remove.lineage(taxonomy=amazon.silva.taxonomy, taxon='Bacteria;Firmicutes;Bacilli;Lactobacillales;').\n");
225 m->mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n\n");
227 catch(exception& e) {
228 m->errorOut(e, "RemoveLineageCommand", "help");
233 //**********************************************************************************************************************
235 int RemoveLineageCommand::execute(){
238 if (abort == true) { return 0; }
240 if (m->control_pressed) { return 0; }
242 //read through the correct file and output lines you want to keep
243 if (taxfile != "") { readTax(); } //fills the set of names to remove
244 if (namefile != "") { readName(); }
245 if (fastafile != "") { readFasta(); }
246 if (groupfile != "") { readGroup(); }
247 if (alignfile != "") { readAlign(); }
248 if (listfile != "") { readList(); }
251 if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; }
253 if (outputNames.size() != 0) {
254 m->mothurOutEndLine();
255 m->mothurOut("Output File Names: "); m->mothurOutEndLine();
256 for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); }
257 m->mothurOutEndLine();
263 catch(exception& e) {
264 m->errorOut(e, "RemoveLineageCommand", "execute");
269 //**********************************************************************************************************************
270 int RemoveLineageCommand::readFasta(){
272 string thisOutputDir = outputDir;
273 if (outputDir == "") { thisOutputDir += m->hasPath(fastafile); }
274 string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(fastafile)) + "pick" + m->getExtension(fastafile);
277 m->openOutputFile(outputFileName, out);
280 m->openInputFile(fastafile, in);
283 bool wroteSomething = false;
286 if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; }
288 Sequence currSeq(in);
289 name = currSeq.getName();
292 //if this name is in the accnos file
293 if (names.count(name) == 0) {
294 wroteSomething = true;
296 currSeq.printSequence(out);
304 if (wroteSomething == false) { m->mothurOut("Your fasta file contains only sequences from " + taxons + "."); m->mothurOutEndLine(); }
305 outputNames.push_back(outputFileName); outputTypes["fasta"].push_back(outputFileName);
310 catch(exception& e) {
311 m->errorOut(e, "RemoveLineageCommand", "readFasta");
315 //**********************************************************************************************************************
316 int RemoveLineageCommand::readList(){
318 string thisOutputDir = outputDir;
319 if (outputDir == "") { thisOutputDir += m->hasPath(listfile); }
320 string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(listfile)) + "pick" + m->getExtension(listfile);
323 m->openOutputFile(outputFileName, out);
326 m->openInputFile(listfile, in);
328 bool wroteSomething = false;
331 //read in list vector
334 //make a new list vector
336 newList.setLabel(list.getLabel());
339 for (int i = 0; i < list.getNumBins(); i++) {
340 if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; }
342 //parse out names that are in accnos file
343 string binnames = list.get(i);
345 string newNames = "";
346 while (binnames.find_first_of(',') != -1) {
347 string name = binnames.substr(0,binnames.find_first_of(','));
348 binnames = binnames.substr(binnames.find_first_of(',')+1, binnames.length());
350 //if that name is in the .accnos file, add it
351 if (names.count(name) == 0) { newNames += name + ","; }
355 if (names.count(binnames) == 0) { newNames += binnames + ","; }
357 //if there are names in this bin add to new list
358 if (newNames != "") {
359 newNames = newNames.substr(0, newNames.length()-1); //rip off extra comma
360 newList.push_back(newNames);
364 //print new listvector
365 if (newList.getNumBins() != 0) {
366 wroteSomething = true;
375 if (wroteSomething == false) { m->mothurOut("Your list file contains only sequences from " + taxons + "."); m->mothurOutEndLine(); }
376 outputNames.push_back(outputFileName); outputTypes["list"].push_back(outputFileName);
381 catch(exception& e) {
382 m->errorOut(e, "RemoveLineageCommand", "readList");
386 //**********************************************************************************************************************
387 int RemoveLineageCommand::readName(){
389 string thisOutputDir = outputDir;
390 if (outputDir == "") { thisOutputDir += m->hasPath(namefile); }
391 string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(namefile)) + "pick" + m->getExtension(namefile);
394 m->openOutputFile(outputFileName, out);
397 m->openInputFile(namefile, in);
398 string name, firstCol, secondCol;
400 bool wroteSomething = false;
403 if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; }
408 vector<string> parsedNames;
409 //parse second column saving each name
410 while (secondCol.find_first_of(',') != -1) {
411 name = secondCol.substr(0,secondCol.find_first_of(','));
412 secondCol = secondCol.substr(secondCol.find_first_of(',')+1, secondCol.length());
413 parsedNames.push_back(name);
416 //get name after last ,
417 parsedNames.push_back(secondCol);
419 vector<string> validSecond; validSecond.clear();
420 for (int i = 0; i < parsedNames.size(); i++) {
421 if (names.count(parsedNames[i]) == 0) {
422 validSecond.push_back(parsedNames[i]);
426 if ((dups) && (validSecond.size() != parsedNames.size())) { //if dups is true and we want to get rid of anyone, get rid of everyone
427 for (int i = 0; i < parsedNames.size(); i++) { names.insert(parsedNames[i]); }
429 //if the name in the first column is in the set then print it and any other names in second column also in set
430 if (names.count(firstCol) == 0) {
432 wroteSomething = true;
434 out << firstCol << '\t';
436 //you know you have at least one valid second since first column is valid
437 for (int i = 0; i < validSecond.size()-1; i++) { out << validSecond[i] << ','; }
438 out << validSecond[validSecond.size()-1] << endl;
440 //make first name in set you come to first column and then add the remaining names to second column
443 //you want part of this row
444 if (validSecond.size() != 0) {
446 wroteSomething = true;
448 out << validSecond[0] << '\t';
450 //you know you have at least one valid second since first column is valid
451 for (int i = 0; i < validSecond.size()-1; i++) { out << validSecond[i] << ','; }
452 out << validSecond[validSecond.size()-1] << endl;
461 if (wroteSomething == false) { m->mothurOut("Your name file contains only sequences from " + taxons + "."); m->mothurOutEndLine(); }
462 outputNames.push_back(outputFileName); outputTypes["name"].push_back(outputFileName);
466 catch(exception& e) {
467 m->errorOut(e, "RemoveLineageCommand", "readName");
472 //**********************************************************************************************************************
473 int RemoveLineageCommand::readGroup(){
475 string thisOutputDir = outputDir;
476 if (outputDir == "") { thisOutputDir += m->hasPath(groupfile); }
477 string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(groupfile)) + "pick" + m->getExtension(groupfile);
480 m->openOutputFile(outputFileName, out);
483 m->openInputFile(groupfile, in);
486 bool wroteSomething = false;
489 if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; }
491 in >> name; //read from first column
492 in >> group; //read from second column
494 //if this name is in the accnos file
495 if (names.count(name) == 0) {
496 wroteSomething = true;
497 out << name << '\t' << group << endl;
505 if (wroteSomething == false) { m->mothurOut("Your group file contains only sequences from " + taxons + "."); m->mothurOutEndLine(); }
506 outputNames.push_back(outputFileName); outputTypes["group"].push_back(outputFileName);
510 catch(exception& e) {
511 m->errorOut(e, "RemoveLineageCommand", "readGroup");
515 //**********************************************************************************************************************
516 int RemoveLineageCommand::readTax(){
518 string thisOutputDir = outputDir;
519 if (outputDir == "") { thisOutputDir += m->hasPath(taxfile); }
520 string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(taxfile)) + "pick" + m->getExtension(taxfile);
522 m->openOutputFile(outputFileName, out);
525 m->openInputFile(taxfile, in);
528 bool wroteSomething = false;
532 if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; }
534 in >> name; //read from first column
535 in >> tax; //read from second column
539 //if the users file contains confidence scores we want to ignore them when searching for the taxons
540 int hasConfidences = tax.find_first_of('(');
541 if (hasConfidences != string::npos) {
542 newtax = removeConfidences(tax);
545 int pos = newtax.find(taxons);
547 if (pos == string::npos) {
548 wroteSomething = true;
549 out << name << '\t' << tax << endl;
550 }else{ //this sequence contains the taxon the user wants to remove
559 if (!wroteSomething) { m->mothurOut("Your taxonomy file contains only sequences from " + taxons + "."); m->mothurOutEndLine(); }
560 outputNames.push_back(outputFileName); outputTypes["taxonomy"].push_back(outputFileName);
565 catch(exception& e) {
566 m->errorOut(e, "RemoveLineageCommand", "readTax");
570 /**************************************************************************************************/
571 string RemoveLineageCommand::removeConfidences(string tax) {
575 int taxLength = tax.length();
576 for(int i=0;i<taxLength;i++){
578 taxon = taxon.substr(0, taxon.find_first_of('(')); //rip off confidence
588 catch(exception& e) {
589 m->errorOut(e, "RemoveLineageCommand", "removeConfidences");
593 //**********************************************************************************************************************
594 //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
595 int RemoveLineageCommand::readAlign(){
597 string thisOutputDir = outputDir;
598 if (outputDir == "") { thisOutputDir += m->hasPath(alignfile); }
599 string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(alignfile)) + "pick.align.report";
602 m->openOutputFile(outputFileName, out);
605 m->openInputFile(alignfile, in);
608 bool wroteSomething = false;
610 //read column headers
611 for (int i = 0; i < 16; i++) {
612 if (!in.eof()) { in >> junk; out << junk << '\t'; }
618 if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; }
620 in >> name; //read from first column
622 //if this name is in the accnos file
623 if (names.count(name) == 0) {
624 wroteSomething = true;
629 for (int i = 0; i < 15; i++) {
630 if (!in.eof()) { in >> junk; out << junk << '\t'; }
635 }else {//still read just don't do anything with it
638 for (int i = 0; i < 15; i++) {
639 if (!in.eof()) { in >> junk; }
649 if (wroteSomething == false) { m->mothurOut("Your align file contains only sequences from " + taxons + "."); m->mothurOutEndLine(); }
650 outputNames.push_back(outputFileName); outputTypes["alignreport"].push_back(outputFileName);
655 catch(exception& e) {
656 m->errorOut(e, "RemoveLineageCommand", "readAlign");
660 //**********************************************************************************************************************