2 * getlineagecommand.cpp
5 * Created by westcott on 9/24/10.
6 * Copyright 2010 Schloss Lab. All rights reserved.
10 #include "getlineagecommand.h"
11 #include "sequence.hpp"
12 #include "listvector.hpp"
15 //**********************************************************************************************************************
16 vector<string> GetLineageCommand::getValidParameters(){
18 string Array[] = {"fasta","name", "group", "alignreport", "taxon", "dups", "list","taxonomy","outputdir","inputdir"};
19 vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
23 m->errorOut(e, "GetLineageCommand", "getValidParameters");
27 //**********************************************************************************************************************
28 GetLineageCommand::GetLineageCommand(){
31 //initialize outputTypes
32 vector<string> tempOutNames;
33 outputTypes["fasta"] = tempOutNames;
34 outputTypes["taxonomy"] = tempOutNames;
35 outputTypes["name"] = tempOutNames;
36 outputTypes["group"] = tempOutNames;
37 outputTypes["alignreport"] = tempOutNames;
38 outputTypes["list"] = tempOutNames;
41 m->errorOut(e, "GetLineageCommand", "GetLineageCommand");
45 //**********************************************************************************************************************
46 vector<string> GetLineageCommand::getRequiredParameters(){
48 string Array[] = {"taxonomy","taxon"};
49 vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
53 m->errorOut(e, "GetLineageCommand", "getRequiredParameters");
57 //**********************************************************************************************************************
58 vector<string> GetLineageCommand::getRequiredFiles(){
60 vector<string> myArray;
64 m->errorOut(e, "GetLineageCommand", "getRequiredFiles");
68 //**********************************************************************************************************************
69 GetLineageCommand::GetLineageCommand(string option) {
73 //allow user to run help
74 if(option == "help") { help(); abort = true; }
77 //valid paramters for this command
78 string Array[] = {"fasta","name", "group", "alignreport", "taxon", "dups", "list","taxonomy","outputdir","inputdir"};
79 vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
81 OptionParser parser(option);
82 map<string,string> parameters = parser.getParameters();
84 ValidParameters validParameter;
85 map<string,string>::iterator it;
87 //check to make sure all parameters are valid for command
88 for (it = parameters.begin(); it != parameters.end(); it++) {
89 if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; }
92 //initialize outputTypes
93 vector<string> tempOutNames;
94 outputTypes["fasta"] = tempOutNames;
95 outputTypes["taxonomy"] = tempOutNames;
96 outputTypes["name"] = tempOutNames;
97 outputTypes["group"] = tempOutNames;
98 outputTypes["alignreport"] = tempOutNames;
99 outputTypes["list"] = tempOutNames;
101 //if the user changes the output directory command factory will send this info to us in the output parameter
102 outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){ outputDir = ""; }
104 //if the user changes the input directory command factory will send this info to us in the output parameter
105 string inputDir = validParameter.validFile(parameters, "inputdir", false);
106 if (inputDir == "not found"){ inputDir = ""; }
109 it = parameters.find("alignreport");
110 //user has given a template file
111 if(it != parameters.end()){
112 path = m->hasPath(it->second);
113 //if the user has not given a path then, add inputdir. else leave path alone.
114 if (path == "") { parameters["alignreport"] = inputDir + it->second; }
117 it = parameters.find("fasta");
118 //user has given a template file
119 if(it != parameters.end()){
120 path = m->hasPath(it->second);
121 //if the user has not given a path then, add inputdir. else leave path alone.
122 if (path == "") { parameters["fasta"] = inputDir + it->second; }
125 it = parameters.find("list");
126 //user has given a template file
127 if(it != parameters.end()){
128 path = m->hasPath(it->second);
129 //if the user has not given a path then, add inputdir. else leave path alone.
130 if (path == "") { parameters["list"] = inputDir + it->second; }
133 it = parameters.find("name");
134 //user has given a template file
135 if(it != parameters.end()){
136 path = m->hasPath(it->second);
137 //if the user has not given a path then, add inputdir. else leave path alone.
138 if (path == "") { parameters["name"] = inputDir + it->second; }
141 it = parameters.find("group");
142 //user has given a template file
143 if(it != parameters.end()){
144 path = m->hasPath(it->second);
145 //if the user has not given a path then, add inputdir. else leave path alone.
146 if (path == "") { parameters["group"] = inputDir + it->second; }
149 it = parameters.find("taxonomy");
150 //user has given a template file
151 if(it != parameters.end()){
152 path = m->hasPath(it->second);
153 //if the user has not given a path then, add inputdir. else leave path alone.
154 if (path == "") { parameters["taxonomy"] = inputDir + it->second; }
159 //check for required parameters
160 fastafile = validParameter.validFile(parameters, "fasta", true);
161 if (fastafile == "not open") { abort = true; }
162 else if (fastafile == "not found") { fastafile = ""; }
164 namefile = validParameter.validFile(parameters, "name", true);
165 if (namefile == "not open") { abort = true; }
166 else if (namefile == "not found") { namefile = ""; }
168 groupfile = validParameter.validFile(parameters, "group", true);
169 if (groupfile == "not open") { abort = true; }
170 else if (groupfile == "not found") { groupfile = ""; }
172 alignfile = validParameter.validFile(parameters, "alignreport", true);
173 if (alignfile == "not open") { abort = true; }
174 else if (alignfile == "not found") { alignfile = ""; }
176 listfile = validParameter.validFile(parameters, "list", true);
177 if (listfile == "not open") { abort = true; }
178 else if (listfile == "not found") { listfile = ""; }
180 taxfile = validParameter.validFile(parameters, "taxonomy", true);
181 if (taxfile == "not open") { abort = true; }
182 else if (taxfile == "not found") { taxfile = ""; m->mothurOut("The taxonomy parameter is required for the get.lineage command."); m->mothurOutEndLine(); abort = true; }
184 string usedDups = "true";
185 string temp = validParameter.validFile(parameters, "dups", false); if (temp == "not found") { temp = "false"; usedDups = ""; }
186 dups = m->isTrue(temp);
188 taxons = validParameter.validFile(parameters, "taxon", false);
189 if (taxons == "not found") { taxons = ""; m->mothurOut("No taxons given, please correct."); m->mothurOutEndLine(); abort = true; }
192 if (taxons[0] == '\'') { taxons = taxons.substr(1); }
193 if (taxons[(taxons.length()-1)] == '\'') { taxons = taxons.substr(0, (taxons.length()-1)); }
197 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; }
199 if ((usedDups != "") && (namefile == "")) { m->mothurOut("You may only use dups with the name option."); m->mothurOutEndLine(); abort = true; }
204 catch(exception& e) {
205 m->errorOut(e, "GetLineageCommand", "GetLineageCommand");
209 //**********************************************************************************************************************
211 void GetLineageCommand::help(){
213 m->mothurOut("The get.lineage command reads a taxonomy file and any of the following file types: fasta, name, group, list or alignreport file.\n");
214 m->mothurOut("It outputs a file containing only the sequences from the taxonomy file that are from the taxon requested.\n");
215 m->mothurOut("The get.lineage command parameters are taxon, fasta, name, group, list, taxonomy, alignreport and dups. You must provide taxonomy and taxon.\n");
216 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");
217 m->mothurOut("The taxon parameter allows you to select the taxons you would like to get.\n");
218 m->mothurOut("The get.lineage command should be in the following format: get.lineage(taxonomy=yourTaxonomyFile, taxon=yourTaxons).\n");
219 m->mothurOut("Example get.lineage(taxonomy=amazon.silva.taxonomy, taxon=Bacteria;Firmicutes;Bacilli;Lactobacillales;).\n");
220 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");
221 m->mothurOut("Example get.lineage(taxonomy=amazon.silva.taxonomy, taxon='Bacteria;Firmicutes;Bacilli;Lactobacillales;').\n");
222 m->mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n\n");
224 catch(exception& e) {
225 m->errorOut(e, "GetLineageCommand", "help");
230 //**********************************************************************************************************************
232 int GetLineageCommand::execute(){
235 if (abort == true) { return 0; }
237 if (m->control_pressed) { return 0; }
239 //read through the correct file and output lines you want to keep
240 if (taxfile != "") { readTax(); } //fills the set of names to get
241 if (namefile != "") { readName(); }
242 if (fastafile != "") { readFasta(); }
243 if (groupfile != "") { readGroup(); }
244 if (alignfile != "") { readAlign(); }
245 if (listfile != "") { readList(); }
248 if (m->control_pressed) { outputTypes.clear(); for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; }
250 if (outputNames.size() != 0) {
251 m->mothurOutEndLine();
252 m->mothurOut("Output File Names: "); m->mothurOutEndLine();
253 for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); }
254 m->mothurOutEndLine();
260 catch(exception& e) {
261 m->errorOut(e, "GetLineageCommand", "execute");
266 //**********************************************************************************************************************
267 int GetLineageCommand::readFasta(){
269 string thisOutputDir = outputDir;
270 if (outputDir == "") { thisOutputDir += m->hasPath(fastafile); }
271 string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(fastafile)) + "pick" + m->getExtension(fastafile);
273 m->openOutputFile(outputFileName, out);
277 m->openInputFile(fastafile, in);
280 bool wroteSomething = false;
284 if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; }
286 Sequence currSeq(in);
287 name = currSeq.getName();
290 //if this name is in the accnos file
291 if (names.count(name) != 0) {
292 wroteSomething = true;
294 currSeq.printSequence(out);
302 if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); }
303 outputNames.push_back(outputFileName); outputTypes["fasta"].push_back(outputFileName);
308 catch(exception& e) {
309 m->errorOut(e, "GetLineageCommand", "readFasta");
313 //**********************************************************************************************************************
314 int GetLineageCommand::readList(){
316 string thisOutputDir = outputDir;
317 if (outputDir == "") { thisOutputDir += m->hasPath(listfile); }
318 string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(listfile)) + "pick" + m->getExtension(listfile);
320 m->openOutputFile(outputFileName, out);
323 m->openInputFile(listfile, in);
325 bool wroteSomething = false;
329 if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; }
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++) {
341 //parse out names that are in accnos file
342 string binnames = list.get(i);
344 string newNames = "";
345 while (binnames.find_first_of(',') != -1) {
346 string name = binnames.substr(0,binnames.find_first_of(','));
347 binnames = binnames.substr(binnames.find_first_of(',')+1, binnames.length());
349 //if that name is in the .accnos file, add it
350 if (names.count(name) != 0) { newNames += name + ","; }
354 if (names.count(binnames) != 0) { newNames += binnames + ","; }
356 //if there are names in this bin add to new list
357 if (newNames != "") {
358 newNames = newNames.substr(0, newNames.length()-1); //rip off extra comma
359 newList.push_back(newNames);
363 //print new listvector
364 if (newList.getNumBins() != 0) {
365 wroteSomething = true;
374 if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); }
375 outputNames.push_back(outputFileName); outputTypes["list"].push_back(outputFileName);
380 catch(exception& e) {
381 m->errorOut(e, "GetLineageCommand", "readList");
385 //**********************************************************************************************************************
386 int GetLineageCommand::readName(){
388 string thisOutputDir = outputDir;
389 if (outputDir == "") { thisOutputDir += m->hasPath(namefile); }
390 string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(namefile)) + "pick" + m->getExtension(namefile);
392 m->openOutputFile(outputFileName, out);
396 m->openInputFile(namefile, in);
397 string name, firstCol, secondCol;
399 bool wroteSomething = false;
404 if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; }
410 if (dups) { hold = secondCol; }
412 vector<string> parsedNames;
413 //parse second column saving each name
414 while (secondCol.find_first_of(',') != -1) {
415 name = secondCol.substr(0,secondCol.find_first_of(','));
416 secondCol = secondCol.substr(secondCol.find_first_of(',')+1, secondCol.length());
417 parsedNames.push_back(name);
420 //get name after last ,
421 parsedNames.push_back(secondCol);
423 vector<string> validSecond;
424 for (int i = 0; i < parsedNames.size(); i++) {
425 if (names.count(parsedNames[i]) != 0) {
426 validSecond.push_back(parsedNames[i]);
430 if ((dups) && (validSecond.size() != 0)) { //dups = true and we want to add someone, then add everyone
431 for (int i = 0; i < parsedNames.size(); i++) { names.insert(parsedNames[i]); }
432 out << firstCol << '\t' << hold << endl;
433 wroteSomething = true;
435 //if the name in the first column is in the set then print it and any other names in second column also in set
436 if (names.count(firstCol) != 0) {
438 wroteSomething = true;
440 out << firstCol << '\t';
442 //you know you have at least one valid second since first column is valid
443 for (int i = 0; i < validSecond.size()-1; i++) { out << validSecond[i] << ','; }
444 out << validSecond[validSecond.size()-1] << endl;
447 //make first name in set you come to first column and then add the remaining names to second column
449 //you want part of this row
450 if (validSecond.size() != 0) {
452 wroteSomething = true;
454 out << validSecond[0] << '\t';
456 //you know you have at least one valid second since first column is valid
457 for (int i = 0; i < validSecond.size()-1; i++) { out << validSecond[i] << ','; }
458 out << validSecond[validSecond.size()-1] << endl;
467 if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); }
468 outputNames.push_back(outputFileName); outputTypes["name"].push_back(outputFileName);
473 catch(exception& e) {
474 m->errorOut(e, "GetLineageCommand", "readName");
479 //**********************************************************************************************************************
480 int GetLineageCommand::readGroup(){
482 string thisOutputDir = outputDir;
483 if (outputDir == "") { thisOutputDir += m->hasPath(groupfile); }
484 string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(groupfile)) + "pick" + m->getExtension(groupfile);
486 m->openOutputFile(outputFileName, out);
490 m->openInputFile(groupfile, in);
493 bool wroteSomething = false;
497 if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; }
500 in >> name; //read from first column
501 in >> group; //read from second column
503 //if this name is in the accnos file
504 if (names.count(name) != 0) {
505 wroteSomething = true;
507 out << name << '\t' << group << endl;
515 if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); }
516 outputNames.push_back(outputFileName); outputTypes["group"].push_back(outputFileName);
521 catch(exception& e) {
522 m->errorOut(e, "GetLineageCommand", "readGroup");
526 //**********************************************************************************************************************
527 int GetLineageCommand::readTax(){
529 string thisOutputDir = outputDir;
530 if (outputDir == "") { thisOutputDir += m->hasPath(taxfile); }
531 string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(taxfile)) + "pick" + m->getExtension(taxfile);
533 m->openOutputFile(outputFileName, out);
536 m->openInputFile(taxfile, in);
539 bool wroteSomething = false;
543 if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; }
545 in >> name; //read from first column
546 in >> tax; //read from second column
550 //if the users file contains confidence scores we want to ignore them when searching for the taxons
551 int hasConfidences = tax.find_first_of('(');
552 if (hasConfidences != string::npos) {
553 newtax = removeConfidences(tax);
556 int pos = newtax.find(taxons);
558 if (pos != string::npos) { //this sequence contains the taxon the user wants
560 out << name << '\t' << tax << endl;
568 if (names.size() == 0) { m->mothurOut("Your taxonomy file does not contain any sequences from " + taxons + "."); m->mothurOutEndLine(); }
569 outputNames.push_back(outputFileName); outputTypes["taxonomy"].push_back(outputFileName);
574 catch(exception& e) {
575 m->errorOut(e, "GetLineageCommand", "readTax");
579 /**************************************************************************************************/
580 string GetLineageCommand::removeConfidences(string tax) {
584 int taxLength = tax.length();
585 for(int i=0;i<taxLength;i++){
587 taxon = taxon.substr(0, taxon.find_first_of('(')); //rip off confidence
597 catch(exception& e) {
598 m->errorOut(e, "GetLineageCommand", "removeConfidences");
602 //**********************************************************************************************************************
603 //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
604 int GetLineageCommand::readAlign(){
606 string thisOutputDir = outputDir;
607 if (outputDir == "") { thisOutputDir += m->hasPath(alignfile); }
608 string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(alignfile)) + "pick.align.report";
610 m->openOutputFile(outputFileName, out);
614 m->openInputFile(alignfile, in);
617 bool wroteSomething = false;
619 //read column headers
620 for (int i = 0; i < 16; i++) {
621 if (!in.eof()) { in >> junk; out << junk << '\t'; }
628 if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; }
631 in >> name; //read from first column
633 //if this name is in the accnos file
634 if (names.count(name) != 0) {
635 wroteSomething = true;
640 for (int i = 0; i < 15; i++) {
641 if (!in.eof()) { in >> junk; out << junk << '\t'; }
646 }else {//still read just don't do anything with it
648 for (int i = 0; i < 15; i++) {
649 if (!in.eof()) { in >> junk; }
659 if (wroteSomething == false) { m->mothurOut("Your file does not contain any sequence from the .accnos file."); m->mothurOutEndLine(); }
660 outputNames.push_back(outputFileName); outputTypes["alignreport"].push_back(outputFileName);
665 catch(exception& e) {
666 m->errorOut(e, "GetLineageCommand", "readAlign");
670 //**********************************************************************************************************************