5 * Created by westcott on 5/10/10.
6 * Copyright 2010 Schloss Lab. All rights reserved.
10 #include "chopseqscommand.h"
11 #include "sequence.hpp"
13 //**********************************************************************************************************************
14 vector<string> ChopSeqsCommand::setParameters(){
16 CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(pfasta);
17 CommandParameter pnumbases("numbases", "Number", "", "0", "", "", "",false,true); parameters.push_back(pnumbases);
18 CommandParameter pcountgaps("countgaps", "Boolean", "", "F", "", "", "",false,false); parameters.push_back(pcountgaps);
19 CommandParameter pshort("short", "Boolean", "", "F", "", "", "",false,false); parameters.push_back(pshort);
20 CommandParameter pkeep("keep", "Multiple", "front-back", "front", "", "", "",false,false); parameters.push_back(pkeep);
21 CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir);
22 CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir);
24 vector<string> myArray;
25 for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); }
29 m->errorOut(e, "ChopSeqsCommand", "setParameters");
33 //**********************************************************************************************************************
34 string ChopSeqsCommand::getHelpString(){
36 string helpString = "";
37 helpString += "The chop.seqs command reads a fasta file and outputs a .chop.fasta containing the trimmed sequences. Note: If a sequence is completely 'chopped', an accnos file will be created with the names of the sequences removed. \n";
38 helpString += "The chop.seqs command parameters are fasta, numbases, countgaps and keep. fasta is required unless you have a valid current fasta file. numbases is required.\n";
39 helpString += "The chop.seqs command should be in the following format: chop.seqs(fasta=yourFasta, numbases=yourNum, keep=yourKeep).\n";
40 helpString += "The numbases parameter allows you to specify the number of bases you want to keep.\n";
41 helpString += "The keep parameter allows you to specify whether you want to keep the front or the back of your sequence, default=front.\n";
42 helpString += "The countgaps parameter allows you to specify whether you want to count gaps as bases, default=false.\n";
43 helpString += "The short parameter allows you to specify you want to keep sequences that are too short to chop, default=false.\n";
44 helpString += "For example, if you ran chop.seqs with numbases=200 and short=t, if a sequence had 100 bases mothur would keep the sequence rather than eliminate it.\n";
45 helpString += "Example chop.seqs(fasta=amazon.fasta, numbases=200, keep=front).\n";
46 helpString += "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n";
50 m->errorOut(e, "ChopSeqsCommand", "getHelpString");
54 //**********************************************************************************************************************
55 string ChopSeqsCommand::getOutputFileNameTag(string type, string inputName=""){
57 string outputFileName = "";
58 map<string, vector<string> >::iterator it;
60 //is this a type this command creates
61 it = outputTypes.find(type);
62 if (it == outputTypes.end()) { m->mothurOut("[ERROR]: this command doesn't create a " + type + " output file.\n"); }
64 if (type == "fasta") { outputFileName = "chop.fasta"; }
65 else if (type == "accnos") { outputFileName = "chop.accnos"; }
66 else { m->mothurOut("[ERROR]: No definition for type " + type + " output file tag.\n"); m->control_pressed = true; }
68 return outputFileName;
71 m->errorOut(e, "ChopSeqsCommand", "getOutputFileNameTag");
75 //**********************************************************************************************************************
76 ChopSeqsCommand::ChopSeqsCommand(){
78 abort = true; calledHelp = true;
80 vector<string> tempOutNames;
81 outputTypes["fasta"] = tempOutNames;
82 outputTypes["accnos"] = tempOutNames;
85 m->errorOut(e, "ChopSeqsCommand", "ChopSeqsCommand");
89 //**********************************************************************************************************************
90 ChopSeqsCommand::ChopSeqsCommand(string option) {
92 abort = false; calledHelp = false;
94 //allow user to run help
95 if(option == "help") { help(); abort = true; calledHelp = true; }
96 else if(option == "citation") { citation(); abort = true; calledHelp = true;}
99 vector<string> myArray = setParameters();
101 OptionParser parser(option);
102 map<string,string> parameters = parser.getParameters();
104 ValidParameters validParameter;
105 map<string,string>::iterator it;
107 //check to make sure all parameters are valid for command
108 for (map<string,string>::iterator it = parameters.begin(); it != parameters.end(); it++) {
109 if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; }
112 //initialize outputTypes
113 vector<string> tempOutNames;
114 outputTypes["fasta"] = tempOutNames;
115 outputTypes["accnos"] = tempOutNames;
117 //if the user changes the input directory command factory will send this info to us in the output parameter
118 string inputDir = validParameter.validFile(parameters, "inputdir", false);
119 if (inputDir == "not found"){ inputDir = ""; }
122 it = parameters.find("fasta");
123 //user has given a template file
124 if(it != parameters.end()){
125 path = m->hasPath(it->second);
126 //if the user has not given a path then, add inputdir. else leave path alone.
127 if (path == "") { parameters["fasta"] = inputDir + it->second; }
131 //check for required parameters
132 fastafile = validParameter.validFile(parameters, "fasta", true);
133 if (fastafile == "not open") { abort = true; }
134 else if (fastafile == "not found") { //if there is a current fasta file, use it
135 fastafile = m->getFastaFile();
136 if (fastafile != "") { m->mothurOut("Using " + fastafile + " as input file for the fasta parameter."); m->mothurOutEndLine(); }
137 else { m->mothurOut("You have no current fastafile and the fasta parameter is required."); m->mothurOutEndLine(); abort = true; }
138 }else { m->setFastaFile(fastafile); }
140 //if the user changes the output directory command factory will send this info to us in the output parameter
141 outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){ outputDir = m->hasPath(fastafile); }
143 string temp = validParameter.validFile(parameters, "numbases", false); if (temp == "not found") { temp = "0"; }
144 m->mothurConvert(temp, numbases);
146 temp = validParameter.validFile(parameters, "countgaps", false); if (temp == "not found") { temp = "f"; }
147 countGaps = m->isTrue(temp);
149 temp = validParameter.validFile(parameters, "short", false); if (temp == "not found") { temp = "f"; }
150 Short = m->isTrue(temp);
152 keep = validParameter.validFile(parameters, "keep", false); if (keep == "not found") { keep = "front"; }
154 if (numbases == 0) { m->mothurOut("You must provide the number of bases you want to keep for the chops.seqs command."); m->mothurOutEndLine(); abort = true; }
158 catch(exception& e) {
159 m->errorOut(e, "ChopSeqsCommand", "ChopSeqsCommand");
163 //**********************************************************************************************************************
165 int ChopSeqsCommand::execute(){
168 if (abort == true) { if (calledHelp) { return 0; } return 2; }
170 string outputFileName = outputDir + m->getRootName(m->getSimpleName(fastafile)) + getOutputFileNameTag("fasta");
171 string outputFileNameAccnos = outputDir + m->getRootName(m->getSimpleName(fastafile)) + getOutputFileNameTag("accnos");
174 m->openOutputFile(outputFileName, out);
177 m->openOutputFile(outputFileNameAccnos, outAcc);
180 m->openInputFile(fastafile, in);
182 bool wroteAccnos = false;
188 if (m->control_pressed) { outputTypes.clear(); in.close(); out.close(); outAcc.close(); m->mothurRemove(outputFileName); m->mothurRemove(outputFileNameAccnos); return 0; }
190 if (seq.getName() != "") {
191 string newSeqString = getChopped(seq);
193 //output trimmed sequence
194 if (newSeqString != "") {
195 out << ">" << seq.getName() << endl << newSeqString << endl;
197 outAcc << seq.getName() << endl;
206 m->mothurOutEndLine();
207 m->mothurOut("Output File Name: "); m->mothurOutEndLine();
208 m->mothurOut(outputFileName); m->mothurOutEndLine(); outputNames.push_back(outputFileName); outputTypes["fasta"].push_back(outputFileName);
210 if (wroteAccnos) { m->mothurOut(outputFileNameAccnos); m->mothurOutEndLine(); outputNames.push_back(outputFileNameAccnos); outputTypes["accnos"].push_back(outputFileNameAccnos); }
211 else { m->mothurRemove(outputFileNameAccnos); }
213 m->mothurOutEndLine();
215 //set fasta file as new current fastafile
217 itTypes = outputTypes.find("fasta");
218 if (itTypes != outputTypes.end()) {
219 if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setFastaFile(current); }
222 if (wroteAccnos) { //set accnos file as new current accnosfile
223 itTypes = outputTypes.find("accnos");
224 if (itTypes != outputTypes.end()) {
225 if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setAccnosFile(current); }
233 catch(exception& e) {
234 m->errorOut(e, "ChopSeqsCommand", "execute");
238 //**********************************************************************************************************************
239 string ChopSeqsCommand::getChopped(Sequence seq) {
241 string temp = seq.getAligned();
242 string tempUnaligned = seq.getUnaligned();
245 //if needed trim sequence
246 if (keep == "front") {//you want to keep the beginning
247 int tempLength = temp.length();
249 if (tempLength > numbases) { //you have enough bases to remove some
252 int numBasesCounted = 0;
254 for (int i = 0; i < temp.length(); i++) {
256 if (toupper(temp[i]) == 'N') { temp[i] = '.'; }
260 if (numBasesCounted >= numbases) { stopSpot = i; break; }
263 if (stopSpot == 0) { temp = ""; }
264 else { temp = temp.substr(0, stopSpot+1); }
267 if (!Short) { temp = ""; } //sequence too short
269 }else { //you are keeping the back
270 int tempLength = temp.length();
271 if (tempLength > numbases) { //you have enough bases to remove some
274 int numBasesCounted = 0;
276 for (int i = (temp.length()-1); i >= 0; i--) {
278 if (toupper(temp[i]) == 'N') { temp[i] = '.'; }
282 if (numBasesCounted >= numbases) { stopSpot = i; break; }
285 if (stopSpot == 0) { temp = ""; }
286 else { temp = temp.substr(stopSpot+1); }
288 if (!Short) { temp = ""; } //sequence too short
294 //if needed trim sequence
295 if (keep == "front") {//you want to keep the beginning
296 int tempLength = tempUnaligned.length();
298 if (tempLength > numbases) { //you have enough bases to remove some
301 int numBasesCounted = 0;
303 for (int i = 0; i < temp.length(); i++) {
305 if (toupper(temp[i]) == 'N') {
308 if (tempLength < numbases) { stopSpot = 0; break; }
311 if(isalpha(temp[i])) { numBasesCounted++; }
313 if (numBasesCounted >= numbases) { stopSpot = i; break; }
316 if (stopSpot == 0) { temp = ""; }
317 else { temp = temp.substr(0, stopSpot+1); }
320 if (!Short) { temp = ""; } //sequence too short
322 }else { //you are keeping the back
323 int tempLength = tempUnaligned.length();
324 if (tempLength > numbases) { //you have enough bases to remove some
327 int numBasesCounted = 0;
329 for (int i = (temp.length()-1); i >= 0; i--) {
331 if (toupper(temp[i]) == 'N') {
334 if (tempLength < numbases) { stopSpot = 0; break; }
337 if(isalpha(temp[i])) { numBasesCounted++; }
339 if (numBasesCounted >= numbases) { stopSpot = i; break; }
342 if (stopSpot == 0) { temp = ""; }
343 else { temp = temp.substr(stopSpot); }
345 if (!Short) { temp = ""; } //sequence too short
352 catch(exception& e) {
353 m->errorOut(e, "ChopSeqsCommand", "getChopped");
357 //**********************************************************************************************************************