5 * Created by westcott on 6/21/10.
6 * Copyright 2010 Schloss Lab. All rights reserved.
10 #include "degapseqscommand.h"
11 #include "sequence.hpp"
13 //**********************************************************************************************************************
14 vector<string> DegapSeqsCommand::setParameters(){
16 CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "none","fasta",false,true,true); parameters.push_back(pfasta);
17 CommandParameter pinputdir("inputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(pinputdir);
18 CommandParameter poutputdir("outputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(poutputdir);
20 vector<string> myArray;
21 for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); }
25 m->errorOut(e, "DegapSeqsCommand", "setParameters");
29 //**********************************************************************************************************************
30 string DegapSeqsCommand::getHelpString(){
32 string helpString = "";
33 helpString += "The degap.seqs command reads a fastafile and removes all gap characters.\n";
34 helpString += "The degap.seqs command parameter is fasta.\n";
35 helpString += "The fasta parameter allows you to enter the fasta file containing your sequences, and is required unless you have a valid current fasta file. \n";
36 helpString += "You may enter multiple fasta files by separating their names with dashes. ie. fasta=abrecovery.fasta-amzon.fasta \n";
37 helpString += "The degap.seqs command should be in the following format: \n";
38 helpString += "degap.seqs(fasta=yourFastaFile) \n";
39 helpString += "Example: degap.seqs(fasta=abrecovery.align) \n";
40 helpString += "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFastaFile).\n";
44 m->errorOut(e, "DegapSeqsCommand", "getHelpString");
48 //**********************************************************************************************************************
49 string DegapSeqsCommand::getOutputPattern(string type) {
53 if (type == "fasta") { pattern = "[filename],ng.fasta"; }
54 else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; }
59 m->errorOut(e, "DegapSeqsCommand", "getOutputPattern");
63 //**********************************************************************************************************************
64 DegapSeqsCommand::DegapSeqsCommand(){
66 abort = true; calledHelp = true;
68 vector<string> tempOutNames;
69 outputTypes["fasta"] = tempOutNames;
72 m->errorOut(e, "DegapSeqsCommand", "DegapSeqsCommand");
76 //***************************************************************************************************************
77 DegapSeqsCommand::DegapSeqsCommand(string option) {
79 abort = false; calledHelp = false;
81 //allow user to run help
82 if(option == "help") { help(); abort = true; calledHelp = true; }
83 else if(option == "citation") { citation(); abort = true; calledHelp = true;}
86 vector<string> myArray = setParameters();
88 OptionParser parser(option);
89 map<string,string> parameters = parser.getParameters();
91 ValidParameters validParameter;
92 map<string,string>::iterator it;
94 //check to make sure all parameters are valid for command
95 for (it = parameters.begin(); it != parameters.end(); it++) {
96 if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; }
100 //initialize outputTypes
101 vector<string> tempOutNames;
102 outputTypes["fasta"] = tempOutNames;
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 = ""; }
108 //check for required parameters
109 fastafile = validParameter.validFile(parameters, "fasta", false);
110 if (fastafile == "not found") {
111 fastafile = m->getFastaFile();
112 if (fastafile != "") { fastaFileNames.push_back(fastafile); m->mothurOut("Using " + fastafile + " as input file for the fasta parameter."); m->mothurOutEndLine(); }
113 else { m->mothurOut("You have no current fastafile and the fasta parameter is required."); m->mothurOutEndLine(); abort = true; }
116 m->splitAtDash(fastafile, fastaFileNames);
118 //go through files and make sure they are good, if not, then disregard them
119 for (int i = 0; i < fastaFileNames.size(); i++) {
122 if (fastaFileNames[i] == "current") {
123 fastaFileNames[i] = m->getFastaFile();
124 if (fastaFileNames[i] != "") { m->mothurOut("Using " + fastaFileNames[i] + " as input file for the fasta parameter where you had given current."); m->mothurOutEndLine(); }
126 m->mothurOut("You have no current fastafile, ignoring current."); m->mothurOutEndLine(); ignore=true;
127 //erase from file list
128 fastaFileNames.erase(fastaFileNames.begin()+i);
134 if (inputDir != "") {
135 string path = m->hasPath(fastaFileNames[i]);
136 //if the user has not given a path then, add inputdir. else leave path alone.
137 if (path == "") { fastaFileNames[i] = inputDir + fastaFileNames[i]; }
141 int ableToOpen = m->openInputFile(fastaFileNames[i], in, "noerror");
143 //if you can't open it, try default location
144 if (ableToOpen == 1) {
145 if (m->getDefaultPath() != "") { //default path is set
146 string tryPath = m->getDefaultPath() + m->getSimpleName(fastaFileNames[i]);
147 m->mothurOut("Unable to open " + fastaFileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine();
149 ableToOpen = m->openInputFile(tryPath, in2, "noerror");
151 fastaFileNames[i] = tryPath;
155 //if you can't open it, try default location
156 if (ableToOpen == 1) {
157 if (m->getOutputDir() != "") { //default path is set
158 string tryPath = m->getOutputDir() + m->getSimpleName(fastaFileNames[i]);
159 m->mothurOut("Unable to open " + fastaFileNames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine();
161 ableToOpen = m->openInputFile(tryPath, in2, "noerror");
163 fastaFileNames[i] = tryPath;
169 if (ableToOpen == 1) {
170 m->mothurOut("Unable to open " + fastaFileNames[i] + ". It will be disregarded."); m->mothurOutEndLine();
171 //erase from file list
172 fastaFileNames.erase(fastaFileNames.begin()+i);
174 }else { m->setFastaFile(fastaFileNames[i]); }
178 //make sure there is at least one valid file left
179 if (fastaFileNames.size() == 0) { m->mothurOut("no valid files."); m->mothurOutEndLine(); abort = true; }
183 //if the user changes the output directory command factory will send this info to us in the output parameter
184 outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){
186 outputDir += m->hasPath(fastafile); //if user entered a file with a path then preserve it
191 catch(exception& e) {
192 m->errorOut(e, "DegapSeqsCommand", "DegapSeqsCommand");
196 //***************************************************************************************************************
197 int DegapSeqsCommand::execute(){
200 if (abort == true) { if (calledHelp) { return 0; } return 2; }
202 for (int s = 0; s < fastaFileNames.size(); s++) {
204 m->mothurOut("Degapping sequences from " + fastaFileNames[s] + " ..." ); m->mothurOutEndLine();
206 m->openInputFile(fastaFileNames[s], inFASTA);
209 string tempOutputDir = outputDir;
210 if (outputDir == "") { tempOutputDir = m->hasPath(fastaFileNames[s]); }
211 map<string, string> variables;
212 variables["[filename]"] = tempOutputDir + m->getRootName(m->getSimpleName(fastaFileNames[s]));
213 string degapFile = getOutputFileName("fasta", variables);
214 m->openOutputFile(degapFile, outFASTA);
216 while(!inFASTA.eof()){
217 if (m->control_pressed) { outputTypes.clear(); inFASTA.close(); outFASTA.close(); m->mothurRemove(degapFile); for (int j = 0; j < outputNames.size(); j++) { m->mothurRemove(outputNames[j]); } return 0; }
219 Sequence currSeq(inFASTA); m->gobble(inFASTA);
220 if (currSeq.getName() != "") {
221 outFASTA << ">" << currSeq.getName() << endl;
222 outFASTA << currSeq.getUnaligned() << endl;
228 outputNames.push_back(degapFile); outputTypes["fasta"].push_back(degapFile);
230 if (m->control_pressed) { outputTypes.clear(); m->mothurRemove(degapFile); for (int j = 0; j < outputNames.size(); j++) { m->mothurRemove(outputNames[j]); } return 0; }
233 //set fasta file as new current fastafile
235 itTypes = outputTypes.find("fasta");
236 if (itTypes != outputTypes.end()) {
237 if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setFastaFile(current); }
240 m->mothurOutEndLine();
241 m->mothurOut("Output File Names: "); m->mothurOutEndLine();
242 for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); }
243 m->mothurOutEndLine();
249 catch(exception& e) {
250 m->errorOut(e, "DegapSeqsCommand", "execute");
255 //***************************************************************************************************************