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",false,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 DegapSeqsCommand::DegapSeqsCommand(){
51 abort = true; calledHelp = true;
53 vector<string> tempOutNames;
54 outputTypes["fasta"] = tempOutNames;
57 m->errorOut(e, "DegapSeqsCommand", "DegapSeqsCommand");
61 //***************************************************************************************************************
62 DegapSeqsCommand::DegapSeqsCommand(string option) {
64 abort = false; calledHelp = false;
66 //allow user to run help
67 if(option == "help") { help(); abort = true; calledHelp = true; }
68 else if(option == "citation") { citation(); abort = true; calledHelp = true;}
71 vector<string> myArray = setParameters();
73 OptionParser parser(option);
74 map<string,string> parameters = parser.getParameters();
76 ValidParameters validParameter;
77 map<string,string>::iterator it;
79 //check to make sure all parameters are valid for command
80 for (it = parameters.begin(); it != parameters.end(); it++) {
81 if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; }
85 //initialize outputTypes
86 vector<string> tempOutNames;
87 outputTypes["fasta"] = tempOutNames;
89 //if the user changes the input directory command factory will send this info to us in the output parameter
90 string inputDir = validParameter.validFile(parameters, "inputdir", false);
91 if (inputDir == "not found"){ inputDir = ""; }
93 //check for required parameters
94 fastafile = validParameter.validFile(parameters, "fasta", false);
95 if (fastafile == "not found") {
96 fastafile = m->getFastaFile();
97 if (fastafile != "") { fastaFileNames.push_back(fastafile); m->mothurOut("Using " + fastafile + " as input file for the fasta parameter."); m->mothurOutEndLine(); }
98 else { m->mothurOut("You have no current fastafile and the fasta parameter is required."); m->mothurOutEndLine(); abort = true; }
101 m->splitAtDash(fastafile, fastaFileNames);
103 //go through files and make sure they are good, if not, then disregard them
104 for (int i = 0; i < fastaFileNames.size(); i++) {
107 if (fastaFileNames[i] == "current") {
108 fastaFileNames[i] = m->getFastaFile();
109 if (fastaFileNames[i] != "") { m->mothurOut("Using " + fastaFileNames[i] + " as input file for the fasta parameter where you had given current."); m->mothurOutEndLine(); }
111 m->mothurOut("You have no current fastafile, ignoring current."); m->mothurOutEndLine(); ignore=true;
112 //erase from file list
113 fastaFileNames.erase(fastaFileNames.begin()+i);
119 if (inputDir != "") {
120 string path = m->hasPath(fastaFileNames[i]);
121 //if the user has not given a path then, add inputdir. else leave path alone.
122 if (path == "") { fastaFileNames[i] = inputDir + fastaFileNames[i]; }
126 int ableToOpen = m->openInputFile(fastaFileNames[i], in, "noerror");
128 //if you can't open it, try default location
129 if (ableToOpen == 1) {
130 if (m->getDefaultPath() != "") { //default path is set
131 string tryPath = m->getDefaultPath() + m->getSimpleName(fastaFileNames[i]);
132 m->mothurOut("Unable to open " + fastaFileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine();
134 ableToOpen = m->openInputFile(tryPath, in2, "noerror");
136 fastaFileNames[i] = tryPath;
140 //if you can't open it, try default location
141 if (ableToOpen == 1) {
142 if (m->getOutputDir() != "") { //default path is set
143 string tryPath = m->getOutputDir() + m->getSimpleName(fastaFileNames[i]);
144 m->mothurOut("Unable to open " + fastaFileNames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine();
146 ableToOpen = m->openInputFile(tryPath, in2, "noerror");
148 fastaFileNames[i] = tryPath;
154 if (ableToOpen == 1) {
155 m->mothurOut("Unable to open " + fastaFileNames[i] + ". It will be disregarded."); m->mothurOutEndLine();
156 //erase from file list
157 fastaFileNames.erase(fastaFileNames.begin()+i);
159 }else { m->setFastaFile(fastaFileNames[i]); }
163 //make sure there is at least one valid file left
164 if (fastaFileNames.size() == 0) { m->mothurOut("no valid files."); m->mothurOutEndLine(); abort = true; }
168 //if the user changes the output directory command factory will send this info to us in the output parameter
169 outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){
171 outputDir += m->hasPath(fastafile); //if user entered a file with a path then preserve it
176 catch(exception& e) {
177 m->errorOut(e, "DegapSeqsCommand", "DegapSeqsCommand");
181 //***************************************************************************************************************
182 int DegapSeqsCommand::execute(){
185 if (abort == true) { if (calledHelp) { return 0; } return 2; }
187 for (int s = 0; s < fastaFileNames.size(); s++) {
189 m->mothurOut("Degapping sequences from " + fastaFileNames[s] + " ..." ); m->mothurOutEndLine();
191 m->openInputFile(fastaFileNames[s], inFASTA);
194 string tempOutputDir = outputDir;
195 if (outputDir == "") { tempOutputDir = m->hasPath(fastaFileNames[s]); }
196 string degapFile = tempOutputDir + m->getRootName(m->getSimpleName(fastaFileNames[s])) + "ng.fasta";
197 m->openOutputFile(degapFile, outFASTA);
199 while(!inFASTA.eof()){
200 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; }
202 Sequence currSeq(inFASTA); m->gobble(inFASTA);
203 if (currSeq.getName() != "") {
204 outFASTA << ">" << currSeq.getName() << endl;
205 outFASTA << currSeq.getUnaligned() << endl;
211 outputNames.push_back(degapFile); outputTypes["fasta"].push_back(degapFile);
213 if (m->control_pressed) { outputTypes.clear(); m->mothurRemove(degapFile); for (int j = 0; j < outputNames.size(); j++) { m->mothurRemove(outputNames[j]); } return 0; }
216 //set fasta file as new current fastafile
218 itTypes = outputTypes.find("fasta");
219 if (itTypes != outputTypes.end()) {
220 if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setFastaFile(current); }
223 m->mothurOutEndLine();
224 m->mothurOut("Output File Name: "); m->mothurOutEndLine();
225 for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); }
226 m->mothurOutEndLine();
232 catch(exception& e) {
233 m->errorOut(e, "DegapSeqsCommand", "execute");
238 //***************************************************************************************************************