X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=degapseqscommand.cpp;fp=degapseqscommand.cpp;h=1d83f3bef00d08574a66d7e5ecf21efa148452a4;hb=0caf3fbabaa3ece404f8ce77f4c883dc5b1bf1dc;hp=0000000000000000000000000000000000000000;hpb=1b73ff67c83892a025e597dabd9df6fe7b58206a;p=mothur.git diff --git a/degapseqscommand.cpp b/degapseqscommand.cpp new file mode 100644 index 0000000..1d83f3b --- /dev/null +++ b/degapseqscommand.cpp @@ -0,0 +1,239 @@ +/* + * degapseqscommand.cpp + * Mothur + * + * Created by westcott on 6/21/10. + * Copyright 2010 Schloss Lab. All rights reserved. + * + */ + +#include "degapseqscommand.h" +#include "sequence.hpp" + +//********************************************************************************************************************** +vector DegapSeqsCommand::setParameters(){ + try { + CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(pfasta); + CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir); + CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir); + + vector myArray; + for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); } + return myArray; + } + catch(exception& e) { + m->errorOut(e, "DegapSeqsCommand", "setParameters"); + exit(1); + } +} +//********************************************************************************************************************** +string DegapSeqsCommand::getHelpString(){ + try { + string helpString = ""; + helpString += "The degap.seqs command reads a fastafile and removes all gap characters.\n"; + helpString += "The degap.seqs command parameter is fasta.\n"; + 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"; + helpString += "You may enter multiple fasta files by separating their names with dashes. ie. fasta=abrecovery.fasta-amzon.fasta \n"; + helpString += "The degap.seqs command should be in the following format: \n"; + helpString += "degap.seqs(fasta=yourFastaFile) \n"; + helpString += "Example: degap.seqs(fasta=abrecovery.align) \n"; + helpString += "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFastaFile).\n"; + return helpString; + } + catch(exception& e) { + m->errorOut(e, "DegapSeqsCommand", "getHelpString"); + exit(1); + } +} +//********************************************************************************************************************** +DegapSeqsCommand::DegapSeqsCommand(){ + try { + abort = true; calledHelp = true; + setParameters(); + vector tempOutNames; + outputTypes["fasta"] = tempOutNames; + } + catch(exception& e) { + m->errorOut(e, "DegapSeqsCommand", "DegapSeqsCommand"); + exit(1); + } +} +//*************************************************************************************************************** +DegapSeqsCommand::DegapSeqsCommand(string option) { + try { + abort = false; calledHelp = false; + + //allow user to run help + if(option == "help") { help(); abort = true; calledHelp = true; } + else if(option == "citation") { citation(); abort = true; calledHelp = true;} + + else { + vector myArray = setParameters(); + + OptionParser parser(option); + map parameters = parser.getParameters(); + + ValidParameters validParameter; + map::iterator it; + + //check to make sure all parameters are valid for command + for (it = parameters.begin(); it != parameters.end(); it++) { + if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; } + } + + + //initialize outputTypes + vector tempOutNames; + outputTypes["fasta"] = tempOutNames; + + //if the user changes the input directory command factory will send this info to us in the output parameter + string inputDir = validParameter.validFile(parameters, "inputdir", false); + if (inputDir == "not found"){ inputDir = ""; } + + //check for required parameters + fastafile = validParameter.validFile(parameters, "fasta", false); + if (fastafile == "not found") { + fastafile = m->getFastaFile(); + if (fastafile != "") { fastaFileNames.push_back(fastafile); m->mothurOut("Using " + fastafile + " as input file for the fasta parameter."); m->mothurOutEndLine(); } + else { m->mothurOut("You have no current fastafile and the fasta parameter is required."); m->mothurOutEndLine(); abort = true; } + } + else { + m->splitAtDash(fastafile, fastaFileNames); + + //go through files and make sure they are good, if not, then disregard them + for (int i = 0; i < fastaFileNames.size(); i++) { + + bool ignore = false; + if (fastaFileNames[i] == "current") { + fastaFileNames[i] = m->getFastaFile(); + if (fastaFileNames[i] != "") { m->mothurOut("Using " + fastaFileNames[i] + " as input file for the fasta parameter where you had given current."); m->mothurOutEndLine(); } + else { + m->mothurOut("You have no current fastafile, ignoring current."); m->mothurOutEndLine(); ignore=true; + //erase from file list + fastaFileNames.erase(fastaFileNames.begin()+i); + i--; + } + } + + if (!ignore) { + if (inputDir != "") { + string path = m->hasPath(fastaFileNames[i]); + //if the user has not given a path then, add inputdir. else leave path alone. + if (path == "") { fastaFileNames[i] = inputDir + fastaFileNames[i]; } + } + + ifstream in; + int ableToOpen = m->openInputFile(fastaFileNames[i], in, "noerror"); + + //if you can't open it, try default location + if (ableToOpen == 1) { + if (m->getDefaultPath() != "") { //default path is set + string tryPath = m->getDefaultPath() + m->getSimpleName(fastaFileNames[i]); + m->mothurOut("Unable to open " + fastaFileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine(); + ifstream in2; + ableToOpen = m->openInputFile(tryPath, in2, "noerror"); + in2.close(); + fastaFileNames[i] = tryPath; + } + } + + //if you can't open it, try default location + if (ableToOpen == 1) { + if (m->getOutputDir() != "") { //default path is set + string tryPath = m->getOutputDir() + m->getSimpleName(fastaFileNames[i]); + m->mothurOut("Unable to open " + fastaFileNames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine(); + ifstream in2; + ableToOpen = m->openInputFile(tryPath, in2, "noerror"); + in2.close(); + fastaFileNames[i] = tryPath; + } + } + + in.close(); + + if (ableToOpen == 1) { + m->mothurOut("Unable to open " + fastaFileNames[i] + ". It will be disregarded."); m->mothurOutEndLine(); + //erase from file list + fastaFileNames.erase(fastaFileNames.begin()+i); + i--; + }else { m->setFastaFile(fastaFileNames[i]); } + } + } + + //make sure there is at least one valid file left + if (fastaFileNames.size() == 0) { m->mothurOut("no valid files."); m->mothurOutEndLine(); abort = true; } + } + + + //if the user changes the output directory command factory will send this info to us in the output parameter + outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){ + outputDir = ""; + outputDir += m->hasPath(fastafile); //if user entered a file with a path then preserve it + } + + } + } + catch(exception& e) { + m->errorOut(e, "DegapSeqsCommand", "DegapSeqsCommand"); + exit(1); + } +} +//*************************************************************************************************************** +int DegapSeqsCommand::execute(){ + try{ + + if (abort == true) { if (calledHelp) { return 0; } return 2; } + + for (int s = 0; s < fastaFileNames.size(); s++) { + + m->mothurOut("Degapping sequences from " + fastaFileNames[s] + " ..." ); m->mothurOutEndLine(); + ifstream inFASTA; + m->openInputFile(fastaFileNames[s], inFASTA); + + ofstream outFASTA; + string tempOutputDir = outputDir; + if (outputDir == "") { tempOutputDir = m->hasPath(fastaFileNames[s]); } + string degapFile = tempOutputDir + m->getRootName(m->getSimpleName(fastaFileNames[s])) + "ng.fasta"; + m->openOutputFile(degapFile, outFASTA); + + while(!inFASTA.eof()){ + 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; } + + Sequence currSeq(inFASTA); m->gobble(inFASTA); + if (currSeq.getName() != "") { + outFASTA << ">" << currSeq.getName() << endl; + outFASTA << currSeq.getUnaligned() << endl; + } + } + inFASTA.close(); + outFASTA.close(); + + outputNames.push_back(degapFile); outputTypes["fasta"].push_back(degapFile); + + if (m->control_pressed) { outputTypes.clear(); m->mothurRemove(degapFile); for (int j = 0; j < outputNames.size(); j++) { m->mothurRemove(outputNames[j]); } return 0; } + } + + //set fasta file as new current fastafile + string current = ""; + itTypes = outputTypes.find("fasta"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setFastaFile(current); } + } + + m->mothurOutEndLine(); + m->mothurOut("Output File Name: "); m->mothurOutEndLine(); + for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); } + m->mothurOutEndLine(); + + + return 0; + + } + catch(exception& e) { + m->errorOut(e, "DegapSeqsCommand", "execute"); + exit(1); + } +} + +//*************************************************************************************************************** +