]> git.donarmstrong.com Git - mothur.git/blobdiff - trimseqscommand.cpp
added warning about merging with something above cutoff to cluster. working on chimeras
[mothur.git] / trimseqscommand.cpp
index f7773244bc37d888d4c44818cdd8dd1d020444ba..70b1b4ae8a0c931ff3f84a56d4dd68fa1edd537a 100644 (file)
@@ -21,7 +21,8 @@ TrimSeqsCommand::TrimSeqsCommand(string option){
                
                else {
                        //valid paramters for this command
-                       string AlignArray[] =  {"fasta", "flip", "oligos", "maxambig", "maxhomop", "minlength", "maxlength", "qfile", "qthreshold", "qaverage", "allfiles", "qtrim"};
+                       string AlignArray[] =  {"fasta", "flip", "oligos", "maxambig", "maxhomop", "minlength", "maxlength", "qfile", 
+                                                                       "qthreshold", "qaverage", "allfiles", "qtrim", "outputdir","inputdir"};
                        
                        vector<string> myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string)));
                        
@@ -29,17 +30,54 @@ TrimSeqsCommand::TrimSeqsCommand(string option){
                        map<string,string> parameters = parser.getParameters();
                        
                        ValidParameters validParameter;
+                       map<string,string>::iterator it;
                        
                        //check to make sure all parameters are valid for command
-                       for (map<string,string>::iterator it = parameters.begin(); it != parameters.end(); it++) { 
+                       for (it = parameters.begin(); it != parameters.end(); it++) { 
                                if (validParameter.isValidParameter(it->first, myArray, it->second) != true) {  abort = true;  }
                        }
                        
+                       //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 = "";          }
+                       else {
+                               string path;
+                               it = parameters.find("fasta");
+                               //user has given a template file
+                               if(it != parameters.end()){ 
+                                       path = hasPath(it->second);
+                                       //if the user has not given a path then, add inputdir. else leave path alone.
+                                       if (path == "") {       parameters["fasta"] = inputDir + it->second;            }
+                               }
+                               
+                               it = parameters.find("oligos");
+                               //user has given a template file
+                               if(it != parameters.end()){ 
+                                       path = hasPath(it->second);
+                                       //if the user has not given a path then, add inputdir. else leave path alone.
+                                       if (path == "") {       parameters["oligos"] = inputDir + it->second;           }
+                               }
+                               
+                               it = parameters.find("qfile");
+                               //user has given a template file
+                               if(it != parameters.end()){ 
+                                       path = hasPath(it->second);
+                                       //if the user has not given a path then, add inputdir. else leave path alone.
+                                       if (path == "") {       parameters["qfile"] = inputDir + it->second;            }
+                               }
+                       }
+
+                       
                        //check for required parameters
                        fastaFile = validParameter.validFile(parameters, "fasta", true);
                        if (fastaFile == "not found") { mothurOut("fasta is a required parameter for the screen.seqs command."); mothurOutEndLine(); abort = true; }
                        else if (fastaFile == "not open") { 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 += hasPath(fastaFile); //if user entered a file with a path then preserve it  
+                       }
                
                        //check for optional parameter and set defaults
                        // ...at some point should added some additional type checking...
@@ -67,7 +105,7 @@ TrimSeqsCommand::TrimSeqsCommand(string option){
                        
                        temp = validParameter.validFile(parameters, "qfile", true);     
                        if (temp == "not found")        {       qFileName = "";         }
-                       else if(temp == "not open")     {       abort = 0;              }
+                       else if(temp == "not open")     {       abort = true;           }
                        else                                            {       qFileName = temp;       }
                        
                        temp = validParameter.validFile(parameters, "qthreshold", false);       if (temp == "not found") { temp = "0"; }
@@ -145,33 +183,37 @@ int TrimSeqsCommand::execute(){
        try{
        
                if (abort == true) { return 0; }
-
+               
+               numFPrimers = 0;  //this needs to be initialized
+               numRPrimers = 0;
+               
                ifstream inFASTA;
                openInputFile(fastaFile, inFASTA);
                
                ofstream outFASTA;
-               string trimSeqFile = getRootName(fastaFile) + "trim.fasta";
+               string trimSeqFile = outputDir + getRootName(getSimpleName(fastaFile)) + "trim.fasta";
                openOutputFile(trimSeqFile, outFASTA);
                
                ofstream outGroups;
                vector<ofstream*> fastaFileNames;
                if(oligoFile != ""){
-                       string groupFile = getRootName(fastaFile) + "groups"; 
+                       string groupFile = outputDir + getRootName(getSimpleName(fastaFile)) + "groups"; 
                        openOutputFile(groupFile, outGroups);
                        getOligos(fastaFileNames);
                }
                
                ofstream scrapFASTA;
-               string scrapSeqFile = getRootName(fastaFile) + "scrap.fasta";
+               string scrapSeqFile = outputDir + getRootName(getSimpleName(fastaFile)) + "scrap.fasta";
                openOutputFile(scrapSeqFile, scrapFASTA);
                
                ifstream qFile;
                if(qFileName != "")     {       openInputFile(qFileName, qFile);        }
                
                bool success;
-                       
+
                while(!inFASTA.eof()){
                        Sequence currSeq(inFASTA);
+
                        string origSeq = currSeq.getUnaligned();
                        if (origSeq != "") {
                                int group;
@@ -185,19 +227,22 @@ int TrimSeqsCommand::execute(){
                                        }
                                        if(!success)                    {       trashCode += 'q';                                                               }
                                }
+                       
                                if(barcodes.size() != 0){
-                                       
                                        success = stripBarcode(currSeq, group);
                                        if(!success){   trashCode += 'b';       }
                                }
+                       
                                if(numFPrimers != 0){
                                        success = stripForward(currSeq);
                                        if(!success){   trashCode += 'f';       }
                                }
+                                       
                                if(numRPrimers != 0){
                                        success = stripReverse(currSeq);
                                        if(!success){   trashCode += 'r';       }
                                }
+               
                                if(minLength > 0 || maxLength > 0){
                                        success = cullLength(currSeq);
                                        if(!success){   trashCode += 'l'; }
@@ -247,7 +292,7 @@ int TrimSeqsCommand::execute(){
                        string seqName;
                        openInputFile(getRootName(fastaFile) + groupVector[i] + ".fasta", inFASTA);
                        ofstream outGroups;
-                       openOutputFile(getRootName(fastaFile) + groupVector[i] + ".groups", outGroups);
+                       openOutputFile(outputDir + getRootName(getSimpleName(fastaFile)) + groupVector[i] + ".groups", outGroups);
                        
                        while(!inFASTA.eof()){
                                if(inFASTA.get() == '>'){
@@ -259,8 +304,7 @@ int TrimSeqsCommand::execute(){
                        outGroups.close();
                        inFASTA.close();
                }
-               
-               
+                       
                return 0;               
        }
        catch(exception& e) {
@@ -299,7 +343,9 @@ void TrimSeqsCommand::getOligos(vector<ofstream*>& outFASTAVec){
                                        forPrimer.push_back(oligo);
                                }
                                else if(type == "reverse"){
-                                       revPrimer.push_back(oligo);
+                                       Sequence oligoRC("reverse", oligo);
+                                       oligoRC.reverseComplement();
+                                       revPrimer.push_back(oligoRC.getUnaligned());
                                }
                                else if(type == "barcode"){
                                        inOligos >> group;
@@ -307,7 +353,7 @@ void TrimSeqsCommand::getOligos(vector<ofstream*>& outFASTAVec){
                                        groupVector.push_back(group);
                                        
                                        if(allFiles){
-                                               outFASTAVec.push_back(new ofstream((getRootName(fastaFile) + group + ".fasta").c_str(), ios::ate));
+                                               outFASTAVec.push_back(new ofstream((outputDir + getRootName(getSimpleName(fastaFile)) + group + ".fasta").c_str(), ios::ate));
                                        }
                                }
                        }
@@ -404,7 +450,7 @@ bool TrimSeqsCommand::stripReverse(Sequence& seq){
                        }
                        
                        if(compareDNASeq(oligo, rawSequence.substr(rawSequence.length()-oligo.length(),oligo.length()))){
-                               seq.setUnaligned(rawSequence.substr(rawSequence.length()-oligo.length()));
+                               seq.setUnaligned(rawSequence.substr(0,rawSequence.length()-oligo.length()));
                                success = 1;
                                break;
                        }