]> git.donarmstrong.com Git - mothur.git/blobdiff - aligncommand.cpp
changes to filter.seqs
[mothur.git] / aligncommand.cpp
index 784155745fa9c0141d6b2db0ba80133b39e3a85f..257587fa048ac3b494fa4f0ed4481f2cd505e513 100644 (file)
@@ -28,9 +28,9 @@
 
 //**********************************************************************************************************************
 
-AlignCommand::AlignCommand(string option){
+AlignCommand::AlignCommand(string option)  {
        try {
-               //              globaldata = GlobalData::getInstance();
+               
                abort = false;
                
                //allow user to run help
@@ -52,16 +52,20 @@ AlignCommand::AlignCommand(string option){
                        for (it = parameters.begin(); it != parameters.end(); it++) { 
                                if (validParameter.isValidParameter(it->first, myArray, it->second) != true) {  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 = "";         }
                        
+
                        //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("template");
+
                                //user has given a template file
                                if(it != parameters.end()){ 
                                        path = hasPath(it->second);
@@ -69,17 +73,18 @@ AlignCommand::AlignCommand(string option){
                                        if (path == "") {       parameters["template"] = inputDir + it->second;         }
                                }
                        }
-                       
+
                        //check for required parameters
                        templateFileName = validParameter.validFile(parameters, "template", true);
+                       
                        if (templateFileName == "not found") { 
-                               mothurOut("template is a required parameter for the align.seqs command."); 
-                               mothurOutEndLine();
+                               m->mothurOut("template is a required parameter for the align.seqs command."); 
+                               m->mothurOutEndLine();
                                abort = true; 
                        }else if (templateFileName == "not open") { abort = true; }     
                        
                        candidateFileName = validParameter.validFile(parameters, "candidate", false);
-                       if (candidateFileName == "not found") { mothurOut("candidate is a required parameter for the align.seqs command."); mothurOutEndLine(); abort = true;  }
+                       if (candidateFileName == "not found") { m->mothurOut("candidate is a required parameter for the align.seqs command."); m->mothurOutEndLine(); abort = true;  }
                        else { 
                                splitAtDash(candidateFileName, candidateFileNames);
                                
@@ -95,7 +100,7 @@ AlignCommand::AlignCommand(string option){
                                        ifstream in;
                                        ableToOpen = openInputFile(candidateFileNames[i], in);
                                        if (ableToOpen == 1) { 
-                                               mothurOut(candidateFileNames[i] + " will be disregarded."); mothurOutEndLine(); 
+                                               m->mothurOut(candidateFileNames[i] + " will be disregarded."); m->mothurOutEndLine(); 
                                                //erase from file list
                                                candidateFileNames.erase(candidateFileNames.begin()+i);
                                                i--;
@@ -104,9 +109,8 @@ AlignCommand::AlignCommand(string option){
                                }
                                
                                //make sure there is at least one valid file left
-                               if (candidateFileNames.size() == 0) { mothurOut("no valid files."); mothurOutEndLine(); abort = true; }
+                               if (candidateFileNames.size() == 0) { m->mothurOut("no valid files."); m->mothurOutEndLine(); abort = true; }
                        }
-                               
                        
                        //check for optional parameter and set defaults
                        // ...at some point should added some additional type checking...
@@ -142,7 +146,7 @@ AlignCommand::AlignCommand(string option){
                
        }
        catch(exception& e) {
-               errorOut(e, "AlignCommand", "AlignCommand");
+               m->errorOut(e, "AlignCommand", "AlignCommand");
                exit(1);
        }
 }
@@ -162,27 +166,27 @@ AlignCommand::~AlignCommand(){
 
 void AlignCommand::help(){
        try {
-               mothurOut("The align.seqs command reads a file containing sequences and creates an alignment file and a report file.\n");
-               mothurOut("The align.seqs command parameters are template, candidate, search, ksize, align, match, mismatch, gapopen and gapextend.\n");
-               mothurOut("The template and candidate parameters are required. You may enter multiple fasta files by separating their names with dashes. ie. fasta=abrecovery.fasta-amzon.fasta \n");
-               mothurOut("The search parameter allows you to specify the method to find most similar template.  Your options are: suffix, kmer and blast. The default is kmer.\n");
-               mothurOut("The align parameter allows you to specify the alignment method to use.  Your options are: gotoh, needleman, blast and noalign. The default is needleman.\n");
-               mothurOut("The ksize parameter allows you to specify the kmer size for finding most similar template to candidate.  The default is 8.\n");
-               mothurOut("The match parameter allows you to specify the bonus for having the same base. The default is 1.0.\n");
-               mothurOut("The mistmatch parameter allows you to specify the penalty for having different bases.  The default is -1.0.\n");
-               mothurOut("The gapopen parameter allows you to specify the penalty for opening a gap in an alignment. The default is -2.0.\n");
-               mothurOut("The gapextend parameter allows you to specify the penalty for extending a gap in an alignment.  The default is -1.0.\n");
-               mothurOut("The flip parameter is used to specify whether or not you want mothur to try the reverse complement if a sequence falls below the threshold.  The default is false.\n");
-               mothurOut("The threshold is used to specify a cutoff at which an alignment is deemed 'bad' and the reverse complement may be tried. The default threshold is 0.50, meaning 50% of the bases are removed in the alignment.\n");
-               mothurOut("If the flip parameter is set to true the reverse complement of the sequence is aligned and the better alignment is reported.\n");
-               mothurOut("The default for the threshold parameter is 0.50, meaning at least 50% of the bases must remain or the sequence is reported as potentially reversed.\n");
-               mothurOut("The align.seqs command should be in the following format: \n");
-               mothurOut("align.seqs(template=yourTemplateFile, candidate=yourCandidateFile, align=yourAlignmentMethod, search=yourSearchmethod, ksize=yourKmerSize, match=yourMatchBonus, mismatch=yourMismatchpenalty, gapopen=yourGapopenPenalty, gapextend=yourGapExtendPenalty) \n");
-               mothurOut("Example align.seqs(candidate=candidate.fasta, template=core.filtered, align=kmer, search=gotoh, ksize=8, match=2.0, mismatch=3.0, gapopen=-2.0, gapextend=-1.0)\n");
-               mothurOut("Note: No spaces between parameter labels (i.e. candidate), '=' and parameters (i.e.yourFastaFile).\n\n");
+               m->mothurOut("The align.seqs command reads a file containing sequences and creates an alignment file and a report file.\n");
+               m->mothurOut("The align.seqs command parameters are template, candidate, search, ksize, align, match, mismatch, gapopen and gapextend.\n");
+               m->mothurOut("The template and candidate parameters are required. You may enter multiple fasta files by separating their names with dashes. ie. fasta=abrecovery.fasta-amzon.fasta \n");
+               m->mothurOut("The search parameter allows you to specify the method to find most similar template.  Your options are: suffix, kmer and blast. The default is kmer.\n");
+               m->mothurOut("The align parameter allows you to specify the alignment method to use.  Your options are: gotoh, needleman, blast and noalign. The default is needleman.\n");
+               m->mothurOut("The ksize parameter allows you to specify the kmer size for finding most similar template to candidate.  The default is 8.\n");
+               m->mothurOut("The match parameter allows you to specify the bonus for having the same base. The default is 1.0.\n");
+               m->mothurOut("The mistmatch parameter allows you to specify the penalty for having different bases.  The default is -1.0.\n");
+               m->mothurOut("The gapopen parameter allows you to specify the penalty for opening a gap in an alignment. The default is -2.0.\n");
+               m->mothurOut("The gapextend parameter allows you to specify the penalty for extending a gap in an alignment.  The default is -1.0.\n");
+               m->mothurOut("The flip parameter is used to specify whether or not you want mothur to try the reverse complement if a sequence falls below the threshold.  The default is false.\n");
+               m->mothurOut("The threshold is used to specify a cutoff at which an alignment is deemed 'bad' and the reverse complement may be tried. The default threshold is 0.50, meaning 50% of the bases are removed in the alignment.\n");
+               m->mothurOut("If the flip parameter is set to true the reverse complement of the sequence is aligned and the better alignment is reported.\n");
+               m->mothurOut("The default for the threshold parameter is 0.50, meaning at least 50% of the bases must remain or the sequence is reported as potentially reversed.\n");
+               m->mothurOut("The align.seqs command should be in the following format: \n");
+               m->mothurOut("align.seqs(template=yourTemplateFile, candidate=yourCandidateFile, align=yourAlignmentMethod, search=yourSearchmethod, ksize=yourKmerSize, match=yourMatchBonus, mismatch=yourMismatchpenalty, gapopen=yourGapopenPenalty, gapextend=yourGapExtendPenalty) \n");
+               m->mothurOut("Example align.seqs(candidate=candidate.fasta, template=core.filtered, align=kmer, search=gotoh, ksize=8, match=2.0, mismatch=3.0, gapopen=-2.0, gapextend=-1.0)\n");
+               m->mothurOut("Note: No spaces between parameter labels (i.e. candidate), '=' and parameters (i.e.yourFastaFile).\n\n");
        }
        catch(exception& e) {
-               errorOut(e, "AlignCommand", "help");
+               m->errorOut(e, "AlignCommand", "help");
                exit(1);
        }
 }
@@ -202,18 +206,22 @@ int AlignCommand::execute(){
                else if(align == "blast")               {       alignment = new BlastAlignment(gapOpen, gapExtend, match, misMatch);            }
                else if(align == "noalign")             {       alignment = new NoAlign();                                                                                                      }
                else {
-                       mothurOut(align + " is not a valid alignment option. I will run the command using needleman.");
-                       mothurOutEndLine();
+                       m->mothurOut(align + " is not a valid alignment option. I will run the command using needleman.");
+                       m->mothurOutEndLine();
                        alignment = new NeedlemanOverlap(gapOpen, match, misMatch, longestBase);
                }
+               vector<string> outputNames;
                
                for (int s = 0; s < candidateFileNames.size(); s++) {
-                       mothurOut("Aligning sequences from " + candidateFileNames[s] + " ..." ); mothurOutEndLine();
+                       if (m->control_pressed) { return 0; }
+                       
+                       m->mothurOut("Aligning sequences from " + candidateFileNames[s] + " ..." ); m->mothurOutEndLine();
                        
                        if (outputDir == "") {  outputDir += hasPath(candidateFileNames[s]); }
                        string alignFileName = outputDir + getRootName(getSimpleName(candidateFileNames[s])) + "align";
                        string reportFileName = outputDir + getRootName(getSimpleName(candidateFileNames[s])) + "align.report";
                        string accnosFileName = outputDir + getRootName(getSimpleName(candidateFileNames[s])) + "flip.accnos";
+                       bool hasAccnos = true;
                        
                        int numFastaSeqs = 0;
                        for (int i = 0; i < lines.size(); i++) {  delete lines[i];  }  lines.clear();
@@ -230,14 +238,21 @@ int AlignCommand::execute(){
                                
                                driver(lines[0], alignFileName, reportFileName, accnosFileName, candidateFileNames[s]);
                                
+                               if (m->control_pressed) { 
+                                       remove(accnosFileName.c_str()); 
+                                       remove(alignFileName.c_str()); 
+                                       remove(reportFileName.c_str()); 
+                                       return 0; 
+                               }
+                               
                                //delete accnos file if its blank else report to user
-                               if (isBlank(accnosFileName)) {  remove(accnosFileName.c_str());  }
+                               if (isBlank(accnosFileName)) {  remove(accnosFileName.c_str());  hasAccnos = false; }
                                else { 
-                                       mothurOut("Some of you sequences generated alignments that eliminated too many bases, a list is provided in " + accnosFileName + ".");
+                                       m->mothurOut("Some of you sequences generated alignments that eliminated too many bases, a list is provided in " + accnosFileName + ".");
                                        if (!flip) {
-                                               mothurOut(" If you set the flip parameter to true mothur will try aligning the reverse compliment as well."); 
-                                       }else{  mothurOut(" If the reverse compliment proved to be better it was reported.");  }
-                                       mothurOutEndLine();
+                                               m->mothurOut(" If you set the flip parameter to true mothur will try aligning the reverse compliment as well."); 
+                                       }else{  m->mothurOut(" If the reverse compliment proved to be better it was reported.");  }
+                                       m->mothurOutEndLine();
                                }
                        }
                        else{
@@ -298,11 +313,18 @@ int AlignCommand::execute(){
                                                appendAlignFiles(nonBlankAccnosFiles[h], accnosFileName);
                                                remove(nonBlankAccnosFiles[h].c_str());
                                        }
-                                       mothurOut("Some of you sequences generated alignments that eliminated too many bases, a list is provided in " + accnosFileName + ".");
+                                       m->mothurOut("Some of you sequences generated alignments that eliminated too many bases, a list is provided in " + accnosFileName + ".");
                                        if (!flip) {
-                                               mothurOut(" If you set the flip parameter to true mothur will try aligning the reverse compliment as well."); 
-                                       }else{  mothurOut(" If the reverse compliment proved to be better it was reported.");  }
-                                       mothurOutEndLine();
+                                               m->mothurOut(" If you set the flip parameter to true mothur will try aligning the reverse compliment as well."); 
+                                       }else{  m->mothurOut(" If the reverse compliment proved to be better it was reported.");  }
+                                       m->mothurOutEndLine();
+                               }else{ hasAccnos = false;  }
+                               
+                               if (m->control_pressed) { 
+                                       remove(accnosFileName.c_str()); 
+                                       remove(alignFileName.c_str()); 
+                                       remove(reportFileName.c_str()); 
+                                       return 0; 
                                }
                        }
 #else
@@ -315,29 +337,44 @@ int AlignCommand::execute(){
                        
                        driver(lines[0], alignFileName, reportFileName, accnosFileName, candidateFileNames[s]);
                        
+                       if (m->control_pressed) { 
+                               remove(accnosFileName.c_str()); 
+                               remove(alignFileName.c_str()); 
+                               remove(reportFileName.c_str()); 
+                               return 0; 
+                       }
+                       
                        //delete accnos file if its blank else report to user
-                       if (isBlank(accnosFileName)) {  remove(accnosFileName.c_str());  }
+                       if (isBlank(accnosFileName)) {  remove(accnosFileName.c_str());  hasAccnos = false; }
                        else { 
-                               mothurOut("Some of you sequences generated alignments that eliminated too many bases, a list is provided in " + accnosFileName + ".");
+                               m->mothurOut("Some of you sequences generated alignments that eliminated too many bases, a list is provided in " + accnosFileName + ".");
                                if (!flip) {
-                                       mothurOut(" If you set the flip parameter to true mothur will try aligning the reverse compliment as well."); 
-                               }else{  mothurOut(" If the reverse compliment proved to be better it was reported.");  }
-                               mothurOutEndLine();
+                                       m->mothurOut(" If you set the flip parameter to true mothur will try aligning the reverse compliment as well."); 
+                               }else{  m->mothurOut(" If the reverse compliment proved to be better it was reported.");  }
+                               m->mothurOutEndLine();
                        }
                        
 #endif
                        
-                       
-                       
-                       mothurOut("It took " + toString(time(NULL) - start) + " secs to align " + toString(numFastaSeqs) + " sequences.");
-                       mothurOutEndLine();
-                       mothurOutEndLine();
+                       outputNames.push_back(alignFileName);
+                       outputNames.push_back(reportFileName);
+                       if (hasAccnos)  {       outputNames.push_back(accnosFileName);          }
+                                               
+                       m->mothurOut("It took " + toString(time(NULL) - start) + " secs to align " + toString(numFastaSeqs) + " sequences.");
+                       m->mothurOutEndLine();
+                       m->mothurOutEndLine();
                }
                
+               
+               m->mothurOutEndLine();
+               m->mothurOut("Output File Names: "); m->mothurOutEndLine();
+               for (int i = 0; i < outputNames.size(); i++) {  m->mothurOut(outputNames[i]); m->mothurOutEndLine();    }
+               m->mothurOutEndLine();
+
                return 0;
        }
        catch(exception& e) {
-               errorOut(e, "AlignCommand", "execute");
+               m->errorOut(e, "AlignCommand", "execute");
                exit(1);
        }
 }
@@ -360,7 +397,9 @@ int AlignCommand::driver(linePair* line, string alignFName, string reportFName,
                inFASTA.seekg(line->start);
                
                for(int i=0;i<line->numSeqs;i++){
-               
+                       
+                       if (m->control_pressed) {  return 0; }
+                       
                        Sequence* candidateSeq = new Sequence(inFASTA);  gobble(inFASTA);
                        int origNumBases = candidateSeq->getNumBases();
                        string originalUnaligned = candidateSeq->getUnaligned();
@@ -436,10 +475,10 @@ int AlignCommand::driver(linePair* line, string alignFName, string reportFName,
                        delete candidateSeq;
                        
                        //report progress
-                       if((i+1) % 100 == 0){   mothurOut(toString(i+1)); mothurOutEndLine();           }
+                       if((i+1) % 100 == 0){   m->mothurOut(toString(i+1)); m->mothurOutEndLine();             }
                }
                //report progress
-               if((line->numSeqs) % 100 != 0){ mothurOut(toString(line->numSeqs)); mothurOutEndLine();         }
+               if((line->numSeqs) % 100 != 0){ m->mothurOut(toString(line->numSeqs)); m->mothurOutEndLine();           }
                
                alignmentFile.close();
                inFASTA.close();
@@ -448,17 +487,18 @@ int AlignCommand::driver(linePair* line, string alignFName, string reportFName,
                return 1;
        }
        catch(exception& e) {
-               errorOut(e, "AlignCommand", "driver");
+               m->errorOut(e, "AlignCommand", "driver");
                exit(1);
        }
 }
 
 /**************************************************************************************************/
 
-void AlignCommand::createProcesses(string alignFileName, string reportFileName, string accnosFName, string filename) {
+int AlignCommand::createProcesses(string alignFileName, string reportFileName, string accnosFName, string filename) {
        try {
 #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux)
                int process = 0;
+               int exitCommand = 1;
                //              processIDS.resize(0);
                
                //loop through and create all the processes you want
@@ -469,9 +509,9 @@ void AlignCommand::createProcesses(string alignFileName, string reportFileName,
                                processIDS.push_back(pid);  //create map from line number to pid so you can append files in correct order later
                                process++;
                        }else if (pid == 0){
-                               driver(lines[process], alignFileName + toString(getpid()) + ".temp", reportFileName + toString(getpid()) + ".temp", accnosFName + toString(getpid()) + ".temp", filename);
+                               exitCommand = driver(lines[process], alignFileName + toString(getpid()) + ".temp", reportFileName + toString(getpid()) + ".temp", accnosFName + toString(getpid()) + ".temp", filename);
                                exit(0);
-                       }else { mothurOut("unable to spawn the necessary processes."); mothurOutEndLine(); exit(0); }
+                       }else { m->mothurOut("unable to spawn the necessary processes."); m->mothurOutEndLine(); exit(0); }
                }
                
                //force parent to wait until all the processes are done
@@ -479,10 +519,12 @@ void AlignCommand::createProcesses(string alignFileName, string reportFileName,
                        int temp = processIDS[i];
                        wait(&temp);
                }
+               
+               return exitCommand;
 #endif         
        }
        catch(exception& e) {
-               errorOut(e, "AlignCommand", "createProcesses");
+               m->errorOut(e, "AlignCommand", "createProcesses");
                exit(1);
        }
 }
@@ -506,7 +548,7 @@ void AlignCommand::appendAlignFiles(string temp, string filename) {
                output.close();
        }
        catch(exception& e) {
-               errorOut(e, "AlignCommand", "appendAlignFiles");
+               m->errorOut(e, "AlignCommand", "appendAlignFiles");
                exit(1);
        }
 }
@@ -531,7 +573,7 @@ void AlignCommand::appendReportFiles(string temp, string filename) {
                output.close();
        }
        catch(exception& e) {
-               errorOut(e, "AlignCommand", "appendReportFiles");
+               m->errorOut(e, "AlignCommand", "appendReportFiles");
                exit(1);
        }
 }