]> git.donarmstrong.com Git - mothur.git/blobdiff - chimerapintailcommand.cpp
changing command name classify.shared to classifyrf.shared
[mothur.git] / chimerapintailcommand.cpp
index 01a905f40d4c69514230ad033367cc02982cd3db..fca9f176d9e66c8452a8da5c451eba71ca76d6eb 100644 (file)
 //**********************************************************************************************************************
 vector<string> ChimeraPintailCommand::setParameters(){ 
        try {
-               CommandParameter ptemplate("reference", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(ptemplate);
-               CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(pfasta);
-               CommandParameter pconservation("conservation", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(pconservation);
-               CommandParameter pquantile("quantile", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(pquantile);
-               CommandParameter pfilter("filter", "Boolean", "", "F", "", "", "",false,false); parameters.push_back(pfilter);
-               CommandParameter pwindow("window", "Number", "", "0", "", "", "",false,false); parameters.push_back(pwindow);
-               CommandParameter pincrement("increment", "Number", "", "25", "", "", "",false,false); parameters.push_back(pincrement);
-               CommandParameter pmask("mask", "String", "", "", "", "", "",false,false); parameters.push_back(pmask);
-               CommandParameter pprocessors("processors", "Number", "", "1", "", "", "",false,false); parameters.push_back(pprocessors);
-               CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir);
-               CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir);
-               CommandParameter psave("save", "Boolean", "", "F", "", "", "",false,false); parameters.push_back(psave);
+               CommandParameter ptemplate("reference", "InputTypes", "", "", "none", "none", "none","",false,true,true); parameters.push_back(ptemplate);
+               CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "none","chimera-accnos",false,true,true); parameters.push_back(pfasta);
+               CommandParameter pconservation("conservation", "InputTypes", "", "", "none", "none", "none","",false,false); parameters.push_back(pconservation);
+               CommandParameter pquantile("quantile", "InputTypes", "", "", "none", "none", "none","",false,false); parameters.push_back(pquantile);
+               CommandParameter pfilter("filter", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(pfilter);
+               CommandParameter pwindow("window", "Number", "", "0", "", "", "","","",false,false); parameters.push_back(pwindow);
+               CommandParameter pincrement("increment", "Number", "", "25", "", "", "","",false,false); parameters.push_back(pincrement);
+               CommandParameter pmask("mask", "String", "", "", "", "", "","",false,false); parameters.push_back(pmask);
+               CommandParameter pprocessors("processors", "Number", "", "1", "", "", "","",false,false,true); parameters.push_back(pprocessors);
+               CommandParameter pinputdir("inputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(pinputdir);
+               CommandParameter poutputdir("outputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(poutputdir);
+               CommandParameter psave("save", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(psave);
 
                vector<string> myArray;
                for (int i = 0; i < parameters.size(); i++) {   myArray.push_back(parameters[i].name);          }
@@ -41,7 +41,7 @@ string ChimeraPintailCommand::getHelpString(){
        try {
                string helpString = "";
                helpString += "The chimera.pintail command reads a fastafile and referencefile and outputs potentially chimeric sequences.\n";
-               helpString += "This command was created using the algorythms described in the 'At Least 1 in 20 16S rRNA Sequence Records Currently Held in the Public Repositories is Estimated To Contain Substantial Anomalies' paper by Kevin E. Ashelford 1, Nadia A. Chuzhanova 3, John C. Fry 1, Antonia J. Jones 2 and Andrew J. Weightman 1.\n";
+               helpString += "This command was created using the algorithms described in the 'At Least 1 in 20 16S rRNA Sequence Records Currently Held in the Public Repositories is Estimated To Contain Substantial Anomalies' paper by Kevin E. Ashelford 1, Nadia A. Chuzhanova 3, John C. Fry 1, Antonia J. Jones 2 and Andrew J. Weightman 1.\n";
                helpString += "The chimera.pintail command parameters are fasta, reference, filter, mask, processors, window, increment, conservation and quantile.\n";
                helpString += "The fasta parameter allows you to enter the fasta file containing your potentially chimeric 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";
@@ -69,6 +69,22 @@ string ChimeraPintailCommand::getHelpString(){
        }
 }
 //**********************************************************************************************************************
+string ChimeraPintailCommand::getOutputPattern(string type) {
+    try {
+        string pattern = "";
+        
+        if (type == "chimera") {  pattern = "[filename],[tag],pintail.chimeras-[filename],pintail.chimeras"; } 
+        else if (type == "accnos") {  pattern = "[filename],[tag],pintail.accnos-[filename],pintail.accnos"; } 
+        else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true;  }
+        
+        return pattern;
+    }
+    catch(exception& e) {
+        m->errorOut(e, "ChimeraPintailCommand", "getOutputPattern");
+        exit(1);
+    }
+}
+//**********************************************************************************************************************
 ChimeraPintailCommand::ChimeraPintailCommand(){        
        try {
                abort = true; calledHelp = true;
@@ -76,6 +92,7 @@ ChimeraPintailCommand::ChimeraPintailCommand(){
                vector<string> tempOutNames;
                outputTypes["chimera"] = tempOutNames;
                outputTypes["accnos"] = tempOutNames;
+        
        }
        catch(exception& e) {
                m->errorOut(e, "ChimeraPintailCommand", "ChimeraPintailCommand");
@@ -109,6 +126,7 @@ ChimeraPintailCommand::ChimeraPintailCommand(string option)  {
                        vector<string> tempOutNames;
                        outputTypes["chimera"] = tempOutNames;
                        outputTypes["accnos"] = tempOutNames;
+        
                
                        //if the user changes the input directory command factory will send this info to us in the output parameter 
                        inputDir = validParameter.validFile(parameters, "inputdir", false);             
@@ -225,13 +243,13 @@ ChimeraPintailCommand::ChimeraPintailCommand(string option)  {
                        
                        temp = validParameter.validFile(parameters, "processors", false);       if (temp == "not found"){       temp = m->getProcessors();      }
                        m->setProcessors(temp);
-                       convert(temp, processors);
+                       m->mothurConvert(temp, processors);
                        
                        temp = validParameter.validFile(parameters, "window", false);                   if (temp == "not found") { temp = "0"; }
-                       convert(temp, window);
+                       m->mothurConvert(temp, window);
                        
                        temp = validParameter.validFile(parameters, "increment", false);                if (temp == "not found") { temp = "25"; }
-                       convert(temp, increment);
+                       m->mothurConvert(temp, increment);
                        
                        temp = validParameter.validFile(parameters, "save", false);                     if (temp == "not found"){       temp = "f";                             }
                        save = m->isTrue(temp); 
@@ -392,18 +410,16 @@ int ChimeraPintailCommand::execute(){
                                        }
                                }
                        }
-                       
                        chimera = new Pintail(fastaFileNames[s], templatefile, filter, processors, maskfile, consfile, quanfile, window, increment, outputDir);
                        
                        if (outputDir == "") { outputDir = m->hasPath(fastaFileNames[s]);  }//if user entered a file with a path then preserve it
                        string outputFileName, accnosFileName;
-                       if (maskfile != "") {
-                               outputFileName = outputDir + m->getRootName(m->getSimpleName(fastaFileNames[s])) + m->getSimpleName(m->getRootName(maskfile)) + ".pintail.chimeras";
-                               accnosFileName = outputDir + m->getRootName(m->getSimpleName(fastaFileNames[s])) + m->getSimpleName(m->getRootName(maskfile)) + ".pintail.accnos";
-                       }else {
-                               outputFileName = outputDir + m->getRootName(m->getSimpleName(fastaFileNames[s]))  + "pintail.chimeras";
-                               accnosFileName = outputDir + m->getRootName(m->getSimpleName(fastaFileNames[s]))  + "pintail.accnos";
-                       }
+            map<string, string> variables;
+            variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(fastaFileNames[s]));
+                       if (maskfile != "") { variables["[tag]"] = m->getSimpleName(m->getRootName(maskfile)); }
+            outputFileName = getOutputFileName("chimera", variables);
+            accnosFileName = getOutputFileName("accnos", variables);
+                       
                        
                        if (m->control_pressed) { delete chimera; for (int j = 0; j < outputNames.size(); j++) {        m->mothurRemove(outputNames[j]);        }  return 0;    }
                        
@@ -417,7 +433,7 @@ int ChimeraPintailCommand::execute(){
                #ifdef USE_MPI
                        int pid, numSeqsPerProcessor; 
                                int tag = 2001;
-                               vector<unsigned long int> MPIPos;
+                               vector<unsigned long long> MPIPos;
                                
                                MPI_Status status; 
                                MPI_Comm_rank(MPI_COMM_WORLD, &pid); //find out who we are
@@ -487,14 +503,15 @@ int ChimeraPintailCommand::execute(){
                                MPI_File_close(&outMPIAccnos);
                                MPI_Barrier(MPI_COMM_WORLD); //make everyone wait - just in case
                #else
-                       vector<unsigned long int> positions = m->divideFile(fastaFileNames[s], processors);
-                               
-                       for (int i = 0; i < (positions.size()-1); i++) {
-                               lines.push_back(new linePair(positions[i], positions[(i+1)]));
-                       }       
-                       
+                                               
                        //break up file
-                       #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux)
+                       #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix)
+                               vector<unsigned long long> positions = m->divideFile(fastaFileNames[s], processors);
+                       
+                               for (int i = 0; i < (positions.size()-1); i++) {
+                                       lines.push_back(new linePair(positions[i], positions[(i+1)]));
+                               }       
+                       
                                if(processors == 1){
                
                                        numSeqs = driver(lines[0], outputFileName, fastaFileNames[s], accnosFileName);
@@ -532,6 +549,7 @@ int ChimeraPintailCommand::execute(){
                                }
 
                        #else
+                               lines.push_back(new linePair(0, 1000));
                                numSeqs = driver(lines[0], outputFileName, fastaFileNames[s], accnosFileName);
                                
                                if (m->control_pressed) { outputTypes.clear(); m->mothurRemove(outputFileName); m->mothurRemove(accnosFileName); for (int j = 0; j < outputNames.size(); j++) { m->mothurRemove(outputNames[j]);        } for (int i = 0; i < lines.size(); i++) {  delete lines[i];  }  lines.clear(); delete chimera; return 0; }
@@ -610,18 +628,18 @@ int ChimeraPintailCommand::driver(linePair* filePos, string outputFName, string
                        }
                        delete candidateSeq;
                        
-                       #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux)
-                               unsigned long int pos = inFASTA.tellg();
+                       #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix)
+                               unsigned long long pos = inFASTA.tellg();
                                if ((pos == -1) || (pos >= filePos->end)) { break; }
                        #else
                                if (inFASTA.eof()) { break; }
                        #endif
                        
                        //report progress
-                       if((count) % 100 == 0){ m->mothurOut("Processing sequence: " + toString(count)); m->mothurOutEndLine();         }
+                       if((count) % 100 == 0){ m->mothurOutJustToScreen("Processing sequence: " + toString(count) + "\n");             }
                }
                //report progress
-               if((count) % 100 != 0){ m->mothurOut("Processing sequence: " + toString(count)); m->mothurOutEndLine();         }
+               if((count) % 100 != 0){ m->mothurOutJustToScreen("Processing sequence: " + toString(count) + "\n");             }
                
                out.close();
                out2.close();
@@ -636,7 +654,7 @@ int ChimeraPintailCommand::driver(linePair* filePos, string outputFName, string
 }
 //**********************************************************************************************************************
 #ifdef USE_MPI
-int ChimeraPintailCommand::driverMPI(int start, int num, MPI_File& inMPI, MPI_File& outMPI, MPI_File& outAccMPI, vector<unsigned long int>& MPIPos){
+int ChimeraPintailCommand::driverMPI(int start, int num, MPI_File& inMPI, MPI_File& outMPI, MPI_File& outAccMPI, vector<unsigned long long>& MPIPos){
        try {
                                
                MPI_Status status; 
@@ -677,10 +695,10 @@ int ChimeraPintailCommand::driverMPI(int start, int num, MPI_File& inMPI, MPI_Fi
                        delete candidateSeq;
                        
                        //report progress
-                       if((i+1) % 100 == 0){  cout << "Processing sequence: " << (i+1) << endl;        m->mothurOutJustToLog("Processing sequence: " + toString(i+1) + "\n");          }
+                       if((i+1) % 100 == 0){  cout << "Processing sequence: " << (i+1) << endl;                        }
                }
                //report progress
-               if(num % 100 != 0){             cout << "Processing sequence: " << num << endl; m->mothurOutJustToLog("Processing sequence: " + toString(num) + "\n");  }
+               if(num % 100 != 0){             cout << "Processing sequence: " << num << endl;         }
                
                                
                return 0;
@@ -696,7 +714,7 @@ int ChimeraPintailCommand::driverMPI(int start, int num, MPI_File& inMPI, MPI_Fi
 
 int ChimeraPintailCommand::createProcesses(string outputFileName, string filename, string accnos) {
        try {
-#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux)
+#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix)
                int process = 0;
                int num = 0;