]> git.donarmstrong.com Git - mothur.git/blobdiff - mothurout.cpp
finished added bygroup processing of chimeras in chimera.slayer and chimera.uchime...
[mothur.git] / mothurout.cpp
index 65296221759fa879e591bb0967b0f20872106adc..45d1176f9ddafeee56b219529efed45ea3d19d02 100644 (file)
@@ -39,6 +39,8 @@ void MothurOut::printCurrentFiles()  {
                if (sharedfile != "")           {  mothurOut("shared=" + sharedfile); mothurOutEndLine();                       }
                if (taxonomyfile != "")         {  mothurOut("taxonomy=" + taxonomyfile); mothurOutEndLine();           }
                if (treefile != "")                     {  mothurOut("tree=" + treefile); mothurOutEndLine();                           }
+               if (flowfile != "")                     {  mothurOut("flow=" + flowfile); mothurOutEndLine();                           }
+               if (processors != "1")          {  mothurOut("processors=" + processors); mothurOutEndLine();           }
                
        }
        catch(exception& e) {
@@ -70,6 +72,8 @@ bool MothurOut::hasCurrentFiles()  {
                if (sharedfile != "")           {  return true;                 }
                if (taxonomyfile != "")         {  return true;                 }
                if (treefile != "")                     {  return true;                 }
+               if (flowfile != "")                     {  return true;                 }
+               if (processors != "1")          {  return true;                 }
                
                return hasCurrent;
                
@@ -101,7 +105,9 @@ void MothurOut::clearCurrentFiles()  {
                sfffile = "";
                oligosfile = "";
                accnosfile = "";
-               taxonomyfile = "";              
+               taxonomyfile = "";      
+               flowfile = "";
+               processors = "1";
        }
        catch(exception& e) {
                errorOut(e, "MothurOut", "clearCurrentFiles");
@@ -241,6 +247,53 @@ void MothurOut::mothurOutEndLine() {
        }
 }
 /*********************************************************************************************/
+void MothurOut::mothurOut(string output, ofstream& outputFile) {
+       try {
+               
+#ifdef USE_MPI
+               int pid;
+               MPI_Comm_rank(MPI_COMM_WORLD, &pid); 
+               
+               if (pid == 0) { //only one process should output to screen
+#endif
+                       
+                       cout << output;
+                       out << output;
+                       outputFile << output;
+                       
+#ifdef USE_MPI
+               }
+#endif
+       }
+       catch(exception& e) {
+               errorOut(e, "MothurOut", "MothurOut");
+               exit(1);
+       }
+}
+/*********************************************************************************************/
+void MothurOut::mothurOutEndLine(ofstream& outputFile) {
+       try {
+#ifdef USE_MPI
+               int pid;
+               MPI_Comm_rank(MPI_COMM_WORLD, &pid); 
+               
+               if (pid == 0) { //only one process should output to screen
+#endif
+                       
+                       cout << endl;
+                       out << endl;
+                       outputFile << endl;
+                       
+#ifdef USE_MPI
+               }
+#endif
+       }
+       catch(exception& e) {
+               errorOut(e, "MothurOut", "MothurOutEndLine");
+               exit(1);
+       }
+}
+/*********************************************************************************************/
 void MothurOut::mothurOutJustToLog(string output) {
        try {
                #ifdef USE_MPI
@@ -432,12 +485,12 @@ string MothurOut::getline(ifstream& fileHandle) {
        
                string line = "";
                
-               while (!fileHandle.eof())       {
+               while (fileHandle)      {
                        //get next character
                        char c = fileHandle.get(); 
                        
                        //are you at the end of the line
-                       if ((c == '\n') || (c == '\r') || (c == '\f')){  break; }       
+                       if ((c == '\n') || (c == '\r') || (c == '\f') || (c == EOF)){  break;   }       
                        else {          line += c;              }
                }
                
@@ -509,6 +562,21 @@ string MothurOut::getSimpleName(string longName){
 
 /***********************************************************************/
 
+int MothurOut::getRandomIndex(int highest){
+       try {
+               
+               int random = (int) ((float)(highest+1) * (float)(rand()) / ((float)RAND_MAX+1.0));
+               
+               return random;
+       }
+       catch(exception& e) {
+               errorOut(e, "MothurOut", "getRandomIndex");
+               exit(1);
+       }       
+       
+}
+/**********************************************************************/
+
 string MothurOut::getPathName(string longName){
        try {
                string rootPathName = longName;
@@ -743,7 +811,7 @@ int MothurOut::openInputFile(string fileName, ifstream& fileHandle, string m){
           cerr << "Decompressing " << completeFileName << " via temporary named pipe " << tempName << "\n";
           system(command.c_str());
           cerr << "Done decompressing " << completeFileName << "\n";
-          remove(tempName.c_str());
+          mothurRemove(tempName);
           exit(EXIT_SUCCESS);
         } else {
           cerr << "waiting on child process " << fork_result << "\n";
@@ -789,7 +857,7 @@ int MothurOut::openInputFile(string fileName, ifstream& fileHandle){
       cerr << "Decompressing " << completeFileName << " via temporary named pipe " << tempName << "\n";
       system(command.c_str());
       cerr << "Done decompressing " << completeFileName << "\n";
-      remove(tempName.c_str());
+      mothurRemove(tempName);
       exit(EXIT_SUCCESS);
     } else {
       cerr << "waiting on child process " << fork_result << "\n";
@@ -834,7 +902,7 @@ int MothurOut::renameFile(string oldName, string newName){
                string command = "mv " + oldName + " " + newName;
                system(command.c_str());
        #else
-               remove(newName.c_str());
+               mothurRemove(newName);
                int renameOk = rename(oldName.c_str(), newName.c_str());
        #endif
                return 0;
@@ -890,7 +958,7 @@ int MothurOut::openOutputFile(string fileName, ofstream& fileHandle){
 }
 
 /**************************************************************************************************/
-void MothurOut::appendFiles(string temp, string filename) {
+int MothurOut::appendFiles(string temp, string filename) {
        try{
                ofstream output;
                ifstream input;
@@ -900,15 +968,18 @@ void MothurOut::appendFiles(string temp, string filename) {
                int ableToOpen = openInputFile(temp, input, "no error");
                //int ableToOpen = openInputFile(temp, input);
                
+               int numLines = 0;
                if (ableToOpen == 0) { //you opened it
                        while(char c = input.get()){
                                if(input.eof())         {       break;                  }
-                               else                            {       output << c;    }
+                               else                            {       output << c;    if (c == '\n') {numLines++;} }
                        }
                        input.close();
                }
                
                output.close();
+               
+               return numLines;
        }
        catch(exception& e) {
                errorOut(e, "MothurOut", "appendFiles");
@@ -970,8 +1041,8 @@ string MothurOut::sortFile(string distFile, string outputDir){
                        output.close();
                
                        //remove temp files
-                       remove(tempDistFile.c_str());
-                       remove(tempOutfile.c_str());
+                       mothurRemove(tempDistFile);
+                       mothurRemove(tempOutfile);
                #endif
                
                return outfile;
@@ -982,19 +1053,27 @@ string MothurOut::sortFile(string distFile, string outputDir){
        }       
 }
 /**************************************************************************************************/
-vector<unsigned long int> MothurOut::setFilePosFasta(string filename, int& num) {
+vector<unsigned long long> MothurOut::setFilePosFasta(string filename, int& num) {
        try {
-                       vector<unsigned long int> positions;
+                       vector<unsigned long long> positions;
                        ifstream inFASTA;
-                       openInputFile(filename, inFASTA);
+                       //openInputFile(filename, inFASTA);
+                       inFASTA.open(filename.c_str(), ios::binary);
                                                
                        string input;
+                       unsigned long long count = 0;
                        while(!inFASTA.eof()){
-                               input = getline(inFASTA); 
-                               if (input.length() != 0) {
-                                       if(input[0] == '>'){    unsigned long int pos = inFASTA.tellg(); positions.push_back(pos - input.length() - 1); }
+                               //input = getline(inFASTA); 
+                               //cout << input << '\t' << inFASTA.tellg() << endl;
+                               //if (input.length() != 0) {
+                               //      if(input[0] == '>'){    unsigned long int pos = inFASTA.tellg(); positions.push_back(pos - input.length() - 1);  cout << (pos - input.length() - 1) << endl; }
+                               //}
+                               //gobble(inFASTA); //has to be here since windows line endings are 2 characters and mess up the positions
+                               char c = inFASTA.get(); count++;
+                               if (c == '>') {
+                                       positions.push_back(count-1);
+                                       //cout << count << endl;
                                }
-                               gobble(inFASTA); //has to be here since windows line endings are 2 characters and mess up the positions
                        }
                        inFASTA.close();
                
@@ -1012,7 +1091,7 @@ vector<unsigned long int> MothurOut::setFilePosFasta(string filename, int& num)
                                fclose (pFile);
                        }*/
                        
-                       unsigned long int size = positions[(positions.size()-1)];
+                       unsigned long long size = positions[(positions.size()-1)];
                        ifstream in;
                        openInputFile(filename, in);
                        
@@ -1025,6 +1104,7 @@ vector<unsigned long int> MothurOut::setFilePosFasta(string filename, int& num)
                        in.close();
                
                        positions.push_back(size);
+                       positions[0] = 0;
                
                        return positions;
        }
@@ -1034,31 +1114,51 @@ vector<unsigned long int> MothurOut::setFilePosFasta(string filename, int& num)
        }
 }
 /**************************************************************************************************/
-vector<unsigned long int> MothurOut::setFilePosEachLine(string filename, int& num) {
+vector<unsigned long long> MothurOut::setFilePosEachLine(string filename, int& num) {
        try {
                        filename = getFullPathName(filename);
                        
-                       vector<unsigned long int> positions;
+                       vector<unsigned long long> positions;
                        ifstream in;
-                       openInputFile(filename, in);
-                               
+                       //openInputFile(filename, in);
+                       in.open(filename.c_str(), ios::binary);
+               
                        string input;
+                       unsigned long long count = 0;
+                       positions.push_back(0);
+               
                        while(!in.eof()){
-                               unsigned long int lastpos = in.tellg();
-                               input = getline(in); 
-                               if (input.length() != 0) {
-                                       unsigned long int pos = in.tellg(); 
-                                       if (pos != -1) { positions.push_back(pos - input.length() - 1); }
-                                       else {  positions.push_back(lastpos);  }
+                               //unsigned long long lastpos = in.tellg();
+                               //input = getline(in); 
+                               //if (input.length() != 0) {
+                                       //unsigned long long pos = in.tellg(); 
+                                       //if (pos != -1) { positions.push_back(pos - input.length() - 1);       }
+                                       //else {  positions.push_back(lastpos);  }
+                               //}
+                               //gobble(in); //has to be here since windows line endings are 2 characters and mess up the positions
+                               
+                               
+                               //getline counting reads
+                               char d = in.get(); count++;
+                               while ((d != '\n') && (d != '\r') && (d != '\f') && (d != in.eof()))    {
+                                       //get next character
+                                       d = in.get(); 
+                                       count++;
+                               }
+                               
+                               if (!in.eof()) {
+                                       d=in.get(); count++;
+                                       while(isspace(d) && (d != in.eof()))            { d=in.get(); count++;}
                                }
-                               gobble(in); //has to be here since windows line endings are 2 characters and mess up the positions
+                               positions.push_back(count-1);
+                               cout << count-1 << endl;
                        }
                        in.close();
                
-                       num = positions.size();
+                       num = positions.size()-1;
                
                        FILE * pFile;
-                       unsigned long int size;
+                       unsigned long long size;
                        
                        //get num bytes in file
                        pFile = fopen (filename.c_str(),"rb");
@@ -1069,7 +1169,7 @@ vector<unsigned long int> MothurOut::setFilePosEachLine(string filename, int& nu
                                fclose (pFile);
                        }
                
-                       positions.push_back(size);
+                       positions[(positions.size()-1)] = size;
                
                        return positions;
        }
@@ -1080,14 +1180,14 @@ vector<unsigned long int> MothurOut::setFilePosEachLine(string filename, int& nu
 }
 /**************************************************************************************************/
 
-vector<unsigned long int> MothurOut::divideFile(string filename, int& proc) {
+vector<unsigned long long> MothurOut::divideFile(string filename, int& proc) {
        try{
        
-               vector<unsigned long int> filePos;
+               vector<unsigned long long> filePos;
                filePos.push_back(0);
                
                FILE * pFile;
-               unsigned long int size;
+               unsigned long long size;
                
                filename = getFullPathName(filename);
                
@@ -1101,7 +1201,7 @@ vector<unsigned long int> MothurOut::divideFile(string filename, int& proc) {
                }
        
                //estimate file breaks
-               unsigned long int chunkSize = 0;
+               unsigned long long chunkSize = 0;
                chunkSize = size / proc;
 
                //file to small to divide by processors
@@ -1109,21 +1209,21 @@ vector<unsigned long int> MothurOut::divideFile(string filename, int& proc) {
        
                //for each process seekg to closest file break and search for next '>' char. make that the filebreak
                for (int i = 0; i < proc; i++) {
-                       unsigned long int spot = (i+1) * chunkSize;
+                       unsigned long long spot = (i+1) * chunkSize;
                        
                        ifstream in;
                        openInputFile(filename, in);
                        in.seekg(spot);
                        
                        //look for next '>'
-                       unsigned long int newSpot = spot;
+                       unsigned long long newSpot = spot;
                        while (!in.eof()) {
                           char c = in.get();
                           if (c == '>') {   in.putback(c); newSpot = in.tellg(); break;  }
                        }
                
                        //there was not another sequence before the end of the file
-                       unsigned long int sanityPos = in.tellg();
+                       unsigned long long sanityPos = in.tellg();
 
                        if (sanityPos == -1) {  break;  }
                        else {  filePos.push_back(newSpot);  }
@@ -1148,7 +1248,43 @@ vector<unsigned long int> MothurOut::divideFile(string filename, int& proc) {
                exit(1);
        }
 }
-
+/**************************************************************************************************/
+int MothurOut::divideFile(string filename, int& proc, vector<string>& files) {
+       try{
+               
+               vector<unsigned long long> filePos = divideFile(filename, proc);
+               
+               for (int i = 0; i < (filePos.size()-1); i++) {
+                       
+                       //read file chunk
+                       ifstream in;
+                       openInputFile(filename, in);
+                       in.seekg(filePos[i]);
+                       unsigned long long size = filePos[(i+1)] - filePos[i];
+                       char* chunk = new char[size];
+                       in.read(chunk, size);
+                       in.close();
+                       
+                       //open new file
+                       string fileChunkName = filename + "." + toString(i) + ".tmp";
+                       ofstream out; 
+                       openOutputFile(fileChunkName, out);
+                       
+                       out << chunk << endl;
+                       out.close();
+                       delete[] chunk;
+                       
+                       //save name
+                       files.push_back(fileChunkName);
+               }
+                               
+               return 0;
+       }
+       catch(exception& e) {
+               errorOut(e, "MothurOut", "divideFile");
+               exit(1);
+       }
+}
 /***********************************************************************/
 
 bool MothurOut::isTrue(string f){
@@ -1187,6 +1323,33 @@ float MothurOut::ceilDist(float dist, int precision){
                exit(1);
        }
 }
+/**********************************************************************************************************************/
+int MothurOut::readNames(string namefile, map<string, string>& nameMap) { 
+       try {
+               
+               //open input file
+               ifstream in;
+               openInputFile(namefile, in);
+               
+               while (!in.eof()) {
+                       if (control_pressed) { break; }
+                       
+                       string firstCol, secondCol;
+                       in >> firstCol >> secondCol; gobble(in);
+                       
+                       nameMap[firstCol] = secondCol;
+               }
+               in.close();
+               
+               return 0;
+               
+       }
+       catch(exception& e) {
+               errorOut(e, "MothurOut", "readNames");
+               exit(1);
+       }
+}
+
 /**********************************************************************************************************************/
 map<string, int> MothurOut::readNames(string namefile) { 
        try {
@@ -1276,7 +1439,18 @@ int MothurOut::getNumNames(string names){
                exit(1);
        }
 }
+/***********************************************************************/
 
+void MothurOut::mothurRemove(string filename){
+       try {
+               filename = getFullPathName(filename);
+               remove(filename.c_str());
+       }
+       catch(exception& e) {
+               errorOut(e, "MothurOut", "mothurRemove");
+               exit(1);
+       }
+}
 /**************************************************************************************************/
 
 vector<vector<double> > MothurOut::binomial(int maxOrder){