]> git.donarmstrong.com Git - mothur.git/blobdiff - sequence.cpp
pat's updates on 7/19/10
[mothur.git] / sequence.cpp
index b73bfab7caefdb0a97e5f7cc8f3271ec3e51cb57..38e9b6230838424dd136562111f25967f6822099 100644 (file)
 #include "sequence.hpp"
 
 /***********************************************************************/
-
 Sequence::Sequence(){
        m = MothurOut::getInstance();
        initialize();
 }
-
 /***********************************************************************/
-
 Sequence::Sequence(string newName, string sequence) {
        try {
                m = MothurOut::getInstance();
@@ -33,43 +30,99 @@ Sequence::Sequence(string newName, string sequence) {
                exit(1);
        }                       
 }
+/***********************************************************************/
+Sequence::Sequence(string newName, string sequence, string justUnAligned) {
+       try {
+               m = MothurOut::getInstance();
+               initialize();   
+               name = newName;
+               
+               //setUnaligned removes any gap characters for us
+               setUnaligned(sequence);
+       }
+       catch(exception& e) {
+               m->errorOut(e, "Sequence", "Sequence");
+               exit(1);
+       }                       
+}
+
 //********************************************************************************************************************
 //this function will jump over commented out sequences, but if the last sequence in a file is commented out it makes a blank seq
 Sequence::Sequence(istringstream& fastaString){
        try {
                m = MothurOut::getInstance();
-       int pid;
-       MPI_Comm_rank(MPI_COMM_WORLD, &pid); 
-       cout << pid << " after mothur instance " << &name << endl;
+       
                initialize();
-       cout << "after mothur initialize" << endl;
                fastaString >> name;
-       cout << "after name "  << endl;
-               name = name.substr(1);
-               string sequence;
                
-               //read comments
-               while ((name[0] == '#') && fastaString) { 
-                       while (fastaString)     {       char c = fastaString.get(); if (c == 10 || c == 13){    break;  }       } // get rest of line if there's any crap there
-                       sequence = getCommentString(fastaString);
+               if (name.length() != 0) { 
+               
+                       name = name.substr(1);
+                       string sequence;
+               
+                       //read comments
+                       while ((name[0] == '#') && fastaString) { 
+                               while (!fastaString.eof())      {       char c = fastaString.get(); if (c == 10 || c == 13){    break;  }       } // get rest of line if there's any crap there
+                               sequence = getCommentString(fastaString);
+                               
+                               if (fastaString) {  
+                                       fastaString >> name;  
+                                       name = name.substr(1);  
+                               }else { 
+                                       name = "";
+                                       break;
+                               }
+                       }
                        
-                       if (fastaString) {  
-                               fastaString >> name;  
-                               name = name.substr(1);  
-                       }else { 
-                               name = "";
-                               break;
+                       while (!fastaString.eof())      {       char c = fastaString.get();  if (c == 10 || c == 13){   break;  }       } // get rest of line if there's any crap there
+                       
+                       sequence = getSequenceString(fastaString);              
+                       setAligned(sequence);   
+                       //setUnaligned removes any gap characters for us                                                
+                       setUnaligned(sequence);         
+               }else{ m->mothurOut("Error in reading your fastafile, at position " + toString(fastaString.tellg()) + ". Blank name."); m->mothurOutEndLine(); }
+
+       }
+       catch(exception& e) {
+               m->errorOut(e, "Sequence", "Sequence");
+               exit(1);
+       }                                                               
+}
+//********************************************************************************************************************
+//this function will jump over commented out sequences, but if the last sequence in a file is commented out it makes a blank seq
+Sequence::Sequence(istringstream& fastaString, string JustUnaligned){
+       try {
+               m = MothurOut::getInstance();
+       
+               initialize();
+               fastaString >> name;
+               
+               if (name.length() != 0) { 
+               
+                       name = name.substr(1);
+                       string sequence;
+               
+                       //read comments
+                       while ((name[0] == '#') && fastaString) { 
+                               while (!fastaString.eof())      {       char c = fastaString.get(); if (c == 10 || c == 13){    break;  }       } // get rest of line if there's any crap there
+                               sequence = getCommentString(fastaString);
+                               
+                               if (fastaString) {  
+                                       fastaString >> name;  
+                                       name = name.substr(1);  
+                               }else { 
+                                       name = "";
+                                       break;
+                               }
                        }
-               }
-       cout << "after mothur comment" << endl; 
-               //read real sequence
-               while (fastaString)     {       char c = fastaString.get(); if (c == 10 || c == 13){    break;  }       } // get rest of line if there's any crap there
-       cout << "after mothur name" << endl;    
-               sequence = getSequenceString(fastaString);              
-       cout << "after mothur sequence" << endl;        
-               setAligned(sequence);   
-               //setUnaligned removes any gap characters for us                                                
-               setUnaligned(sequence);         
+                       
+                       while (!fastaString.eof())      {       char c = fastaString.get();  if (c == 10 || c == 13){   break;  }       } // get rest of line if there's any crap there
+                       
+                       sequence = getSequenceString(fastaString);              
+                       
+                       //setUnaligned removes any gap characters for us                                                
+                       setUnaligned(sequence);         
+               }else{ m->mothurOut("Error in reading your fastafile, at position " + toString(fastaString.tellg()) + ". Blank name."); m->mothurOutEndLine(); }
        }
        catch(exception& e) {
                m->errorOut(e, "Sequence", "Sequence");
@@ -77,6 +130,7 @@ Sequence::Sequence(istringstream& fastaString){
        }                                                               
 }
 
+
 //********************************************************************************************************************
 //this function will jump over commented out sequences, but if the last sequence in a file is commented out it makes a blank seq
 Sequence::Sequence(ifstream& fastaFile){
@@ -84,37 +138,85 @@ Sequence::Sequence(ifstream& fastaFile){
                m = MothurOut::getInstance();
                initialize();
                fastaFile >> name;
-               name = name.substr(1);
-               string sequence;
+
+               if (name.length() != 0) { 
                
-               //read comments
-               while ((name[0] == '#') && fastaFile) { 
-                       while (!fastaFile.eof())        {       char c = fastaFile.get(); if (c == 10 || c == 13){      break;  }       } // get rest of line if there's any crap there
-                       sequence = getCommentString(fastaFile);
+                       name = name.substr(1); 
                        
-                       if (fastaFile) {  
-                               fastaFile >> name;  
-                               name = name.substr(1);  
-                       }else { 
-                               name = "";
-                               break;
+                       string sequence;
+               
+                       //read comments
+                       while ((name[0] == '#') && fastaFile) { 
+                               while (!fastaFile.eof())        {       char c = fastaFile.get(); if (c == 10 || c == 13){      break;  }       } // get rest of line if there's any crap there
+                               sequence = getCommentString(fastaFile);
+                               
+                               if (fastaFile) {  
+                                       fastaFile >> name;  
+                                       name = name.substr(1);  
+                               }else { 
+                                       name = "";
+                                       break;
+                               }
                        }
-               }
+                       
+                       //read real sequence
+                       while (!fastaFile.eof())        {       char c = fastaFile.get(); if (c == 10 || c == 13){      break;  }       } // get rest of line if there's any crap there
+                       
+                       sequence = getSequenceString(fastaFile);                
                
-               //read real sequence
-               while (!fastaFile.eof())        {       char c = fastaFile.get(); if (c == 10 || c == 13){      break;  }       } // get rest of line if there's any crap there
+                       setAligned(sequence);   
+                       //setUnaligned removes any gap characters for us                                                
+                       setUnaligned(sequence); 
+               }else{ m->mothurOut("Error in reading your fastafile, at position " + toString(fastaFile.tellg()) + ". Blank name."); m->mothurOutEndLine(); }
                
-               sequence = getSequenceString(fastaFile);                
+       }
+       catch(exception& e) {
+               m->errorOut(e, "Sequence", "Sequence");
+               exit(1);
+       }                                                       
+}
+//********************************************************************************************************************
+//this function will jump over commented out sequences, but if the last sequence in a file is commented out it makes a blank seq
+Sequence::Sequence(ifstream& fastaFile, string JustUnaligned){
+       try {
+               m = MothurOut::getInstance();
+               initialize();
+               fastaFile >> name;
                
-               setAligned(sequence);   
-               //setUnaligned removes any gap characters for us                                                
-               setUnaligned(sequence); 
+               if (name.length() != 0) { 
+                       name = name.substr(1);
+                       string sequence;
+                       
+                       //read comments
+                       while ((name[0] == '#') && fastaFile) { 
+                               while (!fastaFile.eof())        {       char c = fastaFile.get(); if (c == 10 || c == 13){      break;  }       } // get rest of line if there's any crap there
+                               sequence = getCommentString(fastaFile);
+                               
+                               if (fastaFile) {  
+                                       fastaFile >> name;  
+                                       name = name.substr(1);  
+                               }else { 
+                                       name = "";
+                                       break;
+                               }
+                       }
+                       
+                       //read real sequence
+                       while (!fastaFile.eof())        {       char c = fastaFile.get(); if (c == 10 || c == 13){      break;  }       } // get rest of line if there's any crap there
+                       
+                       sequence = getSequenceString(fastaFile);                
+                       
+                       //setUnaligned removes any gap characters for us                                                
+                       setUnaligned(sequence); 
+               }else{ m->mothurOut("Error in reading your fastafile, at position " + toString(fastaFile.tellg()) + ". Blank name."); m->mothurOutEndLine(); }
+
        }
        catch(exception& e) {
                m->errorOut(e, "Sequence", "Sequence");
                exit(1);
        }                                                       
 }
+
 //********************************************************************************************************************
 string Sequence::getSequenceString(ifstream& fastaFile) {
        try {
@@ -169,8 +271,9 @@ string Sequence::getSequenceString(istringstream& fastaFile) {
                char letter;
                string sequence = "";   
                
-               while(fastaFile){
+               while(!fastaFile.eof()){
                        letter= fastaFile.get();
+       
                        if(letter == '>'){
                                fastaFile.putback(letter);
                                break;
@@ -319,7 +422,8 @@ string Sequence::getName(){
 //********************************************************************************************************************
 
 string Sequence::getAligned(){
-       return aligned;
+       if(isAligned == 0)      { return unaligned; }
+       else                            {  return aligned;  }
 }
 
 //********************************************************************************************************************
@@ -376,6 +480,18 @@ int Sequence::getAmbigBases(){
 
 //********************************************************************************************************************
 
+void Sequence::removeAmbigBases(){
+       
+       for(int j=0;j<alignmentLength;j++){
+               if(aligned[j] != 'A' && aligned[j] != 'T' && aligned[j] != 'G' && aligned[j] != 'C'){
+                       aligned[j] = '-';
+               }
+       }
+       setUnaligned(aligned);
+}
+       
+//********************************************************************************************************************
+
 int Sequence::getLongHomoPolymer(){
        if(longHomoPolymer == -1){
                longHomoPolymer = 1;
@@ -448,5 +564,4 @@ void Sequence::reverseComplement(){
        aligned = temp;
        
 }
-
-//********************************************************************************************************************
+/**************************************************************************************************/