stdcparser.g

plugin for eclipse

{
import isis.anp.common.CToken;
import isis.anp.common.LineObject;
import isis.anp.common.PreprocessorInfoChannel;

import java.io.InputStream;
import java.io.Reader;
import java.util.Hashtable;

import antlr.ANTLRHashString;
import antlr.ByteBuffer;
import antlr.CharBuffer;
import antlr.CharStreamException;
import antlr.CharStreamIOException;
import antlr.InputBuffer;
import antlr.LexerSharedInputState;
import antlr.NoViableAltForCharException;
import antlr.RecognitionException;
import antlr.Token;
import antlr.TokenStream;
import antlr.TokenStreamException;
import antlr.TokenStreamIOException;
import antlr.TokenStreamRecognitionException;
import antlr.collections.impl.BitSet;
}

class StdCLexer extends Lexer;

options
        {
        k = 3;
        exportVocab = StdC;
        testLiterals = false;
        }

{
  LineObject lineObject = new LineObject();
  String originalSource = "";
  PreprocessorInfoChannel preprocessorInfoChannel = new PreprocessorInfoChannel();
  int tokenNumber = 0;
  boolean countingTokens = true;
  int deferredLineCount = 0;

  public void setCountingTokens(boolean ct) 
  {
    countingTokens = ct;
    if ( countingTokens ) {
      tokenNumber = 0;
    }
    else {
      tokenNumber = 1;
    }
  }

  public void setOriginalSource(String src) 
  {
    originalSource = src;
    lineObject.setSource(src);
  }
  public void setSource(String src) 
  {
    lineObject.setSource(src);
  }
  
  public PreprocessorInfoChannel getPreprocessorInfoChannel() 
  {
    return preprocessorInfoChannel;
  }

  public void setPreprocessingDirective(String pre)
  {
    preprocessorInfoChannel.addLineForTokenNumber( pre, new Integer(tokenNumber) );
  }
  
  protected Token makeToken(int t)
  {
    if ( t != Token.SKIP && countingTokens) {
        tokenNumber++;
    }
    CToken tok = (CToken) super.makeToken(t);
    tok.setLine(lineObject.line);
    tok.setSource(lineObject.source);
    tok.setTokenNumber(tokenNumber);

    lineObject.line += deferredLineCount;
    deferredLineCount = 0;
    return tok;
  }

    public void deferredNewline() { 
        deferredLineCount++;
    }

    public void newline() { 
    	super.newline();
        lineObject.newline();
    }

}

protected
Vocabulary
        :       '\3'..'\377'
        ;


/* Operators: */

ASSIGN          : '=' ;
COLON           : ':' ;
COMMA           : ',' ;
QUESTION        : '?' ;
SEMI            : ';' ;
PTR             : "->" ;


// DOT & VARARGS are commented out since they are generated as part of
// the Number rule below due to some bizarre lexical ambiguity shme.

// DOT  :       '.' ;
protected
DOT:;

// VARARGS      : "..." ;
protected
VARARGS:;


LPAREN          : '(' ;
RPAREN          : ')' ;
LBRACKET        : '[' ;
RBRACKET        : ']' ;
LCURLY          : '{' ;
RCURLY          : '}' ;

EQUAL           : "==" ;
NOT_EQUAL       : "!=" ;
LTE             : "<=" ;
LT              : "<" ;
GTE             : ">=" ;
GT              : ">" ;

DIV             : '/' ;
DIV_ASSIGN      : "/=" ;
PLUS            : '+' ;
PLUS_ASSIGN     : "+=" ;
INC             : "++" ;
MINUS           : '-' ;
MINUS_ASSIGN    : "-=" ;
DEC             : "--" ;
STAR            : '*' ;
STAR_ASSIGN     : "*=" ;
MOD             : '%' ;
MOD_ASSIGN      : "%=" ;
RSHIFT          : ">>" ;
RSHIFT_ASSIGN   : ">>=" ;
LSHIFT          : "<<" ;
LSHIFT_ASSIGN   : "<<=" ;

LAND            : "&&" ;
LNOT            : '!' ;
LOR             : "||" ;

BAND            : '&' ;
BAND_ASSIGN     : "&=" ;
BNOT            : '~' ;
BOR             : '|' ;
BOR_ASSIGN      : "|=" ;
BXOR            : '^' ;
BXOR_ASSIGN     : "^=" ;


Whitespace
        :       ( ( '\003'..'\010' | '\t' | '\013' | '\f' | '\016'.. '\037' | '\177'..'\377' | ' ' )
                | "\r\n"                { newline(); }
                | ( '\n' | '\r' )       { newline(); }
                )                       { _ttype = Token.SKIP;  }
        ;


Comment
        :       "/*"
                ( { LA(2) != '/' }? '*'
                | "\r\n"                { deferredNewline(); }
                | ( '\r' | '\n' )       { deferredNewline();    }
                | ~( '*'| '\r' | '\n' )
                )*
                "*/"                    { _ttype = Token.SKIP;  
                                        }
        ;


CPPComment
        :
                "//" ( ~('\n') )* 
                        {
                        _ttype = Token.SKIP;
                        }
        ;

PREPROC_DIRECTIVE
options {
  paraphrase = "a line directive";
}

        :
        '#'
        ( ( "line" || (( ' ' | '\t' | '\014')+ '0'..'9')) => LineDirective      
            | (~'\n')*                                  { setPreprocessingDirective(getText()); }
        )
                {  
                    _ttype = Token.SKIP;
                }
        ;

protected  Space:
        ( ' ' | '\t' | '\014')
        ;

protected LineDirective
{
        boolean oldCountingTokens = countingTokens;
        countingTokens = false;
}
:
                {
                        lineObject = new LineObject();
                        deferredLineCount = 0;
                }
        ("line")?  //this would be for if the directive started "#line", but not there for GNU directives
        (Space)+
        n:Number { lineObject.setLine(Integer.parseInt(n.getText())); } 
        (Space)+
        (       fn:StringLiteral {  try { 
                                          lineObject.setSource(fn.getText().substring(1,fn.getText().length()-1)); 
                                    } 
                                    catch (StringIndexOutOfBoundsException e) { /*not possible*/ } 
                                 }
                | fi:ID { lineObject.setSource(fi.getText()); }
        )?
        (Space)*
        ("1"            { lineObject.setEnteringFile(true); } )?
        (Space)*
        ("2"            { lineObject.setReturningToFile(true); } )?
        (Space)*
        ("3"            { lineObject.setSystemHeader(true); } )?
        (Space)*
        ("4"            { lineObject.setTreatAsC(true); } )?
        (~('\r' | '\n'))*
        ("\r\n" | "\r" | "\n")
                {
                        preprocessorInfoChannel.addLineForTokenNumber(new LineObject(lineObject), new Integer(tokenNumber));
                        countingTokens = oldCountingTokens;
                }
        ;



/* Literals: */

/*
 * Note that we do NOT handle tri-graphs nor multi-byte sequences.
 */


/*
 * Note that we can't have empty character constants (even though we
 * can have empty strings :-).
 */
CharLiteral
        :       '\'' ( Escape | ~( '\'' ) ) '\''
        ;


/*
 * Can't have raw imbedded newlines in string constants.  Strict reading of
 * the standard gives odd dichotomy between newlines & carriage returns.
 * Go figure.
 */
StringLiteral
        :       '"'
                ( Escape
                | ( 
                    '\r'        { deferredNewline(); }
                  | '\n'        {
                                deferredNewline();
                                _ttype = BadStringLiteral;
                                }
                  | '\\' '\n'   {
                                deferredNewline();
                                }
                  )
                | ~( '"' | '\r' | '\n' | '\\' )
                )*
                '"'
        ;


protected BadStringLiteral
        :       // Imaginary token.
        ;


/*
 * Handle the various escape sequences.
 *
 * Note carefully that these numeric escape *sequences* are *not* of the
 * same form as the C language numeric *constants*.
 *
 * There is no such thing as a binary numeric escape sequence.
 *
 * Octal escape sequences are either 1, 2, or 3 octal digits exactly.
 *
 * There is no such thing as a decimal escape sequence.
 *
 * Hexadecimal escape sequences are begun with a leading \x and continue
 * until a non-hexadecimal character is found.
 *
 * No real handling of tri-graph sequences, yet.
 */

protected
Escape  
        :       '\\'
                ( options{warnWhenFollowAmbig=false;}:
                  'a'
                | 'b'
                | 'f'
                | 'n'
                | 'r'
                | 't'
                | 'v'
                | '"'
                | '\''
                | '\\'
                | '?'
                | ('0'..'3') ( options{warnWhenFollowAmbig=false;}: Digit ( options{warnWhenFollowAmbig=false;}: Digit )? )?
                | ('4'..'7') ( options{warnWhenFollowAmbig=false;}: Digit )?
                | 'x' ( options{warnWhenFollowAmbig=false;}: Digit | 'a'..'f' | 'A'..'F' )+
                )
        ;


/* Numeric Constants: */

protected
Digit
        :       '0'..'9'
        ;

protected
LongSuffix
        :       'l'
        |       'L'
        ;

protected
UnsignedSuffix
        :       'u'
        |       'U'
        ;

protected
FloatSuffix
        :       'f'
        |       'F'
        ;

protected
Exponent
        :       ( 'e' | 'E' ) ( '+' | '-' )? ( Digit )+
        ;


protected
DoubleDoubleConst:;

protected
FloatDoubleConst:;

protected
LongDoubleConst:;

protected
IntOctalConst:;

protected
LongOctalConst:;

protected
UnsignedOctalConst:;

protected
IntIntConst:;

protected
LongIntConst:;

protected
UnsignedIntConst:;

protected
IntHexConst:;

protected
LongHexConst:;

protected
UnsignedHexConst:;




Number
        :       ( ( Digit )+ ( '.' | 'e' | 'E' ) )=> ( Digit )+
                ( '.' ( Digit )* ( Exponent )?
                | Exponent
                )                       { _ttype = DoubleDoubleConst;   }
                ( FloatSuffix           { _ttype = FloatDoubleConst;    }
                | LongSuffix            { _ttype = LongDoubleConst;     }
                )?

        |       ( "..." )=> "..."       { _ttype = VARARGS;     }

        |       '.'                     { _ttype = DOT; }
                ( ( Digit )+ ( Exponent )?
                                        { _ttype = DoubleDoubleConst;   }
                  ( FloatSuffix         { _ttype = FloatDoubleConst;    }
                  | LongSuffix          { _ttype = LongDoubleConst;     }
                  )?
                )?

        |       '0' ( '0'..'7' )*       { _ttype = IntOctalConst;       }
                ( LongSuffix            { _ttype = LongOctalConst;      }
                | UnsignedSuffix        { _ttype = UnsignedOctalConst;  }
                )?

        |       '1'..'9' ( Digit )*     { _ttype = IntIntConst;         }
                ( LongSuffix            { _ttype = LongIntConst;        }
                | UnsignedSuffix        { _ttype = UnsignedIntConst;    }
                )?

        |       '0' ( 'x' | 'X' ) ( 'a'..'f' | 'A'..'F' | Digit )+
                                        { _ttype = IntHexConst;         }
                ( LongSuffix            { _ttype = LongHexConst;        }
                | UnsignedSuffix        { _ttype = UnsignedHexConst;    }
                )?
        ;


ID
        options 
                {
                testLiterals = true; 
                }
        :       ( 'a'..'z' | 'A'..'Z' | '_' )
                ( 'a'..'z' | 'A'..'Z' | '_' | '0'..'9' )*
        ;