java.g

Java写的词法/语法分析器。可生成JAVA语言或者是C++的词法和语法分析器。并可产生语法分析树和对该树进行遍历

	// Attach a label to the front of a statement
	|	IDENT c:COLON^ {#c->setType(LABELED_STAT);} statement

	// If-else statement
	|	"if"^ LPAREN! expression RPAREN! statement
		(
			// CONFLICT: the old "dangling-else" problem...
			//           ANTLR generates proper code matching
			//			 as soon as possible.  Hush warning.
			options {
				warnWhenFollowAmbig = false;
			}
		:
			"else"! statement
		)?

	// For statement
	|	"for"^
			LPAREN!
				forInit SEMI!   // initializer
				forCond	SEMI!   // condition test
				forIter         // updater
			RPAREN!
			statement                     // statement to loop over

	// While statement
	|	"while"^ LPAREN! expression RPAREN! statement

	// do-while statement
	|	"do"^ statement "while"! LPAREN! expression RPAREN! SEMI!

	// get out of a loop (or switch)
	|	"break"^ (IDENT)? SEMI!

	// do next iteration of a loop
	|	"continue"^ (IDENT)? SEMI!

	// Return an expression
	|	"return"^ (expression)? SEMI!

	// switch/case statement
	|	"switch"^ LPAREN! expression RPAREN! LCURLY!
			( casesGroup )*
		RCURLY!

	// exception try-catch block
	|	tryBlock

	// throw an exception
	|	"throw"^ expression SEMI!

	// synchronize a statement
	|	"synchronized"^ LPAREN! expression RPAREN! compoundStatement

	// empty statement
	|	s:SEMI {#s->setType(EMPTY_STAT);}
	;


casesGroup
	:	(	// CONFLICT: to which case group do the statements bind?
			//           ANTLR generates proper code: it groups the
			//           many "case"/"default" labels together then
			//           follows them with the statements
			options {
				warnWhenFollowAmbig = false;
			}
			:
			aCase
		)+
		caseSList
		{#casesGroup = #([CASE_GROUP, "CASE_GROUP"], #casesGroup);}
	;

aCase
	:	("case"^ expression | "default") COLON!
	;

caseSList
	:	(statement)*
		{#caseSList = #(#[SLIST,"SLIST"],#caseSList);}
	;

// The initializer for a for loop
forInit
		// if it looks like a declaration, it is
	:	(	(declaration)=> declaration
		// otherwise it could be an expression list...
		|	expressionList
		)?
		{#forInit = #(#[FOR_INIT,"FOR_INIT"],#forInit);}
	;

forCond
	:	(expression)?
		{#forCond = #(#[FOR_CONDITION,"FOR_CONDITION"],#forCond);}
	;

forIter
	:	(expressionList)?
		{#forIter = #(#[FOR_ITERATOR,"FOR_ITERATOR"],#forIter);}
	;

// an exception handler try/catch block
tryBlock
	:	"try"^ compoundStatement
		(handler)*
		( "finally"^ compoundStatement )?
	;


// an exception handler
handler
	:	"catch"^ LPAREN! parameterDeclaration RPAREN! compoundStatement
	;


// expressions
// Note that most of these expressions follow the pattern
//   thisLevelExpression :
//       nextHigherPrecedenceExpression
//           (OPERATOR nextHigherPrecedenceExpression)*
// which is a standard recursive definition for a parsing an expression.
// The operators in java have the following precedences:
//    lowest  (13)  = *= /= %= += -= <<= >>= >>>= &= ^= |=
//            (12)  ?:
//            (11)  ||
//            (10)  &&
//            ( 9)  |
//            ( 8)  ^
//            ( 7)  &
//            ( 6)  == !=
//            ( 5)  < <= > >=
//            ( 4)  << >>
//            ( 3)  +(binary) -(binary)
//            ( 2)  * / %
//            ( 1)  ++ -- +(unary) -(unary)  ~  !  (type)
//                  []   () (method call)  . (dot -- identifier qualification)
//                  new   ()  (explicit parenthesis)
//
// the last two are not usually on a precedence chart; I put them in
// to point out that new has a higher precedence than '.', so you
// can validy use
//     new Frame().show()
// 
// Note that the above precedence levels map to the rules below...
// Once you have a precedence chart, writing the appropriate rules as below
//   is usually very straightfoward



// the mother of all expressions
expression
	:	assignmentExpression
		{#expression = #(#[EXPR,"EXPR"],#expression);}
	;


// This is a list of expressions.
expressionList
	:	expression (COMMA! expression)*
		{#expressionList = #(#[ELIST,"ELIST"], expressionList);}
	;


// assignment expression (level 13)
assignmentExpression
	:	conditionalExpression
		(	(	ASSIGN^
            |   PLUS_ASSIGN^
            |   MINUS_ASSIGN^
            |   STAR_ASSIGN^
            |   DIV_ASSIGN^
            |   MOD_ASSIGN^
            |   SR_ASSIGN^
            |   BSR_ASSIGN^
            |   SL_ASSIGN^
            |   BAND_ASSIGN^
            |   BXOR_ASSIGN^
            |   BOR_ASSIGN^
            )
			assignmentExpression
		)?
	;


// conditional test (level 12)
conditionalExpression
	:	logicalOrExpression
		( QUESTION^ conditionalExpression COLON! conditionalExpression )?
	;


// logical or (||)  (level 11)
logicalOrExpression
	:	logicalAndExpression (LOR^ logicalAndExpression)*
	;


// logical and (&&)  (level 10)
logicalAndExpression
	:	inclusiveOrExpression (LAND^ inclusiveOrExpression)*
	;


// bitwise or non-short-circuiting or (|)  (level 9)
inclusiveOrExpression
	:	exclusiveOrExpression (BOR^ exclusiveOrExpression)*
	;


// exclusive or (^)  (level 8)
exclusiveOrExpression
	:	andExpression (BXOR^ andExpression)*
	;


// bitwise or non-short-circuiting and (&)  (level 7)
andExpression
	:	equalityExpression (BAND^ equalityExpression)*
	;


// equality/inequality (==/!=) (level 6)
equalityExpression
	:	relationalExpression ((NOT_EQUAL^ | EQUAL^) relationalExpression)*
	;


// boolean relational expressions (level 5)
relationalExpression
	:	shiftExpression
		(	(	LT_^
			|	GT^
			|	LE^
			|	GE^
			)
			shiftExpression
		)*
	;


// bit shift expressions (level 4)
shiftExpression
	:	additiveExpression ((SL^ | SR^ | BSR^) additiveExpression)*
	;


// binary addition/subtraction (level 3)
additiveExpression
	:	multiplicativeExpression ((PLUS^ | MINUS^) multiplicativeExpression)*
	;


// multiplication/division/modulo (level 2)
multiplicativeExpression
	:	castExpression ((STAR^ | DIV^ | MOD^ ) castExpression)*
	;

// cast/unary (level 1)
castExpression
	// if it _looks_ like a cast, it _is_ a cast
	:	( LPAREN typeSpec[true] RPAREN castExpression )=>
			lp:LPAREN^ {#lp->setType(TYPECAST);} typeSpec[true] RPAREN!
			c:castExpression

	// otherwise it's a unary expression
	|	INC^ castExpression
	|	DEC^ castExpression
	|	MINUS^ {#MINUS->setType(UNARY_MINUS);} castExpression
	|	PLUS^  {#PLUS->setType(UNARY_PLUS);} castExpression
	|	BNOT^ castExpression
	|	LNOT^ castExpression
	|	postfixExpression ( "instanceof"^ typeSpec[true] )?
		// instanceof should not allow just primitives (x instanceof int)
		// need a semantic check if we're compiling...
	;

// qualified names, array expressions, method invocation, post inc/dec
postfixExpression
	:	primaryExpression // start with a primary

		
		(	// qualified id (id.id.id.id...) -- build the name
			DOT^ ( IDENT
				| "this"
				| "class"
				| newExpression
				| "super" LPAREN ( expressionList )? RPAREN
				)
			// the above line needs a semantic check to make sure "class"
			//   is the _last_ qualifier.

			// an array indexing operation
		|	lb:LBRACK^ {#lb->setType(INDEX_OP);} expression RBRACK!

			// method invocation
			// The next line is not strictly proper; it allows x(3)(4) or
			//   x[2](4) which are not valid in Java.  If this grammar were used
			//   to validate a Java program a semantic check would be needed, or
			//   this rule would get really ugly...
		|	lp:LPAREN^ {#lp->setType(METHOD_CALL);}
				argList
			RPAREN!
		)*

			// possibly add on a post-increment or post-decrement
		(	in:INC^ {#in->setType(POST_INC);}
	 	|	de:DEC^ {#de->setType(POST_DEC);}
		|	// nothing
		)
	;

// the basic element of an expression
primaryExpression
	:	IDENT
	|	builtInType 
		( lb:LBRACK^ {#lb->setType(ARRAY_DECLARATOR);} RBRACK! )*
		DOT^ "class"
	|	newExpression
	|	constant
	|	"super"
	|	"true"
	|	"false"
	|	"this"
	|	"null"
	|	LPAREN! assignmentExpression RPAREN!
	;


/** object instantiation.
 *  Trees are built as illustrated by the following input/tree pairs:
 *  
 *  new T()
 *  
 *  new
 *   |
 *   T --  ELIST
 *           |
 *          arg1 -- arg2 -- .. -- argn
 *  
 *  new int[]
 *
 *  new
 *   |
 *  int -- ARRAY_DECLARATOR
 *  
 *  new int[] {1,2}
 *
 *  new
 *   |
 *  int -- ARRAY_DECLARATOR -- ARRAY_INIT
 *                                  |
 *                                EXPR -- EXPR
 *                                  |      |
 *                                  1      2
 *  
 *  new int[3]
 *  new
 *   |
 *  int -- ARRAY_DECLARATOR
 *                |
 *              EXPR
 *                |
 *                3
 *  
 *  new int[1][2]
 *  
 *  new
 *   |
 *  int -- ARRAY_DECLARATOR
 *               |
 *         ARRAY_DECLARATOR -- EXPR
 *               |              |
 *             EXPR             1
 *               |
 *               2
 *  
 */
newExpression
	:	"new"^ type
		(	LPAREN! argList RPAREN! (classBlock)?

			//java 1.1
			// Note: This will allow bad constructs like
			//    new int[4][][3] {exp,exp}.
			//    There needs to be a semantic check here...
			// to make sure:
			//   a) [ expr ] and [ ] are not mixed
			//   b) [ expr ] and an init are not used together

		|	newArrayDeclarator (arrayInitializer)?
		)
	;

argList
	:	(	expressionList
		|	/*nothing*/
			{#argList = #[ELIST,"ELIST"];}
		)
	;

newArrayDeclarator
	:	(
			// CONFLICT:
			// newExpression is a primaryExpression which can be
			// followed by an array index reference.  This is ok,
			// as the generated code will stay in this loop as
			// long as it sees an LBRACK (proper behavior)
			options {
				warnWhenFollowAmbig = false;
			}
		:
			lb:LBRACK^ {#lb->setType(ARRAY_DECLARATOR);}
				(expression)?
			RBRACK!
		)+
	;

constant
	:	NUM_INT
	|	CHAR_LITERAL
	|	STRING_LITERAL
	|	NUM_FLOAT
	;