Untitled

/** A Java 1.5 grammar for ANTLR v3 derived from the spec
 *
 *  This is a very close representation of the spec; the changes
 *  are comestic (remove left recursion) and also fixes (the spec
 *  isn't exactly perfect).  I have run this on the 1.4.2 source
 *  and some nasty looking enums from 1.5, but have not really
 *  tested for 1.5 compatibility.
 *
 *  I built this with: java -Xmx100M org.antlr.Tool java.g 
 *  and got two errors that are ok (for now):
 *  java.g:691:9: Decision can match input such as
 *    "'0'..'9'{'E', 'e'}{'+', '-'}'0'..'9'{'D', 'F', 'd', 'f'}"
 *    using multiple alternatives: 3, 4
 *  As a result, alternative(s) 4 were disabled for that input
 *  java.g:734:35: Decision can match input such as "{'$', 'A'..'Z',
 *    '_', 'a'..'z', '\u00C0'..'\u00D6', '\u00D8'..'\u00F6',
 *    '\u00F8'..'\u1FFF', '\u3040'..'\u318F', '\u3300'..'\u337F',
 *    '\u3400'..'\u3D2D', '\u4E00'..'\u9FFF', '\uF900'..'\uFAFF'}"
 *    using multiple alternatives: 1, 2
 *  As a result, alternative(s) 2 were disabled for that input
 *
 *  You can turn enum on/off as a keyword :)
 *
 *  Version 1.0 -- initial release July 5, 2006 (requires 3.0b2 or higher)
 *
 *  Primary author: Terence Parr, July 2006
 *
 *  Version 1.0.1 -- corrections by Koen Vanderkimpen & Marko van Dooren,
 *      October 25, 2006;
 *      fixed normalInterfaceDeclaration: now uses typeParameters instead
 *          of typeParameter (according to JLS, 3rd edition)
 *      fixed castExpression: no longer allows expression next to type
 *          (according to semantics in JLS, in contrast with syntax in JLS)
 */
grammar XML;


COMMENT
	:	'<!--' (options {greedy=false;} : .)* '-->'
	;
	
 INTERNAL_DTD : '[' (options {greedy=false;} : .)* ']' ;



TAG_START_OPEN : '<' { tagMode = true; } ;

TAG_END_OPEN : '</' { tagMode = true; } ;

TAG_CLOSE : { tagMode }?=> '>' { tagMode = false; } ;

TAG_EMPTY_CLOSE : { tagMode }?=> '/>' { tagMode = false; } ;

ATTR_EQ : { tagMode }?=> '=' ;

ATTR_VALUE : { tagMode }?=>
        ( '"' (~'"')* '"'
        | '\'' (~'\'')* '\''
        )
    ;

PCDATA : { !tagMode }?=> (~'<')+ ;

GENERIC_ID
    : { tagMode }?=>
      ( LETTER | '_' | ':') (NAMECHAR)*
    ;

fragment NAMECHAR
    : LETTER | DIGIT | '.' | '-' | '_' | ':'
    ;

fragment DIGIT
    :    '0'..'9'
    ;

fragment LETTER
    : 'a'..'z'
    | 'A'..'Z'
    ;

WS  :  { tagMode }?=>
       (' '|'\r'|'\t'|'\u000C'|'\n') {channel=99;}
    ;