1/*
2 [The "BSD licence"]
3 Copyright (c) 2013 Terence Parr
4 All rights reserved.
5
6 Redistribution and use in source and binary forms, with or without
7 modification, are permitted provided that the following conditions
8 are met:
9 1. Redistributions of source code must retain the above copyright
10    notice, this list of conditions and the following disclaimer.
11 2. Redistributions in binary form must reproduce the above copyright
12    notice, this list of conditions and the following disclaimer in the
13    documentation and/or other materials provided with the distribution.
14 3. The name of the author may not be used to endorse or promote products
15    derived from this software without specific prior written permission.
16
17 THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
18 IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
19 OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
20 IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
21 INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
22 NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
23 DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
24 THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
25 (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
26 THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
27*/
28
29/** XML lexer derived from ANTLR v4 ref guide book example */
30lexer grammar XMLLexer;
31
32// Default "mode": Everything OUTSIDE of a tag
33COMMENT     :   '<!--' .*? '-->' ;
34CDATA       :   '<![CDATA[' .*? ']]>' ;
35/** Scarf all DTD stuff, Entity Declarations like <!ENTITY ...>,
36 *  and Notation Declarations <!NOTATION ...>
37 */
38DTD         :   '<!' .*? '>'            -> skip ;
39EntityRef   :   '&' Name ';' ;
40CharRef     :   '&#' DIGIT+ ';'
41            |   '&#x' HEXDIGIT+ ';'
42            ;
43SEA_WS      :   (' '|'\t'|'\r'? '\n')+ ;
44
45OPEN        :   '<'                     -> pushMode(INSIDE) ;
46XMLDeclOpen :   '<?xml' S               -> pushMode(INSIDE) ;
47SPECIAL_OPEN:   '<?' Name               -> more, pushMode(PROC_INSTR) ;
48
49TEXT        :   ~[<&]+ ;        // match any 16 bit char other than < and &
50
51// ----------------- Everything INSIDE of a tag ---------------------
52mode INSIDE;
53
54CLOSE       :   '>'                     -> popMode ;
55SPECIAL_CLOSE:  '?>'                    -> popMode ; // close <?xml...?>
56SLASH_CLOSE :   '/>'                    -> popMode ;
57SLASH       :   '/' ;
58EQUALS      :   '=' ;
59STRING      :   '"' ~[<"]* '"'
60            |   '\'' ~[<']* '\''
61            ;
62Name        :   NameStartChar NameChar* ;
63S           :   [ \t\r\n]               -> skip ;
64
65fragment
66HEXDIGIT    :   [a-fA-F0-9] ;
67
68fragment
69DIGIT       :   [0-9] ;
70
71fragment
72NameChar    :   NameStartChar
73            |   '-' | '_' | '.' | DIGIT
74            |   '\u00B7'
75            |   '\u0300'..'\u036F'
76            |   '\u203F'..'\u2040'
77            ;
78
79fragment
80NameStartChar
81            :   [:a-zA-Z]
82            |   '\u2070'..'\u218F'
83            |   '\u2C00'..'\u2FEF'
84            |   '\u3001'..'\uD7FF'
85            |   '\uF900'..'\uFDCF'
86            |   '\uFDF0'..'\uFFFD'
87            ;
88
89// ----------------- Handle <? ... ?> ---------------------
90mode PROC_INSTR;
91
92PI          :   '?>'                    -> popMode ; // close <?...?>
93IGNORE      :   .                       -> more ;
94