File: unicode.g

package info (click to toggle)
antlr 2.7.7%2Bdfsg-14
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid, trixie
  • size: 10,016 kB
  • sloc: java: 54,649; cs: 12,537; makefile: 8,854; cpp: 7,359; pascal: 5,273; sh: 4,333; python: 4,297; lisp: 1,969; xml: 220; lex: 192; ansic: 127
file content (62 lines) | stat: -rw-r--r-- 835 bytes parent folder | download | duplicates (11)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
// This file is part of PyANTLR. See LICENSE.txt for license
// details..........Copyright (C) Wolfgang Haefelinger, 2004.
//
// $Id$

options {
  language = Python;
}


class unicode_l extends Lexer;

options {
	// Allow any char but \uFFFF (16 bit -1)
	charVocabulary='\u0000'..'\uFFFE';
}

{
    done = False

    def uponEOF(self):
        done=True

    def another(self):
        pass	

}

ID	:	ID_START_LETTER ( ID_LETTER )*
	;

WS	:	(' '|'\n') {$skip}
	;

protected
ID_START_LETTER
	:	'$'
	|	'_'
	|	'a'..'z'
	|	'\u0080'..'\ufffe'
	;

protected
ID_LETTER
	:	ID_START_LETTER  
{
            // got a LETTER_ID
            // handle it

            // whatever
}
	|	'0'..'9'
	;


// ANTLR should actually allow this here. Would enable me to write
// something like:
//{
//  if __name__ == '__main__' : 
//    ## test lexer
//
//}