summaryrefslogtreecommitdiffstats
path: root/Lib/sre_constants.py
blob: af883094d40398cd68ac8746fd311dcffc22484f (plain)
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
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
#
# Secret Labs' Regular Expression Engine
# $Id$
#
# various symbols used by the regular expression engine.
# run this script to update the _sre include files!
#
# Copyright (c) 1998-2000 by Secret Labs AB.  All rights reserved.
#
# This code can only be used for 1.6 alpha testing.  All other use
# require explicit permission from Secret Labs AB.
#
# Portions of this engine have been developed in cooperation with
# CNRI.  Hewlett-Packard provided funding for 1.6 integration and
# other compatibility work.
#

# operators

FAILURE = "failure"
SUCCESS = "success"

ANY = "any"
ASSERT = "assert"
AT = "at"
BRANCH = "branch"
CALL = "call"
CATEGORY = "category"
GROUP = "group"
GROUP_IGNORE = "group_ignore"
IN = "in"
IN_IGNORE = "in_ignore"
JUMP = "jump"
LITERAL = "literal"
LITERAL_IGNORE = "literal_ignore"
MARK = "mark"
MAX_REPEAT = "max_repeat"
MAX_REPEAT_ONE = "max_repeat_one"
MAX_UNTIL = "max_until"
MIN_REPEAT = "min_repeat"
MIN_UNTIL = "min_until"
NEGATE = "negate"
NOT_LITERAL = "not_literal"
NOT_LITERAL_IGNORE = "not_literal_ignore"
RANGE = "range"
REPEAT = "repeat"
SUBPATTERN = "subpattern"

# positions
AT_BEGINNING = "at_beginning"
AT_BOUNDARY = "at_boundary"
AT_NON_BOUNDARY = "at_non_boundary"
AT_END = "at_end"

# categories

CATEGORY_DIGIT = "category_digit"
CATEGORY_NOT_DIGIT = "category_not_digit"
CATEGORY_SPACE = "category_space"
CATEGORY_NOT_SPACE = "category_not_space"
CATEGORY_WORD = "category_word"
CATEGORY_NOT_WORD = "category_not_word"

CODES = [

    # failure=0 success=1 (just because it looks better that way :-)
    FAILURE, SUCCESS,

    ANY,
    ASSERT,
    AT,
    BRANCH,
    CALL,
    CATEGORY,
    GROUP, GROUP_IGNORE,
    IN, IN_IGNORE,
    JUMP,
    LITERAL, LITERAL_IGNORE,
    MARK,
    MAX_REPEAT, MAX_UNTIL,
    MAX_REPEAT_ONE,
    MIN_REPEAT, MIN_UNTIL,
    NOT_LITERAL, NOT_LITERAL_IGNORE,
    NEGATE,
    RANGE,
    REPEAT

]

# convert to dictionary
c = {}
i = 0
for code in CODES:
    c[code] = i
    i = i + 1
CODES = c

# replacement operations for "ignore case" mode
MAP_IGNORE = {
    GROUP: GROUP_IGNORE,
    IN: IN_IGNORE,
    LITERAL: LITERAL_IGNORE,
    NOT_LITERAL: NOT_LITERAL_IGNORE
}

POSITIONS = {
    AT_BEGINNING: ord("a"),
    AT_BOUNDARY: ord("b"),
    AT_NON_BOUNDARY: ord("B"),
    AT_END: ord("z"),
}

CATEGORIES = {
    CATEGORY_DIGIT: ord("d"),
    CATEGORY_NOT_DIGIT: ord("D"),
    CATEGORY_SPACE: ord("s"),
    CATEGORY_NOT_SPACE: ord("S"),
    CATEGORY_WORD: ord("w"),
    CATEGORY_NOT_WORD: ord("W"),
}

if __name__ == "__main__":
    import string
    items = CODES.items()
    items.sort(lambda a, b: cmp(a[1], b[1]))
    f = open("sre_constants.h", "w")
    f.write("/* generated by sre_constants.py */\n")
    for k, v in items:
	f.write("#define SRE_OP_" + string.upper(k) + " " + str(v) + "\n")
    f.close()
    print "done"