sre_constants.py revision 72b82ba16dea929b3fa9db5208b2353e8449c2d5 
1#
2# Secret Labs' Regular Expression Engine
3#
4# various symbols used by the regular expression engine.
5# run this script to update the _sre include files!
6#
7# Copyright (c) 1998-2000 by Secret Labs AB.  All rights reserved.
8#
9# Portions of this engine have been developed in cooperation with
10# CNRI.  Hewlett-Packard provided funding for 2.0 integration and
11# other compatibility work.
12#
13
14# should this really be here?
15
16class error(Exception):
17    pass
18
19# operators
20
21FAILURE = "failure"
22SUCCESS = "success"
23
24ANY = "any"
25ASSERT = "assert"
26ASSERT_NOT = "assert_not"
27AT = "at"
28BRANCH = "branch"
29CALL = "call"
30CATEGORY = "category"
31CHARSET = "charset"
32GROUPREF = "groupref"
33GROUPREF_IGNORE = "groupref_ignore"
34IN = "in"
35IN_IGNORE = "in_ignore"
36INDEX = "index"
37INFO = "info"
38JUMP = "jump"
39LITERAL = "literal"
40LITERAL_IGNORE = "literal_ignore"
41MARK = "mark"
42MAX_REPEAT = "max_repeat"
43MAX_REPEAT_ONE = "max_repeat_one"
44MIN_REPEAT = "min_repeat"
45NEGATE = "negate"
46NOT_LITERAL = "not_literal"
47NOT_LITERAL_IGNORE = "not_literal_ignore"
48RANGE = "range"
49REPEAT = "repeat"
50REPEAT_ONE = "repeat_one"
51SUBPATTERN = "subpattern"
52
53# positions
54AT_BEGINNING = "at_beginning"
55AT_BEGINNING_LINE = "at_beginning_line"
56AT_BOUNDARY = "at_boundary"
57AT_NON_BOUNDARY = "at_non_boundary"
58AT_END = "at_end"
59AT_END_LINE = "at_end_line"
60
61# categories
62CATEGORY_DIGIT = "category_digit"
63CATEGORY_NOT_DIGIT = "category_not_digit"
64CATEGORY_SPACE = "category_space"
65CATEGORY_NOT_SPACE = "category_not_space"
66CATEGORY_WORD = "category_word"
67CATEGORY_NOT_WORD = "category_not_word"
68CATEGORY_LINEBREAK = "category_linebreak"
69CATEGORY_NOT_LINEBREAK = "category_not_linebreak"
70CATEGORY_LOC_WORD = "category_loc_word"
71CATEGORY_LOC_NOT_WORD = "category_loc_not_word"
72CATEGORY_UNI_DIGIT = "category_uni_digit"
73CATEGORY_UNI_NOT_DIGIT = "category_uni_not_digit"
74CATEGORY_UNI_SPACE = "category_uni_space"
75CATEGORY_UNI_NOT_SPACE = "category_uni_not_space"
76CATEGORY_UNI_WORD = "category_uni_word"
77CATEGORY_UNI_NOT_WORD = "category_uni_not_word"
78CATEGORY_UNI_LINEBREAK = "category_uni_linebreak"
79CATEGORY_UNI_NOT_LINEBREAK = "category_uni_not_linebreak"
80
81OPCODES = [
82
83    # failure=0 success=1 (just because it looks better that way :-)
84    FAILURE, SUCCESS,
85
86    ANY,
87    ASSERT, ASSERT_NOT,
88    AT,
89    BRANCH,
90    CALL,
91    CATEGORY,
92    CHARSET,
93    GROUPREF, GROUPREF_IGNORE,
94    INDEX,
95    IN, IN_IGNORE,
96    INFO,
97    JUMP,
98    LITERAL, LITERAL_IGNORE,
99    MARK,
100    MAX_REPEAT,
101    MAX_REPEAT_ONE,
102    MIN_REPEAT,
103    NOT_LITERAL, NOT_LITERAL_IGNORE,
104    NEGATE,
105    RANGE,
106    REPEAT
107
108]
109
110ATCODES = [
111    AT_BEGINNING, AT_BEGINNING_LINE, AT_BOUNDARY,
112    AT_NON_BOUNDARY, AT_END, AT_END_LINE
113]
114
115CHCODES = [
116    CATEGORY_DIGIT, CATEGORY_NOT_DIGIT, CATEGORY_SPACE,
117    CATEGORY_NOT_SPACE, CATEGORY_WORD, CATEGORY_NOT_WORD,
118    CATEGORY_LINEBREAK, CATEGORY_NOT_LINEBREAK, CATEGORY_LOC_WORD,
119    CATEGORY_LOC_NOT_WORD, CATEGORY_UNI_DIGIT, CATEGORY_UNI_NOT_DIGIT,
120    CATEGORY_UNI_SPACE, CATEGORY_UNI_NOT_SPACE, CATEGORY_UNI_WORD,
121    CATEGORY_UNI_NOT_WORD, CATEGORY_UNI_LINEBREAK,
122    CATEGORY_UNI_NOT_LINEBREAK
123]
124
125def makedict(list):
126    d = {}
127    i = 0
128    for item in list:
129        d[item] = i
130        i = i + 1
131    return d
132
133OPCODES = makedict(OPCODES)
134ATCODES = makedict(ATCODES)
135CHCODES = makedict(CHCODES)
136
137# replacement operations for "ignore case" mode
138OP_IGNORE = {
139    GROUPREF: GROUPREF_IGNORE,
140    IN: IN_IGNORE,
141    LITERAL: LITERAL_IGNORE,
142    NOT_LITERAL: NOT_LITERAL_IGNORE
143}
144
145AT_MULTILINE = {
146    AT_BEGINNING: AT_BEGINNING_LINE,
147    AT_END: AT_END_LINE
148}
149
150CH_LOCALE = {
151    CATEGORY_DIGIT: CATEGORY_DIGIT,
152    CATEGORY_NOT_DIGIT: CATEGORY_NOT_DIGIT,
153    CATEGORY_SPACE: CATEGORY_SPACE,
154    CATEGORY_NOT_SPACE: CATEGORY_NOT_SPACE,
155    CATEGORY_WORD: CATEGORY_LOC_WORD,
156    CATEGORY_NOT_WORD: CATEGORY_LOC_NOT_WORD,
157    CATEGORY_LINEBREAK: CATEGORY_LINEBREAK,
158    CATEGORY_NOT_LINEBREAK: CATEGORY_NOT_LINEBREAK
159}
160
161CH_UNICODE = {
162    CATEGORY_DIGIT: CATEGORY_UNI_DIGIT,
163    CATEGORY_NOT_DIGIT: CATEGORY_UNI_NOT_DIGIT,
164    CATEGORY_SPACE: CATEGORY_UNI_SPACE,
165    CATEGORY_NOT_SPACE: CATEGORY_UNI_NOT_SPACE,
166    CATEGORY_WORD: CATEGORY_UNI_WORD,
167    CATEGORY_NOT_WORD: CATEGORY_UNI_NOT_WORD,
168    CATEGORY_LINEBREAK: CATEGORY_UNI_LINEBREAK,
169    CATEGORY_NOT_LINEBREAK: CATEGORY_UNI_NOT_LINEBREAK
170}
171
172# flags
173SRE_FLAG_TEMPLATE = 1 # template mode (disable backtracking)
174SRE_FLAG_IGNORECASE = 2 # case insensitive
175SRE_FLAG_LOCALE = 4 # honour system locale
176SRE_FLAG_MULTILINE = 8 # treat target as multiline string
177SRE_FLAG_DOTALL = 16 # treat target as a single string
178SRE_FLAG_UNICODE = 32 # use unicode locale
179SRE_FLAG_VERBOSE = 64 # ignore whitespace and comments
180
181# flags for INFO primitive
182SRE_INFO_PREFIX = 1 # has prefix
183SRE_INFO_LITERAL = 2 # entire pattern is literal (given by prefix)
184SRE_INFO_CHARSET = 4 # pattern starts with character from given set
185
186if __name__ == "__main__":
187    import string
188    def dump(f, d, prefix):
189        items = d.items()
190        items.sort(lambda a, b: cmp(a[1], b[1]))
191        for k, v in items:
192            f.write("#define %s_%s %s\n" % (prefix, string.upper(k), v))
193    f = open("sre_constants.h", "w")
194    f.write("""\
195/*
196 * Secret Labs' Regular Expression Engine
197 *
198 * regular expression matching engine
199 *
200 * NOTE: This file is generated by sre_constants.py.  If you need
201 * to change anything in here, edit sre_constants.py and run it.
202 *
203 * Copyright (c) 1997-2000 by Secret Labs AB.  All rights reserved.
204 *
205 * See the _sre.c file for information on usage and redistribution.
206 */
207
208""")
209
210    dump(f, OPCODES, "SRE_OP")
211    dump(f, ATCODES, "SRE")
212    dump(f, CHCODES, "SRE")
213
214    f.write("#define SRE_FLAG_TEMPLATE %d\n" % SRE_FLAG_TEMPLATE)
215    f.write("#define SRE_FLAG_IGNORECASE %d\n" % SRE_FLAG_IGNORECASE)
216    f.write("#define SRE_FLAG_LOCALE %d\n" % SRE_FLAG_LOCALE)
217    f.write("#define SRE_FLAG_MULTILINE %d\n" % SRE_FLAG_MULTILINE)
218    f.write("#define SRE_FLAG_DOTALL %d\n" % SRE_FLAG_DOTALL)
219    f.write("#define SRE_FLAG_UNICODE %d\n" % SRE_FLAG_UNICODE)
220    f.write("#define SRE_FLAG_VERBOSE %d\n" % SRE_FLAG_VERBOSE)
221
222    f.write("#define SRE_INFO_PREFIX %d\n" % SRE_INFO_PREFIX)
223    f.write("#define SRE_INFO_LITERAL %d\n" % SRE_INFO_LITERAL)
224    f.write("#define SRE_INFO_CHARSET %d\n" % SRE_INFO_CHARSET)
225
226    f.close()
227    print "done"
228