sre_constants.py revision 5c24d0e504f9271ee095f706b493566ec0162879 
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) 1998-2001 by Secret Labs AB.  All rights reserved.
8#
9# See the sre.py file for information on usage and redistribution.
10#
11
12"""Internal support module for sre"""
13
14# update when constants are added or removed
15
16MAGIC = 20031017
17
18from _sre import MAXREPEAT
19
20# SRE standard exception (access as sre.error)
21# should this really be here?
22
23class error(Exception):
24    pass
25
26# operators
27
28FAILURE = "failure"
29SUCCESS = "success"
30
31ANY = "any"
32ANY_ALL = "any_all"
33ASSERT = "assert"
34ASSERT_NOT = "assert_not"
35AT = "at"
36BIGCHARSET = "bigcharset"
37BRANCH = "branch"
38CALL = "call"
39CATEGORY = "category"
40CHARSET = "charset"
41GROUPREF = "groupref"
42GROUPREF_IGNORE = "groupref_ignore"
43GROUPREF_EXISTS = "groupref_exists"
44IN = "in"
45IN_IGNORE = "in_ignore"
46INFO = "info"
47JUMP = "jump"
48LITERAL = "literal"
49LITERAL_IGNORE = "literal_ignore"
50MARK = "mark"
51MAX_REPEAT = "max_repeat"
52MAX_UNTIL = "max_until"
53MIN_REPEAT = "min_repeat"
54MIN_UNTIL = "min_until"
55NEGATE = "negate"
56NOT_LITERAL = "not_literal"
57NOT_LITERAL_IGNORE = "not_literal_ignore"
58RANGE = "range"
59REPEAT = "repeat"
60REPEAT_ONE = "repeat_one"
61SUBPATTERN = "subpattern"
62MIN_REPEAT_ONE = "min_repeat_one"
63
64# positions
65AT_BEGINNING = "at_beginning"
66AT_BEGINNING_LINE = "at_beginning_line"
67AT_BEGINNING_STRING = "at_beginning_string"
68AT_BOUNDARY = "at_boundary"
69AT_NON_BOUNDARY = "at_non_boundary"
70AT_END = "at_end"
71AT_END_LINE = "at_end_line"
72AT_END_STRING = "at_end_string"
73AT_LOC_BOUNDARY = "at_loc_boundary"
74AT_LOC_NON_BOUNDARY = "at_loc_non_boundary"
75AT_UNI_BOUNDARY = "at_uni_boundary"
76AT_UNI_NON_BOUNDARY = "at_uni_non_boundary"
77
78# categories
79CATEGORY_DIGIT = "category_digit"
80CATEGORY_NOT_DIGIT = "category_not_digit"
81CATEGORY_SPACE = "category_space"
82CATEGORY_NOT_SPACE = "category_not_space"
83CATEGORY_WORD = "category_word"
84CATEGORY_NOT_WORD = "category_not_word"
85CATEGORY_LINEBREAK = "category_linebreak"
86CATEGORY_NOT_LINEBREAK = "category_not_linebreak"
87CATEGORY_LOC_WORD = "category_loc_word"
88CATEGORY_LOC_NOT_WORD = "category_loc_not_word"
89CATEGORY_UNI_DIGIT = "category_uni_digit"
90CATEGORY_UNI_NOT_DIGIT = "category_uni_not_digit"
91CATEGORY_UNI_SPACE = "category_uni_space"
92CATEGORY_UNI_NOT_SPACE = "category_uni_not_space"
93CATEGORY_UNI_WORD = "category_uni_word"
94CATEGORY_UNI_NOT_WORD = "category_uni_not_word"
95CATEGORY_UNI_LINEBREAK = "category_uni_linebreak"
96CATEGORY_UNI_NOT_LINEBREAK = "category_uni_not_linebreak"
97
98OPCODES = [
99
100    # failure=0 success=1 (just because it looks better that way :-)
101    FAILURE, SUCCESS,
102
103    ANY, ANY_ALL,
104    ASSERT, ASSERT_NOT,
105    AT,
106    BRANCH,
107    CALL,
108    CATEGORY,
109    CHARSET, BIGCHARSET,
110    GROUPREF, GROUPREF_EXISTS, GROUPREF_IGNORE,
111    IN, IN_IGNORE,
112    INFO,
113    JUMP,
114    LITERAL, LITERAL_IGNORE,
115    MARK,
116    MAX_UNTIL,
117    MIN_UNTIL,
118    NOT_LITERAL, NOT_LITERAL_IGNORE,
119    NEGATE,
120    RANGE,
121    REPEAT,
122    REPEAT_ONE,
123    SUBPATTERN,
124    MIN_REPEAT_ONE
125
126]
127
128ATCODES = [
129    AT_BEGINNING, AT_BEGINNING_LINE, AT_BEGINNING_STRING, AT_BOUNDARY,
130    AT_NON_BOUNDARY, AT_END, AT_END_LINE, AT_END_STRING,
131    AT_LOC_BOUNDARY, AT_LOC_NON_BOUNDARY, AT_UNI_BOUNDARY,
132    AT_UNI_NON_BOUNDARY
133]
134
135CHCODES = [
136    CATEGORY_DIGIT, CATEGORY_NOT_DIGIT, CATEGORY_SPACE,
137    CATEGORY_NOT_SPACE, CATEGORY_WORD, CATEGORY_NOT_WORD,
138    CATEGORY_LINEBREAK, CATEGORY_NOT_LINEBREAK, CATEGORY_LOC_WORD,
139    CATEGORY_LOC_NOT_WORD, CATEGORY_UNI_DIGIT, CATEGORY_UNI_NOT_DIGIT,
140    CATEGORY_UNI_SPACE, CATEGORY_UNI_NOT_SPACE, CATEGORY_UNI_WORD,
141    CATEGORY_UNI_NOT_WORD, CATEGORY_UNI_LINEBREAK,
142    CATEGORY_UNI_NOT_LINEBREAK
143]
144
145def makedict(list):
146    d = {}
147    i = 0
148    for item in list:
149        d[item] = i
150        i = i + 1
151    return d
152
153OPCODES = makedict(OPCODES)
154ATCODES = makedict(ATCODES)
155CHCODES = makedict(CHCODES)
156
157# replacement operations for "ignore case" mode
158OP_IGNORE = {
159    GROUPREF: GROUPREF_IGNORE,
160    IN: IN_IGNORE,
161    LITERAL: LITERAL_IGNORE,
162    NOT_LITERAL: NOT_LITERAL_IGNORE
163}
164
165AT_MULTILINE = {
166    AT_BEGINNING: AT_BEGINNING_LINE,
167    AT_END: AT_END_LINE
168}
169
170AT_LOCALE = {
171    AT_BOUNDARY: AT_LOC_BOUNDARY,
172    AT_NON_BOUNDARY: AT_LOC_NON_BOUNDARY
173}
174
175AT_UNICODE = {
176    AT_BOUNDARY: AT_UNI_BOUNDARY,
177    AT_NON_BOUNDARY: AT_UNI_NON_BOUNDARY
178}
179
180CH_LOCALE = {
181    CATEGORY_DIGIT: CATEGORY_DIGIT,
182    CATEGORY_NOT_DIGIT: CATEGORY_NOT_DIGIT,
183    CATEGORY_SPACE: CATEGORY_SPACE,
184    CATEGORY_NOT_SPACE: CATEGORY_NOT_SPACE,
185    CATEGORY_WORD: CATEGORY_LOC_WORD,
186    CATEGORY_NOT_WORD: CATEGORY_LOC_NOT_WORD,
187    CATEGORY_LINEBREAK: CATEGORY_LINEBREAK,
188    CATEGORY_NOT_LINEBREAK: CATEGORY_NOT_LINEBREAK
189}
190
191CH_UNICODE = {
192    CATEGORY_DIGIT: CATEGORY_UNI_DIGIT,
193    CATEGORY_NOT_DIGIT: CATEGORY_UNI_NOT_DIGIT,
194    CATEGORY_SPACE: CATEGORY_UNI_SPACE,
195    CATEGORY_NOT_SPACE: CATEGORY_UNI_NOT_SPACE,
196    CATEGORY_WORD: CATEGORY_UNI_WORD,
197    CATEGORY_NOT_WORD: CATEGORY_UNI_NOT_WORD,
198    CATEGORY_LINEBREAK: CATEGORY_UNI_LINEBREAK,
199    CATEGORY_NOT_LINEBREAK: CATEGORY_UNI_NOT_LINEBREAK
200}
201
202# flags
203SRE_FLAG_TEMPLATE = 1 # template mode (disable backtracking)
204SRE_FLAG_IGNORECASE = 2 # case insensitive
205SRE_FLAG_LOCALE = 4 # honour system locale
206SRE_FLAG_MULTILINE = 8 # treat target as multiline string
207SRE_FLAG_DOTALL = 16 # treat target as a single string
208SRE_FLAG_UNICODE = 32 # use unicode "locale"
209SRE_FLAG_VERBOSE = 64 # ignore whitespace and comments
210SRE_FLAG_DEBUG = 128 # debugging
211SRE_FLAG_ASCII = 256 # use ascii "locale"
212
213# flags for INFO primitive
214SRE_INFO_PREFIX = 1 # has prefix
215SRE_INFO_LITERAL = 2 # entire pattern is literal (given by prefix)
216SRE_INFO_CHARSET = 4 # pattern starts with character from given set
217
218if __name__ == "__main__":
219    def dump(f, d, prefix):
220        items = sorted(d.items(), key=lambda a: a[1])
221        for k, v in items:
222            f.write("#define %s_%s %s\n" % (prefix, k.upper(), v))
223    f = open("sre_constants.h", "w")
224    f.write("""\
225/*
226 * Secret Labs' Regular Expression Engine
227 *
228 * regular expression matching engine
229 *
230 * NOTE: This file is generated by sre_constants.py.  If you need
231 * to change anything in here, edit sre_constants.py and run it.
232 *
233 * Copyright (c) 1997-2001 by Secret Labs AB.  All rights reserved.
234 *
235 * See the _sre.c file for information on usage and redistribution.
236 */
237
238""")
239
240    f.write("#define SRE_MAGIC %d\n" % MAGIC)
241
242    dump(f, OPCODES, "SRE_OP")
243    dump(f, ATCODES, "SRE")
244    dump(f, CHCODES, "SRE")
245
246    f.write("#define SRE_FLAG_TEMPLATE %d\n" % SRE_FLAG_TEMPLATE)
247    f.write("#define SRE_FLAG_IGNORECASE %d\n" % SRE_FLAG_IGNORECASE)
248    f.write("#define SRE_FLAG_LOCALE %d\n" % SRE_FLAG_LOCALE)
249    f.write("#define SRE_FLAG_MULTILINE %d\n" % SRE_FLAG_MULTILINE)
250    f.write("#define SRE_FLAG_DOTALL %d\n" % SRE_FLAG_DOTALL)
251    f.write("#define SRE_FLAG_UNICODE %d\n" % SRE_FLAG_UNICODE)
252    f.write("#define SRE_FLAG_VERBOSE %d\n" % SRE_FLAG_VERBOSE)
253    f.write("#define SRE_FLAG_DEBUG %d\n" % SRE_FLAG_DEBUG)
254    f.write("#define SRE_FLAG_ASCII %d\n" % SRE_FLAG_ASCII)
255
256    f.write("#define SRE_INFO_PREFIX %d\n" % SRE_INFO_PREFIX)
257    f.write("#define SRE_INFO_LITERAL %d\n" % SRE_INFO_LITERAL)
258    f.write("#define SRE_INFO_CHARSET %d\n" % SRE_INFO_CHARSET)
259
260    f.close()
261    print("done")
262