| 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 |
|
| 16 | MAGIC = 20031017
|
| 17 |
|
| 18 | try:
|
| 19 | from _sre import MAXREPEAT
|
| 20 | except ImportError:
|
| 21 | import _sre
|
| 22 | MAXREPEAT = _sre.MAXREPEAT = 65535
|
| 23 |
|
| 24 | # SRE standard exception (access as sre.error)
|
| 25 | # should this really be here?
|
| 26 |
|
| 27 | class error(Exception):
|
| 28 | pass
|
| 29 |
|
| 30 | # operators
|
| 31 |
|
| 32 | FAILURE = "failure"
|
| 33 | SUCCESS = "success"
|
| 34 |
|
| 35 | ANY = "any"
|
| 36 | ANY_ALL = "any_all"
|
| 37 | ASSERT = "assert"
|
| 38 | ASSERT_NOT = "assert_not"
|
| 39 | AT = "at"
|
| 40 | BIGCHARSET = "bigcharset"
|
| 41 | BRANCH = "branch"
|
| 42 | CALL = "call"
|
| 43 | CATEGORY = "category"
|
| 44 | CHARSET = "charset"
|
| 45 | GROUPREF = "groupref"
|
| 46 | GROUPREF_IGNORE = "groupref_ignore"
|
| 47 | GROUPREF_EXISTS = "groupref_exists"
|
| 48 | IN = "in"
|
| 49 | IN_IGNORE = "in_ignore"
|
| 50 | INFO = "info"
|
| 51 | JUMP = "jump"
|
| 52 | LITERAL = "literal"
|
| 53 | LITERAL_IGNORE = "literal_ignore"
|
| 54 | MARK = "mark"
|
| 55 | MAX_REPEAT = "max_repeat"
|
| 56 | MAX_UNTIL = "max_until"
|
| 57 | MIN_REPEAT = "min_repeat"
|
| 58 | MIN_UNTIL = "min_until"
|
| 59 | NEGATE = "negate"
|
| 60 | NOT_LITERAL = "not_literal"
|
| 61 | NOT_LITERAL_IGNORE = "not_literal_ignore"
|
| 62 | RANGE = "range"
|
| 63 | REPEAT = "repeat"
|
| 64 | REPEAT_ONE = "repeat_one"
|
| 65 | SUBPATTERN = "subpattern"
|
| 66 | MIN_REPEAT_ONE = "min_repeat_one"
|
| 67 |
|
| 68 | # positions
|
| 69 | AT_BEGINNING = "at_beginning"
|
| 70 | AT_BEGINNING_LINE = "at_beginning_line"
|
| 71 | AT_BEGINNING_STRING = "at_beginning_string"
|
| 72 | AT_BOUNDARY = "at_boundary"
|
| 73 | AT_NON_BOUNDARY = "at_non_boundary"
|
| 74 | AT_END = "at_end"
|
| 75 | AT_END_LINE = "at_end_line"
|
| 76 | AT_END_STRING = "at_end_string"
|
| 77 | AT_LOC_BOUNDARY = "at_loc_boundary"
|
| 78 | AT_LOC_NON_BOUNDARY = "at_loc_non_boundary"
|
| 79 | AT_UNI_BOUNDARY = "at_uni_boundary"
|
| 80 | AT_UNI_NON_BOUNDARY = "at_uni_non_boundary"
|
| 81 |
|
| 82 | # categories
|
| 83 | CATEGORY_DIGIT = "category_digit"
|
| 84 | CATEGORY_NOT_DIGIT = "category_not_digit"
|
| 85 | CATEGORY_SPACE = "category_space"
|
| 86 | CATEGORY_NOT_SPACE = "category_not_space"
|
| 87 | CATEGORY_WORD = "category_word"
|
| 88 | CATEGORY_NOT_WORD = "category_not_word"
|
| 89 | CATEGORY_LINEBREAK = "category_linebreak"
|
| 90 | CATEGORY_NOT_LINEBREAK = "category_not_linebreak"
|
| 91 | CATEGORY_LOC_WORD = "category_loc_word"
|
| 92 | CATEGORY_LOC_NOT_WORD = "category_loc_not_word"
|
| 93 | CATEGORY_UNI_DIGIT = "category_uni_digit"
|
| 94 | CATEGORY_UNI_NOT_DIGIT = "category_uni_not_digit"
|
| 95 | CATEGORY_UNI_SPACE = "category_uni_space"
|
| 96 | CATEGORY_UNI_NOT_SPACE = "category_uni_not_space"
|
| 97 | CATEGORY_UNI_WORD = "category_uni_word"
|
| 98 | CATEGORY_UNI_NOT_WORD = "category_uni_not_word"
|
| 99 | CATEGORY_UNI_LINEBREAK = "category_uni_linebreak"
|
| 100 | CATEGORY_UNI_NOT_LINEBREAK = "category_uni_not_linebreak"
|
| 101 |
|
| 102 | OPCODES = [
|
| 103 |
|
| 104 | # failure=0 success=1 (just because it looks better that way :-)
|
| 105 | FAILURE, SUCCESS,
|
| 106 |
|
| 107 | ANY, ANY_ALL,
|
| 108 | ASSERT, ASSERT_NOT,
|
| 109 | AT,
|
| 110 | BRANCH,
|
| 111 | CALL,
|
| 112 | CATEGORY,
|
| 113 | CHARSET, BIGCHARSET,
|
| 114 | GROUPREF, GROUPREF_EXISTS, GROUPREF_IGNORE,
|
| 115 | IN, IN_IGNORE,
|
| 116 | INFO,
|
| 117 | JUMP,
|
| 118 | LITERAL, LITERAL_IGNORE,
|
| 119 | MARK,
|
| 120 | MAX_UNTIL,
|
| 121 | MIN_UNTIL,
|
| 122 | NOT_LITERAL, NOT_LITERAL_IGNORE,
|
| 123 | NEGATE,
|
| 124 | RANGE,
|
| 125 | REPEAT,
|
| 126 | REPEAT_ONE,
|
| 127 | SUBPATTERN,
|
| 128 | MIN_REPEAT_ONE
|
| 129 |
|
| 130 | ]
|
| 131 |
|
| 132 | ATCODES = [
|
| 133 | AT_BEGINNING, AT_BEGINNING_LINE, AT_BEGINNING_STRING, AT_BOUNDARY,
|
| 134 | AT_NON_BOUNDARY, AT_END, AT_END_LINE, AT_END_STRING,
|
| 135 | AT_LOC_BOUNDARY, AT_LOC_NON_BOUNDARY, AT_UNI_BOUNDARY,
|
| 136 | AT_UNI_NON_BOUNDARY
|
| 137 | ]
|
| 138 |
|
| 139 | CHCODES = [
|
| 140 | CATEGORY_DIGIT, CATEGORY_NOT_DIGIT, CATEGORY_SPACE,
|
| 141 | CATEGORY_NOT_SPACE, CATEGORY_WORD, CATEGORY_NOT_WORD,
|
| 142 | CATEGORY_LINEBREAK, CATEGORY_NOT_LINEBREAK, CATEGORY_LOC_WORD,
|
| 143 | CATEGORY_LOC_NOT_WORD, CATEGORY_UNI_DIGIT, CATEGORY_UNI_NOT_DIGIT,
|
| 144 | CATEGORY_UNI_SPACE, CATEGORY_UNI_NOT_SPACE, CATEGORY_UNI_WORD,
|
| 145 | CATEGORY_UNI_NOT_WORD, CATEGORY_UNI_LINEBREAK,
|
| 146 | CATEGORY_UNI_NOT_LINEBREAK
|
| 147 | ]
|
| 148 |
|
| 149 | def makedict(list):
|
| 150 | d = {}
|
| 151 | i = 0
|
| 152 | for item in list:
|
| 153 | d[item] = i
|
| 154 | i = i + 1
|
| 155 | return d
|
| 156 |
|
| 157 | OPCODES = makedict(OPCODES)
|
| 158 | ATCODES = makedict(ATCODES)
|
| 159 | CHCODES = makedict(CHCODES)
|
| 160 |
|
| 161 | # replacement operations for "ignore case" mode
|
| 162 | OP_IGNORE = {
|
| 163 | GROUPREF: GROUPREF_IGNORE,
|
| 164 | IN: IN_IGNORE,
|
| 165 | LITERAL: LITERAL_IGNORE,
|
| 166 | NOT_LITERAL: NOT_LITERAL_IGNORE
|
| 167 | }
|
| 168 |
|
| 169 | AT_MULTILINE = {
|
| 170 | AT_BEGINNING: AT_BEGINNING_LINE,
|
| 171 | AT_END: AT_END_LINE
|
| 172 | }
|
| 173 |
|
| 174 | AT_LOCALE = {
|
| 175 | AT_BOUNDARY: AT_LOC_BOUNDARY,
|
| 176 | AT_NON_BOUNDARY: AT_LOC_NON_BOUNDARY
|
| 177 | }
|
| 178 |
|
| 179 | AT_UNICODE = {
|
| 180 | AT_BOUNDARY: AT_UNI_BOUNDARY,
|
| 181 | AT_NON_BOUNDARY: AT_UNI_NON_BOUNDARY
|
| 182 | }
|
| 183 |
|
| 184 | CH_LOCALE = {
|
| 185 | CATEGORY_DIGIT: CATEGORY_DIGIT,
|
| 186 | CATEGORY_NOT_DIGIT: CATEGORY_NOT_DIGIT,
|
| 187 | CATEGORY_SPACE: CATEGORY_SPACE,
|
| 188 | CATEGORY_NOT_SPACE: CATEGORY_NOT_SPACE,
|
| 189 | CATEGORY_WORD: CATEGORY_LOC_WORD,
|
| 190 | CATEGORY_NOT_WORD: CATEGORY_LOC_NOT_WORD,
|
| 191 | CATEGORY_LINEBREAK: CATEGORY_LINEBREAK,
|
| 192 | CATEGORY_NOT_LINEBREAK: CATEGORY_NOT_LINEBREAK
|
| 193 | }
|
| 194 |
|
| 195 | CH_UNICODE = {
|
| 196 | CATEGORY_DIGIT: CATEGORY_UNI_DIGIT,
|
| 197 | CATEGORY_NOT_DIGIT: CATEGORY_UNI_NOT_DIGIT,
|
| 198 | CATEGORY_SPACE: CATEGORY_UNI_SPACE,
|
| 199 | CATEGORY_NOT_SPACE: CATEGORY_UNI_NOT_SPACE,
|
| 200 | CATEGORY_WORD: CATEGORY_UNI_WORD,
|
| 201 | CATEGORY_NOT_WORD: CATEGORY_UNI_NOT_WORD,
|
| 202 | CATEGORY_LINEBREAK: CATEGORY_UNI_LINEBREAK,
|
| 203 | CATEGORY_NOT_LINEBREAK: CATEGORY_UNI_NOT_LINEBREAK
|
| 204 | }
|
| 205 |
|
| 206 | # flags
|
| 207 | SRE_FLAG_TEMPLATE = 1 # template mode (disable backtracking)
|
| 208 | SRE_FLAG_IGNORECASE = 2 # case insensitive
|
| 209 | SRE_FLAG_LOCALE = 4 # honour system locale
|
| 210 | SRE_FLAG_MULTILINE = 8 # treat target as multiline string
|
| 211 | SRE_FLAG_DOTALL = 16 # treat target as a single string
|
| 212 | SRE_FLAG_UNICODE = 32 # use unicode locale
|
| 213 | SRE_FLAG_VERBOSE = 64 # ignore whitespace and comments
|
| 214 | SRE_FLAG_DEBUG = 128 # debugging
|
| 215 |
|
| 216 | # flags for INFO primitive
|
| 217 | SRE_INFO_PREFIX = 1 # has prefix
|
| 218 | SRE_INFO_LITERAL = 2 # entire pattern is literal (given by prefix)
|
| 219 | SRE_INFO_CHARSET = 4 # pattern starts with character from given set
|
| 220 |
|
| 221 | if __name__ == "__main__":
|
| 222 | def dump(f, d, prefix):
|
| 223 | items = d.items()
|
| 224 | items.sort(key=lambda a: a[1])
|
| 225 | for k, v in items:
|
| 226 | f.write("#define %s_%s %s\n" % (prefix, k.upper(), v))
|
| 227 | f = open("sre_constants.h", "w")
|
| 228 | f.write("""\
|
| 229 | /*
|
| 230 | * Secret Labs' Regular Expression Engine
|
| 231 | *
|
| 232 | * regular expression matching engine
|
| 233 | *
|
| 234 | * NOTE: This file is generated by sre_constants.py. If you need
|
| 235 | * to change anything in here, edit sre_constants.py and run it.
|
| 236 | *
|
| 237 | * Copyright (c) 1997-2001 by Secret Labs AB. All rights reserved.
|
| 238 | *
|
| 239 | * See the _sre.c file for information on usage and redistribution.
|
| 240 | */
|
| 241 |
|
| 242 | """)
|
| 243 |
|
| 244 | f.write("#define SRE_MAGIC %d\n" % MAGIC)
|
| 245 |
|
| 246 | dump(f, OPCODES, "SRE_OP")
|
| 247 | dump(f, ATCODES, "SRE")
|
| 248 | dump(f, CHCODES, "SRE")
|
| 249 |
|
| 250 | f.write("#define SRE_FLAG_TEMPLATE %d\n" % SRE_FLAG_TEMPLATE)
|
| 251 | f.write("#define SRE_FLAG_IGNORECASE %d\n" % SRE_FLAG_IGNORECASE)
|
| 252 | f.write("#define SRE_FLAG_LOCALE %d\n" % SRE_FLAG_LOCALE)
|
| 253 | f.write("#define SRE_FLAG_MULTILINE %d\n" % SRE_FLAG_MULTILINE)
|
| 254 | f.write("#define SRE_FLAG_DOTALL %d\n" % SRE_FLAG_DOTALL)
|
| 255 | f.write("#define SRE_FLAG_UNICODE %d\n" % SRE_FLAG_UNICODE)
|
| 256 | f.write("#define SRE_FLAG_VERBOSE %d\n" % SRE_FLAG_VERBOSE)
|
| 257 |
|
| 258 | f.write("#define SRE_INFO_PREFIX %d\n" % SRE_INFO_PREFIX)
|
| 259 | f.write("#define SRE_INFO_LITERAL %d\n" % SRE_INFO_LITERAL)
|
| 260 | f.write("#define SRE_INFO_CHARSET %d\n" % SRE_INFO_CHARSET)
|
| 261 |
|
| 262 | f.close()
|
| 263 | # Commented out because OPy compiler doesn't like print statements.
|
| 264 | #print "done"
|