Lib/sre_constants.py

   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 = 20010701
  17
  18 # max code word in this release
  19
  20 MAXREPEAT = 65535
  21
  22 # SRE standard exception (access as sre.error)
  23 # should this really be here?
  24
  25 class error(Exception):
  26     pass
  27
  28 # operators
  29
  30 FAILURE = "failure"
  31 SUCCESS = "success"
  32
  33 ANY = "any"
  34 ANY_ALL = "any_all"
  35 ASSERT = "assert"
  36 ASSERT_NOT = "assert_not"
  37 AT = "at"
  38 BIGCHARSET = "bigcharset"
  39 BRANCH = "branch"
  40 CALL = "call"
  41 CATEGORY = "category"
  42 CHARSET = "charset"
  43 GROUPREF = "groupref"
  44 GROUPREF_IGNORE = "groupref_ignore"
  45 IN = "in"
  46 IN_IGNORE = "in_ignore"
  47 INFO = "info"
  48 JUMP = "jump"
  49 LITERAL = "literal"
  50 LITERAL_IGNORE = "literal_ignore"
  51 MARK = "mark"
  52 MAX_REPEAT = "max_repeat"
  53 MAX_UNTIL = "max_until"
  54 MIN_REPEAT = "min_repeat"
  55 MIN_UNTIL = "min_until"
  56 NEGATE = "negate"
  57 NOT_LITERAL = "not_literal"
  58 NOT_LITERAL_IGNORE = "not_literal_ignore"
  59 RANGE = "range"
  60 REPEAT = "repeat"
  61 REPEAT_ONE = "repeat_one"
  62 SUBPATTERN = "subpattern"
  63
  64 # positions
  65 AT_BEGINNING = "at_beginning"
  66 AT_BEGINNING_LINE = "at_beginning_line"
  67 AT_BEGINNING_STRING = "at_beginning_string"
  68 AT_BOUNDARY = "at_boundary"
  69 AT_NON_BOUNDARY = "at_non_boundary"
  70 AT_END = "at_end"
  71 AT_END_LINE = "at_end_line"
  72 AT_END_STRING = "at_end_string"
  73 AT_LOC_BOUNDARY = "at_loc_boundary"
  74 AT_LOC_NON_BOUNDARY = "at_loc_non_boundary"
  75 AT_UNI_BOUNDARY = "at_uni_boundary"
  76 AT_UNI_NON_BOUNDARY = "at_uni_non_boundary"
  77
  78 # categories
  79 CATEGORY_DIGIT = "category_digit"
  80 CATEGORY_NOT_DIGIT = "category_not_digit"
  81 CATEGORY_SPACE = "category_space"
  82 CATEGORY_NOT_SPACE = "category_not_space"
  83 CATEGORY_WORD = "category_word"
  84 CATEGORY_NOT_WORD = "category_not_word"
  85 CATEGORY_LINEBREAK = "category_linebreak"
  86 CATEGORY_NOT_LINEBREAK = "category_not_linebreak"
  87 CATEGORY_LOC_WORD = "category_loc_word"
  88 CATEGORY_LOC_NOT_WORD = "category_loc_not_word"
  89 CATEGORY_UNI_DIGIT = "category_uni_digit"
  90 CATEGORY_UNI_NOT_DIGIT = "category_uni_not_digit"
  91 CATEGORY_UNI_SPACE = "category_uni_space"
  92 CATEGORY_UNI_NOT_SPACE = "category_uni_not_space"
  93 CATEGORY_UNI_WORD = "category_uni_word"
  94 CATEGORY_UNI_NOT_WORD = "category_uni_not_word"
  95 CATEGORY_UNI_LINEBREAK = "category_uni_linebreak"
  96 CATEGORY_UNI_NOT_LINEBREAK = "category_uni_not_linebreak"
  97
  98 OPCODES = [
  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_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
 125 ]
 126
 127 ATCODES = [
 128     AT_BEGINNING, AT_BEGINNING_LINE, AT_BEGINNING_STRING, AT_BOUNDARY,
 129     AT_NON_BOUNDARY, AT_END, AT_END_LINE, AT_END_STRING,
 130     AT_LOC_BOUNDARY, AT_LOC_NON_BOUNDARY, AT_UNI_BOUNDARY,
 131     AT_UNI_NON_BOUNDARY
 132 ]
 133
 134 CHCODES = [
 135     CATEGORY_DIGIT, CATEGORY_NOT_DIGIT, CATEGORY_SPACE,
 136     CATEGORY_NOT_SPACE, CATEGORY_WORD, CATEGORY_NOT_WORD,
 137     CATEGORY_LINEBREAK, CATEGORY_NOT_LINEBREAK, CATEGORY_LOC_WORD,
 138     CATEGORY_LOC_NOT_WORD, CATEGORY_UNI_DIGIT, CATEGORY_UNI_NOT_DIGIT,
 139     CATEGORY_UNI_SPACE, CATEGORY_UNI_NOT_SPACE, CATEGORY_UNI_WORD,
 140     CATEGORY_UNI_NOT_WORD, CATEGORY_UNI_LINEBREAK,
 141     CATEGORY_UNI_NOT_LINEBREAK
 142 ]
 143
 144 def makedict(list):
 145     d = {}
 146     i = 0
 147     for item in list:
 148         d[item] = i
 149         i = i + 1
 150     return d
 151
 152 OPCODES = makedict(OPCODES)
 153 ATCODES = makedict(ATCODES)
 154 CHCODES = makedict(CHCODES)
 155
 156 # replacement operations for "ignore case" mode
 157 OP_IGNORE = {
 158     GROUPREF: GROUPREF_IGNORE,
 159     IN: IN_IGNORE,
 160     LITERAL: LITERAL_IGNORE,
 161     NOT_LITERAL: NOT_LITERAL_IGNORE
 162 }
 163
 164 AT_MULTILINE = {
 165     AT_BEGINNING: AT_BEGINNING_LINE,
 166     AT_END: AT_END_LINE
 167 }
 168
 169 AT_LOCALE = {
 170     AT_BOUNDARY: AT_LOC_BOUNDARY,
 171     AT_NON_BOUNDARY: AT_LOC_NON_BOUNDARY
 172 }
 173
 174 AT_UNICODE = {
 175     AT_BOUNDARY: AT_UNI_BOUNDARY,
 176     AT_NON_BOUNDARY: AT_UNI_NON_BOUNDARY
 177 }
 178
 179 CH_LOCALE = {
 180     CATEGORY_DIGIT: CATEGORY_DIGIT,
 181     CATEGORY_NOT_DIGIT: CATEGORY_NOT_DIGIT,
 182     CATEGORY_SPACE: CATEGORY_SPACE,
 183     CATEGORY_NOT_SPACE: CATEGORY_NOT_SPACE,
 184     CATEGORY_WORD: CATEGORY_LOC_WORD,
 185     CATEGORY_NOT_WORD: CATEGORY_LOC_NOT_WORD,
 186     CATEGORY_LINEBREAK: CATEGORY_LINEBREAK,
 187     CATEGORY_NOT_LINEBREAK: CATEGORY_NOT_LINEBREAK
 188 }
 189
 190 CH_UNICODE = {
 191     CATEGORY_DIGIT: CATEGORY_UNI_DIGIT,
 192     CATEGORY_NOT_DIGIT: CATEGORY_UNI_NOT_DIGIT,
 193     CATEGORY_SPACE: CATEGORY_UNI_SPACE,
 194     CATEGORY_NOT_SPACE: CATEGORY_UNI_NOT_SPACE,
 195     CATEGORY_WORD: CATEGORY_UNI_WORD,
 196     CATEGORY_NOT_WORD: CATEGORY_UNI_NOT_WORD,
 197     CATEGORY_LINEBREAK: CATEGORY_UNI_LINEBREAK,
 198     CATEGORY_NOT_LINEBREAK: CATEGORY_UNI_NOT_LINEBREAK
 199 }
 200
 201 # flags
 202 SRE_FLAG_TEMPLATE = 1 # template mode (disable backtracking)
 203 SRE_FLAG_IGNORECASE = 2 # case insensitive
 204 SRE_FLAG_LOCALE = 4 # honour system locale
 205 SRE_FLAG_MULTILINE = 8 # treat target as multiline string
 206 SRE_FLAG_DOTALL = 16 # treat target as a single string
 207 SRE_FLAG_UNICODE = 32 # use unicode locale
 208 SRE_FLAG_VERBOSE = 64 # ignore whitespace and comments
 209 SRE_FLAG_DEBUG = 128 # debugging
 210
 211 # flags for INFO primitive
 212 SRE_INFO_PREFIX = 1 # has prefix
 213 SRE_INFO_LITERAL = 2 # entire pattern is literal (given by prefix)
 214 SRE_INFO_CHARSET = 4 # pattern starts with character from given set
 215
 216 if __name__ == "__main__":
 217     import string
 218     def dump(f, d, prefix):
 219         items = d.items()
 220         items.sort(lambda a, b: cmp(a[1], b[1]))
 221         for k, v in items:
 222             f.write("#define %s_%s %s\n" % (prefix, string.upper(k), 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
 254     f.write("#define SRE_INFO_PREFIX %d\n" % SRE_INFO_PREFIX)
 255     f.write("#define SRE_INFO_LITERAL %d\n" % SRE_INFO_LITERAL)
 256     f.write("#define SRE_INFO_CHARSET %d\n" % SRE_INFO_CHARSET)
 257
 258     f.close()
 259     print "done"