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 # update when constants are added or removed
  13
  14 MAGIC = 20010115
  15
  16 # max code word in this release
  17
  18 MAXREPEAT = 65535
  19
  20 # SRE standard exception (access as sre.error)
  21 # should this really be here?
  22
  23 class error(Exception):
  24     pass
  25
  26 # operators
  27
  28 FAILURE = "failure"
  29 SUCCESS = "success"
  30
  31 ANY = "any"
  32 ANY_ALL = "any_all"
  33 ASSERT = "assert"
  34 ASSERT_NOT = "assert_not"
  35 AT = "at"
  36 BRANCH = "branch"
  37 CALL = "call"
  38 CATEGORY = "category"
  39 CHARSET = "charset"
  40 GROUPREF = "groupref"
  41 GROUPREF_IGNORE = "groupref_ignore"
  42 IN = "in"
  43 IN_IGNORE = "in_ignore"
  44 INFO = "info"
  45 JUMP = "jump"
  46 LITERAL = "literal"
  47 LITERAL_IGNORE = "literal_ignore"
  48 MARK = "mark"
  49 MAX_REPEAT = "max_repeat"
  50 MAX_UNTIL = "max_until"
  51 MIN_REPEAT = "min_repeat"
  52 MIN_UNTIL = "min_until"
  53 NEGATE = "negate"
  54 NOT_LITERAL = "not_literal"
  55 NOT_LITERAL_IGNORE = "not_literal_ignore"
  56 RANGE = "range"
  57 REPEAT = "repeat"
  58 REPEAT_ONE = "repeat_one"
  59 SUBPATTERN = "subpattern"
  60
  61 # positions
  62 AT_BEGINNING = "at_beginning"
  63 AT_BEGINNING_LINE = "at_beginning_line"
  64 AT_BEGINNING_STRING = "at_beginning_string"
  65 AT_BOUNDARY = "at_boundary"
  66 AT_NON_BOUNDARY = "at_non_boundary"
  67 AT_END = "at_end"
  68 AT_END_LINE = "at_end_line"
  69 AT_END_STRING = "at_end_string"
  70
  71 # categories
  72 CATEGORY_DIGIT = "category_digit"
  73 CATEGORY_NOT_DIGIT = "category_not_digit"
  74 CATEGORY_SPACE = "category_space"
  75 CATEGORY_NOT_SPACE = "category_not_space"
  76 CATEGORY_WORD = "category_word"
  77 CATEGORY_NOT_WORD = "category_not_word"
  78 CATEGORY_LINEBREAK = "category_linebreak"
  79 CATEGORY_NOT_LINEBREAK = "category_not_linebreak"
  80 CATEGORY_LOC_WORD = "category_loc_word"
  81 CATEGORY_LOC_NOT_WORD = "category_loc_not_word"
  82 CATEGORY_UNI_DIGIT = "category_uni_digit"
  83 CATEGORY_UNI_NOT_DIGIT = "category_uni_not_digit"
  84 CATEGORY_UNI_SPACE = "category_uni_space"
  85 CATEGORY_UNI_NOT_SPACE = "category_uni_not_space"
  86 CATEGORY_UNI_WORD = "category_uni_word"
  87 CATEGORY_UNI_NOT_WORD = "category_uni_not_word"
  88 CATEGORY_UNI_LINEBREAK = "category_uni_linebreak"
  89 CATEGORY_UNI_NOT_LINEBREAK = "category_uni_not_linebreak"
  90
  91 OPCODES = [
  92
  93     # failure=0 success=1 (just because it looks better that way :-)
  94     FAILURE, SUCCESS,
  95
  96     ANY, ANY_ALL,
  97     ASSERT, ASSERT_NOT,
  98     AT,
  99     BRANCH,
 100     CALL,
 101     CATEGORY,
 102     CHARSET,
 103     GROUPREF, GROUPREF_IGNORE,
 104     IN, IN_IGNORE,
 105     INFO,
 106     JUMP,
 107     LITERAL, LITERAL_IGNORE,
 108     MARK,
 109     MAX_UNTIL,
 110     MIN_UNTIL,
 111     NOT_LITERAL, NOT_LITERAL_IGNORE,
 112     NEGATE,
 113     RANGE,
 114     REPEAT,
 115     REPEAT_ONE,
 116     SUBPATTERN
 117
 118 ]
 119
 120 ATCODES = [
 121     AT_BEGINNING, AT_BEGINNING_LINE, AT_BEGINNING_STRING, AT_BOUNDARY,
 122     AT_NON_BOUNDARY, AT_END, AT_END_LINE, AT_END_STRING
 123 ]
 124
 125 CHCODES = [
 126     CATEGORY_DIGIT, CATEGORY_NOT_DIGIT, CATEGORY_SPACE,
 127     CATEGORY_NOT_SPACE, CATEGORY_WORD, CATEGORY_NOT_WORD,
 128     CATEGORY_LINEBREAK, CATEGORY_NOT_LINEBREAK, CATEGORY_LOC_WORD,
 129     CATEGORY_LOC_NOT_WORD, CATEGORY_UNI_DIGIT, CATEGORY_UNI_NOT_DIGIT,
 130     CATEGORY_UNI_SPACE, CATEGORY_UNI_NOT_SPACE, CATEGORY_UNI_WORD,
 131     CATEGORY_UNI_NOT_WORD, CATEGORY_UNI_LINEBREAK,
 132     CATEGORY_UNI_NOT_LINEBREAK
 133 ]
 134
 135 def makedict(list):
 136     d = {}
 137     i = 0
 138     for item in list:
 139         d[item] = i
 140         i = i + 1
 141     return d
 142
 143 OPCODES = makedict(OPCODES)
 144 ATCODES = makedict(ATCODES)
 145 CHCODES = makedict(CHCODES)
 146
 147 # replacement operations for "ignore case" mode
 148 OP_IGNORE = {
 149     GROUPREF: GROUPREF_IGNORE,
 150     IN: IN_IGNORE,
 151     LITERAL: LITERAL_IGNORE,
 152     NOT_LITERAL: NOT_LITERAL_IGNORE
 153 }
 154
 155 AT_MULTILINE = {
 156     AT_BEGINNING: AT_BEGINNING_LINE,
 157     AT_END: AT_END_LINE
 158 }
 159
 160 CH_LOCALE = {
 161     CATEGORY_DIGIT: CATEGORY_DIGIT,
 162     CATEGORY_NOT_DIGIT: CATEGORY_NOT_DIGIT,
 163     CATEGORY_SPACE: CATEGORY_SPACE,
 164     CATEGORY_NOT_SPACE: CATEGORY_NOT_SPACE,
 165     CATEGORY_WORD: CATEGORY_LOC_WORD,
 166     CATEGORY_NOT_WORD: CATEGORY_LOC_NOT_WORD,
 167     CATEGORY_LINEBREAK: CATEGORY_LINEBREAK,
 168     CATEGORY_NOT_LINEBREAK: CATEGORY_NOT_LINEBREAK
 169 }
 170
 171 CH_UNICODE = {
 172     CATEGORY_DIGIT: CATEGORY_UNI_DIGIT,
 173     CATEGORY_NOT_DIGIT: CATEGORY_UNI_NOT_DIGIT,
 174     CATEGORY_SPACE: CATEGORY_UNI_SPACE,
 175     CATEGORY_NOT_SPACE: CATEGORY_UNI_NOT_SPACE,
 176     CATEGORY_WORD: CATEGORY_UNI_WORD,
 177     CATEGORY_NOT_WORD: CATEGORY_UNI_NOT_WORD,
 178     CATEGORY_LINEBREAK: CATEGORY_UNI_LINEBREAK,
 179     CATEGORY_NOT_LINEBREAK: CATEGORY_UNI_NOT_LINEBREAK
 180 }
 181
 182 # flags
 183 SRE_FLAG_TEMPLATE = 1 # template mode (disable backtracking)
 184 SRE_FLAG_IGNORECASE = 2 # case insensitive
 185 SRE_FLAG_LOCALE = 4 # honour system locale
 186 SRE_FLAG_MULTILINE = 8 # treat target as multiline string
 187 SRE_FLAG_DOTALL = 16 # treat target as a single string
 188 SRE_FLAG_UNICODE = 32 # use unicode locale
 189 SRE_FLAG_VERBOSE = 64 # ignore whitespace and comments
 190 SRE_FLAG_DEBUG = 128 # debugging
 191
 192 # flags for INFO primitive
 193 SRE_INFO_PREFIX = 1 # has prefix
 194 SRE_INFO_LITERAL = 2 # entire pattern is literal (given by prefix)
 195 SRE_INFO_CHARSET = 4 # pattern starts with character from given set
 196
 197 if __name__ == "__main__":
 198     import string
 199     def dump(f, d, prefix):
 200         items = d.items()
 201         items.sort(lambda a, b: cmp(a[1], b[1]))
 202         for k, v in items:
 203             f.write("#define %s_%s %s\n" % (prefix, string.upper(k), v))
 204     f = open("sre_constants.h", "w")
 205     f.write("""\
 206 /*
 207  * Secret Labs' Regular Expression Engine
 208  *
 209  * regular expression matching engine
 210  *
 211  * NOTE: This file is generated by sre_constants.py.  If you need
 212  * to change anything in here, edit sre_constants.py and run it.
 213  *
 214  * Copyright (c) 1997-2001 by Secret Labs AB.  All rights reserved.
 215  *
 216  * See the _sre.c file for information on usage and redistribution.
 217  */
 218
 219 """)
 220
 221     f.write("#define SRE_MAGIC %d\n" % MAGIC)
 222
 223     dump(f, OPCODES, "SRE_OP")
 224     dump(f, ATCODES, "SRE")
 225     dump(f, CHCODES, "SRE")
 226
 227     f.write("#define SRE_FLAG_TEMPLATE %d\n" % SRE_FLAG_TEMPLATE)
 228     f.write("#define SRE_FLAG_IGNORECASE %d\n" % SRE_FLAG_IGNORECASE)
 229     f.write("#define SRE_FLAG_LOCALE %d\n" % SRE_FLAG_LOCALE)
 230     f.write("#define SRE_FLAG_MULTILINE %d\n" % SRE_FLAG_MULTILINE)
 231     f.write("#define SRE_FLAG_DOTALL %d\n" % SRE_FLAG_DOTALL)
 232     f.write("#define SRE_FLAG_UNICODE %d\n" % SRE_FLAG_UNICODE)
 233     f.write("#define SRE_FLAG_VERBOSE %d\n" % SRE_FLAG_VERBOSE)
 234
 235     f.write("#define SRE_INFO_PREFIX %d\n" % SRE_INFO_PREFIX)
 236     f.write("#define SRE_INFO_LITERAL %d\n" % SRE_INFO_LITERAL)
 237     f.write("#define SRE_INFO_CHARSET %d\n" % SRE_INFO_CHARSET)
 238
 239     f.close()
 240     print "done"