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 # 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 GROUPREF_EXISTS = "groupref_exists"

    46 IN = "in"

    47 IN_IGNORE = "in_ignore"

    48 INFO = "info"

    49 JUMP = "jump"

    50 LITERAL = "literal"

    51 LITERAL_IGNORE = "literal_ignore"

    52 MARK = "mark"

    53 MAX_REPEAT = "max_repeat"

    54 MAX_UNTIL = "max_until"

    55 MIN_REPEAT = "min_repeat"

    56 MIN_UNTIL = "min_until"

    57 NEGATE = "negate"

    58 NOT_LITERAL = "not_literal"

    59 NOT_LITERAL_IGNORE = "not_literal_ignore"

    60 RANGE = "range"

    61 REPEAT = "repeat"

    62 REPEAT_ONE = "repeat_one"

    63 SUBPATTERN = "subpattern"

    64 MIN_REPEAT_ONE = "min_repeat_one"

    65 

    66 # positions

    67 AT_BEGINNING = "at_beginning"

    68 AT_BEGINNING_LINE = "at_beginning_line"

    69 AT_BEGINNING_STRING = "at_beginning_string"

    70 AT_BOUNDARY = "at_boundary"

    71 AT_NON_BOUNDARY = "at_non_boundary"

    72 AT_END = "at_end"

    73 AT_END_LINE = "at_end_line"

    74 AT_END_STRING = "at_end_string"

    75 AT_LOC_BOUNDARY = "at_loc_boundary"

    76 AT_LOC_NON_BOUNDARY = "at_loc_non_boundary"

    77 AT_UNI_BOUNDARY = "at_uni_boundary"

    78 AT_UNI_NON_BOUNDARY = "at_uni_non_boundary"

    79 

    80 # categories

    81 CATEGORY_DIGIT = "category_digit"

    82 CATEGORY_NOT_DIGIT = "category_not_digit"

    83 CATEGORY_SPACE = "category_space"

    84 CATEGORY_NOT_SPACE = "category_not_space"

    85 CATEGORY_WORD = "category_word"

    86 CATEGORY_NOT_WORD = "category_not_word"

    87 CATEGORY_LINEBREAK = "category_linebreak"

    88 CATEGORY_NOT_LINEBREAK = "category_not_linebreak"

    89 CATEGORY_LOC_WORD = "category_loc_word"

    90 CATEGORY_LOC_NOT_WORD = "category_loc_not_word"

    91 CATEGORY_UNI_DIGIT = "category_uni_digit"

    92 CATEGORY_UNI_NOT_DIGIT = "category_uni_not_digit"

    93 CATEGORY_UNI_SPACE = "category_uni_space"

    94 CATEGORY_UNI_NOT_SPACE = "category_uni_not_space"

    95 CATEGORY_UNI_WORD = "category_uni_word"

    96 CATEGORY_UNI_NOT_WORD = "category_uni_not_word"

    97 CATEGORY_UNI_LINEBREAK = "category_uni_linebreak"

    98 CATEGORY_UNI_NOT_LINEBREAK = "category_uni_not_linebreak"

    99 

   100 OPCODES = [

   101 

   102     # failure=0 success=1 (just because it looks better that way :-)

   103     FAILURE, SUCCESS,

   104 

   105     ANY, ANY_ALL,

   106     ASSERT, ASSERT_NOT,

   107     AT,

   108     BRANCH,

   109     CALL,

   110     CATEGORY,

   111     CHARSET, BIGCHARSET,

   112     GROUPREF, GROUPREF_EXISTS, GROUPREF_IGNORE,

   113     IN, IN_IGNORE,

   114     INFO,

   115     JUMP,

   116     LITERAL, LITERAL_IGNORE,

   117     MARK,

   118     MAX_UNTIL,

   119     MIN_UNTIL,

   120     NOT_LITERAL, NOT_LITERAL_IGNORE,

   121     NEGATE,

   122     RANGE,

   123     REPEAT,

   124     REPEAT_ONE,

   125     SUBPATTERN,

   126     MIN_REPEAT_ONE

   127 

   128 ]

   129 

   130 ATCODES = [

   131     AT_BEGINNING, AT_BEGINNING_LINE, AT_BEGINNING_STRING, AT_BOUNDARY,

   132     AT_NON_BOUNDARY, AT_END, AT_END_LINE, AT_END_STRING,

   133     AT_LOC_BOUNDARY, AT_LOC_NON_BOUNDARY, AT_UNI_BOUNDARY,

   134     AT_UNI_NON_BOUNDARY

   135 ]

   136 

   137 CHCODES = [

   138     CATEGORY_DIGIT, CATEGORY_NOT_DIGIT, CATEGORY_SPACE,

   139     CATEGORY_NOT_SPACE, CATEGORY_WORD, CATEGORY_NOT_WORD,

   140     CATEGORY_LINEBREAK, CATEGORY_NOT_LINEBREAK, CATEGORY_LOC_WORD,

   141     CATEGORY_LOC_NOT_WORD, CATEGORY_UNI_DIGIT, CATEGORY_UNI_NOT_DIGIT,

   142     CATEGORY_UNI_SPACE, CATEGORY_UNI_NOT_SPACE, CATEGORY_UNI_WORD,

   143     CATEGORY_UNI_NOT_WORD, CATEGORY_UNI_LINEBREAK,

   144     CATEGORY_UNI_NOT_LINEBREAK

   145 ]

   146 

   147 def makedict(list):

   148     d = {}

   149     i = 0

   150     for item in list:

   151         d[item] = i

   152         i = i + 1

   153     return d

   154 

   155 OPCODES = makedict(OPCODES)

   156 ATCODES = makedict(ATCODES)

   157 CHCODES = makedict(CHCODES)

   158 

   159 # replacement operations for "ignore case" mode

   160 OP_IGNORE = {

   161     GROUPREF: GROUPREF_IGNORE,

   162     IN: IN_IGNORE,

   163     LITERAL: LITERAL_IGNORE,

   164     NOT_LITERAL: NOT_LITERAL_IGNORE

   165 }

   166 

   167 AT_MULTILINE = {

   168     AT_BEGINNING: AT_BEGINNING_LINE,

   169     AT_END: AT_END_LINE

   170 }

   171 

   172 AT_LOCALE = {

   173     AT_BOUNDARY: AT_LOC_BOUNDARY,

   174     AT_NON_BOUNDARY: AT_LOC_NON_BOUNDARY

   175 }

   176 

   177 AT_UNICODE = {

   178     AT_BOUNDARY: AT_UNI_BOUNDARY,

   179     AT_NON_BOUNDARY: AT_UNI_NON_BOUNDARY

   180 }

   181 

   182 CH_LOCALE = {

   183     CATEGORY_DIGIT: CATEGORY_DIGIT,

   184     CATEGORY_NOT_DIGIT: CATEGORY_NOT_DIGIT,

   185     CATEGORY_SPACE: CATEGORY_SPACE,

   186     CATEGORY_NOT_SPACE: CATEGORY_NOT_SPACE,

   187     CATEGORY_WORD: CATEGORY_LOC_WORD,

   188     CATEGORY_NOT_WORD: CATEGORY_LOC_NOT_WORD,

   189     CATEGORY_LINEBREAK: CATEGORY_LINEBREAK,

   190     CATEGORY_NOT_LINEBREAK: CATEGORY_NOT_LINEBREAK

   191 }

   192 

   193 CH_UNICODE = {

   194     CATEGORY_DIGIT: CATEGORY_UNI_DIGIT,

   195     CATEGORY_NOT_DIGIT: CATEGORY_UNI_NOT_DIGIT,

   196     CATEGORY_SPACE: CATEGORY_UNI_SPACE,

   197     CATEGORY_NOT_SPACE: CATEGORY_UNI_NOT_SPACE,

   198     CATEGORY_WORD: CATEGORY_UNI_WORD,

   199     CATEGORY_NOT_WORD: CATEGORY_UNI_NOT_WORD,

   200     CATEGORY_LINEBREAK: CATEGORY_UNI_LINEBREAK,

   201     CATEGORY_NOT_LINEBREAK: CATEGORY_UNI_NOT_LINEBREAK

   202 }

   203 

   204 # flags

   205 SRE_FLAG_TEMPLATE = 1 # template mode (disable backtracking)

   206 SRE_FLAG_IGNORECASE = 2 # case insensitive

   207 SRE_FLAG_LOCALE = 4 # honour system locale

   208 SRE_FLAG_MULTILINE = 8 # treat target as multiline string

   209 SRE_FLAG_DOTALL = 16 # treat target as a single string

   210 SRE_FLAG_UNICODE = 32 # use unicode locale

   211 SRE_FLAG_VERBOSE = 64 # ignore whitespace and comments

   212 SRE_FLAG_DEBUG = 128 # debugging

   213 

   214 # flags for INFO primitive

   215 SRE_INFO_PREFIX = 1 # has prefix

   216 SRE_INFO_LITERAL = 2 # entire pattern is literal (given by prefix)

   217 SRE_INFO_CHARSET = 4 # pattern starts with character from given set

   218 

   219 if __name__ == "__main__":

   220     def dump(f, d, prefix):

   221         items = d.items()

   222         items.sort(key=lambda a: a[1])

   223         for k, v in items:

   224             f.write("#define %s_%s %s\n" % (prefix, k.upper(), v))

   225     f = open("sre_constants.h", "w")

   226     f.write("""\

   227 /*

   228  * Secret Labs' Regular Expression Engine

   229  *

   230  * regular expression matching engine

   231  *

   232  * NOTE: This file is generated by sre_constants.py.  If you need

   233  * to change anything in here, edit sre_constants.py and run it.

   234  *

   235  * Copyright (c) 1997-2001 by Secret Labs AB.  All rights reserved.

   236  *

   237  * See the _sre.c file for information on usage and redistribution.

   238  */

   239 

   240 """)

   241 

   242     f.write("#define SRE_MAGIC %d\n" % MAGIC)

   243 

   244     dump(f, OPCODES, "SRE_OP")

   245     dump(f, ATCODES, "SRE")

   246     dump(f, CHCODES, "SRE")

   247 

   248     f.write("#define SRE_FLAG_TEMPLATE %d\n" % SRE_FLAG_TEMPLATE)

   249     f.write("#define SRE_FLAG_IGNORECASE %d\n" % SRE_FLAG_IGNORECASE)

   250     f.write("#define SRE_FLAG_LOCALE %d\n" % SRE_FLAG_LOCALE)

   251     f.write("#define SRE_FLAG_MULTILINE %d\n" % SRE_FLAG_MULTILINE)

   252     f.write("#define SRE_FLAG_DOTALL %d\n" % SRE_FLAG_DOTALL)

   253     f.write("#define SRE_FLAG_UNICODE %d\n" % SRE_FLAG_UNICODE)

   254     f.write("#define SRE_FLAG_VERBOSE %d\n" % SRE_FLAG_VERBOSE)

   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"