| 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 __init__.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 = 20230612 |
| 17 |
|
| 18 |
from _sre import MAXREPEAT, MAXGROUPS # noqa: F401 |
| 19 |
|
| 20 |
# SRE standard exception (access as sre.error) |
| 21 |
# should this really be here? |
| 22 |
|
| 23 |
class PatternError(Exception): |
| 24 |
"""Exception raised for invalid regular expressions. |
| 25 |
|
| 26 |
Attributes: |
| 27 |
|
| 28 |
msg: The unformatted error message |
| 29 |
pattern: The regular expression pattern |
| 30 |
pos: The index in the pattern where compilation failed (may be None) |
| 31 |
lineno: The line corresponding to pos (may be None) |
| 32 |
colno: The column corresponding to pos (may be None) |
| 33 |
""" |
| 34 |
|
| 35 |
__module__ = 're' |
| 36 |
|
| 37 |
def __init__(self, msg, pattern=None, pos=None): |
| 38 |
self.msg = msg |
| 39 |
self.pattern = pattern |
| 40 |
self.pos = pos |
| 41 |
if pattern is not None and pos is not None: |
| 42 |
msg = '%s at position %d' % (msg, pos) |
| 43 |
if isinstance(pattern, str): |
| 44 |
newline = '\n' |
| 45 |
else: |
| 46 |
newline = b'\n' |
| 47 |
self.lineno = pattern.count(newline, 0, pos) + 1 |
| 48 |
self.colno = pos - pattern.rfind(newline, 0, pos) |
| 49 |
if newline in pattern: |
| 50 |
msg = '%s (line %d, column %d)' % (msg, self.lineno, self.colno) |
| 51 |
else: |
| 52 |
self.lineno = self.colno = None |
| 53 |
super().__init__(msg) |
| 54 |
|
| 55 |
|
| 56 |
# Backward compatibility after renaming in 3.13 |
| 57 |
error = PatternError |
| 58 |
|
| 59 |
class _NamedIntConstant(int): |
| 60 |
def __new__(cls, value, name): |
| 61 |
self = super(_NamedIntConstant, cls).__new__(cls, value) |
| 62 |
self.name = name |
| 63 |
return self |
| 64 |
|
| 65 |
def __repr__(self): |
| 66 |
return self.name |
| 67 |
|
| 68 |
__reduce__ = None |
| 69 |
|
| 70 |
MAXREPEAT = _NamedIntConstant(MAXREPEAT, 'MAXREPEAT') |
| 71 |
|
| 72 |
def _makecodes(*names): |
| 73 |
items = [_NamedIntConstant(i, name) for i, name in enumerate(names)] |
| 74 |
globals().update({item.name: item for item in items}) |
| 75 |
return items |
| 76 |
|
| 77 |
# operators |
| 78 |
OPCODES = _makecodes( |
| 79 |
# failure=0 success=1 (just because it looks better that way :-) |
| 80 |
'FAILURE', 'SUCCESS', |
| 81 |
|
| 82 |
'ANY', 'ANY_ALL', |
| 83 |
'ASSERT', 'ASSERT_NOT', |
| 84 |
'AT', |
| 85 |
'BRANCH', |
| 86 |
'CATEGORY', |
| 87 |
'CHARSET', 'BIGCHARSET', |
| 88 |
'GROUPREF', 'GROUPREF_EXISTS', |
| 89 |
'IN', |
| 90 |
'INFO', |
| 91 |
'JUMP', |
| 92 |
'LITERAL', |
| 93 |
'MARK', |
| 94 |
'MAX_UNTIL', |
| 95 |
'MIN_UNTIL', |
| 96 |
'NOT_LITERAL', |
| 97 |
'NEGATE', |
| 98 |
'RANGE', |
| 99 |
'REPEAT', |
| 100 |
'REPEAT_ONE', |
| 101 |
'SUBPATTERN', |
| 102 |
'MIN_REPEAT_ONE', |
| 103 |
'ATOMIC_GROUP', |
| 104 |
'POSSESSIVE_REPEAT', |
| 105 |
'POSSESSIVE_REPEAT_ONE', |
| 106 |
|
| 107 |
'GROUPREF_IGNORE', |
| 108 |
'IN_IGNORE', |
| 109 |
'LITERAL_IGNORE', |
| 110 |
'NOT_LITERAL_IGNORE', |
| 111 |
|
| 112 |
'GROUPREF_LOC_IGNORE', |
| 113 |
'IN_LOC_IGNORE', |
| 114 |
'LITERAL_LOC_IGNORE', |
| 115 |
'NOT_LITERAL_LOC_IGNORE', |
| 116 |
|
| 117 |
'GROUPREF_UNI_IGNORE', |
| 118 |
'IN_UNI_IGNORE', |
| 119 |
'LITERAL_UNI_IGNORE', |
| 120 |
'NOT_LITERAL_UNI_IGNORE', |
| 121 |
'RANGE_UNI_IGNORE', |
| 122 |
|
| 123 |
# The following opcodes are only occurred in the parser output, |
| 124 |
# but not in the compiled code. |
| 125 |
'MIN_REPEAT', 'MAX_REPEAT', |
| 126 |
) |
| 127 |
del OPCODES[-2:] # remove MIN_REPEAT and MAX_REPEAT |
| 128 |
|
| 129 |
# positions |
| 130 |
ATCODES = _makecodes( |
| 131 |
'AT_BEGINNING', 'AT_BEGINNING_LINE', 'AT_BEGINNING_STRING', |
| 132 |
'AT_BOUNDARY', 'AT_NON_BOUNDARY', |
| 133 |
'AT_END', 'AT_END_LINE', 'AT_END_STRING', |
| 134 |
|
| 135 |
'AT_LOC_BOUNDARY', 'AT_LOC_NON_BOUNDARY', |
| 136 |
|
| 137 |
'AT_UNI_BOUNDARY', 'AT_UNI_NON_BOUNDARY', |
| 138 |
) |
| 139 |
|
| 140 |
# categories |
| 141 |
CHCODES = _makecodes( |
| 142 |
'CATEGORY_DIGIT', 'CATEGORY_NOT_DIGIT', |
| 143 |
'CATEGORY_SPACE', 'CATEGORY_NOT_SPACE', |
| 144 |
'CATEGORY_WORD', 'CATEGORY_NOT_WORD', |
| 145 |
'CATEGORY_LINEBREAK', 'CATEGORY_NOT_LINEBREAK', |
| 146 |
|
| 147 |
'CATEGORY_LOC_WORD', 'CATEGORY_LOC_NOT_WORD', |
| 148 |
|
| 149 |
'CATEGORY_UNI_DIGIT', 'CATEGORY_UNI_NOT_DIGIT', |
| 150 |
'CATEGORY_UNI_SPACE', 'CATEGORY_UNI_NOT_SPACE', |
| 151 |
'CATEGORY_UNI_WORD', 'CATEGORY_UNI_NOT_WORD', |
| 152 |
'CATEGORY_UNI_LINEBREAK', 'CATEGORY_UNI_NOT_LINEBREAK', |
| 153 |
) |
| 154 |
|
| 155 |
|
| 156 |
# replacement operations for "ignore case" mode |
| 157 |
OP_IGNORE = { |
| 158 |
LITERAL: LITERAL_IGNORE, |
| 159 |
NOT_LITERAL: NOT_LITERAL_IGNORE, |
| 160 |
} |
| 161 |
|
| 162 |
OP_LOCALE_IGNORE = { |
| 163 |
LITERAL: LITERAL_LOC_IGNORE, |
| 164 |
NOT_LITERAL: NOT_LITERAL_LOC_IGNORE, |
| 165 |
} |
| 166 |
|
| 167 |
OP_UNICODE_IGNORE = { |
| 168 |
LITERAL: LITERAL_UNI_IGNORE, |
| 169 |
NOT_LITERAL: NOT_LITERAL_UNI_IGNORE, |
| 170 |
} |
| 171 |
|
| 172 |
AT_MULTILINE = { |
| 173 |
AT_BEGINNING: AT_BEGINNING_LINE, |
| 174 |
AT_END: AT_END_LINE |
| 175 |
} |
| 176 |
|
| 177 |
AT_LOCALE = { |
| 178 |
AT_BOUNDARY: AT_LOC_BOUNDARY, |
| 179 |
AT_NON_BOUNDARY: AT_LOC_NON_BOUNDARY |
| 180 |
} |
| 181 |
|
| 182 |
AT_UNICODE = { |
| 183 |
AT_BOUNDARY: AT_UNI_BOUNDARY, |
| 184 |
AT_NON_BOUNDARY: AT_UNI_NON_BOUNDARY |
| 185 |
} |
| 186 |
|
| 187 |
CH_LOCALE = { |
| 188 |
CATEGORY_DIGIT: CATEGORY_DIGIT, |
| 189 |
CATEGORY_NOT_DIGIT: CATEGORY_NOT_DIGIT, |
| 190 |
CATEGORY_SPACE: CATEGORY_SPACE, |
| 191 |
CATEGORY_NOT_SPACE: CATEGORY_NOT_SPACE, |
| 192 |
CATEGORY_WORD: CATEGORY_LOC_WORD, |
| 193 |
CATEGORY_NOT_WORD: CATEGORY_LOC_NOT_WORD, |
| 194 |
CATEGORY_LINEBREAK: CATEGORY_LINEBREAK, |
| 195 |
CATEGORY_NOT_LINEBREAK: CATEGORY_NOT_LINEBREAK |
| 196 |
} |
| 197 |
|
| 198 |
CH_UNICODE = { |
| 199 |
CATEGORY_DIGIT: CATEGORY_UNI_DIGIT, |
| 200 |
CATEGORY_NOT_DIGIT: CATEGORY_UNI_NOT_DIGIT, |
| 201 |
CATEGORY_SPACE: CATEGORY_UNI_SPACE, |
| 202 |
CATEGORY_NOT_SPACE: CATEGORY_UNI_NOT_SPACE, |
| 203 |
CATEGORY_WORD: CATEGORY_UNI_WORD, |
| 204 |
CATEGORY_NOT_WORD: CATEGORY_UNI_NOT_WORD, |
| 205 |
CATEGORY_LINEBREAK: CATEGORY_UNI_LINEBREAK, |
| 206 |
CATEGORY_NOT_LINEBREAK: CATEGORY_UNI_NOT_LINEBREAK |
| 207 |
} |
| 208 |
|
| 209 |
CH_NEGATE = dict(zip(CHCODES[::2] + CHCODES[1::2], CHCODES[1::2] + CHCODES[::2])) |
| 210 |
|
| 211 |
# flags |
| 212 |
SRE_FLAG_IGNORECASE = 2 # case insensitive |
| 213 |
SRE_FLAG_LOCALE = 4 # honour system locale |
| 214 |
SRE_FLAG_MULTILINE = 8 # treat target as multiline string |
| 215 |
SRE_FLAG_DOTALL = 16 # treat target as a single string |
| 216 |
SRE_FLAG_UNICODE = 32 # use unicode "locale" |
| 217 |
SRE_FLAG_VERBOSE = 64 # ignore whitespace and comments |
| 218 |
SRE_FLAG_DEBUG = 128 # debugging |
| 219 |
SRE_FLAG_ASCII = 256 # use ascii "locale" |
| 220 |
|
| 221 |
# flags for INFO primitive |
| 222 |
SRE_INFO_PREFIX = 1 # has prefix |
| 223 |
SRE_INFO_LITERAL = 2 # entire pattern is literal (given by prefix) |
| 224 |
SRE_INFO_CHARSET = 4 # pattern starts with character from given set |