1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
|
"""Filename matching with shell patterns.
fnmatch(FILENAME, PATTERN) matches according to the local convention.
fnmatchcase(FILENAME, PATTERN) always takes case in account.
The functions operate by translating the pattern into a regular
expression. They cache the compiled regular expressions for speed.
The function translate(PATTERN) returns a regular expression
corresponding to PATTERN. (It does not compile it.)
"""
import os
import posixpath
import re
import functools
__all__ = ["filter", "fnmatch", "fnmatchcase", "translate"]
# Build a thread-safe incrementing counter to help create unique regexp group
# names across calls.
from itertools import count
_nextgroupnum = count().__next__
del count
def fnmatch(name, pat):
"""Test whether FILENAME matches PATTERN.
Patterns are Unix shell style:
* matches everything
? matches any single character
[seq] matches any character in seq
[!seq] matches any char not in seq
An initial period in FILENAME is not special.
Both FILENAME and PATTERN are first case-normalized
if the operating system requires it.
If you don't want this, use fnmatchcase(FILENAME, PATTERN).
"""
name = os.path.normcase(name)
pat = os.path.normcase(pat)
return fnmatchcase(name, pat)
@functools.lru_cache(maxsize=256, typed=True)
def _compile_pattern(pat):
if isinstance(pat, bytes):
pat_str = str(pat, 'ISO-8859-1')
res_str = translate(pat_str)
res = bytes(res_str, 'ISO-8859-1')
else:
res = translate(pat)
return re.compile(res).match
def filter(names, pat):
"""Construct a list from those elements of the iterable NAMES that match PAT."""
result = []
pat = os.path.normcase(pat)
match = _compile_pattern(pat)
if os.path is posixpath:
# normcase on posix is NOP. Optimize it away from the loop.
for name in names:
if match(name):
result.append(name)
else:
for name in names:
if match(os.path.normcase(name)):
result.append(name)
return result
def fnmatchcase(name, pat):
"""Test whether FILENAME matches PATTERN, including case.
This is a version of fnmatch() which doesn't case-normalize
its arguments.
"""
match = _compile_pattern(pat)
return match(name) is not None
def translate(pat):
"""Translate a shell PATTERN to a regular expression.
There is no way to quote meta-characters.
"""
STAR = object()
res = []
add = res.append
i, n = 0, len(pat)
while i < n:
c = pat[i]
i = i+1
if c == '*':
# compress consecutive `*` into one
if (not res) or res[-1] is not STAR:
add(STAR)
elif c == '?':
add('.')
elif c == '[':
j = i
if j < n and pat[j] == '!':
j = j+1
if j < n and pat[j] == ']':
j = j+1
while j < n and pat[j] != ']':
j = j+1
if j >= n:
add('\\[')
else:
stuff = pat[i:j]
if '-' not in stuff:
stuff = stuff.replace('\\', r'\\')
else:
chunks = []
k = i+2 if pat[i] == '!' else i+1
while True:
k = pat.find('-', k, j)
if k < 0:
break
chunks.append(pat[i:k])
i = k+1
k = k+3
chunk = pat[i:j]
if chunk:
chunks.append(chunk)
else:
chunks[-1] += '-'
# Remove empty ranges -- invalid in RE.
for k in range(len(chunks)-1, 0, -1):
if chunks[k-1][-1] > chunks[k][0]:
chunks[k-1] = chunks[k-1][:-1] + chunks[k][1:]
del chunks[k]
# Escape backslashes and hyphens for set difference (--).
# Hyphens that create ranges shouldn't be escaped.
stuff = '-'.join(s.replace('\\', r'\\').replace('-', r'\-')
for s in chunks)
# Escape set operations (&&, ~~ and ||).
stuff = re.sub(r'([&~|])', r'\\\1', stuff)
i = j+1
if not stuff:
# Empty range: never match.
add('(?!)')
elif stuff == '!':
# Negated empty range: match any character.
add('.')
else:
if stuff[0] == '!':
stuff = '^' + stuff[1:]
elif stuff[0] in ('^', '['):
stuff = '\\' + stuff
add(f'[{stuff}]')
else:
add(re.escape(c))
assert i == n
# Deal with STARs.
inp = res
res = []
add = res.append
i, n = 0, len(inp)
# Fixed pieces at the start?
while i < n and inp[i] is not STAR:
add(inp[i])
i += 1
# Now deal with STAR fixed STAR fixed ...
# For an interior `STAR fixed` pairing, we want to do a minimal
# .*? match followed by `fixed`, with no possibility of backtracking.
# We can't spell that directly, but can trick it into working by matching
# .*?fixed
# in a lookahead assertion, save the matched part in a group, then
# consume that group via a backreference. If the overall match fails,
# the lookahead assertion won't try alternatives. So the translation is:
# (?=(?P<name>.*?fixed))(?P=name)
# Group names are created as needed: g0, g1, g2, ...
# The numbers are obtained from _nextgroupnum() to ensure they're unique
# across calls and across threads. This is because people rely on the
# undocumented ability to join multiple translate() results together via
# "|" to build large regexps matching "one of many" shell patterns.
while i < n:
assert inp[i] is STAR
i += 1
if i == n:
add(".*")
break
assert inp[i] is not STAR
fixed = []
while i < n and inp[i] is not STAR:
fixed.append(inp[i])
i += 1
fixed = "".join(fixed)
if i == n:
add(".*")
add(fixed)
else:
groupnum = _nextgroupnum()
add(f"(?=(?P<g{groupnum}>.*?{fixed}))(?P=g{groupnum})")
assert i == n
res = "".join(res)
return fr'(?s:{res})\Z'
|
