1995-01-26 22:41:45 -04:00
|
|
|
"""Filename matching with shell patterns.
|
1992-01-12 19:29:29 -04:00
|
|
|
|
1995-01-26 22:41:45 -04:00
|
|
|
fnmatch(FILENAME, PATTERN) matches according to the local convention.
|
|
|
|
fnmatchcase(FILENAME, PATTERN) always takes case in account.
|
1992-01-12 19:29:29 -04:00
|
|
|
|
1995-01-26 22:41:45 -04:00
|
|
|
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.)
|
|
|
|
"""
|
2010-07-23 13:22:25 -03:00
|
|
|
import os
|
|
|
|
import posixpath
|
1997-10-22 18:00:49 -03:00
|
|
|
import re
|
|
|
|
|
2010-08-09 09:47:33 -03:00
|
|
|
__all__ = ["filter", "fnmatch", "fnmatchcase", "purge", "translate"]
|
|
|
|
|
|
|
|
_cache = {} # Maps text patterns to compiled regexen.
|
|
|
|
_cacheb = {} # Ditto for bytes patterns.
|
|
|
|
_MAXCACHE = 100 # Maximum size of caches.
|
|
|
|
|
|
|
|
|
|
|
|
def purge():
|
|
|
|
"""Clear the pattern cache."""
|
|
|
|
_cache.clear()
|
|
|
|
_cacheb.clear()
|
|
|
|
|
2010-07-23 13:22:25 -03:00
|
|
|
|
1991-01-01 14:11:14 -04:00
|
|
|
def fnmatch(name, pat):
|
2001-01-14 19:36:06 -04:00
|
|
|
"""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)
|
1995-01-26 22:41:45 -04:00
|
|
|
|
2010-08-09 09:47:33 -03:00
|
|
|
|
|
|
|
def _compile_pattern(pat):
|
|
|
|
cache = _cacheb if isinstance(pat, bytes) else _cache
|
|
|
|
regex = cache.get(pat)
|
|
|
|
if regex is None:
|
|
|
|
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)
|
|
|
|
if len(cache) >= _MAXCACHE:
|
|
|
|
cache.clear()
|
|
|
|
cache[pat] = regex = re.compile(res)
|
|
|
|
return regex.match
|
|
|
|
|
2010-07-23 13:22:25 -03:00
|
|
|
|
2001-06-06 03:24:38 -03:00
|
|
|
def filter(names, pat):
|
2010-07-23 13:22:25 -03:00
|
|
|
"""Return the subset of the list NAMES that match PAT."""
|
2008-10-02 15:55:37 -03:00
|
|
|
result = []
|
|
|
|
pat = os.path.normcase(pat)
|
2010-08-09 09:47:33 -03:00
|
|
|
match = _compile_pattern(pat)
|
2001-06-06 03:24:38 -03:00
|
|
|
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
|
|
|
|
|
2010-08-09 09:47:33 -03:00
|
|
|
|
1995-01-26 22:41:45 -04:00
|
|
|
def fnmatchcase(name, pat):
|
2001-01-14 19:36:06 -04:00
|
|
|
"""Test whether FILENAME matches PATTERN, including case.
|
|
|
|
|
|
|
|
This is a version of fnmatch() which doesn't case-normalize
|
|
|
|
its arguments.
|
|
|
|
"""
|
2010-08-09 09:47:33 -03:00
|
|
|
match = _compile_pattern(pat)
|
2008-10-02 15:55:37 -03:00
|
|
|
return match(name) is not None
|
1991-01-01 14:11:14 -04:00
|
|
|
|
2010-07-23 13:22:25 -03:00
|
|
|
|
1992-01-12 19:29:29 -04:00
|
|
|
def translate(pat):
|
2001-01-14 19:36:06 -04:00
|
|
|
"""Translate a shell PATTERN to a regular expression.
|
|
|
|
|
|
|
|
There is no way to quote meta-characters.
|
|
|
|
"""
|
|
|
|
|
|
|
|
i, n = 0, len(pat)
|
|
|
|
res = ''
|
|
|
|
while i < n:
|
|
|
|
c = pat[i]
|
|
|
|
i = i+1
|
|
|
|
if c == '*':
|
|
|
|
res = res + '.*'
|
|
|
|
elif c == '?':
|
|
|
|
res = res + '.'
|
|
|
|
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:
|
|
|
|
res = res + '\\['
|
|
|
|
else:
|
2001-03-21 14:05:48 -04:00
|
|
|
stuff = pat[i:j].replace('\\','\\\\')
|
2001-01-14 19:36:06 -04:00
|
|
|
i = j+1
|
|
|
|
if stuff[0] == '!':
|
2001-03-21 14:05:48 -04:00
|
|
|
stuff = '^' + stuff[1:]
|
|
|
|
elif stuff[0] == '^':
|
|
|
|
stuff = '\\' + stuff
|
|
|
|
res = '%s[%s]' % (res, stuff)
|
2001-01-14 19:36:06 -04:00
|
|
|
else:
|
|
|
|
res = res + re.escape(c)
|
2009-08-16 15:58:46 -03:00
|
|
|
return res + '\Z(?ms)'
|