"""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 re __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() 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). """ import os name = os.path.normcase(name) pat = os.path.normcase(pat) return fnmatchcase(name, pat) 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 def filter(names, pat): """Return the subset of the list NAMES that match PAT""" import os,posixpath 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. """ 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: stuff = pat[i:j].replace('\\','\\\\') i = j+1 if stuff[0] == '!': stuff = '^' + stuff[1:] elif stuff[0] == '^': stuff = '\\' + stuff res = '%s[%s]' % (res, stuff) else: res = res + re.escape(c) return res + '\Z(?ms)'