Python fnmatch模块详解：Shell风格文件名匹配实战

"""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"]

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):
  """Return the subset of the list 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.
  """

  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 r'(?s:%s)\Z' % res

def gen_find(filepat, top):
  """
  查找符合Shell正则匹配的目录树下的所有文件名
  :param filepat: shell正则
  :param top: 目录路径
  :return: 文件绝对路径生成器
  """
  for path, _, filenames in os.walk(top):
    for file in fnmatch.filter(filenames, filepat):
      yield os.path.join(path, file)

# 列出元组中所有的python文件
pyfiles = [py for py in ('restart.py', 'index.php', 'file.txt') if fnmatch(py, '*.py')]
# 字符串的 startswith() 和 endswith() 方法对于过滤一个目录的内容也是很有用的

# 这两个函数通常会被忽略的一个特性是在处理非文件名的字符串时候它们也是很有用的。 比如，假设你有一个街道地址的列表数据
address = [
  '5412 N CLARK ST',
  '1060 W ADDISON ST',
  '1039 W GRANVILLE AVE',
  '2122 N CLARK ST',
  '4802 N BROADWAY',
]
print([addr for addr in address if fnmatchcase(addr, '* ST')])

shell_match = 'Celery_?*.py'
print(translate(shell_match))
# 输出结果：(?s:Celery_..*\.py)\Z