blob: 9d7cbc5da68da8605d271b9314befb206b87bca6 [file] [log] [blame]
"""
Filename globbing utility. Mostly a copy of `glob` from Python 3.5.
Changes include:
* `yield from` and PEP3102 `*` removed.
* Hidden files are not ignored.
"""
import os
import re
import fnmatch
__all__ = ["glob", "iglob", "escape"]
def glob(pathname, recursive=False):
"""Return a list of paths matching a pathname pattern.
The pattern may contain simple shell-style wildcards a la
fnmatch. However, unlike fnmatch, filenames starting with a
dot are special cases that are not matched by '*' and '?'
patterns.
If recursive is true, the pattern '**' will match any files and
zero or more directories and subdirectories.
"""
return list(iglob(pathname, recursive=recursive))
def iglob(pathname, recursive=False):
"""Return an iterator which yields the paths matching a pathname pattern.
The pattern may contain simple shell-style wildcards a la
fnmatch. However, unlike fnmatch, filenames starting with a
dot are special cases that are not matched by '*' and '?'
patterns.
If recursive is true, the pattern '**' will match any files and
zero or more directories and subdirectories.
"""
it = _iglob(pathname, recursive)
if recursive and _isrecursive(pathname):
s = next(it) # skip empty string
assert not s
return it
def _iglob(pathname, recursive):
dirname, basename = os.path.split(pathname)
if not has_magic(pathname):
if basename:
if os.path.lexists(pathname):
yield pathname
else:
# Patterns ending with a slash should match only directories
if os.path.isdir(dirname):
yield pathname
return
if not dirname:
if recursive and _isrecursive(basename):
for x in glob2(dirname, basename):
yield x
else:
for x in glob1(dirname, basename):
yield x
return
# `os.path.split()` returns the argument itself as a dirname if it is a
# drive or UNC path. Prevent an infinite recursion if a drive or UNC path
# contains magic characters (i.e. r'\\?\C:').
if dirname != pathname and has_magic(dirname):
dirs = _iglob(dirname, recursive)
else:
dirs = [dirname]
if has_magic(basename):
if recursive and _isrecursive(basename):
glob_in_dir = glob2
else:
glob_in_dir = glob1
else:
glob_in_dir = glob0
for dirname in dirs:
for name in glob_in_dir(dirname, basename):
yield os.path.join(dirname, name)
# These 2 helper functions non-recursively glob inside a literal directory.
# They return a list of basenames. `glob1` accepts a pattern while `glob0`
# takes a literal basename (so it only has to check for its existence).
def glob1(dirname, pattern):
if not dirname:
if isinstance(pattern, bytes):
dirname = os.curdir.encode('ASCII')
else:
dirname = os.curdir
try:
names = os.listdir(dirname)
except OSError:
return []
return fnmatch.filter(names, pattern)
def glob0(dirname, basename):
if not basename:
# `os.path.split()` returns an empty basename for paths ending with a
# directory separator. 'q*x/' should match only directories.
if os.path.isdir(dirname):
return [basename]
else:
if os.path.lexists(os.path.join(dirname, basename)):
return [basename]
return []
# This helper function recursively yields relative pathnames inside a literal
# directory.
def glob2(dirname, pattern):
assert _isrecursive(pattern)
yield pattern[:0]
for x in _rlistdir(dirname):
yield x
# Recursively yields relative pathnames inside a literal directory.
def _rlistdir(dirname):
if not dirname:
if isinstance(dirname, bytes):
dirname = os.curdir.encode('ASCII')
else:
dirname = os.curdir
try:
names = os.listdir(dirname)
except os.error:
return
for x in names:
yield x
path = os.path.join(dirname, x) if dirname else x
for y in _rlistdir(path):
yield os.path.join(x, y)
magic_check = re.compile('([*?[])')
magic_check_bytes = re.compile(b'([*?[])')
def has_magic(s):
if isinstance(s, bytes):
match = magic_check_bytes.search(s)
else:
match = magic_check.search(s)
return match is not None
def _isrecursive(pattern):
if isinstance(pattern, bytes):
return pattern == b'**'
else:
return pattern == '**'
def escape(pathname):
"""Escape all special characters.
"""
# Escaping is done by wrapping any of "*?[" between square brackets.
# Metacharacters do not work in the drive part and shouldn't be escaped.
drive, pathname = os.path.splitdrive(pathname)
if isinstance(pathname, bytes):
pathname = magic_check_bytes.sub(br'[\1]', pathname)
else:
pathname = magic_check.sub(r'[\1]', pathname)
return drive + pathname