glob.py

"""Filename globbing utility."""

import os
import re
import fnmatch

__all__ = ["glob", "iglob"]

def glob(pathname):
    """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.

    """
    return list(iglob(pathname))

def iglob(pathname):
    """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.

    """
    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:
        yield from glob1(None, basename)
        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)
    else:
        dirs = [dirname]
    if has_magic(basename):
        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 = bytes(os.curdir, 'ASCII')
        else:
            dirname = os.curdir
    try:
        names = os.listdir(dirname)
    except OSError:
        return []
    if not _ishidden(pattern):
        names = [x for x in names if not _ishidden(x)]
    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 []


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 _ishidden(path):
    return path[0] in ('.', b'.'[0])

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