Python glob but against a list of strings rather than the filesystem

Question

I want to be able to match a pattern in glob format to a list of strings, rather than to actual files in the filesystem. Is there any way to do this, or convert a glob

Answer 1

Here is a glob that can deal with escaped punctuation. It does not stop on path separators. I'm posting it here because it matches the title of the question.

To use on a list:

rex = glob_to_re(glob_pattern)
rex = r'(?s:%s)\Z' % rex # Can match newline; match whole string.
rex = re.compile(rex)
matches = [name for name in names if rex.match(name)]

Here's the code:

import re as _re

class GlobSyntaxError(SyntaxError):
    pass

def glob_to_re(pattern):
    r"""
    Given pattern, a unicode string, return the equivalent regular expression.
    Any special character * ? [ ! - ] \ can be escaped by preceding it with 
    backslash ('\') in the pattern.  Forward-slashes ('/') and escaped 
    backslashes ('\\') are treated as ordinary characters, not boundaries.

    Here is the language glob_to_re understands.
    Earlier alternatives within rules have precedence.  
        pattern = item*
        item    = '*'  |  '?'  |  '[!' set ']'  |  '[' set ']'  |  literal
        set     = element element*
        element = literal '-' literal  |  literal
        literal = '\' char  |  char other than \  [  ] and sometimes -
    glob_to_re does not understand "{a,b...}".
    """
    # (Note: the docstring above is r""" ... """ to preserve backslashes.)
    def expect_char(i, context):
        if i >= len(pattern):
            s = "Unfinished %s: %r, position %d." % (context, pattern, i)
            raise GlobSyntaxError(s)
    
    def literal_to_re(i, context="pattern", bad="[]"):
        if pattern[i] == '\\':
            i += 1
            expect_char(i, "backslashed literal")
        else:
            if pattern[i] in bad:
                s = "Unexpected %r in %s: %r, position %d." \
                    % (pattern[i], context, pattern, i)
                raise GlobSyntaxError(s)
        return _re.escape(pattern[i]), i + 1

    def set_to_re(i):
        assert pattern[i] == '['
        set_re = "["
        i += 1
        try:
            if pattern[i] == '!':
                set_re += '^'
                i += 1
            while True:
                lit_re, i = literal_to_re(i, "character set", bad="[-]")
                set_re += lit_re
                if pattern[i] == '-':
                    set_re += '-'
                    i += 1
                    expect_char(i, "character set range")
                    lit_re, i = literal_to_re(i, "character set range", bad="[-]")
                    set_re += lit_re
                if pattern[i] == ']':
                    return set_re + ']', i + 1
                
        except IndexError:
            expect_char(i, "character set")  # Trigger "unfinished" error.

    i = 0
    re_pat = ""
    while i < len(pattern):
        if pattern[i] == '*':
            re_pat += ".*"
            i += 1
        elif pattern[i] == '?':
            re_pat += "."
            i += 1
        elif pattern[i] == '[':
            set_re, i = set_to_re(i)
            re_pat += set_re
        else:
            lit_re, i = literal_to_re(i)
            re_pat += lit_re
    return re_pat