rustpython-pylib 0.5.0

A subset of the Python standard library for use with RustPython
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113

import os
import re

_default_seps = os.sep + str(os.altsep) * bool(os.altsep)


class Translator:
    """
    >>> Translator('xyz')
    Traceback (most recent call last):
    ...
    AssertionError: Invalid separators

    >>> Translator('')
    Traceback (most recent call last):
    ...
    AssertionError: Invalid separators
    """

    seps: str

    def __init__(self, seps: str = _default_seps):
        assert seps and set(seps) <= set(_default_seps), "Invalid separators"
        self.seps = seps

    def translate(self, pattern):
        """
        Given a glob pattern, produce a regex that matches it.
        """
        return self.extend(self.match_dirs(self.translate_core(pattern)))

    def extend(self, pattern):
        r"""
        Extend regex for pattern-wide concerns.

        Apply '(?s:)' to create a non-matching group that
        matches newlines (valid on Unix).

        Append '\z' to imply fullmatch even when match is used.
        """
        return rf'(?s:{pattern})\z'

    def match_dirs(self, pattern):
        """
        Ensure that zipfile.Path directory names are matched.

        zipfile.Path directory names always end in a slash.
        """
        return rf'{pattern}[/]?'

    def translate_core(self, pattern):
        r"""
        Given a glob pattern, produce a regex that matches it.

        >>> t = Translator()
        >>> t.translate_core('*.txt').replace('\\\\', '')
        '[^/]*\\.txt'
        >>> t.translate_core('a?txt')
        'a[^/]txt'
        >>> t.translate_core('**/*').replace('\\\\', '')
        '.*/[^/][^/]*'
        """
        self.restrict_rglob(pattern)
        return ''.join(map(self.replace, separate(self.star_not_empty(pattern))))

    def replace(self, match):
        """
        Perform the replacements for a match from :func:`separate`.
        """
        return match.group('set') or (
            re.escape(match.group(0))
            .replace('\\*\\*', r'.*')
            .replace('\\*', rf'[^{re.escape(self.seps)}]*')
            .replace('\\?', r'[^/]')
        )

    def restrict_rglob(self, pattern):
        """
        Raise ValueError if ** appears in anything but a full path segment.

        >>> Translator().translate('**foo')
        Traceback (most recent call last):
        ...
        ValueError: ** must appear alone in a path segment
        """
        seps_pattern = rf'[{re.escape(self.seps)}]+'
        segments = re.split(seps_pattern, pattern)
        if any('**' in segment and segment != '**' for segment in segments):
            raise ValueError("** must appear alone in a path segment")

    def star_not_empty(self, pattern):
        """
        Ensure that * will not match an empty segment.
        """

        def handle_segment(match):
            segment = match.group(0)
            return '?*' if segment == '*' else segment

        not_seps_pattern = rf'[^{re.escape(self.seps)}]+'
        return re.sub(not_seps_pattern, handle_segment, pattern)


def separate(pattern):
    """
    Separate out character sets to avoid translating their contents.

    >>> [m.group(0) for m in separate('*.txt')]
    ['*.txt']
    >>> [m.group(0) for m in separate('a[?]txt')]
    ['a', '[?]', 'txt']
    """
    return re.finditer(r'([^\[]+)|(?P<set>[\[].*?[\]])|([\[][^\]]*$)', pattern)