summaryrefslogtreecommitdiffstats
path: root/Lib/encodings/__init__.py
blob: d72eae93281f2ab4cf7e8a624760e576477112d5 (plain)
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
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
""" Standard "encodings" Package

    Standard Python encoding modules are stored in this package
    directory.

    Codec modules must have names corresponding to normalized encoding
    names as defined in the normalize_encoding() function below, e.g.
    'utf-8' must be implemented by the module 'utf_8.py'.

    Each codec module must export the following interface:

    * getregentry() -> codecs.CodecInfo object
    The getregentry() API must a CodecInfo object with encoder, decoder,
    incrementalencoder, incrementaldecoder, streamwriter and streamreader
    atttributes which adhere to the Python Codec Interface Standard.

    In addition, a module may optionally also define the following
    APIs which are then used by the package's codec search function:

    * getaliases() -> sequence of encoding name strings to use as aliases

    Alias names returned by getaliases() must be normalized encoding
    names as defined by normalize_encoding().

Written by Marc-Andre Lemburg (mal@lemburg.com).

(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.

"""#"

import codecs
from . import aliases

_cache = {}
_unknown = '--unknown--'
_import_tail = ['*']
_aliases = aliases.aliases

class CodecRegistryError(LookupError, SystemError):
    pass

def normalize_encoding(encoding):

    """ Normalize an encoding name.

        Normalization works as follows: all non-alphanumeric
        characters except the dot used for Python package names are
        collapsed and replaced with a single underscore, e.g. '  -;#'
        becomes '_'. Leading and trailing underscores are removed.

        Note that encoding names should be ASCII only; if they do use
        non-ASCII characters, these must be Latin-1 compatible.

    """
    if isinstance(encoding, bytes):
        encoding = str(encoding, "ascii")
    chars = []
    punct = False
    for c in encoding:
        if c.isalnum() or c == '.':
            if punct and chars:
                chars.append('_')
            chars.append(c)
            punct = False
        else:
            punct = True
    return ''.join(chars)

def search_function(encoding):

    # Cache lookup
    entry = _cache.get(encoding, _unknown)
    if entry is not _unknown:
        return entry

    # Import the module:
    #
    # First try to find an alias for the normalized encoding
    # name and lookup the module using the aliased name, then try to
    # lookup the module using the standard import scheme, i.e. first
    # try in the encodings package, then at top-level.
    #
    norm_encoding = normalize_encoding(encoding)
    aliased_encoding = _aliases.get(norm_encoding) or \
                       _aliases.get(norm_encoding.replace('.', '_'))
    if aliased_encoding is not None:
        modnames = [aliased_encoding,
                    norm_encoding]
    else:
        modnames = [norm_encoding]
    for modname in modnames:
        if not modname or '.' in modname:
            continue
        try:
            # Import is absolute to prevent the possibly malicious import of a
            # module with side-effects that is not in the 'encodings' package.
            mod = __import__('encodings.' + modname, fromlist=_import_tail,
                             level=0)
        except ImportError:
            pass
        else:
            break
    else:
        mod = None

    try:
        getregentry = mod.getregentry
    except AttributeError:
        # Not a codec module
        mod = None

    if mod is None:
        # Cache misses
        _cache[encoding] = None
        return None

    # Now ask the module for the registry entry
    entry = getregentry()
    if not isinstance(entry, codecs.CodecInfo):
        if not 4 <= len(entry) <= 7:
            raise CodecRegistryError('module "%s" (%s) failed to register'
                                     % (mod.__name__, mod.__file__))
        if not hasattr(entry[0], '__call__') or \
           not hasattr(entry[1], '__call__') or \
           (entry[2] is not None and not hasattr(entry[2], '__call__')) or \
           (entry[3] is not None and not hasattr(entry[3], '__call__')) or \
           (len(entry) > 4 and entry[4] is not None and not hasattr(entry[4], '__call__')) or \
           (len(entry) > 5 and entry[5] is not None and not hasattr(entry[5], '__call__')):
            raise CodecRegistryError('incompatible codecs in module "%s" (%s)'
                                     % (mod.__name__, mod.__file__))
        if len(entry)<7 or entry[6] is None:
            entry += (None,)*(6-len(entry)) + (mod.__name__.split(".", 1)[1],)
        entry = codecs.CodecInfo(*entry)

    # Cache the codec registry entry
    _cache[encoding] = entry

    # Register its aliases (without overwriting previously registered
    # aliases)
    try:
        codecaliases = mod.getaliases()
    except AttributeError:
        pass
    else:
        for alias in codecaliases:
            if alias not in _aliases:
                _aliases[alias] = modname

    # Return the registry entry
    return entry

# Register the search_function in the Python codec registry
codecs.register(search_function)