mirror of
https://github.com/python/cpython.git
synced 2025-10-31 10:26:02 +00:00
145 lines
4.7 KiB
Python
145 lines
4.7 KiB
Python
""" 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() -> (encoder, decoder, stream_reader, stream_writer)
|
|
The getregentry() API must return callable objects 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, exceptions, types, aliases
|
|
|
|
_cache = {}
|
|
_unknown = '--unknown--'
|
|
_import_tail = ['*']
|
|
_norm_encoding_map = (' . '
|
|
'0123456789 ABCDEFGHIJKLMNOPQRSTUVWXYZ '
|
|
' abcdefghijklmnopqrstuvwxyz '
|
|
' '
|
|
' '
|
|
' ')
|
|
_aliases = aliases.aliases
|
|
|
|
class CodecRegistryError(exceptions.LookupError,
|
|
exceptions.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.
|
|
|
|
"""
|
|
# Make sure we have an 8-bit string, because .translate() works
|
|
# differently for Unicode strings.
|
|
if type(encoding) is types.UnicodeType:
|
|
# Note that .encode('latin-1') does *not* use the codec
|
|
# registry, so this call doesn't recurse. (See unicodeobject.c
|
|
# PyUnicode_AsEncodedString() for details)
|
|
encoding = encoding.encode('latin-1')
|
|
return '_'.join(encoding.translate(_norm_encoding_map).split())
|
|
|
|
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:
|
|
continue
|
|
try:
|
|
mod = __import__(modname,
|
|
globals(), locals(), _import_tail)
|
|
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 = tuple(getregentry())
|
|
if len(entry) != 4:
|
|
raise CodecRegistryError,\
|
|
'module "%s" (%s) failed to register' % \
|
|
(mod.__name__, mod.__file__)
|
|
for obj in entry:
|
|
if not callable(obj):
|
|
raise CodecRegistryError,\
|
|
'incompatible codecs in module "%s" (%s)' % \
|
|
(mod.__name__, mod.__file__)
|
|
|
|
# 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 not _aliases.has_key(alias):
|
|
_aliases[alias] = modname
|
|
|
|
# Return the registry entry
|
|
return entry
|
|
|
|
# Register the search_function in the Python codec registry
|
|
codecs.register(search_function)
|