cpython/Lib/encodings/__init__.py

123 lines
3.6 KiB
Python
Raw Normal View History

2000-03-10 19:17:24 -04:00
""" 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'.
2000-03-10 19:17:24 -04:00
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().
2000-03-10 19:17:24 -04:00
Written by Marc-Andre Lemburg (mal@lemburg.com).
(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
"""#"
import codecs, exceptions, re
2000-03-10 19:17:24 -04:00
_cache = {}
_unknown = '--unknown--'
_import_tail = ['*']
_norm_encoding_RE = re.compile('[^a-zA-Z0-9.]')
2000-03-10 19:17:24 -04:00
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 '_'.
"""
return '_'.join(_norm_encoding_RE.split(encoding))
2000-03-10 19:17:24 -04:00
def search_function(encoding):
2002-08-08 17:19:19 -03:00
2000-03-10 19:17:24 -04:00
# Cache lookup
entry = _cache.get(encoding, _unknown)
if entry is not _unknown:
2000-03-10 19:17:24 -04:00
return entry
# Import the module:
#
# First look in the encodings package, then try to lookup the
# encoding in the aliases mapping and retry the import using the
# default import module lookup scheme with the alias name.
#
modname = normalize_encoding(encoding)
2000-03-10 19:17:24 -04:00
try:
mod = __import__('encodings.' + modname,
globals(), locals(), _import_tail)
except ImportError:
import aliases
modname = (aliases.aliases.get(modname) or
aliases.aliases.get(modname.replace('.', '_')) or
modname)
try:
mod = __import__(modname, globals(), locals(), _import_tail)
except ImportError:
mod = None
try:
getregentry = mod.getregentry
except AttributeError:
# Not a codec module
mod = None
if mod is None:
# Cache misses
2000-03-10 19:17:24 -04:00
_cache[encoding] = None
2002-08-08 17:19:19 -03:00
return None
2000-03-10 19:17:24 -04:00
# Now ask the module for the registry entry
entry = tuple(getregentry())
2000-03-10 19:17:24 -04:00
if len(entry) != 4:
raise CodecRegistryError,\
'module "%s" (%s) failed to register' % \
(mod.__name__, mod.__file__)
2000-03-10 19:17:24 -04:00
for obj in entry:
if not callable(obj):
raise CodecRegistryError,\
'incompatible codecs in module "%s" (%s)' % \
(mod.__name__, mod.__file__)
2000-03-10 19:17:24 -04:00
# Cache the codec registry entry
2000-03-10 19:17:24 -04:00
_cache[encoding] = entry
# Register its aliases (without overwriting previously registered
# aliases)
2000-03-10 19:17:24 -04:00
try:
codecaliases = mod.getaliases()
except AttributeError:
pass
else:
import aliases
2000-03-10 19:17:24 -04:00
for alias in codecaliases:
if not aliases.aliases.has_key(alias):
aliases.aliases[alias] = modname
# Return the registry entry
2000-03-10 19:17:24 -04:00
return entry
# Register the search_function in the Python codec registry
codecs.register(search_function)