mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-11-25 21:11:09 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 10

Change normalize_encodings() to avoid using .translate() or depending on

Browse source 
the string type.  It will always return a Unicode string.  The algoritm's
specification is unchanged.
This commit is contained in:
Guido van Rossum 2007-06-07 21:43:46 +00:00
parent c3b6ac796f
commit ad5b9de288
1 changed files with 11 additions and 14 deletions
Download patch file Download diff file Expand all files Collapse all files

25
Lib/encodings/__init__.py
View file

@ -34,12 +34,6 @@ from . import aliases
_cache = {} _cache = {}
_unknown = '--unknown--' _unknown = '--unknown--'
_import_tail = ['*'] _import_tail = ['*']
_norm_encoding_map = (' . '
'0123456789 ABCDEFGHIJKLMNOPQRSTUVWXYZ '
' abcdefghijklmnopqrstuvwxyz '
' '
' '
' ')
_aliases = aliases.aliases _aliases = aliases.aliases
class CodecRegistryError(LookupError, SystemError): class CodecRegistryError(LookupError, SystemError):
@ -58,14 +52,17 @@ def normalize_encoding(encoding):
non-ASCII characters, these must be Latin-1 compatible. non-ASCII characters, these must be Latin-1 compatible.
""" """
# Make sure we have an 8-bit string, because .translate() works chars = []
# differently for Unicode strings. punct = False
if isinstance(encoding, str): for c in encoding:
# Note that .encode('latin-1') does *not* use the codec if c.isalnum() or c == '.':
# registry, so this call doesn't recurse. (See unicodeobject.c if punct and chars:
# PyUnicode_AsEncodedString() for details) chars.append('_')
encoding = encoding.encode('latin-1') chars.append(c)
return '_'.join(encoding.translate(_norm_encoding_map).split()) punct = False
else:
punct = True
return ''.join(chars)
def search_function(encoding): def search_function(encoding):