Make the unicode-escape and the UTF-16 codecs handle surrogates

correctly and thus roundtrip-safe.

Some minor cleanups of the code.

Added tests for the roundtrip-safety.
This commit is contained in:
Marc-André Lemburg 2001-07-20 17:39:11 +00:00
parent 0d42e0c54a
commit 6c6bfb7c70
2 changed files with 54 additions and 24 deletions

View file

@ -445,11 +445,19 @@ verify(u'hello'.encode('utf-16-le') == 'h\000e\000l\000l\000o\000')
verify(u'hello'.encode('utf-16-be') == '\000h\000e\000l\000l\000o')
verify(u'hello'.encode('latin-1') == 'hello')
# Roundtrip safety for BMP (just the first 1024 chars)
u = u''.join(map(unichr, range(1024)))
for encoding in ('utf-8', 'utf-16', 'utf-16-le', 'utf-16-be',
'raw_unicode_escape', 'unicode_escape', 'unicode_internal'):
verify(unicode(u.encode(encoding),encoding) == u)
# Roundtrip safety for non-BMP (just a few chars)
u = u'\U00010001\U00020002\U00030003\U00040004\U00050005'
for encoding in ('utf-8',
'utf-16', 'utf-16-le', 'utf-16-be',
'raw_unicode_escape', 'unicode_escape', 'unicode_internal'):
verify(unicode(u.encode(encoding),encoding) == u)
u = u''.join(map(unichr, range(256)))
for encoding in (
'latin-1',