mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-08-31 05:58:33 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 7

Normalize the encoding names for Latin-1 and UTF-8 to

Browse source 
'latin-1' and 'utf-8'.

These are optimized in the Python Unicode implementation
to result in more direct processing, bypassing the codec
registry.

Also see issue11303.
This commit is contained in:
Marc-André Lemburg 2011-02-25 15:42:01 +00:00
parent a391b11320
commit 8f36af7a4c
32 changed files with 84 additions and 79 deletions
Download patch file Download diff file Expand all files Collapse all files

5
Lib/test/test_unicode.py
View file

@ -1182,11 +1182,14 @@ class UnicodeTest(string_tests.CommonTest,
self.assertEqual('hello'.encode('ascii'), b'hello')
self.assertEqual('hello'.encode('utf-7'), b'hello')
self.assertEqual('hello'.encode('utf-8'), b'hello')
self.assertEqual('hello'.encode('utf8'), b'hello')
self.assertEqual('hello'.encode('utf-8'), b'hello')
self.assertEqual('hello'.encode('utf-16-le'), b'h\000e\000l\000l\000o\000')
self.assertEqual('hello'.encode('utf-16-be'), b'\000h\000e\000l\000l\000o')
self.assertEqual('hello'.encode('latin-1'), b'hello')
# Default encoding is utf-8
self.assertEqual('\u2603'.encode(), b'\xe2\x98\x83')
# Roundtrip safety for BMP (just the first 1024 chars)
for c in range(1024):
u = chr(c)