mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-12-04 00:30:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 8

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

18
Lib/test/test_bytes.py
View file

@ -188,24 +188,26 @@ class BaseBytesTest(unittest.TestCase):
def test_encoding(self):
sample = "Hello world\n\u1234\u5678\u9abc"
for enc in ("utf8", "utf16"):
for enc in ("utf-8", "utf-16"):
b = self.type2test(sample, enc)
self.assertEqual(b, self.type2test(sample.encode(enc)))
self.assertRaises(UnicodeEncodeError, self.type2test, sample, "latin1")
b = self.type2test(sample, "latin1", "ignore")
self.assertRaises(UnicodeEncodeError, self.type2test, sample, "latin-1")
b = self.type2test(sample, "latin-1", "ignore")
self.assertEqual(b, self.type2test(sample[:-3], "utf-8"))
def test_decode(self):
sample = "Hello world\n\u1234\u5678\u9abc\def0\def0"
for enc in ("utf8", "utf16"):
for enc in ("utf-8", "utf-16"):
b = self.type2test(sample, enc)
self.assertEqual(b.decode(enc), sample)
sample = "Hello world\n\x80\x81\xfe\xff"
b = self.type2test(sample, "latin1")
self.assertRaises(UnicodeDecodeError, b.decode, "utf8")
self.assertEqual(b.decode("utf8", "ignore"), "Hello world\n")
self.assertEqual(b.decode(errors="ignore", encoding="utf8"),
b = self.type2test(sample, "latin-1")
self.assertRaises(UnicodeDecodeError, b.decode, "utf-8")
self.assertEqual(b.decode("utf-8", "ignore"), "Hello world\n")
self.assertEqual(b.decode(errors="ignore", encoding="utf-8"),
"Hello world\n")
# Default encoding is utf-8
self.assertEqual(self.type2test(b'\xe2\x98\x83').decode(), '\u2603')
def test_from_int(self):
b = self.type2test(0)