Mercurial > cpython-lru_cache-weakref
diff Lib/test/test_codeccallbacks.py @ 64590:fc76e8c617dc
Issue #9804: ascii() now always represents unicode surrogate pairs as
a single `\UXXXXXXXX`, regardless of whether the character is printable
or not. Also, the "backslashreplace" error handler now joins surrogate
pairs into a single character on UCS-2 builds.
| author | Antoine Pitrou <solipsis@pitrou.net> |
|---|---|
| date | Thu, 09 Sep 2010 20:30:23 +0000 |
| parents | e0d5a4a49112 |
| children | 9fe76c26ea9f |
line wrap: on
line diff
--- a/Lib/test/test_codeccallbacks.py Thu Sep 09 18:33:21 2010 +0000 +++ b/Lib/test/test_codeccallbacks.py Thu Sep 09 20:30:23 2010 +0000 @@ -577,17 +577,31 @@ UnicodeEncodeError("ascii", "\uffff", 0, 1, "ouch")), ("\\uffff", 1) ) - if sys.maxunicode>0xffff: - self.assertEquals( - codecs.backslashreplace_errors( - UnicodeEncodeError("ascii", "\U00010000", 0, 1, "ouch")), - ("\\U00010000", 1) - ) - self.assertEquals( - codecs.backslashreplace_errors( - UnicodeEncodeError("ascii", "\U0010ffff", 0, 1, "ouch")), - ("\\U0010ffff", 1) - ) + # 1 on UCS-4 builds, 2 on UCS-2 + len_wide = len("\U00010000") + self.assertEquals( + codecs.backslashreplace_errors( + UnicodeEncodeError("ascii", "\U00010000", + 0, len_wide, "ouch")), + ("\\U00010000", len_wide) + ) + self.assertEquals( + codecs.backslashreplace_errors( + UnicodeEncodeError("ascii", "\U0010ffff", + 0, len_wide, "ouch")), + ("\\U0010ffff", len_wide) + ) + # Lone surrogates (regardless of unicode width) + self.assertEquals( + codecs.backslashreplace_errors( + UnicodeEncodeError("ascii", "\ud800", 0, 1, "ouch")), + ("\\ud800", 1) + ) + self.assertEquals( + codecs.backslashreplace_errors( + UnicodeEncodeError("ascii", "\udfff", 0, 1, "ouch")), + ("\\udfff", 1) + ) def test_badhandlerresults(self): results = ( 42, "foo", (1,2,3), ("foo", 1, 3), ("foo", None), ("foo",), ("foo", 1, 3), ("foo", None), ("foo",) )