SF patch #998993: The UTF-8 and the UTF-16 stateful decoders now support

decoding incomplete input (when the input stream is temporarily exhausted).
codecs.StreamReader now implements buffering, which enables proper
readline support for the UTF-16 decoders. codecs.StreamReader.read()
has a new argument chars which specifies the number of characters to
return. codecs.StreamReader.readline() and codecs.StreamReader.readlines()
have a new argument keepends. Trailing "\n"s will be stripped from the lines
if keepends is false. Added C APIs PyUnicode_DecodeUTF8Stateful and
PyUnicode_DecodeUTF16Stateful.

1 files changed, 8 insertions, 10 deletions

diff --git a/Lib/encodings/utf_8.py b/Lib/encodings/utf_8.py
index 89249a9..9cb0b4b 100644
--- a/Lib/encodings/utf_8.py
+++ b/Lib/encodings/utf_8.py
@@ -10,21 +10,19 @@ import codecs
 
 ### Codec APIs
 
-class Codec(codecs.Codec):
+encode = codecs.utf_8_encode
 
-    # Note: Binding these as C functions will result in the class not
-    # converting them to methods. This is intended.
-    encode = codecs.utf_8_encode
-    decode = codecs.utf_8_decode
+def decode(input, errors='strict'):
+    return codecs.utf_8_decode(input, errors, True)
 
-class StreamWriter(Codec,codecs.StreamWriter):
-    pass
+class StreamWriter(codecs.StreamWriter):
+    encode = codecs.utf_8_encode
 
-class StreamReader(Codec,codecs.StreamReader):
-    pass
+class StreamReader(codecs.StreamReader):
+    decode = codecs.utf_8_decode
 
 ### encodings module API
 
 def getregentry():
 
-    return (Codec.encode,Codec.decode,StreamReader,StreamWriter)
+    return (encode,decode,StreamReader,StreamWriter)