Merge p3yk branch with the trunk up to revision 45595. This breaks a fair

number of tests, all because of the codecs/_multibytecodecs issue described
here (it's not a Py3K issue, just something Py3K discovers):
http://mail.python.org/pipermail/python-dev/2006-April/064051.html

Hye-Shik Chang promised to look for a fix, so no need to fix it here. The
tests that are expected to break are:

test_codecencodings_cn
test_codecencodings_hk
test_codecencodings_jp
test_codecencodings_kr
test_codecencodings_tw
test_codecs
test_multibytecodec

This merge fixes an actual test failure (test_weakref) in this branch,
though, so I believe merging is the right thing to do anyway.

1 files changed, 31 insertions, 5 deletions

diff --git a/Lib/codecs.py b/Lib/codecs.py
index 28856c714e..1518d75f9d 100644
--- a/Lib/codecs.py
+++ b/Lib/codecs.py
@@ -14,8 +14,7 @@ import __builtin__, sys
 try:
     from _codecs import *
 except ImportError, why:
-    raise SystemError,\
-          'Failed to load the builtin codecs: %s' % why
+    raise SystemError('Failed to load the builtin codecs: %s' % why)
 
 __all__ = ["register", "lookup", "open", "EncodedFile", "BOM", "BOM_BE",
            "BOM_LE", "BOM32_BE", "BOM32_LE", "BOM64_BE", "BOM64_LE",
@@ -156,13 +155,13 @@ class Codec:
 
 class IncrementalEncoder(object):
     """
-    A IncrementalEncoder encodes an input in multiple steps. The input can be
+    An IncrementalEncoder encodes an input in multiple steps. The input can be
     passed piece by piece to the encode() method. The IncrementalEncoder remembers
     the state of the Encoding process between calls to encode().
     """
     def __init__(self, errors='strict'):
         """
-        Creates a IncrementalEncoder instance.
+        Creates an IncrementalEncoder instance.
 
         The IncrementalEncoder may use different error handling schemes by
         providing the errors keyword argument. See the module docstring
@@ -182,6 +181,33 @@ class IncrementalEncoder(object):
         Resets the encoder to the initial state.
         """
 
+class BufferedIncrementalEncoder(IncrementalEncoder):
+    """
+    This subclass of IncrementalEncoder can be used as the baseclass for an
+    incremental encoder if the encoder must keep some of the output in a
+    buffer between calls to encode().
+    """
+    def __init__(self, errors='strict'):
+        IncrementalEncoder.__init__(self, errors)
+        self.buffer = "" # unencoded input that is kept between calls to encode()
+
+    def _buffer_encode(self, input, errors, final):
+        # Overwrite this method in subclasses: It must encode input
+        # and return an (output, length consumed) tuple
+        raise NotImplementedError
+
+    def encode(self, input, final=False):
+        # encode input (taking the buffer into account)
+        data = self.buffer + input
+        (result, consumed) = self._buffer_encode(data, self.errors, final)
+        # keep unencoded input until the next call
+        self.buffer = data[consumed:]
+        return result
+
+    def reset(self):
+        IncrementalEncoder.reset(self)
+        self.buffer = ""
+
 class IncrementalDecoder(object):
     """
     An IncrementalDecoder decodes an input in multiple steps. The input can be
@@ -234,7 +260,7 @@ class BufferedIncrementalDecoder(IncrementalDecoder):
 
     def reset(self):
         IncrementalDecoder.reset(self)
-        self.bytebuffer = ""
+        self.buffer = ""
 
 #
 # The StreamWriter and StreamReader class provide generic working