Author: Amaury Forgeot d'Arc <[email protected]>
Branch: py3k
Changeset: r58338:82d0647b840c
Date: 2012-10-21 09:12 +0200
http://bitbucket.org/pypy/pypy/changeset/82d0647b840c/
Log: Fix own tests in module/_codecs
diff --git a/pypy/module/_codecs/interp_codecs.py
b/pypy/module/_codecs/interp_codecs.py
--- a/pypy/module/_codecs/interp_codecs.py
+++ b/pypy/module/_codecs/interp_codecs.py
@@ -454,7 +454,7 @@
make_decoder_wrapper('mbcs_decode')
# utf-8 functions are not regular, because we have to pass
-# "allow_surrogates=True"
+# "allow_surrogates=False"
@unwrap_spec(uni=unicode, errors='str_or_None')
def utf_8_encode(space, uni, errors="strict"):
if errors is None:
@@ -462,7 +462,7 @@
state = space.fromcache(CodecState)
result = runicode.unicode_encode_utf_8(
uni, len(uni), errors, state.encode_error_handler,
- allow_surrogates=True)
+ allow_surrogates=False)
return space.newtuple([space.wrapbytes(result), space.wrap(len(uni))])
@unwrap_spec(string='bufferstr', errors='str_or_None',
@@ -475,7 +475,7 @@
result, consumed = runicode.str_decode_utf_8(
string, len(string), errors,
final, state.decode_error_handler,
- allow_surrogates=True)
+ allow_surrogates=False)
return space.newtuple([space.wrap(result), space.wrap(consumed)])
@unwrap_spec(data="bufferstr", errors='str_or_None', byteorder=int,
diff --git a/pypy/rlib/runicode.py b/pypy/rlib/runicode.py
--- a/pypy/rlib/runicode.py
+++ b/pypy/rlib/runicode.py
@@ -295,13 +295,7 @@
r, pos = errorhandler(errors, 'utf-8',
'surrogates not allowed',
s, pos-1, pos)
- for ch in r:
- if ord(ch) < 0x80:
- result.append(chr(ord(ch)))
- else:
- errorhandler('strict', 'utf-8',
- 'surrogates not allowed',
- s, pos-1, pos)
+ result.append(r)
continue
# else: Fall through and handles isolated high surrogates
result.append((chr((0xe0 | (ch >> 12)))))
_______________________________________________
pypy-commit mailing list
[email protected]
http://mail.python.org/mailman/listinfo/pypy-commit
