Author: Antonio Cuni <[email protected]>
Branch: py3k
Changeset: r56104:ad1b4b5cbb55
Date: 2012-07-17 14:18 +0200
http://bitbucket.org/pypy/pypy/changeset/ad1b4b5cbb55/
Log: don't crash if we try to wrap a non-ascii byte string; this might
still happen because e.g. exception messages are not unicode yet
diff --git a/pypy/objspace/std/objspace.py b/pypy/objspace/std/objspace.py
--- a/pypy/objspace/std/objspace.py
+++ b/pypy/objspace/std/objspace.py
@@ -173,7 +173,24 @@
else:
return self.newint(x)
if isinstance(x, str):
- return wrapunicode(self, x.decode('ascii'))
+ # this hack is temporary: look at the comment in
+ # test_stdstdobjspace.test_wrap_string
+ try:
+ unicode_x = x.decode('ascii')
+ except UnicodeDecodeError:
+ # poor man's x.decode('ascii', 'replace'), since it's not
+ # supported by RPython
+ if not we_are_translated():
+ print 'WARNING: space.str() called on a non-ascii byte
string: %r' % x
+ lst = []
+ for ch in x:
+ ch = ord(ch)
+ if ch > 127:
+ lst.append(u'\ufffd')
+ else:
+ lst.append(unichr(ch))
+ unicode_x = u''.join(lst)
+ return wrapunicode(self, unicode_x)
if isinstance(x, unicode):
return wrapunicode(self, x)
if isinstance(x, float):
diff --git a/pypy/objspace/std/test/test_stdobjspace.py
b/pypy/objspace/std/test/test_stdobjspace.py
--- a/pypy/objspace/std/test/test_stdobjspace.py
+++ b/pypy/objspace/std/test/test_stdobjspace.py
@@ -91,3 +91,18 @@
value = 200
x = rffi.cast(rffi.UCHAR, value)
assert space.eq_w(space.wrap(value), space.wrap(x))
+
+ def test_wrap_string(self):
+ from pypy.objspace.std.unicodeobject import W_UnicodeObject
+ w_x = self.space.wrap('foo')
+ assert isinstance(w_x, W_UnicodeObject)
+ assert w_x._value == u'foo'
+ #
+ # calling space.wrap() on a byte string which is not ASCII should
+ # never happen. Howeven it might happen while the py3k port is not
+ # 100% complete. In the meantime, try to return something more or less
+ # sensible instead of crashing with an RPython UnicodeError.
+ from pypy.objspace.std.unicodeobject import W_UnicodeObject
+ w_x = self.space.wrap('foo\xF0')
+ assert isinstance(w_x, W_UnicodeObject)
+ assert w_x._value == u'foo\ufffd'
_______________________________________________
pypy-commit mailing list
[email protected]
http://mail.python.org/mailman/listinfo/pypy-commit
