Author: Matti Picus <[email protected]>
Branch: unicode-utf8-py3
Changeset: r94847:e8413e4a1934
Date: 2018-07-11 06:51 -0700
http://bitbucket.org/pypy/pypy/changeset/e8413e4a1934/
Log: small tweaks, copy partition from py3.5
diff --git a/pypy/objspace/std/bytesobject.py b/pypy/objspace/std/bytesobject.py
--- a/pypy/objspace/std/bytesobject.py
+++ b/pypy/objspace/std/bytesobject.py
@@ -404,9 +404,9 @@
_KIND1 = "byte"
_KIND2 = "bytes"
- def __init__(self, str):
- assert str is not None
- self._value = str
+ def __init__(self, s):
+ assert s is not None
+ self._value = s
def __repr__(self):
"""representation for debugging purposes"""
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
@@ -327,7 +327,7 @@
return W_ListObject.newlist_bytes(self, list_s)
def newlist_text(self, list_t):
- return self.newlist_utf8([decode_utf8sp(self, s) for s in list_t])
+ return self.newlist_utf8([decode_utf8sp(self, s)[0] for s in list_t])
def newlist_utf8(self, list_u, is_ascii=True):
# TODO ignoring is_ascii, is that correct?
@@ -762,7 +762,7 @@
if not e.match(self, self.w_TypeError):
raise
else:
- classname = b'%s.%s' % (modulename, classname)
+ classname = u'%s.%s' % (modulename.decode('utf8'),
classname)
else:
classname = w_type.name.decode('utf-8')
return classname
diff --git a/pypy/objspace/std/stringmethods.py
b/pypy/objspace/std/stringmethods.py
--- a/pypy/objspace/std/stringmethods.py
+++ b/pypy/objspace/std/stringmethods.py
@@ -478,39 +478,56 @@
from pypy.objspace.std.bytearrayobject import W_BytearrayObject
value = self._val(space)
- sub = _get_buffer(space, w_sub)
- sublen = sub.getlength()
- if sublen == 0:
- raise oefmt(space.w_ValueError, "empty separator")
+ if self._use_rstr_ops(space, w_sub):
+ sub = self._op_val(space, w_sub)
+ sublen = len(sub)
+ if sublen == 0:
+ raise oefmt(space.w_ValueError, "empty separator")
- pos = find(value, sub, 0, len(value))
- if pos != -1 and isinstance(self, W_BytearrayObject):
- w_sub = self._new_from_buffer(sub)
+ pos = value.find(sub)
+ else:
+ sub = space.readbuf_w(w_sub)
+ sublen = sub.getlength()
+ if sublen == 0:
+ raise oefmt(space.w_ValueError, "empty separator")
+
+ pos = find(value, sub, 0, len(value))
+ if pos != -1 and isinstance(self, W_BytearrayObject):
+ w_sub = self._new_from_buffer(sub)
if pos == -1:
- self = self._new(value)
+ if isinstance(self, W_BytearrayObject):
+ self = self._new(value)
return space.newtuple([self, self._empty(), self._empty()])
else:
return space.newtuple(
[self._sliced(space, value, 0, pos, self), w_sub,
self._sliced(space, value, pos + sublen, len(value), self)])
- # This is not used for W_UnicodeObject.
def descr_rpartition(self, space, w_sub):
from pypy.objspace.std.bytearrayobject import W_BytearrayObject
value = self._val(space)
- sub = _get_buffer(space, w_sub)
- sublen = sub.getlength()
- if sublen == 0:
- raise oefmt(space.w_ValueError, "empty separator")
+ if self._use_rstr_ops(space, w_sub):
+ sub = self._op_val(space, w_sub)
+ sublen = len(sub)
+ if sublen == 0:
+ raise oefmt(space.w_ValueError, "empty separator")
- pos = rfind(value, sub, 0, len(value))
- if pos != -1 and isinstance(self, W_BytearrayObject):
- w_sub = self._new_from_buffer(sub)
+ pos = value.rfind(sub)
+ else:
+ sub = space.readbuf_w(w_sub)
+ sublen = sub.getlength()
+ if sublen == 0:
+ raise oefmt(space.w_ValueError, "empty separator")
+
+ pos = rfind(value, sub, 0, len(value))
+ if pos != -1 and isinstance(self, W_BytearrayObject):
+ w_sub = self._new_from_buffer(sub)
if pos == -1:
- self = self._new(value)
+ if isinstance(self, W_BytearrayObject):
+ self = self._new(value)
return space.newtuple([self._empty(), self._empty(), self])
else:
return space.newtuple(
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
@@ -84,7 +84,7 @@
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'
+ assert w_x._utf8 == '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
@@ -93,4 +93,4 @@
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'
+ assert w_x._utf8 == 'foo\uxF0'
_______________________________________________
pypy-commit mailing list
[email protected]
https://mail.python.org/mailman/listinfo/pypy-commit
