Author: Matti Picus <[email protected]>
Branch: unicode-utf8-py3
Changeset: r94792:63fcd825e9f2
Date: 2018-07-01 00:05 -0500
http://bitbucket.org/pypy/pypy/changeset/63fcd825e9f2/
Log: pass more module/_io tests
diff --git a/pypy/interpreter/baseobjspace.py b/pypy/interpreter/baseobjspace.py
--- a/pypy/interpreter/baseobjspace.py
+++ b/pypy/interpreter/baseobjspace.py
@@ -1715,6 +1715,9 @@
def convert_to_w_unicode(self, w_obj):
return w_obj.convert_to_w_unicode(self)
+ def realunicode_w(self, w_obj):
+ return w_obj.utf8_w(self).decode('utf8')
+
def utf8_0_w(self, w_obj):
"Like utf8_w, but rejects strings with NUL bytes."
from rpython.rlib import rstring
diff --git a/pypy/module/_io/interp_textio.py b/pypy/module/_io/interp_textio.py
--- a/pypy/module/_io/interp_textio.py
+++ b/pypy/module/_io/interp_textio.py
@@ -739,7 +739,7 @@
def _read(self, space, size):
remaining = size
- builder = UnicodeBuilder(size)
+ builder = StringBuilder(size)
# Keep reading chunks until we have n characters to return
while remaining > 0:
@@ -825,7 +825,7 @@
result = builder.build()
lgt = get_utf8_length(result)
- return space.newutf8(result, lgt)
+ return (result, lgt, lgt)
# _____________________________________________________________
# write methods
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
@@ -387,11 +387,11 @@
if isinstance(s, unicode):
s, lgt = s.encode('utf8'), len(s)
elif isinstance(s, str):
- s, lgt, chk = str_decode_utf8(s, "string", True, None,
+ s, uf8lgt, lgt = str_decode_utf8(s, "string", True, None,
allow_surrogates=True)
elif isinstance(s, tuple):
# result of decode_utf8
- s, lgt, chk = s
+ s, utf8lgt, lgt = s
else:
# XXX what is s ?
lgt = rutf8.check_utf8(s, True)
diff --git a/pypy/objspace/std/unicodeobject.py
b/pypy/objspace/std/unicodeobject.py
--- a/pypy/objspace/std/unicodeobject.py
+++ b/pypy/objspace/std/unicodeobject.py
@@ -587,7 +587,7 @@
return space.newbool(cased)
def descr_isidentifier(self, space):
- return space.newbool(_isidentifier(self._value))
+ return space.newbool(_isidentifier(self._utf8.decode('utf8')))
def descr_startswith(self, space, w_prefix, w_start=None, w_end=None):
start, end = self._unwrap_and_compute_idx_params(space, w_start, w_end)
_______________________________________________
pypy-commit mailing list
[email protected]
https://mail.python.org/mailman/listinfo/pypy-commit
