Author: Armin Rigo <[email protected]>
Branch: unicode-utf8-py3
Changeset: r95069:f9566e8f8110
Date: 2018-09-02 11:14 +0200
http://bitbucket.org/pypy/pypy/changeset/f9566e8f8110/
Log: Fix for id(unicode)
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
@@ -22,7 +22,7 @@
from pypy.objspace.std.sliceobject import (W_SliceObject,
unwrap_start_stop, normalize_simple_slice)
from pypy.objspace.std.stringmethods import StringMethods
-from pypy.objspace.std.util import IDTAG_SPECIAL, IDTAG_SHIFT
+from pypy.objspace.std.util import IDTAG_SPECIAL, IDTAG_SHIFT, IDTAG_ALT_UID
__all__ = ['W_UnicodeObject', 'encode_object', 'decode_object',
'unicode_from_object', 'unicode_to_decimal_w']
@@ -68,7 +68,7 @@
return False
s1 = space.utf8_w(self)
s2 = space.utf8_w(w_other)
- if len(s2) > 2:
+ if self._len() > 1:
return s1 is s2
else: # strings of len <= 1 are unique-ified
return s1 == s2
@@ -76,14 +76,16 @@
def immutable_unique_id(self, space):
if self.user_overridden_class:
return None
- s = space.utf8_w(self)
- if len(s) > 2:
- uid = compute_unique_id(s)
- else: # strings of len <= 1 are unique-ified
- if len(s) == 1:
- base = ~ord(s[0]) # negative base values
- elif len(s) == 2:
- base = ~((ord(s[1]) << 8) | ord(s[0]))
+ l = self._len()
+ if l > 1:
+ # return the uid plus 2, to make sure we don't get
+ # conflicts with W_BytesObject, whose id() might be
+ # identical
+ uid = compute_unique_id(self._utf8) + IDTAG_ALT_UID
+ else: # strings of len <= 1 are unique-ified
+ if l == 1:
+ base = rutf8.codepoint_at_pos(self._utf8, 0)
+ base = ~base # negative base values
else:
base = 257 # empty unicode string: base value 257
uid = (base << IDTAG_SHIFT) | IDTAG_SPECIAL
diff --git a/pypy/objspace/std/util.py b/pypy/objspace/std/util.py
--- a/pypy/objspace/std/util.py
+++ b/pypy/objspace/std/util.py
@@ -4,6 +4,7 @@
from pypy.interpreter import gateway
IDTAG_SHIFT = 4
+IDTAG_ALT_UID = 2 # gives an alternate id() from the same real uid
IDTAG_INT = 1
IDTAG_LONG = 3
_______________________________________________
pypy-commit mailing list
[email protected]
https://mail.python.org/mailman/listinfo/pypy-commit
