summaryrefslogtreecommitdiffstats
path: root/Objects/unicodeobject.c
diff options
context:
space:
mode:
authorFredrik Lundh <fredrik@pythonware.com>2000-07-10 18:27:47 (GMT)
committerFredrik Lundh <fredrik@pythonware.com>2000-07-10 18:27:47 (GMT)
commitdde61644024185891e1c41d6f5de29f8780b1cff (patch)
tree729c72530031a4394196f53a802132cc87954d1c /Objects/unicodeobject.c
parent417c489defd33ceb4a3cb76efaf4975ee886221e (diff)
downloadcpython-dde61644024185891e1c41d6f5de29f8780b1cff.zip
cpython-dde61644024185891e1c41d6f5de29f8780b1cff.tar.gz
cpython-dde61644024185891e1c41d6f5de29f8780b1cff.tar.bz2
- changed hash calculation for unicode strings. the new
value is calculated from the character values, in a way that makes sure an 8-bit ASCII string and a unicode string with the same contents get the same hash value. (as a side effect, this also works for ISO Latin 1 strings). for more details, see the python-dev discussion.
Diffstat (limited to 'Objects/unicodeobject.c')
-rw-r--r--Objects/unicodeobject.c38
1 files changed, 20 insertions, 18 deletions
diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index 70afd0d..7737057 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -3471,26 +3471,28 @@ unicode_getitem(PyUnicodeObject *self, int index)
static long
unicode_hash(PyUnicodeObject *self)
{
- long hash;
- PyObject *utf8;
-
- /* Since Unicode objects compare equal to their UTF-8 string
- counterparts, they should also use the UTF-8 strings as basis
- for their hash value. This is needed to assure that strings and
- Unicode objects behave in the same way as dictionary
- keys. Unfortunately, this costs some performance and also some
- memory if the cached UTF-8 representation is not used later
- on. */
+ /* Since Unicode objects compare equal to their ASCII string
+ counterparts, they should use the individual character values
+ as basis for their hash value. This is needed to assure that
+ strings and Unicode objects behave in the same way as
+ dictionary keys. */
+
+ register int len;
+ register Py_UNICODE *p;
+ register long x;
+
if (self->hash != -1)
return self->hash;
- utf8 = _PyUnicode_AsUTF8String((PyObject *)self, NULL);
- if (utf8 == NULL)
- return -1;
- hash = PyObject_Hash(utf8);
- if (hash == -1)
- return -1;
- self->hash = hash;
- return hash;
+ len = PyUnicode_GET_SIZE(self);
+ p = PyUnicode_AS_UNICODE(self);
+ x = *p << 7;
+ while (--len >= 0)
+ x = (1000003*x) ^ *p++;
+ x ^= PyUnicode_GET_SIZE(self);
+ if (x == -1)
+ x = -2;
+ self->hash = x;
+ return x;
}
static char index__doc__[] =