Added checks to prevent PyUnicode_Count() from dumping core
in case the parameters are out of bounds and fixes error handling
for .count(), .startswith() and .endswith() for the case of
mixed string/Unicode objects.
This patch adds Python style index semantics to PyUnicode_Count()
indices (including the special handling of negative indices).
The patch is an extended version of patch #103249 submitted
by Michael Hudson (mwh) on SF. It also includes new test cases.
diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index 8f7b354..a3678d5 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -1976,7 +1976,7 @@
x = Py_None;
Py_INCREF(x);
} else
- goto onError;
+ goto onError;
}
/* Apply mapping */
@@ -2014,9 +2014,9 @@
(targetsize << 2);
extrachars += needed;
if (_PyUnicode_Resize(v, PyUnicode_GET_SIZE(v) + needed)) {
- Py_DECREF(x);
- goto onError;
- }
+ Py_DECREF(x);
+ goto onError;
+ }
p = PyUnicode_AS_UNICODE(v) + oldpos;
}
Py_UNICODE_COPY(p,
@@ -2112,7 +2112,7 @@
x = Py_None;
Py_INCREF(x);
} else
- goto onError;
+ goto onError;
}
/* Apply mapping */
@@ -2150,9 +2150,9 @@
(targetsize << 2);
extrachars += needed;
if (_PyString_Resize(&v, PyString_GET_SIZE(v) + needed)) {
- Py_DECREF(x);
- goto onError;
- }
+ Py_DECREF(x);
+ goto onError;
+ }
s = PyString_AS_STRING(v) + oldpos;
}
memcpy(s,
@@ -2392,6 +2392,17 @@
{
int count = 0;
+ if (start < 0)
+ start += self->length;
+ if (start < 0)
+ start = 0;
+ if (end > self->length)
+ end = self->length;
+ if (end < 0)
+ end += self->length;
+ if (end < 0)
+ end = 0;
+
if (substring->length == 0)
return (end - start + 1);