summaryrefslogtreecommitdiffstats
path: root/Python/ast.c
diff options
context:
space:
mode:
authorBenjamin Peterson <benjamin@python.org>2009-10-29 02:02:47 (GMT)
committerBenjamin Peterson <benjamin@python.org>2009-10-29 02:02:47 (GMT)
commitc717aec77271f6ed3bb6c2b9f87559fd39e4f642 (patch)
treeebb7992dfe4f675cd357edba62983d332ffe846a /Python/ast.c
parente7228d3e01d03e915ee42fceea914e1c7273b1e2 (diff)
downloadcpython-c717aec77271f6ed3bb6c2b9f87559fd39e4f642.zip
cpython-c717aec77271f6ed3bb6c2b9f87559fd39e4f642.tar.gz
cpython-c717aec77271f6ed3bb6c2b9f87559fd39e4f642.tar.bz2
Merged revisions 75931 via svnmerge from
svn+ssh://pythondev@svn.python.org/python/trunk ........ r75931 | benjamin.peterson | 2009-10-28 20:49:07 -0500 (Wed, 28 Oct 2009) | 5 lines do a backport of r75928 The added test does not fail without the patch, but we still fix the issue of surrogates being used in wide builds where they should not be. ........
Diffstat (limited to 'Python/ast.c')
-rw-r--r--Python/ast.c21
1 files changed, 12 insertions, 9 deletions
diff --git a/Python/ast.c b/Python/ast.c
index a3fdd89..b89e29c 100644
--- a/Python/ast.c
+++ b/Python/ast.c
@@ -3248,10 +3248,11 @@ decode_unicode(struct compiling *c, const char *s, size_t len, int rawmode, cons
u = NULL;
} else {
/* check for integer overflow */
- if (len > PY_SIZE_MAX / 4)
+ if (len > PY_SIZE_MAX / 6)
return NULL;
- /* "\XX" may become "\u005c\uHHLL" (12 bytes) */
- u = PyString_FromStringAndSize((char *)NULL, len * 4);
+ /* "<C3><A4>" (2 bytes) may become "\U000000E4" (10 bytes), or 1:5
+ "\รค" (3 bytes) may become "\u005c\U000000E4" (16 bytes), or ~1:6 */
+ u = PyString_FromStringAndSize((char *)NULL, len * 6);
if (u == NULL)
return NULL;
p = buf = PyString_AsString(u);
@@ -3268,19 +3269,21 @@ decode_unicode(struct compiling *c, const char *s, size_t len, int rawmode, cons
PyObject *w;
char *r;
Py_ssize_t rn, i;
- w = decode_utf8(c, &s, end, "utf-16-be");
+ w = decode_utf8(c, &s, end, "utf-32-be");
if (w == NULL) {
Py_DECREF(u);
return NULL;
}
r = PyString_AsString(w);
rn = PyString_Size(w);
- assert(rn % 2 == 0);
- for (i = 0; i < rn; i += 2) {
- sprintf(p, "\\u%02x%02x",
+ assert(rn % 4 == 0);
+ for (i = 0; i < rn; i += 4) {
+ sprintf(p, "\\U%02x%02x%02x%02x",
r[i + 0] & 0xFF,
- r[i + 1] & 0xFF);
- p += 6;
+ r[i + 1] & 0xFF,
+ r[i + 2] & 0xFF,
+ r[i + 3] & 0xFF);
+ p += 10;
}
Py_DECREF(w);
} else {