1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
|
#! /bin/sh -e
# All lines beginning with `# DPATCH:' are a description of the patch.
# DP: Fix wide unicode heap overflows (CVE-2006-4980)
dir=
if [ $# -eq 3 -a "$2" = '-d' ]; then
pdir="-d $3"
dir="$3/"
elif [ $# -ne 1 ]; then
echo >&2 "usage: `basename $0`: -patch|-unpatch [-d <srcdir>]"
exit 1
fi
case "$1" in
-patch)
patch $pdir -f --no-backup-if-mismatch -p0 < $0
#cd ${dir}gcc && autoconf
;;
-unpatch)
patch $pdir -f --no-backup-if-mismatch -R -p0 < $0
#rm ${dir}gcc/configure
;;
*)
echo >&2 "usage: `basename $0`: -patch|-unpatch [-d <srcdir>]"
exit 1
esac
exit 0
# append the patch here and adjust the -p? flag in the patch calls.
--- Objects/unicodeobject.c.orig 2006-10-02 15:42:31.000000000 -0700
+++ Objects/unicodeobject.c 2006-10-02 15:50:51.058449437 -0700
@@ -1888,7 +1888,28 @@
static const char *hexdigit = "0123456789abcdef";
- repr = PyString_FromStringAndSize(NULL, 2 + 6*size + 1);
+ /* Initial allocation is based on the longest-possible unichr
+ escape.
+
+ In wide (UTF-32) builds '\U00xxxxxx' is 10 chars per source
+ unichr, so in this case it's the longest unichr escape. In
+ narrow (UTF-16) builds this is five chars per source unichr
+ since there are two unichrs in the surrogate pair, so in narrow
+ (UTF-16) builds it's not the longest unichr escape.
+
+ In wide or narrow builds '\uxxxx' is 6 chars per source unichr,
+ so in the narrow (UTF-16) build case it's the longest unichr
+ escape.
+ */
+
+ repr = PyString_FromStringAndSize(NULL,
+ 2
+#ifdef Py_UNICODE_WIDE
+ + 10*size
+#else
+ + 6*size
+#endif
+ + 1);
if (repr == NULL)
return NULL;
@@ -1913,15 +1934,6 @@
#ifdef Py_UNICODE_WIDE
/* Map 21-bit characters to '\U00xxxxxx' */
else if (ch >= 0x10000) {
- int offset = p - PyString_AS_STRING(repr);
-
- /* Resize the string if necessary */
- if (offset + 12 > PyString_GET_SIZE(repr)) {
- if (_PyString_Resize(&repr, PyString_GET_SIZE(repr) + 100))
- return NULL;
- p = PyString_AS_STRING(repr) + offset;
- }
-
*p++ = '\\';
*p++ = 'U';
*p++ = hexdigit[(ch >> 28) & 0x0000000F];
@@ -1934,8 +1946,8 @@
*p++ = hexdigit[ch & 0x0000000F];
continue;
}
-#endif
- /* Map UTF-16 surrogate pairs to Unicode \UXXXXXXXX escapes */
+#else
+ /* Map UTF-16 surrogate pairs to '\U00xxxxxx' */
else if (ch >= 0xD800 && ch < 0xDC00) {
Py_UNICODE ch2;
Py_UCS4 ucs;
@@ -1960,6 +1972,7 @@
s--;
size++;
}
+#endif
/* Map 16-bit characters to '\uxxxx' */
if (ch >= 256) {
|
