Author: bapt
Date: Wed Sep 2 05:55:57 2015
New Revision: 287393
URL: https://svnweb.freebsd.org/changeset/base/287393
Log:
MFC: r286490,r286491,r287125
Per rfc3629 value greater than 0x10ffff should be rejected (r286490,r286491)
Make UTF-8 parsing and generation more strict. (r287125 by ed)
- in mbrtowc() we need to disallow codepoints above 0x10ffff.
- In wcrtomb() we need to disallow codepoints between 0xd800 and 0xdfff.
Modified:
stable/10/lib/libc/locale/utf8.c
Directory Properties:
stable/10/ (props changed)
Modified: stable/10/lib/libc/locale/utf8.c
==============================================================================
--- stable/10/lib/libc/locale/utf8.c Wed Sep 2 05:45:47 2015
(r287392)
+++ stable/10/lib/libc/locale/utf8.c Wed Sep 2 05:55:57 2015
(r287393)
@@ -145,14 +145,6 @@ _UTF8_mbrtowc(wchar_t * __restrict pwc,
mask = 0x07;
want = 4;
lbound = 0x10000;
- } else if ((ch & 0xfc) == 0xf8) {
- mask = 0x03;
- want = 5;
- lbound = 0x200000;
- } else if ((ch & 0xfe) == 0xfc) {
- mask = 0x01;
- want = 6;
- lbound = 0x4000000;
} else {
/*
* Malformed input; input is not UTF-8.
@@ -199,7 +191,7 @@ _UTF8_mbrtowc(wchar_t * __restrict pwc,
errno = EILSEQ;
return ((size_t)-1);
}
- if (wch >= 0xd800 && wch <= 0xdfff) {
+ if ((wch >= 0xd800 && wch <= 0xdfff) || wch > 0x10ffff) {
/*
* Malformed input; invalid code points.
*/
@@ -326,17 +318,15 @@ _UTF8_wcrtomb(char * __restrict s, wchar
lead = 0xc0;
len = 2;
} else if ((wc & ~0xffff) == 0) {
+ if (wc >= 0xd800 && wc <= 0xdfff) {
+ errno = EILSEQ;
+ return ((size_t)-1);
+ }
lead = 0xe0;
len = 3;
- } else if ((wc & ~0x1fffff) == 0) {
+ } else if (wc >= 0 && wc <= 0x10ffff) {
lead = 0xf0;
len = 4;
- } else if ((wc & ~0x3ffffff) == 0) {
- lead = 0xf8;
- len = 5;
- } else if ((wc & ~0x7fffffff) == 0) {
- lead = 0xfc;
- len = 6;
} else {
errno = EILSEQ;
return ((size_t)-1);
_______________________________________________
[email protected] mailing list
https://lists.freebsd.org/mailman/listinfo/svn-src-all
To unsubscribe, send any mail to "[email protected]"
