procyberian/emacs
2
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

(decode_coding_utf_8): Reject overlong sequences.

Browse source
This commit is contained in:
Dave Love 2002-05-27 22:19:17 +00:00
parent afb2e0083a
commit b0edb2c59c
2 changed files with 25 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

6
src/ChangeLog
View file

@ -1,4 +1,8 @@
2002-05-26 Dave Love <d.love@dl.ac.uk> 2002-05-27 Dave Love <fx@gnu.org>
* coding.c (decode_coding_utf_8): Reject overlong sequences.
2002-05-26 Dave Love <fx@gnu.org>
* coding.c: Doc fixes. * coding.c: Doc fixes.
(Fcoding_system_aliases): Fix return value. (Fcoding_system_aliases): Fix return value.

24
src/coding.c
View file

@ -1078,6 +1078,7 @@ detect_coding_utf_8 (coding, mask)
} }
/* Fixme: deal with surrogates? */
static void static void
decode_coding_utf_8 (coding) decode_coding_utf_8 (coding)
struct coding_system *coding; struct coding_system *coding;
@ -1126,23 +1127,38 @@ decode_coding_utf_8 (coding)
if (! UTF_8_EXTRA_OCTET_P (c2)) if (! UTF_8_EXTRA_OCTET_P (c2))
goto invalid_code; goto invalid_code;
if (UTF_8_2_OCTET_LEADING_P (c1)) if (UTF_8_2_OCTET_LEADING_P (c1))
c = ((c1 & 0x1F) << 6) | (c2 & 0x3F); {
c = ((c1 & 0x1F) << 6) | (c2 & 0x3F);
/* Reject overlong sequences here and below. Encoders
producing them are incorrect, they can be misleading,
and they mess up read/write invariance. */
if (c < 128)
goto invalid_code;
}
else else
{ {
ONE_MORE_BYTE (c3); ONE_MORE_BYTE (c3);
if (! UTF_8_EXTRA_OCTET_P (c3)) if (! UTF_8_EXTRA_OCTET_P (c3))
goto invalid_code; goto invalid_code;
if (UTF_8_3_OCTET_LEADING_P (c1)) if (UTF_8_3_OCTET_LEADING_P (c1))
c = (((c1 & 0xF) << 12) {
| ((c2 & 0x3F) << 6) | (c3 & 0x3F)); c = (((c1 & 0xF) << 12)
| ((c2 & 0x3F) << 6) | (c3 & 0x3F));
if (c < 0x800)
goto invalid_code;
}
else else
{ {
ONE_MORE_BYTE (c4); ONE_MORE_BYTE (c4);
if (! UTF_8_EXTRA_OCTET_P (c4)) if (! UTF_8_EXTRA_OCTET_P (c4))
goto invalid_code; goto invalid_code;
if (UTF_8_4_OCTET_LEADING_P (c1)) if (UTF_8_4_OCTET_LEADING_P (c1))
{
c = (((c1 & 0x7) << 18) | ((c2 & 0x3F) << 12) c = (((c1 & 0x7) << 18) | ((c2 & 0x3F) << 12)
| ((c3 & 0x3F) << 6) | (c4 & 0x3F)); | ((c3 & 0x3F) << 6) | (c4 & 0x3F));
if (c < 0x10000)
goto invalid_code;
}
else else
{ {
ONE_MORE_BYTE (c5); ONE_MORE_BYTE (c5);
@ -1153,7 +1169,7 @@ decode_coding_utf_8 (coding)
c = (((c1 & 0x3) << 24) | ((c2 & 0x3F) << 18) c = (((c1 & 0x3) << 24) | ((c2 & 0x3F) << 18)
| ((c3 & 0x3F) << 12) | ((c4 & 0x3F) << 6) | ((c3 & 0x3F) << 12) | ((c4 & 0x3F) << 6)
| (c5 & 0x3F)); | (c5 & 0x3F));
if (c > MAX_CHAR) if ((c > MAX_CHAR) || (c < 0x200000))
goto invalid_code; goto invalid_code;
} }
else else