diff options
| author | Jarkko Hietaniemi <jhi@iki.fi> | 2000-10-24 02:55:33 +0000 |
|---|---|---|
| committer | Jarkko Hietaniemi <jhi@iki.fi> | 2000-10-24 02:55:33 +0000 |
| commit | ba210ebec161cde003bc967e8e460c72f71fb70c (patch) | |
| tree | 7eefd78e8e365cbf64ddf49314681d17b83c3025 /embed.pl | |
| parent | 177b92d2814bfc842f28f277e0a2f353c652a5e3 (diff) | |
| download | perl-ba210ebec161cde003bc967e8e460c72f71fb70c.tar.gz | |
Make the UTF-8 decoding stricter and more verbose when
malformation happens. This involved adding an argument
to utf8_to_uv_chk(), which involved changing its prototype,
and prefer STRLEN over I32 for the UTF-8 length, which as
a domino effect necessitated changing the prototypes of
scan_bin(), scan_oct(), scan_hex(), and reg_uni().
The stricter UTF-8 decoding checking uses Markus Kuhn's
UTF-8 Decode Stress Tester from
http://www.cl.cam.ac.uk/~mgk25/ucs/examples/UTF-8-test.txt
p4raw-id: //depot/perl@7416
Diffstat (limited to 'embed.pl')
| -rwxr-xr-x | embed.pl | 12 |
1 files changed, 6 insertions, 6 deletions
@@ -1941,10 +1941,10 @@ p |OP* |scalar |OP* o p |OP* |scalarkids |OP* o p |OP* |scalarseq |OP* o p |OP* |scalarvoid |OP* o -Ap |NV |scan_bin |char* start|I32 len|I32* retlen -Ap |NV |scan_hex |char* start|I32 len|I32* retlen +Ap |NV |scan_bin |char* start|STRLEN len|STRLEN* retlen +Ap |NV |scan_hex |char* start|STRLEN len|STRLEN* retlen Ap |char* |scan_num |char* s|YYSTYPE *lvalp -Ap |NV |scan_oct |char* start|I32 len|I32* retlen +Ap |NV |scan_oct |char* start|STRLEN len|STRLEN* retlen p |OP* |scope |OP* o Ap |char* |screaminstr |SV* bigsv|SV* littlesv|I32 start_shift \ |I32 end_shift|I32 *state|I32 last @@ -2074,8 +2074,8 @@ Ap |I32 |utf8_distance |U8 *a|U8 *b Ap |U8* |utf8_hop |U8 *s|I32 off ApM |U8* |utf8_to_bytes |U8 *s|STRLEN *len ApM |U8* |bytes_to_utf8 |U8 *s|STRLEN *len -Ap |UV |utf8_to_uv |U8 *s|I32* retlen -Ap |UV |utf8_to_uv_chk |U8 *s|I32* retlen|bool checking +Ap |UV |utf8_to_uv |U8 *s|STRLEN* retlen +Ap |UV |utf8_to_uv_chk |U8 *s|STRLEN curlen|STRLEN* retlen|bool checking Ap |U8* |uv_to_utf8 |U8 *d|UV uv p |void |vivify_defelem |SV* sv p |void |vivify_ref |SV* sv|U32 to_what @@ -2358,7 +2358,7 @@ s |regnode*|reg |I32|I32 * s |regnode*|reganode |U8|U32 s |regnode*|regatom |I32 * s |regnode*|regbranch |I32 *|I32 -s |void |reguni |UV|char *|I32* +s |void |reguni |UV|char *|STRLEN* s |regnode*|regclass s |regnode*|regclassutf8 s |I32 |regcurly |char * |