diff options
| author | Yves Orton <demerphq@gmail.com> | 2012-12-06 11:11:47 +0100 |
|---|---|---|
| committer | Yves Orton <demerphq@gmail.com> | 2012-12-06 13:42:42 +0100 |
| commit | 39a0f513a3472b239cae9745b3b89abe93b6ca79 (patch) | |
| tree | 2683790ba1d31f1aeb44384f6c9a0267e2f10a27 /utf8.h | |
| parent | 3ee084aa8474e0a47583aee63a88beeea5d4742f (diff) | |
| download | perl-39a0f513a3472b239cae9745b3b89abe93b6ca79.tar.gz | |
make regcharclass generate submacros if necessary to keep them short
Some compilers can't handle unexpanded macros longer than something
like 8000 characters. So we split up long ones into sub macros to work
around the problem
Diffstat (limited to 'utf8.h')
| -rw-r--r-- | utf8.h | 17 |
1 files changed, 8 insertions, 9 deletions
@@ -476,6 +476,11 @@ Perl's extended UTF-8 means we can have start bytes up to FF. * takes on the order of 10 minutes to generate, and is never going to change. * The EBCDIC equivalent hasn't been commented out in regcharclass.pl, so it * should generate and run the correct stuff */ +/* + UTF8_CHAR: Matches utf8 from 1 to 4 bytes + + 0x0 - 0x1FFFFF +*/ /*** GENERATED CODE ***/ #define is_UTF8_CHAR_utf8_safe(s,e) \ ( ((e)-(s) > 3) ? \ @@ -488,23 +493,17 @@ Perl's extended UTF-8 means we can have start bytes up to FF. ( ( ( ( ((U8*)s)[1] & 0xC0 ) == 0x80 ) && ( ( ((U8*)s)[2] & 0xC0 ) == 0x80 ) ) ? 3 : 0 )\ : ( 0xF0 == ((U8*)s)[0] ) ? \ ( ( ( ( 0x90 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0xBF ) && ( ( ((U8*)s)[2] & 0xC0 ) == 0x80 ) ) && ( ( ((U8*)s)[3] & 0xC0 ) == 0x80 ) ) ? 4 : 0 )\ - : ( 0xF1 <= ((U8*)s)[0] && ((U8*)s)[0] <= 0xF7 ) ? \ - ( ( ( ( ( ((U8*)s)[1] & 0xC0 ) == 0x80 ) && ( ( ((U8*)s)[2] & 0xC0 ) == 0x80 ) ) && ( ( ((U8*)s)[3] & 0xC0 ) == 0x80 ) ) ? 4 : 0 )\ - : 0 ) \ + : ( ( ( ( 0xF1 <= ((U8*)s)[0] && ((U8*)s)[0] <= 0xF7 ) && ( ( ((U8*)s)[1] & 0xC0 ) == 0x80 ) ) && ( ( ((U8*)s)[2] & 0xC0 ) == 0x80 ) ) && ( ( ((U8*)s)[3] & 0xC0 ) == 0x80 ) ) ? 4 : 0 )\ : ((e)-(s) > 2) ? \ ( ( ( ((U8*)s)[0] & 0x80 ) == 0x00 ) ? 1 \ : ( 0xC2 <= ((U8*)s)[0] && ((U8*)s)[0] <= 0xDF ) ? \ ( ( ( ((U8*)s)[1] & 0xC0 ) == 0x80 ) ? 2 : 0 ) \ : ( 0xE0 == ((U8*)s)[0] ) ? \ ( ( ( ( ((U8*)s)[1] & 0xE0 ) == 0xA0 ) && ( ( ((U8*)s)[2] & 0xC0 ) == 0x80 ) ) ? 3 : 0 )\ - : ( 0xE1 <= ((U8*)s)[0] && ((U8*)s)[0] <= 0xEF ) ? \ - ( ( ( ( ((U8*)s)[1] & 0xC0 ) == 0x80 ) && ( ( ((U8*)s)[2] & 0xC0 ) == 0x80 ) ) ? 3 : 0 )\ - : 0 ) \ + : ( ( ( 0xE1 <= ((U8*)s)[0] && ((U8*)s)[0] <= 0xEF ) && ( ( ((U8*)s)[1] & 0xC0 ) == 0x80 ) ) && ( ( ((U8*)s)[2] & 0xC0 ) == 0x80 ) ) ? 3 : 0 )\ : ((e)-(s) > 1) ? \ ( ( ( ((U8*)s)[0] & 0x80 ) == 0x00 ) ? 1 \ - : ( 0xC2 <= ((U8*)s)[0] && ((U8*)s)[0] <= 0xDF ) ? \ - ( ( ( ((U8*)s)[1] & 0xC0 ) == 0x80 ) ? 2 : 0 ) \ - : 0 ) \ + : ( ( 0xC2 <= ((U8*)s)[0] && ((U8*)s)[0] <= 0xDF ) && ( ( ((U8*)s)[1] & 0xC0 ) == 0x80 ) ) ? 2 : 0 )\ : ((e)-(s) > 0) ? \ ( ( ((U8*)s)[0] & 0x80 ) == 0x00 ) \ : 0 ) |