diff options
| author | Karl Williamson <public@khwilliamson.com> | 2012-09-03 16:59:09 -0600 |
|---|---|---|
| committer | Karl Williamson <public@khwilliamson.com> | 2012-09-13 21:14:03 -0600 |
| commit | 685289b5657b776e8a3871de68a57785e6ccd797 (patch) | |
| tree | effb3627422467ccc329131b12c3de913ff5b8a4 /regcharclass.h | |
| parent | b1af8fefbdf1c044271e0b9d8898e2d808ab7879 (diff) | |
| download | perl-685289b5657b776e8a3871de68a57785e6ccd797.tar.gz | |
Use macro not swash for utf8 quotemeta
The rules for matching whether an above-Latin1 code point are now saved
in a macro generated from a trie by regen/regcharclass.pl, and these are
now used by pp.c to test these cases. This allows removal of a wrapper
subroutine, and also there is no need for dynamic loading at run-time
into a swash.
This macro is about as big as I'm comfortable compiling in, but it
saves the building of a hash that can grow over time, and removes a
subroutine and interpreter variables. Indeed, performance benchmarks
show that it is about the same speed as a hash, but it does not require
having to load the rules in from disk the first time it is used.
Diffstat (limited to 'regcharclass.h')
| -rw-r--r-- | regcharclass.h | 65 |
1 files changed, 65 insertions, 0 deletions
diff --git a/regcharclass.h b/regcharclass.h index 91ab67806d..a7e79ada56 100644 --- a/regcharclass.h +++ b/regcharclass.h @@ -460,6 +460,71 @@ : 0 ) \ : 0 ) +/* + QUOTEMETA: Meta-characters that \Q should quote + + \p{_Perl_Quotemeta} +*/ +/*** GENERATED CODE ***/ +#define is_QUOTEMETA_high(s) \ +( ( 0xCD == ((U8*)s)[0] ) ? \ + ( ( 0x8F == ((U8*)s)[1] ) ? 2 : 0 ) \ +: ( 0xE1 == ((U8*)s)[0] ) ? \ + ( ( 0x85 == ((U8*)s)[1] ) ? \ + ( ( 0x9F == ((U8*)s)[2] || 0xA0 == ((U8*)s)[2] ) ? 3 : 0 ) \ + : ( 0x9A == ((U8*)s)[1] ) ? \ + ( ( 0x80 == ((U8*)s)[2] ) ? 3 : 0 ) \ + : ( 0x9E == ((U8*)s)[1] ) ? \ + ( ( 0xB4 == ((U8*)s)[2] || 0xB5 == ((U8*)s)[2] ) ? 3 : 0 ) \ + : ( 0xA0 == ((U8*)s)[1] ) ? \ + ( ( 0x8B <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x8E ) ? 3 : 0 ) \ + : 0 ) \ +: ( 0xE2 == ((U8*)s)[0] ) ? \ + ( ( 0x80 == ((U8*)s)[1] ) ? \ + ( ( 0x80 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0xBE ) ? 3 : 0 ) \ + : ( 0x81 == ((U8*)s)[1] ) ? \ + ( ( ( 0x81 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x93 ) || ( 0x95 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0xAF ) ) ? 3 : 0 )\ + : ( 0x86 == ((U8*)s)[1] ) ? \ + ( ( 0x90 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0xBF ) ? 3 : 0 ) \ + : ( 0x87 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x90 ) ? \ + ( ( 0x80 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0xBF ) ? 3 : 0 ) \ + : ( 0x91 == ((U8*)s)[1] ) ? \ + ( ( 0x80 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x9F ) ? 3 : 0 ) \ + : ( 0x94 <= ((U8*)s)[1] && ((U8*)s)[1] <= 0x9C ) ? \ + ( ( 0x80 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0xBF ) ? 3 : 0 ) \ + : ( 0x9D == ((U8*)s)[1] ) ? \ + ( ( 0x80 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0xB5 ) ? 3 : 0 ) \ + : ( 0x9E == ((U8*)s)[1] ) ? \ + ( ( 0x94 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0xBF ) ? 3 : 0 ) \ + : ( ( 0x9F <= ((U8*)s)[1] && ((U8*)s)[1] <= 0xAF ) || 0xB8 == ((U8*)s)[1] || 0xB9 == ((U8*)s)[1] ) ?\ + ( ( 0x80 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0xBF ) ? 3 : 0 ) \ + : 0 ) \ +: ( 0xE3 == ((U8*)s)[0] ) ? \ + ( ( 0x80 == ((U8*)s)[1] ) ? \ + ( ( ( 0x80 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x83 ) || ( 0x88 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0xA0 ) || 0xB0 == ((U8*)s)[2] ) ? 3 : 0 )\ + : ( 0x85 == ((U8*)s)[1] ) ? \ + ( ( 0xA4 == ((U8*)s)[2] ) ? 3 : 0 ) \ + : 0 ) \ +: ( 0xEF == ((U8*)s)[0] ) ? \ + ( ( 0xB4 == ((U8*)s)[1] ) ? \ + ( ( 0xBE == ((U8*)s)[2] || 0xBF == ((U8*)s)[2] ) ? 3 : 0 ) \ + : ( 0xB8 == ((U8*)s)[1] ) ? \ + ( ( 0x80 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0x8F ) ? 3 : 0 ) \ + : ( 0xB9 == ((U8*)s)[1] ) ? \ + ( ( 0x85 == ((U8*)s)[2] || 0x86 == ((U8*)s)[2] ) ? 3 : 0 ) \ + : ( 0xBB == ((U8*)s)[1] ) ? \ + ( ( 0xBF == ((U8*)s)[2] ) ? 3 : 0 ) \ + : ( 0xBE == ((U8*)s)[1] ) ? \ + ( ( 0xA0 == ((U8*)s)[2] ) ? 3 : 0 ) \ + : ( 0xBF == ((U8*)s)[1] ) ? \ + ( ( 0xB0 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0xB8 ) ? 3 : 0 ) \ + : 0 ) \ +: ( 0xF0 == ((U8*)s)[0] ) ? \ + ( ( ( ( 0x9D == ((U8*)s)[1] ) && ( 0x85 == ((U8*)s)[2] ) ) && ( 0xB3 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0xBA ) ) ? 4 : 0 )\ +: ( 0xF3 == ((U8*)s)[0] ) ? \ + ( ( ( ( 0xA0 == ((U8*)s)[1] ) && ( 0x80 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0xBF ) ) && ( 0x80 <= ((U8*)s)[3] && ((U8*)s)[3] <= 0xBF ) ) ? 4 : 0 )\ +: 0 ) + #endif /* H_REGCHARCLASS */ |