From 67049a5ffa8b7757041edb8f972a0a74fbe5d63d Mon Sep 17 00:00:00 2001 From: Karl Williamson Date: Wed, 27 Jun 2018 22:01:53 -0600 Subject: Make isSTRICT_UTF8_CHAR() an inline function It was a macro that used a trie. This changes to use the dfa constructed in previous commits. I didn't bother with taking measurements. A dfa should have fewer conditionals for many code points. --- regen/regcharclass.pl | 21 --------------------- 1 file changed, 21 deletions(-) (limited to 'regen') diff --git a/regen/regcharclass.pl b/regen/regcharclass.pl index 4884d1abf1..3dee00060b 100755 --- a/regen/regcharclass.pl +++ b/regen/regcharclass.pl @@ -1653,27 +1653,6 @@ SURROGATE: Surrogate code points # that includes all Unicode code points. # #STRICT_UTF8_CHAR: Matches legal Unicode UTF-8 variant code points, no surrrogates nor non-character code points -#0x0080 - 0xD7FF -#0xE000 - 0xFDCF -#0xFDF0 - 0xFFFD -#0x10000 - 0x1FFFD -#0x20000 - 0x2FFFD -#0x30000 - 0x3FFFD -#0x40000 - 0x4FFFD -#0x50000 - 0x5FFFD -#0x60000 - 0x6FFFD -#0x70000 - 0x7FFFD -#0x80000 - 0x8FFFD -#0x90000 - 0x9FFFD -#0xA0000 - 0xAFFFD -#0xB0000 - 0xBFFFD -#0xC0000 - 0xCFFFD -#0xD0000 - 0xDFFFD -#0xE0000 - 0xEFFFD -#0xF0000 - 0xFFFFD -#0x100000 - 0x10FFFD -# -#STRICT_UTF8_CHAR: Matches legal Unicode UTF-8 variant code points, no surrrogates nor non-character code points #=> UTF8 :no_length_checks only_ebcdic_platform #0x00A0 - 0xD7FF #0xE000 - 0xFDCF -- cgit v1.2.1