From 344c1b1709de522e07b97fe39afa96f46dd74515 Mon Sep 17 00:00:00 2001 From: Bruce Hill Date: Sat, 26 Sep 2020 01:15:41 -0700 Subject: Optimization for utf8 --- grammars/utf8-id.bpeg | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) diff --git a/grammars/utf8-id.bpeg b/grammars/utf8-id.bpeg index 978b61f..a1c0bc4 100644 --- a/grammars/utf8-id.bpeg +++ b/grammars/utf8-id.bpeg @@ -1,10 +1,8 @@ # Definitions of UTF8-compliant identifiers utf8-id: utf8-id-start 0+utf8-id-cont -utf8-id-start: - `A-Z -/ `a-z -/ \xc2 (\xaa / \xb5 / \xba) +utf8-id-start: `A-Z / `a-z / !\x00-x7F ( + \xc2 (\xaa / \xb5 / \xba) / \xc3 (\x80-x96 / \x98-xb6 / \xb8-xbf) / \xc4-xca\x80-xbf / \xcb (\x80-x81 / \x86-x91 / \xa0-xa4 / \xac / \xae) @@ -348,13 +346,10 @@ utf8-id-start: / \xae (\x80-xae\x80-xbf / \xaf\x80-xa0) / \xaf (\xa0-xa7\x80-xbf / \xa8\x80-x9d) ) +) -utf8-id-cont: - `0-9 -/ `A-Z -/ `_ -/ `a-z -/ \xc2 (\xaa / \xb5 / \xb7 / \xba) +utf8-id-cont: `0-9 / `A-Z / `_ / `a-z / !\x00-x7F ( + \xc2 (\xaa / \xb5 / \xb7 / \xba) / \xc3 (\x80-x96 / \x98-xb6 / \xb8-xbf) / \xc4-xca\x80-xbf / \xcb (\x80-x81 / \x86-x91 / \xa0-xa4 / \xac / \xae) @@ -737,3 +732,4 @@ utf8-id-cont: / \xaf (\xa0-xa7\x80-xbf / \xa8\x80-x9d) ) / \xf3\xa0 (\x84-x86\x80-xbf / \x87\x80-xaf) +) -- cgit v1.2.3