From ef8fe557841c440bf9e3e13ee0801bc127091b7e Mon Sep 17 00:00:00 2001
From: Kaz Kylheku <kaz@kylheku.com>
Date: Thu, 21 Apr 2016 06:57:42 -0700
Subject: Handle non-UTF-8 byte in regex scanned from string.

The current behavior is that there is no lex rule for this, so such a
byte gets echoed.

parser.l (grammar): Add fallback rule to match one byte
in SREGEX state and turn it into 0xDCxx character.
---
 parser.l | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/parser.l b/parser.l
index d87e03eb..9ac79228 100644
--- a/parser.l
+++ b/parser.l
@@ -872,6 +872,12 @@ UONLY   {U2}{U}|{U3}{U}{U}|{U4}{U}{U}{U}
   return REGCHAR;
 }
 
+<SREGEX>. {
+  /* Allow non-UTF-8 byte for regexes scanned from string */
+  yylval->chr = (unsigned char) yytext[0] + 0xDC00;
+  return REGCHAR;
+}
+
 <REGEX>. {
   yyerrprepf(yyg, lit("non-UTF-8 byte in regex: '\\x~02x'"),
              num(convert(unsigned char, yytext[0])), nao);
-- 
cgit v1.2.3