From 7bfb695c454b6d5ce0bd40e37cc8a57d264c7ce2 Mon Sep 17 00:00:00 2001
From: Maxime Coste <mawww@kakoune.org>
Date: Fri, 1 Dec 2017 16:37:18 +0800
Subject: [PATCH] Regex: Do not allow private use codepoints literals

We use them to encode non-literals in lookarounds, so they can
trigger bugs.

Fixes #1737
---
 src/regex_impl.cc | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/regex_impl.cc b/src/regex_impl.cc
index 19516f63..91d1816a 100644
--- a/src/regex_impl.cc
+++ b/src/regex_impl.cc
@@ -292,7 +292,7 @@ private:
             case '|': case ')':
                 return {};
             default:
-                if (contains("^$.*+?[]{}", cp))
+                if (contains("^$.*+?[]{}", cp) or (cp >= 0xF0000 and cp <= 0xFFFFF))
                     parse_error(format("unexpected '{}'", cp));
                 ++m_pos;
                 return new_node(ParsedRegex::Literal, cp);