From 5de771224a3059eb8e6744f74c9893d81910bdc4 Mon Sep 17 00:00:00 2001
From: starflowerbracken <starflower.bracken@gmail.com>
Date: Wed, 29 Sep 2021 12:44:03 +0100
Subject: [PATCH] Update SearchEvents.pl

Remove four-byte UTF-8 BMP characters that MySQL won't like. The best way was to simply remove them by regex.
---
 SearchEvents.pl | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/SearchEvents.pl b/SearchEvents.pl
index 2d2c6ef..bddb8d9 100644
--- a/SearchEvents.pl
+++ b/SearchEvents.pl
@@ -60,6 +60,9 @@
 		$description =~ s/\xA0/ /g;
 		$description =~ s/&amp;nbsp;/ /g;
 		$description =~ s/&nbsp;/ /g;
+		# the next two lines remove four-byte UTF-8 characters that MySQL won't like
+		my $not_bmp = qr([\x{10000}-\x{10FFFF}]);
+		$description =~ s/$not_bmp//g;
 		
 		use HTML::Strip;
 	
@@ -77,6 +80,8 @@
 		$name =~ s/\xA0/ /g;
 		$name =~ s/&amp;nbsp;/ /g;
 		$name =~ s/&nbsp;/ /g;
+		# the next line removes four-byte UTF-8 characters that MySQL won't like (see above)
+		$name =~ s/$not_bmp//g;
 		# had to comment these out as another source of problem characters
 		#utf8::decode($name);