From ff5ff8d0d27bd8482171399ece41182a8072fc33 Mon Sep 17 00:00:00 2001 From: Brad Morrical Date: Fri, 28 Feb 2020 09:26:18 -0600 Subject: [PATCH] fix invalid byte sequence in UTF-8 (ArgumentError) (#9077) --- script/import_scripts/simplepress.rb | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/script/import_scripts/simplepress.rb b/script/import_scripts/simplepress.rb index 6932338009d..3375258790f 100644 --- a/script/import_scripts/simplepress.rb +++ b/script/import_scripts/simplepress.rb @@ -195,6 +195,11 @@ class ImportScripts::SimplePress < ImportScripts::Base def process_simplepress_post(raw, import_id) s = raw.dup + # fix invalid byte sequence in UTF-8 (ArgumentError) + unless s.valid_encoding? + s.force_encoding("UTF-8") + end + # convert the quote line s.gsub!(/\[quote='([^']+)'.*?pid='(\d+).*?\]/) { "[quote=\"#{convert_username($1, import_id)}, " + post_id_to_post_num_and_topic($2, import_id) + '"]'