Merge pull request #9767 from alphagov/convert-to-utf8mb4

Convert all tables to use UTF8MB4 charset
alphagov · Feb 3, 2025 · ff06996 · ff06996
2 parents 95985ce + 6bab3a5
commit ff06996
Show file tree

Hide file tree

Showing 3 changed files with 185 additions and 174 deletions.
diff --git a/config/database.yml b/config/database.yml
@@ -1,5 +1,5 @@
 default: &default
-  encoding: utf8
+  encoding: utf8mb4
   adapter: mysql2
   prepared_statements: true
   variables:

diff --git a/db/data_migration/2024121711524600_convert_text_columns_to_utf8mb4.rb b/db/data_migration/2024121711524600_convert_text_columns_to_utf8mb4.rb
@@ -0,0 +1,11 @@
+# Convert all tables to utf8mb4 in order to improve support for non-English languages.
+
+connection = ActiveRecord::Base.connection
+# Disable foreign key constraints because foreign keys using strings will prevent conversion due to a charset mismatch.
+connection.execute "SET foreign_key_checks = 0;"
+connection.tables.each do |table|
+  puts "START: Converting table #{table} to utf8mb4"
+  connection.execute "ALTER TABLE `#{table}` CONVERT TO CHARACTER SET utf8mb4 COLLATE utf8mb4_unicode_ci;"
+  puts "END: Converted table #{table} to utf8mb4"
+end
+connection.execute "SET foreign_key_checks = 1;"