mysql: change collation of tag table

utf8mb4_unicode_ci considers that 'caché' is equal to 'cache' which
can lead to attaching incorrect tags to entries. This issue is due to
some unicode normalization done by MySQL.

utf8mb4_bin makes no unicode normalization, letting wallabag to consider
'cache' and 'caché' as two different tags.

We change the collation of the whole table as Doctrine does not support
setting a collation on a column for a specific platform (it tries to
apply utf8mb4_bin even for pgsql and sqlite).

Fixes #3302

Signed-off-by: Kevin Decherf <kevin@kdecherf.com>

1 files changed, 30 insertions, 0 deletions

diff --git a/app/DoctrineMigrations/Version20190511165128.php b/app/DoctrineMigrations/Version20190511165128.php
new file mode 100644
index 00000000..7b6b1bec
--- /dev/null
+++ b/app/DoctrineMigrations/Version20190511165128.php
@@ -0,0 +1,30 @@
+<?php
+
+declare(strict_types=1);
+
+namespace Application\Migrations;
+
+use Doctrine\DBAL\Schema\Schema;
+use Wallabag\CoreBundle\Doctrine\WallabagMigration;
+
+/**
+ * Convert tab label to utf8mb4_bin (MySQL only).
+ */
+final class Version20190511165128 extends WallabagMigration
+{
+    public function up(Schema $schema): void
+    {
+        $this->skipIf('mysql' !== $this->connection->getDatabasePlatform()->getName(), 'This migration only apply to MySQL');
+
+        $this->addSql('ALTER TABLE ' . $this->getTable('tag') . ' CHANGE `label` `label` longtext CHARACTER SET utf8mb4 COLLATE utf8mb4_bin;');
+        $this->addSql('ALTER TABLE ' . $this->getTable('tag') . ' CHANGE `slug` `slug` VARCHAR(128) CHARACTER SET utf8mb4 COLLATE utf8mb4_bin;');
+    }
+
+    public function down(Schema $schema): void
+    {
+        $this->skipIf('mysql' !== $this->connection->getDatabasePlatform()->getName(), 'This migration only apply to MySQL');
+
+        $this->addSql('ALTER TABLE ' . $this->getTable('tag') . ' CHANGE `slug` `slug` VARCHAR(128) CHARACTER SET utf8mb4 COLLATE utf8mb4_unicode_ci;');
+        $this->addSql('ALTER TABLE ' . $this->getTable('tag') . ' CHANGE `label` `label` longtext CHARACTER SET utf8mb4 COLLATE utf8mb4_unicode_ci;');
+    }
+}