URL 正規化 (#409) (#410)

Reviewed-on: #410
Co-authored-by: miteruzo <miteruzo@naver.com>
Co-committed-by: miteruzo <miteruzo@naver.com>
このコミットはPull リクエスト #410 でマージされました.
このコミットが含まれているのは:
2026-07-14 12:38:02 +09:00
committed by みてるぞ
コミット 38650b5671
9個のファイルの変更674行の追加5行の削除
+61
ファイルの表示
@@ -0,0 +1,61 @@
class CreatePostUrlSanitisationRules < ActiveRecord::Migration[8.0]
class PostUrlSanitisationRule < ActiveRecord::Base
self.table_name = 'post_url_sanitisation_rules'
end
def up
create_table :post_url_sanitisation_rules, id: :integer, primary_key: :priority do |t|
t.string :source_pattern, null: false
t.string :replacement, null: false
t.timestamps
t.datetime :discarded_at
t.index :source_pattern, unique: true
t.index :discarded_at
end
now = Time.current
PostUrlSanitisationRule.insert_all!([
{ priority: 10,
source_pattern: '\Ahttps?://youtu\.be/([^/?#]+)(?:[?#].*)?\z',
replacement: 'https://www.youtube.com/watch?v=\1',
created_at: now,
updated_at: now },
{ priority: 20,
source_pattern: '\Ahttps?://(?:www\.|m\.)?youtube\.com/live/([^/?#]+)(?:[?#].*)?\z',
replacement: 'https://www.youtube.com/watch?v=\1',
created_at: now,
updated_at: now },
{ priority: 30,
source_pattern: '\Ahttps?://(?:www\.|m\.)?youtube\.com/shorts/([^/?#]+)(?:[?#].*)?\z',
replacement: 'https://www.youtube.com/watch?v=\1',
created_at: now,
updated_at: now },
{ priority: 40,
source_pattern: '\Ahttps?://(?:www\.|m\.)?youtube\.com/embed/([^/?#]+)(?:[?#].*)?\z',
replacement: 'https://www.youtube.com/watch?v=\1',
created_at: now,
updated_at: now },
{ priority: 50,
source_pattern:
'\Ahttps?://(?:www\.|m\.)?youtube\.com/watch\?(?:[^#&]+&)*v=([^&#]+)(?:[&#].*)?\z',
replacement: 'https://www.youtube.com/watch?v=\1',
created_at: now,
updated_at: now },
{ priority: 60,
source_pattern: '\Ahttps?://nico\.ms/([^/?#]+)(?:[?#].*)?\z',
replacement: 'https://www.nicovideo.jp/watch/\1',
created_at: now,
updated_at: now },
{ priority: 70,
source_pattern: '\Ahttps?://(?:www\.)?nicovideo\.jp/watch/([^?#/]+)(?:[?#].*)?\z',
replacement: 'https://www.nicovideo.jp/watch/\1',
created_at: now,
updated_at: now }])
end
def down
drop_table :post_url_sanitisation_rules
end
end