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
生成ファイル
+11 -1
ファイルの表示
@@ -10,7 +10,7 @@
#
# It's strongly recommended that you check this file into your version control system.
ActiveRecord::Schema[8.0].define(version: 2026_07_05_000000) do
ActiveRecord::Schema[8.0].define(version: 2026_07_13_000000) do
create_table "active_storage_attachments", charset: "utf8mb4", collation: "utf8mb4_0900_ai_ci", force: :cascade do |t|
t.string "name", null: false
t.string "record_type", null: false
@@ -331,6 +331,16 @@ ActiveRecord::Schema[8.0].define(version: 2026_07_05_000000) do
t.index ["tag_id"], name: "index_post_tags_on_tag_id"
end
create_table "post_url_sanitisation_rules", primary_key: "priority", id: :integer, charset: "utf8mb4", collation: "utf8mb4_0900_ai_ci", force: :cascade do |t|
t.string "source_pattern", null: false
t.string "replacement", null: false
t.datetime "created_at", null: false
t.datetime "updated_at", null: false
t.datetime "discarded_at"
t.index ["discarded_at"], name: "index_post_url_sanitisation_rules_on_discarded_at"
t.index ["source_pattern"], name: "index_post_url_sanitisation_rules_on_source_pattern", unique: true
end
create_table "post_versions", charset: "utf8mb4", collation: "utf8mb4_0900_ai_ci", force: :cascade do |t|
t.bigint "post_id", null: false
t.integer "version_no", null: false
+37
ファイルの表示
@@ -8,6 +8,43 @@
# MovieGenre.find_or_create_by!(name: genre_name)
# end
post_url_sanitisation_rules = [
{ priority: 10,
source_pattern: '\Ahttps?://youtu\.be/([^/?#]+)(?:[?#].*)?\z',
replacement: 'https://www.youtube.com/watch?v=\1' },
{ priority: 20,
source_pattern: '\Ahttps?://(?:www\.|m\.)?youtube\.com/live/([^/?#]+)(?:[?#].*)?\z',
replacement: 'https://www.youtube.com/watch?v=\1' },
{ priority: 30,
source_pattern: '\Ahttps?://(?:www\.|m\.)?youtube\.com/shorts/([^/?#]+)(?:[?#].*)?\z',
replacement: 'https://www.youtube.com/watch?v=\1' },
{ priority: 40,
source_pattern: '\Ahttps?://(?:www\.|m\.)?youtube\.com/embed/([^/?#]+)(?:[?#].*)?\z',
replacement: 'https://www.youtube.com/watch?v=\1' },
{ priority: 50,
source_pattern:
'\Ahttps?://(?:www\.|m\.)?youtube\.com/watch\?(?:[^#&]+&)*v=([^&#]+)(?:[&#].*)?\z',
replacement: 'https://www.youtube.com/watch?v=\1' },
{ priority: 60,
source_pattern: '\Ahttps?://nico\.ms/([^/?#]+)(?:[?#].*)?\z',
replacement: 'https://www.nicovideo.jp/watch/\1' },
{ priority: 70,
source_pattern: '\Ahttps?://(?:www\.)?nicovideo\.jp/watch/([^?#/]+)(?:[?#].*)?\z',
replacement: 'https://www.nicovideo.jp/watch/\1' }
]
post_url_sanitisation_rule_scope = PostUrlSanitisationRule.unscoped
post_url_sanitisation_rules.each do |attributes|
priority = attributes.fetch(:priority)
source_pattern = attributes.fetch(:source_pattern)
next if post_url_sanitisation_rule_scope.exists?(priority:)
next if post_url_sanitisation_rule_scope.exists?(source_pattern:)
post_url_sanitisation_rule_scope.create!(attributes)
end
material_sync_source_uri = ENV['MATERIAL_SYNC_SOURCE_URI']
material_sync_source_file_id = ENV['MATERIAL_SYNC_SOURCE_FILE_ID']