fabi/Mangalord
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

perf: denormalize content-warning filter to manga_content_warnings

Browse Source 
The content-warning include/exclude filter (and its count) ran a correlated
page_content_warnings->pages->chapters join per candidate manga — O(mangas *
pages) on every filtered list. Add a manga_content_warnings(manga_id, warning)
table holding each manga's deduped warning union, maintained by triggers that
recompute an affected manga's set (delete+reinsert of the tiny five-label set,
robust across page/chapter/manga cascade deletes), backfilled in the migration.
The filter is now a single indexed lookup.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
MechaCat02
2026-07-11 14:24:31 +02:00
parent d749b56d58
commit c11df3182c
6 changed files with 150 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
backend/Cargo.lock generated
View File

@@ -1558,7 +1558,7 @@ checksum = "c41e0c4fef86961ac6d6f8a82609f55f31b05e4fce149ac5710e439df7619ba4"
[[package]]
name = "mangalord"
version = "0.124.22"
version = "0.124.23"
dependencies = [
"anyhow",
"argon2",

2
backend/Cargo.toml
View File

@@ -1,6 +1,6 @@
[package]
name = "mangalord"
version = "0.124.22"
version = "0.124.23"
edition = "2021"
default-run = "mangalord"

103
backend/migrations/0036_manga_content_warnings.sql Normal file
View File

@@ -0,0 +1,103 @@
-- Denormalized manga -> content-warning set.
--
-- The list filter previously tested each candidate manga with a correlated
-- `page_content_warnings -> pages -> chapters` join, i.e. O(mangas * pages) on
-- every filtered list AND its count. This table holds the DISTINCT union of a
-- manga's page warnings so the filter is a single indexed lookup.
--
-- Kept in sync by triggers that recompute an affected manga's set from current
-- data (the set is tiny — at most the five moderation labels — so a
-- delete-and-reinsert per change is cheap and always correct, sidestepping the
-- cascade-ordering hazards of incremental maintenance).
CREATE TABLE manga_content_warnings (
manga_id uuid NOT NULL REFERENCES mangas(id) ON DELETE CASCADE,
warning text NOT NULL
CHECK (warning IN ('sexual', 'nudity', 'gore', 'violence', 'disturbing')),
PRIMARY KEY (manga_id, warning)
);
-- warning -> mangas, for the include/exclude list filters.
CREATE INDEX manga_content_warnings_warning_idx ON manga_content_warnings (warning);
-- Recompute a single manga's warning set from the live per-page rows.
CREATE OR REPLACE FUNCTION mcw_refresh_for_manga(mid uuid) RETURNS void AS $$
BEGIN
-- Skip when the manga is gone (e.g. mid-cascade of a manga delete) so we
-- never re-insert a row that would violate the FK / resurrect a deleted set.
IF NOT EXISTS (SELECT 1 FROM mangas WHERE id = mid) THEN
RETURN;
END IF;
DELETE FROM manga_content_warnings WHERE manga_id = mid;
INSERT INTO manga_content_warnings (manga_id, warning)
SELECT DISTINCT mid, pw.warning
FROM page_content_warnings pw
JOIN pages p ON p.id = pw.page_id
JOIN chapters c ON c.id = p.chapter_id
WHERE c.manga_id = mid;
END;
$$ LANGUAGE plpgsql;
-- page_content_warnings changed for a page: refresh that page's manga.
CREATE OR REPLACE FUNCTION mcw_on_pcw_change() RETURNS trigger AS $$
DECLARE
mid uuid;
pid uuid := COALESCE(NEW.page_id, OLD.page_id);
BEGIN
-- The page (and thus chapter) may already be gone when this fires as part
-- of a pages/chapters cascade; in that case the pages/chapters triggers do
-- the refresh instead, so a missing join here is harmless.
SELECT c.manga_id INTO mid
FROM pages p JOIN chapters c ON c.id = p.chapter_id
WHERE p.id = pid;
IF mid IS NOT NULL THEN
PERFORM mcw_refresh_for_manga(mid);
END IF;
RETURN NULL;
END;
$$ LANGUAGE plpgsql;
CREATE TRIGGER mcw_pcw_ins AFTER INSERT ON page_content_warnings
FOR EACH ROW EXECUTE FUNCTION mcw_on_pcw_change();
CREATE TRIGGER mcw_pcw_del AFTER DELETE ON page_content_warnings
FOR EACH ROW EXECUTE FUNCTION mcw_on_pcw_change();
-- A page was deleted (directly, or via a chapter cascade): its
-- page_content_warnings rows are already cascade-gone, so recompute from the
-- chapter's manga. If the chapter is gone too, the chapters trigger covers it.
CREATE OR REPLACE FUNCTION mcw_on_page_delete() RETURNS trigger AS $$
DECLARE
mid uuid;
BEGIN
SELECT c.manga_id INTO mid FROM chapters c WHERE c.id = OLD.chapter_id;
IF mid IS NOT NULL THEN
PERFORM mcw_refresh_for_manga(mid);
END IF;
RETURN NULL;
END;
$$ LANGUAGE plpgsql;
CREATE TRIGGER mcw_page_del AFTER DELETE ON pages
FOR EACH ROW EXECUTE FUNCTION mcw_on_page_delete();
-- A chapter was deleted (directly, or via a manga cascade): recompute from the
-- chapter's manga. `chapters.manga_id` is on the row, so it is always available
-- even after the child pages have cascaded; the refresh no-ops when the manga
-- itself is being deleted.
CREATE OR REPLACE FUNCTION mcw_on_chapter_delete() RETURNS trigger AS $$
BEGIN
PERFORM mcw_refresh_for_manga(OLD.manga_id);
RETURN NULL;
END;
$$ LANGUAGE plpgsql;
CREATE TRIGGER mcw_chapter_del AFTER DELETE ON chapters
FOR EACH ROW EXECUTE FUNCTION mcw_on_chapter_delete();
-- Backfill from existing per-page rows.
INSERT INTO manga_content_warnings (manga_id, warning)
SELECT DISTINCT c.manga_id, pw.warning
FROM page_content_warnings pw
JOIN pages p ON p.id = pw.page_id
JOIN chapters c ON c.id = p.chapter_id
ON CONFLICT DO NOTHING;

12
backend/src/repo/manga.rs
View File

@@ -144,17 +144,13 @@ const FILTER_WHERE: &str = r#"
AND NOT EXISTS (
SELECT 1 FROM unnest($6::text[]) AS req(w)
WHERE NOT EXISTS (
SELECT 1 FROM page_content_warnings pw
JOIN pages p ON p.id = pw.page_id
JOIN chapters c ON c.id = p.chapter_id
WHERE c.manga_id = mangas.id AND pw.warning = req.w
SELECT 1 FROM manga_content_warnings mcw
WHERE mcw.manga_id = mangas.id AND mcw.warning = req.w
)
)
AND NOT EXISTS (
SELECT 1 FROM page_content_warnings pw
JOIN pages p ON p.id = pw.page_id
JOIN chapters c ON c.id = p.chapter_id
WHERE c.manga_id = mangas.id AND pw.warning = ANY($7::text[])
SELECT 1 FROM manga_content_warnings mcw
WHERE mcw.manga_id = mangas.id AND mcw.warning = ANY($7::text[])
)
"#;

40
backend/tests/api_manga_warnings.rs
View File

@@ -127,6 +127,46 @@ async fn list_filters_by_content_warning(pool: PgPool) {
assert_eq!(ids, want);
}
#[sqlx::test(migrations = "./migrations")]
async fn denormalized_warnings_track_chapter_deletion(pool: PgPool) {
// The denormalized manga_content_warnings table must stay in sync when the
// underlying pages disappear. Deleting the only chapter (which cascade-
// deletes its pages and their page_content_warnings) must drop the manga
// from the include filter.
let h = common::harness(pool.clone());
let gory = seed_manga(&pool, "Gory", &[&["gore"]]).await;
// Present in the denorm table and matched by the filter.
let count: i64 =
sqlx::query_scalar("SELECT count(*) FROM manga_content_warnings WHERE manga_id = $1")
.bind(gory)
.fetch_one(&pool)
.await
.unwrap();
assert_eq!(count, 1, "warning denormalized on insert");
assert_eq!(list_ids(&h.app, "cw_include=gore").await, vec![gory.to_string()]);
// Delete the chapter → cascade removes pages + page_content_warnings →
// trigger recomputes the (now empty) set for this manga.
sqlx::query("DELETE FROM chapters WHERE manga_id = $1")
.bind(gory)
.execute(&pool)
.await
.unwrap();
let count: i64 =
sqlx::query_scalar("SELECT count(*) FROM manga_content_warnings WHERE manga_id = $1")
.bind(gory)
.fetch_one(&pool)
.await
.unwrap();
assert_eq!(count, 0, "warning removed after chapter (and pages) deleted");
assert!(
list_ids(&h.app, "cw_include=gore").await.is_empty(),
"manga no longer matches the include filter"
);
}
#[sqlx::test(migrations = "./migrations")]
async fn list_rejects_unknown_warning(pool: PgPool) {
let h = common::harness(pool.clone());