Mangalord/backend/tests/crawler_sync.rs

//! Integration tests for `repo::crawler`.
//!
//! Each test runs against a fresh, migrated DB via `#[sqlx::test]`.
//! `DATABASE_URL` must point to a Postgres where the test user can
//! `CREATEDB`.

use mangalord::crawler::source::{SourceChapterRef, SourceManga};
use mangalord::repo::crawler::{self, ChapterDiff, UpsertStatus};
use sqlx::PgPool;
use uuid::Uuid;

/// Helper to spin up a `SourceManga` fixture with a stable shape so
/// each test can tweak just the fields it cares about.
fn sample_manga(key: &str, title: &str, hash: &str) -> SourceManga {
    SourceManga {
        source_manga_key: key.to_string(),
        title: title.to_string(),
        alternative_titles: vec!["Alt 1".into()],
        authors: vec!["Author One".into()],
        // Action is in the seeded `genres` table; Fantasy is too.
        genres: vec!["Action".into(), "Fantasy".into()],
        tags: vec!["popular".into()],
        status: Some("ongoing".into()),
        summary: Some("Sample summary.".into()),
        cover_url: Some("/cover.jpg".into()),
        chapters: vec![],
        metadata_hash: hash.to_string(),
    }
}

#[sqlx::test(migrations = "./migrations")]
async fn ensure_source_is_idempotent(pool: PgPool) {
    crawler::ensure_source(&pool, "target", "Target Site", "https://x.example")
        .await
        .unwrap();
    crawler::ensure_source(&pool, "target", "Target Site v2", "https://x.example")
        .await
        .unwrap();
    let count: (i64,) = sqlx::query_as("SELECT COUNT(*) FROM sources WHERE id = 'target'")
        .fetch_one(&pool)
        .await
        .unwrap();
    assert_eq!(count.0, 1);
    let name: (String,) = sqlx::query_as("SELECT name FROM sources WHERE id = 'target'")
        .fetch_one(&pool)
        .await
        .unwrap();
    assert_eq!(name.0, "Target Site v2", "name updates on re-call");
}

#[sqlx::test(migrations = "./migrations")]
async fn first_upsert_inserts_manga_and_links_metadata(pool: PgPool) {
    crawler::ensure_source(&pool, "target", "T", "https://x.example")
        .await
        .unwrap();
    let m = sample_manga("foo", "Foo Manga", "hash-1");

    let res = crawler::upsert_manga_from_source(&pool, "target", "https://x.example/foo", &m)
        .await
        .unwrap();
    assert_eq!(res.status, UpsertStatus::New);

    // mangas row created
    let row: (String, String, Vec<String>) =
        sqlx::query_as("SELECT title, status, alt_titles FROM mangas WHERE id = $1")
            .bind(res.manga_id)
            .fetch_one(&pool)
            .await
            .unwrap();
    assert_eq!(row.0, "Foo Manga");
    assert_eq!(row.1, "ongoing");
    assert_eq!(row.2, vec!["Alt 1"]);

    // manga_sources row links the two
    let link: (String, Uuid, Option<String>) = sqlx::query_as(
        "SELECT source_id, manga_id, metadata_hash FROM manga_sources WHERE source_manga_key = $1",
    )
    .bind("foo")
    .fetch_one(&pool)
    .await
    .unwrap();
    assert_eq!(link.0, "target");
    assert_eq!(link.1, res.manga_id);
    assert_eq!(link.2.as_deref(), Some("hash-1"));

    // Authors, genres, tags M2M populated
    let n_authors: (i64,) =
        sqlx::query_as("SELECT COUNT(*) FROM manga_authors WHERE manga_id = $1")
            .bind(res.manga_id)
            .fetch_one(&pool)
            .await
            .unwrap();
    assert_eq!(n_authors.0, 1);
    let n_genres: (i64,) =
        sqlx::query_as("SELECT COUNT(*) FROM manga_genres WHERE manga_id = $1")
            .bind(res.manga_id)
            .fetch_one(&pool)
            .await
            .unwrap();
    assert_eq!(n_genres.0, 2, "Action + Fantasy");
    let n_tags: (i64,) = sqlx::query_as("SELECT COUNT(*) FROM manga_tags WHERE manga_id = $1")
        .bind(res.manga_id)
        .fetch_one(&pool)
        .await
        .unwrap();
    assert_eq!(n_tags.0, 1);
}

#[sqlx::test(migrations = "./migrations")]
async fn second_upsert_with_same_hash_reports_unchanged(pool: PgPool) {
    crawler::ensure_source(&pool, "target", "T", "https://x.example")
        .await
        .unwrap();
    let m = sample_manga("foo", "Foo Manga", "hash-1");
    let first = crawler::upsert_manga_from_source(&pool, "target", "https://x.example/foo", &m)
        .await
        .unwrap();
    let second = crawler::upsert_manga_from_source(&pool, "target", "https://x.example/foo", &m)
        .await
        .unwrap();
    assert_eq!(second.status, UpsertStatus::Unchanged);
    assert_eq!(second.manga_id, first.manga_id);
}

#[sqlx::test(migrations = "./migrations")]
async fn upsert_with_changed_hash_updates_fields(pool: PgPool) {
    crawler::ensure_source(&pool, "target", "T", "https://x.example")
        .await
        .unwrap();
    let mut m = sample_manga("foo", "Foo Manga", "hash-1");
    let first = crawler::upsert_manga_from_source(&pool, "target", "https://x.example/foo", &m)
        .await
        .unwrap();

    m.title = "Foo Manga (Revised)".into();
    m.status = Some("completed".into());
    m.metadata_hash = "hash-2".into();
    let second = crawler::upsert_manga_from_source(&pool, "target", "https://x.example/foo", &m)
        .await
        .unwrap();

    assert_eq!(second.status, UpsertStatus::Updated);
    assert_eq!(second.manga_id, first.manga_id);

    let row: (String, String) =
        sqlx::query_as("SELECT title, status FROM mangas WHERE id = $1")
            .bind(first.manga_id)
            .fetch_one(&pool)
            .await
            .unwrap();
    assert_eq!(row.0, "Foo Manga (Revised)");
    assert_eq!(row.1, "completed");
}

#[sqlx::test(migrations = "./migrations")]
async fn sync_chapters_adds_new_refreshes_existing_and_drops_vanished(pool: PgPool) {
    crawler::ensure_source(&pool, "target", "T", "https://x.example")
        .await
        .unwrap();
    let m = sample_manga("foo", "Foo Manga", "hash-1");
    let up = crawler::upsert_manga_from_source(&pool, "target", "https://x.example/foo", &m)
        .await
        .unwrap();

    let initial = vec![
        SourceChapterRef {
            source_chapter_key: "1".into(),
            number: 1,
            title: Some("Ch.1".into()),
            url: "https://x.example/foo/1".into(),
        },
        SourceChapterRef {
            source_chapter_key: "2".into(),
            number: 2,
            title: Some("Ch.2".into()),
            url: "https://x.example/foo/2".into(),
        },
    ];
    let diff = crawler::sync_manga_chapters(&pool, "target", up.manga_id, &initial)
        .await
        .unwrap();
    assert_eq!(
        diff,
        ChapterDiff {
            new: 2,
            refreshed: 0,
            dropped: 0
        }
    );

    // Second run: keep ch1, replace ch2 with ch3 — ch2 should be dropped.
    let second = vec![
        SourceChapterRef {
            source_chapter_key: "1".into(),
            number: 1,
            title: Some("Ch.1 (renamed)".into()),
            url: "https://x.example/foo/1".into(),
        },
        SourceChapterRef {
            source_chapter_key: "3".into(),
            number: 3,
            title: Some("Ch.3".into()),
            url: "https://x.example/foo/3".into(),
        },
    ];
    let diff = crawler::sync_manga_chapters(&pool, "target", up.manga_id, &second)
        .await
        .unwrap();
    assert_eq!(
        diff,
        ChapterDiff {
            new: 1,
            refreshed: 1,
            dropped: 1
        }
    );

    // Renamed title propagated to chapters.title
    let title: (Option<String>,) =
        sqlx::query_as("SELECT c.title FROM chapters c JOIN chapter_sources cs ON cs.chapter_id = c.id WHERE cs.source_chapter_key = '1'")
            .fetch_one(&pool)
            .await
            .unwrap();
    assert_eq!(title.0.as_deref(), Some("Ch.1 (renamed)"));

    // Vanished chapter is soft-dropped (row still exists, dropped_at set).
    let dropped: (Option<chrono::DateTime<chrono::Utc>>,) =
        sqlx::query_as("SELECT dropped_at FROM chapter_sources WHERE source_chapter_key = '2'")
            .fetch_one(&pool)
            .await
            .unwrap();
    assert!(dropped.0.is_some(), "ch2 should be soft-dropped");
}

/// Real-world sources publish multiple chapters at the same number
/// (different uploaders, translator notes, re-releases). After the
/// (manga_id, number) UNIQUE drop in 0013, each `SourceChapterRef`
/// becomes its own `chapters` row even when the parsed number matches
/// — chapter identity is now the chapter id, not the number.
#[sqlx::test(migrations = "./migrations")]
async fn sync_chapters_keeps_duplicate_numbered_chapters_as_separate_rows(pool: PgPool) {
    crawler::ensure_source(&pool, "target", "T", "https://x.example")
        .await
        .unwrap();
    let m = sample_manga("foo", "Foo Manga", "hash-1");
    let up = crawler::upsert_manga_from_source(&pool, "target", "https://x.example/foo", &m)
        .await
        .unwrap();

    // Two distinct uploads of Ch.52 (different uploaders → different
    // URLs/keys, same parsed number) plus a notice/hiatus row that
    // parses to number=0 alongside a real chapter at number 1.
    let chapters = vec![
        SourceChapterRef {
            source_chapter_key: "br_chapter-A".into(),
            number: 52,
            title: Some("Ch.52 : Official".into()),
            url: "https://x.example/foo/A/pg-1/".into(),
        },
        SourceChapterRef {
            source_chapter_key: "br_chapter-B".into(),
            number: 52,
            title: Some("Ch.52 : Official (alt)".into()),
            url: "https://x.example/foo/B/pg-1/".into(),
        },
        SourceChapterRef {
            source_chapter_key: "br_chapter-NOTICE".into(),
            number: 0,
            title: Some("hitaus.".into()),
            url: "https://x.example/foo/notice/pg-1/".into(),
        },
        SourceChapterRef {
            source_chapter_key: "br_chapter-1".into(),
            number: 1,
            title: Some("Ch.1 : Official".into()),
            url: "https://x.example/foo/1/pg-1/".into(),
        },
    ];

    let diff = crawler::sync_manga_chapters(&pool, "target", up.manga_id, &chapters)
        .await
        .unwrap();
    assert_eq!(
        diff,
        ChapterDiff {
            new: 4,
            refreshed: 0,
            dropped: 0
        },
        "every source ref yields a new chapter row"
    );

    let rows: (i64,) =
        sqlx::query_as("SELECT COUNT(*) FROM chapters WHERE manga_id = $1")
            .bind(up.manga_id)
            .fetch_one(&pool)
            .await
            .unwrap();
    assert_eq!(rows.0, 4, "4 distinct chapter rows even with duplicate numbers");

    let ch52_count: (i64,) = sqlx::query_as(
        "SELECT COUNT(*) FROM chapters WHERE manga_id = $1 AND number = 52",
    )
    .bind(up.manga_id)
    .fetch_one(&pool)
    .await
    .unwrap();
    assert_eq!(ch52_count.0, 2, "both Ch.52 uploads survive as separate rows");
}

#[sqlx::test(migrations = "./migrations")]
async fn mark_dropped_mangas_only_drops_unseen(pool: PgPool) {
    crawler::ensure_source(&pool, "target", "T", "https://x.example")
        .await
        .unwrap();
    // Seed two mangas before "now" so a later run_started_at sees them as stale.
    let _ = crawler::upsert_manga_from_source(
        &pool,
        "target",
        "https://x.example/foo",
        &sample_manga("foo", "Foo", "hf"),
    )
    .await
    .unwrap();
    let _ = crawler::upsert_manga_from_source(
        &pool,
        "target",
        "https://x.example/bar",
        &sample_manga("bar", "Bar", "hb"),
    )
    .await
    .unwrap();

    // Now mark a new "run" beginning. Re-upsert only `foo` — `bar`
    // should be the one flagged dropped.
    let run_started = chrono::Utc::now();
    // Sleep briefly so the second upsert's NOW() > run_started_at.
    tokio::time::sleep(std::time::Duration::from_millis(20)).await;
    let _ = crawler::upsert_manga_from_source(
        &pool,
        "target",
        "https://x.example/foo",
        &sample_manga("foo", "Foo", "hf"),
    )
    .await
    .unwrap();

    let n = crawler::mark_dropped_mangas(&pool, "target", run_started)
        .await
        .unwrap();
    assert_eq!(n, 1, "only bar should have been dropped");

    let foo_dropped: (Option<chrono::DateTime<chrono::Utc>>,) =
        sqlx::query_as("SELECT dropped_at FROM manga_sources WHERE source_manga_key = 'foo'")
            .fetch_one(&pool)
            .await
            .unwrap();
    assert!(foo_dropped.0.is_none(), "foo seen this run, must not be dropped");
    let bar_dropped: (Option<chrono::DateTime<chrono::Utc>>,) =
        sqlx::query_as("SELECT dropped_at FROM manga_sources WHERE source_manga_key = 'bar'")
            .fetch_one(&pool)
            .await
            .unwrap();
    assert!(bar_dropped.0.is_some());
}

#[sqlx::test(migrations = "./migrations")]
async fn upsert_surfaces_cover_image_path_for_backfill_decisions(pool: PgPool) {
    crawler::ensure_source(&pool, "target", "T", "https://x.example")
        .await
        .unwrap();
    let m = sample_manga("foo", "Foo", "h1");

    // First upsert: row is brand new, no cover stored yet.
    let first = crawler::upsert_manga_from_source(&pool, "target", "https://x.example/foo", &m)
        .await
        .unwrap();
    assert!(first.cover_image_path.is_none(), "new manga has no cover yet");

    // Simulate cover landing in storage post-upsert.
    sqlx::query("UPDATE mangas SET cover_image_path = $1 WHERE id = $2")
        .bind("mangas/foo/cover.jpg")
        .bind(first.manga_id)
        .execute(&pool)
        .await
        .unwrap();

    // Second upsert with same hash → Unchanged, but cover path is now
    // surfaced so the caller knows the backfill is done.
    let second = crawler::upsert_manga_from_source(&pool, "target", "https://x.example/foo", &m)
        .await
        .unwrap();
    assert_eq!(second.status, UpsertStatus::Unchanged);
    assert_eq!(
        second.cover_image_path.as_deref(),
        Some("mangas/foo/cover.jpg")
    );
}

#[sqlx::test(migrations = "./migrations")]
async fn arbitrary_genres_from_source_get_inserted(pool: PgPool) {
    crawler::ensure_source(&pool, "target", "T", "https://x.example")
        .await
        .unwrap();
    let mut m = sample_manga("foo", "Foo", "h");
    // "Action" is seeded by migration 0009. "Webtoons" is not.
    m.genres = vec!["Action".into(), "Webtoons".into()];

    let up = crawler::upsert_manga_from_source(&pool, "target", "https://x.example/foo", &m)
        .await
        .unwrap();

    let n_genre_links: (i64,) =
        sqlx::query_as("SELECT COUNT(*) FROM manga_genres WHERE manga_id = $1")
            .bind(up.manga_id)
            .fetch_one(&pool)
            .await
            .unwrap();
    assert_eq!(n_genre_links.0, 2, "both seeded and source-added genres attach");

    let webtoons: (i64,) =
        sqlx::query_as("SELECT COUNT(*) FROM genres WHERE name = 'Webtoons'")
            .fetch_one(&pool)
            .await
            .unwrap();
    assert_eq!(webtoons.0, 1, "non-seeded genre was inserted");

    // Case-insensitive de-dup: a second sync with the genre re-cased
    // attaches the existing row, not a new one.
    let mut m2 = sample_manga("bar", "Bar", "h2");
    m2.genres = vec!["webtoons".into()];
    let _ = crawler::upsert_manga_from_source(&pool, "target", "https://x.example/bar", &m2)
        .await
        .unwrap();
    let webtoons_count: (i64,) =
        sqlx::query_as("SELECT COUNT(*) FROM genres WHERE lower(name) = 'webtoons'")
            .fetch_one(&pool)
            .await
            .unwrap();
    assert_eq!(webtoons_count.0, 1, "case-insensitive lookup reuses the existing row");
}

/// User-attached tags (rows with non-NULL `added_by` in `manga_tags`)
/// must survive a crawler upsert. The crawler owns source-attached tags
/// (added_by IS NULL); user attachments are owned by the user who made
/// them and the recurring metadata pass must not delete them.
#[sqlx::test(migrations = "./migrations")]
async fn sync_tags_preserves_user_attached_tags(pool: PgPool) {
    crawler::ensure_source(&pool, "target", "T", "https://x.example")
        .await
        .unwrap();
    let m = sample_manga("foo", "Foo Manga", "hash-1");
    let up = crawler::upsert_manga_from_source(&pool, "target", "https://x.example/foo", &m)
        .await
        .unwrap();

    // A real user attaches a personal tag.
    let user = mangalord::repo::user::create(&pool, "alice", "phc-stub")
        .await
        .unwrap();
    let outcome = mangalord::repo::tag::attach_to_manga(&pool, up.manga_id, "personal", user.id)
        .await
        .unwrap();
    assert!(outcome.created_attachment);

    // Second crawler pass. Use a different metadata_hash so the upsert
    // takes the Updated branch, but the bug also fires on Unchanged
    // ticks since sync_tags runs unconditionally.
    let mut m2 = m.clone();
    m2.metadata_hash = "hash-2".into();
    m2.tags = vec!["popular".into(), "weekly".into()];
    let _ = crawler::upsert_manga_from_source(&pool, "target", "https://x.example/foo", &m2)
        .await
        .unwrap();

    // The user tag must still be attached.
    let user_tag_rows: (i64,) = sqlx::query_as(
        "SELECT COUNT(*) FROM manga_tags mt \
           JOIN tags t ON t.id = mt.tag_id \
          WHERE mt.manga_id = $1 AND lower(t.name) = 'personal' \
            AND mt.added_by = $2",
    )
    .bind(up.manga_id)
    .bind(user.id)
    .fetch_one(&pool)
    .await
    .unwrap();
    assert_eq!(
        user_tag_rows.0, 1,
        "user-attached tag must survive a crawler upsert"
    );

    // The source's tags should still attach as well, as crawler-owned.
    let source_tag_rows: (i64,) = sqlx::query_as(
        "SELECT COUNT(*) FROM manga_tags mt \
           JOIN tags t ON t.id = mt.tag_id \
          WHERE mt.manga_id = $1 \
            AND mt.added_by IS NULL \
            AND lower(t.name) IN ('popular', 'weekly')",
    )
    .bind(up.manga_id)
    .fetch_one(&pool)
    .await
    .unwrap();
    assert_eq!(source_tag_rows.0, 2, "source tags re-attach on each pass");

    // A subsequent pass where the source drops a previously-seen tag
    // must clear that crawler-owned attachment (otherwise crawler-tags
    // would only ever accumulate).
    let mut m3 = m2.clone();
    m3.metadata_hash = "hash-3".into();
    m3.tags = vec!["popular".into()];
    let _ = crawler::upsert_manga_from_source(&pool, "target", "https://x.example/foo", &m3)
        .await
        .unwrap();
    let weekly_rows: (i64,) = sqlx::query_as(
        "SELECT COUNT(*) FROM manga_tags mt \
           JOIN tags t ON t.id = mt.tag_id \
          WHERE mt.manga_id = $1 AND lower(t.name) = 'weekly'",
    )
    .bind(up.manga_id)
    .fetch_one(&pool)
    .await
    .unwrap();
    assert_eq!(weekly_rows.0, 0, "source-owned tag dropped by source goes away");

    // And the user tag still survives that third pass.
    let user_tag_rows: (i64,) = sqlx::query_as(
        "SELECT COUNT(*) FROM manga_tags mt \
           JOIN tags t ON t.id = mt.tag_id \
          WHERE mt.manga_id = $1 AND lower(t.name) = 'personal' \
            AND mt.added_by = $2",
    )
    .bind(up.manga_id)
    .bind(user.id)
    .fetch_one(&pool)
    .await
    .unwrap();
    assert_eq!(user_tag_rows.0, 1);
}

/// `manga_tags.added_by` is `ON DELETE SET NULL` on the user FK. When
/// the attaching user is deleted, their attachments become orphans
/// indistinguishable from crawler-owned rows — and the crawler should
/// reap them on the next pass. Pins the semantic so a future change
/// can't quietly leave orphan rows lying around.
#[sqlx::test(migrations = "./migrations")]
async fn sync_tags_garbage_collects_orphan_user_attachments(pool: PgPool) {
    crawler::ensure_source(&pool, "target", "T", "https://x.example")
        .await
        .unwrap();
    let m = sample_manga("foo", "Foo", "hash-1");
    let up = crawler::upsert_manga_from_source(&pool, "target", "https://x.example/foo", &m)
        .await
        .unwrap();

    // A user attaches "personal", then the user gets deleted. The
    // attachment row stays (manga_tags.manga_id FK is CASCADE on
    // mangas only; we never CASCADE-delete user attachments). The FK
    // on added_by is `ON DELETE SET NULL`, so the row's owner column
    // goes NULL — same shape as a crawler-owned row.
    let user = mangalord::repo::user::create(&pool, "bob", "phc-stub")
        .await
        .unwrap();
    let _ = mangalord::repo::tag::attach_to_manga(&pool, up.manga_id, "personal", user.id)
        .await
        .unwrap();
    sqlx::query("DELETE FROM users WHERE id = $1")
        .bind(user.id)
        .execute(&pool)
        .await
        .unwrap();

    // Sanity: the orphan still exists post-user-delete with added_by NULL.
    let (orphan_rows,): (i64,) = sqlx::query_as(
        "SELECT COUNT(*) FROM manga_tags mt \
           JOIN tags t ON t.id = mt.tag_id \
          WHERE mt.manga_id = $1 AND lower(t.name) = 'personal' \
            AND mt.added_by IS NULL",
    )
    .bind(up.manga_id)
    .fetch_one(&pool)
    .await
    .unwrap();
    assert_eq!(orphan_rows, 1);

    // Next crawler pass — orphan should be reaped along with any
    // other source-owned rows that aren't in the new tag list.
    let mut m2 = m.clone();
    m2.metadata_hash = "hash-2".into();
    m2.tags = vec!["popular".into()];
    let _ = crawler::upsert_manga_from_source(&pool, "target", "https://x.example/foo", &m2)
        .await
        .unwrap();
    let (orphan_rows,): (i64,) = sqlx::query_as(
        "SELECT COUNT(*) FROM manga_tags mt \
           JOIN tags t ON t.id = mt.tag_id \
          WHERE mt.manga_id = $1 AND lower(t.name) = 'personal'",
    )
    .bind(up.manga_id)
    .fetch_one(&pool)
    .await
    .unwrap();
    assert_eq!(orphan_rows, 0, "orphan user-attached tag should be reaped");
}

#[sqlx::test(migrations = "./migrations")]
async fn re_appearing_manga_clears_dropped_at(pool: PgPool) {
    crawler::ensure_source(&pool, "target", "T", "https://x.example")
        .await
        .unwrap();
    let m = sample_manga("foo", "Foo", "h1");
    let up = crawler::upsert_manga_from_source(&pool, "target", "https://x.example/foo", &m)
        .await
        .unwrap();

    // Drop it manually.
    sqlx::query(
        "UPDATE manga_sources SET dropped_at = NOW() WHERE source_manga_key = 'foo'",
    )
    .execute(&pool)
    .await
    .unwrap();

    // Re-upsert: the link should un-drop.
    let _ = crawler::upsert_manga_from_source(&pool, "target", "https://x.example/foo", &m)
        .await
        .unwrap();
    let dropped: (Option<chrono::DateTime<chrono::Utc>>, Uuid) = sqlx::query_as(
        "SELECT dropped_at, manga_id FROM manga_sources WHERE source_manga_key = 'foo'",
    )
    .fetch_one(&pool)
    .await
    .unwrap();
    assert!(dropped.0.is_none());
    assert_eq!(dropped.1, up.manga_id);
}