Files
Mangalord/backend/tests/crawler_incremental.rs
MechaCat02 9b4f3525f6 feat: incremental crawl mode with seed-completion gate (0.33.0)
Daemon now auto-detects mode per source: Backfill until the first
full walk records `seed_completed:<source>` in `crawler_state`, then
Incremental (newest-first, stops after N consecutive Unchanged
upserts). `CRAWLER_MODE` overrides to a fixed mode; CLI rejects
`auto` since it has no pre-run DB state.

`Source::discover` returns a lazy `DiscoverWalk` so Incremental can
break out mid-walk without prefetching pages. The drop pass and seed
marker are now gated on a true full walk — fixes a latent soft-drop
of the index tail under partial sweeps.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-28 06:41:16 +02:00

86 lines
3.1 KiB
Rust

//! Integration tests for the incremental-mode coordination state:
//! `mark_seed_completed` / `seed_completed_at` round-trip via the
//! `crawler_state` table.
//!
//! End-to-end pipeline behavior (walker + stop-on-Unchanged) requires
//! a real `chromiumoxide::Browser` to construct a `FetchContext`, so
//! the live integration of that path is covered by
//! `crawler_browser_smoke.rs` instead. The pure stop logic itself is
//! unit-tested in `crawler::pipeline::tests`.
use chrono::Utc;
use mangalord::repo::crawler;
use sqlx::PgPool;
#[sqlx::test(migrations = "./migrations")]
async fn seed_completed_at_none_before_any_run(pool: PgPool) {
crawler::ensure_source(&pool, "target", "T", "https://x.example")
.await
.unwrap();
let res = crawler::seed_completed_at(&pool, "target").await.unwrap();
assert!(res.is_none(), "fresh source has no seed marker");
}
#[sqlx::test(migrations = "./migrations")]
async fn mark_seed_completed_then_read_round_trips_timestamp(pool: PgPool) {
crawler::ensure_source(&pool, "target", "T", "https://x.example")
.await
.unwrap();
let at = Utc::now();
crawler::mark_seed_completed(&pool, "target", at)
.await
.unwrap();
let read = crawler::seed_completed_at(&pool, "target")
.await
.unwrap()
.expect("marker present after mark");
// RFC3339 round-trip is millisecond-precise on chrono::Utc; allow a
// 1ms tolerance to absorb postgres jsonb whitespace canonicalization.
let drift = (read - at).num_milliseconds().abs();
assert!(drift <= 1, "round-trip drift: {drift}ms (at={at}, read={read})");
}
#[sqlx::test(migrations = "./migrations")]
async fn mark_seed_completed_overwrites_previous_value(pool: PgPool) {
crawler::ensure_source(&pool, "target", "T", "https://x.example")
.await
.unwrap();
let first = Utc::now() - chrono::Duration::hours(1);
let second = Utc::now();
crawler::mark_seed_completed(&pool, "target", first)
.await
.unwrap();
crawler::mark_seed_completed(&pool, "target", second)
.await
.unwrap();
let read = crawler::seed_completed_at(&pool, "target")
.await
.unwrap()
.expect("marker present");
let drift = (read - second).num_milliseconds().abs();
assert!(drift <= 1, "should reflect the latest mark, not the first");
}
#[sqlx::test(migrations = "./migrations")]
async fn seed_completed_is_per_source(pool: PgPool) {
// Two sources, only one is marked complete. The other must still
// report None — the key is namespaced by source_id.
crawler::ensure_source(&pool, "target", "T", "https://x.example")
.await
.unwrap();
crawler::ensure_source(&pool, "other", "O", "https://y.example")
.await
.unwrap();
crawler::mark_seed_completed(&pool, "target", Utc::now())
.await
.unwrap();
assert!(crawler::seed_completed_at(&pool, "target")
.await
.unwrap()
.is_some());
assert!(crawler::seed_completed_at(&pool, "other")
.await
.unwrap()
.is_none());
}