Files
Mangalord/backend/tests/api_admin_crawler.rs
MechaCat02 832042d2b7 fix(crawler): review findings — requeue dedup, restart result, session validation
- requeue_dead_jobs: when a chapter has multiple dead jobs, revive only the
  newest (DISTINCT ON the chapter key) so a single UPDATE can't flip two
  dead rows for one chapter to pending and violate the partial unique dedup
  index (was a 500 that requeued nothing). Non-chapter jobs fall back to row
  id. Regression test added. (critical)
- coordinated_restart: a caller that coalesces into an in-progress restart
  now reports that restart's real outcome instead of a blind success, so the
  session-update "valid" / restart "ok" signal can't be falsely positive.
- SessionController::update: reject control chars / ';' / ',' in PHPSESSID
  before it reaches the cookie string + CDP cookie. Test added.
- Add non-admin 403 test on a mutating crawler endpoint; fix stale
  stream-to-storage doc comment.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-03 21:07:10 +02:00

182 lines
5.4 KiB
Rust

//! Integration tests for the admin crawler observability/control API.
//!
//! The default test harness wires `AppState.crawler = None` (no daemon),
//! so the *control* endpoints return 503 and the *read* endpoints that
//! work off the DB (status shell, dead-jobs list/requeue) still function.
//! This is exactly the production "daemon disabled" posture.
mod common;
use axum::http::StatusCode;
use axum::Router;
use serde_json::json;
use sqlx::PgPool;
use tower::ServiceExt;
use uuid::Uuid;
use common::{body_json, get, get_with_cookie, post_json_with_cookie, register_user, harness};
async fn seed_admin(pool: &PgPool, app: &Router) -> String {
let (username, cookie) = register_user(app).await;
let u = mangalord::repo::user::find_by_username(pool, &username)
.await
.unwrap()
.unwrap();
mangalord::repo::user::set_is_admin_unchecked(pool, u.id, true)
.await
.unwrap();
cookie
}
async fn seed_dead_job(pool: &PgPool, title: &str) -> Uuid {
let manga_id = Uuid::new_v4();
let chapter_id = Uuid::new_v4();
sqlx::query("INSERT INTO mangas (id, title) VALUES ($1, $2)")
.bind(manga_id)
.bind(title)
.execute(pool)
.await
.unwrap();
sqlx::query("INSERT INTO chapters (id, manga_id, number) VALUES ($1, $2, 1)")
.bind(chapter_id)
.bind(manga_id)
.execute(pool)
.await
.unwrap();
let job_id = Uuid::new_v4();
sqlx::query(
"INSERT INTO crawler_jobs (id, payload, state, attempts, last_error) \
VALUES ($1, $2, 'dead', 5, 'boom')",
)
.bind(job_id)
.bind(json!({
"kind": "sync_chapter_content",
"source_id": "target",
"chapter_id": chapter_id,
"source_chapter_key": "k",
}))
.execute(pool)
.await
.unwrap();
job_id
}
#[sqlx::test(migrations = "./migrations")]
async fn get_status_requires_admin(pool: PgPool) {
let h = harness(pool);
// Unauthenticated → 401.
let resp = h.app.clone().oneshot(get("/api/v1/admin/crawler")).await.unwrap();
assert_eq!(resp.status(), StatusCode::UNAUTHORIZED);
// Authenticated non-admin → 403.
let (_u, cookie) = register_user(&h.app).await;
let resp = h
.app
.clone()
.oneshot(get_with_cookie("/api/v1/admin/crawler", &cookie))
.await
.unwrap();
assert_eq!(resp.status(), StatusCode::FORBIDDEN);
}
#[sqlx::test(migrations = "./migrations")]
async fn get_status_reports_disabled_daemon_with_queue_counts(pool: PgPool) {
seed_dead_job(&pool, "Naruto").await;
let h = harness(pool.clone());
let cookie = seed_admin(&pool, &h.app).await;
let resp = h
.app
.clone()
.oneshot(get_with_cookie("/api/v1/admin/crawler", &cookie))
.await
.unwrap();
assert_eq!(resp.status(), StatusCode::OK);
let body = body_json(resp).await;
assert_eq!(body["daemon"], "disabled");
assert_eq!(body["queue"]["dead"], 1);
assert_eq!(body["browser"], "down");
}
#[sqlx::test(migrations = "./migrations")]
async fn control_endpoints_return_503_when_daemon_disabled(pool: PgPool) {
let h = harness(pool.clone());
let cookie = seed_admin(&pool, &h.app).await;
for uri in [
"/api/v1/admin/crawler/run",
"/api/v1/admin/crawler/browser/restart",
"/api/v1/admin/crawler/session/clear-expired",
] {
let resp = h
.app
.clone()
.oneshot(post_json_with_cookie(uri, json!({}), &cookie))
.await
.unwrap();
assert_eq!(
resp.status(),
StatusCode::SERVICE_UNAVAILABLE,
"{uri} should be 503 when daemon disabled"
);
}
}
#[sqlx::test(migrations = "./migrations")]
async fn mutating_endpoints_reject_non_admin(pool: PgPool) {
let h = harness(pool);
// A logged-in non-admin must be forbidden from a mutating endpoint.
let (_u, cookie) = register_user(&h.app).await;
let resp = h
.app
.clone()
.oneshot(post_json_with_cookie(
"/api/v1/admin/crawler/dead-jobs/requeue",
json!({ "scope": "all" }),
&cookie,
))
.await
.unwrap();
assert_eq!(resp.status(), StatusCode::FORBIDDEN);
}
#[sqlx::test(migrations = "./migrations")]
async fn dead_jobs_list_and_requeue_over_http(pool: PgPool) {
let job_id = seed_dead_job(&pool, "Bleach").await;
let h = harness(pool.clone());
let cookie = seed_admin(&pool, &h.app).await;
// List.
let resp = h
.app
.clone()
.oneshot(get_with_cookie("/api/v1/admin/crawler/dead-jobs", &cookie))
.await
.unwrap();
assert_eq!(resp.status(), StatusCode::OK);
let body = body_json(resp).await;
assert_eq!(body["page"]["total"], 1);
assert_eq!(body["items"][0]["manga_title"], "Bleach");
// Requeue the single job.
let resp = h
.app
.clone()
.oneshot(post_json_with_cookie(
"/api/v1/admin/crawler/dead-jobs/requeue",
json!({ "scope": "job", "job_id": job_id }),
&cookie,
))
.await
.unwrap();
assert_eq!(resp.status(), StatusCode::OK);
let body = body_json(resp).await;
assert_eq!(body["requeued"], 1);
let state: String = sqlx::query_scalar("SELECT state FROM crawler_jobs WHERE id = $1")
.bind(job_id)
.fetch_one(&pool)
.await
.unwrap();
assert_eq!(state, "pending");
}