fix: enforce the analysis image cap while reading, not after

The OCR and vision dispatchers read the whole page image into a Vec via
storage.get() and only then checked max_image_bytes, so the cap couldn't
bound the read. Stream via get_stream() + safety::accumulate_capped so the
read bails as soon as the running total exceeds the cap.

Bump to 0.124.6.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
MechaCat02
2026-07-07 21:10:29 +02:00
parent 46134c8760
commit ce9a727c73
6 changed files with 56 additions and 23 deletions

View File

@@ -99,6 +99,36 @@ async fn dispatch_persists_ocr_lines_and_search_doc(pool: PgPool) {
assert!(has_doc, "search_doc must be populated from OCR text");
}
#[sqlx::test(migrations = "./migrations")]
async fn dispatch_rejects_page_image_over_the_byte_cap(pool: PgPool) {
let dir = TempDir::new().unwrap();
let storage: Arc<dyn Storage> = Arc::new(LocalStorage::new(dir.path()));
let key = "mangas/x/big.png";
// 4 KiB on disk, 1 KiB cap — the streamed read must bail on the cap
// rather than buffering the whole blob and OCR-ing it.
storage.put(key, &vec![0u8; 4096]).await.unwrap();
let page_id = seed_page(&pool, key).await;
let dispatcher = OcrAnalyzeDispatcher {
db: pool.clone(),
storage: Arc::clone(&storage),
engine: StubOcrEngine::new(&["should not run"]),
max_image_bytes: 1024,
ocr_permits: Arc::new(tokio::sync::Semaphore::new(1)),
};
let err = dispatcher.dispatch(page_id).await.unwrap_err();
assert!(
err.chain().any(|c| c.to_string().contains("cap")),
"expected an over-cap error, got: {err:#}"
);
// A rejected page must not land an analysis row.
assert!(repo::page_analysis::load(&pool, page_id)
.await
.unwrap()
.is_none());
}
#[sqlx::test(migrations = "./migrations")]
async fn dispatch_missing_page_is_noop(pool: PgPool) {
let dir = TempDir::new().unwrap();