Fix recovery stale-URL handling and task accounting

This commit is contained in:
Fisto
2026-09-18 11:59:41 +02:00
parent 2ae90b23f4
commit e3edd9c200
6 changed files with 67 additions and 13 deletions
+8 -2
View File
@@ -709,7 +709,8 @@ export class ScrapeEngine {
// resolve one from the provider or the page before caching it.
let previewRow = row;
if (row.source === "embed" && !row.preview_url) {
const resolved = await resolveEmbedPreview(row, options);
// play_url is the refreshed direct media link; url may carry an expired signature.
const resolved = await resolveEmbedPreview({ ...row, url: row.play_url ?? row.url }, options);
if (!resolved) {
store.markPreviewError(row.id, "no preview source");
result.skipped++;
@@ -812,7 +813,12 @@ export class ScrapeEngine {
playUrl: row.play_url
});
if (refreshed && refreshed !== previewRow.url) {
const retry = await downloadPreview({ ...previewRow, url: refreshed }, join(dir, "thumbs"), options);
let retryRow = { ...previewRow, url: refreshed };
if (row.source === "embed") {
const again = await resolveEmbedPreview({ ...row, url: refreshed }, options);
if (again) retryRow = { ...retryRow, preview_url: again };
}
const retry = await downloadPreview(retryRow, join(dir, "thumbs"), options);
if (retry.state === "downloaded" && retry.hash) {
store.markPreview(row.id, {
hash: retry.hash,
+13 -4
View File
@@ -572,13 +572,18 @@ export class ScrapeStore {
this.db.prepare("UPDATE media SET preview_suspect = NULL, preview_retry_at = NULL WHERE id = ?").run(id);
}
/** Discord-CDN rows closed out with an HTTP error; the recovery task retries these. */
/**
* Discord-CDN rows the recovery task retries: closed out with an HTTP error, or suspect rows
* whose single retry already failed (they may have been hit by the same stale-URL bug).
*/
discordPreviewFailures(limit = 5000): MediaRow[] {
return this.db
.prepare(
`SELECT * FROM media
WHERE preview_hash IS NULL AND preview_error IS NOT NULL
AND lower(url) LIKE '%discordapp%'
WHERE preview_hash IS NULL
AND lower(COALESCE(url, '') || ' ' || COALESCE(play_url, '')) LIKE '%discordapp%'
AND (preview_error IS NOT NULL
OR (preview_suspect IS NOT NULL AND preview_retry_at IS NULL))
ORDER BY id LIMIT ?`
)
.all(limit) as unknown as MediaRow[];
@@ -591,7 +596,11 @@ export class ScrapeStore {
discordPreviewFailureCount(): number {
const row = this.db
.prepare(
"SELECT COUNT(*) AS count FROM media WHERE preview_hash IS NULL AND preview_error IS NOT NULL AND lower(url) LIKE '%discordapp%'"
`SELECT COUNT(*) AS count FROM media
WHERE preview_hash IS NULL
AND lower(COALESCE(url, '') || ' ' || COALESCE(play_url, '')) LIKE '%discordapp%'
AND (preview_error IS NOT NULL
OR (preview_suspect IS NOT NULL AND preview_retry_at IS NULL))`
)
.get() as { count: number | null } | undefined;
return row?.count ?? 0;