AI/firecrawl
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/mendableai/firecrawl synced 2025-08-13 04:18:59 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix(queue-worker): bring done add to earlier

Browse Source
This commit is contained in:
Gergő Móricz 2025-01-17 17:46:29 +01:00
parent 13abb2bc0e
commit dbc6d07871
1 changed files with 13 additions and 33 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

46
apps/api/src/services/queue-worker.ts
View File

@ -997,6 +997,19 @@ async function processJob(job: Job & { id: string }, token: string) {
logger.info(`🐂 Job done ${job.id}`); logger.info(`🐂 Job done ${job.id}`);
return data; return data;
} catch (error) { } catch (error) {
if (job.data.crawl_id) {
const sc = (await getCrawl(job.data.crawl_id)) as StoredCrawl;
logger.debug("Declaring job as done...");
await addCrawlJobDone(job.data.crawl_id, job.id, false);
await redisConnection.srem(
"crawl:" + job.data.crawl_id + ":visited_unique",
normalizeURL(job.data.url, sc),
);
await finishCrawlIfNeeded(job, sc);
}
const isEarlyTimeout = const isEarlyTimeout =
error instanceof Error && error.message === "timeout"; error instanceof Error && error.message === "timeout";
const isCancelled = const isCancelled =
@ -1076,39 +1089,6 @@ async function processJob(job: Job & { id: string }, token: string) {
}, },
true, true,
); );
if (job.data.crawl_id) {
const sc = (await getCrawl(job.data.crawl_id)) as StoredCrawl;
logger.debug("Declaring job as done...");
await addCrawlJobDone(job.data.crawl_id, job.id, false);
await redisConnection.srem(
"crawl:" + job.data.crawl_id + ":visited_unique",
normalizeURL(job.data.url, sc),
);
await finishCrawlIfNeeded(job, sc);
// await logJob({
// job_id: job.data.crawl_id,
// success: false,
// message:
// typeof error === "string"
// ? error
// : error.message ??
// "Something went wrong... Contact help@mendable.ai",
// num_docs: 0,
// docs: [],
// time_taken: 0,
// team_id: job.data.team_id,
// mode: job.data.crawlerOptions !== null ? "crawl" : "batch_scrape",
// url: sc ? sc.originUrl ?? job.data.url : job.data.url,
// crawlerOptions: sc ? sc.crawlerOptions : undefined,
// scrapeOptions: sc ? sc.scrapeOptions : job.data.scrapeOptions,
// origin: job.data.origin,
// });
}
// done(null, data);
return data; return data;
} }
} }