KoviAnusha commented on code in PR #56910:
URL: https://github.com/apache/airflow/pull/56910#discussion_r2446912912
##########
providers/amazon/src/airflow/providers/amazon/aws/triggers/s3.py:
##########
@@ -108,11 +115,25 @@ async def run(self) -> AsyncIterator[TriggerEvent]:
client, self.bucket_name, self.bucket_key,
self.wildcard_match, self.use_regex
):
if self.should_check_fn:
- s3_objects = await self.hook.get_files_async(
+ raw_objects = await self.hook.get_files_async(
client, self.bucket_name, self.bucket_key,
self.wildcard_match
)
- await asyncio.sleep(self.poke_interval)
- yield TriggerEvent({"status": "running", "files":
s3_objects})
+ files = []
+ for f in raw_objects:
+ metadata = {}
+ if "*" in self.metadata_keys:
+ metadata = await
self.hook.head_object_async(f, self.bucket_name)
+ else:
+ for mk in self.metadata_keys:
+ try:
+ metadata[mk] = f[mk]
+ except KeyError:
+ self.log.info("Key %s not found,
performing head_object", mk)
+ obj = await
self.hook.head_object_async(f, self.bucket_name)
+ metadata[mk] = obj.get(mk, None)
+ files.append(metadata)
+
+ yield TriggerEvent({"status": "running", "files":
files})
Review Comment:
Great fix. This brings deferrable and non-deferrable modes into full parity
by restoring context and metadata consistency. As a growth note, it might help
to add a small test ensuring both modes return identical structures to prevent
regressions in future.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
