WweiL commented on code in PR #41540:
URL: https://github.com/apache/spark/pull/41540#discussion_r1230027267
##########
python/pyspark/sql/streaming/listener.py:
##########
@@ -155,11 +156,31 @@ class QueryStartedEvent:
This API is evolving.
"""
- def __init__(self, jevent: JavaObject) -> None:
- self._id: uuid.UUID = uuid.UUID(jevent.id().toString())
- self._runId: uuid.UUID = uuid.UUID(jevent.runId().toString())
- self._name: Optional[str] = jevent.name()
- self._timestamp: str = jevent.timestamp()
+ def __init__(
+ self, id: uuid.UUID, runId: uuid.UUID, name: Optional[str], timestamp:
str
+ ) -> None:
+ self._id: uuid.UUID = id
+ self._runId: uuid.UUID = runId
+ self._name: Optional[str] = name
+ self._timestamp: str = timestamp
+
+ @classmethod
+ def fromJObject(cls, jevent: JavaObject) -> "QueryStartedEvent":
+ return cls(
+ id=uuid.UUID(jevent.id().toString()),
+ runId=uuid.UUID(jevent.runId().toString()),
+ name=jevent.name(),
+ timestamp=jevent.timestamp(),
+ )
+
+ @classmethod
+ def fromJson(cls, j: Dict[str, Any]) -> "QueryStartedEvent":
Review Comment:
Sure! Here is the pointer:
https://github.com/apache/spark/pull/41096/files#r1230025798
Note that it's draft code so it's really messy. Basically since we register
a scala listener but run python code inside it. We need a way to send the
events to python process. And JSON is a safe way for that job
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
