HeartSaVioR commented on code in PR #45977:
URL: https://github.com/apache/spark/pull/45977#discussion_r1583126915
##########
python/pyspark/sql/streaming/python_streaming_source_runner.py:
##########
@@ -60,14 +68,29 @@ def latest_offset_func(reader: DataSourceStreamReader,
outfile: IO) -> None:
write_with_length(json.dumps(offset).encode("utf-8"), outfile)
-def partitions_func(reader: DataSourceStreamReader, infile: IO, outfile: IO)
-> None:
+def partitions_func(
+ reader: DataSourceStreamReader,
+ data_source: DataSource,
+ schema: StructType,
+ max_arrow_batch_size: int,
+ infile: IO,
+ outfile: IO,
+) -> None:
start_offset = json.loads(utf8_deserializer.loads(infile))
end_offset = json.loads(utf8_deserializer.loads(infile))
partitions = reader.partitions(start_offset, end_offset)
# Return the serialized partition values.
write_int(len(partitions), outfile)
for partition in partitions:
pickleSer._write_with_length(partition, outfile)
+ if isinstance(reader, _SimpleStreamReaderWrapper):
+ it = reader.getCache(start_offset, end_offset)
+ if it is None:
Review Comment:
Never mind, got the rationale.
--
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]
