Abacn commented on code in PR #22130:
URL: https://github.com/apache/beam/pull/22130#discussion_r914941476
##########
sdks/python/apache_beam/io/filebasedsink.py:
##########
@@ -406,10 +417,33 @@ def __init__(self, sink, temp_shard_path):
self.sink = sink
self.temp_shard_path = temp_shard_path
self.temp_handle = self.sink.open(temp_shard_path)
+ self.num_records_written = 0
def write(self, value):
self.sink.write_record(self.temp_handle, value)
+ if self.sink.max_records_per_shard:
+ self.num_records_written += 1
+ return self.num_records_written >= self.sink.max_records_per_shard
+ if self.sink.max_bytes_per_shard:
+ return (
+ self.sink.byte_counter.bytes_written >=
self.sink.max_bytes_per_shard)
def close(self):
self.sink.close(self.temp_handle)
return self.temp_shard_path
+
+
+class _ByteCountingWriter:
Review Comment:
I see, if the writer is compressed, record sends to FileBasedWriter may have
different length to the record actually written and that's why a wrapped class
is needed here
--
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]
