jrmccluskey commented on code in PR #29175:
URL: https://github.com/apache/beam/pull/29175#discussion_r1378855433
##########
sdks/python/apache_beam/transforms/util.py:
##########
@@ -646,6 +647,113 @@ def finish_bundle(self):
self._target_batch_size = self._batch_size_estimator.next_batch_size()
+def _pardo_stateful_batch_elements(
+ input_coder: coders.Coder,
+ batch_size_estimator: _BatchSizeEstimator,
+ max_buffering_duration_secs: int,
+ clock=time.time):
+ ELEMENT_STATE = BagStateSpec('values', input_coder)
+ COUNT_STATE = CombiningValueStateSpec('count', input_coder, CountCombineFn())
+ BATCH_SIZE_STATE = ReadModifyWriteStateSpec('batch_size', input_coder)
+ WINDOW_TIMER = TimerSpec('window_end', TimeDomain.WATERMARK)
+ BUFFERING_TIMER = TimerSpec('buffering_end', TimeDomain.REAL_TIME)
+ BATCH_ESTIMATOR_STATE = ReadModifyWriteStateSpec(
+ 'batch_estimator', coders.PickleCoder())
+
+ class _StatefulBatchElementsDoFn(DoFn):
+ def process(
+ self,
+ element,
+ window=DoFn.WindowParam,
+ element_state=DoFn.StateParam(ELEMENT_STATE),
+ count_state=DoFn.StateParam(COUNT_STATE),
+ batch_size_state=DoFn.StateParam(BATCH_SIZE_STATE),
+ batch_estimator_state=DoFn.StateParam(BATCH_ESTIMATOR_STATE),
+ window_timer=DoFn.TimerParam(WINDOW_TIMER),
+ buffering_timer=DoFn.TimerParam(BUFFERING_TIMER)):
+ state_estimator = batch_estimator_state.read()
+ if state_estimator is not None:
+ batch_estimator = state_estimator
+ else:
+ # Should only happen on the first element
+ batch_estimator = batch_size_estimator
Review Comment:
Done
--
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]
