robertwb commented on a change in pull request #11005: [BEAM-8335] Modify the
StreamingCache to subclass the CacheManager
URL: https://github.com/apache/beam/pull/11005#discussion_r387271259
##########
File path: sdks/python/apache_beam/runners/direct/transform_evaluator.py
##########
@@ -432,6 +455,45 @@ def finish_bundle(self):
self, self.bundles, [], None, {None: self._watermark})
+class PairWithTimingEvaluator(_TransformEvaluator):
+ """TransformEvaluator for the PairWithTiming transform.
+
+ This transform takes an element as an input and outputs
+ KV(element, `TimingInfo`). Where the `TimingInfo` contains both the
+ processing time timestamp and watermark.
+ """
+ def __init__(
+ self,
+ evaluation_context,
+ applied_ptransform,
+ input_committed_bundle,
+ side_inputs):
+ assert not side_inputs
+ super(PairWithTimingEvaluator, self).__init__(
+ evaluation_context,
+ applied_ptransform,
+ input_committed_bundle,
+ side_inputs)
+
+ def start_bundle(self):
+ main_output = list(self._outputs)[0]
+ self.bundle = self._evaluation_context.create_bundle(main_output)
+
+ def process_element(self, element):
+ watermark_manager = self._evaluation_context._watermark_manager
+ watermarks = watermark_manager.get_watermarks(self._applied_ptransform)
+
+ output_watermark = watermarks.output_watermark
+ now = Timestamp(seconds=watermark_manager._clock.time())
+ timing_info = TimingInfo(now, output_watermark)
+
+ element.value = (element.value, timing_info)
Review comment:
Don't mutate the input.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
