rohdesamuel commented on a change in pull request #11148: [BEAM-8335] Adds a
streaming wordcount integration test
URL: https://github.com/apache/beam/pull/11148#discussion_r397351701
##########
File path:
sdks/python/apache_beam/runners/interactive/interactive_runner_test.py
##########
@@ -147,6 +150,97 @@ def process(self, element):
]
self.assertEqual(actual_reified, expected_reified)
+ def test_streaming_wordcount(self):
+ class WordExtractingDoFn(beam.DoFn):
+ def process(self, element):
+ text_line = element.strip()
+ words = text_line.split()
+ return words
+
+ # Add the TestStream so that it can be cached.
+ ib.options.capturable_sources.add(TestStream)
+ ib.options.capture_duration = timedelta(seconds=1)
+
+ p = beam.Pipeline(
+ runner=interactive_runner.InteractiveRunner(),
+ options=StandardOptions(streaming=True))
+
+ data = (
+ p
+ | TestStream()
+ .advance_watermark_to(0)
+ .advance_processing_time(1)
+ .add_elements(['to', 'be', 'or', 'not', 'to', 'be'])
+ .advance_watermark_to(20)
+ .advance_processing_time(1)
+ .add_elements(['to', 'be', 'or', 'not', 'to', 'be'])
+ .advance_watermark_to(40)
+ .advance_processing_time(1)
+ .add_elements(['to', 'be', 'or', 'not', 'to', 'be'])
+ | beam.WindowInto(beam.window.FixedWindows(10))) # yapf: disable
+
+ counts = (
+ data
+ | 'split' >> beam.ParDo(WordExtractingDoFn())
+ | 'pair_with_one' >> beam.Map(lambda x: (x, 1))
+ | 'group' >> beam.GroupByKey()
+ | 'count' >> beam.Map(lambda wordones: (wordones[0],
sum(wordones[1]))))
+
+ # Watch the local scope for Interactive Beam so that referenced
PCollections
+ # will be cached.
+ ib.watch(locals())
+
+ # This is normally done in the interactive_utils when a transform is
+ # applied but needs an IPython environment. So we manually run this here.
+ ie.current_env().track_user_pipelines()
+
+ # This tests that the data was correctly cached.
+ pane_info = PaneInfo(True, True, PaneInfoTiming.UNKNOWN, 0, 0)
+ expected_data_df = pd.DataFrame(
+ [('to', 0, [beam.window.IntervalWindow(0, 10)], pane_info),
Review comment:
Initially I had the test to generate the data in code, but I felt that this
was more explicit and easier to show what we are expecting. In some ways, the
test is about the data and to make that obvious and explicit makes it easier to
understand.
----------------------------------------------------------------
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:
us...@infra.apache.org
With regards,
Apache Git Services
