TheNeuralBit commented on a change in pull request #14568:
URL: https://github.com/apache/beam/pull/14568#discussion_r628276678
##########
File path: sdks/python/apache_beam/dataframe/schemas_test.py
##########
@@ -203,19 +223,32 @@ def test_batch_with_df_transform(self):
proxy=schemas.generate_proxy(Animal)))
assert_that(res, equal_to([('Falcon', 375.), ('Parrot', 25.)]))
+ def assert_typehints_equal(self, left, right):
+ left = typehints.normalize(left)
+ right = typehints.normalize(right)
+
+ if _match_is_named_tuple(left):
+ self.assertTrue(_match_is_named_tuple(right))
+ self.assertEqual(left.__annotations__, right.__annotations__)
+ else:
+ self.assertEqual(left, right)
+
@parameterized.expand(SERIES_TESTS + NOINDEX_DF_TESTS)
- def test_unbatch_no_index(self, df_or_series, rows):
+ def test_unbatch_no_index(self, df_or_series, rows, beam_type):
proxy = df_or_series[:0]
with TestPipeline() as p:
res = (
p | beam.Create([df_or_series[::2], df_or_series[1::2]])
| schemas.UnbatchPandas(proxy))
+ # Verify that the unbatched PCollection has the expected typehint
+ self.assert_typehints_equal(res.element_type, beam_type)
Review comment:
I see. I suppose we should be able to map them to RowTypeConstraint.
I'll add a TODO(BEAM-8538) and make `_match_is_named_tuple` public
--
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]
