KevinGG commented on a change in pull request #15490:
URL: https://github.com/apache/beam/pull/15490#discussion_r708459476
##########
File path: sdks/python/apache_beam/runners/interactive/sql/beam_sql_magics.py
##########
@@ -267,27 +284,65 @@ def _build_query_components(
"""
if found:
user_pipeline = next(iter(found.values())).pipeline
- cache_manager = ie.current_env().get_cache_manager(user_pipeline)
- instrumentation = inst.build_pipeline_instrument(user_pipeline)
sql_pipeline = beam.Pipeline(options=user_pipeline._options)
ie.current_env().add_derived_pipeline(user_pipeline, sql_pipeline)
sql_source = {}
- if instrumentation.has_unbounded_sources:
+ if has_source_to_cache(user_pipeline):
sql_source = pcolls_from_streaming_cache(
- user_pipeline, sql_pipeline, found, instrumentation, cache_manager)
+ user_pipeline, sql_pipeline, found)
else:
+ cache_manager = ie.current_env().get_cache_manager(
+ user_pipeline, create_if_absent=True)
for pcoll_name, pcoll in found.items():
- cache_key = instrumentation.cache_key(pcoll)
+ cache_key = CacheKey.from_pcoll(pcoll_name, pcoll).to_str()
sql_source[pcoll_name] = pcoll_from_file_cache(
sql_pipeline, pcoll, cache_manager, cache_key)
if len(sql_source) == 1:
query = replace_single_pcoll_token(query, next(iter(sql_source.keys())))
sql_source = next(iter(sql_source.values()))
else:
sql_source = beam.Pipeline()
+ ie.current_env().add_user_pipeline(sql_source)
return query, sql_source
+@progress_indicated
+def cache_output(output_name: str, output: PValue) -> None:
+ user_pipeline = ie.current_env().user_pipeline(output.pipeline)
+ if user_pipeline:
+ cache_manager = ie.current_env().get_cache_manager(
+ user_pipeline, create_if_absent=True)
+ else:
+ _LOGGER.warning(
+ 'Something is wrong with %s. Cannot introspect its data.', output)
+ return
+ key = CacheKey.from_pcoll(output_name, output).to_str()
+
+ class Reify(beam.DoFn):
+ def process(
+ self,
+ e,
+ w=beam.DoFn.WindowParam,
+ p=beam.DoFn.PaneInfoParam,
+ t=beam.DoFn.TimestampParam):
+ yield test_stream.WindowedValueHolder(WindowedValue(e, t, [w], p))
+
+ _ = (
+ output | '{}{}'.format('Reify', key) >> beam.ParDo(Reify())
+ | '{}{}'.format('WriteSqlOutputCache', key) >> cache.WriteCache(
+ cache_manager, key))
Review comment:
Yes, I'll refactor them into a common module under `caching` package.
--
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]
