github.com/apache/beam/sdks/v2@v2.48.2/python/apache_beam/runners/interactive/caching/read_cache.py (about)

     1  #
     2  # Licensed to the Apache Software Foundation (ASF) under one or more
     3  # contributor license agreements.  See the NOTICE file distributed with
     4  # this work for additional information regarding copyright ownership.
     5  # The ASF licenses this file to You under the Apache License, Version 2.0
     6  # (the "License"); you may not use this file except in compliance with
     7  # the License.  You may obtain a copy of the License at
     8  #
     9  #    http://www.apache.org/licenses/LICENSE-2.0
    10  #
    11  # Unless required by applicable law or agreed to in writing, software
    12  # distributed under the License is distributed on an "AS IS" BASIS,
    13  # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
    14  # See the License for the specific language governing permissions and
    15  # limitations under the License.
    16  #
    17  
    18  """Module to read cache of computed PCollections.
    19  
    20  For internal use only; no backward-compatibility guarantees.
    21  """
    22  # pytype: skip-file
    23  
    24  from typing import Tuple
    25  
    26  import apache_beam as beam
    27  from apache_beam.portability.api import beam_runner_api_pb2
    28  from apache_beam.runners.interactive import cache_manager as cache
    29  from apache_beam.runners.interactive.caching.cacheable import Cacheable
    30  from apache_beam.runners.interactive.caching.reify import unreify_from_cache
    31  from apache_beam.runners.pipeline_context import PipelineContext
    32  from apache_beam.transforms.ptransform import PTransform
    33  
    34  
    35  class ReadCache:
    36    """Class that facilitates reading cache of computed PCollections.
    37    """
    38    def __init__(
    39        self,
    40        pipeline: beam_runner_api_pb2.Pipeline,
    41        context: PipelineContext,
    42        cache_manager: cache.CacheManager,
    43        cacheable: Cacheable):
    44      self._pipeline = pipeline
    45      self._context = context
    46      self._cache_manager = cache_manager
    47      self._cacheable = cacheable
    48      self._key = repr(cacheable.to_key())
    49  
    50    def read_cache(self) -> Tuple[str, str]:
    51      """Reads cache of the cacheable PCollection and wires the cache into the
    52      pipeline proto. Returns the pipeline-scoped ids of the cacheable PCollection
    53      and the cache reading output PCollection that replaces it.
    54  
    55      First, it creates a temporary pipeline instance on top of the existing
    56      component_id_map from the self._pipeline's context so that both pipelines
    57      share the context and have no conflict component ids.
    58      Second, it instantiates a _ReadCacheTransform to build the temporary
    59      pipeline with a subgraph under top level transforms that reads the cache of
    60      a cacheable PCollection.
    61      Third, it copies components of the subgraph from the temporary pipeline to
    62      self._pipeline, skipping components that are not in the temporary pipeline
    63      but presents in the component_id_map of self._pipeline. Since to_runner_api
    64      generates components for all entries in the component_id_map, those
    65      component ids from the context shared by self._pipeline need to be ignored.
    66      Last, it replaces inputs of all transforms that consume the cacheable
    67      PCollection with the output PCollection of the _ReadCacheTransform so that
    68      the whole pipeline computes with data from the cache. The pipeline
    69      fragment of reading the cacheable PCollection is now disconnected from the
    70      rest of the pipeline and can be pruned later.
    71      """
    72      template, read_output = self._build_runner_api_template()
    73      output_id = self._context.pcollections.get_id(read_output)
    74      source_id = self._context.pcollections.get_id(self._cacheable.pcoll)
    75      # Copy cache reading subgraph from the template to the pipeline proto.
    76      for pcoll_id in template.components.pcollections:
    77        if pcoll_id in self._pipeline.components.pcollections:
    78          continue
    79        self._pipeline.components.pcollections[pcoll_id].CopyFrom(
    80            template.components.pcollections[pcoll_id])
    81      for coder_id in template.components.coders:
    82        if coder_id in self._pipeline.components.coders:
    83          continue
    84        self._pipeline.components.coders[coder_id].CopyFrom(
    85            template.components.coders[coder_id])
    86      for windowing_strategy_id in template.components.windowing_strategies:
    87        if (windowing_strategy_id in
    88            self._pipeline.components.windowing_strategies):
    89          continue
    90        self._pipeline.components.windowing_strategies[
    91            windowing_strategy_id].CopyFrom(
    92                template.components.windowing_strategies[windowing_strategy_id])
    93      template_root_transform_id = template.root_transform_ids[0]
    94      root_transform_id = self._pipeline.root_transform_ids[0]
    95      for transform_id in template.components.transforms:
    96        if (transform_id == template_root_transform_id or
    97            transform_id in self._pipeline.components.transforms):
    98          continue
    99        self._pipeline.components.transforms[transform_id].CopyFrom(
   100            template.components.transforms[transform_id])
   101      self._pipeline.components.transforms[
   102          root_transform_id].subtransforms.extend(
   103              template.components.transforms[template_root_transform_id].
   104              subtransforms)
   105  
   106      # Replace all the input pcoll of source_id with output pcoll of output_id
   107      # from cache reading.
   108      for transform in self._pipeline.components.transforms.values():
   109        inputs = transform.inputs
   110        if source_id in inputs.values():
   111          keys_need_replacement = set()
   112          for key in inputs:
   113            if inputs[key] == source_id:
   114              keys_need_replacement.add(key)
   115          for key in keys_need_replacement:
   116            inputs[key] = output_id
   117  
   118      return source_id, output_id
   119  
   120    def _build_runner_api_template(
   121        self) -> Tuple[beam_runner_api_pb2.Pipeline, beam.pvalue.PCollection]:
   122      transform = _ReadCacheTransform(self._cache_manager, self._key)
   123      tmp_pipeline = beam.Pipeline()
   124      tmp_pipeline.component_id_map = self._context.component_id_map
   125      read_output = tmp_pipeline | 'source_cache_' >> transform
   126      return tmp_pipeline.to_runner_api(), read_output
   127  
   128  
   129  class _ReadCacheTransform(PTransform):
   130    """A composite transform encapsulates reading cache of PCollections.
   131    """
   132    def __init__(self, cache_manager: cache.CacheManager, key: str):
   133      self._cache_manager = cache_manager
   134      self._key = key
   135  
   136    def expand(self, pcoll: beam.pvalue.PCollection) -> beam.pvalue.PCollection:
   137      return unreify_from_cache(
   138          pipeline=pcoll.pipeline,
   139          cache_key=self._key,
   140          cache_manager=self._cache_manager)