airbyte-cdk 0.72.1__py3-none-any.whl → 6.17.1.dev1__py3-none-any.whl
Sign up to get free protection for your applications and to get access to all the features.
- airbyte_cdk/__init__.py +355 -6
- airbyte_cdk/cli/__init__.py +1 -0
- airbyte_cdk/cli/source_declarative_manifest/__init__.py +5 -0
- airbyte_cdk/cli/source_declarative_manifest/_run.py +230 -0
- airbyte_cdk/cli/source_declarative_manifest/spec.json +17 -0
- airbyte_cdk/config_observation.py +29 -10
- airbyte_cdk/connector.py +24 -24
- airbyte_cdk/connector_builder/README.md +53 -0
- airbyte_cdk/connector_builder/connector_builder_handler.py +37 -11
- airbyte_cdk/connector_builder/main.py +45 -13
- airbyte_cdk/connector_builder/message_grouper.py +189 -50
- airbyte_cdk/connector_builder/models.py +3 -2
- airbyte_cdk/destinations/__init__.py +4 -3
- airbyte_cdk/destinations/destination.py +54 -20
- airbyte_cdk/destinations/vector_db_based/README.md +37 -0
- airbyte_cdk/destinations/vector_db_based/config.py +40 -17
- airbyte_cdk/destinations/vector_db_based/document_processor.py +56 -17
- airbyte_cdk/destinations/vector_db_based/embedder.py +57 -15
- airbyte_cdk/destinations/vector_db_based/test_utils.py +14 -4
- airbyte_cdk/destinations/vector_db_based/utils.py +8 -2
- airbyte_cdk/destinations/vector_db_based/writer.py +24 -5
- airbyte_cdk/entrypoint.py +153 -44
- airbyte_cdk/exception_handler.py +21 -3
- airbyte_cdk/logger.py +30 -44
- airbyte_cdk/models/__init__.py +13 -2
- airbyte_cdk/models/airbyte_protocol.py +86 -1
- airbyte_cdk/models/airbyte_protocol_serializers.py +44 -0
- airbyte_cdk/models/file_transfer_record_message.py +13 -0
- airbyte_cdk/models/well_known_types.py +1 -1
- airbyte_cdk/sources/__init__.py +5 -1
- airbyte_cdk/sources/abstract_source.py +125 -79
- airbyte_cdk/sources/concurrent_source/__init__.py +7 -2
- airbyte_cdk/sources/concurrent_source/concurrent_read_processor.py +102 -36
- airbyte_cdk/sources/concurrent_source/concurrent_source.py +29 -36
- airbyte_cdk/sources/concurrent_source/concurrent_source_adapter.py +94 -10
- airbyte_cdk/sources/concurrent_source/stream_thread_exception.py +25 -0
- airbyte_cdk/sources/concurrent_source/thread_pool_manager.py +20 -14
- airbyte_cdk/sources/config.py +3 -2
- airbyte_cdk/sources/connector_state_manager.py +49 -83
- airbyte_cdk/sources/declarative/async_job/job.py +52 -0
- airbyte_cdk/sources/declarative/async_job/job_orchestrator.py +497 -0
- airbyte_cdk/sources/declarative/async_job/job_tracker.py +75 -0
- airbyte_cdk/sources/declarative/async_job/repository.py +35 -0
- airbyte_cdk/sources/declarative/async_job/status.py +24 -0
- airbyte_cdk/sources/declarative/async_job/timer.py +39 -0
- airbyte_cdk/sources/declarative/auth/__init__.py +2 -3
- airbyte_cdk/sources/declarative/auth/declarative_authenticator.py +3 -1
- airbyte_cdk/sources/declarative/auth/jwt.py +191 -0
- airbyte_cdk/sources/declarative/auth/oauth.py +60 -20
- airbyte_cdk/sources/declarative/auth/selective_authenticator.py +10 -2
- airbyte_cdk/sources/declarative/auth/token.py +28 -10
- airbyte_cdk/sources/declarative/auth/token_provider.py +9 -8
- airbyte_cdk/sources/declarative/checks/check_stream.py +16 -8
- airbyte_cdk/sources/declarative/checks/connection_checker.py +4 -2
- airbyte_cdk/sources/declarative/concurrency_level/__init__.py +7 -0
- airbyte_cdk/sources/declarative/concurrency_level/concurrency_level.py +50 -0
- airbyte_cdk/sources/declarative/concurrent_declarative_source.py +490 -0
- airbyte_cdk/sources/declarative/datetime/datetime_parser.py +4 -0
- airbyte_cdk/sources/declarative/datetime/min_max_datetime.py +26 -6
- airbyte_cdk/sources/declarative/declarative_component_schema.yaml +1185 -85
- airbyte_cdk/sources/declarative/declarative_source.py +5 -2
- airbyte_cdk/sources/declarative/declarative_stream.py +95 -9
- airbyte_cdk/sources/declarative/decoders/__init__.py +23 -2
- airbyte_cdk/sources/declarative/decoders/composite_raw_decoder.py +97 -0
- airbyte_cdk/sources/declarative/decoders/decoder.py +11 -4
- airbyte_cdk/sources/declarative/decoders/json_decoder.py +92 -5
- airbyte_cdk/sources/declarative/decoders/noop_decoder.py +21 -0
- airbyte_cdk/sources/declarative/decoders/pagination_decoder_decorator.py +39 -0
- airbyte_cdk/sources/declarative/decoders/xml_decoder.py +98 -0
- airbyte_cdk/sources/declarative/extractors/__init__.py +12 -1
- airbyte_cdk/sources/declarative/extractors/dpath_extractor.py +29 -24
- airbyte_cdk/sources/declarative/extractors/http_selector.py +4 -5
- airbyte_cdk/sources/declarative/extractors/record_extractor.py +2 -3
- airbyte_cdk/sources/declarative/extractors/record_filter.py +63 -8
- airbyte_cdk/sources/declarative/extractors/record_selector.py +85 -26
- airbyte_cdk/sources/declarative/extractors/response_to_file_extractor.py +177 -0
- airbyte_cdk/sources/declarative/extractors/type_transformer.py +55 -0
- airbyte_cdk/sources/declarative/incremental/__init__.py +31 -3
- airbyte_cdk/sources/declarative/incremental/concurrent_partition_cursor.py +340 -0
- airbyte_cdk/sources/declarative/incremental/datetime_based_cursor.py +156 -48
- airbyte_cdk/sources/declarative/incremental/declarative_cursor.py +13 -0
- airbyte_cdk/sources/declarative/incremental/global_substream_cursor.py +350 -0
- airbyte_cdk/sources/declarative/incremental/per_partition_cursor.py +174 -74
- airbyte_cdk/sources/declarative/incremental/per_partition_with_global.py +200 -0
- airbyte_cdk/sources/declarative/incremental/resumable_full_refresh_cursor.py +122 -0
- airbyte_cdk/sources/declarative/interpolation/filters.py +27 -1
- airbyte_cdk/sources/declarative/interpolation/interpolated_boolean.py +23 -5
- airbyte_cdk/sources/declarative/interpolation/interpolated_mapping.py +12 -8
- airbyte_cdk/sources/declarative/interpolation/interpolated_nested_mapping.py +13 -6
- airbyte_cdk/sources/declarative/interpolation/interpolated_string.py +21 -6
- airbyte_cdk/sources/declarative/interpolation/interpolation.py +9 -3
- airbyte_cdk/sources/declarative/interpolation/jinja.py +72 -37
- airbyte_cdk/sources/declarative/interpolation/macros.py +72 -17
- airbyte_cdk/sources/declarative/manifest_declarative_source.py +193 -52
- airbyte_cdk/sources/declarative/migrations/legacy_to_per_partition_state_migration.py +98 -0
- airbyte_cdk/sources/declarative/migrations/state_migration.py +24 -0
- airbyte_cdk/sources/declarative/models/__init__.py +1 -1
- airbyte_cdk/sources/declarative/models/declarative_component_schema.py +1319 -603
- airbyte_cdk/sources/declarative/parsers/custom_exceptions.py +2 -2
- airbyte_cdk/sources/declarative/parsers/manifest_component_transformer.py +26 -4
- airbyte_cdk/sources/declarative/parsers/manifest_reference_resolver.py +26 -15
- airbyte_cdk/sources/declarative/parsers/model_to_component_factory.py +1759 -225
- airbyte_cdk/sources/declarative/partition_routers/__init__.py +24 -4
- airbyte_cdk/sources/declarative/partition_routers/async_job_partition_router.py +65 -0
- airbyte_cdk/sources/declarative/partition_routers/cartesian_product_stream_slicer.py +176 -0
- airbyte_cdk/sources/declarative/partition_routers/list_partition_router.py +39 -9
- airbyte_cdk/sources/declarative/partition_routers/partition_router.py +62 -0
- airbyte_cdk/sources/declarative/partition_routers/single_partition_router.py +15 -3
- airbyte_cdk/sources/declarative/partition_routers/substream_partition_router.py +222 -39
- airbyte_cdk/sources/declarative/requesters/error_handlers/__init__.py +19 -5
- airbyte_cdk/sources/declarative/requesters/error_handlers/backoff_strategies/__init__.py +3 -1
- airbyte_cdk/sources/declarative/requesters/error_handlers/backoff_strategies/constant_backoff_strategy.py +19 -7
- airbyte_cdk/sources/declarative/requesters/error_handlers/backoff_strategies/exponential_backoff_strategy.py +19 -7
- airbyte_cdk/sources/declarative/requesters/error_handlers/backoff_strategies/header_helper.py +4 -2
- airbyte_cdk/sources/declarative/requesters/error_handlers/backoff_strategies/wait_time_from_header_backoff_strategy.py +41 -9
- airbyte_cdk/sources/declarative/requesters/error_handlers/backoff_strategies/wait_until_time_from_header_backoff_strategy.py +29 -14
- airbyte_cdk/sources/declarative/requesters/error_handlers/backoff_strategy.py +5 -13
- airbyte_cdk/sources/declarative/requesters/error_handlers/composite_error_handler.py +32 -16
- airbyte_cdk/sources/declarative/requesters/error_handlers/default_error_handler.py +46 -56
- airbyte_cdk/sources/declarative/requesters/error_handlers/default_http_response_filter.py +40 -0
- airbyte_cdk/sources/declarative/requesters/error_handlers/error_handler.py +6 -32
- airbyte_cdk/sources/declarative/requesters/error_handlers/http_response_filter.py +119 -41
- airbyte_cdk/sources/declarative/requesters/http_job_repository.py +228 -0
- airbyte_cdk/sources/declarative/requesters/http_requester.py +98 -344
- airbyte_cdk/sources/declarative/requesters/paginators/__init__.py +14 -3
- airbyte_cdk/sources/declarative/requesters/paginators/default_paginator.py +105 -46
- airbyte_cdk/sources/declarative/requesters/paginators/no_pagination.py +14 -8
- airbyte_cdk/sources/declarative/requesters/paginators/paginator.py +19 -8
- airbyte_cdk/sources/declarative/requesters/paginators/strategies/__init__.py +9 -3
- airbyte_cdk/sources/declarative/requesters/paginators/strategies/cursor_pagination_strategy.py +53 -21
- airbyte_cdk/sources/declarative/requesters/paginators/strategies/offset_increment.py +42 -19
- airbyte_cdk/sources/declarative/requesters/paginators/strategies/page_increment.py +25 -12
- airbyte_cdk/sources/declarative/requesters/paginators/strategies/pagination_strategy.py +13 -10
- airbyte_cdk/sources/declarative/requesters/paginators/strategies/stop_condition.py +26 -13
- airbyte_cdk/sources/declarative/requesters/request_options/__init__.py +15 -2
- airbyte_cdk/sources/declarative/requesters/request_options/datetime_based_request_options_provider.py +91 -0
- airbyte_cdk/sources/declarative/requesters/request_options/default_request_options_provider.py +60 -0
- airbyte_cdk/sources/declarative/requesters/request_options/interpolated_nested_request_input_provider.py +31 -14
- airbyte_cdk/sources/declarative/requesters/request_options/interpolated_request_input_provider.py +27 -15
- airbyte_cdk/sources/declarative/requesters/request_options/interpolated_request_options_provider.py +63 -10
- airbyte_cdk/sources/declarative/requesters/request_options/request_options_provider.py +1 -1
- airbyte_cdk/sources/declarative/requesters/requester.py +9 -17
- airbyte_cdk/sources/declarative/resolvers/__init__.py +41 -0
- airbyte_cdk/sources/declarative/resolvers/components_resolver.py +55 -0
- airbyte_cdk/sources/declarative/resolvers/config_components_resolver.py +136 -0
- airbyte_cdk/sources/declarative/resolvers/http_components_resolver.py +112 -0
- airbyte_cdk/sources/declarative/retrievers/__init__.py +6 -2
- airbyte_cdk/sources/declarative/retrievers/async_retriever.py +100 -0
- airbyte_cdk/sources/declarative/retrievers/retriever.py +1 -3
- airbyte_cdk/sources/declarative/retrievers/simple_retriever.py +229 -73
- airbyte_cdk/sources/declarative/schema/__init__.py +14 -1
- airbyte_cdk/sources/declarative/schema/default_schema_loader.py +5 -3
- airbyte_cdk/sources/declarative/schema/dynamic_schema_loader.py +236 -0
- airbyte_cdk/sources/declarative/schema/json_file_schema_loader.py +8 -8
- airbyte_cdk/sources/declarative/spec/spec.py +12 -5
- airbyte_cdk/sources/declarative/stream_slicers/__init__.py +1 -2
- airbyte_cdk/sources/declarative/stream_slicers/declarative_partition_generator.py +88 -0
- airbyte_cdk/sources/declarative/stream_slicers/stream_slicer.py +9 -14
- airbyte_cdk/sources/declarative/transformations/add_fields.py +19 -11
- airbyte_cdk/sources/declarative/transformations/flatten_fields.py +52 -0
- airbyte_cdk/sources/declarative/transformations/keys_replace_transformation.py +61 -0
- airbyte_cdk/sources/declarative/transformations/keys_to_lower_transformation.py +22 -0
- airbyte_cdk/sources/declarative/transformations/keys_to_snake_transformation.py +68 -0
- airbyte_cdk/sources/declarative/transformations/remove_fields.py +13 -10
- airbyte_cdk/sources/declarative/transformations/transformation.py +5 -5
- airbyte_cdk/sources/declarative/types.py +19 -110
- airbyte_cdk/sources/declarative/yaml_declarative_source.py +31 -10
- airbyte_cdk/sources/embedded/base_integration.py +16 -5
- airbyte_cdk/sources/embedded/catalog.py +16 -4
- airbyte_cdk/sources/embedded/runner.py +19 -3
- airbyte_cdk/sources/embedded/tools.py +5 -2
- airbyte_cdk/sources/file_based/README.md +152 -0
- airbyte_cdk/sources/file_based/__init__.py +24 -0
- airbyte_cdk/sources/file_based/availability_strategy/__init__.py +9 -2
- airbyte_cdk/sources/file_based/availability_strategy/abstract_file_based_availability_strategy.py +22 -6
- airbyte_cdk/sources/file_based/availability_strategy/default_file_based_availability_strategy.py +46 -10
- airbyte_cdk/sources/file_based/config/abstract_file_based_spec.py +47 -10
- airbyte_cdk/sources/file_based/config/avro_format.py +2 -1
- airbyte_cdk/sources/file_based/config/csv_format.py +29 -10
- airbyte_cdk/sources/file_based/config/excel_format.py +18 -0
- airbyte_cdk/sources/file_based/config/file_based_stream_config.py +16 -4
- airbyte_cdk/sources/file_based/config/jsonl_format.py +2 -1
- airbyte_cdk/sources/file_based/config/parquet_format.py +2 -1
- airbyte_cdk/sources/file_based/config/unstructured_format.py +13 -5
- airbyte_cdk/sources/file_based/discovery_policy/__init__.py +6 -2
- airbyte_cdk/sources/file_based/discovery_policy/abstract_discovery_policy.py +2 -4
- airbyte_cdk/sources/file_based/discovery_policy/default_discovery_policy.py +7 -2
- airbyte_cdk/sources/file_based/exceptions.py +18 -15
- airbyte_cdk/sources/file_based/file_based_source.py +140 -33
- airbyte_cdk/sources/file_based/file_based_stream_reader.py +69 -5
- airbyte_cdk/sources/file_based/file_types/__init__.py +14 -1
- airbyte_cdk/sources/file_based/file_types/avro_parser.py +75 -24
- airbyte_cdk/sources/file_based/file_types/csv_parser.py +116 -34
- airbyte_cdk/sources/file_based/file_types/excel_parser.py +196 -0
- airbyte_cdk/sources/file_based/file_types/file_transfer.py +37 -0
- airbyte_cdk/sources/file_based/file_types/file_type_parser.py +4 -1
- airbyte_cdk/sources/file_based/file_types/jsonl_parser.py +24 -8
- airbyte_cdk/sources/file_based/file_types/parquet_parser.py +60 -18
- airbyte_cdk/sources/file_based/file_types/unstructured_parser.py +141 -41
- airbyte_cdk/sources/file_based/remote_file.py +1 -1
- airbyte_cdk/sources/file_based/schema_helpers.py +38 -10
- airbyte_cdk/sources/file_based/schema_validation_policies/__init__.py +3 -1
- airbyte_cdk/sources/file_based/schema_validation_policies/abstract_schema_validation_policy.py +3 -1
- airbyte_cdk/sources/file_based/schema_validation_policies/default_schema_validation_policies.py +16 -5
- airbyte_cdk/sources/file_based/stream/abstract_file_based_stream.py +50 -13
- airbyte_cdk/sources/file_based/stream/concurrent/adapters.py +67 -27
- airbyte_cdk/sources/file_based/stream/concurrent/cursor/__init__.py +5 -1
- airbyte_cdk/sources/file_based/stream/concurrent/cursor/abstract_concurrent_file_based_cursor.py +14 -23
- airbyte_cdk/sources/file_based/stream/concurrent/cursor/file_based_concurrent_cursor.py +54 -18
- airbyte_cdk/sources/file_based/stream/concurrent/cursor/file_based_final_state_cursor.py +21 -9
- airbyte_cdk/sources/file_based/stream/cursor/abstract_file_based_cursor.py +3 -1
- airbyte_cdk/sources/file_based/stream/cursor/default_file_based_cursor.py +27 -10
- airbyte_cdk/sources/file_based/stream/default_file_based_stream.py +147 -45
- airbyte_cdk/sources/http_logger.py +8 -3
- airbyte_cdk/sources/message/__init__.py +7 -1
- airbyte_cdk/sources/message/repository.py +18 -4
- airbyte_cdk/sources/source.py +42 -38
- airbyte_cdk/sources/streams/__init__.py +2 -2
- airbyte_cdk/sources/streams/availability_strategy.py +54 -3
- airbyte_cdk/sources/streams/call_rate.py +64 -21
- airbyte_cdk/sources/streams/checkpoint/__init__.py +26 -0
- airbyte_cdk/sources/streams/checkpoint/checkpoint_reader.py +335 -0
- airbyte_cdk/sources/{declarative/incremental → streams/checkpoint}/cursor.py +17 -14
- airbyte_cdk/sources/streams/checkpoint/per_partition_key_serializer.py +22 -0
- airbyte_cdk/sources/streams/checkpoint/resumable_full_refresh_cursor.py +51 -0
- airbyte_cdk/sources/streams/checkpoint/substream_resumable_full_refresh_cursor.py +110 -0
- airbyte_cdk/sources/streams/concurrent/README.md +7 -0
- airbyte_cdk/sources/streams/concurrent/abstract_stream.py +7 -2
- airbyte_cdk/sources/streams/concurrent/adapters.py +84 -75
- airbyte_cdk/sources/streams/concurrent/availability_strategy.py +30 -2
- airbyte_cdk/sources/streams/concurrent/cursor.py +313 -48
- airbyte_cdk/sources/streams/concurrent/default_stream.py +12 -3
- airbyte_cdk/sources/streams/concurrent/exceptions.py +3 -0
- airbyte_cdk/sources/streams/concurrent/helpers.py +14 -3
- airbyte_cdk/sources/streams/concurrent/partition_enqueuer.py +12 -3
- airbyte_cdk/sources/streams/concurrent/partition_reader.py +10 -3
- airbyte_cdk/sources/streams/concurrent/partitions/partition.py +1 -16
- airbyte_cdk/sources/streams/concurrent/partitions/stream_slicer.py +21 -0
- airbyte_cdk/sources/streams/concurrent/partitions/types.py +15 -5
- airbyte_cdk/sources/streams/concurrent/state_converters/abstract_stream_state_converter.py +109 -17
- airbyte_cdk/sources/streams/concurrent/state_converters/datetime_stream_state_converter.py +90 -72
- airbyte_cdk/sources/streams/core.py +412 -87
- airbyte_cdk/sources/streams/http/__init__.py +2 -1
- airbyte_cdk/sources/streams/http/availability_strategy.py +12 -101
- airbyte_cdk/sources/streams/http/error_handlers/__init__.py +22 -0
- airbyte_cdk/sources/streams/http/error_handlers/backoff_strategy.py +28 -0
- airbyte_cdk/sources/streams/http/error_handlers/default_backoff_strategy.py +17 -0
- airbyte_cdk/sources/streams/http/error_handlers/default_error_mapping.py +86 -0
- airbyte_cdk/sources/streams/http/error_handlers/error_handler.py +42 -0
- airbyte_cdk/sources/streams/http/error_handlers/error_message_parser.py +19 -0
- airbyte_cdk/sources/streams/http/error_handlers/http_status_error_handler.py +110 -0
- airbyte_cdk/sources/streams/http/error_handlers/json_error_message_parser.py +52 -0
- airbyte_cdk/sources/streams/http/error_handlers/response_models.py +65 -0
- airbyte_cdk/sources/streams/http/exceptions.py +27 -7
- airbyte_cdk/sources/streams/http/http.py +369 -246
- airbyte_cdk/sources/streams/http/http_client.py +531 -0
- airbyte_cdk/sources/streams/http/rate_limiting.py +76 -12
- airbyte_cdk/sources/streams/http/requests_native_auth/abstract_oauth.py +28 -9
- airbyte_cdk/sources/streams/http/requests_native_auth/abstract_token.py +2 -1
- airbyte_cdk/sources/streams/http/requests_native_auth/oauth.py +90 -35
- airbyte_cdk/sources/streams/http/requests_native_auth/token.py +13 -3
- airbyte_cdk/sources/types.py +154 -0
- airbyte_cdk/sources/utils/record_helper.py +36 -21
- airbyte_cdk/sources/utils/schema_helpers.py +13 -6
- airbyte_cdk/sources/utils/slice_logger.py +4 -1
- airbyte_cdk/sources/utils/transform.py +54 -20
- airbyte_cdk/sql/_util/hashing.py +34 -0
- airbyte_cdk/sql/_util/name_normalizers.py +92 -0
- airbyte_cdk/sql/constants.py +32 -0
- airbyte_cdk/sql/exceptions.py +235 -0
- airbyte_cdk/sql/secrets.py +123 -0
- airbyte_cdk/sql/shared/__init__.py +15 -0
- airbyte_cdk/sql/shared/catalog_providers.py +145 -0
- airbyte_cdk/sql/shared/sql_processor.py +786 -0
- airbyte_cdk/sql/types.py +160 -0
- airbyte_cdk/test/catalog_builder.py +70 -18
- airbyte_cdk/test/entrypoint_wrapper.py +117 -42
- airbyte_cdk/test/mock_http/__init__.py +1 -1
- airbyte_cdk/test/mock_http/matcher.py +6 -0
- airbyte_cdk/test/mock_http/mocker.py +57 -10
- airbyte_cdk/test/mock_http/request.py +19 -3
- airbyte_cdk/test/mock_http/response.py +3 -1
- airbyte_cdk/test/mock_http/response_builder.py +32 -16
- airbyte_cdk/test/state_builder.py +18 -10
- airbyte_cdk/test/utils/__init__.py +1 -0
- airbyte_cdk/test/utils/data.py +24 -0
- airbyte_cdk/test/utils/http_mocking.py +16 -0
- airbyte_cdk/test/utils/manifest_only_fixtures.py +60 -0
- airbyte_cdk/test/utils/reading.py +26 -0
- airbyte_cdk/utils/__init__.py +2 -1
- airbyte_cdk/utils/airbyte_secrets_utils.py +5 -3
- airbyte_cdk/utils/analytics_message.py +10 -2
- airbyte_cdk/utils/datetime_format_inferrer.py +4 -1
- airbyte_cdk/utils/event_timing.py +10 -10
- airbyte_cdk/utils/mapping_helpers.py +3 -1
- airbyte_cdk/utils/message_utils.py +20 -11
- airbyte_cdk/utils/print_buffer.py +75 -0
- airbyte_cdk/utils/schema_inferrer.py +198 -28
- airbyte_cdk/utils/slice_hasher.py +30 -0
- airbyte_cdk/utils/spec_schema_transformations.py +6 -3
- airbyte_cdk/utils/stream_status_utils.py +8 -1
- airbyte_cdk/utils/traced_exception.py +61 -21
- airbyte_cdk-6.17.1.dev1.dist-info/METADATA +109 -0
- airbyte_cdk-6.17.1.dev1.dist-info/RECORD +350 -0
- {airbyte_cdk-0.72.1.dist-info → airbyte_cdk-6.17.1.dev1.dist-info}/WHEEL +1 -2
- airbyte_cdk-6.17.1.dev1.dist-info/entry_points.txt +3 -0
- airbyte_cdk/sources/declarative/create_partial.py +0 -92
- airbyte_cdk/sources/declarative/parsers/class_types_registry.py +0 -102
- airbyte_cdk/sources/declarative/parsers/default_implementation_registry.py +0 -64
- airbyte_cdk/sources/declarative/requesters/error_handlers/response_action.py +0 -16
- airbyte_cdk/sources/declarative/requesters/error_handlers/response_status.py +0 -68
- airbyte_cdk/sources/declarative/stream_slicers/cartesian_product_stream_slicer.py +0 -114
- airbyte_cdk/sources/deprecated/base_source.py +0 -94
- airbyte_cdk/sources/deprecated/client.py +0 -99
- airbyte_cdk/sources/singer/__init__.py +0 -8
- airbyte_cdk/sources/singer/singer_helpers.py +0 -304
- airbyte_cdk/sources/singer/source.py +0 -186
- airbyte_cdk/sources/streams/concurrent/partitions/record.py +0 -23
- airbyte_cdk/sources/streams/http/auth/__init__.py +0 -17
- airbyte_cdk/sources/streams/http/auth/core.py +0 -29
- airbyte_cdk/sources/streams/http/auth/oauth.py +0 -113
- airbyte_cdk/sources/streams/http/auth/token.py +0 -47
- airbyte_cdk/sources/streams/utils/stream_helper.py +0 -40
- airbyte_cdk/sources/utils/catalog_helpers.py +0 -22
- airbyte_cdk/sources/utils/schema_models.py +0 -84
- airbyte_cdk-0.72.1.dist-info/METADATA +0 -243
- airbyte_cdk-0.72.1.dist-info/RECORD +0 -466
- airbyte_cdk-0.72.1.dist-info/top_level.txt +0 -3
- source_declarative_manifest/main.py +0 -29
- unit_tests/connector_builder/__init__.py +0 -3
- unit_tests/connector_builder/test_connector_builder_handler.py +0 -871
- unit_tests/connector_builder/test_message_grouper.py +0 -713
- unit_tests/connector_builder/utils.py +0 -27
- unit_tests/destinations/test_destination.py +0 -243
- unit_tests/singer/test_singer_helpers.py +0 -56
- unit_tests/singer/test_singer_source.py +0 -112
- unit_tests/sources/__init__.py +0 -0
- unit_tests/sources/concurrent_source/__init__.py +0 -3
- unit_tests/sources/concurrent_source/test_concurrent_source_adapter.py +0 -106
- unit_tests/sources/declarative/__init__.py +0 -3
- unit_tests/sources/declarative/auth/__init__.py +0 -3
- unit_tests/sources/declarative/auth/test_oauth.py +0 -331
- unit_tests/sources/declarative/auth/test_selective_authenticator.py +0 -39
- unit_tests/sources/declarative/auth/test_session_token_auth.py +0 -182
- unit_tests/sources/declarative/auth/test_token_auth.py +0 -200
- unit_tests/sources/declarative/auth/test_token_provider.py +0 -73
- unit_tests/sources/declarative/checks/__init__.py +0 -3
- unit_tests/sources/declarative/checks/test_check_stream.py +0 -146
- unit_tests/sources/declarative/decoders/__init__.py +0 -0
- unit_tests/sources/declarative/decoders/test_json_decoder.py +0 -16
- unit_tests/sources/declarative/external_component.py +0 -13
- unit_tests/sources/declarative/extractors/__init__.py +0 -3
- unit_tests/sources/declarative/extractors/test_dpath_extractor.py +0 -55
- unit_tests/sources/declarative/extractors/test_record_filter.py +0 -55
- unit_tests/sources/declarative/extractors/test_record_selector.py +0 -179
- unit_tests/sources/declarative/incremental/__init__.py +0 -0
- unit_tests/sources/declarative/incremental/test_datetime_based_cursor.py +0 -860
- unit_tests/sources/declarative/incremental/test_per_partition_cursor.py +0 -406
- unit_tests/sources/declarative/incremental/test_per_partition_cursor_integration.py +0 -332
- unit_tests/sources/declarative/interpolation/__init__.py +0 -3
- unit_tests/sources/declarative/interpolation/test_filters.py +0 -80
- unit_tests/sources/declarative/interpolation/test_interpolated_boolean.py +0 -40
- unit_tests/sources/declarative/interpolation/test_interpolated_mapping.py +0 -35
- unit_tests/sources/declarative/interpolation/test_interpolated_nested_mapping.py +0 -45
- unit_tests/sources/declarative/interpolation/test_interpolated_string.py +0 -25
- unit_tests/sources/declarative/interpolation/test_jinja.py +0 -240
- unit_tests/sources/declarative/interpolation/test_macros.py +0 -73
- unit_tests/sources/declarative/parsers/__init__.py +0 -3
- unit_tests/sources/declarative/parsers/test_manifest_component_transformer.py +0 -406
- unit_tests/sources/declarative/parsers/test_manifest_reference_resolver.py +0 -139
- unit_tests/sources/declarative/parsers/test_model_to_component_factory.py +0 -1847
- unit_tests/sources/declarative/parsers/testing_components.py +0 -36
- unit_tests/sources/declarative/partition_routers/__init__.py +0 -3
- unit_tests/sources/declarative/partition_routers/test_list_partition_router.py +0 -155
- unit_tests/sources/declarative/partition_routers/test_single_partition_router.py +0 -14
- unit_tests/sources/declarative/partition_routers/test_substream_partition_router.py +0 -404
- unit_tests/sources/declarative/requesters/__init__.py +0 -3
- unit_tests/sources/declarative/requesters/error_handlers/__init__.py +0 -3
- unit_tests/sources/declarative/requesters/error_handlers/backoff_strategies/__init__.py +0 -3
- unit_tests/sources/declarative/requesters/error_handlers/backoff_strategies/test_constant_backoff.py +0 -34
- unit_tests/sources/declarative/requesters/error_handlers/backoff_strategies/test_exponential_backoff.py +0 -36
- unit_tests/sources/declarative/requesters/error_handlers/backoff_strategies/test_header_helper.py +0 -38
- unit_tests/sources/declarative/requesters/error_handlers/backoff_strategies/test_wait_time_from_header.py +0 -35
- unit_tests/sources/declarative/requesters/error_handlers/backoff_strategies/test_wait_until_time_from_header.py +0 -64
- unit_tests/sources/declarative/requesters/error_handlers/test_composite_error_handler.py +0 -213
- unit_tests/sources/declarative/requesters/error_handlers/test_default_error_handler.py +0 -178
- unit_tests/sources/declarative/requesters/error_handlers/test_http_response_filter.py +0 -121
- unit_tests/sources/declarative/requesters/error_handlers/test_response_status.py +0 -44
- unit_tests/sources/declarative/requesters/paginators/__init__.py +0 -3
- unit_tests/sources/declarative/requesters/paginators/test_cursor_pagination_strategy.py +0 -64
- unit_tests/sources/declarative/requesters/paginators/test_default_paginator.py +0 -313
- unit_tests/sources/declarative/requesters/paginators/test_no_paginator.py +0 -12
- unit_tests/sources/declarative/requesters/paginators/test_offset_increment.py +0 -58
- unit_tests/sources/declarative/requesters/paginators/test_page_increment.py +0 -70
- unit_tests/sources/declarative/requesters/paginators/test_request_option.py +0 -43
- unit_tests/sources/declarative/requesters/paginators/test_stop_condition.py +0 -105
- unit_tests/sources/declarative/requesters/request_options/__init__.py +0 -3
- unit_tests/sources/declarative/requesters/request_options/test_interpolated_request_options_provider.py +0 -101
- unit_tests/sources/declarative/requesters/test_http_requester.py +0 -974
- unit_tests/sources/declarative/requesters/test_interpolated_request_input_provider.py +0 -32
- unit_tests/sources/declarative/retrievers/__init__.py +0 -3
- unit_tests/sources/declarative/retrievers/test_simple_retriever.py +0 -542
- unit_tests/sources/declarative/schema/__init__.py +0 -6
- unit_tests/sources/declarative/schema/source_test/SourceTest.py +0 -8
- unit_tests/sources/declarative/schema/source_test/__init__.py +0 -3
- unit_tests/sources/declarative/schema/test_default_schema_loader.py +0 -32
- unit_tests/sources/declarative/schema/test_inline_schema_loader.py +0 -19
- unit_tests/sources/declarative/schema/test_json_file_schema_loader.py +0 -26
- unit_tests/sources/declarative/states/__init__.py +0 -3
- unit_tests/sources/declarative/stream_slicers/__init__.py +0 -3
- unit_tests/sources/declarative/stream_slicers/test_cartesian_product_stream_slicer.py +0 -225
- unit_tests/sources/declarative/test_create_partial.py +0 -83
- unit_tests/sources/declarative/test_declarative_stream.py +0 -103
- unit_tests/sources/declarative/test_manifest_declarative_source.py +0 -1260
- unit_tests/sources/declarative/test_types.py +0 -39
- unit_tests/sources/declarative/test_yaml_declarative_source.py +0 -148
- unit_tests/sources/file_based/__init__.py +0 -0
- unit_tests/sources/file_based/availability_strategy/__init__.py +0 -0
- unit_tests/sources/file_based/availability_strategy/test_default_file_based_availability_strategy.py +0 -100
- unit_tests/sources/file_based/config/__init__.py +0 -0
- unit_tests/sources/file_based/config/test_abstract_file_based_spec.py +0 -28
- unit_tests/sources/file_based/config/test_csv_format.py +0 -34
- unit_tests/sources/file_based/config/test_file_based_stream_config.py +0 -84
- unit_tests/sources/file_based/discovery_policy/__init__.py +0 -0
- unit_tests/sources/file_based/discovery_policy/test_default_discovery_policy.py +0 -31
- unit_tests/sources/file_based/file_types/__init__.py +0 -0
- unit_tests/sources/file_based/file_types/test_avro_parser.py +0 -243
- unit_tests/sources/file_based/file_types/test_csv_parser.py +0 -546
- unit_tests/sources/file_based/file_types/test_jsonl_parser.py +0 -158
- unit_tests/sources/file_based/file_types/test_parquet_parser.py +0 -274
- unit_tests/sources/file_based/file_types/test_unstructured_parser.py +0 -593
- unit_tests/sources/file_based/helpers.py +0 -70
- unit_tests/sources/file_based/in_memory_files_source.py +0 -211
- unit_tests/sources/file_based/scenarios/__init__.py +0 -0
- unit_tests/sources/file_based/scenarios/avro_scenarios.py +0 -744
- unit_tests/sources/file_based/scenarios/check_scenarios.py +0 -220
- unit_tests/sources/file_based/scenarios/concurrent_incremental_scenarios.py +0 -2844
- unit_tests/sources/file_based/scenarios/csv_scenarios.py +0 -3105
- unit_tests/sources/file_based/scenarios/file_based_source_builder.py +0 -91
- unit_tests/sources/file_based/scenarios/incremental_scenarios.py +0 -1926
- unit_tests/sources/file_based/scenarios/jsonl_scenarios.py +0 -930
- unit_tests/sources/file_based/scenarios/parquet_scenarios.py +0 -754
- unit_tests/sources/file_based/scenarios/scenario_builder.py +0 -234
- unit_tests/sources/file_based/scenarios/unstructured_scenarios.py +0 -608
- unit_tests/sources/file_based/scenarios/user_input_schema_scenarios.py +0 -746
- unit_tests/sources/file_based/scenarios/validation_policy_scenarios.py +0 -726
- unit_tests/sources/file_based/stream/__init__.py +0 -0
- unit_tests/sources/file_based/stream/concurrent/__init__.py +0 -0
- unit_tests/sources/file_based/stream/concurrent/test_adapters.py +0 -362
- unit_tests/sources/file_based/stream/concurrent/test_file_based_concurrent_cursor.py +0 -458
- unit_tests/sources/file_based/stream/test_default_file_based_cursor.py +0 -310
- unit_tests/sources/file_based/stream/test_default_file_based_stream.py +0 -244
- unit_tests/sources/file_based/test_file_based_scenarios.py +0 -320
- unit_tests/sources/file_based/test_file_based_stream_reader.py +0 -272
- unit_tests/sources/file_based/test_scenarios.py +0 -253
- unit_tests/sources/file_based/test_schema_helpers.py +0 -346
- unit_tests/sources/fixtures/__init__.py +0 -3
- unit_tests/sources/fixtures/source_test_fixture.py +0 -153
- unit_tests/sources/message/__init__.py +0 -0
- unit_tests/sources/message/test_repository.py +0 -153
- unit_tests/sources/streams/__init__.py +0 -0
- unit_tests/sources/streams/concurrent/__init__.py +0 -3
- unit_tests/sources/streams/concurrent/scenarios/__init__.py +0 -3
- unit_tests/sources/streams/concurrent/scenarios/incremental_scenarios.py +0 -250
- unit_tests/sources/streams/concurrent/scenarios/stream_facade_builder.py +0 -140
- unit_tests/sources/streams/concurrent/scenarios/stream_facade_scenarios.py +0 -452
- unit_tests/sources/streams/concurrent/scenarios/test_concurrent_scenarios.py +0 -76
- unit_tests/sources/streams/concurrent/scenarios/thread_based_concurrent_stream_scenarios.py +0 -418
- unit_tests/sources/streams/concurrent/scenarios/thread_based_concurrent_stream_source_builder.py +0 -142
- unit_tests/sources/streams/concurrent/scenarios/utils.py +0 -55
- unit_tests/sources/streams/concurrent/test_adapters.py +0 -380
- unit_tests/sources/streams/concurrent/test_concurrent_read_processor.py +0 -684
- unit_tests/sources/streams/concurrent/test_cursor.py +0 -139
- unit_tests/sources/streams/concurrent/test_datetime_state_converter.py +0 -369
- unit_tests/sources/streams/concurrent/test_default_stream.py +0 -197
- unit_tests/sources/streams/concurrent/test_partition_enqueuer.py +0 -90
- unit_tests/sources/streams/concurrent/test_partition_reader.py +0 -67
- unit_tests/sources/streams/concurrent/test_thread_pool_manager.py +0 -106
- unit_tests/sources/streams/http/__init__.py +0 -0
- unit_tests/sources/streams/http/auth/__init__.py +0 -0
- unit_tests/sources/streams/http/auth/test_auth.py +0 -173
- unit_tests/sources/streams/http/requests_native_auth/__init__.py +0 -0
- unit_tests/sources/streams/http/requests_native_auth/test_requests_native_auth.py +0 -423
- unit_tests/sources/streams/http/test_availability_strategy.py +0 -180
- unit_tests/sources/streams/http/test_http.py +0 -635
- unit_tests/sources/streams/test_availability_strategy.py +0 -70
- unit_tests/sources/streams/test_call_rate.py +0 -300
- unit_tests/sources/streams/test_stream_read.py +0 -405
- unit_tests/sources/streams/test_streams_core.py +0 -184
- unit_tests/sources/test_abstract_source.py +0 -1442
- unit_tests/sources/test_concurrent_source.py +0 -112
- unit_tests/sources/test_config.py +0 -92
- unit_tests/sources/test_connector_state_manager.py +0 -482
- unit_tests/sources/test_http_logger.py +0 -252
- unit_tests/sources/test_integration_source.py +0 -86
- unit_tests/sources/test_source.py +0 -684
- unit_tests/sources/test_source_read.py +0 -460
- unit_tests/test/__init__.py +0 -0
- unit_tests/test/mock_http/__init__.py +0 -0
- unit_tests/test/mock_http/test_matcher.py +0 -53
- unit_tests/test/mock_http/test_mocker.py +0 -214
- unit_tests/test/mock_http/test_request.py +0 -117
- unit_tests/test/mock_http/test_response_builder.py +0 -177
- unit_tests/test/test_entrypoint_wrapper.py +0 -240
- unit_tests/utils/__init__.py +0 -0
- unit_tests/utils/test_datetime_format_inferrer.py +0 -60
- unit_tests/utils/test_mapping_helpers.py +0 -54
- unit_tests/utils/test_message_utils.py +0 -91
- unit_tests/utils/test_rate_limiting.py +0 -26
- unit_tests/utils/test_schema_inferrer.py +0 -202
- unit_tests/utils/test_secret_utils.py +0 -135
- unit_tests/utils/test_stream_status_utils.py +0 -61
- unit_tests/utils/test_traced_exception.py +0 -107
- /airbyte_cdk/sources/{deprecated → declarative/async_job}/__init__.py +0 -0
- {source_declarative_manifest → airbyte_cdk/sources/declarative/migrations}/__init__.py +0 -0
- {unit_tests/destinations → airbyte_cdk/sql}/__init__.py +0 -0
- {unit_tests/singer → airbyte_cdk/sql/_util}/__init__.py +0 -0
- {airbyte_cdk-0.72.1.dist-info → airbyte_cdk-6.17.1.dev1.dist-info}/LICENSE.txt +0 -0
@@ -1,1442 +0,0 @@
|
|
1
|
-
#
|
2
|
-
# Copyright (c) 2023 Airbyte, Inc., all rights reserved.
|
3
|
-
#
|
4
|
-
|
5
|
-
import copy
|
6
|
-
import datetime
|
7
|
-
import logging
|
8
|
-
from collections import defaultdict
|
9
|
-
from typing import Any, Callable, Dict, Iterable, List, Mapping, MutableMapping, Optional, Tuple, Union
|
10
|
-
from unittest.mock import Mock, call
|
11
|
-
|
12
|
-
import pytest
|
13
|
-
from airbyte_cdk.models import (
|
14
|
-
AirbyteCatalog,
|
15
|
-
AirbyteConnectionStatus,
|
16
|
-
AirbyteErrorTraceMessage,
|
17
|
-
AirbyteLogMessage,
|
18
|
-
AirbyteMessage,
|
19
|
-
AirbyteRecordMessage,
|
20
|
-
AirbyteStateBlob,
|
21
|
-
AirbyteStateMessage,
|
22
|
-
AirbyteStateType,
|
23
|
-
AirbyteStream,
|
24
|
-
AirbyteStreamState,
|
25
|
-
AirbyteStreamStatus,
|
26
|
-
AirbyteStreamStatusTraceMessage,
|
27
|
-
AirbyteTraceMessage,
|
28
|
-
ConfiguredAirbyteCatalog,
|
29
|
-
ConfiguredAirbyteStream,
|
30
|
-
DestinationSyncMode,
|
31
|
-
FailureType,
|
32
|
-
Level,
|
33
|
-
Status,
|
34
|
-
StreamDescriptor,
|
35
|
-
SyncMode,
|
36
|
-
TraceType,
|
37
|
-
)
|
38
|
-
from airbyte_cdk.models import Type
|
39
|
-
from airbyte_cdk.models import Type as MessageType
|
40
|
-
from airbyte_cdk.sources import AbstractSource
|
41
|
-
from airbyte_cdk.sources.connector_state_manager import ConnectorStateManager
|
42
|
-
from airbyte_cdk.sources.message import MessageRepository
|
43
|
-
from airbyte_cdk.sources.streams import IncrementalMixin, Stream
|
44
|
-
from airbyte_cdk.sources.utils.record_helper import stream_data_to_airbyte_message
|
45
|
-
from airbyte_cdk.utils.airbyte_secrets_utils import update_secrets
|
46
|
-
from airbyte_cdk.utils.traced_exception import AirbyteTracedException
|
47
|
-
from pytest import fixture
|
48
|
-
|
49
|
-
logger = logging.getLogger("airbyte")
|
50
|
-
|
51
|
-
|
52
|
-
class MockSource(AbstractSource):
|
53
|
-
def __init__(
|
54
|
-
self,
|
55
|
-
check_lambda: Callable[[], Tuple[bool, Optional[Any]]] = None,
|
56
|
-
streams: List[Stream] = None,
|
57
|
-
message_repository: MessageRepository = None,
|
58
|
-
exception_on_missing_stream: bool = True,
|
59
|
-
stop_sync_on_stream_failure: bool = False,
|
60
|
-
):
|
61
|
-
self._streams = streams
|
62
|
-
self.check_lambda = check_lambda
|
63
|
-
self.exception_on_missing_stream = exception_on_missing_stream
|
64
|
-
self._message_repository = message_repository
|
65
|
-
self._stop_sync_on_stream_failure = stop_sync_on_stream_failure
|
66
|
-
|
67
|
-
def check_connection(self, logger: logging.Logger, config: Mapping[str, Any]) -> Tuple[bool, Optional[Any]]:
|
68
|
-
if self.check_lambda:
|
69
|
-
return self.check_lambda()
|
70
|
-
return False, "Missing callable."
|
71
|
-
|
72
|
-
def streams(self, config: Mapping[str, Any]) -> List[Stream]:
|
73
|
-
if not self._streams:
|
74
|
-
raise Exception("Stream is not set")
|
75
|
-
return self._streams
|
76
|
-
|
77
|
-
@property
|
78
|
-
def raise_exception_on_missing_stream(self) -> bool:
|
79
|
-
return self.exception_on_missing_stream
|
80
|
-
|
81
|
-
@property
|
82
|
-
def per_stream_state_enabled(self) -> bool:
|
83
|
-
return self.per_stream
|
84
|
-
|
85
|
-
@property
|
86
|
-
def message_repository(self):
|
87
|
-
return self._message_repository
|
88
|
-
|
89
|
-
|
90
|
-
class MockSourceWithStopSyncFalseOverride(MockSource):
|
91
|
-
@property
|
92
|
-
def stop_sync_on_stream_failure(self) -> bool:
|
93
|
-
return False
|
94
|
-
|
95
|
-
|
96
|
-
class StreamNoStateMethod(Stream):
|
97
|
-
name = "managers"
|
98
|
-
primary_key = None
|
99
|
-
|
100
|
-
def read_records(self, *args, **kwargs) -> Iterable[Mapping[str, Any]]:
|
101
|
-
return {}
|
102
|
-
|
103
|
-
|
104
|
-
class MockStreamOverridesStateMethod(Stream, IncrementalMixin):
|
105
|
-
name = "teams"
|
106
|
-
primary_key = None
|
107
|
-
cursor_field = "updated_at"
|
108
|
-
_cursor_value = ""
|
109
|
-
start_date = "1984-12-12"
|
110
|
-
|
111
|
-
def read_records(self, *args, **kwargs) -> Iterable[Mapping[str, Any]]:
|
112
|
-
return {}
|
113
|
-
|
114
|
-
@property
|
115
|
-
def state(self) -> MutableMapping[str, Any]:
|
116
|
-
return {self.cursor_field: self._cursor_value} if self._cursor_value else {}
|
117
|
-
|
118
|
-
@state.setter
|
119
|
-
def state(self, value: MutableMapping[str, Any]):
|
120
|
-
self._cursor_value = value.get(self.cursor_field, self.start_date)
|
121
|
-
|
122
|
-
|
123
|
-
class StreamRaisesException(Stream):
|
124
|
-
name = "lamentations"
|
125
|
-
primary_key = None
|
126
|
-
|
127
|
-
def __init__(self, exception_to_raise):
|
128
|
-
self._exception_to_raise = exception_to_raise
|
129
|
-
|
130
|
-
def read_records(self, *args, **kwargs) -> Iterable[Mapping[str, Any]]:
|
131
|
-
raise self._exception_to_raise
|
132
|
-
|
133
|
-
|
134
|
-
MESSAGE_FROM_REPOSITORY = Mock()
|
135
|
-
|
136
|
-
|
137
|
-
@fixture
|
138
|
-
def message_repository():
|
139
|
-
message_repository = Mock(spec=MessageRepository)
|
140
|
-
message_repository.consume_queue.return_value = [message for message in [MESSAGE_FROM_REPOSITORY]]
|
141
|
-
return message_repository
|
142
|
-
|
143
|
-
|
144
|
-
def test_successful_check():
|
145
|
-
"""Tests that if a source returns TRUE for the connection check the appropriate connectionStatus success message is returned"""
|
146
|
-
expected = AirbyteConnectionStatus(status=Status.SUCCEEDED)
|
147
|
-
assert expected == MockSource(check_lambda=lambda: (True, None)).check(logger, {})
|
148
|
-
|
149
|
-
|
150
|
-
def test_failed_check():
|
151
|
-
"""Tests that if a source returns FALSE for the connection check the appropriate connectionStatus failure message is returned"""
|
152
|
-
expected = AirbyteConnectionStatus(status=Status.FAILED, message="'womp womp'")
|
153
|
-
assert expected == MockSource(check_lambda=lambda: (False, "womp womp")).check(logger, {})
|
154
|
-
|
155
|
-
|
156
|
-
def test_raising_check(mocker):
|
157
|
-
"""Tests that if a source raises an unexpected exception the appropriate connectionStatus failure message is returned."""
|
158
|
-
check_lambda = mocker.Mock(side_effect=BaseException("this should fail"))
|
159
|
-
with pytest.raises(BaseException):
|
160
|
-
MockSource(check_lambda=check_lambda).check(logger, {})
|
161
|
-
|
162
|
-
|
163
|
-
class MockStream(Stream):
|
164
|
-
def __init__(
|
165
|
-
self,
|
166
|
-
inputs_and_mocked_outputs: List[Tuple[Mapping[str, Any], Iterable[Mapping[str, Any]]]] = None,
|
167
|
-
name: str = None,
|
168
|
-
):
|
169
|
-
self._inputs_and_mocked_outputs = inputs_and_mocked_outputs
|
170
|
-
self._name = name
|
171
|
-
|
172
|
-
@property
|
173
|
-
def name(self):
|
174
|
-
return self._name
|
175
|
-
|
176
|
-
def read_records(self, **kwargs) -> Iterable[Mapping[str, Any]]: # type: ignore
|
177
|
-
# Remove None values
|
178
|
-
kwargs = {k: v for k, v in kwargs.items() if v is not None}
|
179
|
-
if self._inputs_and_mocked_outputs:
|
180
|
-
for _input, output in self._inputs_and_mocked_outputs:
|
181
|
-
if kwargs == _input:
|
182
|
-
return output
|
183
|
-
|
184
|
-
raise Exception(f"No mocked output supplied for input: {kwargs}. Mocked inputs/outputs: {self._inputs_and_mocked_outputs}")
|
185
|
-
|
186
|
-
@property
|
187
|
-
def primary_key(self) -> Optional[Union[str, List[str], List[List[str]]]]:
|
188
|
-
return "pk"
|
189
|
-
|
190
|
-
|
191
|
-
class MockStreamWithState(MockStream):
|
192
|
-
cursor_field = "cursor"
|
193
|
-
|
194
|
-
def __init__(self, inputs_and_mocked_outputs: List[Tuple[Mapping[str, Any], Iterable[Mapping[str, Any]]]], name: str, state=None):
|
195
|
-
super().__init__(inputs_and_mocked_outputs, name)
|
196
|
-
self._state = state
|
197
|
-
|
198
|
-
@property
|
199
|
-
def state(self):
|
200
|
-
return self._state
|
201
|
-
|
202
|
-
@state.setter
|
203
|
-
def state(self, value):
|
204
|
-
pass
|
205
|
-
|
206
|
-
|
207
|
-
class MockStreamEmittingAirbyteMessages(MockStreamWithState):
|
208
|
-
def __init__(
|
209
|
-
self, inputs_and_mocked_outputs: List[Tuple[Mapping[str, Any], Iterable[AirbyteMessage]]] = None, name: str = None, state=None
|
210
|
-
):
|
211
|
-
super().__init__(inputs_and_mocked_outputs, name, state)
|
212
|
-
self._inputs_and_mocked_outputs = inputs_and_mocked_outputs
|
213
|
-
self._name = name
|
214
|
-
|
215
|
-
@property
|
216
|
-
def name(self):
|
217
|
-
return self._name
|
218
|
-
|
219
|
-
@property
|
220
|
-
def primary_key(self) -> Optional[Union[str, List[str], List[List[str]]]]:
|
221
|
-
return "pk"
|
222
|
-
|
223
|
-
@property
|
224
|
-
def state(self) -> MutableMapping[str, Any]:
|
225
|
-
return {self.cursor_field: self._cursor_value} if self._cursor_value else {}
|
226
|
-
|
227
|
-
@state.setter
|
228
|
-
def state(self, value: MutableMapping[str, Any]):
|
229
|
-
self._cursor_value = value.get(self.cursor_field, self.start_date)
|
230
|
-
|
231
|
-
|
232
|
-
def test_discover(mocker):
|
233
|
-
"""Tests that the appropriate AirbyteCatalog is returned from the discover method"""
|
234
|
-
airbyte_stream1 = AirbyteStream(
|
235
|
-
name="1",
|
236
|
-
json_schema={},
|
237
|
-
supported_sync_modes=[SyncMode.full_refresh, SyncMode.incremental],
|
238
|
-
default_cursor_field=["cursor"],
|
239
|
-
source_defined_cursor=True,
|
240
|
-
source_defined_primary_key=[["pk"]],
|
241
|
-
)
|
242
|
-
airbyte_stream2 = AirbyteStream(name="2", json_schema={}, supported_sync_modes=[SyncMode.full_refresh])
|
243
|
-
|
244
|
-
stream1 = MockStream()
|
245
|
-
stream2 = MockStream()
|
246
|
-
mocker.patch.object(stream1, "as_airbyte_stream", return_value=airbyte_stream1)
|
247
|
-
mocker.patch.object(stream2, "as_airbyte_stream", return_value=airbyte_stream2)
|
248
|
-
|
249
|
-
expected = AirbyteCatalog(streams=[airbyte_stream1, airbyte_stream2])
|
250
|
-
src = MockSource(check_lambda=lambda: (True, None), streams=[stream1, stream2])
|
251
|
-
|
252
|
-
assert expected == src.discover(logger, {})
|
253
|
-
|
254
|
-
|
255
|
-
def test_read_nonexistent_stream_raises_exception(mocker):
|
256
|
-
"""Tests that attempting to sync a stream which the source does not return from the `streams` method raises an exception"""
|
257
|
-
s1 = MockStream(name="s1")
|
258
|
-
s2 = MockStream(name="this_stream_doesnt_exist_in_the_source")
|
259
|
-
|
260
|
-
mocker.patch.object(MockStream, "get_json_schema", return_value={})
|
261
|
-
|
262
|
-
src = MockSource(streams=[s1])
|
263
|
-
catalog = ConfiguredAirbyteCatalog(streams=[_configured_stream(s2, SyncMode.full_refresh)])
|
264
|
-
with pytest.raises(KeyError):
|
265
|
-
list(src.read(logger, {}, catalog))
|
266
|
-
|
267
|
-
|
268
|
-
def test_read_nonexistent_stream_without_raises_exception(mocker):
|
269
|
-
"""Tests that attempting to sync a stream which the source does not return from the `streams` method raises an exception"""
|
270
|
-
s1 = MockStream(name="s1")
|
271
|
-
s2 = MockStream(name="this_stream_doesnt_exist_in_the_source")
|
272
|
-
|
273
|
-
mocker.patch.object(MockStream, "get_json_schema", return_value={})
|
274
|
-
|
275
|
-
src = MockSource(streams=[s1], exception_on_missing_stream=False)
|
276
|
-
|
277
|
-
catalog = ConfiguredAirbyteCatalog(streams=[_configured_stream(s2, SyncMode.full_refresh)])
|
278
|
-
messages = list(src.read(logger, {}, catalog))
|
279
|
-
|
280
|
-
assert messages == []
|
281
|
-
|
282
|
-
|
283
|
-
def test_read_stream_emits_repository_message_before_record(mocker, message_repository):
|
284
|
-
stream = MockStream(name="my_stream")
|
285
|
-
mocker.patch.object(MockStream, "get_json_schema", return_value={})
|
286
|
-
mocker.patch.object(MockStream, "read_records", side_effect=[[{"a record": "a value"}, {"another record": "another value"}]])
|
287
|
-
message_repository.consume_queue.side_effect = [[message for message in [MESSAGE_FROM_REPOSITORY]], [], []]
|
288
|
-
|
289
|
-
source = MockSource(streams=[stream], message_repository=message_repository)
|
290
|
-
|
291
|
-
messages = list(source.read(logger, {}, ConfiguredAirbyteCatalog(streams=[_configured_stream(stream, SyncMode.full_refresh)])))
|
292
|
-
|
293
|
-
assert messages.count(MESSAGE_FROM_REPOSITORY) == 1
|
294
|
-
record_messages = (message for message in messages if message.type == Type.RECORD)
|
295
|
-
assert all(messages.index(MESSAGE_FROM_REPOSITORY) < messages.index(record) for record in record_messages)
|
296
|
-
|
297
|
-
|
298
|
-
def test_read_stream_emits_repository_message_on_error(mocker, message_repository):
|
299
|
-
stream = MockStream(name="my_stream")
|
300
|
-
mocker.patch.object(MockStream, "get_json_schema", return_value={})
|
301
|
-
mocker.patch.object(MockStream, "read_records", side_effect=RuntimeError("error"))
|
302
|
-
message_repository.consume_queue.return_value = [message for message in [MESSAGE_FROM_REPOSITORY]]
|
303
|
-
|
304
|
-
source = MockSource(streams=[stream], message_repository=message_repository)
|
305
|
-
|
306
|
-
with pytest.raises(AirbyteTracedException):
|
307
|
-
messages = list(source.read(logger, {}, ConfiguredAirbyteCatalog(streams=[_configured_stream(stream, SyncMode.full_refresh)])))
|
308
|
-
assert MESSAGE_FROM_REPOSITORY in messages
|
309
|
-
|
310
|
-
|
311
|
-
def test_read_stream_with_error_gets_display_message(mocker):
|
312
|
-
stream = MockStream(name="my_stream")
|
313
|
-
|
314
|
-
mocker.patch.object(MockStream, "get_json_schema", return_value={})
|
315
|
-
mocker.patch.object(MockStream, "read_records", side_effect=RuntimeError("oh no!"))
|
316
|
-
|
317
|
-
source = MockSource(streams=[stream])
|
318
|
-
catalog = ConfiguredAirbyteCatalog(streams=[_configured_stream(stream, SyncMode.full_refresh)])
|
319
|
-
|
320
|
-
# without get_error_display_message
|
321
|
-
with pytest.raises(AirbyteTracedException):
|
322
|
-
list(source.read(logger, {}, catalog))
|
323
|
-
|
324
|
-
mocker.patch.object(MockStream, "get_error_display_message", return_value="my message")
|
325
|
-
|
326
|
-
with pytest.raises(AirbyteTracedException) as exc:
|
327
|
-
list(source.read(logger, {}, catalog))
|
328
|
-
assert "oh no!" in exc.value.message
|
329
|
-
|
330
|
-
|
331
|
-
GLOBAL_EMITTED_AT = 1
|
332
|
-
|
333
|
-
|
334
|
-
def _as_record(stream: str, data: Dict[str, Any]) -> AirbyteMessage:
|
335
|
-
return AirbyteMessage(
|
336
|
-
type=Type.RECORD,
|
337
|
-
record=AirbyteRecordMessage(stream=stream, data=data, emitted_at=GLOBAL_EMITTED_AT),
|
338
|
-
)
|
339
|
-
|
340
|
-
|
341
|
-
def _as_records(stream: str, data: List[Dict[str, Any]]) -> List[AirbyteMessage]:
|
342
|
-
return [_as_record(stream, datum) for datum in data]
|
343
|
-
|
344
|
-
|
345
|
-
def _as_stream_status(stream: str, status: AirbyteStreamStatus) -> AirbyteMessage:
|
346
|
-
trace_message = AirbyteTraceMessage(
|
347
|
-
emitted_at=datetime.datetime.now().timestamp() * 1000.0,
|
348
|
-
type=TraceType.STREAM_STATUS,
|
349
|
-
stream_status=AirbyteStreamStatusTraceMessage(
|
350
|
-
stream_descriptor=StreamDescriptor(name=stream),
|
351
|
-
status=status,
|
352
|
-
),
|
353
|
-
)
|
354
|
-
|
355
|
-
return AirbyteMessage(type=MessageType.TRACE, trace=trace_message)
|
356
|
-
|
357
|
-
|
358
|
-
def _as_state(stream_name: str = "", per_stream_state: Dict[str, Any] = None):
|
359
|
-
return AirbyteMessage(
|
360
|
-
type=Type.STATE,
|
361
|
-
state=AirbyteStateMessage(
|
362
|
-
type=AirbyteStateType.STREAM,
|
363
|
-
stream=AirbyteStreamState(
|
364
|
-
stream_descriptor=StreamDescriptor(name=stream_name), stream_state=AirbyteStateBlob.parse_obj(per_stream_state)
|
365
|
-
),
|
366
|
-
),
|
367
|
-
)
|
368
|
-
|
369
|
-
|
370
|
-
def _as_error_trace(
|
371
|
-
stream: str, error_message: str, internal_message: Optional[str], failure_type: Optional[FailureType], stack_trace: Optional[str]
|
372
|
-
) -> AirbyteMessage:
|
373
|
-
trace_message = AirbyteTraceMessage(
|
374
|
-
emitted_at=datetime.datetime.now().timestamp() * 1000.0,
|
375
|
-
type=TraceType.ERROR,
|
376
|
-
error=AirbyteErrorTraceMessage(
|
377
|
-
stream_descriptor=StreamDescriptor(name=stream),
|
378
|
-
message=error_message,
|
379
|
-
internal_message=internal_message,
|
380
|
-
failure_type=failure_type,
|
381
|
-
stack_trace=stack_trace,
|
382
|
-
),
|
383
|
-
)
|
384
|
-
|
385
|
-
return AirbyteMessage(type=MessageType.TRACE, trace=trace_message)
|
386
|
-
|
387
|
-
|
388
|
-
def _configured_stream(stream: Stream, sync_mode: SyncMode):
|
389
|
-
return ConfiguredAirbyteStream(
|
390
|
-
stream=stream.as_airbyte_stream(),
|
391
|
-
sync_mode=sync_mode,
|
392
|
-
destination_sync_mode=DestinationSyncMode.overwrite,
|
393
|
-
)
|
394
|
-
|
395
|
-
|
396
|
-
def _fix_emitted_at(messages: List[AirbyteMessage]) -> List[AirbyteMessage]:
|
397
|
-
for msg in messages:
|
398
|
-
if msg.type == Type.RECORD and msg.record:
|
399
|
-
msg.record.emitted_at = GLOBAL_EMITTED_AT
|
400
|
-
if msg.type == Type.TRACE and msg.trace:
|
401
|
-
msg.trace.emitted_at = GLOBAL_EMITTED_AT
|
402
|
-
return messages
|
403
|
-
|
404
|
-
|
405
|
-
def test_valid_full_refresh_read_no_slices(mocker):
|
406
|
-
"""Tests that running a full refresh sync on streams which don't specify slices produces the expected AirbyteMessages"""
|
407
|
-
stream_output = [{"k1": "v1"}, {"k2": "v2"}]
|
408
|
-
s1 = MockStream([({"stream_state": {}, "sync_mode": SyncMode.full_refresh}, stream_output)], name="s1")
|
409
|
-
s2 = MockStream([({"stream_state": {}, "sync_mode": SyncMode.full_refresh}, stream_output)], name="s2")
|
410
|
-
|
411
|
-
mocker.patch.object(MockStream, "get_json_schema", return_value={})
|
412
|
-
|
413
|
-
src = MockSource(streams=[s1, s2])
|
414
|
-
catalog = ConfiguredAirbyteCatalog(
|
415
|
-
streams=[
|
416
|
-
_configured_stream(s1, SyncMode.full_refresh),
|
417
|
-
_configured_stream(s2, SyncMode.full_refresh),
|
418
|
-
]
|
419
|
-
)
|
420
|
-
|
421
|
-
expected = _fix_emitted_at(
|
422
|
-
[
|
423
|
-
_as_stream_status("s1", AirbyteStreamStatus.STARTED),
|
424
|
-
_as_stream_status("s1", AirbyteStreamStatus.RUNNING),
|
425
|
-
*_as_records("s1", stream_output),
|
426
|
-
_as_state("s1", {"__ab_full_refresh_state_message": True}),
|
427
|
-
_as_stream_status("s1", AirbyteStreamStatus.COMPLETE),
|
428
|
-
_as_stream_status("s2", AirbyteStreamStatus.STARTED),
|
429
|
-
_as_stream_status("s2", AirbyteStreamStatus.RUNNING),
|
430
|
-
*_as_records("s2", stream_output),
|
431
|
-
_as_state("s2", {"__ab_full_refresh_state_message": True}),
|
432
|
-
_as_stream_status("s2", AirbyteStreamStatus.COMPLETE),
|
433
|
-
]
|
434
|
-
)
|
435
|
-
messages = _fix_emitted_at(list(src.read(logger, {}, catalog)))
|
436
|
-
|
437
|
-
assert expected == messages
|
438
|
-
|
439
|
-
|
440
|
-
def test_valid_full_refresh_read_with_slices(mocker):
|
441
|
-
"""Tests that running a full refresh sync on streams which use slices produces the expected AirbyteMessages"""
|
442
|
-
slices = [{"1": "1"}, {"2": "2"}]
|
443
|
-
# When attempting to sync a slice, just output that slice as a record
|
444
|
-
s1 = MockStream(
|
445
|
-
[({"stream_state": {}, "sync_mode": SyncMode.full_refresh, "stream_slice": s}, [s]) for s in slices],
|
446
|
-
name="s1",
|
447
|
-
)
|
448
|
-
s2 = MockStream(
|
449
|
-
[({"stream_state": {}, "sync_mode": SyncMode.full_refresh, "stream_slice": s}, [s]) for s in slices],
|
450
|
-
name="s2",
|
451
|
-
)
|
452
|
-
|
453
|
-
mocker.patch.object(MockStream, "get_json_schema", return_value={})
|
454
|
-
mocker.patch.object(MockStream, "stream_slices", return_value=slices)
|
455
|
-
|
456
|
-
src = MockSource(streams=[s1, s2])
|
457
|
-
catalog = ConfiguredAirbyteCatalog(
|
458
|
-
streams=[
|
459
|
-
_configured_stream(s1, SyncMode.full_refresh),
|
460
|
-
_configured_stream(s2, SyncMode.full_refresh),
|
461
|
-
]
|
462
|
-
)
|
463
|
-
|
464
|
-
expected = _fix_emitted_at(
|
465
|
-
[
|
466
|
-
_as_stream_status("s1", AirbyteStreamStatus.STARTED),
|
467
|
-
_as_stream_status("s1", AirbyteStreamStatus.RUNNING),
|
468
|
-
*_as_records("s1", slices),
|
469
|
-
_as_state("s1", {"__ab_full_refresh_state_message": True}),
|
470
|
-
_as_stream_status("s1", AirbyteStreamStatus.COMPLETE),
|
471
|
-
_as_stream_status("s2", AirbyteStreamStatus.STARTED),
|
472
|
-
_as_stream_status("s2", AirbyteStreamStatus.RUNNING),
|
473
|
-
*_as_records("s2", slices),
|
474
|
-
_as_state("s2", {"__ab_full_refresh_state_message": True}),
|
475
|
-
_as_stream_status("s2", AirbyteStreamStatus.COMPLETE),
|
476
|
-
]
|
477
|
-
)
|
478
|
-
|
479
|
-
messages = _fix_emitted_at(list(src.read(logger, {}, catalog)))
|
480
|
-
|
481
|
-
assert expected == messages
|
482
|
-
|
483
|
-
|
484
|
-
def test_full_refresh_does_not_use_incoming_state(mocker):
|
485
|
-
"""Tests that running a full refresh sync does not use an incoming state message from the platform"""
|
486
|
-
slices = [{"1": "1"}, {"2": "2"}]
|
487
|
-
# When attempting to sync a slice, just output that slice as a record
|
488
|
-
s1 = MockStream(
|
489
|
-
[({"stream_state": {}, "sync_mode": SyncMode.full_refresh, "stream_slice": s}, [s]) for s in slices],
|
490
|
-
name="s1",
|
491
|
-
)
|
492
|
-
s2 = MockStream(
|
493
|
-
[({"stream_state": {}, "sync_mode": SyncMode.full_refresh, "stream_slice": s}, [s]) for s in slices],
|
494
|
-
name="s2",
|
495
|
-
)
|
496
|
-
|
497
|
-
def stream_slices_side_effect(stream_state: Mapping[str, Any], **kwargs) -> List[Mapping[str, Any]]:
|
498
|
-
if stream_state:
|
499
|
-
return slices[1:]
|
500
|
-
else:
|
501
|
-
return slices
|
502
|
-
|
503
|
-
mocker.patch.object(MockStream, "get_json_schema", return_value={})
|
504
|
-
mocker.patch.object(MockStream, "stream_slices", side_effect=stream_slices_side_effect)
|
505
|
-
|
506
|
-
state = [
|
507
|
-
AirbyteStateMessage(
|
508
|
-
type=AirbyteStateType.STREAM,
|
509
|
-
stream=AirbyteStreamState(
|
510
|
-
stream_descriptor=StreamDescriptor(name="s1"),
|
511
|
-
stream_state=AirbyteStateBlob.parse_obj({"created_at": "2024-01-31"}),
|
512
|
-
),
|
513
|
-
),
|
514
|
-
AirbyteStateMessage(
|
515
|
-
type=AirbyteStateType.STREAM,
|
516
|
-
stream=AirbyteStreamState(
|
517
|
-
stream_descriptor=StreamDescriptor(name="s2"),
|
518
|
-
stream_state=AirbyteStateBlob.parse_obj({"__ab_full_refresh_state_message": True}),
|
519
|
-
),
|
520
|
-
),
|
521
|
-
]
|
522
|
-
|
523
|
-
src = MockSource(streams=[s1, s2])
|
524
|
-
catalog = ConfiguredAirbyteCatalog(
|
525
|
-
streams=[
|
526
|
-
_configured_stream(s1, SyncMode.full_refresh),
|
527
|
-
_configured_stream(s2, SyncMode.full_refresh),
|
528
|
-
]
|
529
|
-
)
|
530
|
-
|
531
|
-
expected = _fix_emitted_at(
|
532
|
-
[
|
533
|
-
_as_stream_status("s1", AirbyteStreamStatus.STARTED),
|
534
|
-
_as_stream_status("s1", AirbyteStreamStatus.RUNNING),
|
535
|
-
*_as_records("s1", slices),
|
536
|
-
_as_state("s1", {"__ab_full_refresh_state_message": True}),
|
537
|
-
_as_stream_status("s1", AirbyteStreamStatus.COMPLETE),
|
538
|
-
_as_stream_status("s2", AirbyteStreamStatus.STARTED),
|
539
|
-
_as_stream_status("s2", AirbyteStreamStatus.RUNNING),
|
540
|
-
*_as_records("s2", slices),
|
541
|
-
_as_state("s2", {"__ab_full_refresh_state_message": True}),
|
542
|
-
_as_stream_status("s2", AirbyteStreamStatus.COMPLETE),
|
543
|
-
]
|
544
|
-
)
|
545
|
-
|
546
|
-
messages = _fix_emitted_at(list(src.read(logger, {}, catalog, state)))
|
547
|
-
|
548
|
-
assert messages == expected
|
549
|
-
|
550
|
-
|
551
|
-
@pytest.mark.parametrize(
|
552
|
-
"slices",
|
553
|
-
[[{"1": "1"}, {"2": "2"}], [{"date": datetime.date(year=2023, month=1, day=1)}, {"date": datetime.date(year=2023, month=1, day=1)}]],
|
554
|
-
)
|
555
|
-
def test_read_full_refresh_with_slices_sends_slice_messages(mocker, slices):
|
556
|
-
"""Given the logger is debug and a full refresh, AirbyteMessages are sent for slices"""
|
557
|
-
debug_logger = logging.getLogger("airbyte.debug")
|
558
|
-
debug_logger.setLevel(logging.DEBUG)
|
559
|
-
stream = MockStream(
|
560
|
-
[({"stream_state": {}, "sync_mode": SyncMode.full_refresh, "stream_slice": s}, [s]) for s in slices],
|
561
|
-
name="s1",
|
562
|
-
)
|
563
|
-
|
564
|
-
mocker.patch.object(MockStream, "get_json_schema", return_value={})
|
565
|
-
mocker.patch.object(MockStream, "stream_slices", return_value=slices)
|
566
|
-
|
567
|
-
src = MockSource(streams=[stream])
|
568
|
-
catalog = ConfiguredAirbyteCatalog(
|
569
|
-
streams=[
|
570
|
-
_configured_stream(stream, SyncMode.full_refresh),
|
571
|
-
]
|
572
|
-
)
|
573
|
-
|
574
|
-
messages = src.read(debug_logger, {}, catalog)
|
575
|
-
|
576
|
-
assert 2 == len(list(filter(lambda message: message.log and message.log.message.startswith("slice:"), messages)))
|
577
|
-
|
578
|
-
|
579
|
-
def test_read_incremental_with_slices_sends_slice_messages(mocker):
|
580
|
-
"""Given the logger is debug and a incremental, AirbyteMessages are sent for slices"""
|
581
|
-
debug_logger = logging.getLogger("airbyte.debug")
|
582
|
-
debug_logger.setLevel(logging.DEBUG)
|
583
|
-
slices = [{"1": "1"}, {"2": "2"}]
|
584
|
-
stream = MockStream(
|
585
|
-
[({"sync_mode": SyncMode.incremental, "stream_slice": s, "stream_state": {}}, [s]) for s in slices],
|
586
|
-
name="s1",
|
587
|
-
)
|
588
|
-
|
589
|
-
MockStream.supports_incremental = mocker.PropertyMock(return_value=True)
|
590
|
-
mocker.patch.object(MockStream, "get_json_schema", return_value={})
|
591
|
-
mocker.patch.object(MockStream, "stream_slices", return_value=slices)
|
592
|
-
|
593
|
-
src = MockSource(streams=[stream])
|
594
|
-
catalog = ConfiguredAirbyteCatalog(
|
595
|
-
streams=[
|
596
|
-
_configured_stream(stream, SyncMode.incremental),
|
597
|
-
]
|
598
|
-
)
|
599
|
-
|
600
|
-
messages = src.read(debug_logger, {}, catalog)
|
601
|
-
|
602
|
-
assert 2 == len(list(filter(lambda message: message.log and message.log.message.startswith("slice:"), messages)))
|
603
|
-
|
604
|
-
|
605
|
-
class TestIncrementalRead:
|
606
|
-
@pytest.mark.parametrize(
|
607
|
-
"use_legacy",
|
608
|
-
[
|
609
|
-
pytest.param(True, id="test_incoming_stream_state_as_legacy_format"),
|
610
|
-
pytest.param(False, id="test_incoming_stream_state_as_per_stream_format"),
|
611
|
-
],
|
612
|
-
)
|
613
|
-
def test_with_state_attribute(self, mocker, use_legacy):
|
614
|
-
"""Test correct state passing for the streams that have a state attribute"""
|
615
|
-
stream_output = [{"k1": "v1"}, {"k2": "v2"}]
|
616
|
-
old_state = {"cursor": "old_value"}
|
617
|
-
if use_legacy:
|
618
|
-
input_state = {"s1": old_state}
|
619
|
-
else:
|
620
|
-
input_state = [
|
621
|
-
AirbyteStateMessage(
|
622
|
-
type=AirbyteStateType.STREAM,
|
623
|
-
stream=AirbyteStreamState(
|
624
|
-
stream_descriptor=StreamDescriptor(name="s1"), stream_state=AirbyteStateBlob.parse_obj(old_state)
|
625
|
-
),
|
626
|
-
),
|
627
|
-
]
|
628
|
-
new_state_from_connector = {"cursor": "new_value"}
|
629
|
-
|
630
|
-
stream_1 = MockStreamWithState(
|
631
|
-
[
|
632
|
-
(
|
633
|
-
{"sync_mode": SyncMode.incremental, "stream_state": old_state},
|
634
|
-
stream_output,
|
635
|
-
)
|
636
|
-
],
|
637
|
-
name="s1",
|
638
|
-
)
|
639
|
-
stream_2 = MockStreamWithState(
|
640
|
-
[({"sync_mode": SyncMode.incremental, "stream_state": {}}, stream_output)],
|
641
|
-
name="s2",
|
642
|
-
)
|
643
|
-
mocker.patch.object(MockStreamWithState, "get_updated_state", return_value={})
|
644
|
-
state_property = mocker.patch.object(
|
645
|
-
MockStreamWithState,
|
646
|
-
"state",
|
647
|
-
new_callable=mocker.PropertyMock,
|
648
|
-
return_value=new_state_from_connector,
|
649
|
-
)
|
650
|
-
mocker.patch.object(MockStreamWithState, "get_json_schema", return_value={})
|
651
|
-
src = MockSource(streams=[stream_1, stream_2])
|
652
|
-
catalog = ConfiguredAirbyteCatalog(
|
653
|
-
streams=[
|
654
|
-
_configured_stream(stream_1, SyncMode.incremental),
|
655
|
-
_configured_stream(stream_2, SyncMode.incremental),
|
656
|
-
]
|
657
|
-
)
|
658
|
-
|
659
|
-
expected = _fix_emitted_at(
|
660
|
-
[
|
661
|
-
_as_stream_status("s1", AirbyteStreamStatus.STARTED),
|
662
|
-
_as_stream_status("s1", AirbyteStreamStatus.RUNNING),
|
663
|
-
_as_record("s1", stream_output[0]),
|
664
|
-
_as_record("s1", stream_output[1]),
|
665
|
-
_as_state("s1", new_state_from_connector),
|
666
|
-
_as_stream_status("s1", AirbyteStreamStatus.COMPLETE),
|
667
|
-
_as_stream_status("s2", AirbyteStreamStatus.STARTED),
|
668
|
-
_as_stream_status("s2", AirbyteStreamStatus.RUNNING),
|
669
|
-
_as_record("s2", stream_output[0]),
|
670
|
-
_as_record("s2", stream_output[1]),
|
671
|
-
_as_state("s2", new_state_from_connector),
|
672
|
-
_as_stream_status("s2", AirbyteStreamStatus.COMPLETE),
|
673
|
-
]
|
674
|
-
)
|
675
|
-
messages = _fix_emitted_at(list(src.read(logger, {}, catalog, state=input_state)))
|
676
|
-
|
677
|
-
assert messages == expected
|
678
|
-
assert state_property.mock_calls == [
|
679
|
-
call(old_state), # set state for s1
|
680
|
-
call(), # get state in the end of slice for s1
|
681
|
-
call(), # get state in the end of slice for s2
|
682
|
-
]
|
683
|
-
|
684
|
-
@pytest.mark.parametrize(
|
685
|
-
"use_legacy",
|
686
|
-
[
|
687
|
-
pytest.param(True, id="test_incoming_stream_state_as_legacy_format"),
|
688
|
-
pytest.param(False, id="test_incoming_stream_state_as_per_stream_format"),
|
689
|
-
],
|
690
|
-
)
|
691
|
-
def test_with_checkpoint_interval(self, mocker, use_legacy):
|
692
|
-
"""Tests that an incremental read which doesn't specify a checkpoint interval outputs a STATE message
|
693
|
-
after reading N records within a stream.
|
694
|
-
"""
|
695
|
-
if use_legacy:
|
696
|
-
input_state = defaultdict(dict)
|
697
|
-
else:
|
698
|
-
input_state = []
|
699
|
-
stream_output = [{"k1": "v1"}, {"k2": "v2"}]
|
700
|
-
|
701
|
-
stream_1 = MockStream(
|
702
|
-
[({"sync_mode": SyncMode.incremental, "stream_state": {}}, stream_output)],
|
703
|
-
name="s1",
|
704
|
-
)
|
705
|
-
stream_2 = MockStream(
|
706
|
-
[({"sync_mode": SyncMode.incremental, "stream_state": {}}, stream_output)],
|
707
|
-
name="s2",
|
708
|
-
)
|
709
|
-
state = {"cursor": "value"}
|
710
|
-
mocker.patch.object(MockStream, "get_updated_state", return_value=state)
|
711
|
-
mocker.patch.object(MockStream, "supports_incremental", return_value=True)
|
712
|
-
mocker.patch.object(MockStream, "get_json_schema", return_value={})
|
713
|
-
# Tell the source to output one state message per record
|
714
|
-
mocker.patch.object(
|
715
|
-
MockStream,
|
716
|
-
"state_checkpoint_interval",
|
717
|
-
new_callable=mocker.PropertyMock,
|
718
|
-
return_value=1,
|
719
|
-
)
|
720
|
-
|
721
|
-
src = MockSource(streams=[stream_1, stream_2])
|
722
|
-
catalog = ConfiguredAirbyteCatalog(
|
723
|
-
streams=[
|
724
|
-
_configured_stream(stream_1, SyncMode.incremental),
|
725
|
-
_configured_stream(stream_2, SyncMode.incremental),
|
726
|
-
]
|
727
|
-
)
|
728
|
-
|
729
|
-
expected = _fix_emitted_at(
|
730
|
-
[
|
731
|
-
_as_stream_status("s1", AirbyteStreamStatus.STARTED),
|
732
|
-
_as_stream_status("s1", AirbyteStreamStatus.RUNNING),
|
733
|
-
_as_record("s1", stream_output[0]),
|
734
|
-
_as_state("s1", state),
|
735
|
-
_as_record("s1", stream_output[1]),
|
736
|
-
_as_state("s1", state),
|
737
|
-
_as_state("s1", state),
|
738
|
-
_as_stream_status("s1", AirbyteStreamStatus.COMPLETE),
|
739
|
-
_as_stream_status("s2", AirbyteStreamStatus.STARTED),
|
740
|
-
_as_stream_status("s2", AirbyteStreamStatus.RUNNING),
|
741
|
-
_as_record("s2", stream_output[0]),
|
742
|
-
_as_state("s2", state),
|
743
|
-
_as_record("s2", stream_output[1]),
|
744
|
-
_as_state("s2", state),
|
745
|
-
_as_state("s2", state),
|
746
|
-
_as_stream_status("s2", AirbyteStreamStatus.COMPLETE),
|
747
|
-
]
|
748
|
-
)
|
749
|
-
messages = _fix_emitted_at(list(src.read(logger, {}, catalog, state=input_state)))
|
750
|
-
|
751
|
-
assert expected == messages
|
752
|
-
|
753
|
-
@pytest.mark.parametrize(
|
754
|
-
"use_legacy",
|
755
|
-
[
|
756
|
-
pytest.param(True, id="test_incoming_stream_state_as_legacy_format"),
|
757
|
-
pytest.param(False, id="test_incoming_stream_state_as_per_stream_format"),
|
758
|
-
],
|
759
|
-
)
|
760
|
-
def test_with_no_interval(self, mocker, use_legacy):
|
761
|
-
"""Tests that an incremental read which doesn't specify a checkpoint interval outputs
|
762
|
-
a STATE message only after fully reading the stream and does not output any STATE messages during syncing the stream.
|
763
|
-
"""
|
764
|
-
if use_legacy:
|
765
|
-
input_state = defaultdict(dict)
|
766
|
-
else:
|
767
|
-
input_state = []
|
768
|
-
stream_output = [{"k1": "v1"}, {"k2": "v2"}]
|
769
|
-
|
770
|
-
stream_1 = MockStream(
|
771
|
-
[({"sync_mode": SyncMode.incremental, "stream_state": {}}, stream_output)],
|
772
|
-
name="s1",
|
773
|
-
)
|
774
|
-
stream_2 = MockStream(
|
775
|
-
[({"sync_mode": SyncMode.incremental, "stream_state": {}}, stream_output)],
|
776
|
-
name="s2",
|
777
|
-
)
|
778
|
-
state = {"cursor": "value"}
|
779
|
-
mocker.patch.object(MockStream, "get_updated_state", return_value=state)
|
780
|
-
mocker.patch.object(MockStream, "supports_incremental", return_value=True)
|
781
|
-
mocker.patch.object(MockStream, "get_json_schema", return_value={})
|
782
|
-
|
783
|
-
src = MockSource(streams=[stream_1, stream_2])
|
784
|
-
catalog = ConfiguredAirbyteCatalog(
|
785
|
-
streams=[
|
786
|
-
_configured_stream(stream_1, SyncMode.incremental),
|
787
|
-
_configured_stream(stream_2, SyncMode.incremental),
|
788
|
-
]
|
789
|
-
)
|
790
|
-
|
791
|
-
expected = _fix_emitted_at(
|
792
|
-
[
|
793
|
-
_as_stream_status("s1", AirbyteStreamStatus.STARTED),
|
794
|
-
_as_stream_status("s1", AirbyteStreamStatus.RUNNING),
|
795
|
-
*_as_records("s1", stream_output),
|
796
|
-
_as_state("s1", state),
|
797
|
-
_as_stream_status("s1", AirbyteStreamStatus.COMPLETE),
|
798
|
-
_as_stream_status("s2", AirbyteStreamStatus.STARTED),
|
799
|
-
_as_stream_status("s2", AirbyteStreamStatus.RUNNING),
|
800
|
-
*_as_records("s2", stream_output),
|
801
|
-
_as_state("s2", state),
|
802
|
-
_as_stream_status("s2", AirbyteStreamStatus.COMPLETE),
|
803
|
-
]
|
804
|
-
)
|
805
|
-
|
806
|
-
messages = _fix_emitted_at(list(src.read(logger, {}, catalog, state=input_state)))
|
807
|
-
|
808
|
-
assert expected == messages
|
809
|
-
|
810
|
-
@pytest.mark.parametrize(
|
811
|
-
"use_legacy",
|
812
|
-
[
|
813
|
-
pytest.param(True, id="test_incoming_stream_state_as_legacy_format"),
|
814
|
-
pytest.param(False, id="test_incoming_stream_state_as_per_stream_format"),
|
815
|
-
],
|
816
|
-
)
|
817
|
-
def test_with_slices(self, mocker, use_legacy):
|
818
|
-
"""Tests that an incremental read which uses slices outputs each record in the slice followed by a STATE message, for each slice"""
|
819
|
-
if use_legacy:
|
820
|
-
input_state = defaultdict(dict)
|
821
|
-
else:
|
822
|
-
input_state = []
|
823
|
-
slices = [{"1": "1"}, {"2": "2"}]
|
824
|
-
stream_output = [{"k1": "v1"}, {"k2": "v2"}, {"k3": "v3"}]
|
825
|
-
|
826
|
-
stream_1 = MockStream(
|
827
|
-
[
|
828
|
-
(
|
829
|
-
{
|
830
|
-
"sync_mode": SyncMode.incremental,
|
831
|
-
"stream_slice": s,
|
832
|
-
"stream_state": mocker.ANY,
|
833
|
-
},
|
834
|
-
stream_output,
|
835
|
-
)
|
836
|
-
for s in slices
|
837
|
-
],
|
838
|
-
name="s1",
|
839
|
-
)
|
840
|
-
stream_2 = MockStream(
|
841
|
-
[
|
842
|
-
(
|
843
|
-
{
|
844
|
-
"sync_mode": SyncMode.incremental,
|
845
|
-
"stream_slice": s,
|
846
|
-
"stream_state": mocker.ANY,
|
847
|
-
},
|
848
|
-
stream_output,
|
849
|
-
)
|
850
|
-
for s in slices
|
851
|
-
],
|
852
|
-
name="s2",
|
853
|
-
)
|
854
|
-
state = {"cursor": "value"}
|
855
|
-
mocker.patch.object(MockStream, "get_updated_state", return_value=state)
|
856
|
-
mocker.patch.object(MockStream, "supports_incremental", return_value=True)
|
857
|
-
mocker.patch.object(MockStream, "get_json_schema", return_value={})
|
858
|
-
mocker.patch.object(MockStream, "stream_slices", return_value=slices)
|
859
|
-
|
860
|
-
src = MockSource(streams=[stream_1, stream_2])
|
861
|
-
catalog = ConfiguredAirbyteCatalog(
|
862
|
-
streams=[
|
863
|
-
_configured_stream(stream_1, SyncMode.incremental),
|
864
|
-
_configured_stream(stream_2, SyncMode.incremental),
|
865
|
-
]
|
866
|
-
)
|
867
|
-
|
868
|
-
expected = _fix_emitted_at(
|
869
|
-
[
|
870
|
-
_as_stream_status("s1", AirbyteStreamStatus.STARTED),
|
871
|
-
_as_stream_status("s1", AirbyteStreamStatus.RUNNING),
|
872
|
-
# stream 1 slice 1
|
873
|
-
*_as_records("s1", stream_output),
|
874
|
-
_as_state("s1", state),
|
875
|
-
# stream 1 slice 2
|
876
|
-
*_as_records("s1", stream_output),
|
877
|
-
_as_state("s1", state),
|
878
|
-
_as_stream_status("s1", AirbyteStreamStatus.COMPLETE),
|
879
|
-
_as_stream_status("s2", AirbyteStreamStatus.STARTED),
|
880
|
-
_as_stream_status("s2", AirbyteStreamStatus.RUNNING),
|
881
|
-
# stream 2 slice 1
|
882
|
-
*_as_records("s2", stream_output),
|
883
|
-
_as_state("s2", state),
|
884
|
-
# stream 2 slice 2
|
885
|
-
*_as_records("s2", stream_output),
|
886
|
-
_as_state("s2", state),
|
887
|
-
_as_stream_status("s2", AirbyteStreamStatus.COMPLETE),
|
888
|
-
]
|
889
|
-
)
|
890
|
-
|
891
|
-
messages = _fix_emitted_at(list(src.read(logger, {}, catalog, state=input_state)))
|
892
|
-
|
893
|
-
assert expected == messages
|
894
|
-
|
895
|
-
@pytest.mark.parametrize(
|
896
|
-
"use_legacy",
|
897
|
-
[
|
898
|
-
pytest.param(True, id="test_incoming_stream_state_as_legacy_format"),
|
899
|
-
pytest.param(False, id="test_incoming_stream_state_as_per_stream_format"),
|
900
|
-
],
|
901
|
-
)
|
902
|
-
@pytest.mark.parametrize("slices", [pytest.param([], id="test_slices_as_list"), pytest.param(iter([]), id="test_slices_as_iterator")])
|
903
|
-
def test_no_slices(self, mocker, use_legacy, slices):
|
904
|
-
"""
|
905
|
-
Tests that an incremental read returns at least one state messages even if no records were read:
|
906
|
-
1. outputs a state message after reading the entire stream
|
907
|
-
"""
|
908
|
-
if use_legacy:
|
909
|
-
input_state = defaultdict(dict)
|
910
|
-
else:
|
911
|
-
input_state = []
|
912
|
-
|
913
|
-
stream_output = [{"k1": "v1"}, {"k2": "v2"}, {"k3": "v3"}]
|
914
|
-
state = {"cursor": "value"}
|
915
|
-
stream_1 = MockStreamWithState(
|
916
|
-
[
|
917
|
-
(
|
918
|
-
{
|
919
|
-
"sync_mode": SyncMode.incremental,
|
920
|
-
"stream_slice": s,
|
921
|
-
"stream_state": mocker.ANY,
|
922
|
-
},
|
923
|
-
stream_output,
|
924
|
-
)
|
925
|
-
for s in slices
|
926
|
-
],
|
927
|
-
name="s1",
|
928
|
-
state=state,
|
929
|
-
)
|
930
|
-
stream_2 = MockStreamWithState(
|
931
|
-
[
|
932
|
-
(
|
933
|
-
{
|
934
|
-
"sync_mode": SyncMode.incremental,
|
935
|
-
"stream_slice": s,
|
936
|
-
"stream_state": mocker.ANY,
|
937
|
-
},
|
938
|
-
stream_output,
|
939
|
-
)
|
940
|
-
for s in slices
|
941
|
-
],
|
942
|
-
name="s2",
|
943
|
-
state=state,
|
944
|
-
)
|
945
|
-
|
946
|
-
mocker.patch.object(MockStreamWithState, "supports_incremental", return_value=True)
|
947
|
-
mocker.patch.object(MockStreamWithState, "get_json_schema", return_value={})
|
948
|
-
mocker.patch.object(MockStreamWithState, "stream_slices", return_value=slices)
|
949
|
-
mocker.patch.object(
|
950
|
-
MockStreamWithState,
|
951
|
-
"state_checkpoint_interval",
|
952
|
-
new_callable=mocker.PropertyMock,
|
953
|
-
return_value=2,
|
954
|
-
)
|
955
|
-
|
956
|
-
src = MockSource(streams=[stream_1, stream_2])
|
957
|
-
catalog = ConfiguredAirbyteCatalog(
|
958
|
-
streams=[
|
959
|
-
_configured_stream(stream_1, SyncMode.incremental),
|
960
|
-
_configured_stream(stream_2, SyncMode.incremental),
|
961
|
-
]
|
962
|
-
)
|
963
|
-
|
964
|
-
expected = _fix_emitted_at(
|
965
|
-
[
|
966
|
-
_as_stream_status("s1", AirbyteStreamStatus.STARTED),
|
967
|
-
_as_state("s1", state),
|
968
|
-
_as_stream_status("s1", AirbyteStreamStatus.COMPLETE),
|
969
|
-
_as_stream_status("s2", AirbyteStreamStatus.STARTED),
|
970
|
-
_as_state("s2", state),
|
971
|
-
_as_stream_status("s2", AirbyteStreamStatus.COMPLETE),
|
972
|
-
]
|
973
|
-
)
|
974
|
-
|
975
|
-
messages = _fix_emitted_at(list(src.read(logger, {}, catalog, state=input_state)))
|
976
|
-
|
977
|
-
assert expected == messages
|
978
|
-
|
979
|
-
@pytest.mark.parametrize(
|
980
|
-
"use_legacy",
|
981
|
-
[
|
982
|
-
pytest.param(True, id="test_incoming_stream_state_as_legacy_format"),
|
983
|
-
pytest.param(False, id="test_incoming_stream_state_as_per_stream_format"),
|
984
|
-
],
|
985
|
-
)
|
986
|
-
def test_with_slices_and_interval(self, mocker, use_legacy):
|
987
|
-
"""
|
988
|
-
Tests that an incremental read which uses slices and a checkpoint interval:
|
989
|
-
1. outputs all records
|
990
|
-
2. outputs a state message every N records (N=checkpoint_interval)
|
991
|
-
3. outputs a state message after reading the entire slice
|
992
|
-
"""
|
993
|
-
if use_legacy:
|
994
|
-
input_state = defaultdict(dict)
|
995
|
-
else:
|
996
|
-
input_state = []
|
997
|
-
slices = [{"1": "1"}, {"2": "2"}]
|
998
|
-
stream_output = [{"k1": "v1"}, {"k2": "v2"}, {"k3": "v3"}]
|
999
|
-
stream_1 = MockStream(
|
1000
|
-
[
|
1001
|
-
(
|
1002
|
-
{
|
1003
|
-
"sync_mode": SyncMode.incremental,
|
1004
|
-
"stream_slice": s,
|
1005
|
-
"stream_state": mocker.ANY,
|
1006
|
-
},
|
1007
|
-
stream_output,
|
1008
|
-
)
|
1009
|
-
for s in slices
|
1010
|
-
],
|
1011
|
-
name="s1",
|
1012
|
-
)
|
1013
|
-
stream_2 = MockStream(
|
1014
|
-
[
|
1015
|
-
(
|
1016
|
-
{
|
1017
|
-
"sync_mode": SyncMode.incremental,
|
1018
|
-
"stream_slice": s,
|
1019
|
-
"stream_state": mocker.ANY,
|
1020
|
-
},
|
1021
|
-
stream_output,
|
1022
|
-
)
|
1023
|
-
for s in slices
|
1024
|
-
],
|
1025
|
-
name="s2",
|
1026
|
-
)
|
1027
|
-
state = {"cursor": "value"}
|
1028
|
-
mocker.patch.object(MockStream, "get_updated_state", return_value=state)
|
1029
|
-
mocker.patch.object(MockStream, "supports_incremental", return_value=True)
|
1030
|
-
mocker.patch.object(MockStream, "get_json_schema", return_value={})
|
1031
|
-
mocker.patch.object(MockStream, "stream_slices", return_value=slices)
|
1032
|
-
mocker.patch.object(
|
1033
|
-
MockStream,
|
1034
|
-
"state_checkpoint_interval",
|
1035
|
-
new_callable=mocker.PropertyMock,
|
1036
|
-
return_value=2,
|
1037
|
-
)
|
1038
|
-
|
1039
|
-
src = MockSource(streams=[stream_1, stream_2])
|
1040
|
-
catalog = ConfiguredAirbyteCatalog(
|
1041
|
-
streams=[
|
1042
|
-
_configured_stream(stream_1, SyncMode.incremental),
|
1043
|
-
_configured_stream(stream_2, SyncMode.incremental),
|
1044
|
-
]
|
1045
|
-
)
|
1046
|
-
|
1047
|
-
expected = _fix_emitted_at(
|
1048
|
-
[
|
1049
|
-
# stream 1 slice 1
|
1050
|
-
_as_stream_status("s1", AirbyteStreamStatus.STARTED),
|
1051
|
-
_as_stream_status("s1", AirbyteStreamStatus.RUNNING),
|
1052
|
-
_as_record("s1", stream_output[0]),
|
1053
|
-
_as_record("s1", stream_output[1]),
|
1054
|
-
_as_state("s1", state),
|
1055
|
-
_as_record("s1", stream_output[2]),
|
1056
|
-
_as_state("s1", state),
|
1057
|
-
# stream 1 slice 2
|
1058
|
-
_as_record("s1", stream_output[0]),
|
1059
|
-
_as_state("s1", state),
|
1060
|
-
_as_record("s1", stream_output[1]),
|
1061
|
-
_as_record("s1", stream_output[2]),
|
1062
|
-
_as_state("s1", state),
|
1063
|
-
_as_state("s1", state),
|
1064
|
-
_as_stream_status("s1", AirbyteStreamStatus.COMPLETE),
|
1065
|
-
# stream 2 slice 1
|
1066
|
-
_as_stream_status("s2", AirbyteStreamStatus.STARTED),
|
1067
|
-
_as_stream_status("s2", AirbyteStreamStatus.RUNNING),
|
1068
|
-
_as_record("s2", stream_output[0]),
|
1069
|
-
_as_record("s2", stream_output[1]),
|
1070
|
-
_as_state("s2", state),
|
1071
|
-
_as_record("s2", stream_output[2]),
|
1072
|
-
_as_state("s2", state),
|
1073
|
-
# stream 2 slice 2
|
1074
|
-
_as_record("s2", stream_output[0]),
|
1075
|
-
_as_state("s2", state),
|
1076
|
-
_as_record("s2", stream_output[1]),
|
1077
|
-
_as_record("s2", stream_output[2]),
|
1078
|
-
_as_state("s2", state),
|
1079
|
-
_as_state("s2", state),
|
1080
|
-
_as_stream_status("s2", AirbyteStreamStatus.COMPLETE),
|
1081
|
-
]
|
1082
|
-
)
|
1083
|
-
|
1084
|
-
messages = _fix_emitted_at(list(src.read(logger, {}, catalog, state=input_state)))
|
1085
|
-
|
1086
|
-
assert messages == expected
|
1087
|
-
|
1088
|
-
def test_emit_non_records(self, mocker):
|
1089
|
-
"""
|
1090
|
-
Tests that an incremental read which uses slices and a checkpoint interval:
|
1091
|
-
1. outputs all records
|
1092
|
-
2. outputs a state message every N records (N=checkpoint_interval)
|
1093
|
-
3. outputs a state message after reading the entire slice
|
1094
|
-
"""
|
1095
|
-
|
1096
|
-
input_state = []
|
1097
|
-
slices = [{"1": "1"}, {"2": "2"}]
|
1098
|
-
stream_output = [
|
1099
|
-
{"k1": "v1"},
|
1100
|
-
AirbyteLogMessage(level=Level.INFO, message="HELLO"),
|
1101
|
-
{"k2": "v2"},
|
1102
|
-
{"k3": "v3"},
|
1103
|
-
]
|
1104
|
-
stream_1 = MockStreamEmittingAirbyteMessages(
|
1105
|
-
[
|
1106
|
-
(
|
1107
|
-
{
|
1108
|
-
"sync_mode": SyncMode.incremental,
|
1109
|
-
"stream_slice": s,
|
1110
|
-
"stream_state": mocker.ANY,
|
1111
|
-
},
|
1112
|
-
stream_output,
|
1113
|
-
)
|
1114
|
-
for s in slices
|
1115
|
-
],
|
1116
|
-
name="s1",
|
1117
|
-
state=copy.deepcopy(input_state),
|
1118
|
-
)
|
1119
|
-
stream_2 = MockStreamEmittingAirbyteMessages(
|
1120
|
-
[
|
1121
|
-
(
|
1122
|
-
{
|
1123
|
-
"sync_mode": SyncMode.incremental,
|
1124
|
-
"stream_slice": s,
|
1125
|
-
"stream_state": mocker.ANY,
|
1126
|
-
},
|
1127
|
-
stream_output,
|
1128
|
-
)
|
1129
|
-
for s in slices
|
1130
|
-
],
|
1131
|
-
name="s2",
|
1132
|
-
state=copy.deepcopy(input_state),
|
1133
|
-
)
|
1134
|
-
state = {"cursor": "value"}
|
1135
|
-
mocker.patch.object(MockStream, "get_updated_state", return_value=state)
|
1136
|
-
mocker.patch.object(MockStream, "supports_incremental", return_value=True)
|
1137
|
-
mocker.patch.object(MockStream, "get_json_schema", return_value={})
|
1138
|
-
mocker.patch.object(MockStream, "stream_slices", return_value=slices)
|
1139
|
-
mocker.patch.object(
|
1140
|
-
MockStream,
|
1141
|
-
"state_checkpoint_interval",
|
1142
|
-
new_callable=mocker.PropertyMock,
|
1143
|
-
return_value=2,
|
1144
|
-
)
|
1145
|
-
|
1146
|
-
src = MockSource(streams=[stream_1, stream_2])
|
1147
|
-
catalog = ConfiguredAirbyteCatalog(
|
1148
|
-
streams=[
|
1149
|
-
_configured_stream(stream_1, SyncMode.incremental),
|
1150
|
-
_configured_stream(stream_2, SyncMode.incremental),
|
1151
|
-
]
|
1152
|
-
)
|
1153
|
-
|
1154
|
-
expected = _fix_emitted_at(
|
1155
|
-
[
|
1156
|
-
_as_stream_status("s1", AirbyteStreamStatus.STARTED),
|
1157
|
-
_as_stream_status("s1", AirbyteStreamStatus.RUNNING),
|
1158
|
-
# stream 1 slice 1
|
1159
|
-
stream_data_to_airbyte_message("s1", stream_output[0]),
|
1160
|
-
stream_data_to_airbyte_message("s1", stream_output[1]),
|
1161
|
-
stream_data_to_airbyte_message("s1", stream_output[2]),
|
1162
|
-
_as_state("s1", state),
|
1163
|
-
stream_data_to_airbyte_message("s1", stream_output[3]),
|
1164
|
-
_as_state("s1", state),
|
1165
|
-
# stream 1 slice 2
|
1166
|
-
stream_data_to_airbyte_message("s1", stream_output[0]),
|
1167
|
-
_as_state("s1", state),
|
1168
|
-
stream_data_to_airbyte_message("s1", stream_output[1]),
|
1169
|
-
stream_data_to_airbyte_message("s1", stream_output[2]),
|
1170
|
-
stream_data_to_airbyte_message("s1", stream_output[3]),
|
1171
|
-
_as_state("s1", state),
|
1172
|
-
_as_state("s1", state),
|
1173
|
-
_as_stream_status("s1", AirbyteStreamStatus.COMPLETE),
|
1174
|
-
# stream 2 slice 1
|
1175
|
-
_as_stream_status("s2", AirbyteStreamStatus.STARTED),
|
1176
|
-
_as_stream_status("s2", AirbyteStreamStatus.RUNNING),
|
1177
|
-
stream_data_to_airbyte_message("s2", stream_output[0]),
|
1178
|
-
stream_data_to_airbyte_message("s2", stream_output[1]),
|
1179
|
-
stream_data_to_airbyte_message("s2", stream_output[2]),
|
1180
|
-
_as_state("s2", state),
|
1181
|
-
stream_data_to_airbyte_message("s2", stream_output[3]),
|
1182
|
-
_as_state("s2", state),
|
1183
|
-
# stream 2 slice 2
|
1184
|
-
stream_data_to_airbyte_message("s2", stream_output[0]),
|
1185
|
-
_as_state("s2", state),
|
1186
|
-
stream_data_to_airbyte_message("s2", stream_output[1]),
|
1187
|
-
stream_data_to_airbyte_message("s2", stream_output[2]),
|
1188
|
-
stream_data_to_airbyte_message("s2", stream_output[3]),
|
1189
|
-
_as_state("s2", state),
|
1190
|
-
_as_state("s2", state),
|
1191
|
-
_as_stream_status("s2", AirbyteStreamStatus.COMPLETE),
|
1192
|
-
]
|
1193
|
-
)
|
1194
|
-
|
1195
|
-
messages = _fix_emitted_at(list(src.read(logger, {}, catalog, state=input_state)))
|
1196
|
-
|
1197
|
-
assert messages == expected
|
1198
|
-
|
1199
|
-
|
1200
|
-
def test_checkpoint_state_from_stream_instance():
|
1201
|
-
teams_stream = MockStreamOverridesStateMethod()
|
1202
|
-
managers_stream = StreamNoStateMethod()
|
1203
|
-
state_manager = ConnectorStateManager(
|
1204
|
-
{
|
1205
|
-
"teams": AirbyteStream(
|
1206
|
-
name="teams", namespace="", json_schema={}, supported_sync_modes=[SyncMode.full_refresh, SyncMode.incremental]
|
1207
|
-
),
|
1208
|
-
"managers": AirbyteStream(
|
1209
|
-
name="managers", namespace="", json_schema={}, supported_sync_modes=[SyncMode.full_refresh, SyncMode.incremental]
|
1210
|
-
),
|
1211
|
-
},
|
1212
|
-
[],
|
1213
|
-
)
|
1214
|
-
|
1215
|
-
# The stream_state passed to checkpoint_state() should be ignored since stream implements state function
|
1216
|
-
teams_stream.state = {"updated_at": "2022-09-11"}
|
1217
|
-
actual_message = teams_stream._checkpoint_state({"ignored": "state"}, state_manager)
|
1218
|
-
assert actual_message == _as_state("teams", {"updated_at": "2022-09-11"})
|
1219
|
-
|
1220
|
-
# The stream_state passed to checkpoint_state() should be used since the stream does not implement state function
|
1221
|
-
actual_message = managers_stream._checkpoint_state({"updated": "expected_here"}, state_manager)
|
1222
|
-
assert actual_message == _as_state("managers", {"updated": "expected_here"})
|
1223
|
-
|
1224
|
-
|
1225
|
-
@pytest.mark.parametrize(
|
1226
|
-
"exception_to_raise,expected_error_message,expected_internal_message",
|
1227
|
-
[
|
1228
|
-
pytest.param(
|
1229
|
-
AirbyteTracedException(message="I was born only to crash like Icarus"),
|
1230
|
-
"I was born only to crash like Icarus",
|
1231
|
-
None,
|
1232
|
-
id="test_raises_traced_exception",
|
1233
|
-
),
|
1234
|
-
pytest.param(
|
1235
|
-
Exception("Generic connector error message"),
|
1236
|
-
"Something went wrong in the connector. See the logs for more details.",
|
1237
|
-
"Generic connector error message",
|
1238
|
-
id="test_raises_generic_exception",
|
1239
|
-
),
|
1240
|
-
],
|
1241
|
-
)
|
1242
|
-
def test_continue_sync_with_failed_streams(mocker, exception_to_raise, expected_error_message, expected_internal_message):
|
1243
|
-
"""
|
1244
|
-
Tests that running a sync for a connector with multiple streams will continue syncing when one stream fails
|
1245
|
-
with an error. This source does not override the default behavior defined in the AbstractSource class.
|
1246
|
-
"""
|
1247
|
-
stream_output = [{"k1": "v1"}, {"k2": "v2"}]
|
1248
|
-
s1 = MockStream([({"sync_mode": SyncMode.full_refresh}, stream_output)], name="s1")
|
1249
|
-
s2 = StreamRaisesException(exception_to_raise=exception_to_raise)
|
1250
|
-
s3 = MockStream([({"sync_mode": SyncMode.full_refresh}, stream_output)], name="s3")
|
1251
|
-
|
1252
|
-
mocker.patch.object(MockStream, "get_json_schema", return_value={})
|
1253
|
-
mocker.patch.object(StreamRaisesException, "get_json_schema", return_value={})
|
1254
|
-
|
1255
|
-
src = MockSource(streams=[s1, s2, s3])
|
1256
|
-
catalog = ConfiguredAirbyteCatalog(
|
1257
|
-
streams=[
|
1258
|
-
_configured_stream(s1, SyncMode.full_refresh),
|
1259
|
-
_configured_stream(s2, SyncMode.full_refresh),
|
1260
|
-
_configured_stream(s3, SyncMode.full_refresh),
|
1261
|
-
]
|
1262
|
-
)
|
1263
|
-
|
1264
|
-
expected = _fix_emitted_at(
|
1265
|
-
[
|
1266
|
-
_as_stream_status("s1", AirbyteStreamStatus.STARTED),
|
1267
|
-
_as_stream_status("s1", AirbyteStreamStatus.RUNNING),
|
1268
|
-
*_as_records("s1", stream_output),
|
1269
|
-
_as_stream_status("s1", AirbyteStreamStatus.COMPLETE),
|
1270
|
-
_as_stream_status("lamentations", AirbyteStreamStatus.STARTED),
|
1271
|
-
_as_stream_status("lamentations", AirbyteStreamStatus.INCOMPLETE),
|
1272
|
-
_as_error_trace("lamentations", expected_error_message, expected_internal_message, FailureType.system_error, None),
|
1273
|
-
_as_stream_status("s3", AirbyteStreamStatus.STARTED),
|
1274
|
-
_as_stream_status("s3", AirbyteStreamStatus.RUNNING),
|
1275
|
-
*_as_records("s3", stream_output),
|
1276
|
-
_as_stream_status("s3", AirbyteStreamStatus.COMPLETE),
|
1277
|
-
]
|
1278
|
-
)
|
1279
|
-
|
1280
|
-
with pytest.raises(AirbyteTracedException) as exc:
|
1281
|
-
messages = [_remove_stack_trace(message) for message in src.read(logger, {}, catalog)]
|
1282
|
-
messages = _fix_emitted_at(messages)
|
1283
|
-
|
1284
|
-
assert expected == messages
|
1285
|
-
|
1286
|
-
assert "lamentations" in exc.value.message
|
1287
|
-
assert exc.value.failure_type == FailureType.config_error
|
1288
|
-
|
1289
|
-
|
1290
|
-
def test_continue_sync_source_override_false(mocker):
|
1291
|
-
"""
|
1292
|
-
Tests that running a sync for a connector explicitly overriding the default AbstractSource.stop_sync_on_stream_failure
|
1293
|
-
property to be False which will continue syncing stream even if one encountered an exception.
|
1294
|
-
"""
|
1295
|
-
update_secrets(["API_KEY_VALUE"])
|
1296
|
-
|
1297
|
-
stream_output = [{"k1": "v1"}, {"k2": "v2"}]
|
1298
|
-
s1 = MockStream([({"sync_mode": SyncMode.full_refresh}, stream_output)], name="s1")
|
1299
|
-
s2 = StreamRaisesException(exception_to_raise=AirbyteTracedException(message="I was born only to crash like Icarus"))
|
1300
|
-
s3 = MockStream([({"sync_mode": SyncMode.full_refresh}, stream_output)], name="s3")
|
1301
|
-
|
1302
|
-
mocker.patch.object(MockStream, "get_json_schema", return_value={})
|
1303
|
-
mocker.patch.object(StreamRaisesException, "get_json_schema", return_value={})
|
1304
|
-
|
1305
|
-
src = MockSourceWithStopSyncFalseOverride(streams=[s1, s2, s3])
|
1306
|
-
catalog = ConfiguredAirbyteCatalog(
|
1307
|
-
streams=[
|
1308
|
-
_configured_stream(s1, SyncMode.full_refresh),
|
1309
|
-
_configured_stream(s2, SyncMode.full_refresh),
|
1310
|
-
_configured_stream(s3, SyncMode.full_refresh),
|
1311
|
-
]
|
1312
|
-
)
|
1313
|
-
|
1314
|
-
expected = _fix_emitted_at(
|
1315
|
-
[
|
1316
|
-
_as_stream_status("s1", AirbyteStreamStatus.STARTED),
|
1317
|
-
_as_stream_status("s1", AirbyteStreamStatus.RUNNING),
|
1318
|
-
*_as_records("s1", stream_output),
|
1319
|
-
_as_stream_status("s1", AirbyteStreamStatus.COMPLETE),
|
1320
|
-
_as_stream_status("lamentations", AirbyteStreamStatus.STARTED),
|
1321
|
-
_as_stream_status("lamentations", AirbyteStreamStatus.INCOMPLETE),
|
1322
|
-
_as_error_trace("lamentations", "I was born only to crash like Icarus", None, FailureType.system_error, None),
|
1323
|
-
_as_stream_status("s3", AirbyteStreamStatus.STARTED),
|
1324
|
-
_as_stream_status("s3", AirbyteStreamStatus.RUNNING),
|
1325
|
-
*_as_records("s3", stream_output),
|
1326
|
-
_as_stream_status("s3", AirbyteStreamStatus.COMPLETE),
|
1327
|
-
]
|
1328
|
-
)
|
1329
|
-
|
1330
|
-
with pytest.raises(AirbyteTracedException) as exc:
|
1331
|
-
messages = [_remove_stack_trace(message) for message in src.read(logger, {}, catalog)]
|
1332
|
-
messages = _fix_emitted_at(messages)
|
1333
|
-
|
1334
|
-
assert expected == messages
|
1335
|
-
|
1336
|
-
assert "lamentations" in exc.value.message
|
1337
|
-
assert exc.value.failure_type == FailureType.config_error
|
1338
|
-
|
1339
|
-
|
1340
|
-
def test_sync_error_trace_messages_obfuscate_secrets(mocker):
|
1341
|
-
"""
|
1342
|
-
Tests that exceptions emitted as trace messages by a source have secrets properly sanitized
|
1343
|
-
"""
|
1344
|
-
update_secrets(["API_KEY_VALUE"])
|
1345
|
-
|
1346
|
-
stream_output = [{"k1": "v1"}, {"k2": "v2"}]
|
1347
|
-
s1 = MockStream([({"sync_mode": SyncMode.full_refresh}, stream_output)], name="s1")
|
1348
|
-
s2 = StreamRaisesException(
|
1349
|
-
exception_to_raise=AirbyteTracedException(message="My api_key value API_KEY_VALUE flew too close to the sun.")
|
1350
|
-
)
|
1351
|
-
s3 = MockStream([({"sync_mode": SyncMode.full_refresh}, stream_output)], name="s3")
|
1352
|
-
|
1353
|
-
mocker.patch.object(MockStream, "get_json_schema", return_value={})
|
1354
|
-
mocker.patch.object(StreamRaisesException, "get_json_schema", return_value={})
|
1355
|
-
|
1356
|
-
src = MockSource(streams=[s1, s2, s3])
|
1357
|
-
catalog = ConfiguredAirbyteCatalog(
|
1358
|
-
streams=[
|
1359
|
-
_configured_stream(s1, SyncMode.full_refresh),
|
1360
|
-
_configured_stream(s2, SyncMode.full_refresh),
|
1361
|
-
_configured_stream(s3, SyncMode.full_refresh),
|
1362
|
-
]
|
1363
|
-
)
|
1364
|
-
|
1365
|
-
expected = _fix_emitted_at(
|
1366
|
-
[
|
1367
|
-
_as_stream_status("s1", AirbyteStreamStatus.STARTED),
|
1368
|
-
_as_stream_status("s1", AirbyteStreamStatus.RUNNING),
|
1369
|
-
*_as_records("s1", stream_output),
|
1370
|
-
_as_stream_status("s1", AirbyteStreamStatus.COMPLETE),
|
1371
|
-
_as_stream_status("lamentations", AirbyteStreamStatus.STARTED),
|
1372
|
-
_as_stream_status("lamentations", AirbyteStreamStatus.INCOMPLETE),
|
1373
|
-
_as_error_trace("lamentations", "My api_key value **** flew too close to the sun.", None, FailureType.system_error, None),
|
1374
|
-
_as_stream_status("s3", AirbyteStreamStatus.STARTED),
|
1375
|
-
_as_stream_status("s3", AirbyteStreamStatus.RUNNING),
|
1376
|
-
*_as_records("s3", stream_output),
|
1377
|
-
_as_stream_status("s3", AirbyteStreamStatus.COMPLETE),
|
1378
|
-
]
|
1379
|
-
)
|
1380
|
-
|
1381
|
-
with pytest.raises(AirbyteTracedException) as exc:
|
1382
|
-
messages = [_remove_stack_trace(message) for message in src.read(logger, {}, catalog)]
|
1383
|
-
messages = _fix_emitted_at(messages)
|
1384
|
-
|
1385
|
-
assert expected == messages
|
1386
|
-
|
1387
|
-
assert "lamentations" in exc.value.message
|
1388
|
-
assert exc.value.failure_type == FailureType.config_error
|
1389
|
-
|
1390
|
-
|
1391
|
-
def test_continue_sync_with_failed_streams_with_override_false(mocker):
|
1392
|
-
"""
|
1393
|
-
Tests that running a sync for a connector with multiple streams and stop_sync_on_stream_failure enabled stops
|
1394
|
-
the sync when one stream fails with an error.
|
1395
|
-
"""
|
1396
|
-
stream_output = [{"k1": "v1"}, {"k2": "v2"}]
|
1397
|
-
s1 = MockStream([({"stream_state": {}, "sync_mode": SyncMode.full_refresh}, stream_output)], name="s1")
|
1398
|
-
s2 = StreamRaisesException(AirbyteTracedException(message="I was born only to crash like Icarus"))
|
1399
|
-
s3 = MockStream([({"stream_state": {}, "sync_mode": SyncMode.full_refresh}, stream_output)], name="s3")
|
1400
|
-
|
1401
|
-
mocker.patch.object(MockStream, "get_json_schema", return_value={})
|
1402
|
-
mocker.patch.object(StreamRaisesException, "get_json_schema", return_value={})
|
1403
|
-
|
1404
|
-
src = MockSource(streams=[s1, s2, s3])
|
1405
|
-
mocker.patch.object(MockSource, "stop_sync_on_stream_failure", return_value=True)
|
1406
|
-
catalog = ConfiguredAirbyteCatalog(
|
1407
|
-
streams=[
|
1408
|
-
_configured_stream(s1, SyncMode.full_refresh),
|
1409
|
-
_configured_stream(s2, SyncMode.full_refresh),
|
1410
|
-
_configured_stream(s3, SyncMode.full_refresh),
|
1411
|
-
]
|
1412
|
-
)
|
1413
|
-
|
1414
|
-
expected = _fix_emitted_at(
|
1415
|
-
[
|
1416
|
-
_as_stream_status("s1", AirbyteStreamStatus.STARTED),
|
1417
|
-
_as_stream_status("s1", AirbyteStreamStatus.RUNNING),
|
1418
|
-
*_as_records("s1", stream_output),
|
1419
|
-
_as_stream_status("s1", AirbyteStreamStatus.COMPLETE),
|
1420
|
-
_as_stream_status("lamentations", AirbyteStreamStatus.STARTED),
|
1421
|
-
_as_stream_status("lamentations", AirbyteStreamStatus.INCOMPLETE),
|
1422
|
-
_as_error_trace("lamentations", "I was born only to crash like Icarus", None, FailureType.system_error, None),
|
1423
|
-
]
|
1424
|
-
)
|
1425
|
-
|
1426
|
-
with pytest.raises(AirbyteTracedException) as exc:
|
1427
|
-
messages = [_remove_stack_trace(message) for message in src.read(logger, {}, catalog)]
|
1428
|
-
messages = _fix_emitted_at(messages)
|
1429
|
-
|
1430
|
-
assert expected == messages
|
1431
|
-
|
1432
|
-
assert "lamentations" in exc.value.message
|
1433
|
-
assert exc.value.failure_type == FailureType.config_error
|
1434
|
-
|
1435
|
-
|
1436
|
-
def _remove_stack_trace(message: AirbyteMessage) -> AirbyteMessage:
|
1437
|
-
"""
|
1438
|
-
Helper method that removes the stack trace from Airbyte trace messages to make asserting against expected records easier
|
1439
|
-
"""
|
1440
|
-
if message.trace and message.trace.error and message.trace.error.stack_trace:
|
1441
|
-
message.trace.error.stack_trace = None
|
1442
|
-
return message
|