airbyte-cdk 0.72.0__py3-none-any.whl → 6.13.1.dev4106__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 +421 -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 +1213 -88
- 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 +65 -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 +25 -3
- 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 +159 -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 +1329 -595
- 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 +1699 -226
- 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 +228 -72
- 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 +58 -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 +52 -15
- airbyte_cdk/sources/file_based/file_based_source.py +163 -33
- airbyte_cdk/sources/file_based/file_based_stream_reader.py +83 -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 +145 -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 +175 -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 +298 -42
- 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-6.13.1.dev4106.dist-info/METADATA +109 -0
- airbyte_cdk-6.13.1.dev4106.dist-info/RECORD +349 -0
- {airbyte_cdk-0.72.0.dist-info → airbyte_cdk-6.13.1.dev4106.dist-info}/WHEEL +1 -2
- airbyte_cdk-6.13.1.dev4106.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-0.72.0.dist-info/METADATA +0 -243
- airbyte_cdk-0.72.0.dist-info/RECORD +0 -466
- airbyte_cdk-0.72.0.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 -1841
- 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-0.72.0.dist-info → airbyte_cdk-6.13.1.dev4106.dist-info}/LICENSE.txt +0 -0
@@ -1,684 +0,0 @@
|
|
1
|
-
#
|
2
|
-
# Copyright (c) 2023 Airbyte, Inc., all rights reserved.
|
3
|
-
#
|
4
|
-
|
5
|
-
import json
|
6
|
-
import logging
|
7
|
-
import tempfile
|
8
|
-
from collections import defaultdict
|
9
|
-
from contextlib import nullcontext as does_not_raise
|
10
|
-
from typing import Any, Iterable, List, Mapping, MutableMapping, Optional, Tuple
|
11
|
-
|
12
|
-
import pytest
|
13
|
-
import requests
|
14
|
-
from airbyte_cdk.models import (
|
15
|
-
AirbyteGlobalState,
|
16
|
-
AirbyteStateBlob,
|
17
|
-
AirbyteStateMessage,
|
18
|
-
AirbyteStateType,
|
19
|
-
AirbyteStreamState,
|
20
|
-
ConfiguredAirbyteCatalog,
|
21
|
-
StreamDescriptor,
|
22
|
-
SyncMode,
|
23
|
-
Type,
|
24
|
-
)
|
25
|
-
from airbyte_cdk.sources import AbstractSource, Source
|
26
|
-
from airbyte_cdk.sources.streams.core import Stream
|
27
|
-
from airbyte_cdk.sources.streams.http.availability_strategy import HttpAvailabilityStrategy
|
28
|
-
from airbyte_cdk.sources.streams.http.http import HttpStream, HttpSubStream
|
29
|
-
from airbyte_cdk.sources.utils.transform import TransformConfig, TypeTransformer
|
30
|
-
from pydantic import ValidationError
|
31
|
-
|
32
|
-
|
33
|
-
class MockSource(Source):
|
34
|
-
def read(
|
35
|
-
self, logger: logging.Logger, config: Mapping[str, Any], catalog: ConfiguredAirbyteCatalog, state: MutableMapping[str, Any] = None
|
36
|
-
):
|
37
|
-
pass
|
38
|
-
|
39
|
-
def check(self, logger: logging.Logger, config: Mapping[str, Any]):
|
40
|
-
pass
|
41
|
-
|
42
|
-
def discover(self, logger: logging.Logger, config: Mapping[str, Any]):
|
43
|
-
pass
|
44
|
-
|
45
|
-
|
46
|
-
class MockAbstractSource(AbstractSource):
|
47
|
-
def __init__(self, streams: Optional[List[Stream]] = None):
|
48
|
-
self._streams = streams
|
49
|
-
|
50
|
-
def check_connection(self, *args, **kwargs) -> Tuple[bool, Optional[Any]]:
|
51
|
-
return True, ""
|
52
|
-
|
53
|
-
def streams(self, *args, **kwargs) -> List[Stream]:
|
54
|
-
if self._streams:
|
55
|
-
return self._streams
|
56
|
-
return []
|
57
|
-
|
58
|
-
|
59
|
-
@pytest.fixture
|
60
|
-
def source():
|
61
|
-
return MockSource()
|
62
|
-
|
63
|
-
|
64
|
-
@pytest.fixture
|
65
|
-
def catalog():
|
66
|
-
configured_catalog = {
|
67
|
-
"streams": [
|
68
|
-
{
|
69
|
-
"stream": {"name": "mock_http_stream", "json_schema": {}, "supported_sync_modes": ["full_refresh"]},
|
70
|
-
"destination_sync_mode": "overwrite",
|
71
|
-
"sync_mode": "full_refresh",
|
72
|
-
},
|
73
|
-
{
|
74
|
-
"stream": {"name": "mock_stream", "json_schema": {}, "supported_sync_modes": ["full_refresh"]},
|
75
|
-
"destination_sync_mode": "overwrite",
|
76
|
-
"sync_mode": "full_refresh",
|
77
|
-
},
|
78
|
-
]
|
79
|
-
}
|
80
|
-
return ConfiguredAirbyteCatalog.parse_obj(configured_catalog)
|
81
|
-
|
82
|
-
|
83
|
-
@pytest.fixture
|
84
|
-
def abstract_source(mocker):
|
85
|
-
mocker.patch.multiple(HttpStream, __abstractmethods__=set())
|
86
|
-
mocker.patch.multiple(Stream, __abstractmethods__=set())
|
87
|
-
|
88
|
-
class MockHttpStream(mocker.MagicMock, HttpStream):
|
89
|
-
url_base = "http://example.com"
|
90
|
-
path = "/dummy/path"
|
91
|
-
get_json_schema = mocker.MagicMock()
|
92
|
-
|
93
|
-
def supports_incremental(self):
|
94
|
-
return True
|
95
|
-
|
96
|
-
def __init__(self, *args, **kvargs):
|
97
|
-
mocker.MagicMock.__init__(self)
|
98
|
-
HttpStream.__init__(self, *args, kvargs)
|
99
|
-
self.read_records = mocker.MagicMock()
|
100
|
-
|
101
|
-
@property
|
102
|
-
def availability_strategy(self):
|
103
|
-
return None
|
104
|
-
|
105
|
-
class MockStream(mocker.MagicMock, Stream):
|
106
|
-
page_size = None
|
107
|
-
get_json_schema = mocker.MagicMock()
|
108
|
-
|
109
|
-
def __init__(self, **kwargs):
|
110
|
-
mocker.MagicMock.__init__(self)
|
111
|
-
self.read_records = mocker.MagicMock()
|
112
|
-
|
113
|
-
streams = [MockHttpStream(), MockStream()]
|
114
|
-
|
115
|
-
class MockAbstractSource(AbstractSource):
|
116
|
-
def check_connection(self):
|
117
|
-
return True, None
|
118
|
-
|
119
|
-
def streams(self, config):
|
120
|
-
self.streams_config = config
|
121
|
-
return streams
|
122
|
-
|
123
|
-
return MockAbstractSource()
|
124
|
-
|
125
|
-
|
126
|
-
@pytest.mark.parametrize(
|
127
|
-
"incoming_state, expected_state, expected_error",
|
128
|
-
[
|
129
|
-
pytest.param(
|
130
|
-
[
|
131
|
-
{
|
132
|
-
"type": "STREAM",
|
133
|
-
"stream": {
|
134
|
-
"stream_state": {"created_at": "2009-07-19"},
|
135
|
-
"stream_descriptor": {"name": "movies", "namespace": "public"},
|
136
|
-
},
|
137
|
-
}
|
138
|
-
],
|
139
|
-
[
|
140
|
-
AirbyteStateMessage(
|
141
|
-
type=AirbyteStateType.STREAM,
|
142
|
-
stream=AirbyteStreamState(
|
143
|
-
stream_descriptor=StreamDescriptor(name="movies", namespace="public"),
|
144
|
-
stream_state=AirbyteStateBlob.parse_obj({"created_at": "2009-07-19"}),
|
145
|
-
),
|
146
|
-
)
|
147
|
-
],
|
148
|
-
does_not_raise(),
|
149
|
-
id="test_incoming_stream_state",
|
150
|
-
),
|
151
|
-
pytest.param(
|
152
|
-
[
|
153
|
-
{
|
154
|
-
"type": "STREAM",
|
155
|
-
"stream": {
|
156
|
-
"stream_state": {"created_at": "2009-07-19"},
|
157
|
-
"stream_descriptor": {"name": "movies", "namespace": "public"},
|
158
|
-
},
|
159
|
-
},
|
160
|
-
{
|
161
|
-
"type": "STREAM",
|
162
|
-
"stream": {
|
163
|
-
"stream_state": {"id": "villeneuve_denis"},
|
164
|
-
"stream_descriptor": {"name": "directors", "namespace": "public"},
|
165
|
-
},
|
166
|
-
},
|
167
|
-
{
|
168
|
-
"type": "STREAM",
|
169
|
-
"stream": {
|
170
|
-
"stream_state": {"created_at": "1995-12-27"},
|
171
|
-
"stream_descriptor": {"name": "actors", "namespace": "public"},
|
172
|
-
},
|
173
|
-
},
|
174
|
-
],
|
175
|
-
[
|
176
|
-
AirbyteStateMessage(
|
177
|
-
type=AirbyteStateType.STREAM,
|
178
|
-
stream=AirbyteStreamState(
|
179
|
-
stream_descriptor=StreamDescriptor(name="movies", namespace="public"),
|
180
|
-
stream_state=AirbyteStateBlob.parse_obj({"created_at": "2009-07-19"}),
|
181
|
-
),
|
182
|
-
),
|
183
|
-
AirbyteStateMessage(
|
184
|
-
type=AirbyteStateType.STREAM,
|
185
|
-
stream=AirbyteStreamState(
|
186
|
-
stream_descriptor=StreamDescriptor(name="directors", namespace="public"),
|
187
|
-
stream_state=AirbyteStateBlob.parse_obj({"id": "villeneuve_denis"}),
|
188
|
-
),
|
189
|
-
),
|
190
|
-
AirbyteStateMessage(
|
191
|
-
type=AirbyteStateType.STREAM,
|
192
|
-
stream=AirbyteStreamState(
|
193
|
-
stream_descriptor=StreamDescriptor(name="actors", namespace="public"),
|
194
|
-
stream_state=AirbyteStateBlob.parse_obj({"created_at": "1995-12-27"}),
|
195
|
-
),
|
196
|
-
),
|
197
|
-
],
|
198
|
-
does_not_raise(),
|
199
|
-
id="test_incoming_multiple_stream_states",
|
200
|
-
),
|
201
|
-
pytest.param(
|
202
|
-
[
|
203
|
-
{
|
204
|
-
"type": "GLOBAL",
|
205
|
-
"global": {
|
206
|
-
"shared_state": {"shared_key": "shared_val"},
|
207
|
-
"stream_states": [
|
208
|
-
{"stream_state": {"created_at": "2009-07-19"}, "stream_descriptor": {"name": "movies", "namespace": "public"}}
|
209
|
-
],
|
210
|
-
},
|
211
|
-
}
|
212
|
-
],
|
213
|
-
[
|
214
|
-
AirbyteStateMessage.parse_obj(
|
215
|
-
{
|
216
|
-
"type": AirbyteStateType.GLOBAL,
|
217
|
-
"global": AirbyteGlobalState(
|
218
|
-
shared_state=AirbyteStateBlob.parse_obj({"shared_key": "shared_val"}),
|
219
|
-
stream_states=[
|
220
|
-
AirbyteStreamState(
|
221
|
-
stream_descriptor=StreamDescriptor(name="movies", namespace="public"),
|
222
|
-
stream_state=AirbyteStateBlob.parse_obj({"created_at": "2009-07-19"}),
|
223
|
-
)
|
224
|
-
],
|
225
|
-
),
|
226
|
-
}
|
227
|
-
),
|
228
|
-
],
|
229
|
-
does_not_raise(),
|
230
|
-
id="test_incoming_global_state",
|
231
|
-
),
|
232
|
-
pytest.param(
|
233
|
-
{"movies": {"created_at": "2009-07-19"}, "directors": {"id": "villeneuve_denis"}},
|
234
|
-
{"movies": {"created_at": "2009-07-19"}, "directors": {"id": "villeneuve_denis"}},
|
235
|
-
does_not_raise(),
|
236
|
-
id="test_incoming_legacy_state",
|
237
|
-
),
|
238
|
-
pytest.param([], defaultdict(dict, {}), does_not_raise(), id="test_empty_incoming_stream_state"),
|
239
|
-
pytest.param(None, defaultdict(dict, {}), does_not_raise(), id="test_none_incoming_state"),
|
240
|
-
pytest.param({}, defaultdict(dict, {}), does_not_raise(), id="test_empty_incoming_legacy_state"),
|
241
|
-
pytest.param(
|
242
|
-
[
|
243
|
-
{
|
244
|
-
"type": "NOT_REAL",
|
245
|
-
"stream": {
|
246
|
-
"stream_state": {"created_at": "2009-07-19"},
|
247
|
-
"stream_descriptor": {"name": "movies", "namespace": "public"},
|
248
|
-
},
|
249
|
-
}
|
250
|
-
],
|
251
|
-
None,
|
252
|
-
pytest.raises(ValidationError),
|
253
|
-
id="test_invalid_stream_state_invalid_type",
|
254
|
-
),
|
255
|
-
pytest.param(
|
256
|
-
[{"type": "STREAM", "stream": {"stream_state": {"created_at": "2009-07-19"}}}],
|
257
|
-
None,
|
258
|
-
pytest.raises(ValidationError),
|
259
|
-
id="test_invalid_stream_state_missing_descriptor",
|
260
|
-
),
|
261
|
-
pytest.param(
|
262
|
-
[{"type": "GLOBAL", "global": {"shared_state": {"shared_key": "shared_val"}}}],
|
263
|
-
None,
|
264
|
-
pytest.raises(ValidationError),
|
265
|
-
id="test_invalid_global_state_missing_streams",
|
266
|
-
),
|
267
|
-
pytest.param(
|
268
|
-
[
|
269
|
-
{
|
270
|
-
"type": "GLOBAL",
|
271
|
-
"global": {
|
272
|
-
"shared_state": {"shared_key": "shared_val"},
|
273
|
-
"stream_states": {
|
274
|
-
"stream_state": {"created_at": "2009-07-19"},
|
275
|
-
"stream_descriptor": {"name": "movies", "namespace": "public"},
|
276
|
-
},
|
277
|
-
},
|
278
|
-
}
|
279
|
-
],
|
280
|
-
None,
|
281
|
-
pytest.raises(ValidationError),
|
282
|
-
id="test_invalid_global_state_streams_not_list",
|
283
|
-
),
|
284
|
-
pytest.param(
|
285
|
-
[{"type": "LEGACY", "not": "something"}],
|
286
|
-
None,
|
287
|
-
pytest.raises(ValueError),
|
288
|
-
id="test_invalid_state_message_has_no_stream_global_or_data",
|
289
|
-
),
|
290
|
-
],
|
291
|
-
)
|
292
|
-
def test_read_state(source, incoming_state, expected_state, expected_error):
|
293
|
-
with tempfile.NamedTemporaryFile("w") as state_file:
|
294
|
-
state_file.write(json.dumps(incoming_state))
|
295
|
-
state_file.flush()
|
296
|
-
with expected_error:
|
297
|
-
actual = source.read_state(state_file.name)
|
298
|
-
assert actual == expected_state
|
299
|
-
|
300
|
-
|
301
|
-
def test_read_invalid_state(source):
|
302
|
-
with tempfile.NamedTemporaryFile("w") as state_file:
|
303
|
-
state_file.write("invalid json content")
|
304
|
-
state_file.flush()
|
305
|
-
with pytest.raises(ValueError, match="Could not read json file"):
|
306
|
-
source.read_state(state_file.name)
|
307
|
-
|
308
|
-
|
309
|
-
def test_read_state_sends_new_legacy_format_if_source_does_not_implement_read():
|
310
|
-
expected_state = [
|
311
|
-
AirbyteStateMessage(
|
312
|
-
type=AirbyteStateType.LEGACY, data={"movies": {"created_at": "2009-07-19"}, "directors": {"id": "villeneuve_denis"}}
|
313
|
-
)
|
314
|
-
]
|
315
|
-
source = MockAbstractSource()
|
316
|
-
with tempfile.NamedTemporaryFile("w") as state_file:
|
317
|
-
state_file.write(json.dumps({"movies": {"created_at": "2009-07-19"}, "directors": {"id": "villeneuve_denis"}}))
|
318
|
-
state_file.flush()
|
319
|
-
actual = source.read_state(state_file.name)
|
320
|
-
assert actual == expected_state
|
321
|
-
|
322
|
-
|
323
|
-
@pytest.mark.parametrize(
|
324
|
-
"source, expected_state",
|
325
|
-
[
|
326
|
-
pytest.param(MockSource(), {}, id="test_source_implementing_read_returns_legacy_format"),
|
327
|
-
pytest.param(MockAbstractSource(), [], id="test_source_not_implementing_read_returns_per_stream_format"),
|
328
|
-
],
|
329
|
-
)
|
330
|
-
def test_read_state_nonexistent(source, expected_state):
|
331
|
-
assert source.read_state("") == expected_state
|
332
|
-
|
333
|
-
|
334
|
-
def test_read_catalog(source):
|
335
|
-
configured_catalog = {
|
336
|
-
"streams": [
|
337
|
-
{
|
338
|
-
"stream": {
|
339
|
-
"name": "mystream",
|
340
|
-
"json_schema": {"type": "object", "properties": {"k": "v"}},
|
341
|
-
"supported_sync_modes": ["full_refresh"],
|
342
|
-
},
|
343
|
-
"destination_sync_mode": "overwrite",
|
344
|
-
"sync_mode": "full_refresh",
|
345
|
-
}
|
346
|
-
]
|
347
|
-
}
|
348
|
-
expected = ConfiguredAirbyteCatalog.parse_obj(configured_catalog)
|
349
|
-
with tempfile.NamedTemporaryFile("w") as catalog_file:
|
350
|
-
catalog_file.write(expected.json(exclude_unset=True))
|
351
|
-
catalog_file.flush()
|
352
|
-
actual = source.read_catalog(catalog_file.name)
|
353
|
-
assert actual == expected
|
354
|
-
|
355
|
-
|
356
|
-
def test_internal_config(abstract_source, catalog):
|
357
|
-
streams = abstract_source.streams(None)
|
358
|
-
assert len(streams) == 2
|
359
|
-
http_stream, non_http_stream = streams
|
360
|
-
assert isinstance(http_stream, HttpStream)
|
361
|
-
assert not isinstance(non_http_stream, HttpStream)
|
362
|
-
http_stream.read_records.return_value = [{}] * 3
|
363
|
-
non_http_stream.read_records.return_value = [{}] * 3
|
364
|
-
|
365
|
-
# Test with empty config
|
366
|
-
logger = logging.getLogger(f"airbyte.{getattr(abstract_source, 'name', '')}")
|
367
|
-
records = [r for r in abstract_source.read(logger=logger, config={}, catalog=catalog, state={})]
|
368
|
-
# 3 for http stream, 3 for non http stream, 1 for state message for each stream (2x) and 3 for stream status messages for each stream (2x)
|
369
|
-
assert len(records) == 3 + 3 + 1 + 1 + 3 + 3
|
370
|
-
assert http_stream.read_records.called
|
371
|
-
assert non_http_stream.read_records.called
|
372
|
-
# Make sure page_size havent been set
|
373
|
-
assert not http_stream.page_size
|
374
|
-
assert not non_http_stream.page_size
|
375
|
-
# Test with records limit set to 1
|
376
|
-
internal_config = {"some_config": 100, "_limit": 1}
|
377
|
-
records = [r for r in abstract_source.read(logger=logger, config=internal_config, catalog=catalog, state={})]
|
378
|
-
# 1 from http stream + 1 from non http stream, 1 for state message for each stream (2x) and 3 for stream status messages for each stream (2x)
|
379
|
-
assert len(records) == 1 + 1 + 1 + 1 + 3 + 3
|
380
|
-
assert "_limit" not in abstract_source.streams_config
|
381
|
-
assert "some_config" in abstract_source.streams_config
|
382
|
-
# Test with records limit set to number that exceeds expceted records
|
383
|
-
internal_config = {"some_config": 100, "_limit": 20}
|
384
|
-
records = [r for r in abstract_source.read(logger=logger, config=internal_config, catalog=catalog, state={})]
|
385
|
-
assert len(records) == 3 + 3 + 1 + 1 + 3 + 3
|
386
|
-
|
387
|
-
# Check if page_size paramter is set to http instance only
|
388
|
-
internal_config = {"some_config": 100, "_page_size": 2}
|
389
|
-
records = [r for r in abstract_source.read(logger=logger, config=internal_config, catalog=catalog, state={})]
|
390
|
-
assert "_page_size" not in abstract_source.streams_config
|
391
|
-
assert "some_config" in abstract_source.streams_config
|
392
|
-
assert len(records) == 3 + 3 + 1 + 1 + 3 + 3
|
393
|
-
assert http_stream.page_size == 2
|
394
|
-
# Make sure page_size havent been set for non http streams
|
395
|
-
assert not non_http_stream.page_size
|
396
|
-
|
397
|
-
|
398
|
-
def test_internal_config_limit(mocker, abstract_source, catalog):
|
399
|
-
logger_mock = mocker.MagicMock()
|
400
|
-
logger_mock.level = logging.DEBUG
|
401
|
-
del catalog.streams[1]
|
402
|
-
STREAM_LIMIT = 2
|
403
|
-
SLICE_DEBUG_LOG_COUNT = 1
|
404
|
-
FULL_RECORDS_NUMBER = 3
|
405
|
-
TRACE_STATUS_COUNT = 3
|
406
|
-
STATE_COUNT = 1
|
407
|
-
streams = abstract_source.streams(None)
|
408
|
-
http_stream = streams[0]
|
409
|
-
http_stream.read_records.return_value = [{}] * FULL_RECORDS_NUMBER
|
410
|
-
internal_config = {"some_config": 100, "_limit": STREAM_LIMIT}
|
411
|
-
|
412
|
-
catalog.streams[0].sync_mode = SyncMode.full_refresh
|
413
|
-
records = [r for r in abstract_source.read(logger=logger_mock, config=internal_config, catalog=catalog, state={})]
|
414
|
-
assert len(records) == STREAM_LIMIT + SLICE_DEBUG_LOG_COUNT + TRACE_STATUS_COUNT + STATE_COUNT
|
415
|
-
logger_info_args = [call[0][0] for call in logger_mock.info.call_args_list]
|
416
|
-
# Check if log line matches number of limit
|
417
|
-
read_log_record = [_l for _l in logger_info_args if _l.startswith("Read")]
|
418
|
-
assert read_log_record[0].startswith(f"Read {STREAM_LIMIT} ")
|
419
|
-
|
420
|
-
# No limit, check if state record produced for incremental stream
|
421
|
-
catalog.streams[0].sync_mode = SyncMode.incremental
|
422
|
-
records = [r for r in abstract_source.read(logger=logger_mock, config={}, catalog=catalog, state={})]
|
423
|
-
assert len(records) == FULL_RECORDS_NUMBER + SLICE_DEBUG_LOG_COUNT + TRACE_STATUS_COUNT + 1
|
424
|
-
assert records[-2].type == Type.STATE
|
425
|
-
assert records[-1].type == Type.TRACE
|
426
|
-
|
427
|
-
# Set limit and check if state is produced when limit is set for incremental stream
|
428
|
-
logger_mock.reset_mock()
|
429
|
-
records = [r for r in abstract_source.read(logger=logger_mock, config=internal_config, catalog=catalog, state={})]
|
430
|
-
assert len(records) == STREAM_LIMIT + SLICE_DEBUG_LOG_COUNT + TRACE_STATUS_COUNT + 1
|
431
|
-
assert records[-2].type == Type.STATE
|
432
|
-
assert records[-1].type == Type.TRACE
|
433
|
-
logger_info_args = [call[0][0] for call in logger_mock.info.call_args_list]
|
434
|
-
read_log_record = [_l for _l in logger_info_args if _l.startswith("Read")]
|
435
|
-
assert read_log_record[0].startswith(f"Read {STREAM_LIMIT} ")
|
436
|
-
|
437
|
-
|
438
|
-
SCHEMA = {"type": "object", "properties": {"value": {"type": "string"}}}
|
439
|
-
|
440
|
-
|
441
|
-
def test_source_config_no_transform(mocker, abstract_source, catalog):
|
442
|
-
SLICE_DEBUG_LOG_COUNT = 1
|
443
|
-
TRACE_STATUS_COUNT = 3
|
444
|
-
STATE_COUNT = 1
|
445
|
-
logger_mock = mocker.MagicMock()
|
446
|
-
logger_mock.level = logging.DEBUG
|
447
|
-
streams = abstract_source.streams(None)
|
448
|
-
http_stream, non_http_stream = streams
|
449
|
-
http_stream.get_json_schema.return_value = non_http_stream.get_json_schema.return_value = SCHEMA
|
450
|
-
http_stream.read_records.return_value, non_http_stream.read_records.return_value = [[{"value": 23}] * 5] * 2
|
451
|
-
records = [r for r in abstract_source.read(logger=logger_mock, config={}, catalog=catalog, state={})]
|
452
|
-
assert len(records) == 2 * (5 + SLICE_DEBUG_LOG_COUNT + TRACE_STATUS_COUNT + STATE_COUNT)
|
453
|
-
assert [r.record.data for r in records if r.type == Type.RECORD] == [{"value": 23}] * 2 * 5
|
454
|
-
assert http_stream.get_json_schema.call_count == 5
|
455
|
-
assert non_http_stream.get_json_schema.call_count == 5
|
456
|
-
|
457
|
-
|
458
|
-
def test_source_config_transform(mocker, abstract_source, catalog):
|
459
|
-
logger_mock = mocker.MagicMock()
|
460
|
-
logger_mock.level = logging.DEBUG
|
461
|
-
SLICE_DEBUG_LOG_COUNT = 2
|
462
|
-
TRACE_STATUS_COUNT = 6
|
463
|
-
STATE_COUNT = 2
|
464
|
-
streams = abstract_source.streams(None)
|
465
|
-
http_stream, non_http_stream = streams
|
466
|
-
http_stream.transformer = TypeTransformer(TransformConfig.DefaultSchemaNormalization)
|
467
|
-
non_http_stream.transformer = TypeTransformer(TransformConfig.DefaultSchemaNormalization)
|
468
|
-
http_stream.get_json_schema.return_value = non_http_stream.get_json_schema.return_value = SCHEMA
|
469
|
-
http_stream.read_records.return_value, non_http_stream.read_records.return_value = [{"value": 23}], [{"value": 23}]
|
470
|
-
records = [r for r in abstract_source.read(logger=logger_mock, config={}, catalog=catalog, state={})]
|
471
|
-
assert len(records) == 2 + SLICE_DEBUG_LOG_COUNT + TRACE_STATUS_COUNT + STATE_COUNT
|
472
|
-
assert [r.record.data for r in records if r.type == Type.RECORD] == [{"value": "23"}] * 2
|
473
|
-
|
474
|
-
|
475
|
-
def test_source_config_transform_and_no_transform(mocker, abstract_source, catalog):
|
476
|
-
logger_mock = mocker.MagicMock()
|
477
|
-
logger_mock.level = logging.DEBUG
|
478
|
-
SLICE_DEBUG_LOG_COUNT = 2
|
479
|
-
TRACE_STATUS_COUNT = 6
|
480
|
-
STATE_COUNT = 2
|
481
|
-
streams = abstract_source.streams(None)
|
482
|
-
http_stream, non_http_stream = streams
|
483
|
-
http_stream.transformer = TypeTransformer(TransformConfig.DefaultSchemaNormalization)
|
484
|
-
http_stream.get_json_schema.return_value = non_http_stream.get_json_schema.return_value = SCHEMA
|
485
|
-
http_stream.read_records.return_value, non_http_stream.read_records.return_value = [{"value": 23}], [{"value": 23}]
|
486
|
-
records = [r for r in abstract_source.read(logger=logger_mock, config={}, catalog=catalog, state={})]
|
487
|
-
assert len(records) == 2 + SLICE_DEBUG_LOG_COUNT + TRACE_STATUS_COUNT + STATE_COUNT
|
488
|
-
assert [r.record.data for r in records if r.type == Type.RECORD] == [{"value": "23"}, {"value": 23}]
|
489
|
-
|
490
|
-
|
491
|
-
def test_read_default_http_availability_strategy_stream_available(catalog, mocker):
|
492
|
-
mocker.patch.multiple(HttpStream, __abstractmethods__=set())
|
493
|
-
mocker.patch.multiple(Stream, __abstractmethods__=set())
|
494
|
-
|
495
|
-
class MockHttpStream(mocker.MagicMock, HttpStream):
|
496
|
-
url_base = "http://example.com"
|
497
|
-
path = "/dummy/path"
|
498
|
-
get_json_schema = mocker.MagicMock()
|
499
|
-
|
500
|
-
def supports_incremental(self):
|
501
|
-
return True
|
502
|
-
|
503
|
-
def __init__(self, *args, **kvargs):
|
504
|
-
mocker.MagicMock.__init__(self)
|
505
|
-
HttpStream.__init__(self, *args, kvargs)
|
506
|
-
self.read_records = mocker.MagicMock()
|
507
|
-
|
508
|
-
class MockStream(mocker.MagicMock, Stream):
|
509
|
-
page_size = None
|
510
|
-
get_json_schema = mocker.MagicMock()
|
511
|
-
|
512
|
-
def __init__(self, *args, **kvargs):
|
513
|
-
mocker.MagicMock.__init__(self)
|
514
|
-
self.read_records = mocker.MagicMock()
|
515
|
-
|
516
|
-
streams = [MockHttpStream(), MockStream()]
|
517
|
-
http_stream, non_http_stream = streams
|
518
|
-
assert isinstance(http_stream, HttpStream)
|
519
|
-
assert not isinstance(non_http_stream, HttpStream)
|
520
|
-
|
521
|
-
assert isinstance(http_stream.availability_strategy, HttpAvailabilityStrategy)
|
522
|
-
assert non_http_stream.availability_strategy is None
|
523
|
-
|
524
|
-
# Add an extra record for the default HttpAvailabilityStrategy to pull from
|
525
|
-
# during the try: next(records) check, since we are mocking the return value
|
526
|
-
# and not re-creating the generator like we would during actual reading
|
527
|
-
http_stream.read_records.return_value = iter([{"value": "test"}] + [{}] * 3)
|
528
|
-
non_http_stream.read_records.return_value = iter([{}] * 3)
|
529
|
-
|
530
|
-
source = MockAbstractSource(streams=streams)
|
531
|
-
logger = logging.getLogger(f"airbyte.{getattr(abstract_source, 'name', '')}")
|
532
|
-
records = [r for r in source.read(logger=logger, config={}, catalog=catalog, state={})]
|
533
|
-
# 3 for http stream, 3 for non http stream, 1 for state message for each stream (2x) and 3 for stream status messages for each stream (2x)
|
534
|
-
assert len(records) == 3 + 3 + 1 + 1 + 3 + 3
|
535
|
-
assert http_stream.read_records.called
|
536
|
-
assert non_http_stream.read_records.called
|
537
|
-
|
538
|
-
|
539
|
-
def test_read_default_http_availability_strategy_stream_unavailable(catalog, mocker, caplog):
|
540
|
-
mocker.patch.multiple(Stream, __abstractmethods__=set())
|
541
|
-
|
542
|
-
class MockHttpStream(HttpStream):
|
543
|
-
url_base = "https://test_base_url.com"
|
544
|
-
primary_key = ""
|
545
|
-
|
546
|
-
def __init__(self, **kwargs):
|
547
|
-
super().__init__(**kwargs)
|
548
|
-
self.resp_counter = 1
|
549
|
-
|
550
|
-
def next_page_token(self, response: requests.Response) -> Optional[Mapping[str, Any]]:
|
551
|
-
return None
|
552
|
-
|
553
|
-
def path(self, **kwargs) -> str:
|
554
|
-
return ""
|
555
|
-
|
556
|
-
def parse_response(self, response: requests.Response, **kwargs) -> Iterable[Mapping]:
|
557
|
-
stub_response = {"data": self.resp_counter}
|
558
|
-
self.resp_counter += 1
|
559
|
-
yield stub_response
|
560
|
-
|
561
|
-
class MockStream(mocker.MagicMock, Stream):
|
562
|
-
page_size = None
|
563
|
-
get_json_schema = mocker.MagicMock()
|
564
|
-
|
565
|
-
def __init__(self, *args, **kvargs):
|
566
|
-
mocker.MagicMock.__init__(self)
|
567
|
-
self.read_records = mocker.MagicMock()
|
568
|
-
|
569
|
-
streams = [MockHttpStream(), MockStream()]
|
570
|
-
http_stream, non_http_stream = streams
|
571
|
-
assert isinstance(http_stream, HttpStream)
|
572
|
-
assert not isinstance(non_http_stream, HttpStream)
|
573
|
-
|
574
|
-
assert isinstance(http_stream.availability_strategy, HttpAvailabilityStrategy)
|
575
|
-
assert non_http_stream.availability_strategy is None
|
576
|
-
|
577
|
-
# Don't set anything for read_records return value for HttpStream, since
|
578
|
-
# it should be skipped due to the stream being unavailable
|
579
|
-
non_http_stream.read_records.return_value = iter([{}] * 3)
|
580
|
-
|
581
|
-
# Patch HTTP request to stream endpoint to make it unavailable
|
582
|
-
req = requests.Response()
|
583
|
-
req.status_code = 403
|
584
|
-
mocker.patch.object(requests.Session, "send", return_value=req)
|
585
|
-
|
586
|
-
source = MockAbstractSource(streams=streams)
|
587
|
-
logger = logging.getLogger("test_read_default_http_availability_strategy_stream_unavailable")
|
588
|
-
with caplog.at_level(logging.WARNING):
|
589
|
-
records = [r for r in source.read(logger=logger, config={}, catalog=catalog, state={})]
|
590
|
-
|
591
|
-
# 0 for http stream, 3 for non http stream, 1 for non http stream state message and 3 status trace messages
|
592
|
-
assert len(records) == 0 + 3 + 1 + 3
|
593
|
-
assert non_http_stream.read_records.called
|
594
|
-
expected_logs = [
|
595
|
-
f"Skipped syncing stream '{http_stream.name}' because it was unavailable.",
|
596
|
-
f"Unable to read {http_stream.name} stream.",
|
597
|
-
"This is most likely due to insufficient permissions on the credentials in use.",
|
598
|
-
f"Please visit https://docs.airbyte.com/integrations/sources/{source.name} to learn more.",
|
599
|
-
]
|
600
|
-
for message in expected_logs:
|
601
|
-
assert message in caplog.text
|
602
|
-
|
603
|
-
|
604
|
-
def test_read_default_http_availability_strategy_parent_stream_unavailable(catalog, mocker, caplog):
|
605
|
-
"""Test default availability strategy if error happens during slice extraction (reading of parent stream)"""
|
606
|
-
mocker.patch.multiple(Stream, __abstractmethods__=set())
|
607
|
-
|
608
|
-
class MockHttpParentStream(HttpStream):
|
609
|
-
url_base = "https://test_base_url.com"
|
610
|
-
primary_key = ""
|
611
|
-
|
612
|
-
def __init__(self, **kwargs):
|
613
|
-
super().__init__(**kwargs)
|
614
|
-
self.resp_counter = 1
|
615
|
-
|
616
|
-
def next_page_token(self, response: requests.Response) -> Optional[Mapping[str, Any]]:
|
617
|
-
return None
|
618
|
-
|
619
|
-
def path(self, **kwargs) -> str:
|
620
|
-
return ""
|
621
|
-
|
622
|
-
def parse_response(self, response: requests.Response, **kwargs) -> Iterable[Mapping]:
|
623
|
-
stub_response = {"data": self.resp_counter}
|
624
|
-
self.resp_counter += 1
|
625
|
-
yield stub_response
|
626
|
-
|
627
|
-
class MockHttpStream(HttpSubStream):
|
628
|
-
url_base = "https://test_base_url.com"
|
629
|
-
primary_key = ""
|
630
|
-
|
631
|
-
def __init__(self, **kwargs):
|
632
|
-
super().__init__(**kwargs)
|
633
|
-
self.resp_counter = 1
|
634
|
-
|
635
|
-
def next_page_token(self, response: requests.Response) -> Optional[Mapping[str, Any]]:
|
636
|
-
return None
|
637
|
-
|
638
|
-
def path(self, **kwargs) -> str:
|
639
|
-
return ""
|
640
|
-
|
641
|
-
def parse_response(self, response: requests.Response, **kwargs) -> Iterable[Mapping]:
|
642
|
-
stub_response = {"data": self.resp_counter}
|
643
|
-
self.resp_counter += 1
|
644
|
-
yield stub_response
|
645
|
-
|
646
|
-
http_stream = MockHttpStream(parent=MockHttpParentStream())
|
647
|
-
streams = [http_stream]
|
648
|
-
assert isinstance(http_stream, HttpSubStream)
|
649
|
-
assert isinstance(http_stream.availability_strategy, HttpAvailabilityStrategy)
|
650
|
-
|
651
|
-
# Patch HTTP request to stream endpoint to make it unavailable
|
652
|
-
req = requests.Response()
|
653
|
-
req.status_code = 403
|
654
|
-
mocker.patch.object(requests.Session, "send", return_value=req)
|
655
|
-
|
656
|
-
source = MockAbstractSource(streams=streams)
|
657
|
-
logger = logging.getLogger("test_read_default_http_availability_strategy_parent_stream_unavailable")
|
658
|
-
configured_catalog = {
|
659
|
-
"streams": [
|
660
|
-
{
|
661
|
-
"stream": {
|
662
|
-
"name": "mock_http_stream",
|
663
|
-
"json_schema": {"type": "object", "properties": {"k": "v"}},
|
664
|
-
"supported_sync_modes": ["full_refresh"],
|
665
|
-
},
|
666
|
-
"destination_sync_mode": "overwrite",
|
667
|
-
"sync_mode": "full_refresh",
|
668
|
-
}
|
669
|
-
]
|
670
|
-
}
|
671
|
-
catalog = ConfiguredAirbyteCatalog.parse_obj(configured_catalog)
|
672
|
-
with caplog.at_level(logging.WARNING):
|
673
|
-
records = [r for r in source.read(logger=logger, config={}, catalog=catalog, state={})]
|
674
|
-
|
675
|
-
# 0 for http stream, 3 for non http stream and 3 status trace messages
|
676
|
-
assert len(records) == 0
|
677
|
-
expected_logs = [
|
678
|
-
f"Skipped syncing stream '{http_stream.name}' because it was unavailable.",
|
679
|
-
f"Unable to get slices for {http_stream.name} stream, because of error in parent stream",
|
680
|
-
"This is most likely due to insufficient permissions on the credentials in use.",
|
681
|
-
f"Please visit https://docs.airbyte.com/integrations/sources/{source.name} to learn more.",
|
682
|
-
]
|
683
|
-
for message in expected_logs:
|
684
|
-
assert message in caplog.text
|