airbyte-cdk 7.0.3__py3-none-any.whl → 7.0.4__py3-none-any.whl

airbyte_cdk/sources/declarative/declarative_component_schema.yaml

@@ -3797,7 +3797,6 @@ definitions:
       - polling_requester
       - download_requester
       - status_extractor
-      - download_target_extractor
     properties:
       type:
         type: string

airbyte_cdk/sources/declarative/models/declarative_component_schema.py

@@ -2852,8 +2852,8 @@ class AsyncRetriever(BaseModel):
     status_extractor: Union[DpathExtractor, CustomRecordExtractor] = Field(
         ..., description="Responsible for fetching the actual status of the async job."
     )
-    download_target_extractor: Union[DpathExtractor, CustomRecordExtractor] = Field(
-        ...,
+    download_target_extractor: Optional[Union[DpathExtractor, CustomRecordExtractor]] = Field(
+        None,
         description="Responsible for fetching the final result `urls` provided by the completed / finished / ready async job.",
     )
     download_extractor: Optional[

airbyte_cdk/sources/declarative/parsers/model_to_component_factory.py

@@ -3467,6 +3467,11 @@ class ModelToComponentFactory:
         transformations: List[RecordTransformation],
         **kwargs: Any,
     ) -> AsyncRetriever:
+        if model.download_target_requester and not model.download_target_extractor:
+            raise ValueError(
+                f"`download_target_extractor` required if using a `download_target_requester`"
+            )
+
         def _get_download_retriever(
             requester: Requester, extractor: RecordExtractor, _decoder: Decoder
         ) -> SimpleRetriever:
@@ -3624,11 +3629,15 @@ class ModelToComponentFactory:
         status_extractor = self._create_component_from_model(
             model=model.status_extractor, decoder=decoder, config=config, name=name
         )
-        download_target_extractor = self._create_component_from_model(
-            model=model.download_target_extractor,
-            decoder=decoder,
-            config=config,
-            name=name,
+        download_target_extractor = (
+            self._create_component_from_model(
+                model=model.download_target_extractor,
+                decoder=decoder,
+                config=config,
+                name=name,
+            )
+            if model.download_target_extractor
+            else None
         )
 
         job_repository: AsyncJobRepository = AsyncHttpJobRepository(

airbyte_cdk/sources/declarative/requesters/README.md

@@ -1,8 +1,19 @@
+# Download Target and Download Requester
+
+- The `creation_response` and `polling_response` interpolation contexts are always available during the job download step of the process.
+
+- The`download_target` interpolation context is generated by the `download_target_extractor` and made available to the job download step as well.
+  - if `download_target_requester` is not provided, `download_target_extractor` will get urls from the `polling_response`
+  - if `download_target_requester` is provided, an additional request will be made to fetch job download targets and `download_target_extractor` will operate on that response
+
+## Some important considerations
+
+- **Note:** If the `download_target_extractor` and `download_target_requester` are not defined, a single job download request will be made without the `download_target` context.
+- **Note:** The `download_target_extractor` is required (not optional) if using a `download_target_requester`
+
 # AsyncHttpJobRepository sequence diagram
 
 - Components marked as optional are not required and can be ignored.
-- if `download_target_requester` is not provided, `download_target_extractor` will get urls from the `polling_response`
-- interpolation_context, e.g. `creation_response` or `polling_response` can be obtained from stream_slice
 
 ```mermaid
 ---
@@ -37,7 +48,7 @@ sequenceDiagram
         UrlRequester -->> AsyncHttpJobRepository: Download URLs
 
         AsyncHttpJobRepository ->> DownloadRetriever: Download reports
-        DownloadRetriever ->> Reporting Server: Retrieve report data (interpolation_context: `url`)
+        DownloadRetriever ->> Reporting Server: Retrieve report data (interpolation_context: `download_target`, `creation_response`, `polling_response`)
         Reporting Server -->> DownloadRetriever: Report data
         DownloadRetriever -->> AsyncHttpJobRepository: Report data
     else Status: Failed

airbyte_cdk/sources/declarative/requesters/http_job_repository.py

@@ -43,7 +43,7 @@ class AsyncHttpJobRepository(AsyncJobRepository):
     delete_requester: Optional[Requester]
     status_extractor: DpathExtractor
     status_mapping: Mapping[str, AsyncJobStatus]
-    download_target_extractor: DpathExtractor
+    download_target_extractor: Optional[DpathExtractor]
 
     # timeout for the job to be completed, passed from `polling_job_timeout`
     job_timeout: Optional[timedelta] = None
@@ -213,14 +213,16 @@ class AsyncHttpJobRepository(AsyncJobRepository):
 
         """
 
-        for target_url in self._get_download_targets(job):
+        for download_target in self._get_download_targets(job):
             job_slice = job.job_parameters()
             stream_slice = StreamSlice(
                 partition=job_slice.partition,
                 cursor_slice=job_slice.cursor_slice,
                 extra_fields={
                     **job_slice.extra_fields,
-                    "download_target": target_url,
+                    "download_target": download_target,
+                    "creation_response": self._get_creation_response_interpolation_context(job),
+                    "polling_response": self._get_polling_response_interpolation_context(job),
                 },
             )
             for message in self.download_retriever.read_records({}, stream_slice):
@@ -330,9 +332,27 @@ class AsyncHttpJobRepository(AsyncJobRepository):
         )
 
     def _get_download_targets(self, job: AsyncJob) -> Iterable[str]:
-        if not self.download_target_requester:
-            url_response = self._polling_job_response_by_id[job.api_job_id()]
-        else:
+        """Returns an iterable of strings to help target requests for downloading async jobs."""
+        # If neither download_target_extractor nor download_target_requester are provided, yield a single empty string
+        # to express the need to make a single download request without any download_target value
+        if not self.download_target_extractor:
+            if not self.download_target_requester:
+                lazy_log(
+                    LOGGER,
+                    logging.DEBUG,
+                    lambda: "No download_target_extractor or download_target_requester provided. Will attempt a single download request without a `download_target`.",
+                )
+                yield ""
+                return
+            else:
+                raise AirbyteTracedException(
+                    internal_message="Must define a `download_target_extractor` when using a `download_target_requester`.",
+                    failure_type=FailureType.config_error,
+                )
+
+        # We have a download_target_extractor, use it to extract the donload_target
+        if self.download_target_requester:
+            # if a download_target_requester if defined, we extract from the response of a request specifically for download targets.
             stream_slice: StreamSlice = StreamSlice(
                 partition={},
                 cursor_slice={},
@@ -346,5 +366,8 @@ class AsyncHttpJobRepository(AsyncJobRepository):
                     internal_message="Always expect a response or an exception from download_target_requester",
                     failure_type=FailureType.system_error,
                 )
+        else:
+            # if no download_target_requester is defined, we extract from the polling response
+            url_response = self._polling_job_response_by_id[job.api_job_id()]
 
         yield from self.download_target_extractor.extract_records(url_response)  # type: ignore # we expect download_target_extractor to always return list of strings

{airbyte_cdk-7.0.3.dist-info → airbyte_cdk-7.0.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: airbyte-cdk
-Version: 7.0.3
+Version: 7.0.4
 Summary: A framework for writing Airbyte Connectors.
 Home-page: https://airbyte.com
 License: MIT

{airbyte_cdk-7.0.3.dist-info → airbyte_cdk-7.0.4.dist-info}/RECORD

@@ -130,7 +130,7 @@ airbyte_cdk/sources/declarative/concurrent_declarative_source.py,sha256=MdXptT-2
 airbyte_cdk/sources/declarative/datetime/__init__.py,sha256=4Hw-PX1-VgESLF16cDdvuYCzGJtHntThLF4qIiULWeo,61
 airbyte_cdk/sources/declarative/datetime/datetime_parser.py,sha256=_zGNGq31RNy_0QBLt_EcTvgPyhj7urPdx6oA3M5-r3o,3150
 airbyte_cdk/sources/declarative/datetime/min_max_datetime.py,sha256=0BHBtDNQZfvwM45-tY5pNlTcKAFSGGNxemoi0Jic-0E,5785
-airbyte_cdk/sources/declarative/declarative_component_schema.yaml,sha256=L-xvZ3tKpBQBYLoh9SwoPyQCoEbr8QywyYITF0kXf7w,187221
+airbyte_cdk/sources/declarative/declarative_component_schema.yaml,sha256=U-cTJz0M00sYP2NSeLB29148suEQO8Z-LTPiixOoHoQ,187187
 airbyte_cdk/sources/declarative/decoders/__init__.py,sha256=JHb_0d3SE6kNY10mxA5YBEKPeSbsWYjByq1gUQxepoE,953
 airbyte_cdk/sources/declarative/decoders/composite_raw_decoder.py,sha256=qB4lRUrCXLTE-a3VlpOLaazHiC7RIF_FIVJesuz7ebw,8078
 airbyte_cdk/sources/declarative/decoders/decoder.py,sha256=1PeKwuMK8x9dsA2zqUjSVinEWVSEgYcUS6npiW3aC2c,855
@@ -165,14 +165,14 @@ airbyte_cdk/sources/declarative/migrations/legacy_to_per_partition_state_migrati
 airbyte_cdk/sources/declarative/migrations/state_migration.py,sha256=KWPjealMLKSMtajXgkdGgKg7EmTLR-CqqD7UIh0-eDU,794
 airbyte_cdk/sources/declarative/models/__init__.py,sha256=nUFxNCiKeYRVXuZEKA7GD-lTHxsiKcQ8FitZjKhPIvE,100
 airbyte_cdk/sources/declarative/models/base_model_with_deprecations.py,sha256=Imnj3yef0aqRdLfaUxkIYISUb8YkiPrRH_wBd-x8HjM,5999
-airbyte_cdk/sources/declarative/models/declarative_component_schema.py,sha256=0ttIVcgsg0ZKyCfKXr1DP3FGcSlOPVbTeJkMI6y_utA,131541
+airbyte_cdk/sources/declarative/models/declarative_component_schema.py,sha256=ePqmIj2g8gPItvflsgKmRBm91qDPGgGyD_GQDUSqjCA,131552
 airbyte_cdk/sources/declarative/parsers/__init__.py,sha256=ZnqYNxHsKCgO38IwB34RQyRMXTs4GTvlRi3ImKnIioo,61
 airbyte_cdk/sources/declarative/parsers/custom_code_compiler.py,sha256=nlVvHC511NUyDEEIRBkoeDTAvLqKNp-hRy8D19z8tdk,5941
 airbyte_cdk/sources/declarative/parsers/custom_exceptions.py,sha256=wnRUP0Xeru9Rbu5OexXSDN9QWDo8YU4tT9M2LDVOgGA,802
 airbyte_cdk/sources/declarative/parsers/manifest_component_transformer.py,sha256=la9Ulpc0lQewiBLKJ0FpsWxyU5XISv-ulmFRHJLJ1Pc,11292
 airbyte_cdk/sources/declarative/parsers/manifest_normalizer.py,sha256=EtKjS9c94yNp3AwQC8KUCQaAYW5T3zvFYxoWYjc_buI,19729
 airbyte_cdk/sources/declarative/parsers/manifest_reference_resolver.py,sha256=pJmg78vqE5VfUrF_KJnWjucQ4k9IWFULeAxHCowrHXE,6806
-airbyte_cdk/sources/declarative/parsers/model_to_component_factory.py,sha256=Zu4E2nvPzGyi_EnmbdrUrQ1myUvPQ5GtcWITzksYMcQ,184235
+airbyte_cdk/sources/declarative/parsers/model_to_component_factory.py,sha256=X8qIjanJCog3GflyEoZ-5ECID-xqcfFQgW3E6AzyFNU,184572
 airbyte_cdk/sources/declarative/partition_routers/__init__.py,sha256=TBC9AkGaUqHm2IKHMPN6punBIcY5tWGULowcLoAVkfw,1109
 airbyte_cdk/sources/declarative/partition_routers/async_job_partition_router.py,sha256=VelO7zKqKtzMJ35jyFeg0ypJLQC0plqqIBNXoBW1G2E,3001
 airbyte_cdk/sources/declarative/partition_routers/cartesian_product_stream_slicer.py,sha256=ocm4hZ4k-tEGs5HLrtI8ecWSK0hGqNH0Rvz2byx_HZk,6927
@@ -181,7 +181,7 @@ airbyte_cdk/sources/declarative/partition_routers/list_partition_router.py,sha25
 airbyte_cdk/sources/declarative/partition_routers/partition_router.py,sha256=v8C1farE9_UVnIN_PV7qnn2p3C_qK6DJ8b0-6JmsAPc,1288
 airbyte_cdk/sources/declarative/partition_routers/single_partition_router.py,sha256=iP6eL6gYhGL8PuH9mXjL_PfqFyJ3xefmuFxf7yzy66s,1778
 airbyte_cdk/sources/declarative/partition_routers/substream_partition_router.py,sha256=xV_xCTwlO2LiOBCrk9hiP1r6N3KatiAa9dRZUv27iWQ,18423
-airbyte_cdk/sources/declarative/requesters/README.md,sha256=DQll2qsIzzTiiP35kJp16ONpr7cFeUQNgPfhl5krB24,2675
+airbyte_cdk/sources/declarative/requesters/README.md,sha256=D-3n-Hlf6IrouihdieY_lOWSZUeMwBFOlGRa_C0nJ3k,3450
 airbyte_cdk/sources/declarative/requesters/__init__.py,sha256=d7a3OoHbqaJDyyPli3nqqJ2yAW_SLX6XDaBAKOwvpxw,364
 airbyte_cdk/sources/declarative/requesters/error_handlers/__init__.py,sha256=SkEDcJxlT1683rNx93K9whoS0OyUukkuOfToGtgpF58,776
 airbyte_cdk/sources/declarative/requesters/error_handlers/backoff_strategies/__init__.py,sha256=1WZdpFmWL6W_Dko0qjflTaKIWeqt8jHT-D6HcujIp3s,884
@@ -196,7 +196,7 @@ airbyte_cdk/sources/declarative/requesters/error_handlers/default_error_handler.
 airbyte_cdk/sources/declarative/requesters/error_handlers/default_http_response_filter.py,sha256=q0YkeYUUWO6iErUy0vjqiOkhg8_9d5YcCmtlpXAJJ9E,1314
 airbyte_cdk/sources/declarative/requesters/error_handlers/error_handler.py,sha256=Tan66odx8VHzfdyyXMQkXz2pJYksllGqvxmpoajgcK4,669
 airbyte_cdk/sources/declarative/requesters/error_handlers/http_response_filter.py,sha256=E-fQbt4ShfxZVoqfnmOx69C6FUPWZz8BIqI3DN9Kcjs,7935
-airbyte_cdk/sources/declarative/requesters/http_job_repository.py,sha256=yU61dCEX9961QMA6lt26c0bOM5MXp_iuxuSljwD_5Jo,14326
+airbyte_cdk/sources/declarative/requesters/http_job_repository.py,sha256=RLaQlvb-kL2FqnhuV3TJlJhSfnBSaDIgUgM81qFsCkY,15847
 airbyte_cdk/sources/declarative/requesters/http_requester.py,sha256=cktdjnOu-o98smdCdrWC361iWNamPTZ-csT32OFh00c,18920
 airbyte_cdk/sources/declarative/requesters/paginators/__init__.py,sha256=uArbKs9JKNCt7t9tZoeWwjDpyI1HoPp29FNW0JzvaEM,644
 airbyte_cdk/sources/declarative/requesters/paginators/default_paginator.py,sha256=kH_gwgULvEr8na-sST93gpr5pgqk8oT2aZNPebyMqlc,12293
@@ -457,9 +457,9 @@ airbyte_cdk/utils/slice_hasher.py,sha256=EDxgROHDbfG-QKQb59m7h_7crN1tRiawdf5uU7G
 airbyte_cdk/utils/spec_schema_transformations.py,sha256=9YDJmnIGFsT51CVQf2tSSvTapGimITjEFGbUTSZAGTI,963
 airbyte_cdk/utils/stream_status_utils.py,sha256=ZmBoiy5HVbUEHAMrUONxZvxnvfV9CesmQJLDTAIWnWw,1171
 airbyte_cdk/utils/traced_exception.py,sha256=C8uIBuCL_E4WnBAOPSxBicD06JAldoN9fGsQDp463OY,6292
-airbyte_cdk-7.0.3.dist-info/LICENSE.txt,sha256=Wfe61S4BaGPj404v8lrAbvhjYR68SHlkzeYrg3_bbuM,1051
-airbyte_cdk-7.0.3.dist-info/LICENSE_SHORT,sha256=aqF6D1NcESmpn-cqsxBtszTEnHKnlsp8L4x9wAh3Nxg,55
-airbyte_cdk-7.0.3.dist-info/METADATA,sha256=H974zlTwTHg5w991ZshrilcgpSUMVvHCTlMcUrMOf6E,6799
-airbyte_cdk-7.0.3.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
-airbyte_cdk-7.0.3.dist-info/entry_points.txt,sha256=eLZ2UYvJZGm1s07Pplcs--1Gim60YhZWTb53j_dghwU,195
-airbyte_cdk-7.0.3.dist-info/RECORD,,
+airbyte_cdk-7.0.4.dist-info/LICENSE.txt,sha256=Wfe61S4BaGPj404v8lrAbvhjYR68SHlkzeYrg3_bbuM,1051
+airbyte_cdk-7.0.4.dist-info/LICENSE_SHORT,sha256=aqF6D1NcESmpn-cqsxBtszTEnHKnlsp8L4x9wAh3Nxg,55
+airbyte_cdk-7.0.4.dist-info/METADATA,sha256=mPycx2yG98V8BkQJp9vwCLHAjACLczgUquxx-jgf7og,6799
+airbyte_cdk-7.0.4.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
+airbyte_cdk-7.0.4.dist-info/entry_points.txt,sha256=eLZ2UYvJZGm1s07Pplcs--1Gim60YhZWTb53j_dghwU,195
+airbyte_cdk-7.0.4.dist-info/RECORD,,