airbyte-source-github 1.8.1__py3-none-any.whl → 1.8.2__py3-none-any.whl

{airbyte_source_github-1.8.1.dist-info → airbyte_source_github-1.8.2.dist-info}/METADATA

@@ -1,18 +1,17 @@
 Metadata-Version: 2.1
 Name: airbyte-source-github
-Version: 1.8.1
+Version: 1.8.2
 Summary: Source implementation for GitHub.
 Home-page: https://airbyte.com
 License: MIT
 Author: Airbyte
 Author-email: contact@airbyte.io
-Requires-Python: >=3.9,<3.12
+Requires-Python: >=3.10,<3.12
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
-Requires-Dist: airbyte-cdk (>=3,<4)
+Requires-Dist: airbyte-cdk (>=4,<5)
 Requires-Dist: sgqlc (==16.3)
 Project-URL: Documentation, https://docs.airbyte.com/integrations/sources/github
 Project-URL: Repository, https://github.com/airbytehq/airbyte

{airbyte_source_github-1.8.1.dist-info → airbyte_source_github-1.8.2.dist-info}/RECORD

@@ -2,7 +2,7 @@ source_github/__init__.py,sha256=punPc3v0mXEYOun7cbkfM5KUhgjv72B9DgDhI4VtzcQ,113
 source_github/backoff_strategies.py,sha256=Vo4sAhlm4A134gxCu7l9ELpnUvMP6nviIgQlHBwDJNY,2286
 source_github/config_migrations.py,sha256=Dq-x0yoQNLpcO6ZwRJDfd3Mhuk4SSQDjEVfhOpto_Xc,3849
 source_github/constants.py,sha256=Hj3Q4y7OoU-Iff4m9gEC2CjwmWJYXhNbHVNjg8EBLmQ,238
-source_github/errors_handlers.py,sha256=eFRm7y9DNSiXbMXjyIPVoh0uuEK7JwMMzcP5AHt773w,5870
+source_github/errors_handlers.py,sha256=vxbaaPfnDjky483hEuf0jkuco9hufj_jSiYqeBAgIt8,6320
 source_github/github_schema.py,sha256=JHFeNATAjLjB2RvdPJks1JMrCotipLBAOnpikp30oUI,1600314
 source_github/graphql.py,sha256=csp3C9Mgf5MIzShbRlb1DWffZ1qRnZzmXwmfHpfUP5U,11625
 source_github/run.py,sha256=onA-rP2aVhWHvDquKZdR1381CU66rnzqJ7EFMS5dd4Q,407
@@ -56,9 +56,9 @@ source_github/schemas/workflow_runs.json,sha256=XDmIsjtzka-ItEonImD3ZATZjxRNkbFo
 source_github/schemas/workflows.json,sha256=gSNw8WZaVKbX4AL97PbjZHzvxcOltXqv9Ao1RNQOFXM,1470
 source_github/source.py,sha256=tRD2GOEIJ063wFvOxn5T1hqzrYYUsA83I-sZnnM6SOc,14247
 source_github/spec.json,sha256=7LOQm01fP_RvPF-HifhNPJ7i0AxT2LTNPaLAA3uOfNY,7443
-source_github/streams.py,sha256=UX7m_PuiM0oJn55zKq60p66iR5O-nck-eme5N0HB6Vc,75476
+source_github/streams.py,sha256=UdO9tE8T-sqoIuov6PIGmQwu-Uax8IJnhchca_RaZ7M,76296
 source_github/utils.py,sha256=DfAHFjsF8hzDXeSCR6qtfs7W_av6o2BkkEVhtHpWbis,5462
-airbyte_source_github-1.8.1.dist-info/METADATA,sha256=mDbaLaXdCRVp0-MnvkhBHlGZNheZBD8cJki6kQiUS64,5238
-airbyte_source_github-1.8.1.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-airbyte_source_github-1.8.1.dist-info/entry_points.txt,sha256=gYhqVrTAZvMwuYByg0b_-o115yUFLLcfNxMrLZmiW9k,55
-airbyte_source_github-1.8.1.dist-info/RECORD,,
+airbyte_source_github-1.8.2.dist-info/METADATA,sha256=uOQm-MrDeU_bHEe51yPhD0S629EwsebTRRnba-sicKs,5189
+airbyte_source_github-1.8.2.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+airbyte_source_github-1.8.2.dist-info/entry_points.txt,sha256=gYhqVrTAZvMwuYByg0b_-o115yUFLLcfNxMrLZmiW9k,55
+airbyte_source_github-1.8.2.dist-info/RECORD,,

source_github/errors_handlers.py

@@ -90,6 +90,15 @@ class GithubStreamABCErrorHandler(HttpStatusErrorHandler):
 
 
 class ContributorActivityErrorHandler(HttpStatusErrorHandler):
+    """
+    This custom error handler is needed for streams based on repository statistics endpoints like ContributorActivity because
+    when requesting data that hasn't been cached yet when the request is made, you'll receive a 202 response. And these requests
+    need to retried to get the actual results.
+
+    See the docs for more info:
+    https://docs.github.com/en/rest/metrics/statistics?apiVersion=2022-11-28#a-word-about-caching
+    """
+
     def interpret_response(self, response_or_exception: Optional[Union[requests.Response, Exception]] = None) -> ErrorResolution:
         if isinstance(response_or_exception, requests.Response) and response_or_exception.status_code == requests.codes.ACCEPTED:
             return ErrorResolution(

source_github/streams.py

@@ -9,10 +9,11 @@ from urllib import parse
 
 import pendulum
 import requests
-from airbyte_cdk import BackoffStrategy
+from airbyte_cdk import BackoffStrategy, StreamSlice
 from airbyte_cdk.models import AirbyteLogMessage, AirbyteMessage, Level, SyncMode
 from airbyte_cdk.models import Type as MessageType
 from airbyte_cdk.sources.streams.availability_strategy import AvailabilityStrategy
+from airbyte_cdk.sources.streams.checkpoint.substream_resumable_full_refresh_cursor import SubstreamResumableFullRefreshCursor
 from airbyte_cdk.sources.streams.core import CheckpointMixin, Stream
 from airbyte_cdk.sources.streams.http import HttpStream
 from airbyte_cdk.sources.streams.http.error_handlers import ErrorHandler, ErrorResolution, HttpStatusErrorHandler, ResponseAction
@@ -57,6 +58,9 @@ class GithubStreamABC(HttpStream, ABC):
         self.api_url = api_url
         self.state = {}
 
+        if not self.supports_incremental:
+            self.cursor = SubstreamResumableFullRefreshCursor()
+
     @property
     def url_base(self) -> str:
         return self.api_url
@@ -1613,7 +1617,8 @@ class ContributorActivity(GithubStream):
         return record
 
     def get_error_handler(self) -> Optional[ErrorHandler]:
-        return ContributorActivityErrorHandler(logger=self.logger, max_retries=self.max_retries, error_mapping=GITHUB_DEFAULT_ERROR_MAPPING)
+
+        return ContributorActivityErrorHandler(logger=self.logger, max_retries=5, error_mapping=GITHUB_DEFAULT_ERROR_MAPPING)
 
     def get_backoff_strategy(self) -> Optional[Union[BackoffStrategy, List[BackoffStrategy]]]:
         return ContributorActivityBackoffStrategy()
@@ -1645,6 +1650,13 @@ class ContributorActivity(GithubStream):
                         message=f"Syncing `{self.__class__.__name__}` " f"stream isn't available for repository `{repository}`.",
                     ),
                 )
+
+                # In order to retain the existing stream behavior before we added RFR to this stream, we need to close out the
+                # partition after we give up the maximum number of retries on the 202 response. This does lead to the question
+                # of if we should prematurely exit in the first place, but for now we're going to aim for feature parity
+                partition_obj = stream_slice.get("partition")
+                if self.cursor and partition_obj:
+                    self.cursor.close_slice(StreamSlice(cursor_slice={}, partition=partition_obj))
             else:
                 raise e