Fix: Misc cleanup (#317)

Author: aaronsteers

airbyte/__init__.py

@@ -1,8 +1,5 @@
 # Copyright (c) 2024 Airbyte, Inc., all rights reserved.
-"""PyAirbyte brings Airbyte ELT to every Python developer.
-
-PyAirbyte brings the power of Airbyte to every Python developer. PyAirbyte provides a set of
-utilities to use Airbyte connectors in Python.
+"""***PyAirbyte brings the power of Airbyte to every Python developer.***
 
 [![PyPI version](https://badge.fury.io/py/airbyte.svg)](https://badge.fury.io/py/airbyte)
 [![PyPI - Downloads](https://img.shields.io/pypi/dm/airbyte)](https://pypi.org/project/airbyte/)
@@ -121,7 +118,7 @@
 
 ----------------------
 
-"""
+"""  # noqa: D415
 
 from __future__ import annotations
 

airbyte/_connector_base.py

@@ -230,7 +230,6 @@ def _yaml_spec(self) -> str:
     @property
     def docs_url(self) -> str:
         """Get the URL to the connector's documentation."""
-        # TODO: Replace with docs URL from metadata when available
         return (
             f"https://docs.airbyte.com/integrations/{self.connector_type}s/"
             + self.name.lower().replace(f"{self.connector_type}-", "")

airbyte/_executors/declarative.py

@@ -40,7 +40,7 @@ class DeclarativeExecutor(Executor):
 
     def __init__(
         self,
-        manifest: str | dict | Path,
+        manifest: dict | Path,
     ) -> None:
         """Initialize a declarative executor.
 
@@ -53,18 +53,17 @@ def __init__(
         if isinstance(manifest, Path):
             self._manifest_dict = cast(dict, json.loads(manifest.read_text()))
 
-        elif isinstance(manifest, str):
-            # TODO: Implement HTTP path parsing
-            raise NotImplementedError("HTTP path parsing is not yet implemented.")
-
         elif isinstance(manifest, dict):
             self._manifest_dict = manifest
 
         if not isinstance(self._manifest_dict, dict):
             raise PyAirbyteInternalError(message="Manifest must be a dict.")
 
         self.declarative_source = ManifestDeclarativeSource(source_config=self._manifest_dict)
-        self.reported_version: str | None = None  # TODO: Consider adding version detection
+
+        # TODO: Consider adding version detection
+        # https://github.com/airbytehq/airbyte/issues/318
+        self.reported_version: str | None = None
 
     @property
     def _cli(self) -> list[str]:

airbyte/_executors/local.py

@@ -41,9 +41,6 @@ def ensure_installation(
         try:
             self.execute(["spec"])
         except Exception as e:
-            # TODO: Improve error handling. We should try to distinguish between
-            #       a connector that is not installed and a connector that is not
-            #       working properly.
             raise exc.AirbyteConnectorExecutableNotFoundError(
                 connector_name=self.name,
             ) from e

airbyte/_executors/python.py

@@ -98,7 +98,6 @@ def uninstall(self) -> None:
     @property
     def docs_url(self) -> str:
         """Get the URL to the connector's documentation."""
-        # TODO: Refactor installation so that this can just live in the Source class.
         return "https://docs.airbyte.com/integrations/sources/" + self.name.lower().replace(
             "source-", ""
         )

airbyte/_future_cdk/sql_processor.py

@@ -206,9 +206,6 @@ def get_sql_table_name(
     ) -> str:
         """Return the name of the SQL table for the given stream."""
         table_prefix = self.sql_config.table_prefix
-
-        # TODO: Add default prefix based on the source name.
-
         return self.normalizer.normalize(
             f"{table_prefix}{stream_name}",
         )
@@ -433,6 +430,7 @@ def _ensure_compatible_table_schema(
         input stream.
         """
         # TODO: Expand this to check for column types and sizes.
+        # https://github.com/airbytehq/pyairbyte/issues/321
         self._add_missing_columns_to_table(
             stream_name=stream_name,
             table_name=table_name,

airbyte/_processors/sql/postgres.py

@@ -48,6 +48,6 @@ class PostgresSqlProcessor(SqlProcessorBase):
     or another import method. (Relatively low priority, since for now it works fine as-is.)
     """
 
-    supports_merge_insert = False  # TODO: Add native implementation for merge insert
+    supports_merge_insert = False
     file_writer_class = JsonlWriter
     sql_config: PostgresConfig

airbyte/_util/api_util.py

@@ -254,7 +254,7 @@ def create_source(
         models.SourceCreateRequest(
             name=name,
             workspace_id=workspace_id,
-            configuration=config,  # TODO: wrap in a proper configuration object
+            configuration=config,
             definition_id=None,  # Not used alternative to config.sourceType.
             secret_id=None,  # For OAuth, not yet supported
         ),
@@ -337,7 +337,7 @@ def create_destination(
         models.DestinationCreateRequest(
             name=name,
             workspace_id=workspace_id,
-            configuration=config,  # TODO: wrap in a proper configuration object
+            configuration=config,
         ),
     )
     if status_ok(response.status_code) and response.destination_response:
@@ -368,6 +368,7 @@ def get_destination(
     if status_ok(response.status_code):
         # TODO: This is a temporary workaround to resolve an issue where
         # the destination API response is of the wrong type.
+        # https://github.com/airbytehq/pyairbyte/issues/320
         raw_response: dict[str, Any] = json.loads(response.raw_response.text)
         raw_configuration: dict[str, Any] = raw_response["configuration"]
         destination_type = raw_response.get("destinationType")
@@ -538,10 +539,6 @@ def delete_connection(
 #     api_key: str,
 #     workspace_id: str | None = None,
 # ) -> api.SourceCheckResponse:
-#     """Check a source.
-
-#     # TODO: Need to use legacy Configuration API for this:
-#     # https://airbyte-public-api-docs.s3.us-east-2.amazonaws.com/rapidoc-api-docs.html#post-/v1/sources/check_connection
-#     """
+#     """Check a source."""
 #     _ = source_id, workspace_id, api_root, api_key
 #     raise NotImplementedError

airbyte/_util/document_rendering.py

@@ -43,6 +43,7 @@ class DocumentRenderer(BaseModel):
     render_metadata: bool = False
 
     # TODO: Add primary key and cursor key support:
+    # https://github.com/airbytehq/pyairbyte/issues/319
     # primary_key_properties: list[str]
     # cursor_property: str | None
 
@@ -72,13 +73,6 @@ def render_document(self, record: dict[str, Any]) -> Document:
             content += yaml.dump({key: record[key] for key in self.metadata_properties})
             content += "```\n"
 
-        # TODO: Add support for primary key and doc ID generation:
-        # doc_id: str = (
-        #     "-".join(str(record[key]) for key in self.primary_key_properties)
-        #     if self.primary_key_properties
-        #     else str(hash(record))
-        # )
-
         if not self.content_properties:
             pass
         elif len(self.content_properties) == 1:

airbyte/caches/motherduck.py

@@ -48,7 +48,8 @@ def get_sql_alchemy_url(self) -> SecretString:
 
         return SecretString(
             f"duckdb:///md:{self.database}?motherduck_token={self.api_key}"
-            # f"&schema={self.schema_name}"  # TODO: Debug why this doesn't work
+            # Not sure why this doesn't work. We have to override later in the flow.
+            # f"&schema={self.schema_name}"
         )
 
     @overrides