chore: resolve ruff lint issues (#16)

Author: aaronsteers

airbyte_cdk/models/airbyte_protocol.py

@@ -6,9 +6,11 @@
 from typing import Annotated, Any, Dict, List, Mapping, Optional, Union
 
 from airbyte_cdk.models.file_transfer_record_message import AirbyteFileTransferRecordMessage
-from airbyte_protocol_dataclasses.models import *
+from airbyte_protocol_dataclasses.models import *  # noqa: F403  # Allow '*'
 from serpyco_rs.metadata import Alias
 
+# ruff: noqa: F405  # ignore fuzzy import issues with 'import *'
+
 
 @dataclass
 class AirbyteStateBlob:

airbyte_cdk/models/well_known_types.py

@@ -2,4 +2,4 @@
 # Copyright (c) 2023 Airbyte, Inc., all rights reserved.
 #
 
-from airbyte_protocol_dataclasses.models.well_known_types import *
+from airbyte_protocol_dataclasses.models.well_known_types import *  # noqa: F403  # Allow '*'

airbyte_cdk/sources/declarative/datetime/min_max_datetime.py

@@ -32,7 +32,7 @@ class MinMaxDatetime:
     parameters: InitVar[Mapping[str, Any]]
     # datetime_format is a unique case where we inherit it from the parent if it is not specified before using the default value
     # which is why we need dedicated getter/setter methods and private dataclass field
-    datetime_format: str = ""
+    datetime_format: str
     _datetime_format: str = field(init=False, repr=False, default="")
     min_datetime: Union[InterpolatedString, str] = ""
     max_datetime: Union[InterpolatedString, str] = ""

airbyte_cdk/sources/file_based/file_types/csv_parser.py

@@ -362,22 +362,22 @@ def _cast_types(
                     else:
                         warnings.append(_format_warning(key, value, prop_type))
 
-                elif python_type == bool:
+                elif python_type is bool:
                     try:
                         cast_value = _value_to_bool(
                             value, config_format.true_values, config_format.false_values
                         )
                     except ValueError:
                         warnings.append(_format_warning(key, value, prop_type))
 
-                elif python_type == dict:
+                elif python_type is dict:
                     try:
                         # we don't re-use _value_to_object here because we type the column as object as long as there is only one object
                         cast_value = orjson.loads(value)
                     except orjson.JSONDecodeError:
                         warnings.append(_format_warning(key, value, prop_type))
 
-                elif python_type == list:
+                elif python_type is list:
                     try:
                         cast_value = _value_to_list(value)
                     except (ValueError, json.JSONDecodeError):

airbyte_cdk/sources/file_based/file_types/excel_parser.py

@@ -151,7 +151,7 @@ def dtype_to_json_type(current_type: Optional[str], dtype: dtype_) -> str:
         if current_type == "string":
             # Previous column values were of the string type, no need to look further.
             return current_type
-        if dtype == object:
+        if dtype is object:
             return "string"
         if dtype in number_types and (not current_type or current_type == "number"):
             return "number"

pyproject.toml

@@ -104,9 +104,7 @@ skip = ["__init__.py"]  # TODO: Remove after this is fixed: https://github.com/a
 [tool.ruff]
 exclude = ["__init__.py"]  # TODO: Remove after this is fixed: https://github.com/airbytehq/airbyte-python-cdk/issues/12
 
-# Setting python version to at least 3.10 avoids `from __future__ import annotations`.
 target-version = "py310"
-# This is consistent with airbytehq/airbyte root pyproject.toml Black rule defined.
 line-length = 100
 
 [tool.poe.tasks]

unit_tests/sources/streams/concurrent/test_concurrent_read_processor.py

@@ -735,35 +735,6 @@ def test_given_partition_completion_is_not_success_then_do_not_close_partition(s
 
         assert self._an_open_partition.close.call_count == 0
 
-    def test_given_partition_completion_is_not_success_then_do_not_close_partition(self):
-        stream_instances_to_read_from = [self._stream, self._another_stream]
-
-        handler = ConcurrentReadProcessor(
-            stream_instances_to_read_from,
-            self._partition_enqueuer,
-            self._thread_pool_manager,
-            self._logger,
-            self._slice_logger,
-            self._message_repository,
-            self._partition_reader,
-        )
-
-        handler.start_next_partition_generator()
-        handler.on_partition(self._an_open_partition)
-        list(
-            handler.on_partition_generation_completed(
-                PartitionGenerationCompletedSentinel(self._stream)
-            )
-        )
-
-        list(
-            handler.on_partition_complete_sentinel(
-                PartitionCompleteSentinel(self._an_open_partition, not _IS_SUCCESSFUL)
-            )
-        )
-
-        assert self._an_open_partition.close.call_count == 0
-
     def test_is_done_is_false_if_there_are_any_instances_to_read_from(self):
         stream_instances_to_read_from = [self._stream]
 

unit_tests/test/mock_http/test_mocker.py

@@ -266,15 +266,6 @@ def decorated_function(http_mocker):
         with pytest.raises(ValueError):
             decorated_function()
 
-    def test_given_unknown_request_when_assert_number_of_calls_then_raise(self):
-        @HttpMocker()
-        def decorated_function(http_mocker):
-            http_mocker.get(HttpRequest(_A_URL), _A_RESPONSE)
-            http_mocker.assert_number_of_calls(HttpRequest(_ANOTHER_URL), 1)
-
-        with pytest.raises(ValueError):
-            decorated_function()
-
     def test_given_request_already_mocked_when_decorate_then_raise(self):
         with HttpMocker() as http_mocker:
             a_request = HttpRequest(_A_URL, _SOME_QUERY_PARAMS, _SOME_HEADERS)