fix: remove redundant imports and errors

Author: zafatar

integrations/amazon_textract/pyproject.toml

@@ -28,7 +28,6 @@ classifiers = [
   "Programming Language :: Python :: 3.13",
   "Programming Language :: Python :: 3.14",
   "Programming Language :: Python :: Implementation :: CPython",
-  "Programming Language :: Python :: Implementation :: PyPy",
 ]
 dependencies = [
     "haystack-ai>=2.24.1",
@@ -63,7 +62,6 @@ fmt-check = "ruff check {args} && ruff format --check {args}"
 [tool.hatch.envs.test]
 dependencies = [
     "pytest",
-    "pytest-asyncio",
     "pytest-cov",
     "pytest-rerunfailures",
     "mypy",
@@ -173,7 +171,7 @@ exclude_lines = ["no cov", "if __name__ == .__main__.:", "if TYPE_CHECKING:"]
 [tool.pytest.ini_options]
 addopts = "--strict-markers"
 markers = [
+  "unit: unit tests",
   "integration: integration tests",
 ]
 log_cli = true
-asyncio_default_fixture_loop_scope = "function"

integrations/amazon_textract/src/haystack_integrations/components/converters/amazon_textract/__init__.py

@@ -2,6 +2,7 @@
 #
 # SPDX-License-Identifier: Apache-2.0
 
-from haystack_integrations.components.converters.amazon_textract.converter import AmazonTextractConverter
+from .converter import AmazonTextractConverter
+from .errors import AmazonTextractConfigurationError
 
-__all__ = ["AmazonTextractConverter"]
+__all__ = ["AmazonTextractConfigurationError", "AmazonTextractConverter"]

integrations/amazon_textract/src/haystack_integrations/components/converters/amazon_textract/converter.py

@@ -2,7 +2,6 @@
 #
 # SPDX-License-Identifier: Apache-2.0
 
-import os
 from pathlib import Path
 from typing import Any
 
@@ -14,9 +13,7 @@
 from haystack.dataclasses import ByteStream
 from haystack.utils import Secret, deserialize_secrets_inplace
 
-from haystack_integrations.components.converters.amazon_textract.errors import (
-    AmazonTextractConfigurationError,
-)
+from .errors import AmazonTextractConfigurationError
 
 logger = logging.getLogger(__name__)
 
@@ -125,7 +122,7 @@ def resolve_secret(secret: Secret | None) -> str | None:
                 **(self.boto3_config if self.boto3_config else {}),
             )
             self._client = session.client("textract", config=config)
-        except Exception as e:
+        except BotoCoreError as e:
             msg = (
                 "Could not connect to AWS Textract. Make sure the AWS environment is configured correctly. "
                 "See https://boto3.amazonaws.com/v1/documentation/api/latest/guide/quickstart.html#configuration"
@@ -180,7 +177,7 @@ def run(
 
                 merged_metadata = {**bytestream.meta, **metadata}
                 if not self.store_full_path and (file_path := bytestream.meta.get("file_path")):
-                    merged_metadata["file_path"] = os.path.basename(file_path)
+                    merged_metadata["file_path"] = Path(file_path).name
 
                 doc = self._create_document(response, merged_metadata)
                 documents.append(doc)

integrations/amazon_textract/src/haystack_integrations/components/converters/amazon_textract/errors.py

@@ -3,9 +3,5 @@
 # SPDX-License-Identifier: Apache-2.0
 
 
-class AmazonTextractError(Exception):
-    """Any error generated by the Amazon Textract integration."""
-
-
-class AmazonTextractConfigurationError(AmazonTextractError):
+class AmazonTextractConfigurationError(Exception):
     """Exception raised when AWS is not configured correctly for Textract."""

integrations/amazon_textract/tests/test_amazon_textract_converter.py

@@ -6,7 +6,7 @@
 from unittest.mock import MagicMock, patch
 
 import pytest
-from botocore.exceptions import ClientError
+from botocore.exceptions import BotoCoreError, ClientError
 from haystack.dataclasses import ByteStream
 from haystack.utils import Secret
 
@@ -190,7 +190,7 @@ def test_warm_up_idempotent(self, mock_session_cls):
 
     @patch(
         "haystack_integrations.components.converters.amazon_textract.converter.boto3.Session",
-        side_effect=Exception("bad config"),
+        side_effect=BotoCoreError(),
     )
     def test_warm_up_configuration_error(self, _mock_session_cls):
         converter = AmazonTextractConverter(