test(04-01): add failing tests for BaseProcessor abstract class

- Test BaseProcessor cannot be instantiated directly
- Test subclass must implement process() method
- Test state_manager attribute is provided
- Test STEP_NAME class attribute requirement

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

kb_pipeline/processors/base.py

@@ -0,0 +1,55 @@
+"""BaseProcessor - Abstract base class for all pipeline processors
+
+Provides a unified interface that all processors (parse, download, asr, analyze)
+must follow, enabling consistent state management and error handling.
+"""
+
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+from typing import Optional, TYPE_CHECKING
+
+from kb_pipeline.config import get_settings
+from kb_pipeline.schemas import StepInput, StepOutput
+
+if TYPE_CHECKING:
+    from kb_pipeline.state import WorkflowStateManager
+
+
+class BaseProcessor(ABC):
+    """Abstract base class for all pipeline processors.
+
+    All processors (ParseProcessor, DownloadProcessor, ASRProcessor, AnalyzeProcessor)
+    must inherit from this class and implement the process() method.
+
+    Attributes:
+        STEP_NAME: Class attribute identifying the processor step name.
+        settings: KBSettings instance from get_settings().
+        state_manager: Optional WorkflowStateManager for state recording.
+    """
+
+    STEP_NAME: str
+
+    def __init__(self, state_manager: Optional[WorkflowStateManager] = None):
+        """Initialize the processor.
+
+        Args:
+            state_manager: Optional WorkflowStateManager for recording step state.
+        """
+        self.settings = get_settings()
+        self.state_manager = state_manager
+
+    @abstractmethod
+    async def process(self, input_data: StepInput) -> StepOutput:
+        """Process the input data and return the result.
+
+        Args:
+            input_data: Input data for the processor step.
+
+        Returns:
+            StepOutput with processing results.
+
+        Raises:
+            Exception: If processing fails.
+        """
+        pass

tests/test_processors/test_base.py

@@ -0,0 +1,130 @@
+"""Tests for BaseProcessor abstract class
+
+Tests that BaseProcessor:
+- Cannot be instantiated directly (abstract)
+- Requires subclass to implement process() method
+- Provides state_manager attribute
+- Provides STEP_NAME class attribute
+"""
+
+import pytest
+from abc import ABC
+from unittest.mock import MagicMock, patch
+
+
+class TestBaseProcessorAbstract:
+    """BaseProcessor 抽象类测试"""
+
+    def test_base_processor_cannot_be_instantiated(self):
+        """BaseProcessor 不能直接实例化"""
+        from kb_pipeline.processors.base import BaseProcessor
+
+        with pytest.raises(TypeError):
+            BaseProcessor()
+
+    def test_base_processor_is_abstract(self):
+        """BaseProcessor 是抽象类"""
+        from kb_pipeline.processors.base import BaseProcessor
+
+        assert issubclass(BaseProcessor, ABC)
+
+    def test_subclass_must_implement_process(self):
+        """子类必须实现 process() 方法"""
+        from kb_pipeline.processors.base import BaseProcessor
+        from kb_pipeline.schemas import StepInput, StepOutput
+
+        # 缺少 process 实现的子类无法实例化
+        class IncompleteProcessor(BaseProcessor):
+            STEP_NAME = "incomplete"
+
+        with pytest.raises(TypeError):
+            IncompleteProcessor()
+
+    def test_subclass_can_be_instantiated_with_process(self):
+        """实现了 process() 的子类可以实例化"""
+        from kb_pipeline.processors.base import BaseProcessor
+        from kb_pipeline.schemas import StepInput, StepOutput
+
+        class CompleteProcessor(BaseProcessor):
+            STEP_NAME = "complete"
+
+            async def process(self, input_data: StepInput) -> StepOutput:
+                pass
+
+        # 可以实例化
+        with patch("kb_pipeline.processors.base.get_settings") as mock_settings:
+            mock_settings.return_value = MagicMock()
+            processor = CompleteProcessor()
+            assert processor is not None
+
+
+class TestBaseProcessorAttributes:
+    """BaseProcessor 属性测试"""
+
+    def test_base_processor_has_step_name_class_attribute(self):
+        """BaseProcessor 要求子类定义 STEP_NAME 类属性"""
+        from kb_pipeline.processors.base import BaseProcessor
+        from kb_pipeline.schemas import StepInput, StepOutput
+
+        class TestProcessor(BaseProcessor):
+            STEP_NAME = "test_step"
+
+            async def process(self, input_data: StepInput) -> StepOutput:
+                pass
+
+        with patch("kb_pipeline.processors.base.get_settings") as mock_settings:
+            mock_settings.return_value = MagicMock()
+            processor = TestProcessor()
+            assert processor.STEP_NAME == "test_step"
+
+    def test_base_processor_provides_state_manager(self):
+        """BaseProcessor 提供 state_manager 属性"""
+        from kb_pipeline.processors.base import BaseProcessor
+        from kb_pipeline.schemas import StepInput, StepOutput
+
+        class TestProcessor(BaseProcessor):
+            STEP_NAME = "test"
+
+            async def process(self, input_data: StepInput) -> StepOutput:
+                pass
+
+        mock_state_manager = MagicMock()
+
+        with patch("kb_pipeline.processors.base.get_settings") as mock_settings:
+            mock_settings.return_value = MagicMock()
+            processor = TestProcessor(state_manager=mock_state_manager)
+            assert processor.state_manager is mock_state_manager
+
+    def test_base_processor_state_manager_optional(self):
+        """BaseProcessor state_manager 是可选的"""
+        from kb_pipeline.processors.base import BaseProcessor
+        from kb_pipeline.schemas import StepInput, StepOutput
+
+        class TestProcessor(BaseProcessor):
+            STEP_NAME = "test"
+
+            async def process(self, input_data: StepInput) -> StepOutput:
+                pass
+
+        with patch("kb_pipeline.processors.base.get_settings") as mock_settings:
+            mock_settings.return_value = MagicMock()
+            processor = TestProcessor()
+            assert processor.state_manager is None
+
+    def test_base_processor_provides_settings(self):
+        """BaseProcessor 提供 settings 属性"""
+        from kb_pipeline.processors.base import BaseProcessor
+        from kb_pipeline.schemas import StepInput, StepOutput
+
+        class TestProcessor(BaseProcessor):
+            STEP_NAME = "test"
+
+            async def process(self, input_data: StepInput) -> StepOutput:
+                pass
+
+        mock_settings = MagicMock()
+
+        with patch("kb_pipeline.processors.base.get_settings") as mock_get_settings:
+            mock_get_settings.return_value = mock_settings
+            processor = TestProcessor()
+            assert processor.settings is mock_settings