test(12-01): add failing tests for ASRCorrector

- Test obvious homophone error correction
- Test contextual error correction
- Test no overcorrection on correct text
- Test AI unavailable fallback
- Test batch processing for long text
- Test empty text handling

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

tests/test_srt_processor.py

@@ -238,3 +238,105 @@ class TestSemanticSegmenter:
         paragraphs = segmenter.segment([])
 
         assert paragraphs == []
+
+
+# =============================================================================
+# Test 3: ASR Corrector
+# =============================================================================
+
+class TestASRCorrector:
+    """测试 ASR 纠错器"""
+
+    def test_correct_obvious_errors(self):
+        """Test 1: 明显的同音字错误被纠正"""
+        from kb_workflow.srt.corrector import ASRCorrector
+
+        # 创建一个 mock AI 客户端
+        class MockAIClient:
+            def generate(self, prompt: str, max_tokens: int = 16000) -> str:
+                # 模拟纠错结果
+                if "什么" in prompt:
+                    return "什么是机器学习"
+                return prompt
+
+        corrector = ASRCorrector(ai_client=MockAIClient())
+        result = corrector.correct("什么是机器学习")
+
+        # 纠错后的文本应该被返回
+        assert result is not None
+        assert len(result) > 0
+
+    def test_correct_contextual_errors(self):
+        """Test 2: 上下文相关的错误被纠正"""
+        from kb_workflow.srt.corrector import ASRCorrector
+
+        class MockAIClient:
+            def generate(self, prompt: str, max_tokens: int = 16000) -> str:
+                # 模拟纠错结果
+                return "这是一个测试文本，已经被纠正了。"
+
+        corrector = ASRCorrector(ai_client=MockAIClient())
+        result = corrector.correct("这是一个测试文本，已经被纠正了。")
+
+        assert "测试" in result
+
+    def test_no_overcorrection(self):
+        """Test 3: 正确文本不被过度修改"""
+        from kb_workflow.srt.corrector import ASRCorrector
+
+        original_text = "这是一段完全正确的中文文本，不需要修改。"
+
+        class MockAIClient:
+            def generate(self, prompt: str, max_tokens: int = 16000) -> str:
+                # 返回原文，表示没有错误
+                return original_text
+
+        corrector = ASRCorrector(ai_client=MockAIClient())
+        result = corrector.correct(original_text)
+
+        # 正确文本应该基本保持不变
+        assert result == original_text
+
+    def test_ai_unavailable_returns_original(self):
+        """AI 不可用时返回原文"""
+        from kb_workflow.srt.corrector import ASRCorrector
+
+        # 没有提供 AI 客户端
+        corrector = ASRCorrector(ai_client=None)
+        text = "这是原始文本"
+        result = corrector.correct(text)
+
+        # 应该返回原文
+        assert result == text
+
+    def test_batch_processing(self):
+        """长文本被分批处理"""
+        from kb_workflow.srt.corrector import ASRCorrector
+
+        # 创建超长文本
+        long_text = "这是一段很长的文本。" * 1000  # 约 10,000 字符
+
+        call_count = 0
+
+        class MockAIClient:
+            def generate(self, prompt: str, max_tokens: int = 16000) -> str:
+                nonlocal call_count
+                call_count += 1
+                # 返回提示词中的文本部分
+                return "处理后的文本"
+
+        corrector = ASRCorrector(ai_client=MockAIClient(), batch_size=5000)
+        result = corrector.correct(long_text)
+
+        # 应该被分批处理（至少调用2次）
+        assert call_count >= 2
+        assert result is not None
+
+    def test_empty_text(self):
+        """空文本返回空字符串"""
+        from kb_workflow.srt.corrector import ASRCorrector
+
+        corrector = ASRCorrector(ai_client=None)
+        result = corrector.correct("")
+
+        assert result == ""