feat(12-01): implement SRTProcessor and Markdown generation

- Add SRTInput/SRTOutput schemas to pipeline
- Create SRTProcessor following BaseProcessor pattern
- Generate Markdown with YAML frontmatter
- Support metadata extraction and formatting
- Handle missing metadata gracefully

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

tests/test_srt_processor.py

@@ -7,6 +7,9 @@ Tests for:
 - SRTProcessor (pipeline processor)
 """
 
+import asyncio
+import json
+
 import pytest
 from pathlib import Path
 from dataclasses import dataclass
@@ -340,3 +343,150 @@ class TestASRCorrector:
         result = corrector.correct("")
 
         assert result == ""
+
+
+# =============================================================================
+# Test 4: SRTProcessor
+# =============================================================================
+
+
+@pytest.fixture
+def srt_test_files(tmp_path: Path):
+    """创建测试用的 SRT 和元数据文件"""
+    # 创建 SRT 文件
+    srt_content = """1
+00:00:00,000 --> 00:00:05,000
+第一句字幕内容
+
+2
+00:00:05,000 --> 00:00:10,000
+第二句字幕内容
+
+3
+00:00:10,000 --> 00:00:15,000
+第三句字幕内容
+"""
+    srt_file = tmp_path / "test.srt"
+    srt_file.write_text(srt_content, encoding="utf-8")
+
+    # 创建元数据文件
+    metadata = {
+        "title": "测试视频标题",
+        "author": "测试作者",
+        "platform": "bilibili",
+        "bvid": "BV1test123",
+        "duration": 60,
+        "url": "https://www.bilibili.com/video/BV1test123",
+        "pubtime": "2026-03-19"
+    }
+    metadata_file = tmp_path / "metadata.json"
+    metadata_file.write_text(json.dumps(metadata, ensure_ascii=False), encoding="utf-8")
+
+    # 输出文件路径
+    output_file = tmp_path / "output.md"
+
+    return {
+        "srt_file": str(srt_file),
+        "metadata_file": str(metadata_file),
+        "output_file": str(output_file)
+    }
+
+
+class TestSRTProcessor:
+    """测试 SRTProcessor 处理器"""
+
+    def test_srt_processor_generates_markdown(self, srt_test_files):
+        """SRTProcessor 能处理 SRT 文件生成 Markdown"""
+        from kb_workflow.pipeline.processors.srt import SRTProcessor
+        from kb_workflow.pipeline.schemas import SRTInput
+
+        processor = SRTProcessor(enable_correction=False)
+
+        input_data = SRTInput(
+            content_id="BV1test123",
+            platform="bilibili",
+            srt_file=srt_test_files["srt_file"],
+            metadata_file=srt_test_files["metadata_file"],
+            output_file=srt_test_files["output_file"]
+        )
+
+        # 运行处理
+        result = asyncio.run(processor.process(input_data))
+
+        assert result.success
+        assert Path(result.output_file).exists()
+
+        # 验证 Markdown 内容
+        content = Path(result.output_file).read_text(encoding="utf-8")
+        assert "---" in content  # frontmatter
+        assert "title:" in content
+        assert "测试视频标题" in content
+        assert "## 内容" in content
+        assert "第一句字幕内容" in content
+
+    def test_srt_processor_with_yaml_frontmatter(self, srt_test_files):
+        """输出包含 YAML frontmatter（元数据和标签）"""
+        from kb_workflow.pipeline.processors.srt import SRTProcessor
+        from kb_workflow.pipeline.schemas import SRTInput
+
+        processor = SRTProcessor(enable_correction=False)
+
+        input_data = SRTInput(
+            content_id="BV1test123",
+            platform="bilibili",
+            srt_file=srt_test_files["srt_file"],
+            metadata_file=srt_test_files["metadata_file"],
+            output_file=srt_test_files["output_file"]
+        )
+
+        result = asyncio.run(processor.process(input_data))
+
+        content = Path(result.output_file).read_text(encoding="utf-8")
+
+        # 验证 frontmatter 字段
+        assert "title:" in content
+        assert "date:" in content
+        assert "author:" in content
+        assert "platform:" in content
+        assert "bvid:" in content
+        assert "url:" in content
+
+    def test_srt_processor_follows_base_processor_pattern(self):
+        """处理器遵循 BaseProcessor 模式"""
+        from kb_workflow.pipeline.processors.srt import SRTProcessor
+        from kb_workflow.pipeline.processors.base import BaseProcessor
+
+        # SRTProcessor 应该继承 BaseProcessor
+        assert issubclass(SRTProcessor, BaseProcessor)
+
+        # 应该有 STEP_NAME
+        assert hasattr(SRTProcessor, 'STEP_NAME')
+        assert SRTProcessor.STEP_NAME == "srt"
+
+    def test_srt_processor_handles_missing_metadata(self, tmp_path: Path):
+        """元数据文件缺失时能正常处理"""
+        from kb_workflow.pipeline.processors.srt import SRTProcessor
+        from kb_workflow.pipeline.schemas import SRTInput
+
+        # 创建 SRT 文件
+        srt_content = "1\n00:00:00,000 --> 00:00:05,000\n测试内容\n"
+        srt_file = tmp_path / "test.srt"
+        srt_file.write_text(srt_content, encoding="utf-8")
+
+        # 不存在的元数据文件
+        output_file = tmp_path / "output.md"
+
+        processor = SRTProcessor(enable_correction=False)
+
+        input_data = SRTInput(
+            content_id="test123",
+            platform="bilibili",
+            srt_file=str(srt_file),
+            metadata_file=str(tmp_path / "nonexistent.json"),
+            output_file=str(output_file)
+        )
+
+        result = asyncio.run(processor.process(input_data))
+
+        assert result.success
+        assert Path(result.output_file).exists()