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

- Test merging short segments into paragraphs
- Test segmentation on topic change (time gap)
- Test max paragraph length constraint
- Test empty segments handling

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

tests/test_srt_processor.py

@@ -149,3 +149,92 @@ class TestParseSrtFile:
 
         with pytest.raises(FileNotFoundError):
             parse_srt_file(Path("/nonexistent/file.srt"))
+
+
+# =============================================================================
+# Test 2: Semantic Segmenter
+# =============================================================================
+
+@pytest.fixture
+def short_segments():
+    """连续短句字幕分段"""
+    from kb_workflow.srt.parser import Segment
+    return [
+        Segment(id=1, start_time=0.0, end_time=2.0, text="这是第一句短句"),
+        Segment(id=2, start_time=2.0, end_time=4.0, text="这是第二句短句"),
+        Segment(id=3, start_time=4.0, end_time=6.0, text="这是第三句短句"),
+    ]
+
+
+@pytest.fixture
+def segments_with_gap():
+    """带有长停顿的字幕分段"""
+    from kb_workflow.srt.parser import Segment
+    return [
+        Segment(id=1, start_time=0.0, end_time=5.0, text="第一段内容在这里"),
+        Segment(id=2, start_time=5.0, end_time=10.0, text="继续第一段"),
+        # 5秒停顿
+        Segment(id=3, start_time=15.0, end_time=20.0, text="第二段从这里开始"),
+        Segment(id=4, start_time=20.0, end_time=25.0, text="继续第二段"),
+    ]
+
+
+@pytest.fixture
+def long_text_segment():
+    """长文本分段（超过500字符）"""
+    from kb_workflow.srt.parser import Segment
+    long_text = "这是一段很长的文本，" * 50  # 约600字符
+    return [
+        Segment(id=1, start_time=0.0, end_time=60.0, text=long_text),
+    ]
+
+
+class TestSemanticSegmenter:
+    """测试语义分段器"""
+
+    def test_merge_short_segments(self, short_segments):
+        """Test 1: 连续短句被合并为段落"""
+        from kb_workflow.srt.segmenter import SemanticSegmenter
+
+        segmenter = SemanticSegmenter()
+        paragraphs = segmenter.segment(short_segments)
+
+        # 所有短句应该被合并
+        assert len(paragraphs) >= 1
+        # 验证所有内容都被保留
+        merged_text = ' '.join(paragraphs)
+        assert "第一句短句" in merged_text
+        assert "第二句短句" in merged_text
+        assert "第三句短句" in merged_text
+
+    def test_segment_on_topic_change(self, segments_with_gap):
+        """Test 2: 主题变化时自动分段（基于时间间隔）"""
+        from kb_workflow.srt.segmenter import SemanticSegmenter
+
+        segmenter = SemanticSegmenter(gap_threshold=3.0)
+        paragraphs = segmenter.segment(segments_with_gap)
+
+        # 应该分成两段（因为中间有5秒停顿）
+        assert len(paragraphs) == 2
+        assert "第一段" in paragraphs[0]
+        assert "第二段" in paragraphs[1]
+
+    def test_max_paragraph_length(self, long_text_segment):
+        """Test 3: 单个段落不超过 500 字符"""
+        from kb_workflow.srt.segmenter import SemanticSegmenter
+
+        segmenter = SemanticSegmenter(max_paragraph_chars=500)
+        paragraphs = segmenter.segment(long_text_segment)
+
+        # 每个段落不应该超过限制
+        for para in paragraphs:
+            assert len(para) <= 520  # 允许小范围超出（最后一块）
+
+    def test_empty_segments(self):
+        """空分段列表返回空列表"""
+        from kb_workflow.srt.segmenter import SemanticSegmenter
+
+        segmenter = SemanticSegmenter()
+        paragraphs = segmenter.segment([])
+
+        assert paragraphs == []