starmen1265/kb-skills
Archived
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(13-07): integrate SemanticSegmentationEngine into SRTProcessor

Browse Source 
- 添加 enable_semantic_segmentation 参数到 SRTProcessor.__init__
- 启用时使用 SemanticSegmentationEngine，禁用时使用 SemanticSegmenter
- AI 不可用时自动降级到规则分段
- 更新 _generate_markdown() 支持带标题的 VideoSegment 输出
- 调整步骤顺序：先加载元数据，再进行语义分段
- 更新 UnifiedSegmentationStrategy.segment() 返回 List[VideoSegment]
- 添加代理方法到 SemanticSegmentationEngine 以保持向后兼容
- 创建全面的集成测试（9 个测试用例）
- 更新现有语义引擎测试以适配新 API

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
starmen1265
2026-03-22 00:32:14 +08:00
parent a6c0293c01
commit ef4a660faa
4 changed files with 578 additions and 56 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/test_semantic_engine.py
+34 -24
View File
@@ -11,7 +11,8 @@ from kb_workflow.srt.semantic_engine import (
extract_json_from_llm_response,
VideoSegment,
SegmentationResult,
SemanticSegmentationEngine
SemanticSegmentationEngine,
UnifiedSegmentationStrategy
)
@@ -236,15 +237,17 @@ class TestChineseSentenceBoundary:
Segment(4, 15.0, 20.0, "这是第四句话……")
]
engine = SemanticSegmentationEngine(ai_client=mock_client)
result = engine.segment(segments, {"title": "测试", "video_type": "知识类"})
# 使用新的策略模式 API
from kb_workflow.srt.semantic_engine import UnifiedSegmentationStrategy
strategy = UnifiedSegmentationStrategy(ai_client=mock_client)
result = strategy.segment(segments, {"title": "测试", "video_type": "知识类"})
# 验证分段边界在标点后
assert len(result) == 2
# 第一个分段在问号后结束
assert result[0].strip().endswith("？")
assert result[0].content.strip().endswith("？")
# 第二个分段在省略号后结束
assert result[1].strip().endswith("……")
assert result[1].content.strip().endswith("……")
# ============================================================================
@@ -307,7 +310,8 @@ class TestTopicBoundaryDetection:
}, ensure_ascii=False)
mock_client = MockAIClient(llm_response)
engine = SemanticSegmentationEngine(ai_client=mock_client)
strategy = UnifiedSegmentationStrategy(ai_client=mock_client)
engine = SemanticSegmentationEngine(strategy=strategy)
metadata = {
"title": "AI技术介绍",
@@ -318,8 +322,8 @@ class TestTopicBoundaryDetection:
# 验证：结果包含两个段落
assert len(paragraphs) == 2, f"Expected 2 paragraphs, got {len(paragraphs)}"
assert "机器学习是人工智能" in paragraphs[0], "First paragraph should mention 机器学习"
assert "深度学习是机器学习" in paragraphs[1], "Second paragraph should mention 深度学习"
assert "机器学习是人工智能" in paragraphs[0].content, "First paragraph should mention 机器学习"
assert "深度学习是机器学习" in paragraphs[1].content, "Second paragraph should mention 深度学习"
def test_semantic_completeness(self):
"""测试单个话题内容完整，不混入其他话题
@@ -346,7 +350,8 @@ class TestTopicBoundaryDetection:
}, ensure_ascii=False)
mock_client = MockAIClient(llm_response)
engine = SemanticSegmentationEngine(ai_client=mock_client)
strategy = UnifiedSegmentationStrategy(ai_client=mock_client)
engine = SemanticSegmentationEngine(strategy=strategy)
metadata = {
"title": "优化算法介绍",
@@ -357,10 +362,10 @@ class TestTopicBoundaryDetection:
# 验证：单个段落包含完整内容
assert len(paragraphs) == 1, f"Expected 1 paragraph, got {len(paragraphs)}"
assert "梯度下降是一种优化算法" in paragraphs[0]
assert "批量梯度下降" in paragraphs[0]
assert "随机梯度下降" in paragraphs[0]
assert "小批量梯度下降" in paragraphs[0]
assert "梯度下降是一种优化算法" in paragraphs[0].content
assert "批量梯度下降" in paragraphs[0].content
assert "随机梯度下降" in paragraphs[0].content
assert "小批量梯度下降" in paragraphs[0].content
def test_no_mixed_topics(self):
"""测试分段不混入不同话题的内容
@@ -390,7 +395,8 @@ class TestTopicBoundaryDetection:
}, ensure_ascii=False)
mock_client = MockAIClient(llm_response)
engine = SemanticSegmentationEngine(ai_client=mock_client)
strategy = UnifiedSegmentationStrategy(ai_client=mock_client)
engine = SemanticSegmentationEngine(strategy=strategy)
metadata = {
"title": "AI技术介绍",
@@ -402,7 +408,7 @@ class TestTopicBoundaryDetection:
# 验证：分段内容不混入其他话题
assert len(paragraphs) == 2
# 第一个段落不应该包含深度学习的内容（除了可能的引用）
assert "深度学习" not in paragraphs[0] or "子领域" in paragraphs[0]
assert "深度学习" not in paragraphs[0].content or "子领域" in paragraphs[0].content
# 第二个段落可以提到"机器学习"因为它是"深度学习的超类"
def _create_multi_topic_segments(self) -> list[Segment]:
@@ -559,7 +565,8 @@ class TestSentenceBoundaryProtection:
mock_client.generate.return_value = mock_response
# Create engine and segment
engine = SemanticSegmentationEngine(ai_client=mock_client)
strategy = UnifiedSegmentationStrategy(ai_client=mock_client)
engine = SemanticSegmentationEngine(strategy=strategy)
metadata = {"title": "机器学习介绍", "duration": 9.0}
paragraphs = engine.segment(segments, metadata)
@@ -571,9 +578,10 @@ class TestSentenceBoundaryProtection:
sentence_endings = r'[。？！……]$'
for para in paragraphs:
para_stripped = para.strip()
para_content = para.content if hasattr(para, 'content') else para
para_stripped = para_content.strip()
assert re.search(sentence_endings, para_stripped), \
f"段落应以标点符号结尾: {para[:50]}..."
f"段落应以标点符号结尾: {para_content[:50]}..."
def test_sentence_boundary_in_prompt(self):
"""Test: SEGMENTATION_PROMPT 包含句边界保护指令"""
@@ -626,7 +634,8 @@ class TestArgumentCompleteness:
mock_client.generate.return_value = mock_response
# Create engine and segment
engine = SemanticSegmentationEngine(ai_client=mock_client)
strategy = UnifiedSegmentationStrategy(ai_client=mock_client)
engine = SemanticSegmentationEngine(strategy=strategy)
metadata = {"title": "深度学习介绍", "duration": 12.0}
paragraphs = engine.segment(segments, metadata)
@@ -634,7 +643,7 @@ class TestArgumentCompleteness:
assert len(paragraphs) == 1
# Verify argument completeness - premise and conclusion together
first_para = paragraphs[0]
first_para = paragraphs[0].content
assert "首先" in first_para
assert "因此" in first_para
@@ -698,7 +707,8 @@ class TestParallelStructurePreservation:
mock_client.generate.return_value = mock_response
# Create engine and segment
engine = SemanticSegmentationEngine(ai_client=mock_client)
strategy = UnifiedSegmentationStrategy(ai_client=mock_client)
engine = SemanticSegmentationEngine(strategy=strategy)
metadata = {"title": "数据处理流程", "duration": 12.0}
paragraphs = engine.segment(segments, metadata)
@@ -706,9 +716,9 @@ class TestParallelStructurePreservation:
assert len(paragraphs) == 3
# Verify each parallel point is complete in its segment
assert "首先" in paragraphs[0]
assert "其次" in paragraphs[1]
assert "最后" in paragraphs[2]
assert "首先" in paragraphs[0].content
assert "其次" in paragraphs[1].content
assert "最后" in paragraphs[2].content
def test_no_special_handling_for_parallel_in_prompt(self):
"""Test: SEGMENTATION_PROMPT 不包含并列结构特殊处理