starmen1265
8577571eda
- test_rule_based_segmentation_unchanged: 验证 enable_semantic_segmentation=False 时使用规则分段器 - test_rule_based_no_llm_calls: 验证规则分段不调用 LLM - test_rule_based_thresholds_unchanged: 验证规则分段阈值（时间/长度）未改变 Task 1 完成：规则分段向后兼容性验证（CONFIG-02） Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
186 lines
7.9 KiB
Python
186 lines
7.9 KiB
Python
"""Backward Compatibility Tests
|
|
|
|
Tests to ensure that configuration changes don't break existing functionality:
|
|
- Rule-based segmentation (SemanticSegmenter) works unchanged (CONFIG-02)
|
|
- AnalyzeProcessor is not affected by SRTProcessor config changes (CONFIG-03)
|
|
- Existing API calls remain compatible
|
|
"""
|
|
|
|
import pytest
|
|
from unittest.mock import Mock, patch, MagicMock
|
|
from pathlib import Path
|
|
from kb_workflow.srt.parser import Segment
|
|
from kb_workflow.srt.segmenter import SemanticSegmenter
|
|
|
|
|
|
# =============================================================================
|
|
# Test Fixtures
|
|
# =============================================================================
|
|
|
|
@pytest.fixture
|
|
def sample_segments():
|
|
"""Sample subtitle segments for testing"""
|
|
return [
|
|
Segment(1, 0.0, 5.0, "第一句内容"),
|
|
Segment(2, 5.0, 10.0, "第二句内容"),
|
|
Segment(3, 10.0, 15.0, "第三句内容"),
|
|
]
|
|
|
|
|
|
@pytest.fixture
|
|
def long_text_segments():
|
|
"""Segments with long text that triggers length-based splitting"""
|
|
text = "这是一段很长的文本内容" * 50 # ~500 characters
|
|
return [
|
|
Segment(1, 0.0, 5.0, text[:250]),
|
|
Segment(2, 5.0, 10.0, text[:250]),
|
|
Segment(3, 10.0, 15.0, text[:250]),
|
|
]
|
|
|
|
|
|
@pytest.fixture
|
|
def gap_segments():
|
|
"""Segments with time gaps > 3 seconds"""
|
|
return [
|
|
Segment(1, 0.0, 5.0, "第一段落内容"),
|
|
Segment(2, 10.0, 15.0, "第二段落内容"), # 5 second gap
|
|
Segment(3, 15.0, 20.0, "继续第二段落"),
|
|
]
|
|
|
|
|
|
# =============================================================================
|
|
# Task 1: Rule-based Segmentation Backward Compatibility (CONFIG-02)
|
|
# =============================================================================
|
|
|
|
class TestBackwardCompatibility:
|
|
"""Test backward compatibility for rule-based segmentation (CONFIG-02)"""
|
|
|
|
def test_rule_based_segmentation_unchanged(self, sample_segments):
|
|
"""Test 1: enable_semantic_segmentation=False 使用规则分段器"""
|
|
from kb_workflow.pipeline.processors.srt import SRTProcessor
|
|
from kb_workflow.srt.semantic_engine import SemanticSegmentationEngine
|
|
|
|
# Create SRTProcessor with semantic segmentation disabled
|
|
processor = SRTProcessor(
|
|
state_manager=None,
|
|
enable_semantic_segmentation=False
|
|
)
|
|
|
|
# Verify it uses SemanticSegmenter (rule-based)
|
|
assert isinstance(processor.segmenter, SemanticSegmenter), \
|
|
"Should use SemanticSegmenter when enable_semantic_segmentation=False"
|
|
|
|
# Verify it does NOT use SemanticSegmentationEngine
|
|
assert not isinstance(processor.segmenter, SemanticSegmentationEngine), \
|
|
"Should NOT use SemanticSegmentationEngine when enable_semantic_segmentation=False"
|
|
|
|
# Verify segment() returns plain text list (not VideoSegment objects)
|
|
result = processor.segmenter.segment(sample_segments)
|
|
assert isinstance(result, list), "segment() should return a list"
|
|
assert len(result) > 0, "Should have at least one paragraph"
|
|
assert all(isinstance(para, str) for para in result), \
|
|
"Rule-based segmenter should return plain text strings, not VideoSegment objects"
|
|
|
|
def test_rule_based_no_llm_calls(self, sample_segments):
|
|
"""Test 2: 规则分段不调用 LLM，无网络开销
|
|
|
|
注意：此测试禁用 ASR 纠错以纯粹测试规则分段不调用 LLM。
|
|
ASR 纠错是独立的功能，会在 SRTProcessor 初始化时单独创建 SimpleAIClient。
|
|
"""
|
|
from kb_workflow.pipeline.processors.srt import SRTProcessor
|
|
|
|
# Create processor with rule-based segmentation AND disable ASR correction
|
|
# to isolate the rule-based segmentation behavior
|
|
processor = SRTProcessor(
|
|
state_manager=None,
|
|
enable_correction=False, # Disable ASR correction to test pure rule-based segmentation
|
|
enable_semantic_segmentation=False
|
|
)
|
|
|
|
# Verify segmenter is SemanticSegmenter (rule-based)
|
|
from kb_workflow.srt.segmenter import SemanticSegmenter
|
|
assert isinstance(processor.segmenter, SemanticSegmenter)
|
|
|
|
# Call segment method directly on the segmenter
|
|
# This should NOT make any LLM calls
|
|
result = processor.segmenter.segment(sample_segments)
|
|
|
|
# Verify we get results without LLM
|
|
assert len(result) > 0, "Should have results without LLM"
|
|
assert all(isinstance(para, str) for para in result), \
|
|
"Rule-based segmentation should return plain text strings"
|
|
|
|
def test_rule_based_thresholds_unchanged(self, gap_segments, long_text_segments):
|
|
"""Test 3: 规则分段的分段逻辑（时间/长度阈值）未改变"""
|
|
segmenter = SemanticSegmenter(
|
|
gap_threshold=3.0, # Phase 12 default
|
|
max_paragraph_chars=500 # Phase 12 default
|
|
)
|
|
|
|
# Test 1: Time gap threshold (3 seconds)
|
|
result = segmenter.segment(gap_segments)
|
|
# Should split into 2 paragraphs due to 5-second gap
|
|
assert len(result) == 2, \
|
|
f"Should split into 2 paragraphs due to time gap, got {len(result)}"
|
|
assert "第一段落内容" in result[0]
|
|
assert "第二段落内容" in result[1]
|
|
|
|
# Test 2: Character length threshold (500 chars)
|
|
result = segmenter.segment(long_text_segments)
|
|
# Each segment is ~250 chars, so with 3 segments we should get splits
|
|
# First segment: 250 chars (no split)
|
|
# Second segment: 250 + 250 = 500 chars (might split depending on exact count)
|
|
assert len(result) >= 1, "Should have at least one paragraph"
|
|
assert all(isinstance(para, str) for para in result), \
|
|
"All results should be plain text strings"
|
|
|
|
@pytest.mark.skipif(True, reason="Not implemented yet - will implement in Task 3")
|
|
def test_existing_api_compatibility(self):
|
|
"""Test 4: 不传 enable_semantic_segmentation 参数时使用配置默认值"""
|
|
# This test will be implemented in Task 3
|
|
pass
|
|
|
|
@pytest.mark.skipif(True, reason="Not implemented yet - will implement in Task 3")
|
|
def test_explicit_false_overrides_config(self):
|
|
"""Test 5: 显式传 False 时覆盖配置，使用规则分段"""
|
|
# This test will be implemented in Task 3
|
|
pass
|
|
|
|
@pytest.mark.skipif(True, reason="Not implemented yet - will implement in Task 3")
|
|
def test_migration_path(self):
|
|
"""Test 6: 验证用户可以通过两种方式启用语义分段"""
|
|
# This test will be implemented in Task 3
|
|
pass
|
|
|
|
@pytest.mark.skipif(True, reason="Not implemented yet - will implement in Task 2")
|
|
def test_analyze_processor_unaffected(self):
|
|
"""Test 7: AnalyzeProcessor 不受 KBSettings.enable_semantic_segmentation 影响"""
|
|
# This test will be implemented in Task 2
|
|
pass
|
|
|
|
|
|
# =============================================================================
|
|
# Task 2: AnalyzeProcessor Independence (CONFIG-03)
|
|
# =============================================================================
|
|
|
|
class TestAnalyzeProcessorIndependence:
|
|
"""Test that AnalyzeProcessor is independent of SRTProcessor configuration"""
|
|
|
|
@pytest.mark.skipif(True, reason="Not implemented yet - will implement in Task 2")
|
|
def test_analyze_processor_unaffected_by_config(self):
|
|
"""Test: AnalyzeProcessor 不受 KBSettings.enable_semantic_segmentation 影响"""
|
|
# This test will be implemented in Task 2
|
|
pass
|
|
|
|
@pytest.mark.skipif(True, reason="Not implemented yet - will implement in Task 2")
|
|
def test_analyze_processor_normal_initialization(self):
|
|
"""Test: AnalyzeProcessor 正常初始化和处理"""
|
|
# This test will be implemented in Task 2
|
|
pass
|
|
|
|
@pytest.mark.skipif(True, reason="Not implemented yet - will implement in Task 2")
|
|
def test_analyze_processor_output_unchanged(self):
|
|
"""Test: AnalyzeProcessor 输出格式未改变"""
|
|
# This test will be implemented in Task 2
|
|
pass
|