|
1
|
"""Tests for content cross-referencing between transcript and diagram entities.""" |
|
2
|
|
|
3
|
import json |
|
4
|
from unittest.mock import MagicMock |
|
5
|
|
|
6
|
from video_processor.analyzers.content_analyzer import ContentAnalyzer |
|
7
|
from video_processor.models import Entity, KeyPoint |
|
8
|
|
|
9
|
|
|
10
|
class TestCrossReference: |
|
11
|
def test_exact_match_merges(self): |
|
12
|
analyzer = ContentAnalyzer() |
|
13
|
t_entities = [ |
|
14
|
Entity(name="Python", type="concept", descriptions=["A language"]), |
|
15
|
] |
|
16
|
d_entities = [ |
|
17
|
Entity(name="Python", type="concept", descriptions=["A snake-named lang"]), |
|
18
|
] |
|
19
|
result = analyzer.cross_reference(t_entities, d_entities) |
|
20
|
assert len(result) == 1 |
|
21
|
assert result[0].source == "both" |
|
22
|
assert "A language" in result[0].descriptions |
|
23
|
assert "A snake-named lang" in result[0].descriptions |
|
24
|
|
|
25
|
def test_case_insensitive_merge(self): |
|
26
|
analyzer = ContentAnalyzer() |
|
27
|
t_entities = [Entity(name="Docker", type="technology", descriptions=["Containers"])] |
|
28
|
d_entities = [Entity(name="docker", type="technology", descriptions=["Container runtime"])] |
|
29
|
result = analyzer.cross_reference(t_entities, d_entities) |
|
30
|
assert len(result) == 1 |
|
31
|
assert result[0].source == "both" |
|
32
|
|
|
33
|
def test_no_overlap_keeps_both(self): |
|
34
|
analyzer = ContentAnalyzer() |
|
35
|
t_entities = [Entity(name="Python", type="concept", descriptions=["Lang"])] |
|
36
|
d_entities = [Entity(name="Rust", type="concept", descriptions=["Systems"])] |
|
37
|
result = analyzer.cross_reference(t_entities, d_entities) |
|
38
|
assert len(result) == 2 |
|
39
|
names = {e.name for e in result} |
|
40
|
assert names == {"Python", "Rust"} |
|
41
|
|
|
42
|
def test_transcript_only(self): |
|
43
|
analyzer = ContentAnalyzer() |
|
44
|
t_entities = [Entity(name="Foo", type="concept")] |
|
45
|
result = analyzer.cross_reference(t_entities, []) |
|
46
|
assert len(result) == 1 |
|
47
|
assert result[0].source == "transcript" |
|
48
|
|
|
49
|
def test_diagram_only(self): |
|
50
|
analyzer = ContentAnalyzer() |
|
51
|
d_entities = [Entity(name="Bar", type="concept")] |
|
52
|
result = analyzer.cross_reference([], d_entities) |
|
53
|
assert len(result) == 1 |
|
54
|
assert result[0].source == "diagram" |
|
55
|
|
|
56
|
def test_empty_inputs(self): |
|
57
|
analyzer = ContentAnalyzer() |
|
58
|
result = analyzer.cross_reference([], []) |
|
59
|
assert result == [] |
|
60
|
|
|
61
|
def test_occurrences_merged(self): |
|
62
|
analyzer = ContentAnalyzer() |
|
63
|
t_entities = [ |
|
64
|
Entity(name="API", type="concept", occurrences=[{"source": "transcript", "ts": 10}]), |
|
65
|
] |
|
66
|
d_entities = [ |
|
67
|
Entity(name="API", type="concept", occurrences=[{"source": "diagram", "ts": 20}]), |
|
68
|
] |
|
69
|
result = analyzer.cross_reference(t_entities, d_entities) |
|
70
|
assert len(result) == 1 |
|
71
|
assert len(result[0].occurrences) == 2 |
|
72
|
|
|
73
|
|
|
74
|
class TestFuzzyMatch: |
|
75
|
def test_fuzzy_match_with_llm(self): |
|
76
|
pm = MagicMock() |
|
77
|
pm.chat.return_value = json.dumps( |
|
78
|
[ |
|
79
|
{"transcript": "K8s", "diagram": "Kubernetes"}, |
|
80
|
] |
|
81
|
) |
|
82
|
analyzer = ContentAnalyzer(provider_manager=pm) |
|
83
|
|
|
84
|
t_entities = [ |
|
85
|
Entity(name="K8s", type="technology", descriptions=["Container orchestration"]), |
|
86
|
] |
|
87
|
d_entities = [ |
|
88
|
Entity(name="Kubernetes", type="technology", descriptions=["K8s system"]), |
|
89
|
] |
|
90
|
result = analyzer.cross_reference(t_entities, d_entities) |
|
91
|
|
|
92
|
# Fuzzy match should merge these |
|
93
|
assert len(result) == 1 |
|
94
|
assert result[0].source == "both" |
|
95
|
assert result[0].name == "K8s" |
|
96
|
|
|
97
|
def test_fuzzy_match_no_matches(self): |
|
98
|
pm = MagicMock() |
|
99
|
pm.chat.return_value = "[]" |
|
100
|
analyzer = ContentAnalyzer(provider_manager=pm) |
|
101
|
|
|
102
|
t_entities = [Entity(name="Alpha", type="concept")] |
|
103
|
d_entities = [Entity(name="Beta", type="concept")] |
|
104
|
result = analyzer.cross_reference(t_entities, d_entities) |
|
105
|
assert len(result) == 2 |
|
106
|
|
|
107
|
def test_fuzzy_match_llm_error(self): |
|
108
|
pm = MagicMock() |
|
109
|
pm.chat.side_effect = Exception("API error") |
|
110
|
analyzer = ContentAnalyzer(provider_manager=pm) |
|
111
|
|
|
112
|
t_entities = [Entity(name="X", type="concept")] |
|
113
|
d_entities = [Entity(name="Y", type="concept")] |
|
114
|
result = analyzer.cross_reference(t_entities, d_entities) |
|
115
|
# Should still return both entities despite error |
|
116
|
assert len(result) == 2 |
|
117
|
|
|
118
|
def test_fuzzy_match_bad_json(self): |
|
119
|
pm = MagicMock() |
|
120
|
pm.chat.return_value = "not json at all" |
|
121
|
analyzer = ContentAnalyzer(provider_manager=pm) |
|
122
|
|
|
123
|
t_entities = [Entity(name="A", type="concept")] |
|
124
|
d_entities = [Entity(name="B", type="concept")] |
|
125
|
result = analyzer.cross_reference(t_entities, d_entities) |
|
126
|
assert len(result) == 2 |
|
127
|
|
|
128
|
def test_fuzzy_match_skipped_without_provider(self): |
|
129
|
analyzer = ContentAnalyzer() |
|
130
|
t_entities = [Entity(name="ML", type="concept")] |
|
131
|
d_entities = [Entity(name="Machine Learning", type="concept")] |
|
132
|
result = analyzer.cross_reference(t_entities, d_entities) |
|
133
|
# No LLM so no fuzzy matching — both remain separate |
|
134
|
assert len(result) == 2 |
|
135
|
|
|
136
|
def test_fuzzy_match_skipped_when_all_exact(self): |
|
137
|
pm = MagicMock() |
|
138
|
analyzer = ContentAnalyzer(provider_manager=pm) |
|
139
|
|
|
140
|
t_entities = [Entity(name="Same", type="concept")] |
|
141
|
d_entities = [Entity(name="Same", type="concept")] |
|
142
|
result = analyzer.cross_reference(t_entities, d_entities) |
|
143
|
# All matched exactly — no fuzzy match call needed |
|
144
|
pm.chat.assert_not_called() |
|
145
|
assert len(result) == 1 |
|
146
|
|
|
147
|
|
|
148
|
class TestEnrichKeyPoints: |
|
149
|
def test_enriches_with_matching_diagrams(self): |
|
150
|
analyzer = ContentAnalyzer() |
|
151
|
kps = [ |
|
152
|
KeyPoint(point="The deployment pipeline uses Docker containers"), |
|
153
|
] |
|
154
|
diagrams = [ |
|
155
|
{"elements": ["Docker", "Pipeline", "Build"], "text_content": "CI/CD flow"}, |
|
156
|
] |
|
157
|
result = analyzer.enrich_key_points(kps, diagrams, "") |
|
158
|
assert len(result) == 1 |
|
159
|
assert result[0].related_diagrams == [0] |
|
160
|
|
|
161
|
def test_no_match_below_threshold(self): |
|
162
|
analyzer = ContentAnalyzer() |
|
163
|
kps = [ |
|
164
|
KeyPoint(point="Meeting scheduled for Friday"), |
|
165
|
] |
|
166
|
diagrams = [ |
|
167
|
{"elements": ["Docker", "Pipeline"], "text_content": "Architecture diagram"}, |
|
168
|
] |
|
169
|
result = analyzer.enrich_key_points(kps, diagrams, "") |
|
170
|
assert result[0].related_diagrams == [] |
|
171
|
|
|
172
|
def test_empty_diagrams_returns_unchanged(self): |
|
173
|
analyzer = ContentAnalyzer() |
|
174
|
kps = [KeyPoint(point="Test point")] |
|
175
|
result = analyzer.enrich_key_points(kps, [], "") |
|
176
|
assert len(result) == 1 |
|
177
|
assert result[0].related_diagrams == [] |
|
178
|
|
|
179
|
def test_multiple_diagram_matches(self): |
|
180
|
analyzer = ContentAnalyzer() |
|
181
|
kps = [ |
|
182
|
KeyPoint(point="Database migration requires testing schema changes"), |
|
183
|
] |
|
184
|
diagrams = [ |
|
185
|
{"elements": ["Database", "Schema", "Migration"], "text_content": ""}, |
|
186
|
{"elements": ["Testing", "Schema", "Validation"], "text_content": ""}, |
|
187
|
] |
|
188
|
result = analyzer.enrich_key_points(kps, diagrams, "") |
|
189
|
assert len(result[0].related_diagrams) == 2 |
|
190
|
|
|
191
|
def test_details_used_for_matching(self): |
|
192
|
analyzer = ContentAnalyzer() |
|
193
|
kps = [ |
|
194
|
KeyPoint( |
|
195
|
point="Architecture overview", details="Uses Docker and Kubernetes for deployment" |
|
196
|
), |
|
197
|
] |
|
198
|
diagrams = [ |
|
199
|
{"elements": ["Docker", "Kubernetes"], "text_content": "deployment infrastructure"}, |
|
200
|
] |
|
201
|
result = analyzer.enrich_key_points(kps, diagrams, "") |
|
202
|
assert 0 in result[0].related_diagrams |
|
203
|
|
|
204
|
def test_diagram_as_object_with_attrs(self): |
|
205
|
analyzer = ContentAnalyzer() |
|
206
|
|
|
207
|
class FakeDiagram: |
|
208
|
elements = ["Alpha", "Beta"] |
|
209
|
text_content = "some relevant content" |
|
210
|
|
|
211
|
kps = [KeyPoint(point="Alpha Beta interaction patterns")] |
|
212
|
result = analyzer.enrich_key_points(kps, [FakeDiagram()], "") |
|
213
|
assert result[0].related_diagrams == [0] |
|
214
|
|