123 lines
3.3 KiB
Python
123 lines
3.3 KiB
Python
from evanescere.schemas import ClipCandidate
|
|
from evanescere.services.llm import (
|
|
TranscriptChunk,
|
|
candidate_quota_per_chunk,
|
|
dedupe_and_rank_candidates,
|
|
parse_clip_response,
|
|
render_user_prompt,
|
|
)
|
|
|
|
|
|
def test_parse_clip_response():
|
|
candidates = parse_clip_response(
|
|
"""
|
|
{
|
|
"clips": [
|
|
{
|
|
"start_sec": 10,
|
|
"end_sec": 60,
|
|
"title_zh": "标题",
|
|
"summary_zh": "摘要",
|
|
"reason": "有趣",
|
|
"score": 0.9,
|
|
"tags": ["反应"],
|
|
"subtitle_priority": "high"
|
|
}
|
|
]
|
|
}
|
|
"""
|
|
)
|
|
assert candidates[0].title_zh == "标题"
|
|
|
|
|
|
def test_dedupe_and_rank_candidates_filters_short_and_overlapping():
|
|
candidates = [
|
|
ClipCandidate(
|
|
start_sec=0,
|
|
end_sec=20,
|
|
title_zh="too short",
|
|
summary_zh="",
|
|
reason="",
|
|
score=1,
|
|
),
|
|
ClipCandidate(
|
|
start_sec=0,
|
|
end_sec=60,
|
|
title_zh="best",
|
|
summary_zh="",
|
|
reason="",
|
|
score=0.9,
|
|
),
|
|
ClipCandidate(
|
|
start_sec=10,
|
|
end_sec=65,
|
|
title_zh="overlap",
|
|
summary_zh="",
|
|
reason="",
|
|
score=0.8,
|
|
),
|
|
ClipCandidate(
|
|
start_sec=120,
|
|
end_sec=180,
|
|
title_zh="second",
|
|
summary_zh="",
|
|
reason="",
|
|
score=0.7,
|
|
),
|
|
]
|
|
ranked = dedupe_and_rank_candidates(candidates)
|
|
assert [candidate.title_zh for candidate in ranked] == ["best", "second"]
|
|
|
|
|
|
def test_candidate_quota_uses_total_budget_across_chunks():
|
|
assert candidate_quota_per_chunk(1, 20) == 20
|
|
assert candidate_quota_per_chunk(4, 20) == 5
|
|
assert candidate_quota_per_chunk(0, 20) == 0
|
|
|
|
|
|
def test_dedupe_respects_configured_duration_and_total_cap():
|
|
candidates = [
|
|
ClipCandidate(
|
|
start_sec=index * 240,
|
|
end_sec=index * 240 + duration,
|
|
title_zh=f"clip-{index}",
|
|
summary_zh="",
|
|
reason="",
|
|
score=1 - index / 100,
|
|
)
|
|
for index, duration in enumerate([60, 180, 181, 90])
|
|
]
|
|
ranked = dedupe_and_rank_candidates(
|
|
candidates,
|
|
min_clip_seconds=30,
|
|
max_clip_seconds=180,
|
|
max_candidates_total=2,
|
|
)
|
|
assert [candidate.title_zh for candidate in ranked] == ["clip-0", "clip-1"]
|
|
|
|
|
|
def test_render_user_prompt_inserts_configured_values():
|
|
prompt = render_user_prompt(
|
|
"{max_candidates}|{min_clip_seconds}|{max_clip_seconds}|{chunk_start_sec}|{chunk_end_sec}|{transcript}",
|
|
chunk=TranscriptChunk(12.25, 42.75, "hello"),
|
|
max_candidates=20,
|
|
min_clip_seconds=30,
|
|
max_clip_seconds=180,
|
|
)
|
|
assert prompt == "20|30|180|12.2|42.8|hello"
|
|
|
|
|
|
def test_render_user_prompt_rejects_unknown_placeholder():
|
|
try:
|
|
render_user_prompt(
|
|
"{unknown}",
|
|
chunk=TranscriptChunk(0, 1, "hello"),
|
|
max_candidates=20,
|
|
min_clip_seconds=30,
|
|
max_clip_seconds=180,
|
|
)
|
|
except ValueError as exc:
|
|
assert "Unknown placeholder" in str(exc)
|
|
else:
|
|
raise AssertionError("Expected unknown placeholder to fail")
|