Files
dl-organizer/tests/test_enrichment.py
T

172 lines
5.0 KiB
Python
Raw Normal View History

"""Unit tests for enrichment pipeline."""
from vlm.config import Config
from vlm.enrichment import enrich_identities_data
from vlm.providers.base import ProviderResult
class DummyProvider:
name = "dummy"
def __init__(self):
self.calls = 0
def enrich(self, *, title: str, media_type: str, year=None):
self.calls += 1
return ProviderResult(
provider="dummy",
canonical_id=f"dummy:{title}",
title_zh="测试中文名",
title_en="Test English Title",
translation_source="dummy",
reputation_score=8.2,
reputation_votes=100,
reputation_source="dummy",
)
def test_enrich_incremental_cache_hit(tmp_path, monkeypatch):
"""Second enrichment run should hit cache when fingerprint is unchanged."""
config = Config(
library_root=tmp_path,
enrichment_cache_db=tmp_path / "cache.db",
enrichment_providers=["dummy"],
translation_fallback_machine=False,
)
provider = DummyProvider()
monkeypatch.setattr(
"vlm.enrichment._build_providers",
lambda _config, request_timeout, retries: [provider],
)
identities = {
"metadata": {},
"movies": [
{
"path": "/library/movie/The.Matrix.1999.mkv",
"filename": "The.Matrix.1999.mkv",
"category": "movie",
"title": "The Matrix",
"year": 1999,
"confidence": 0.9,
"needs_review": False,
}
],
"series": [],
"anime": [],
"other": [],
}
_, stats_first = enrich_identities_data(identities, config)
assert stats_first["enriched"] == 1
assert stats_first["cache_hits"] == 0
assert stats_first["api_calls"] == 1
assert provider.calls == 1
_, stats_second = enrich_identities_data(identities, config)
assert stats_second["cache_hits"] == 1
assert stats_second["api_calls"] == 0
assert provider.calls == 1
movie = identities["movies"][0]
assert movie["title_zh"] == "测试中文名"
assert movie["title_en"] == "Test English Title"
assert movie["display_title"] == "测试中文名 Test English Title"
def test_enrich_flags_low_reputation_for_review(tmp_path, monkeypatch):
"""Low reputation should set needs_review when vote count is high enough."""
class LowScoreProvider(DummyProvider):
def enrich(self, *, title: str, media_type: str, year=None):
self.calls += 1
return ProviderResult(
provider="dummy",
canonical_id=f"dummy:{title}",
title_zh="低分作品",
title_en="Low Score",
translation_source="dummy",
reputation_score=4.5,
reputation_votes=500,
reputation_source="dummy",
)
config = Config(
library_root=tmp_path,
enrichment_cache_db=tmp_path / "cache.db",
enrichment_providers=["dummy"],
translation_fallback_machine=False,
reputation_low_score_threshold=6.0,
reputation_min_votes=50,
)
provider = LowScoreProvider()
monkeypatch.setattr(
"vlm.enrichment._build_providers",
lambda _config, request_timeout, retries: [provider],
)
identities = {
"metadata": {},
"movies": [
{
"path": "/library/movie/Unknown.2020.mkv",
"filename": "Unknown.2020.mkv",
"category": "movie",
"title": "Unknown",
"year": 2020,
"confidence": 0.9,
"needs_review": False,
}
],
"series": [],
"anime": [],
"other": [],
}
enrich_identities_data(identities, config)
assert identities["movies"][0]["needs_review"] is True
def test_enrich_refresh_all_bypasses_cache(tmp_path, monkeypatch):
"""refresh_all should not use cache and should invoke provider again."""
config = Config(
library_root=tmp_path,
enrichment_cache_db=tmp_path / "cache.db",
enrichment_providers=["dummy"],
translation_fallback_machine=False,
)
provider = DummyProvider()
monkeypatch.setattr(
"vlm.enrichment._build_providers",
lambda _config, request_timeout, retries: [provider],
)
identities = {
"metadata": {},
"movies": [
{
"path": "/library/movie/Test.2020.mkv",
"filename": "Test.2020.mkv",
"category": "movie",
"title": "Test",
"year": 2020,
"confidence": 0.9,
"needs_review": False,
}
],
"series": [],
"anime": [],
"other": [],
}
enrich_identities_data(identities, config, refresh_mode="incremental")
assert provider.calls == 1
_, stats = enrich_identities_data(identities, config, refresh_mode="refresh_all")
assert provider.calls == 2
assert stats["cache_hits"] == 0