66 lines
2.0 KiB
Python
66 lines
2.0 KiB
Python
import os
|
|
import tempfile
|
|
from unittest.mock import patch, MagicMock
|
|
|
|
import pytest
|
|
|
|
from app import db as db_module
|
|
from app import keyword_extractor
|
|
|
|
|
|
@pytest.fixture
|
|
def tmp_db(monkeypatch):
|
|
fd, path = tempfile.mkstemp(suffix=".db")
|
|
os.close(fd)
|
|
monkeypatch.setattr(db_module, "DB_PATH", path)
|
|
db_module.init_db()
|
|
yield path
|
|
# Windows-safe cleanup: close handles + remove sidecars
|
|
import gc
|
|
gc.collect()
|
|
for ext in ("", "-wal", "-shm"):
|
|
try:
|
|
os.remove(path + ext)
|
|
except OSError:
|
|
pass
|
|
|
|
|
|
def test_count_nouns_extracts_korean_nouns():
|
|
text = "기준금리 인상으로 환율 급등. 기준금리 추가 인상 가능성"
|
|
counts = keyword_extractor._count_nouns(text)
|
|
assert counts["기준금리"] == 2
|
|
assert counts["환율"] == 1
|
|
|
|
|
|
def test_top_candidates_filters_stopwords():
|
|
counts = {"기준금리": 5, "있다": 7, "환율": 3, "그리고": 4}
|
|
top = keyword_extractor._top_candidates(counts, n=10)
|
|
keywords = [k for k, _ in top]
|
|
assert "있다" not in keywords
|
|
assert "그리고" not in keywords
|
|
assert "기준금리" in keywords
|
|
|
|
|
|
def test_extract_for_category_persists(tmp_db):
|
|
# seed articles
|
|
for i in range(3):
|
|
db_module.add_news_article({
|
|
"category": "economy",
|
|
"title": f"기준금리 인상 {i}",
|
|
"link": f"https://example.com/{i}",
|
|
"summary": "환율도 영향",
|
|
})
|
|
|
|
# mock LLM refinement
|
|
fake_refined = [
|
|
{"keyword": "기준금리", "score": 0.92, "reason": "핵심 금융 이슈"},
|
|
{"keyword": "환율", "score": 0.71, "reason": "시장 영향"},
|
|
]
|
|
with patch.object(keyword_extractor, "_refine_with_llm", return_value=fake_refined):
|
|
kws = keyword_extractor.extract_for_category("economy", limit=2)
|
|
|
|
assert len(kws) == 2
|
|
assert kws[0]["keyword"] == "기준금리"
|
|
persisted = db_module.list_trending_keywords(category="economy")
|
|
assert {p["keyword"] for p in persisted} == {"기준금리", "환율"}
|