gahusb/web-page-backend
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(ai_news): pipeline uses articles_source (replaces Naver scraper)

Browse Source
This commit is contained in:
gahusb
2026-05-14 02:09:41 +09:00
parent ec0ccf649e
commit bbe5221e57
2 changed files with 97 additions and 71 deletions
Download Patch File Download Diff File Expand all files Collapse all files

99
stock-lab/tests/test_ai_news_pipeline.py
View File

@@ -26,12 +26,15 @@ def conn():
@pytest.mark.asyncio
async def test_refresh_daily_happy_path(conn):
"""3종목 mini integration — 각 종목별로 scraper/analyzer mock."""
"""3종목 mini integration — articles_source mock + analyzer mock."""
asof = dt.date(2026, 5, 13)
fake_news = [{"title": "헤드라인"}]
async def fake_fetch(client, ticker, n):
return fake_news
fake_articles_by_ticker = {
"005930": [{"title": "삼성 뉴스", "summary": "", "press": "", "pub_date": ""}],
"000660": [{"title": "SK 뉴스", "summary": "", "press": "", "pub_date": ""}],
"373220": [{"title": "LG 뉴스", "summary": "", "press": "", "pub_date": ""}],
}
fake_stats = {"total_articles": 3, "matched_pairs": 3, "hit_tickers": 3}
scores_by_ticker = {
"005930": 7.5, "000660": 4.0, "373220": -6.0,
@@ -43,43 +46,40 @@ async def test_refresh_daily_happy_path(conn):
"tokens_input": 100, "tokens_output": 20, "model": model,
}
with patch.object(pipeline, "_scraper") as ms, \
with patch.object(pipeline, "articles_source") as mas, \
patch.object(pipeline, "_analyzer") as ma, \
patch.object(pipeline, "_make_llm") as ml, \
patch.object(pipeline, "_make_http") as mh:
ms.fetch_news = fake_fetch
patch.object(pipeline, "_make_llm") as ml:
mas.gather_articles_for_tickers = MagicMock(
return_value=(fake_articles_by_ticker, fake_stats)
)
ma.score_sentiment = fake_score
ml.return_value.__aenter__.return_value = AsyncMock()
ml.return_value.__aexit__.return_value = None
mh.return_value.__aenter__.return_value = AsyncMock()
mh.return_value.__aexit__.return_value = None
result = await pipeline.refresh_daily(conn, asof, concurrency=3, rate_limit_sec=0)
result = await pipeline.refresh_daily(conn, asof, concurrency=3)
assert result["asof"] == "2026-05-13"
assert result["updated"] == 3
assert result["failures"] == []
assert len(result["top_pos"]) == 3
assert result["top_pos"][0]["ticker"] == "005930" # 가장 큰 점수
assert result["top_neg"][0]["ticker"] == "373220" # 가장 작은 점수
assert result["tokens_input"] == 300
assert result["tokens_output"] == 60
assert result["top_pos"][0]["ticker"] == "005930"
assert result["top_neg"][0]["ticker"] == "373220"
assert result["mapping"] == fake_stats
# DB upsert 확인
rows = conn.execute("SELECT ticker, score_raw FROM news_sentiment WHERE date=?",
("2026-05-13",)).fetchall()
rows = conn.execute("SELECT ticker, score_raw, source FROM news_sentiment "
"WHERE date=?", ("2026-05-13",)).fetchall()
assert len(rows) == 3
by_ticker = {r["ticker"]: r["score_raw"] for r in rows}
assert by_ticker["005930"] == 7.5
assert by_ticker["373220"] == -6.0
assert all(r["source"] == "articles" for r in rows)
@pytest.mark.asyncio
async def test_refresh_daily_failures_isolated(conn):
"""한 종목이 예외 던져도 나머지 종목은 정상 처리."""
asof = dt.date(2026, 5, 13)
async def fake_fetch(client, ticker, n):
return [{"title": "h"}]
fake_articles_by_ticker = {
"005930": [{"title": "h", "summary": "", "press": "", "pub_date": ""}],
"000660": [{"title": "h", "summary": "", "press": "", "pub_date": ""}],
"373220": [{"title": "h", "summary": "", "press": "", "pub_date": ""}],
}
fake_stats = {"total_articles": 3, "matched_pairs": 3, "hit_tickers": 3}
async def fake_score(llm, ticker, news, *, name=None, model="m"):
if ticker == "000660":
@@ -89,22 +89,57 @@ async def test_refresh_daily_failures_isolated(conn):
"tokens_input": 100, "tokens_output": 20, "model": model,
}
with patch.object(pipeline, "_scraper") as ms, \
with patch.object(pipeline, "articles_source") as mas, \
patch.object(pipeline, "_analyzer") as ma, \
patch.object(pipeline, "_make_llm") as ml, \
patch.object(pipeline, "_make_http") as mh:
ms.fetch_news = fake_fetch
patch.object(pipeline, "_make_llm") as ml:
mas.gather_articles_for_tickers = MagicMock(
return_value=(fake_articles_by_ticker, fake_stats)
)
ma.score_sentiment = fake_score
ml.return_value.__aenter__.return_value = AsyncMock()
ml.return_value.__aexit__.return_value = None
mh.return_value.__aenter__.return_value = AsyncMock()
mh.return_value.__aexit__.return_value = None
result = await pipeline.refresh_daily(conn, asof, concurrency=3, rate_limit_sec=0)
result = await pipeline.refresh_daily(conn, asof, concurrency=3)
assert result["updated"] == 2
assert len(result["failures"]) == 1
@pytest.mark.asyncio
async def test_refresh_daily_no_match_ticker_skipped(conn):
"""매핑 0인 ticker 는 LLM 호출 skip + news_sentiment 행 미생성."""
asof = dt.date(2026, 5, 13)
fake_articles_by_ticker = {
"005930": [{"title": "삼성", "summary": "", "press": "", "pub_date": ""}],
"000660": [], # 매핑 없음
"373220": [], # 매핑 없음
}
fake_stats = {"total_articles": 1, "matched_pairs": 1, "hit_tickers": 1}
async def fake_score(llm, ticker, news, *, name=None, model="m"):
return {
"ticker": ticker, "score_raw": 5.0, "reason": "r",
"news_count": 1, "tokens_input": 100, "tokens_output": 20,
"model": model,
}
with patch.object(pipeline, "articles_source") as mas, \
patch.object(pipeline, "_analyzer") as ma, \
patch.object(pipeline, "_make_llm") as ml:
mas.gather_articles_for_tickers = MagicMock(
return_value=(fake_articles_by_ticker, fake_stats)
)
ma.score_sentiment = fake_score
ml.return_value.__aenter__.return_value = AsyncMock()
ml.return_value.__aexit__.return_value = None
result = await pipeline.refresh_daily(conn, asof, concurrency=3)
assert result["updated"] == 1
rows = conn.execute("SELECT ticker FROM news_sentiment "
"WHERE date=?", ("2026-05-13",)).fetchall()
assert {r["ticker"] for r in rows} == {"005930"}
def test_top_market_cap_tickers(conn):
out = pipeline._top_market_cap_tickers(conn, n=2)
assert out == ["005930", "000660"]