perf(realestate): run_listing_matching 단일 conn+배치 + POST /listings/rematch(MOLIT없이 즉시 재판정)

- get_market_deals_for에 optional conn 파라미터 추가(재사용 시 open/close 안 함, 기존 단건 호출부는 불변) - bulk_upsert_listing_matches 추가(listing_matches 다건 upsert, 단일 connection) - run_listing_matching이 listings 조회+매물별 market_deals 조회+최종 upsert를 단일 _conn()으로 처리 (기존: 269건 매물마다 개별 _conn() 3회 → 병목) - POST /api/realestate/listings/rematch: MOLIT 재수집 없이 기존 listings+market_deals로 즉시 재판정 (알림 미발송, 즉시 피드백용) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01EqCYBhvTcdeCTUDX3RhWx9
2026-07-10 13:56:45 +09:00
parent b471d2c455
commit 4097c95286
6 changed files with 230 additions and 33 deletions
--- a/realestate-lab/app/db.py
+++ b/realestate-lab/app/db.py
@@ -1019,10 +1019,14 @@ def bulk_upsert_market_deals(rows: List[Dict[str, Any]]) -> int:
    return len(payload)


-def get_market_deals_for(dong_code, complex_name, area, deal_type, months=6) -> List[Dict[str, Any]]:
-    with _conn() as conn:
+def get_market_deals_for(dong_code, complex_name, area, deal_type, months=6, conn=None) -> List[Dict[str, Any]]:
+    """conn을 넘기면 재사용(open/close 안 함, 호출부가 소유) — run_listing_matching 단일 conn 배치용.
+    conn 없으면 기존대로 자체 _conn() 열고 닫음(safety-check 등 단건 호출 경로 불변)."""
+    own = conn is None
+    c = conn or _conn()
+    try:
        def _query(cn):
-            rows = conn.execute(
+            rows = c.execute(
                """SELECT * FROM market_deals
                   WHERE dong_code=? AND deal_type=?
                     AND (complex_name=? OR ? IS NULL OR complex_name IS NULL)
@@ -1038,7 +1042,10 @@ def get_market_deals_for(dong_code, complex_name, area, deal_type, months=6) ->
            # 단지 표본이 부족하면 complex 제약을 풀고 같은 동/거래유형/면적±5/최근성으로
            # 광역 재조회한다. 표본을 늘리기만 하므로 안전(잘못된 판정 유발 X).
            deals = _query(None)
-    return deals
+        return deals
+    finally:
+        if own:
+            c.close()


 def upsert_listing_match(data: Dict[str, Any]) -> None:
@@ -1061,6 +1068,39 @@ def upsert_listing_match(data: Dict[str, Any]) -> None:
        """, d)


+def bulk_upsert_listing_matches(recs: List[Dict[str, Any]], conn=None) -> None:
+    """listing_matches 다건 upsert(단일 connection). conn 주면 재사용(호출부 with가 commit) —
+    run_listing_matching 269건×3conn 병목 개선(Task 2). ON CONFLICT 절은 upsert_listing_match와 동일
+    (notified_at 미포함=보존, 재알림 방지)."""
+    if not recs:
+        return
+    cols = ("listing_id", "category", "passed", "match_score", "jeonse_ratio", "safety_tier",
+            "price_ratio", "valuation_tier", "market_median", "sample_size", "budget_ok",
+            "regulation_flags", "reasons", "is_new")
+    own = conn is None
+    c = conn or _conn()
+    try:
+        for data in recs:
+            d = {col: data.get(col) for col in cols}
+            d["regulation_flags"] = json.dumps(data.get("regulation_flags") or [], ensure_ascii=False)
+            d["reasons"] = json.dumps(data.get("reasons") or [], ensure_ascii=False)
+            c.execute(f"""
+                INSERT INTO listing_matches ({','.join(cols)}) VALUES ({','.join(':'+col for col in cols)})
+                ON CONFLICT(listing_id) DO UPDATE SET
+                  passed=excluded.passed, match_score=excluded.match_score,
+                  jeonse_ratio=excluded.jeonse_ratio, safety_tier=excluded.safety_tier,
+                  price_ratio=excluded.price_ratio, valuation_tier=excluded.valuation_tier,
+                  market_median=excluded.market_median, sample_size=excluded.sample_size,
+                  budget_ok=excluded.budget_ok, regulation_flags=excluded.regulation_flags,
+                  reasons=excluded.reasons, category=excluded.category
+            """, d)
+        if own:
+            c.commit()
+    finally:
+        if own:
+            c.close()
+
+
 def get_listings(dong=None, deal_type=None, tier=None, matched_only=False, limit=50, offset=0) -> List[Dict[str, Any]]:
    sql = ("SELECT l.*, m.safety_tier, m.valuation_tier, m.category, m.match_score, m.passed "
           "FROM listings l LEFT JOIN listing_matches m ON m.listing_id=l.id WHERE 1=1")
--- a/realestate-lab/app/listing_matcher.py
+++ b/realestate-lab/app/listing_matcher.py
@@ -2,8 +2,8 @@
 import logging
 import statistics

-from .db import (get_listing_criteria, get_market_deals_for, upsert_listing_match,
-                 get_listings)
+from .db import (get_listing_criteria, get_market_deals_for, bulk_upsert_listing_matches,
+                 _conn)
 from . import finance_rules

 logger = logging.getLogger("realestate-lab")
@@ -74,37 +74,47 @@ def match_listing(criteria, listing, budget) -> dict:


 def run_listing_matching() -> None:
-    """미평가 포함 전체 매물 재평가 → listing_matches upsert (청약 run_matching 대칭)."""
+    """미평가 포함 전체 매물 재평가 → listing_matches upsert (청약 run_matching 대칭).
+    listings 조회 + 매물별 market_deals 조회 + 최종 upsert를 단일 connection으로 처리
+    (Task 2 성능개선: 이전엔 매물마다 get_market_deals_for/upsert_listing_match가 각각
+    자체 _conn()을 열어 269건×~3conn이 발생했다)."""
    criteria = get_listing_criteria()
    equity = criteria.get("equity") or 0
    income = criteria.get("annual_income") or 0
    jeonse_budget = finance_rules.estimate_jeonse_budget(equity, income)
-    for l in get_listings(limit=1000):
-        is_rent = l["deal_type"] != "매매"
-        reg = finance_rules.region_regulation(l.get("dong"))
-        if is_rent:
-            budget = jeonse_budget
-        else:
-            budget = finance_rules.estimate_purchase_budget(
-                equity, income, reg, criteria.get("is_first_home"), criteria.get("is_homeless"))
-        m = match_listing(criteria, l, budget)
-        deals = get_market_deals_for(l.get("dong_code"), l.get("complex_name"),
-                                     l.get("area_exclusive"), "전세" if is_rent else "매매")
-        rec = {"listing_id": l["id"], "category": "임차" if is_rent else "매매",
-               "passed": 1 if m["passed"] else 0, "match_score": m["score"],
-               "sample_size": 0, "reasons": m["reasons"], "is_new": 1,
-               "regulation_flags": reg_flags(reg)}
-        if is_rent:
-            s = compute_safety(l.get("deposit"), l["deal_type"], deals)
-            rec.update({"jeonse_ratio": s["jeonse_ratio"], "safety_tier": s["tier"],
-                        "market_median": s["median"], "sample_size": s["sample"]})
-        else:
-            v = compute_valuation(l.get("sale_price"), deals)
-            rec.update({"price_ratio": v["price_ratio"], "valuation_tier": v["tier"],
-                        "market_median": v["median"], "sample_size": v["sample"],
-                        "budget_ok": 1 if (l.get("sale_price") or 0) <= (budget.get("max_price") or 0) else 0})
-        upsert_listing_match(rec)
-    logger.info("매물 매칭 완료")
+    with _conn() as conn:
+        listings = [dict(r) for r in conn.execute(
+            "SELECT * FROM listings ORDER BY created_at DESC LIMIT 1000"
+        ).fetchall()]
+        recs = []
+        for l in listings:
+            is_rent = l["deal_type"] != "매매"
+            reg = finance_rules.region_regulation(l.get("dong"))
+            if is_rent:
+                budget = jeonse_budget
+            else:
+                budget = finance_rules.estimate_purchase_budget(
+                    equity, income, reg, criteria.get("is_first_home"), criteria.get("is_homeless"))
+            m = match_listing(criteria, l, budget)
+            deals = get_market_deals_for(l.get("dong_code"), l.get("complex_name"),
+                                         l.get("area_exclusive"), "전세" if is_rent else "매매",
+                                         conn=conn)
+            rec = {"listing_id": l["id"], "category": "임차" if is_rent else "매매",
+                   "passed": 1 if m["passed"] else 0, "match_score": m["score"],
+                   "sample_size": 0, "reasons": m["reasons"], "is_new": 1,
+                   "regulation_flags": reg_flags(reg)}
+            if is_rent:
+                s = compute_safety(l.get("deposit"), l["deal_type"], deals)
+                rec.update({"jeonse_ratio": s["jeonse_ratio"], "safety_tier": s["tier"],
+                            "market_median": s["median"], "sample_size": s["sample"]})
+            else:
+                v = compute_valuation(l.get("sale_price"), deals)
+                rec.update({"price_ratio": v["price_ratio"], "valuation_tier": v["tier"],
+                            "market_median": v["median"], "sample_size": v["sample"],
+                            "budget_ok": 1 if (l.get("sale_price") or 0) <= (budget.get("max_price") or 0) else 0})
+            recs.append(rec)
+        bulk_upsert_listing_matches(recs, conn=conn)
+    logger.info("매물 매칭 완료(%d건)", len(recs))


 def reg_flags(reg: dict) -> list:
--- a/realestate-lab/app/main.py
+++ b/realestate-lab/app/main.py
@@ -286,6 +286,18 @@ def api_listing_matches():
    return {"matches": get_listing_matches()}


+@app.post("/api/realestate/listings/rematch")
+def api_listings_rematch():
+    """MOLIT 재수집 없이 기존 listings+market_deals로 즉시 재판정(즉시 피드백용, 알림 미발송)."""
+    with match_notify_lock:
+        run_listing_matching()
+    matches = get_listing_matches()
+    passed = sum(1 for m in matches if m.get("passed"))
+    judged = sum(1 for m in matches if m.get("passed")
+                 and (m.get("safety_tier") or m.get("valuation_tier")) not in (None, "보류"))
+    return {"total": len(matches), "passed": passed, "judged": judged}
+
+
@app.post("/api/realestate/safety-check")
 def api_safety_check(req: SafetyCheckRequest):
    deals = get_market_deals_for(req.dong_code, req.complex_name, req.area,