fix(realestate): 네이버 매물 dong_code를 dong명에서 유도(cortarNo 부재)→ market_deals 매칭·판정 복구

네이버 article에 cortarNo가 없는 경우 listing.dong_code가 None으로 저장되어
get_market_deals_for가 시세를 못 찾아 모든 매물이 '보류'(판정 불가) 상태였다.
dong명은 항상 정확히 태깅되므로 lawd_code(dong)으로 5자리 시군구코드를 유도해
market_deals와 매칭시킨다.

- internal_router.listings_ingest: dong_code 없으면 batch.dong에서 lawd_code로 보정
- db.upsert_listing: ON CONFLICT UPDATE SET에 dong_code 추가(재유입 시 기존 None행 갱신)
- listing_matcher.run_listing_matching: get_market_deals_for 호출 전 dong_code 없으면
  listing.dong에서 즉시 유도(기존 저장된 None행도 재실행만으로 판정 복구)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EqCYBhvTcdeCTUDX3RhWx9
This commit is contained in:
2026-07-10 14:11:51 +09:00
parent 4097c95286
commit f676116336
5 changed files with 63 additions and 3 deletions

View File

@@ -977,7 +977,8 @@ def upsert_listing(data: Dict[str, Any]) -> tuple:
ON CONFLICT(article_no) DO UPDATE SET ON CONFLICT(article_no) DO UPDATE SET
deposit=excluded.deposit, monthly_rent=excluded.monthly_rent, sale_price=excluded.sale_price, deposit=excluded.deposit, monthly_rent=excluded.monthly_rent, sale_price=excluded.sale_price,
floor=excluded.floor, complex_name=excluded.complex_name, address=excluded.address, floor=excluded.floor, complex_name=excluded.complex_name, address=excluded.address,
url=excluded.url, posted_at=excluded.posted_at, raw_json=excluded.raw_json url=excluded.url, posted_at=excluded.posted_at, raw_json=excluded.raw_json,
dong_code=excluded.dong_code
""", d) """, d)
row = conn.execute("SELECT * FROM listings WHERE article_no=?", (d["article_no"],)).fetchone() row = conn.execute("SELECT * FROM listings WHERE article_no=?", (d["article_no"],)).fetchone()
return dict(row), is_new return dict(row), is_new

View File

@@ -8,7 +8,7 @@ from pydantic import BaseModel
from .auth import verify_internal_key from .auth import verify_internal_key
from .db import get_listing_criteria, upsert_listing from .db import get_listing_criteria, upsert_listing
from .lawd_codes import naver_cortar from .lawd_codes import naver_cortar, lawd_code
from .listing_collector import _parse_naver_article from .listing_collector import _parse_naver_article
from .listing_matcher import run_listing_matching from .listing_matcher import run_listing_matching
from .notifier import notify_new_listings from .notifier import notify_new_listings
@@ -55,6 +55,9 @@ def listings_ingest(body: ListingsIngest, background_tasks: BackgroundTasks):
if not d.get("article_no"): if not d.get("article_no"):
continue continue
d["dong"] = batch.dong d["dong"] = batch.dong
# 네이버 article에 cortarNo가 없는 경우가 실사용에서 확인됨 → dong명에서
# 5자리 시군구코드(lawd_code)를 유도(market_deals는 이 5자리를 쓴다).
d["dong_code"] = d.get("dong_code") or lawd_code(batch.dong)
_, is_new = upsert_listing(d) _, is_new = upsert_listing(d)
received += 1 received += 1
if is_new: if is_new:

View File

@@ -5,6 +5,7 @@ import statistics
from .db import (get_listing_criteria, get_market_deals_for, bulk_upsert_listing_matches, from .db import (get_listing_criteria, get_market_deals_for, bulk_upsert_listing_matches,
_conn) _conn)
from . import finance_rules from . import finance_rules
from .lawd_codes import lawd_code
logger = logging.getLogger("realestate-lab") logger = logging.getLogger("realestate-lab")
@@ -96,7 +97,10 @@ def run_listing_matching() -> None:
budget = finance_rules.estimate_purchase_budget( budget = finance_rules.estimate_purchase_budget(
equity, income, reg, criteria.get("is_first_home"), criteria.get("is_homeless")) equity, income, reg, criteria.get("is_first_home"), criteria.get("is_homeless"))
m = match_listing(criteria, l, budget) m = match_listing(criteria, l, budget)
deals = get_market_deals_for(l.get("dong_code"), l.get("complex_name"), # 네이버 cortarNo 부재 등으로 기존 저장된 listing.dong_code가 None일 수 있음 —
# dong명에서 5자리 lawd_code를 유도해 즉시 판정(보류 고착 방지).
dc = l.get("dong_code") or lawd_code(l.get("dong"))
deals = get_market_deals_for(dc, l.get("complex_name"),
l.get("area_exclusive"), "전세" if is_rent else "매매", l.get("area_exclusive"), "전세" if is_rent else "매매",
conn=conn) conn=conn)
rec = {"listing_id": l["id"], "category": "임차" if is_rent else "매매", rec = {"listing_id": l["id"], "category": "임차" if is_rent else "매매",

View File

@@ -59,3 +59,23 @@ def test_ingest_holds_match_notify_lock(monkeypatch):
c.post("/api/internal/realestate/listings-ingest", headers={"X-Internal-Key": "SECRET"}, c.post("/api/internal/realestate/listings-ingest", headers={"X-Internal-Key": "SECRET"},
json={"batches": [{"dong": "신대방동", "articles": [_ARTICLE]}]}) json={"batches": [{"dong": "신대방동", "articles": [_ARTICLE]}]})
assert holds["locked"] is True # 알림 시점에 락 보유(임계구역 직렬화 증명) assert holds["locked"] is True # 알림 시점에 락 보유(임계구역 직렬화 증명)
# ── 근본원인 fix: 네이버 article에 cortarNo 없으면 dong_code=None → 시세 매칭 불가 ──
_ARTICLE_NO_CORTAR = {"articleNo": "N200", "tradeTypeName": "전세", "dealOrWarrantPrc": "2억 9,000",
"area2": "42.5", "floorInfo": "5/15", "articleName": "OO아파트",
"buildingName": "OO"} # cortarNo 없음 — 실제 네이버 응답 케이스
def test_ingest_derives_dong_code_from_dong_when_cortarno_missing(monkeypatch):
c = _client(monkeypatch)
with patch("app.internal_router.notify_new_listings", return_value={"sent": 0}):
r = c.post("/api/internal/realestate/listings-ingest",
headers={"X-Internal-Key": "SECRET"},
json={"batches": [{"dong": "신길동", "articles": [_ARTICLE_NO_CORTAR]}]})
assert r.status_code == 200
from app import db
ls = db.get_listings()
saved = next(l for l in ls if l["article_no"] == "N200")
assert saved["dong_code"] == "11560" # 신길동 → 영등포구 5자리 lawd_code로 유도

View File

@@ -77,3 +77,35 @@ def test_run_listing_matching_end_to_end_safe_rent_and_overpriced_sale():
sale_m = matches[l_sale["id"]] sale_m = matches[l_sale["id"]]
assert sale_m["valuation_tier"] == "고가" assert sale_m["valuation_tier"] == "고가"
assert sale_m["sample_size"] == 4 assert sale_m["sample_size"] == 4
# ── 근본원인 fix: 기존 저장된 listing.dong_code=None(cortarNo 부재) 행도 dong명에서
# lawd_code를 유도해 즉시 판정돼야 한다(보류 고착 방지) ──
def test_run_listing_matching_derives_dong_code_when_none():
from app import db
from app.listing_matcher import run_listing_matching
db.update_listing_criteria({
"dongs": ["신길동"], "deal_types": ["매매"],
"min_area": 40.0, "house_types": ["아파트"],
"equity": 20000, "annual_income": 6000,
})
# 신길동(영등포구=11560) 매매 실거래 시세 3건
for i, v in enumerate((80000, 88000, 90000)):
db.upsert_market_deal({"house_type": "아파트", "dong_code": "11560", "dong": "신길동",
"complex_name": "QQ", "area": 59.0, "deal_type": "매매",
"deposit": None, "sale_amount": v,
"deal_ym": f"2026{i+1:02d}", "floor": "8", "source": "molit"})
# 매물은 dong_code=None으로 저장(네이버 cortarNo 부재 시나리오)
l_sale, _ = db.upsert_listing({"article_no": "R3", "source": "naver", "deal_type": "매매",
"sale_price": 84000, "area_exclusive": 59.0,
"complex_name": "QQ", "dong": "신길동", "dong_code": None})
run_listing_matching()
matches = {m["listing_id"]: m for m in db.get_listing_matches()}
m = matches[l_sale["id"]]
assert m["sample_size"] == 3
assert m["valuation_tier"] != "보류"