Light1YT
b51893f7c3
rosreestr ДКП deals used dedup_hash = md5('ros:dkp:' || id) — a hash of
an already-unique natural key. The md5 is collision-prone (theoretically),
not human-readable, and irreversible (can't recover the source id from it,
which mattered because deals.source_id was never populated).
Replace with the plain natural key 'ros:dkp:' || id (injective, zero
collision, reversible) and populate deals.source_id going forward, in both
the live scheduler import (import_rosreestr_dkp) and the legacy
deploy/import-rosreestr.sh.
Migration 077 backfills the existing 49,791 rows: recovers the original id
from FDW foreign table gendesign_rosreestr_deals by matching the old md5,
then writes the plain key + source_id. Idempotent; plain keys and md5 hex
are format-disjoint so no transient UNIQUE violation on deals_dedup_hash_key.
Verified via prod dry-run (ROLLBACK): UPDATE 49791, 0 md5 remaining, 3.85s.
Closes #576
87 lines
4.3 KiB
Bash
Executable file
87 lines
4.3 KiB
Bash
Executable file
#!/usr/bin/env bash
|
||
# Импорт реальных сделок Росреестра из gendesign-БД в tradein deals.
|
||
#
|
||
# Источник: gendesign-postgres-1 / rosreestr_deals (6.8М строк, партиц.).
|
||
# Берём ЕКБ квартиры (realestate_type_code=002001003000) за последние ~18 мес.
|
||
# rooms выводим из площади (Росреестр не отдаёт кол-во комнат).
|
||
# Координаты — NULL, проставляются отдельно (geocode по street).
|
||
#
|
||
# Только ДКП (вторичка) — ДДУ застройщиков скёюят median, отделены сознательно. См. PR-A.
|
||
#
|
||
# Запуск на прод-хосте: ./import-rosreestr.sh
|
||
# Повторяемо: дедуп по dedup_hash, новый запуск подтянет свежие кварталы.
|
||
|
||
set -euo pipefail
|
||
|
||
SRC_PG="${SRC_PG:-gendesign-postgres-1}"
|
||
DST_PG="${DST_PG:-tradein-postgres}"
|
||
SRC_DB="${SRC_DB:-gendesign}"
|
||
SRC_USER="${SRC_USER:-gendesign}"
|
||
SINCE="${SINCE:-2024-01-01}"
|
||
|
||
echo "[$(date -u +%H:%M:%S)] import-rosreestr: ЕКБ квартиры с $SINCE"
|
||
|
||
# 1. Staging-таблица в tradein.
|
||
docker exec "$DST_PG" psql -U tradein -d tradein -v ON_ERROR_STOP=on -c "
|
||
-- DROP перед CREATE: страхует от устаревшей формы staging-таблицы, если прошлый
|
||
-- запуск упал между CREATE и финальным DROP под старым кодом (без source_id).
|
||
DROP TABLE IF EXISTS deals_ros_staging;
|
||
CREATE TABLE deals_ros_staging (
|
||
dedup_hash text PRIMARY KEY, source_id text, address text, rooms int, area_m2 numeric,
|
||
floor int, year_built int, price_rub bigint, price_per_m2 int, deal_date date
|
||
);
|
||
"
|
||
|
||
# 2. Трансформируем на gendesign-стороне, пайпим CSV в staging.
|
||
docker exec "$SRC_PG" psql -U "$SRC_USER" -d "$SRC_DB" -v ON_ERROR_STOP=on -c "
|
||
COPY (
|
||
SELECT
|
||
'ros:dkp:' || id::text AS dedup_hash,
|
||
id::text AS source_id,
|
||
'Екатеринбург, ' || trim(street) AS address,
|
||
CASE
|
||
WHEN area < 30 THEN 0 WHEN area < 44 THEN 1
|
||
WHEN area < 62 THEN 2 WHEN area < 85 THEN 3
|
||
ELSE 4 END AS rooms,
|
||
round(area, 2) AS area_m2,
|
||
LEAST(NULLIF(substring(floor from '[0-9]+'), '')::int, 100) AS floor,
|
||
year_build AS year_built,
|
||
round(deal_price)::bigint AS price_rub,
|
||
round(price_per_sqm)::int AS price_per_m2,
|
||
period_start_date AS deal_date
|
||
FROM rosreestr_deals
|
||
WHERE region_code = 66
|
||
AND city ILIKE '%катеринбург%'
|
||
AND realestate_type_code = '002001003000'
|
||
AND area BETWEEN 18 AND 200
|
||
AND deal_price BETWEEN 1000000 AND 100000000
|
||
AND street IS NOT NULL AND trim(street) <> ''
|
||
AND doc_type = 'ДКП'
|
||
AND period_start_date >= '$SINCE'
|
||
) TO STDOUT WITH CSV
|
||
" | docker exec -i "$DST_PG" psql -U tradein -d tradein -v ON_ERROR_STOP=on -c "
|
||
COPY deals_ros_staging FROM STDIN WITH CSV
|
||
"
|
||
|
||
STAGED=$(docker exec "$DST_PG" psql -U tradein -d tradein -tAc "SELECT count(*) FROM deals_ros_staging")
|
||
echo "[$(date -u +%H:%M:%S)] staged: $STAGED строк"
|
||
|
||
# 3. Удаляем старые синтетические сделки, вставляем реальные (дедуп).
|
||
docker exec "$DST_PG" psql -U tradein -d tradein -v ON_ERROR_STOP=on -c "
|
||
DELETE FROM deals WHERE address = 'Екатеринбург, реальная сделка';
|
||
|
||
INSERT INTO deals (
|
||
source, dedup_hash, source_id, address, rooms, area_m2, floor,
|
||
year_built, price_rub, price_per_m2, deal_date
|
||
)
|
||
SELECT 'rosreestr', dedup_hash, source_id, address, rooms, area_m2, floor,
|
||
year_built, price_rub, price_per_m2, deal_date
|
||
FROM deals_ros_staging
|
||
ON CONFLICT (dedup_hash) DO NOTHING;
|
||
|
||
DROP TABLE deals_ros_staging;
|
||
"
|
||
|
||
TOTAL=$(docker exec "$DST_PG" psql -U tradein -d tradein -tAc "SELECT count(*) FROM deals")
|
||
echo "[$(date -u +%H:%M:%S)] deals всего: $TOTAL"
|
||
echo "Координаты проставит geocode-deals (отдельный шаг)."
|