-- 178_schema_cadastral_value.sql
-- Rosreestr open dataset: dataset_КАДАСТРСТОИМОСТЬ (cadastral value).
-- Source URL pattern (region group 60–92, contains Свердловская обл. = 66):
--   https://rosreestr.gov.ru/.../dataset_КАДАСТРСТОИМОСТЬ_r-r_60-92_y_{YYYY}_q_{Q}.csv
-- Encoding: UTF-8. Separator: '~'. QUOTE '"'. NULL '' (empty string).
-- Header columns (verified, in order):
--   number ~ realestate_type_code ~ purpose_code ~ area ~ region_code ~ district ~
--   city ~ quarter_cad_number ~ street ~ registration_quarter ~ application_quarter ~
--   cost ~ cost_per_area ~ period
--
-- Purpose: cadastral ₽/m² floor per cadastral quarter, used to denoise the deals
--   price index (mv_quarter_price_per_m2) — registered deals priced below
--   0.7 × the cadastral median for their quarter are dropped as data noise.
--   realestate_type_code='002001003000' (помещения/квартиры) — same code as
--   rosreestr_deals; quarter_cad_number JOIN-compatible with rosreestr_deals.
--   `number` = count of aggregated objects collapsed into that source row.
--
-- Scope: region-66-scoped — the .py loader (178b_load_cadastral_value.py) filters
--   region_code='66' on INSERT. The 60–92 CSV is loaded once per quarter MANUALLY
--   by an operator after deploy (this migration only creates the empty schema).
--
-- Dependencies: none. Auto-applied on prod via deploy.yml (_schema_migrations).
-- Idempotent: CREATE TABLE/INDEX IF NOT EXISTS — safe to re-apply.

BEGIN;

-- Typed target table (region-66-scoped after loader filter).
CREATE TABLE IF NOT EXISTS rosreestr_cadastral_value (
    id                    BIGSERIAL    PRIMARY KEY,
    source_quarter        VARCHAR(8)   NOT NULL,        -- '2026Q1' for traceability
    -- Source columns (typed)
    number                INTEGER,                      -- aggregated object count
    realestate_type_code  TEXT,                         -- '002001003000' = помещения
    purpose_code          TEXT,
    area                  NUMERIC,                      -- м²
    region_code           SMALLINT,                     -- 66 = Свердловская обл.
    district              TEXT,
    city                  TEXT,
    quarter_cad_number    VARCHAR(30),                  -- '66:41:0506001' — JOIN-ключ
    street                TEXT,
    registration_quarter  TEXT,
    application_quarter   TEXT,
    cost                  NUMERIC,                      -- кадастровая стоимость, ₽
    cost_per_area         NUMERIC,                      -- кадастровая ₽/m²
    period                TEXT,
    -- Audit
    loaded_at             TIMESTAMPTZ  NOT NULL DEFAULT NOW()
);

-- Lookup index for the cad_floor CTE (filter by quarter + apartment type code).
CREATE INDEX IF NOT EXISTS rosreestr_cadastral_value_cq_type_idx
    ON rosreestr_cadastral_value (quarter_cad_number, realestate_type_code);

-- Idempotent skip-if-loaded check in the loader is by source_quarter.
CREATE INDEX IF NOT EXISTS rosreestr_cadastral_value_source_quarter_idx
    ON rosreestr_cadastral_value (source_quarter);

-- Staging: один общий буфер. Перед каждым кварталом TRUNCATE.
-- 14 source columns, all TEXT, in CSV header order — typed cast happens on INSERT.
CREATE UNLOGGED TABLE IF NOT EXISTS rosreestr_cadastral_value_staging (
    number                TEXT,
    realestate_type_code  TEXT,
    purpose_code          TEXT,
    area                  TEXT,
    region_code           TEXT,
    district              TEXT,
    city                  TEXT,
    quarter_cad_number    TEXT,
    street                TEXT,
    registration_quarter  TEXT,
    application_quarter   TEXT,
    cost                  TEXT,
    cost_per_area         TEXT,
    period                TEXT
);

COMMIT;