"""Download Statistics Canada benchmarks via the WDS API (public, no key).

- 18-10-0004-01 CPI monthly NSA: Quebec (geo 11), Montréal (13), Canada (2) × food aggregates (members 3,4,5,21,22,28,29,30,34,39,49,58)
- 18-10-0245-01 Monthly average retail prices for selected products: Quebec, all 110 products
Raw JSON kept in data/raw/statcan/ with download timestamp; tidy CSVs in data/processed/.
"""
from __future__ import annotations
import json, time, requests, pandas as pd
from src.common import ROOT, path, get_logger, ledger

log = get_logger("statcan")
WDS = "https://www150.statcan.gc.ca/t1/wds/rest/"
RAW = ROOT / "data" / "raw" / "statcan"; RAW.mkdir(parents=True, exist_ok=True)

def coords(product_id: int, pairs: list[tuple[int, int]], periods: int) -> pd.DataFrame:
    body = [{"productId": product_id, "coordinate": f"{g}.{p}.0.0.0.0.0.0.0.0", "latestN": periods} for g, p in pairs]
    r = requests.post(WDS + "getDataFromCubePidCoordAndLatestNPeriods", json=body, timeout=120); r.raise_for_status()
    (RAW / f"{product_id}_{int(time.time())}.json").write_text(r.text)
    rows = []
    for item in r.json():
        if item["status"] != "SUCCESS":
            log.warning("WDS item failed: %s", item); continue
        o = item["object"]
        for dp in o["vectorDataPoint"]:
            rows.append(dict(productId=product_id, coordinate=o["coordinate"], vectorId=o["vectorId"],
                             ref_date=dp["refPer"], value=dp["value"], scalar=dp["scalarFactorCode"], status=dp.get("statusCode")))
    return pd.DataFrame(rows)

def main() -> None:
    meta = {}
    for pid in (18100004, 18100245):
        r = requests.post(WDS + "getCubeMetadata", json=[{"productId": pid}], timeout=120); r.raise_for_status()
        meta[pid] = r.json()[0]["object"]; (RAW / f"meta_{pid}.json").write_text(r.text)
    # CPI
    m = meta[18100004]; geo = {x["memberId"]: x["memberNameEn"] for x in m["dimension"][0]["member"]}
    prodn = {x["memberId"]: x["memberNameEn"] for x in m["dimension"][1]["member"]}
    food_members = [2, 3, 4, 5, 16, 21, 22, 28, 29, 30, 34, 39, 49, 58]
    cpi = coords(18100004, [(g, p) for g in (2, 11, 13) for p in food_members], periods=60)
    cpi["geo"] = cpi.coordinate.str.split(".").str[0].astype(int).map(geo)
    cpi["product"] = cpi.coordinate.str.split(".").str[1].astype(int).map(prodn)
    cpi.to_csv(path("processed") / "statcan_cpi_food.csv", index=False)
    log.info("CPI: %d points, %s → %s, latest release %s", len(cpi), cpi.ref_date.min(), cpi.ref_date.max(), m.get("releaseTime"))
    # Average retail prices
    m2 = meta[18100245]; geo2 = {x["memberId"]: x["memberNameEn"] for x in m2["dimension"][0]["member"]}
    prod2 = {x["memberId"]: x["memberNameEn"] for x in m2["dimension"][1]["member"]}
    qc = [k for k, v in geo2.items() if v == "Quebec"][0]
    arp = coords(18100245, [(qc, p) for p in prod2], periods=36)
    arp["geo"] = "Quebec"; arp["product"] = arp.coordinate.str.split(".").str[1].astype(int).map(prod2)
    arp.to_csv(path("processed") / "statcan_avg_retail_prices_qc.csv", index=False)
    log.info("Average retail prices QC: %d points, %d products, %s → %s", len(arp), arp["product"].nunique(), arp.ref_date.min(), arp.ref_date.max())
    ledger("1", "statcan", f"CPI {len(cpi)} pts to {cpi.ref_date.max()}; ARP {len(arp)} pts to {arp.ref_date.max()}")

if __name__ == "__main__":
    main()