#!/usr/bin/env python3
"""Fetch XSP (mini-SPX) options daily OHLCV for the equity-index VRP test. HARD-CAPPED.

get_cost-gated: prints the exact cost and ABORTS if above CAP — no surprise charges.
Single dataset/schema/symbol/window. ohlcv-1d only (NOT definition).
"""
import os
import sys

import databento as db

CAP = 70.00                                   # hard cap — abort if cost exceeds this
DS, SCH, SYM = "OPRA.PILLAR", "ohlcv-1d", "XSP.OPT"
START, END = "2013-04-01", "2026-06-05"
OUT = "data/surfer/xsp_ohlcv1d.dbn"


def main():
    c = db.Historical(os.environ["DATABENTO_API_KEY"])
    if os.path.exists(OUT):
        print(f"already downloaded: {OUT}"); return 0
    cost = c.metadata.get_cost(dataset=DS, symbols=[SYM], schema=SCH, start=START, end=END, stype_in="parent")
    gb = c.metadata.get_billable_size(dataset=DS, symbols=[SYM], schema=SCH, start=START, end=END, stype_in="parent") / 1e9
    print(f"EXACT get_cost = ${cost:.2f}  ({gb:.2f} GB)   CAP = ${CAP:.2f}")
    if cost > CAP:
        print(f"ABORT: ${cost:.2f} exceeds cap ${CAP:.2f} — NOTHING downloaded.")
        return 1
    print(f"under cap by ${CAP - cost:.2f} -> downloading {SYM} {SCH} year-chunked (same total cost)")
    os.makedirs("data/surfer/xsp", exist_ok=True)
    for yr in range(2013, 2027):
        ys = f"{yr}-01-01" if yr > 2013 else "2013-04-01"
        ye = f"{yr+1}-01-01" if yr < 2026 else "2026-06-05"
        out = f"data/surfer/xsp/xsp_{yr}.dbn"
        if os.path.exists(out):
            print(f"  {yr}: exists"); continue
        for attempt in range(3):
            try:
                d = c.timeseries.get_range(dataset=DS, symbols=[SYM], schema=SCH, start=ys, end=ye, stype_in="parent")
                d.to_file(out)
                print(f"  {yr}: saved ({os.path.getsize(out)/1e6:.1f} MB)")
                break
            except Exception as e:
                print(f"  {yr}: attempt {attempt+1} {type(e).__name__}; retry")
    print(f"DONE -> data/surfer/xsp/")
    return 0


if __name__ == "__main__":
    sys.exit(main())