#!/usr/bin/env python3
"""Rebuild scripts/data/bright_stars.json from the Yale Bright Star Catalogue.

Source: Hoffleit & Warren, *The Bright Star Catalogue, 5th Revised Ed.*
(NASA Astronomical Data Center, 1991), distributed by CDS as VizieR V/50.
A US-government (NASA ADC) data product, redistributed by CDS without
restriction; treated as public domain. No star-chart software data is used.

Usage (the catalogue itself is not committed; the script checks its sha256):

    curl -o /tmp/bsc5_catalog.gz https://cdsarc.cds.unistra.fr/ftp/V/50/catalog.gz
    python3 scripts/build_bright_stars.py /tmp/bsc5_catalog.gz
"""
from __future__ import annotations

import gzip
import hashlib
import json
import sys
from pathlib import Path

SOURCE_URL = "https://cdsarc.cds.unistra.fr/ftp/V/50/catalog.gz"
SOURCE_SHA256 = "3dc44b1e90be8fbe5bcc7656032560f51275f985c7e3f783c9028e1838ec7bed"
MAX_MAGNITUDE = 4.0
OUT = Path(__file__).resolve().parent / "data" / "bright_stars.json"

# Asterism polylines by HR number. Each inner list is one continuous stroke.
LINES = [
    {"id": "big_dipper", "strokes": [[5191, 5054, 4905, 4660, 4554, 4295, 4301, 4660]]},
    {"id": "cassiopeia", "strokes": [[21, 168, 264, 403, 542]]},
    {
        "id": "orion",
        "strokes": [
            [2061, 1879, 1790],
            [2061, 1948, 1903, 1852, 1790],
            [1948, 2004],
            [1852, 1713],
        ],
    },
]


def _parse(raw: bytes) -> list[dict]:
    stars: list[dict] = []
    for line in raw.decode("latin-1").splitlines():
        if len(line) < 107 or not line[75:77].strip() or not line[102:107].strip():
            continue  # HR entries without a J2000 position or V magnitude (novae, removed objects)
        vmag = float(line[102:107])
        if vmag > MAX_MAGNITUDE:
            continue
        hr = int(line[0:4])
        ra = (int(line[75:77]) + int(line[77:79]) / 60 + float(line[79:83]) / 3600) * 15
        dec = int(line[84:86]) + int(line[86:88]) / 60 + int(line[88:90]) / 3600
        if line[83] == "-":
            dec = -dec
        stars.append({"hr": hr, "ra": round(ra, 5), "dec": round(dec, 5), "vmag": vmag})
    return stars


def main(path: str) -> None:
    packed = Path(path).read_bytes()
    digest = hashlib.sha256(packed).hexdigest()
    if digest != SOURCE_SHA256:
        raise SystemExit(f"sha256 mismatch: {digest}")
    stars = _parse(gzip.decompress(packed))
    known = {star["hr"] for star in stars}
    for line in LINES:
        for stroke in line["strokes"]:
            missing = [hr for hr in stroke if hr not in known]
            if missing:
                raise SystemExit(f"{line['id']} needs HR {missing} brighter than {MAX_MAGNITUDE}")
    payload = {
        "source": "Yale Bright Star Catalogue, 5th Revised Ed. (Hoffleit & Warren 1991), VizieR V/50",
        "source_url": SOURCE_URL,
        "source_sha256": SOURCE_SHA256,
        "license": "Public domain (NASA Astronomical Data Center product, redistributed by CDS without restriction)",
        "selection": f"V magnitude <= {MAX_MAGNITUDE}; J2000.0 equinox and epoch; proper motion not applied",
        "fields": ["hr", "ra_deg_j2000", "dec_deg_j2000", "vmag"],
        "generator": "scripts/build_bright_stars.py",
        "lines": LINES,
        "stars": [[s["hr"], s["ra"], s["dec"], s["vmag"]] for s in stars],
    }
    OUT.write_text(json.dumps(payload, ensure_ascii=False, separators=(",", ":")) + "\n", encoding="utf-8")
    print(f"{len(stars)} stars -> {OUT}")


if __name__ == "__main__":
    main(sys.argv[1] if len(sys.argv) > 1 else "/tmp/bsc5_catalog.gz")