"""Step 1: download the public catalogues from VizieR (cached in RAW)."""
from common import tap_csv, VIZIER_TAP

TABLES = {
    # ALFALFA alpha.100 extragalactic catalogue (Haynes et al. 2018)
    "a100.csv": 'SELECT * FROM "J/ApJ/861/49/table2"',
    # ALFALFA-SDSS catalogue (Durbala et al. 2020)
    "durbala_t1.csv": 'SELECT * FROM "J/AJ/160/271/table1"',
    "durbala_t2.csv": 'SELECT * FROM "J/AJ/160/271/table2"',
    # Cosmicflows-4 Tully-Fisher catalogue (Kourkchi et al. 2020)
    "cf4_t1.csv": 'SELECT * FROM "J/ApJ/902/145/table1"',
    "cf4_t4.csv": 'SELECT * FROM "J/ApJ/902/145/table4"',
    # SDSS DR12 spectroscopic galaxies (Tempel et al. 2017), used only to flag
    # HI confusion (other galaxies inside the Arecibo beam at the same redshift)
    "tempel_dr12.csv": 'SELECT GalID, RAJ2000, DEJ2000, zobs, "rmag" FROM "J/A+A/602/A100/table1" '
                       'WHERE zobs<0.07 AND DEJ2000>-3 AND DEJ2000<39',
}


def main():
    for fn, q in TABLES.items():
        p = tap_csv(VIZIER_TAP, q, fn, maxrec=200000)
        n = sum(1 for _ in open(p)) - 1
        print(f"  {fn:18s} rows={n}")


if __name__ == "__main__":
    main()