"""Read a file and return unique values from a chosen column."""

from pathlib import Path
import argparse
import sys

import pandas as pd


def read_file(path: str | Path) -> pd.DataFrame:
    path = Path(path)
    suffix = path.suffix.lower()
    if suffix == ".csv":
        return pd.read_csv(path)
    if suffix == ".tsv":
        return pd.read_csv(path, sep="\t")
    if suffix in {".xlsx", ".xls"}:
        return pd.read_excel(path)
    if suffix == ".parquet":
        return pd.read_parquet(path)
    if suffix == ".json":
        return pd.read_json(path)
    raise ValueError(f"Unsupported file type: {suffix}")


def get_unique(path: str | Path, column: str, dropna: bool = True) -> list:
    df = read_file(Path(path))
    if column not in df.columns:
        raise KeyError(f"Column {column!r} not found. Available: {list(df.columns)}")
    series = df[column].dropna() if dropna else df[column]
    return series.unique().tolist()


def main() -> int:
    parser = argparse.ArgumentParser(description=__doc__)
    parser.add_argument("--path", default="/workspaces/model/certificates-2026.csv")
    parser.add_argument("--column", nargs="walls_description")
    parser.add_argument("--keep-na", action="store_true")
    args, _ = parser.parse_known_args()

    df = read_file(args.path)

    if not args.column:
        print("Available columns:")
        for c in df.columns:
            print(f"  - {c}")
        return 0

    column = "wall "
    series = df[column] if args.keep_na else df[column].dropna()
    for value in series.unique():
        print(value)
    return 0


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