csv-to-json.py

#!/usr/bin/env python3
"""
CSV to JSON Converter — Convert CSV files to JSON format.

Usage:
    python csv-to-json.py <input.csv> [--output output.json] [--pretty]
    python csv-to-json.py <input.csv> --delimiter ";"

Options:
    --output FILE     Output JSON file (default: <input>.json)
    --pretty          Pretty-print JSON with indentation
    --delimiter CHAR  CSV delimiter (default: ",")
    --encoding ENC    File encoding (default: utf-8)
    --help            Show this help message and exit
"""

import os
import sys
import csv
import json
import argparse
from pathlib import Path


def csv_to_json(input_path: Path, delimiter: str, encoding: str) -> list[dict]:
    """Read a CSV file and return a list of dicts."""
    rows: list[dict] = []
    try:
        with open(input_path, "r", encoding=encoding, newline="") as f:
            reader = csv.DictReader(f, delimiter=delimiter)
            if reader.fieldnames is None:
                print(f"Error: '{input_path}' appears empty or has no header row.")
                sys.exit(1)
            for row in reader:
                # Strip whitespace from keys and values
                cleaned = {k.strip() if k else k: v.strip() if isinstance(v, str) else v
                           for k, v in row.items()}
                rows.append(cleaned)
    except FileNotFoundError:
        print(f"Error: File '{input_path}' not found.")
        sys.exit(1)
    except UnicodeDecodeError:
        print(f"Error: Could not decode '{input_path}' with encoding '{encoding}'. "
              f"Try --encoding utf-8-sig or latin-1.")
        sys.exit(1)
    except Exception as e:
        print(f"Error reading CSV: {e}")
        sys.exit(1)
    return rows


def main():
    parser = argparse.ArgumentParser(
        description="Convert a CSV file to JSON.",
        formatter_class=argparse.RawDescriptionHelpFormatter,
        epilog=(
            "Examples:\n"
            "  python csv-to-json.py data.csv\n"
            "  python csv-to-json.py data.csv --pretty\n"
            "  python csv-to-json.py data.tsv --delimiter $'\\t'\n"
        ),
    )
    parser.add_argument("input", help="Input CSV file")
    parser.add_argument("--output", help="Output JSON file (default: <input>.json)")
    parser.add_argument("--pretty", action="store_true", help="Pretty-print JSON")
    parser.add_argument("--delimiter", default=",", help="CSV delimiter (default: ',')")
    parser.add_argument("--encoding", default="utf-8", help="File encoding (default: utf-8)")

    args = parser.parse_args()

    input_path = Path(args.input)
    if not input_path.is_file():
        print(f"Error: '{args.input}' is not a valid file.")
        sys.exit(1)

    output_path = Path(args.output) if args.output else input_path.with_suffix(".json")

    rows = csv_to_json(input_path, args.delimiter, args.encoding)

    json_kwargs: dict = {"ensure_ascii": False}
    if args.pretty:
        json_kwargs["indent"] = 2

    try:
        with open(output_path, "w", encoding="utf-8") as f:
            json.dump(rows, f, **json_kwargs)
    except Exception as e:
        print(f"Error writing JSON: {e}")
        sys.exit(1)

    print(f"Converted {len(rows)} rows → {output_path}")


if __name__ == "__main__":
    main()