convert_jsonl_to_json.py

import argparse
import json
import os
import sys

def jsonl_to_json(jsonl_file_path: str, json_file_path: str):
    """
    Converts a JSONL file to a JSON file.

    Args:
        jsonl_file_path: Path to the input JSONL file.
        json_file_path: Path to the output JSON file.
    """
    data = []
    try:
        with open(jsonl_file_path, 'r', encoding='utf-8') as infile:
            for line in infile:
                line = line.strip()
                if line:  # Ensure the line is not empty
                    try:
                        data.append(json.loads(line))
                    except json.JSONDecodeError as e:
                        print(f"Error decoding JSON on line: {line}", file=sys.stderr)
                        print(f"Error: {e}", file=sys.stderr)
                        return False  # Indicate failure
    except FileNotFoundError:
        print(f"Error: Input file not found at {jsonl_file_path}", file=sys.stderr)
        return False
    except Exception as e:
        print(f"An unexpected error occurred while reading the file: {e}", file=sys.stderr)
        return False

    try:
        with open(json_file_path, 'w', encoding='utf-8') as outfile:
            json.dump(data, outfile, indent=2) # Use indent=2 for pretty printing
        print(f"Successfully converted '{jsonl_file_path}' to '{json_file_path}'")
        return True # Indicate success
    except Exception as e:
        print(f"An error occurred while writing the JSON file: {e}", file=sys.stderr)
        return False

def main():
    parser = argparse.ArgumentParser(description='Convert a JSONL file to a JSON file.')
    parser.add_argument('jsonl_file', help='Path to the input JSONL file.')

    args = parser.parse_args()

    input_path = args.jsonl_file
    if not input_path.lower().endswith('.jsonl'):
        print("Warning: Input file does not have a .jsonl extension.", file=sys.stderr)

    # Create output path by replacing .jsonl with .json
    base_name = os.path.splitext(input_path)[0]
    output_path = base_name + '.json'

    if os.path.exists(output_path):
        overwrite = input(f"Output file '{output_path}' already exists. Overwrite? (y/N): ").lower()
        if overwrite != 'y':
            print("Operation cancelled.")
            sys.exit(0)

    if not jsonl_to_json(input_path, output_path):
        sys.exit(1) # Exit with error code if conversion failed


if __name__ == "__main__":
    main()