Load a JSON file from the command line and estimat...

process.py

# /// script
# description = "Load a JSON file from the command line and estimate its schema."
# authors = ["Script-Magic AI Generator"]
# date = "2023-10-07"
# requires-python = ">=3.9"
# dependencies = [
#     "jsonschema"
# ]
# tags = ["json", "schema", "data analysis"]
# ///

# Generated from the prompt: "Load a JSON {{file}} from the command line and assuming it is an array of objects use best effort to estimate the schema and output the schema to the command line"

import json
import argparse
from collections import defaultdict

def estimate_schema(data):
    # Create a default dictionary to hold the types of fields
    schema = defaultdict(set)

    # Iterate through each object in the JSON array
    for obj in data:
        for key, value in obj.items():
            # Add the type of the value to the set for that key
            schema[key].add(type(value).__name__)

    # Convert schema sets to a list for easier readability
    return {key: list(value) for key, value in schema.items()}

def main():
    # Set up command line argument parsing
    parser = argparse.ArgumentParser(description="Estimate schema from JSON file.")
    parser.add_argument('file', type=str, help="Path to the JSON file.")

    args = parser.parse_args()

    try:
        # Load the JSON data from the specified file
        with open(args.file, 'r') as f:
            data = json.load(f)

        # Ensure the data is a list
        if not isinstance(data, list):
            raise ValueError("The JSON data should be an array of objects.")

        # Estimate the schema
        schema = estimate_schema(data)

        # Print the estimated schema
        print(json.dumps(schema, indent=4))
    except FileNotFoundError:
        print(f"Error: File '{args.file}' not found.")
    except json.JSONDecodeError:
        print(f"Error: '{args.file}' is not a valid JSON file.")
    except Exception as e:
        print(f"Error: {e}")

if __name__ == '__main__':
    main()