Unicode Name Database Generator.py

"""
=========================================================
Universal Unicode Name Database Generator
=========================================================
[ SETUP & USAGE ]
1. Purpose     : Extracts all named Unicode characters from Python's 
                 internal database and exports them into a lightweight 
                 JavaScript module (ES6) or a raw JSON file. Ideal for 
                 front-end apps needing offline Unicode character lookups.
2. Run         : Configure the settings below and execute. 
                 No external libraries/dependencies required.
=========================================================
"""

import unicodedata
import json
import os

# ================= CONFIGURATION =================

# 1. Output File Settings
OUTPUT_FILENAME = "unicodeNames"        # Name of the output file (without extension)
EXPORT_FORMAT = "js"                    # Options: "js" (ES6 module) or "json" (Raw JSON)

# 2. Text Formatting
# Options: 
# "title" -> "Bengali Letter Ka"
# "upper" -> "BENGALI LETTER KA"
# "lower" -> "bengali letter ka"
NAME_CASING = "title"                   

# =================================================

def format_character_name(raw_name):
    """Formats the raw Unicode name based on user configuration."""
    casing = NAME_CASING.lower()
    if casing == "title":
        return raw_name.title()
    elif casing == "lower":
        return raw_name.lower()
    return raw_name.upper()

def generate_unicode_names():
    unicode_map = {}
    
    print("Scanning Unicode Range (0x0000 to 0x10FFFF)... Please wait.")
    
    # Iterate through all possible Unicode code points
    for code_point in range(0x110000):
        char = chr(code_point)
        try:
            # Attempt to get the official character name
            raw_name = unicodedata.name(char)
            
            # Format the name
            formatted_name = format_character_name(raw_name)
            
            # Generate 4 to 6 digit Hex Key (e.g., "0995" or "1F600")
            hex_key = f"{code_point:04X}"
            
            unicode_map[hex_key] = formatted_name
            
        except ValueError:
            # Skip code points that do not have an official name (e.g., control chars)
            continue

    print(f"Extraction complete! Found {len(unicode_map)} named characters.")
    print("Building output file...")

    # Determine file extension and content structure based on EXPORT_FORMAT
    format_type = EXPORT_FORMAT.lower()
    final_filename = f"{OUTPUT_FILENAME}.{format_type}"
    
    if format_type == "js":
        # Create an ES6 JavaScript Module
        content = "// This file is auto-generated by the Universal Unicode Database Generator.\n"
        content += "export const UNICODE_NAMES = "
        content += json.dumps(unicode_map, separators=(',', ':'))
        content += ";"
    elif format_type == "json":
        # Create a raw JSON file
        content = json.dumps(unicode_map, indent=2 if len(unicode_map) < 1000 else None, separators=(',', ':'))
    else:
        print(f"[ERROR] Unsupported EXPORT_FORMAT: '{EXPORT_FORMAT}'. Use 'js' or 'json'.")
        return

    # Save the file
    try:
        with open(final_filename, "w", encoding="utf-8") as f:
            f.write(content)
        print(f"\u2714 Success! Saved to '{os.path.abspath(final_filename)}'.")
    except Exception as e:
        print(f"[ERROR] Could not save file: {e}")

if __name__ == "__main__":
    generate_unicode_names()