This script will update all the Unicode codepoints in json/yaml/toml files to point to new Nerd Font icon locations

translate-unicode-nf.py

import os
import sys

def unicode_to_surrogate_pair(codepoint):
    # Convert a Unicode codepoint to a surrogate pair if necessary
    code = int(codepoint, 16)
    if code <= 0xFFFF:
        return f"\\u{codepoint.lower()}"
    # Calculation for surrogate pairs
    code -= 0x10000
    high_surrogate = 0xD800 + (code // 0x400)
    low_surrogate = 0xDC00 + (code % 0x400)
    return f"\\u{high_surrogate:04x}\\u{low_surrogate:04x}"

def load_translation_table(filename):
    translation_dict = {}
    try:
        with open(filename, 'r', encoding='utf-8') as file:
            for line in file:
                parts = line.strip().split()
                if len(parts) >= 2:
                    old_code, new_code = parts[:2]
                    old_char = chr(int(old_code, 16))
                    new_char = chr(int(new_code, 16))
                    old_escape = f"\\u{old_code.lower()}"
                    new_escape = unicode_to_surrogate_pair(new_code)
                    translation_dict[old_char] = new_char
                    translation_dict[old_escape] = new_escape
    except FileNotFoundError:
        print(f"Error: The file '{filename}' was not found.")
        sys.exit(1)
    except Exception as e:
        print(f"An error occurred: {e}")
        sys.exit(1)
    return translation_dict

def replace_codepoints(text_content, translation_dict):
    for old_pattern, new_pattern in translation_dict.items():
        text_content = text_content.replace(old_pattern, new_pattern)
    return text_content

def process_directory(source_dir, dest_dir, translation_dict):
    supported_extensions = {'.json', '.yaml', '.yml', '.toml'}
    for root, dirs, files in os.walk(source_dir):
        for file in files:
            file_path = os.path.join(root, file)
            file_ext = os.path.splitext(file)[1]
            if file_ext in supported_extensions:
                with open(file_path, 'r', encoding='utf-8') as f:
                    content = f.read()

                updated_content = replace_codepoints(content, translation_dict)

                dest_file_path = os.path.join(dest_dir, file)
                os.makedirs(os.path.dirname(dest_file_path), exist_ok=True)
                with open(dest_file_path, 'w', encoding='utf-8') as f:
                    f.write(updated_content)

def main():
    if len(sys.argv) != 3:
        print("Usage: python script.py <source_directory> <destination_directory>")
        sys.exit(1)

    source_dir = sys.argv[1]
    dest_dir = sys.argv[2]
    table_filename = os.path.join(sys.path[0], "nerdfont-new-unicode-icon-lookup-table")
    translation_dict = load_translation_table(table_filename)

    process_directory(source_dir, dest_dir, translation_dict)

if __name__ == "__main__":
    main()