import os
import re
import argparse
import shutil
import zipfile
from tqdm import tqdm
import hashlib
import base64

def base64_hash(s):
    b64 = base64.b64encode(s.encode()).decode()
    hash_str = ''.join(filter(lambda c: not c.isdigit(), b64))
    return hash_str[:16].lower()


def md5_hash_without_digits(text: str) -> str:
    # Convert text to bytes and calculate MD5 hash
    hash_object = hashlib.md5(text.encode())

    # Get hex representation of the hash, remove digits, and lowercase
    hash_str = hash_object.hexdigest()
    hash_str_no_digits = hash_str
    # hash_str_no_digits = ''.join(c for c in hash_str if not c.isdigit())
    hash_str_no_digits_lower = hash_str_no_digits.lower()

    # Return the first 8 characters of the hash string
    return hash_str_no_digits_lower


def process_js_files(extracted_folder):
    # Step 2: Find all files in the specified folder that meet the *_interface.js mask
    files_to_process = []
    for root, dirs, files in os.walk(extracted_folder):
        for file in files:
            if file.endswith("_interface.js"):
                files_to_process.append(os.path.join(root, file))

    # Step 3: Map id and description inside a dictionary
    dictionary = {}
    for file_path in tqdm(files_to_process, desc="Processing files"):
        with open(file_path, "r", encoding='utf-8') as f:
            file_name = os.path.basename(file_path)
            prefix = file_name.split("_")[0:-1]  # Get all parts of the filename before "_interface.js"
            prefix = "_".join(prefix)
            content = f.read()
            matches = re.findall(r"\{id:\"(\w+)\", description:\"(\w+)\"", content)
            for match in matches:
                if match[0] == 'Save':
                    continue

                dictionary[match[0]] = base64_hash(md5_hash_without_digits(match[1] + "_" + prefix))

    # Step 5: Find all js files inside folder and replace all substrings represented in dictionary as keys with their values inside dictionary
    for root, dirs, files in os.walk(extracted_folder):
        for file_path in tqdm(files, desc="Replacing substrings"):
            if file_path.endswith(".js"):
                with open(os.path.join(root, file_path), "r+", encoding='utf-8') as f:
                    content = f.read()
                    for key in dictionary:
                        content = content.replace(key, dictionary[key])
                    f.seek(0)
                    f.write(content)
                    f.truncate()


def create_updated_archive(input_archive_path):
    # Step 1: Unzip the archive and get the path to the folder containing the JS files
    with zipfile.ZipFile(input_archive_path, "r") as zip_ref:
        extracted_folder = zip_ref.namelist()[0]
        extracted_folder = os.path.join("temp", extracted_folder)
        zip_ref.extractall("temp")

    process_js_files(extracted_folder)

    # Step 6: Zip the updated files and replace the original archive
    output_archive_path = input_archive_path[:-4] + "_updated.zip"
    with zipfile.ZipFile(output_archive_path, "w") as zip_ref:
        for root, dirs, files in os.walk(extracted_folder):
            for file in files:
                file_path = os.path.join(root, file)
                archive_path = os.path.join(input_archive_path[:-4], file_path[len(extracted_folder):])
                zip_ref.write(file_path, arcname=archive_path)

    # Clean up temporary files
    shutil.rmtree("temp")

    # Replace the original archive with the updated archive
    os.remove(input_archive_path)
    os.rename(output_archive_path, input_archive_path)


if __name__ == "__main__":
    # Parse command line arguments
    parser = argparse.ArgumentParser(description="Process JS files inside a ZIP archive.")
    parser.add_argument("archive", help="path to the ZIP archive containing the folder with JS files")
    args = parser.parse_args()

    specified_archive_path = args.archive

    create_updated_archive(specified_archive_path)