i18n.py

import json
import re
from googletrans import Translator
from bs4 import BeautifulSoup

# Function to translate text while preserving placeholders
def translate_text_with_placeholders(text, target_language):
    # Define placeholder pattern
    placeholder_pattern = re.compile(r'\$([^\$]+)\$', flags=re.IGNORECASE)
    
    # Split text into segments containing text and placeholders
    segments = placeholder_pattern.split(text)
    
    # Separate text and placeholders into arrays
    text_segments = [segments[i] for i in range(len(segments)) if i % 2 == 0]
    placeholder_segments = [segments[i] for i in range(len(segments)) if i % 2 == 1]
    
    # Translate text segments
    translated_text_segments = []
    for segment in text_segments:
        try:
            translation = Translator().translate(segment, dest=target_language).text
            translated_text_segments.append(translation)
        except Exception as e:
            translated_text_segments.append(segment)
    
    # Rebuild translated text by joining translated segments with placeholders
    translated_text = ''
    for i in range(len(text_segments)):
        translated_text += translated_text_segments[i]
        if i < len(placeholder_segments):
            translated_text += ' $' + placeholder_segments[i] + '$ '

    # Regular expression patterns
    pattern_dot = r'\$ \.'
    pattern_comma = r'\$ \,'
    pattern_end = r'(\$\s$)'

    # Perform replacement for all matches
    filtered_translated_text = re.sub(pattern_dot, r'$.', translated_text)
    filtered_translated_text = re.sub(pattern_comma, r'$,', filtered_translated_text)
    filtered_translated_text = re.sub(pattern_end, r'$', filtered_translated_text)

    return filtered_translated_text

# Function to translate HTML content while preserving placeholders
def translate_html_with_placeholders(key, html_content, target_language):
    # Parse HTML content
    soup = BeautifulSoup(html_content, 'html.parser')
    
    # Translate text within HTML tags
    for tag in soup.find_all(string=True):
        if not tag.strip():  # Skip empty strings
            continue
        translated_text = translate_text_with_placeholders(tag, target_language)
        tag.replace_with(translated_text)
    
    # Reconstruct translated HTML content
    translated_html = str(soup)
    
    return translated_html

# Read the JSON file
with open('messages.json', 'r') as file:
    data = json.load(file)

# Translate messages and update JSON
for key, value in data.items():
    # Translate the message
    translated_message = translate_html_with_placeholders(key, value["message"], "es")
    value["message"] = translated_message

# Write the updated JSON to a file
output_file = 'translated_file.json'
with open(output_file, 'w', encoding='utf-8') as file:
    json.dump(data, file, ensure_ascii=False, indent=2)

# Print that the file has been saved
print(f'The translated JSON file has been saved as "{output_file}"')