from bs4 import BeautifulSoup
from langdetect import detect, DetectorFactory
import re
import os

# Set seed for consistent language detection results
DetectorFactory.seed = 0

def extract_text_from_html(html_content):
    """Extracts visible text from HTML content."""
    soup = BeautifulSoup(html_content, 'html.parser')

    # Remove script and style elements
    for script in soup(['script', 'style']):
        script.decompose()

    # Get text and clean up whitespace
    text = soup.get_text(separator=' ')
    text = re.sub(r'\s+', ' ', text).strip()
    return text

def detect_language(text):
    """Detects the language of a given text."""
    try:
        return detect(text)
    except:
        return "unknown"

def analyze_email_with_subject(html_file_path: str, subject: str):
    """Reads HTML template from file, combines with subject, and detects language."""
    # Read HTML content from file
    with open(html_file_path, 'r', encoding='utf-8') as file:
        html_content = file.read()

    # Extract text from HTML
    html_text = extract_text_from_html(html_content)

    # Combine subject and body text
    combined_text = subject.strip() + " " + html_text

    # Detect language of the combined text
    language = detect_language(combined_text)

    return language


# 🔽 Example usage:
if __name__ == "__main__":
    fr_subject = "À BIENTÔT FRANCE⭐️"
    # en_subject = "SEE YOU SOON SWEDEN⭐️⭐️⭐️"
    html_file = os.path.join(os.path.dirname(__file__), 'tate_mcrae_french_template.html')

    detected_language = analyze_email_with_subject(html_file, fr_subject)

    print("Detected language of email content and subject:", detected_language)

"CA": {
    "default": {
        "name": "Sony Music Entertainment Canada Inc.",
        "address": "99 Atlantic Avenue, Suite 800, Toronto, Ontario, M6K 3J8"
    },
    "fr": {
        "name": "Sony Music Entertainment Canada Inc.",
        "address": "99 avenue Atlantic, bureau 800, Toronto, Ontario, M6K 3J"
    }
}