import display_gloss as dg
import synonyms_preprocess as sp
from NLP_Spacy_base_translator import NlpSpacyBaseTranslator 
from flask import Flask, render_template, Response, request
import requests

app = Flask(__name__)

# Initialize data
nlp, dict_docs_spacy = sp.load_spacy_values()
dataset, list_2000_tokens = dg.load_data()

def translate_korean_to_english(text):
    url = "https://translate.googleapis.com/translate_a/single"
    params = {
        "client": "gtx",
        "sl": "ko",
        "tl": "en",
        "dt": ["t", "bd"],  # Added "bd" for better translation
        "q": text
    }
    try:
        response = requests.get(url, params=params)
        translation = response.json()[0][0][0]
        # Basic post-processing
        translation = translation.replace("It is", "").replace("There is", "").strip()
        return translation
    except Exception as e:
        print(f"Translation error: {e}")
        return text

def process_gloss_conversion(english_text):
    # Custom mapping for common Korean-specific terms
    term_mapping = {
        "Korea": "KOREA",
        "Seoul": "SEOUL",
        "four seasons": "FOUR SEASON",
        "beautiful": "BEAUTIFUL",
        "country": "COUNTRY"
    }
    
    # Apply mappings before ASL conversion
    for term, replacement in term_mapping.items():
        english_text = english_text.replace(term.lower(), replacement)
    
    return english_text

@app.route('/')
def index():
    return render_template('index.html')

@app.route('/translate/', methods=['POST'])
def result():
    if request.method == 'POST':
        input_text = request.form['inputSentence']
        
        # Check if input is Korean (simplified check)
        is_korean = any(ord('가') <= ord(char) <= ord('힣') for char in input_text)
        
        if is_korean:
            english_translation = translate_korean_to_english(input_text)
        else:
            english_translation = input_text
            
        # Pre-process for better ASL conversion
        processed_english = process_gloss_conversion(english_translation)
        
        # Convert to ASL
        eng_to_asl_translator = NlpSpacyBaseTranslator(sentence=processed_english)
        generated_gloss = eng_to_asl_translator.translate_to_gloss()
        
        gloss_list_lower = [gloss.lower() for gloss in generated_gloss.split() if gloss.isalnum()]
        gloss_sentence_before_synonym = " ".join(gloss_list_lower)
        
        # Apply custom synonym rules
        gloss_list = [sp.find_synonyms(gloss, nlp, dict_docs_spacy, list_2000_tokens) 
                     for gloss in gloss_list_lower]
        gloss_sentence_after_synonym = " ".join(gloss_list)
        
        return render_template('result.html',
                            original_sentence=input_text,
                            english_translation=english_translation,
                            gloss_sentence_before_synonym=gloss_sentence_before_synonym,
                            gloss_sentence_after_synonym=gloss_sentence_after_synonym)

@app.route('/video_feed')
def video_feed():
    sentence = request.args.get('gloss_sentence_to_display', '')
    gloss_list = sentence.split()
    return Response(dg.generate_video(gloss_list, dataset, list_2000_tokens), 
                   mimetype='multipart/x-mixed-replace; boundary=frame')

if __name__ == "__main__":
    app.run(host="0.0.0.0", port=5000, debug=True)