app.py

import os
import json
import gradio as gr
import fasttext
from google.cloud import translate_v2 as translate
from transformers import pipeline
from dotenv import load_dotenv
import subprocess


BASE_DIR = os.path.dirname(os.path.abspath(__file__))
MODEL_PATH = os.path.join(BASE_DIR, "models", "lid.176.bin")
fasttext_model = fasttext.load_model(MODEL_PATH)

# model = fasttext.load_model("models\lid.176.bin")
# print(model.predict("Hello world"))

# --- Setup FastText model (download if missing) ---
# MODEL_PATH = "C:/_Prep/_code/Python/language-detection-compare-models/models/lid.176.bin"
# os.makedirs("models", exist_ok=True)
# if not os.path.exists(MODEL_PATH):
#     os.system(
#         f"wget -O {MODEL_PATH} https://dl.fbaipublicfiles.com/fasttext/supervised-models/lid.176.bin"
#     )

try:
    fasttext_model = fasttext.load_model(MODEL_PATH)
except ValueError:
    raise RuntimeError("FastText model file could not be loaded.")

# --- Setup Google Translate Client ---
# google_creds = os.getenv("GOOGLE_APPLICATION_CREDENTIALS")
# if google_creds:
#     with open("google_creds.json", "w") as f:
#         f.write(google_creds)
#     os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = "google_creds.json"
#     translate_client = translate.Client()
# else:
#     translate_client = None

#print("Current working directory:", os.getcwd())
#load_dotenv(dotenv_path=r"C:\_Prep\_code\Python\language-detection-compare-models\.env")  # If needed
#C:\_Prep\_code\Python\language-detection-compare-models\.env

google_creds_path = os.getenv("GOOGLE_APPLICATION_CREDENTIAL")
#print("Resolved GOOGLE_APPLICATION_CREDENTIALS:", google_creds_path)

# load_dotenv()

# google_creds_path = os.getenv("GOOGLE_APPLICATION_CREDENTIALS")


#google_creds_path = os.getenv("GOOGLE_APPLICATION_CREDENTIALS")
if google_creds_path and os.path.isfile(google_creds_path):
    os.environ["GOOGLE_APPLICATION_CREDENTIAL"] = google_creds_path  # redundant but explicit
    from google.cloud import translate_v2 as translate
    translate_client = translate.Client()
else:
    translate_client = None


# --- Setup Hugging Face pipeline ---
HF_MODEL_NAME = "papluca/xlm-roberta-base-language-detection"
hf_lang_detector = pipeline("text-classification", model=HF_MODEL_NAME)

# --- Mapping ISO 639-1 language codes to countries with flag emojis ---
# Source: filtered and truncated for top 5 countries (edit as needed)
LANGUAGE_TO_COUNTRIES = {
    "en": ["US", "GB", "CA", "AU", "IN"],
    "fr": ["FR", "BE", "CA", "CH", "LU"],
    "es": ["ES", "MX", "CO", "AR", "PE"],
    "de": ["DE", "AT", "CH", "LU", "BE"],
    "ar": ["EG", "SA", "IQ", "DZ", "MA"],
    "hi": ["IN", "FJ", "MU", "NP", "SG"],
    "zh": ["CN", "SG", "MY", "TW", "HK"],
    "ru": ["RU", "BY", "KZ", "UA", "KG"],
    "pt": ["PT", "BR", "AO", "MZ", "GW"],
    "ja": ["JP"],
    "ko": ["KR"],
}

def flag_emoji(country_code):
    return "".join(chr(0x1F1E6 + ord(c) - ord('A')) for c in country_code)

def render_result(model_name, lang_code, score):
    flags = LANGUAGE_TO_COUNTRIES.get(lang_code, [])
    if flags:
        flag_str = " ".join(flag_emoji(c) for c in flags[:5])
        etc = "<br>...etc" if len(flags) > 5 else ""
    else:
        flag_str = "🌐"
        etc = ""
    return f"<b>{model_name}:</b> <code>{lang_code}</code> ({score})<br>{flag_str}{etc}"

# def detect_languages(text, hf_model_path=None):
#     # FastText
#     try:
#         ft_label, ft_score = fasttext_model.predict(text, k=1)
#         ft_lang = ft_label[0].replace("__label__", "")
#         ft_score = round(ft_score[0], 3)
#     except Exception:
#         ft_lang, ft_score = "Error", 0

#     # Google Translate
#     if translate_client:
#         try:
#             result = translate_client.detect_language(text)
#             google_lang = result.get("language", "N/A")
#             google_conf = round(result.get("confidence", 0), 3)
#         except Exception:
#             google_lang, google_conf = "Error", 0
#     else:
#         google_lang, google_conf = "NotConfigured", 0

#     # Hugging Face
#     try:
#         model = (
#             pipeline("text-classification", model=hf_model_path)
#             if hf_model_path and hf_model_path.strip()
#             else hf_lang_detector
#         )
#         hf_results = model(text)
#         hf_lang = hf_results[0]["label"].lower()
#         hf_score = round(hf_results[0]["score"], 3)
#     except Exception:
#         hf_lang, hf_score = "Error", 0

#     return (
#         render_result("FastText", ft_lang, ft_score),
#         render_result("Google", google_lang, google_conf),
#         render_result("HuggingFace", hf_lang, hf_score)
#     )

from langcodes import Language

# Maps language code to top 5 countries where it's predominantly spoken
LANG_COUNTRY_MAP = {
    'af': ['ZA', 'NA'],
    'am': ['ET'],
    'ar': ['SA', 'EG', 'IQ', 'MA', 'DZ', 'SD', 'SY', 'YE', 'JO', 'LB', 'TN', 'AE', 'OM', 'KW', 'BH', 'QA', 'LY'],
    'az': ['AZ'],
    'be': ['BY'],
    'bg': ['BG'],
    'bn': ['BD', 'IN'],
    'bs': ['BA'],
    'ca': ['ES', 'AD'],
    'ceb': ['PH'],
    'cs': ['CZ'],
    'cy': ['GB'],
    'da': ['DK'],
    'de': ['DE', 'AT', 'CH', 'LU', 'BE', 'LI'],
    'el': ['GR', 'CY'],
    'en': ['US', 'GB', 'CA', 'AU', 'NZ', 'IE', 'ZA', 'IN', 'PH', 'NG', 'KE', 'UG'],
    'eo': ['PL', 'FR', 'DE', 'US'],
    'es': ['ES', 'MX', 'CO', 'AR', 'PE', 'VE', 'CL', 'EC', 'GT', 'CU', 'BO', 'DO', 'HN', 'PY', 'SV', 'NI', 'CR', 'PA', 'UY'],
    'et': ['EE'],
    'eu': ['ES', 'FR'],
    'fa': ['IR', 'AF', 'TJ'],
    'fi': ['FI'],
    'fil': ['PH'],
    'fj': ['FJ'],
    'fr': ['FR', 'BE', 'CA', 'CH', 'LU', 'CI', 'SN', 'ML', 'CM', 'HT', 'MG', 'NE', 'TG', 'GA', 'CD', 'BF', 'TD'],
    'fy': ['NL'],
    'ga': ['IE'],
    'gd': ['GB'],
    'gl': ['ES'],
    'gu': ['IN'],
    'ha': ['NG', 'NE', 'GH'],
    'haw': ['US'],
    'he': ['IL'],
    'hi': ['IN', 'FJ', 'MU', 'NP', 'SG'],
    'hmn': ['US'],
    'hr': ['HR', 'BA'],
    'ht': ['HT'],
    'hu': ['HU'],
    'hy': ['AM'],
    'id': ['ID'],
    'ig': ['NG'],
    'is': ['IS'],
    'it': ['IT', 'CH', 'SM'],
    'ja': ['JP'],
    'jv': ['ID'],
    'ka': ['GE'],
    'kk': ['KZ'],
    'km': ['KH'],
    'kn': ['IN'],
    'ko': ['KR', 'KP'],
    'ku': ['IQ', 'TR', 'SY', 'IR'],
    'ky': ['KG'],
    'la': ['VA'],
    'lb': ['LU'],
    'lo': ['LA'],
    'lt': ['LT'],
    'lv': ['LV'],
    'mg': ['MG'],
    'mi': ['NZ'],
    'mk': ['MK'],
    'ml': ['IN'],
    'mn': ['MN'],
    'mr': ['IN'],
    'ms': ['MY', 'BN', 'SG'],
    'mt': ['MT'],
    'my': ['MM'],
    'ne': ['NP'],
    'nl': ['NL', 'BE', 'SR', 'AW', 'CW'],
    'no': ['NO'],
    'ny': ['MW', 'ZM', 'ZW'],
    'pa': ['IN', 'PK'],
    'pl': ['PL'],
    'ps': ['AF'],
    'pt': ['PT', 'BR', 'AO', 'MZ', 'GW', 'ST', 'CV'],
    'ro': ['RO', 'MD'],
    'ru': ['RU', 'BY', 'KZ', 'KG', 'UA'],
    'rw': ['RW'],
    'sd': ['PK'],
    'si': ['LK'],
    'sk': ['SK'],
    'sl': ['SI'],
    'sm': ['WS'],
    'sn': ['ZW'],
    'so': ['SO'],
    'sq': ['AL', 'XK', 'MK'],
    'sr': ['RS', 'BA', 'ME'],
    'st': ['LS'],
    'su': ['ID'],
    'sv': ['SE', 'FI'],
    'sw': ['KE', 'TZ', 'UG'],
    'ta': ['IN', 'LK', 'SG', 'MY'],
    'te': ['IN'],
    'tg': ['TJ'],
    'th': ['TH'],
    'ti': ['ET', 'ER'],
    'tk': ['TM'],
    'tl': ['PH'],
    'tr': ['TR', 'CY'],
    'tt': ['RU'],
    'ug': ['CN'],
    'uk': ['UA'],
    'ur': ['PK', 'IN'],
    'uz': ['UZ'],
    'vi': ['VN'],
    'xh': ['ZA'],
    'yi': ['US', 'IL'],
    'yo': ['NG'],
    'zh': ['CN', 'SG', 'MY', 'TW'],
    'zu': ['ZA'],
}


def country_flag_img(country_code):
    #return f"<img src='https://flagcdn.com/w40/{country_code.lower()}.png' height='20' style='margin-right:4px'/><br/>"
    return f"<img src='https://flagcdn.com/w40/{country_code.lower()}.png' title='{LANG_COUNTRY_MAP.get(country_code, country_code)}' height='20' style='margin-right:4px'/><br/>"

def format_with_flags(lang_code):
    countries = LANG_COUNTRY_MAP.get(lang_code, [])
    flags_html = ''.join([country_flag_img(c) for c in countries[:5]])
    if len(countries) > 5:
        flags_html += "<span style='margin-left:4px;'>etc...</span>"
    return flags_html

def detect_languages(text, hf_model_path=None):
    ft_label, ft_score = fasttext_model.predict(text, k=1)
    ft_lang = ft_label[0].replace("__label__", "")
    ft_score = round(ft_score[0], 3)

    if translate_client:
        try:
            result = translate_client.detect_language(text)
            google_lang = result.get("language", "N/A")
            google_conf = round(result.get("confidence", 0), 3)
        except Exception:
            google_lang = "Error"
            google_conf = 0
    else:
        google_lang = "Not Configured"
        google_conf = 0

    if hf_model_path and hf_model_path.strip() != "":
        try:
            custom_detector = pipeline("text-classification", model=hf_model_path)
            hf_results = custom_detector(text)
        except Exception:
            hf_results = [{"label": "Error", "score": 0}]
    else:
        hf_results = hf_lang_detector(text)

    hf_label = hf_results[0]["label"].lower()
    hf_score = round(hf_results[0]["score"], 3)

    return (
        f"FastText: {ft_lang} ({ft_score})<br>{format_with_flags(ft_lang)}",
        f"Google API: {google_lang} ({google_conf})<br>{format_with_flags(google_lang)}",
        f"HuggingFace: {hf_label} ({hf_score})<br>{format_with_flags(hf_label)}"
    )

with gr.Blocks() as demo:
    gr.Markdown("## 🌍 Language Detection Comparison")

    with gr.Row():
        input_text = gr.TextArea(label="Enter text", lines=4, placeholder="Type text to detect language...", value="Die Renaissance war eine kulturelle und intellektuelle Bewegung, die im 14. Jahrhundert in Italien begann und sich bis ins 17. Jahrhundert über Europa ausbreitete. Sie markierte eine Wiederbelebung der klassischen Kunst, Literatur und Wissenschaft, die den Humanismus, die wissenschaftliche Forschung und den individuellen Ausdruck betonte. Zu den Schlüsselpersonen gehören Leonardo da Vinci, Michelangelo und Galileo.")

    with gr.Row():
        hf_model_path = gr.Textbox(label="HuggingFace Model Path (optional)", value="papluca/xlm-roberta-base-language-detection", placeholder="e.g. papluca/xlm-roberta-base-language-detection")

    detect_btn = gr.Button("Detect Language")

    with gr.Row():
        fasttext_out = gr.HTML(label="FastText")
        google_out = gr.HTML(label="Google")
        hf_out = gr.HTML(label="Hugging Face")

    detect_btn.click(
        detect_languages,
        inputs=[input_text, hf_model_path],
        outputs=[fasttext_out, google_out, hf_out]
    )

if __name__ == "__main__":
    demo.launch()