import streamlit as st
import nltk
from nltk.corpus import stopwords
from nltk.cluster.util import cosine_distance
import numpy as np
import networkx as nx
from googletrans import Translator

# Download NLTK resources
nltk.download('punkt')
nltk.download('stopwords')

def read_article(article):
    sentences = nltk.sent_tokenize(article)
    sentences = [sentence for sentence in sentences if len(sentence) > 10]  # filter very short sentences
    return sentences

def sentence_similarity(sent1, sent2, stopwords):
    words1 = nltk.word_tokenize(sent1)
    words2 = nltk.word_tokenize(sent2)

    words1 = [word.lower() for word in words1 if word.isalnum()]
    words2 = [word.lower() for word in words2 if word.isalnum()]

    all_words = list(set(words1 + words2))

    vector1 = [0] * len(all_words)
    vector2 = [0] * len(all_words)

    for word in words1:
        if word in stopwords:
            continue
        vector1[all_words.index(word)] += 1

    for word in words2:
        if word in stopwords:
            continue
        vector2[all_words.index(word)] += 1

    return 1 - cosine_distance(vector1, vector2)

def build_similarity_matrix(sentences, stopwords):
    similarity_matrix = np.zeros((len(sentences), len(sentences)))

    for i in range(len(sentences)):
        for j in range(len(sentences)):
            if i == j:  
                continue
            similarity_matrix[i][j] = sentence_similarity(sentences[i], sentences[j], stopwords)

    return similarity_matrix

def generate_summary(article, top_n=5):
    sentences = read_article(article)
    stop_words = set(stopwords.words('english'))
    sentence_similarity_matrix = build_similarity_matrix(sentences, stop_words)

    sentence_similarity_graph = nx.from_numpy_array(sentence_similarity_matrix)

    scores = nx.pagerank(sentence_similarity_graph)

    ranked_sentences = sorted(((scores[i], sentence) for i, sentence in enumerate(sentences)), reverse=True)

    summary = " ".join([sentence for _, sentence in ranked_sentences[:top_n]])
    return summary

# Set page configuration and styles
st.set_page_config(page_title="Article Summarizer", page_icon="✍️")
st.title("We sumerize and translate your articles")

st.markdown(
    """
    <style>
    .stApp {
        background-color: orange;
        color: #333;
    }
    .stButton button {
        background-color: black;
        color: white;
        border-radius: 5px;
    }
    .stTextInput input {
        color: #333;
        border: 1px solid #008CBA;
        border-radius: 5px;
    }
    .stText {
        color: #333;
    }
    </style>
    """,
    unsafe_allow_html=True,
)

# Input text area
user_article = st.text_area("✒️ Enter your article here:", height=100)

# Translation options
translate = st.checkbox("🌐 Translate Summary")
if translate:
    target_language = st.selectbox("🌎 Select Target Language", ["🇺🇸 English", "🇫🇷 French", "🇪🇸 Spanish", "🇩🇪 German"])

# Summarize button
if st.button("Summarize"):
    if user_article:
        summary = generate_summary(user_article)
        st.subheader("📄 Summary:")
        st.write(summary)

        # Translation logic
        if translate:
            if target_language == "🇺🇸 English":
                target_language_code = "en"
            elif target_language == "🇫🇷 French":
                target_language_code = "fr"
            elif target_language == "🇪🇸 Spanish":
                target_language_code = "es"
            elif target_language == "🇩🇪 German":
                target_language_code = "de"

            translator = Translator()
            translated_summary = translator.translate(summary, dest=target_language_code)
            st.subheader("🌐 Translated Summary:")
            st.write(translated_summary.text)
    else:
        st.warning("🚫 Please enter an article to summarize.")