import streamlit as st
from transformers import AutoTokenizer, AutoModelForCausalLM
from sentence_transformers import SentenceTransformer, util
import PyPDF2
from docx import Document

# Load the tokenizer and model for sentence embeddings
@st.cache_resource
def load_model():
    tokenizer = AutoTokenizer.from_pretrained("rakeshkiriyath/gpt2Medium_text_to_sql")
    model = AutoModelForCausalLM.from_pretrained("rakeshkiriyath/gpt2Medium_text_to_sql")
    sentence_model = SentenceTransformer('all-MiniLM-L6-v2')  # Smaller, faster sentence embeddings model
    return tokenizer, model, sentence_model

# Extract text from a PDF file
def extract_text_from_pdf(pdf_file):
    pdf_reader = PyPDF2.PdfReader(pdf_file)
    text = ""
    for page in pdf_reader.pages:
        text += page.extract_text()
    return text

# Extract text from a Word document
def extract_text_from_word(docx_file):
    doc = Document(docx_file)
    text = ""
    for paragraph in doc.paragraphs:
        text += paragraph.text + "\n"
    return text

# Compare sentences for similarity
def compare_sentences(doc1_sentences, doc2_sentences, sentence_model):
    similar_sentences = []
    for i, sent1 in enumerate(doc1_sentences):
        best_match = None
        best_score = 0
        for j, sent2 in enumerate(doc2_sentences):
            score = util.pytorch_cos_sim(sentence_model.encode(sent1), sentence_model.encode(sent2)).item()
            if score > best_score:  # Higher similarity score
                best_score = score
                best_match = (i, j, score, sent1, sent2)
        if best_match and best_score > 0.6:  # Threshold for similarity
            similar_sentences.append(best_match)
    return similar_sentences

# Streamlit UI
def main():
    st.title("Comparative Analysis of Two Documents")
    st.sidebar.header("Upload Files")

    # Upload files
    uploaded_file1 = st.sidebar.file_uploader("Upload the First Document (PDF/Word)", type=["pdf", "docx"])
    uploaded_file2 = st.sidebar.file_uploader("Upload the Second Document (PDF/Word)", type=["pdf", "docx"])

    if uploaded_file1 and uploaded_file2:
        # Extract text from the uploaded documents
        text1 = extract_text_from_pdf(uploaded_file1) if uploaded_file1.name.endswith(".pdf") else extract_text_from_word(uploaded_file1)
        text2 = extract_text_from_pdf(uploaded_file2) if uploaded_file2.name.endswith(".pdf") else extract_text_from_word(uploaded_file2)

        # Split text into sentences
        doc1_sentences = text1.split('. ')
        doc2_sentences = text2.split('. ')

        # Load model
        tokenizer, model, sentence_model = load_model()

        # Perform sentence comparison
        similar_sentences = compare_sentences(doc1_sentences, doc2_sentences, sentence_model)

        # Display results
        st.header("Comparative Analysis Results")
        if similar_sentences:
            for match in similar_sentences:
                doc1_index, doc2_index, score, sent1, sent2 = match
                st.markdown(f"**Document 1 Sentence {doc1_index + 1}:** {sent1}")
                st.markdown(f"**Document 2 Sentence {doc2_index + 1}:** {sent2}")
                st.markdown(f"**Similarity Score:** {score:.2f}")
                st.markdown("---")
        else:
            st.info("No significantly similar sentences found.")

    else:
        st.warning("Please upload two documents to compare.")

if __name__ == "__main__":
    main()