import os
import streamlit as st
import arxiv
import requests
import datetime
import networkx as nx
import matplotlib.pyplot as plt

# -------------------------------
# Groq API Client
# -------------------------------
from groq import Groq

client = Groq(
    api_key=os.environ.get("GROQ_API_KEY"),
)

# -------------------------------
# Helper Functions (Groq-based)
# -------------------------------
def groq_summarize(text: str) -> str:
    """
    Summarize the given text using Groq's chat completion API.
    """
    response = client.chat.completions.create(
        messages=[
            {"role": "user", "content": f"Summarize the following text in detail:\n\n{text}"}
        ],
        model="llama-3.3-70b-versatile",
    )
    return response.choices[0].message.content.strip()

# -------------------------------
# Trust & Relevance Scores
# -------------------------------
def get_citation_metadata(arxiv_id):
    """Fetch trust & relevance scores from external sources."""
    metadata = {"citations": 0, "trust_score": 0, "relevance_score": 0, "links": {}}

    # Fetch citation data from scite.ai
    scite_url = f"https://api.scite.ai/papers/{arxiv_id}"
    response = requests.get(scite_url)
    if response.status_code == 200:
        scite_data = response.json()
        metadata["citations"] = scite_data.get("citation_count", 0)
        metadata["trust_score"] = scite_data.get("trust_score", 0)

    # Generate Connected Papers & Litmaps links
    metadata["links"]["Connected Papers"] = f"https://www.connectedpapers.com/main/{arxiv_id}"
    metadata["links"]["Bibliographic Explorer"] = f"https://arxiv.org/bib_explorer/{arxiv_id}"
    metadata["links"]["Litmaps"] = f"https://www.litmaps.com/publications/{arxiv_id}"

    # Calculate relevance score
    metadata["relevance_score"] = metadata["citations"] * 0.8 + metadata["trust_score"] * 0.2

    return metadata

# -------------------------------
# Retrieve Papers
# -------------------------------
def retrieve_papers(query, max_results=5):
    """Retrieve academic papers from arXiv & add Trust/Relevance scores."""
    search = arxiv.Search(query=query, max_results=max_results)
    papers = []

    for result in search.results():
        paper_id = result.entry_id.split("/")[-1]  # Extract arXiv ID
        metadata = get_citation_metadata(paper_id)

        paper = {
            "title": result.title,
            "summary": result.summary,
            "url": result.pdf_url,
            "authors": [author.name for author in result.authors],
            "published": result.published,
            "citations": metadata["citations"],
            "trust_score": metadata["trust_score"],
            "relevance_score": metadata["relevance_score"],
            "links": metadata["links"],
        }
        papers.append(paper)

    return papers

# -------------------------------
# Streamlit Interface
# -------------------------------
st.title("📚 PaperPilot – Intelligent Academic Navigator")

# Sidebar: Search & Toggle
with st.sidebar:
    st.header("🔍 Search Parameters")
    query = st.text_input("Research topic or question:")
    show_scores = st.checkbox("Enable Trust & Relevance Scores", value=True)
    
    if st.button("🚀 Find Articles"):
        if query.strip():
            with st.spinner("Searching arXiv..."):
                papers = retrieve_papers(query)
                if papers:
                    st.session_state.papers = papers
                    st.session_state.active_section = "articles"
                    st.success(f"Found {len(papers)} papers!")
                else:
                    st.error("No papers found. Try different keywords.")
        else:
            st.warning("Please enter a search query")

# Main Content
if 'papers' in st.session_state and st.session_state.papers:
    papers = st.session_state.papers

    st.header("📑 Retrieved Papers")
    for idx, paper in enumerate(papers, 1):
        with st.expander(f"{idx}. {paper['title']}"):
            st.markdown(f"**Authors:** {', '.join(paper['authors'])}")
            st.markdown(f"**Published:** {paper['published']}")
            st.markdown(f"**Link:** [PDF]({paper['url']})")

            # Show Trust & Relevance Scores if enabled
            if show_scores:
                st.markdown(f"📊 **Citations:** {paper['citations']}")
                st.markdown(f"🛡️ **Trust Score:** {round(paper['trust_score'], 2)} / 10")
                st.markdown(f"🔍 **Relevance Score:** {round(paper['relevance_score'], 2)} / 10")
                
                # External Links
                st.markdown(f"[🔗 Connected Papers]({paper['links']['Connected Papers']})")
                st.markdown(f"[📖 Bibliographic Explorer]({paper['links']['Bibliographic Explorer']})")
                st.markdown(f"[📊 Litmaps]({paper['links']['Litmaps']})")

            # Display Summary
            st.markdown("**Abstract:**")
            st.write(paper['summary'])

st.caption("Built with ❤️ using AI")