import os
import subprocess
from flask import Flask, render_template, request, Response, jsonify
from rss_processor import fetch_rss_feeds, process_and_store_articles, vector_db
import logging
import time
import hashlib

app = Flask(__name__)

# Setup logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

@app.route('/')
def loading():
    # Start loading feeds in a subprocess
    subprocess.Popen(["python", "rss_processor.py", "load_feeds"])
    return render_template("loading.html")

@app.route('/check_feeds', methods=['GET'])
def check_feeds():
    try:
        # Check if vector DB has documents
        docs = vector_db.similarity_search("news", k=1)
        if docs:
            logger.info("Feeds loaded successfully in vector DB")
            return jsonify({"status": "loaded"})
        return jsonify({"status": "loading"}), 202
    except Exception as e:
        logger.error(f"Error checking feeds: {e}")
        return jsonify({"status": "error", "message": str(e)}), 500

@app.route('/index', methods=['GET'])
def index():
    # Show existing articles while new feeds load in background
    stored_docs = vector_db.similarity_search("news", k=1000)  # Show all available articles
    # Use a set to ensure unique articles by title, link, and description hash
    unique_articles = {}
    for doc in stored_docs:
        title = doc.metadata["title"]
        link = doc.metadata["link"]
        description = doc.metadata["original_description"]
        desc_hash = hashlib.md5(description.encode()).hexdigest()[:10]
        key = f"{title}|{link}|{desc_hash}"
        if key not in unique_articles:
            unique_articles[key] = {
                "title": title,
                "link": link,
                "description": description,
                "category": doc.metadata["category"],
                "published": doc.metadata["published"],
                "image": doc.metadata.get("image", "svg"),
            }
    enriched_articles = list(unique_articles.values())
    logger.info(f"Enriched {len(enriched_articles)} unique articles for display")

    if request.method == 'POST' and 'search' in request.form:
        query = request.form.get('search')
        if query:
            logger.info(f"Processing search query: {query}")
            results = vector_db.similarity_search(query, k=10)
            unique_search_articles = {}
            for doc in results:
                title = doc.metadata["title"]
                link = doc.metadata["link"]
                description = doc.metadata["original_description"]
                desc_hash = hashlib.md5(description.encode()).hexdigest()[:10]
                key = f"{title}|{link}|{desc_hash}"
                if key not in unique_search_articles:
                    unique_search_articles[key] = {
                        "title": title,
                        "link": link,
                        "description": description,
                        "category": doc.metadata["category"],
                        "published": doc.metadata["published"],
                        "image": doc.metadata.get("image", "svg"),
                    }
            enriched_articles = list(unique_search_articles.values())
            logger.info(f"Search returned {len(enriched_articles)} unique results")

    categorized_articles = {}
    for article in enriched_articles:
        cat = article["category"]
        if cat not in categorized_articles:
            categorized_articles[cat] = []
        categorized_articles[cat].append(article)

    return render_template("index.html", categorized_articles=categorized_articles, loading_new_feeds=True)

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