from __future__ import annotations
from typing import Dict, Any, Optional
from .config import load_openrouter_config
from .retriever import VectorNewsRetriever
from .analyzer import QueryRewriter, ClaimAnalyzer
from .firebase_loader import FirebaseNewsLoader

class FactCheckSystem:
    def __init__(self, api_key: Optional[str] = None, vector_dir: str = "./vector_db"):
        cfg = load_openrouter_config(api_key)
        self.cfg = cfg
        self.retriever = VectorNewsRetriever(persist_directory=vector_dir)
        self.rewriter = QueryRewriter(cfg)
        self.analyzer = ClaimAnalyzer(cfg)
        self.firebase = FirebaseNewsLoader()
    def ingest_firebase(self, collection: str = "english_articles", limit: int = 5000, language: str = "English") -> Dict[str, Any]:
        """Load articles from Firebase and store in vector DB with enhanced English articles support."""
        try:
            # Try to fetch from dedicated English articles collection first
            if language.lower() in ["english", "en"] and collection == "english_articles":
                print(f"🎯 Fetching from dedicated English articles collection...")
                arts = self.firebase.fetch_english_articles(limit=limit)
            else:
                print(f"🔍 Fetching from '{collection}' collection with language filter '{language}'...")
                arts = self.firebase.fetch_articles(limit=limit, language=language)
            
            if not arts:
                return {
                    "synced": 0, 
                    "collection": collection, 
                    "success": False, 
                    "error": f"No articles found in collection '{collection}'"
                }
            
            print(f"📚 Processing {len(arts)} articles for vector storage...")
            
            # Clear and refresh vector store
            self.retriever.store_articles_in_vector_db(arts, clear_first=True)
            
            return {
                "synced": len(arts), 
                "collection": collection, 
                "success": True, 
                "language": language,
                "message": f"Successfully ingested {len(arts)} articles"
            }
            
        except Exception as e:
            print(f"❌ Firebase ingestion error: {e}")
            return {
                "synced": 0, 
                "collection": collection, 
                "success": False, 
                "error": str(e)
            }
    def fact_check(self, claim: str, k: int = 5) -> Dict[str, Any]:
        base = self.retriever.semantic_search(claim, k=k)
        urls = {a.get("url", "") for a in base}
        for q in self.rewriter.rewrite(claim):
            more = self.retriever.semantic_search(q, k=3)
            for m in more:
                u = m.get("url", "")
                if u and u not in urls:
                    base.append(m)
                    urls.add(u)
        result = self.analyzer.analyze(claim, base[:8])
        result["sources_used"] = len(base[:8])
        result["retrieved_articles"] = [a.get("url", "") for a in base[:8]]
        return result