from __future__ import annotations
import os
from typing import Dict, Any, Optional, List
from .firebase_loader import FirebaseNewsLoader
from .retriever import VectorNewsRetriever

class FirebaseVectorSync:
    def __init__(self, vector_persist_dir: str = "./vector_db"):
        # Auto-detect writable directory for Hugging Face Spaces
        if vector_persist_dir == "./vector_db":
            if os.path.exists("/data"):
                vector_persist_dir = "/data/vector_db"
            elif os.path.exists("/tmp"):
                vector_persist_dir = "/tmp/vector_db"
        
        self.firebase_loader = FirebaseNewsLoader()
        self.vector_retriever = VectorNewsRetriever(persist_directory=vector_persist_dir)
    def analyze_firebase_schema(self, collection: str = "Articles") -> Dict[str, Any]:
        schema = self.firebase_loader.analyze_schema(collection)
        return schema
    def sync_from_firebase(self, collection_name: str = "Articles", limit: Optional[int] = None) -> Dict[str, Any]:
        # If limit is None => fetch ALL via pagination logic in loader.
        arts = self.firebase_loader.load_news_articles(collection_name, limit if limit is not None else None)
        if not arts and collection_name != "Articles":
            arts = self.firebase_loader.load_news_articles("Articles", limit if limit is not None else None)
            if arts:
                collection_name = "Articles"
        if not arts:
            return {"error": "No articles found", "synced": 0, "success": False}
        self.vector_retriever.store_articles_in_vector_db(arts)
        return {"synced": len(arts), "collection": collection_name, "success": True}
    def quick_sync(self, limit: int = 100) -> Dict[str, Any]:
        return self.sync_from_firebase(limit=limit)
    def full_sync(self) -> Dict[str, Any]:
        return self.sync_from_firebase(limit=None)
    def list_firebase_collections(self) -> List[Dict[str, Any]]:
        return self.firebase_loader.get_collections_info()