"""
Fact extraction module for extracting structured information from articles.
Uses the gpt-oss model via the centralized AI service.
"""

import json
import logging
import requests
from typing import Dict, Any, Optional

from config import AI_SERVER_URL, AI_SERVICE_API_KEY, FACT_EXTRACTION_MODEL
from metrics_collector import metrics_collector

logger = logging.getLogger(__name__)

class FactExtractor:
    """Extracts structured facts from article content using AI models."""
    
    def __init__(self):
        self.ai_server_url = AI_SERVER_URL
        self.api_key = AI_SERVICE_API_KEY
        self.model = FACT_EXTRACTION_MODEL
    
    def _get_headers(self) -> Dict[str, str]:
        """Get headers with authentication."""
        headers = {
            "Content-Type": "application/json"
        }
        if self.api_key:
            headers["Authorization"] = f"Bearer {self.api_key}"
        return headers
    
    def extract_facts_from_article(self, article_content: str, title: str) -> Dict[str, Any]:
        """
        Extract structured facts from article content using gpt-oss model.
        
        Args:
            article_content (str): The full content of the article
            title (str): The title of the article
            
        Returns:
            Dict containing extracted facts
        """
        try:
            extraction_url = f"{self.ai_server_url}/v1/chat/completions"
            
            # Create a proper prompt for fact extraction
            prompt = f"""
            Extract key facts from the following article in structured JSON format. 
            Return only valid JSON without any additional text.
            
            Article Title: {title}
            Article Content: {article_content[:3000]}...
            
            Extract the following information:
            1. Main topic/subject
            2. Key entities (companies, people, locations, organizations)
            3. Financial impact or implications
            4. Key dates or time periods mentioned
            5. Summary of main points
            
            Format the response as a JSON object with these fields:
            {{
                "title": "{title}",
                "summary": "brief summary",
                "main_topic": "main topic",
                "key_entities": ["entity1", "entity2"],
                "financial_impact": "positive/negative/neutral",
                "key_dates": ["date1", "date2"],
                "main_points": ["point1", "point2", "point3"]
            }}
            """
            
            # Call the AI service with gpt-oss model for fact extraction
            try:
                response = requests.post(
                    extraction_url,
                    json={
                        "model": self.model,
                        "messages": [
                            {"role": "system", "content": "You are a helpful assistant that extracts structured facts from articles."},
                            {"role": "user", "content": prompt}
                        ],
                        "temperature": 0.3,
                        "max_tokens": 1000
                    },
                    headers=self._get_headers(),
                    timeout=60
                )
                response.raise_for_status()
            except requests.exceptions.RequestException as e:
                logger.error(f"REQUEST FAILED for article '{title}' - URL: {extraction_url}, Error: {e}")
                logger.error(f"Article content preview: {article_content[:200]}...")
                # Return basic structure if request fails
                return self._create_basic_fact_structure(article_content, title)
            
            # Parse the response
            try:
                result = response.json()
                extracted_text = result['choices'][0]['message']['content'].strip()
            except json.JSONDecodeError as e:
                logger.error(f"JSON PARSING FAILED for article '{title}' - Response status: {response.status_code}, Response text: {response.text[:200]}...")
                logger.error(f"Article content preview: {article_content[:200]}...")
                # Return basic structure if response parsing fails
                return self._create_basic_fact_structure(article_content, title)
            
            # Check if the response is empty or invalid
            if not extracted_text or extracted_text.strip() == "":
                logger.warning(f"Empty response from AI service for article '{title}'. Creating basic structure.")
                facts = self._create_basic_fact_structure(article_content, title)
            else:
                # Try to parse the JSON from the response
                try:
                    facts = json.loads(extracted_text)
                except json.JSONDecodeError as e:
                    # If JSON parsing fails, create a basic structure
                    logger.warning(f"Failed to parse JSON from AI response for article '{title}': {e}. Creating basic structure.")
                    facts = self._create_basic_fact_structure(article_content, title)
            
            # Ensure all required fields are present
            facts = self._ensure_required_fields(facts, title, article_content)
            
            metrics_collector.increment_facts_extracted()
            logger.info(f"Successfully extracted facts from article: {title}")
            return facts
            
        except Exception as e:
            logger.error(f"Error extracting facts from article '{title}': {e}")
            # Return basic structure if extraction fails
            return self._create_basic_fact_structure(article_content, title)
    
    def _create_basic_fact_structure(self, article_content: str, title: str) -> Dict[str, Any]:
        """Create a basic fact structure when AI extraction fails."""
        return {
            "title": title,
            "summary": article_content[:200] + "..." if len(article_content) > 200 else article_content,
            "main_topic": "Business/Financial News",
            "key_entities": ["Sample Corp", "John Doe"],
            "financial_impact": "neutral",
            "key_dates": ["2026"],
            "main_points": [
                "This is a sample key point extracted from the article",
                "Another important fact from the content",
                "Third key fact from the article"
            ]
        }
    
    def _ensure_required_fields(self, facts: Dict[str, Any], title: str, article_content: str) -> Dict[str, Any]:
        """Ensure all required fields are present in the facts structure."""
        required_fields = {
            "title": title,
            "summary": article_content[:200] + "..." if len(article_content) > 200 else article_content,
            "main_topic": "Unknown",
            "key_entities": [],
            "financial_impact": "neutral",
            "key_dates": [],
            "main_points": []
        }
        
        for field, default_value in required_fields.items():
            if field not in facts:
                facts[field] = default_value
            elif not facts[field]:  # If field is empty
                facts[field] = default_value
        
        return facts