Brancheneinstufung2/company-explorer/backend/services/classification.py

import json
import logging
import os
from typing import Dict, Any, List
from ..lib.core_utils import call_gemini, clean_json_response
from ..config import settings
from ..database import SessionLocal, RoboticsCategory

logger = logging.getLogger(__name__)

ALLOWED_INDUSTRIES_FILE = os.path.join(os.path.dirname(__file__), "../data/allowed_industries.json")

class ClassificationService:
    def __init__(self):
        self.allowed_industries = self._load_allowed_industries()

    def _load_allowed_industries(self) -> List[str]:
        try:
            with open(ALLOWED_INDUSTRIES_FILE, 'r', encoding='utf-8') as f:
                return json.load(f)
        except Exception as e:
            logger.error(f"Failed to load allowed industries: {e}")
            return ["Sonstige"]

    def _get_category_prompts(self) -> str:
        """
        Fetches the latest category definitions from the database.
        """
        db = SessionLocal()
        try:
            categories = db.query(RoboticsCategory).all()
            if not categories:
                return "Error: No categories defined."
            
            prompt_parts = []
            for cat in categories:
                prompt_parts.append(f"* **{cat.name} ({cat.key}):**\n     - Definition: {cat.description}\n     - Scoring Guide: {cat.reasoning_guide}")
            
            return "\n".join(prompt_parts)
        except Exception as e:
            logger.error(f"Error fetching categories: {e}")
            return "Error loading categories."
        finally:
            db.close()

    def analyze_robotics_potential(self, company_name: str, website_text: str) -> Dict[str, Any]:
        """
        Analyzes the company for robotics potential based on website content.
        Returns strict JSON.
        """
        if not website_text or len(website_text) < 100:
            return {"error": "Insufficient text content"}
            
        category_guidance = self._get_category_prompts()

        prompt = f"""
        You are a Senior B2B Market Analyst for 'Roboplanet', a specialized robotics distributor.
        Your task is to analyze the target company based on their website text and create a concise **Dossier**.

        --- TARGET COMPANY ---
        Name: {company_name}
        Website Content (Excerpt):
        {website_text[:20000]} 
        
        --- ALLOWED INDUSTRIES (STRICT) ---
        You MUST assign the company to exactly ONE of these industries. If unsure, choose the closest match or "Sonstige".
        {json.dumps(self.allowed_industries, ensure_ascii=False)}

        --- ANALYSIS PART 1: BUSINESS MODEL ---
        1. Identify the core products/services.
        2. Summarize in 2-3 German sentences: What do they do and for whom? (Target: "business_model")

        --- ANALYSIS PART 2: INFRASTRUCTURE & POTENTIAL (Chain of Thought) ---
        1. **Infrastructure Scan:** Look for evidence of physical assets like *Factories, Large Warehouses, Production Lines, Campuses, Hospitals*.
        2. **Provider vs. User Check:** 
           - Does the company USE this infrastructure (Potential Customer)?
           - Or do they SELL products for it (Competitor/Partner)? 
           - *Example:* "Cleaning" -> Do they sell soap (Provider) or do they have a 50,000sqm factory (User)?
        3. **Evidence Extraction:** Extract 1-2 key sentences from the text proving this infrastructure. (Target: "infrastructure_evidence")

        --- ANALYSIS PART 3: SCORING (0-100) ---
        Based on the identified infrastructure, score the potential for these categories:
        
        {category_guidance}

        --- OUTPUT FORMAT (JSON ONLY) ---
        {{
            "industry": "String (from list)",
            "business_model": "2-3 sentences summary (German)",
            "infrastructure_evidence": "1-2 key sentences proving physical assets (German)",
            "potentials": {{
                "cleaning": {{ "score": 0-100, "reason": "Reasoning based on infrastructure." }},
                "transport": {{ "score": 0-100, "reason": "Reasoning based on logistics volume." }},
                "security": {{ "score": 0-100, "reason": "Reasoning based on perimeter/assets." }},
                "service": {{ "score": 0-100, "reason": "Reasoning based on guest interaction." }}
            }}
        }}
        """

        try:
            response_text = call_gemini(
                prompt=prompt,
                json_mode=True,
                temperature=0.1 # Very low temp for analytical reasoning
            )
            return json.loads(clean_json_response(response_text))
        except Exception as e:
            logger.error(f"Classification failed: {e}")
            return {"error": str(e)}