From ea87ace6e21ac158e058dcd0b7f6756539576f4d Mon Sep 17 00:00:00 2001
From: Floke <floke.com@gmail.com>
Date: Mon, 19 Jan 2026 07:58:49 +0000
Subject: [PATCH] feat: Connect classification service to DB industries &
 update docs

---
 MIGRATION_PLAN.md                             |  2 +-
 .../backend/services/classification.py        | 26 ++++++++++++-------
 2 files changed, 18 insertions(+), 10 deletions(-)

diff --git a/MIGRATION_PLAN.md b/MIGRATION_PLAN.md
index 8bc06231..d6c48cac 100644
--- a/MIGRATION_PLAN.md
+++ b/MIGRATION_PLAN.md
@@ -304,6 +304,6 @@ Based on the identified infrastructure, score the potential for these categories
 **Variablen:**
 *   **`company_name`**: Name des Unternehmens.
 *   **`website_text`**: Der gescrapte Text der Hauptseite (max. 20.000 Zeichen).
-*   **`allowed_industries`**: JSON-Liste der erlaubten Branchen (Strict Mode).
+*   **`allowed_industries`**: Dynamisch geladene Liste der erlaubten Branchen aus der Datenbanktabelle `industries` (konfiguriert via Settings > Industry Focus).
 *   **`category_guidance`**: Dynamisch generierte Definitionen und Scoring-Regeln für die Robotik-Kategorien (aus der Datenbank).
 
diff --git a/company-explorer/backend/services/classification.py b/company-explorer/backend/services/classification.py
index 3a077691..1771e055 100644
--- a/company-explorer/backend/services/classification.py
+++ b/company-explorer/backend/services/classification.py
@@ -4,23 +4,30 @@ 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
+from ..database import SessionLocal, RoboticsCategory, Industry
 
 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()
+        pass
 
-    def _load_allowed_industries(self) -> List[str]:
+    def _get_allowed_industries(self) -> List[str]:
+        """
+        Fetches the allowed industries from the database (Settings > Industry Focus).
+        """
+        db = SessionLocal()
         try:
-            with open(ALLOWED_INDUSTRIES_FILE, 'r', encoding='utf-8') as f:
-                return json.load(f)
+            # Query all industries, order by name for consistency
+            industries = db.query(Industry.name).order_by(Industry.name).all()
+            # extract names from tuples (query returns list of tuples)
+            names = [i[0] for i in industries]
+            return names if names else ["Sonstige"]
         except Exception as e:
-            logger.error(f"Failed to load allowed industries: {e}")
+            logger.error(f"Failed to load allowed industries from DB: {e}")
             return ["Sonstige"]
+        finally:
+            db.close()
 
     def _get_category_prompts(self) -> str:
         """
@@ -52,6 +59,7 @@ class ClassificationService:
             return {"error": "Insufficient text content"}
             
         category_guidance = self._get_category_prompts()
+        allowed_industries = self._get_allowed_industries()
 
         prompt = f"""
         You are a Senior B2B Market Analyst for 'Roboplanet', a specialized robotics distributor.
@@ -64,7 +72,7 @@ class ClassificationService:
         
         --- 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)}
+        {json.dumps(allowed_industries, ensure_ascii=False)}
 
         --- ANALYSIS PART 1: BUSINESS MODEL ---
         1. Identify the core products/services.