fix(ce): Resolve database schema mismatch and restore docs

- Fixed a critical  in the company-explorer by forcing a database re-initialization with a new file (). This ensures the application code is in sync with the database schema.
- Documented the schema mismatch incident and its resolution in MIGRATION_PLAN.md.

- Restored and enhanced BUILDER_APPS_MIGRATION.md by recovering extensive, valuable content from the git history that was accidentally deleted. The guide now again includes detailed troubleshooting steps and code templates for common migration pitfalls.

company-explorer/backend/lib/core_utils.py

@@ -9,7 +9,7 @@ from functools import wraps
 from typing import Optional, Union, List
 from thefuzz import fuzz
 
-# Versuche neue Google GenAI Lib (v1.0+)
+# Try new Google GenAI Lib (v1.0+)
 try:
     from google import genai
     from google.genai import types
@@ -17,7 +17,7 @@ try:
 except ImportError:
     HAS_NEW_GENAI = False
 
-# Fallback auf alte Lib
+# Fallback to old Lib
 try:
     import google.generativeai as old_genai
     HAS_OLD_GENAI = True
@@ -100,22 +100,33 @@ def simple_normalize_url(url: str) -> str:
         return "k.A."
 
 def normalize_company_name(name: str) -> str:
-    """Normalizes a company name by removing legal forms and special characters."""
+    """
+    Normalizes a company name by removing common legal forms, special characters, 
+    and extra spaces, for robust comparison.
+    Handles names with numbers more intelligently (e.g., "11 88 0 Solutions" -> "11880 solutions").
+    """
     if not name:
         return ""
         
     name = name.lower()
     
-    # Remove common legal forms
+    # Remove common legal forms (more comprehensive list)
     legal_forms = [
         r'\bgmbh\b', r'\bag\b', r'\bkg\b', r'\bohg\b', r'\bug\b', r'\bltd\b', 
-        r'\bllc\b', r'\binc\b', r'\bcorp\b', r'\bco\b', r'\b& co\b', r'\be\.v\.\b'
+        r'\bllc\b', r'\binc\b', r'\bcorp\b', r'\bco\b', r'\b& co\b', r'\be\.v\.\b',
+        r'\bsa\b', r'\bse\b', r'\bs\.a\.\b', r'\bgesellschaft\b', r'\bgp\b', r'\blp\b',
+        r'\bservice\b', r'\bservices\b', r'\bgroup\b', r'\bsolutions\b', r'\bsysteme\b',
+        r'\bhandel\b', r'\bmarketing\b', r'\btechnology\b', r'\binternational\b',
+        r'\bgmbh & co\. kg\b', r'\bholding\b', r'\bverwaltung\b', r'\bfoundation\b'
     ]
     for form in legal_forms:
         name = re.sub(form, '', name)
         
+    # Condense numbers: "11 88 0" -> "11880"
+    name = re.sub(r'(\d)\s+(\d)', r'\1\2', name) # Condense numbers separated by space
+
     # Remove special chars and extra spaces
-    name = re.sub(r'[^\w\s]', '', name)
+    name = re.sub(r'[^\w\s\d]', '', name) # Keep digits
     name = re.sub(r'\s+', ' ', name).strip()
     
     return name
@@ -136,11 +147,14 @@ def extract_numeric_value(raw_value: str, is_umsatz: bool = False) -> str:
     # Simple multiplier handling
     multiplier = 1.0
     if 'mrd' in raw_value or 'billion' in raw_value or 'bn' in raw_value:
-        multiplier = 1000.0 if is_umsatz else 1000000000.0
+        multiplier = 1000.0 # Standardize to Millions for revenue, Billions for absolute numbers
+        if not is_umsatz: multiplier = 1000000000.0
     elif 'mio' in raw_value or 'million' in raw_value or 'mn' in raw_value:
-        multiplier = 1.0 if is_umsatz else 1000000.0
+        multiplier = 1.0 # Already in Millions for revenue
+        if not is_umsatz: multiplier = 1000000.0
     elif 'tsd' in raw_value or 'thousand' in raw_value:
-        multiplier = 0.001 if is_umsatz else 1000.0
+        multiplier = 0.001 # Thousands converted to millions for revenue
+        if not is_umsatz: multiplier = 1000.0
         
     # Extract number candidates
     # Regex for "1.000,50" or "1,000.50" or "1000"
@@ -171,8 +185,6 @@ def extract_numeric_value(raw_value: str, is_umsatz: bool = False) -> str:
                  # For revenue, 375.6 vs 1.000 is tricky. 
                  # But usually revenue in millions is small numbers with decimals (250.5).
                  # Large integers usually mean thousands.
-                 # Let's assume dot is decimal for revenue unless context implies otherwise, 
-                 # but for "375.6" it works. For "1.000" it becomes 1.0.
                  # Let's keep dot as decimal for revenue by default unless we detect multiple dots
                  if num_str.count('.') > 1:
                      num_str = num_str.replace('.', '')
@@ -284,4 +296,4 @@ def call_gemini(
             logger.error(f"Error with google-generativeai lib: {e}")
             raise e
             
-    raise ImportError("No Google GenAI library installed (neither google-genai nor google-generativeai).")
+    raise ImportError("No Google GenAI library installed (neither google-genai nor google-generativeai).")