fix: handle word reordering in domain name matching

"Jubiler Agat" now matches "agat-jubiler.pl" by checking individual
words in any order, not just concatenated substring.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

services/website_discovery_service.py

@@ -462,29 +462,37 @@ class WebsiteDiscoveryService:
         return signals
 
     def _domain_matches_company(self, domain, company_name):
-        """Check if domain name contains normalized company name."""
+        """Check if domain name matches company name (handles word reordering)."""
         if not domain or not company_name:
             return False
-        # Normalize: lowercase, remove common suffixes, special chars
+        # Normalize: lowercase, remove common suffixes
         name = company_name.lower()
-        # Remove legal forms
         for suffix in [' sp. z o.o.', ' sp.z o.o.', ' s.a.', ' s.c.', ' sp.j.',
                        ' sp. k.', ' sp.p.', ' sp. z o. o.']:
             name = name.replace(suffix, '')
-        # Remove special chars, keep only letters and digits
-        name = re.sub(r'[^a-z0-9ąćęłńóśźż]', '', name)
+
         # Polish char mapping for domain comparison
         pl_map = {'ą': 'a', 'ć': 'c', 'ę': 'e', 'ł': 'l', 'ń': 'n',
                   'ó': 'o', 'ś': 's', 'ź': 'z', 'ż': 'z'}
-        name_ascii = ''.join(pl_map.get(c, c) for c in name)
 
         # Get domain without TLD
         domain_base = domain.split('.')[0].lower()
-        domain_base = re.sub(r'[^a-z0-9]', '', domain_base)
+        domain_base_clean = re.sub(r'[^a-z0-9]', '', domain_base)
 
-        # Match if domain base contains the company name (or vice versa for short names)
-        if len(name_ascii) >= 3 and (name_ascii in domain_base or domain_base in name_ascii):
+        # Method 1: Full name match (concatenated)
+        name_concat = re.sub(r'[^a-z0-9ąćęłńóśźż]', '', name)
+        name_ascii = ''.join(pl_map.get(c, c) for c in name_concat)
+        if len(name_ascii) >= 3 and (name_ascii in domain_base_clean or domain_base_clean in name_ascii):
             return True
+
+        # Method 2: All significant words present in domain (handles word reordering)
+        words = re.findall(r'[a-ząćęłńóśźż]+', name)
+        words = [w for w in words if len(w) >= 3]  # skip short words like "i", "sp"
+        if words:
+            words_ascii = [''.join(pl_map.get(c, c) for c in w) for w in words]
+            if all(w in domain_base_clean for w in words_ascii):
+                return True
+
         return False
 
     def _compute_confidence(self, signals):