Improve address matching

compare-addresses.py

@@ -14,6 +14,7 @@ Usage:
 import argparse
 import json
 import os
+import re
 import shutil
 import sys
 import zipfile
@@ -374,10 +375,41 @@ out geom;"""
         
         return processed_gdf
     
+    def _normalize_street_name(self, street: str) -> str:
+        """
+        Normalize street names for better matching.
+        Handles common abbreviation and formatting differences between county and OSM data.
+        """
+        if not street or street == 'nan':
+            return ''
+
+        street = street.strip()
+
+        # Convert to lowercase for comparison
+        street_lower = street.lower()
+
+        # Normalize State Road variations
+        street_lower = re.sub(r'\bstate road\b', 'sr', street_lower)
+        street_lower = re.sub(r'\bstate route\b', 'sr', street_lower)
+
+        # Normalize County Road variations
+        street_lower = re.sub(r'\bcounty road\b', 'cr', street_lower)
+        street_lower = re.sub(r'\bc\b', 'cr', street_lower)  # "C 44a" -> "cr 44a"
+
+        # Normalize County Road number formatting: "109d 1" -> "109d-1", "109d-1" stays same
+        # This handles both space and hyphen separators
+        street_lower = re.sub(r'\b(cr\s+\d+[a-z])\s+(\d+)', r'\1-\2', street_lower)
+        street_lower = re.sub(r'\b(cr\s+\d+[a-z])-(\d+)', r'\1-\2', street_lower)
+
+        # Remove extra spaces
+        street_lower = re.sub(r'\s+', ' ', street_lower).strip()
+
+        return street_lower
+
     def compare_addresses(self, local_file: str, osm_file: str) -> Tuple[List[Dict], List[Dict], List[Dict]]:
         """
         Compare local and OSM address data.
-        
+
         Returns:
             Tuple of (new_addresses, existing_addresses, removed_addresses)
         """
@@ -435,19 +467,28 @@ out geom;"""
                 local_house_num = str(local_row.get('addr:housenumber', ''))
                 osm_house_num = str(osm_row.get('addr:housenumber', ''))
 
-                # Check street name match (required)
-                local_street = str(local_row.get('addr:street', '')).strip().lower()
-                osm_street = str(osm_row.get('addr:street', '')).strip().lower()
-                street_match = (local_street == osm_street and local_street != '' and local_street != 'nan')
+                # Check street name match (required) - use normalization for better matching
+                local_street = self._normalize_street_name(str(local_row.get('addr:street', '')))
+                osm_street = self._normalize_street_name(str(osm_row.get('addr:street', '')))
+                street_match = (local_street == osm_street and local_street != '')
 
-                # Check unit match (only if both have units specified)
+                # Check unit match - if either has a unit, both must match
                 local_unit = local_row.get('addr:unit')
                 osm_unit = osm_row.get('addr:unit')
-                # Unit matches if: (1) both are None/null, OR (2) both have values and they're equal
-                unit_match = True
-                if local_unit is not None and pd.notna(local_unit) and osm_unit is not None and pd.notna(osm_unit):
+
+                # Determine if each side has a unit
+                local_has_unit = local_unit is not None and pd.notna(local_unit) and str(local_unit).strip() != ''
+                osm_has_unit = osm_unit is not None and pd.notna(osm_unit) and str(osm_unit).strip() != ''
+
+                if local_has_unit and osm_has_unit:
                     # Both have units - they must match
                     unit_match = (str(local_unit).strip().lower() == str(osm_unit).strip().lower())
+                elif local_has_unit or osm_has_unit:
+                    # One has unit, other doesn't - no match
+                    unit_match = False
+                else:
+                    # Neither has unit - match
+                    unit_match = True
 
                 # Only consider as potential match if house numbers, street, and unit all match
                 if (local_house_num == osm_house_num and
@@ -500,10 +541,10 @@ out geom;"""
                 local_house_num = str(local_row.get('addr:housenumber', ''))
                 osm_house_num = str(osm_row.get('addr:housenumber', ''))
 
-                # Check street name match (required)
-                local_street = str(local_row.get('addr:street', '')).strip().lower()
-                osm_street = str(osm_row.get('addr:street', '')).strip().lower()
-                street_match = (local_street == osm_street and local_street != '' and local_street != 'nan')
+                # Check street name match (required) - use normalization for better matching
+                local_street = self._normalize_street_name(str(local_row.get('addr:street', '')))
+                osm_street = self._normalize_street_name(str(osm_row.get('addr:street', '')))
+                street_match = (local_street == osm_street and local_street != '')
 
                 # Check unit match (only if both have units specified)
                 local_unit = local_row.get('addr:unit')