Address rename detection with Accept Rename tag-edit export, hover-to-toggle snap dots, cross-layer click fix, fix county street naming (Saint, County Road, Parkway), and keep OSM ids in address downloads

compare-addresses.py

@@ -20,6 +20,7 @@ from pathlib import Path
 from typing import Dict, List, Tuple
 
 import geopandas as gpd
+import numpy as np
 import pandas as pd
 from shapely.strtree import STRtree
 import warnings
@@ -28,6 +29,7 @@ warnings.filterwarnings('ignore')
 
 
 CONFLICT_RADIUS_METERS = 5.0
+RENAME_RADIUS_METERS = 100.0
 
 
 class AddressComparator:
@@ -86,6 +88,53 @@ class AddressComparator:
                     break
             addr['conflict'] = conflict
 
+    def _flag_possible_renames(self, new_addresses: List[Dict], removed_addresses: List[Dict],
+                               radius_meters: float = RENAME_RADIUS_METERS) -> int:
+        """Pair each new county address with an unmatched OSM address nearby that
+        has the same house number (and a compatible unit) but a different street
+        name, e.g. county "828 Donelin Circle" vs OSM "828 Donelin CR". Both sides
+        get 'possible_rename' set to the other side's street so the map can show
+        them as a likely rename/misnaming rather than an unrelated add + removal,
+        and a shared 'rename_pair' id so the map can accept both together.
+        Returns the number of pairs found."""
+        if not new_addresses or not removed_addresses:
+            return 0
+        geoms = [a['geometry'] for a in removed_addresses]
+        tree = STRtree(geoms)
+        radius_deg = radius_meters / 111000.0
+        paired = set()
+        count = 0
+        for addr in new_addresses:
+            num = self._normalize_multi(addr.get('addr:housenumber'))
+            street = self._normalize_street_name(str(addr.get('addr:street', '')))
+            unit = self._normalize_multi(addr.get('addr:unit'))
+            if not num or not street:
+                continue
+            best, best_dist = None, float('inf')
+            for j in tree.query(addr['geometry'].buffer(radius_deg)):
+                if j in paired:
+                    continue
+                osm = removed_addresses[j]
+                if self._normalize_multi(osm.get('addr:housenumber')) != num:
+                    continue
+                osm_street = self._normalize_street_name(str(osm.get('addr:street', '')))
+                if not osm_street or osm_street == street:
+                    continue
+                osm_unit = self._normalize_multi(osm.get('addr:unit'))
+                if unit and osm_unit and unit != osm_unit:
+                    continue
+                d = addr['geometry'].distance(geoms[j]) * 111000.0
+                if d <= radius_meters and d < best_dist:
+                    best, best_dist = j, d
+            if best is not None:
+                paired.add(best)
+                osm = removed_addresses[best]
+                addr['possible_rename'] = str(osm.get('addr:street'))
+                osm['possible_rename'] = str(addr.get('addr:street'))
+                count += 1
+                addr['rename_pair'] = osm['rename_pair'] = count
+        return count
+
     def compare_addresses(self, local_file: str, osm_file: str) -> Tuple[List[Dict], List[Dict], List[Dict]]:
         """Compare local and OSM address data.
 
@@ -197,10 +246,17 @@ class AddressComparator:
         for idx, osm_row in osm_gdf.iterrows():
             if idx not in matched_osm:
                 props = dict(osm_row.drop('geometry'))
+                # geopandas reads JSON int arrays (osm_nodes) as numpy arrays,
+                # which would be written back out as a string
+                for k, v in props.items():
+                    if isinstance(v, np.ndarray):
+                        props[k] = [int(x) for x in v.tolist()]
                 props['status'] = 'removed'
                 removed_addresses.append({'geometry': osm_row.geometry, **props})
 
         self._flag_close_conflicts(new_addresses)
+        renames = self._flag_possible_renames(new_addresses, removed_addresses)
+        print(f"Possible street renames (same number nearby, different street): {renames}")
 
         return new_addresses, existing_addresses, removed_addresses