Split unit designators (UNIT/APT/STE/etc) out of combined address strings into addr:unit instead of leaving them in addr:street

convert-addresses.py

@@ -52,14 +52,17 @@ def process_address_fields(gdf, exceptions):
             mapping['addr:housenumber'] = series.round().astype('Int64')
             break
 
-    # Unit
+    # Unit (a dedicated column takes priority; otherwise fall back to a unit
+    # designator embedded in a combined street+unit address string below)
+    unit_from_column = [None] * len(processed)
     for field in ['UNIT', 'UnitNumber', 'UNIT_NUM', 'APT']:
         if field in processed.columns:
             series = processed[field].copy().replace(['nan', 'None', '', None], None)
-            mapping['addr:unit'] = series.where(series.notna(), None)
+            unit_from_column = list(series.where(series.notna(), None))
             break
 
     # Street name
+    unit_from_address = [None] * len(processed)
     if 'SADD' in processed.columns:
         # Sumter: full address string in SADD
         mapping['addr:street'] = [
@@ -67,6 +70,11 @@ def process_address_fields(gdf, exceptions):
             if pd.notna(v) else None
             for v in processed['SADD']
         ]
+        unit_from_address = [
+            qgis_functions.title(qgis_functions.getunitfromaddress(str(v), None, None) or '') or None
+            if pd.notna(v) else None
+            for v in processed['SADD']
+        ]
     elif 'FullAddres' in processed.columns:
         # Lake: full address string in FullAddres
         mapping['addr:street'] = [
@@ -74,6 +82,11 @@ def process_address_fields(gdf, exceptions):
             if pd.notna(v) else None
             for v in processed['FullAddres']
         ]
+        unit_from_address = [
+            qgis_functions.title(qgis_functions.getunitfromaddress(str(v), None, None) or '') or None
+            if pd.notna(v) else None
+            for v in processed['FullAddres']
+        ]
     elif 'BaseStreet' in processed.columns:
         # Lake alternative: assemble from components
         street_names = []
@@ -85,6 +98,11 @@ def process_address_fields(gdf, exceptions):
             street_names.append(qgis_functions.title(' '.join(parts)) if parts else None)
         mapping['addr:street'] = street_names
 
+    mapping['addr:unit'] = [
+        col if col is not None else addr
+        for col, addr in zip(unit_from_column, unit_from_address)
+    ]
+
     # Apply street name exceptions
     if 'addr:street' in mapping and exceptions:
         mapping['addr:street'] = [

qgis-functions.py

@@ -21,13 +21,32 @@ def title(s):
         result = re.sub(pattern, replacement, result)
     return result
 
+# Secondary unit designators that may appear inline in a full address string,
+# e.g. "123 ROLLING ACRES RD UNIT 208" - everything from the designator on is
+# the unit, not part of the street name.
+_UNIT_DESIGNATORS = {'UNIT', 'APT', 'APARTMENT', 'STE', 'SUITE', 'BLDG', 'BUILDING', 'LOT'}
+
+def _splitunit(parts):
+    for i, part in enumerate(parts):
+        if part.upper().rstrip('.') in _UNIT_DESIGNATORS:
+            return parts[:i], (" ".join(parts[i + 1:]) or None)
+    return parts, None
+
 # @qgsfunction(args='auto', group='Custom', referenced_columns=[])
 def getstreetfromaddress(value1, feature, parent):
     parts = value1.split()
     parts.pop(0) # Ignore the first bit (i.e. "123" in "123 N MAIN ST")
+    street_parts, _ = _splitunit(parts)
     #parts = map(formatstreetname, parts)
     #return " ".join(parts)
-    return formatstreet(" ".join(parts), None, None)
+    return formatstreet(" ".join(street_parts), None, None)
+
+# @qgsfunction(args='auto', group='Custom', referenced_columns=[])
+def getunitfromaddress(value1, feature, parent):
+    parts = value1.split()
+    parts.pop(0) # Ignore the first bit (i.e. "123" in "123 N MAIN ST")
+    _, unit = _splitunit(parts)
+    return unit
 
 # @qgsfunction(args='auto', group='Custom', referenced_columns=[])
 def formatstreet(value1, feature, parent):