icu: switch postcodes to using the pre-formatted one

lib-sql/functions/interpolation.sql

@@ -156,7 +156,6 @@ DECLARE
   linegeo GEOMETRY;
   splitline GEOMETRY;
   sectiongeo GEOMETRY;
-  interpol_postcode TEXT;
   postcode TEXT;
   stepmod SMALLINT;
 BEGIN
@@ -174,8 +173,6 @@ BEGIN
                                                  ST_PointOnSurface(NEW.linegeo),
                                                  NEW.linegeo);
 
-  interpol_postcode := token_normalized_postcode(NEW.address->'postcode');
-
   NEW.token_info := token_strip_info(NEW.token_info);
   IF NEW.address ? '_inherited' THEN
     NEW.address := hstore('interpolation', NEW.address->'interpolation');
@@ -207,6 +204,11 @@ BEGIN
     FOR nextnode IN
       SELECT DISTINCT ON (nodeidpos)
           osm_id, address, geometry,
+          -- Take the postcode from the node only if it has a housenumber itself.
+          -- Note that there is a corner-case where the node has a wrongly
+          -- formatted postcode and therefore 'postcode' contains a derived
+          -- variant.
+          CASE WHEN address ? 'postcode' THEN placex.postcode ELSE NULL::text END as postcode,
           substring(address->'housenumber','[0-9]+')::integer as hnr
         FROM placex, generate_series(1, array_upper(waynodes, 1)) nodeidpos
         WHERE osm_type = 'N' and osm_id = waynodes[nodeidpos]::BIGINT
@@ -260,13 +262,10 @@ BEGIN
         endnumber := newend;
 
         -- determine postcode
-        postcode := coalesce(interpol_postcode,
+        postcode := coalesce(prevnode.postcode, nextnode.postcode, postcode);
-                             token_normalized_postcode(prevnode.address->'postcode'),
+        IF postcode is NULL and NEW.parent_place_id > 0 THEN
-                             token_normalized_postcode(nextnode.address->'postcode'),
+            SELECT placex.postcode FROM placex
-                             postcode);
+              WHERE place_id = NEW.parent_place_id INTO postcode;
-        IF postcode is NULL THEN
-            SELECT token_normalized_postcode(placex.postcode)
-              FROM placex WHERE place_id = NEW.parent_place_id INTO postcode;
         END IF;
         IF postcode is NULL THEN
             postcode := get_nearest_postcode(NEW.country_code, nextnode.geometry);

lib-sql/functions/placex_triggers.sql

@@ -992,7 +992,7 @@ BEGIN
       {% if debug %}RAISE WARNING 'Got parent details from search name';{% endif %}
 
       -- determine postcode
-      NEW.postcode := coalesce(token_normalized_postcode(NEW.address->'postcode'),
+      NEW.postcode := coalesce(token_get_postcode(NEW.token_info),
                                location.postcode,
                                get_nearest_postcode(NEW.country_code, NEW.centroid));
 
@@ -1150,8 +1150,7 @@ BEGIN
 
   {% if debug %}RAISE WARNING 'RETURN insert_addresslines: %, %, %', NEW.parent_place_id, NEW.postcode, nameaddress_vector;{% endif %}
 
-  NEW.postcode := coalesce(token_normalized_postcode(NEW.address->'postcode'),
+  NEW.postcode := coalesce(token_get_postcode(NEW.token_info), NEW.postcode);
-                           NEW.postcode);
 
   -- if we have a name add this to the name search table
   IF NEW.name IS NOT NULL THEN

lib-sql/tokenizer/icu_tokenizer.sql

@@ -104,6 +104,13 @@ AS $$
 $$ LANGUAGE SQL IMMUTABLE STRICT;
 
 
+CREATE OR REPLACE FUNCTION token_get_postcode(info JSONB)
+  RETURNS TEXT
+AS $$
+  SELECT info->>'postcode';
+$$ LANGUAGE SQL IMMUTABLE STRICT;
+
+
 -- Return token info that should be saved permanently in the database.
 CREATE OR REPLACE FUNCTION token_strip_info(info JSONB)
   RETURNS JSONB

nominatim/tokenizer/icu_tokenizer.py

@@ -675,6 +675,9 @@ class _TokenInfo:
         if self.address_tokens:
             out['addr'] = self.address_tokens
 
+        if self.postcode:
+            out['postcode'] = self.postcode
+
         return out