Merge pull request #3530 from lonvia/clean-use-of-os-environ

[nominatim.git] / lib-sql / functions / placex_triggers.sql

diff --git a/lib-sql/functions/placex_triggers.sql b/lib-sql/functions/placex_triggers.sql
index 4432fa2458d4447b1f59a0731ab89fda3c318fc8..01f99715e6cbf63770a8cab2f813383196166b7d 100644 (file)
--- a/lib-sql/functions/placex_triggers.sql
+++ b/lib-sql/functions/placex_triggers.sql
@@ -2,7 +2,7 @@
 --
 -- This file is part of Nominatim. (https://nominatim.org)
 --
 --
 -- This file is part of Nominatim. (https://nominatim.org)
 --

--- Copyright (C) 2022 by the Nominatim developer community.
+-- Copyright (C) 2024 by the Nominatim developer community.

 -- For a full list of authors see the git log.
 
 -- Trigger functions for the placex table.
 -- For a full list of authors see the git log.
 
 -- Trigger functions for the placex table.


@@ -88,12 +88,18 @@ BEGIN
       -- Add all names from the place nodes that deviate from the name
       -- in the relation with the prefix '_place_'. Deviation means that
       -- either the value is different or a given key is missing completely
       -- Add all names from the place nodes that deviate from the name
       -- in the relation with the prefix '_place_'. Deviation means that
       -- either the value is different or a given key is missing completely

-      SELECT hstore(array_agg('_place_' || key), array_agg(value)) INTO extra_names
-        FROM each(location.name - result.name);
-      {% if debug %}RAISE WARNING 'Extra names: %', extra_names;{% endif %}
+      IF result.name is null THEN
+        SELECT hstore(array_agg('_place_' || key), array_agg(value))
+          INTO result.name
+          FROM each(location.name);
+      ELSE
+        SELECT hstore(array_agg('_place_' || key), array_agg(value)) INTO extra_names
+          FROM each(location.name - result.name);
+        {% if debug %}RAISE WARNING 'Extra names: %', extra_names;{% endif %}

 
 

-      IF extra_names is not null THEN
-          result.name := result.name || extra_names;
+        IF extra_names is not null THEN
+            result.name := result.name || extra_names;
+        END IF;

       END IF;
 
       {% if debug %}RAISE WARNING 'Final names: %', result.name;{% endif %}
       END IF;
 
       {% if debug %}RAISE WARNING 'Final names: %', result.name;{% endif %}


@@ -107,13 +113,20 @@ LANGUAGE plpgsql STABLE;
 
 
 CREATE OR REPLACE FUNCTION find_associated_street(poi_osm_type CHAR(1),
 
 
 CREATE OR REPLACE FUNCTION find_associated_street(poi_osm_type CHAR(1),

-                                                  poi_osm_id BIGINT)
+                                                  poi_osm_id BIGINT,
+                                                  bbox GEOMETRY)

   RETURNS BIGINT
   AS $$
 DECLARE
   location RECORD;
   RETURNS BIGINT
   AS $$
 DECLARE
   location RECORD;

+  member JSONB;

   parent RECORD;
   parent RECORD;

+  result BIGINT;
+  distance FLOAT;
+  new_distance FLOAT;
+  waygeom GEOMETRY;

 BEGIN
 BEGIN

+{% if db.middle_db_format == '1' %}

   FOR location IN
     SELECT members FROM planet_osm_rels
     WHERE parts @> ARRAY[poi_osm_id]
   FOR location IN
     SELECT members FROM planet_osm_rels
     WHERE parts @> ARRAY[poi_osm_id]


@@ -123,19 +136,68 @@ BEGIN
     FOR i IN 1..array_upper(location.members, 1) BY 2 LOOP
       IF location.members[i+1] = 'street' THEN
         FOR parent IN
     FOR i IN 1..array_upper(location.members, 1) BY 2 LOOP
       IF location.members[i+1] = 'street' THEN
         FOR parent IN

-          SELECT place_id from placex
+          SELECT place_id, geometry
+           FROM placex

            WHERE osm_type = upper(substring(location.members[i], 1, 1))::char(1)
                  and osm_id = substring(location.members[i], 2)::bigint
                  and name is not null
                  and rank_search between 26 and 27
         LOOP
            WHERE osm_type = upper(substring(location.members[i], 1, 1))::char(1)
                  and osm_id = substring(location.members[i], 2)::bigint
                  and name is not null
                  and rank_search between 26 and 27
         LOOP

-          RETURN parent.place_id;
+          -- Find the closest 'street' member.
+          -- Avoid distance computation for the frequent case where there is
+          -- only one street member.
+          IF waygeom is null THEN
+            result := parent.place_id;
+            waygeom := parent.geometry;
+          ELSE
+            distance := coalesce(distance, ST_Distance(waygeom, bbox));
+            new_distance := ST_Distance(parent.geometry, bbox);
+            IF new_distance < distance THEN
+              distance := new_distance;
+              result := parent.place_id;
+              waygeom := parent.geometry;
+            END IF;
+          END IF;

         END LOOP;
       END IF;
     END LOOP;
   END LOOP;
 
         END LOOP;
       END IF;
     END LOOP;
   END LOOP;
 

-  RETURN NULL;
+{% else %}
+  FOR member IN
+    SELECT value FROM planet_osm_rels r, LATERAL jsonb_array_elements(members)
+    WHERE planet_osm_member_ids(members, poi_osm_type::char(1)) && ARRAY[poi_osm_id]
+          and tags->>'type' = 'associatedStreet'
+          and value->>'role' = 'street'
+  LOOP
+    FOR parent IN
+      SELECT place_id, geometry
+       FROM placex
+       WHERE osm_type = (member->>'type')::char(1)
+             and osm_id = (member->>'ref')::bigint
+             and name is not null
+             and rank_search between 26 and 27
+    LOOP
+      -- Find the closest 'street' member.
+      -- Avoid distance computation for the frequent case where there is
+      -- only one street member.
+      IF waygeom is null THEN
+        result := parent.place_id;
+        waygeom := parent.geometry;
+      ELSE
+        distance := coalesce(distance, ST_Distance(waygeom, bbox));
+        new_distance := ST_Distance(parent.geometry, bbox);
+        IF new_distance < distance THEN
+          distance := new_distance;
+          result := parent.place_id;
+          waygeom := parent.geometry;
+        END IF;
+      END IF;
+    END LOOP;
+  END LOOP;
+{% endif %}
+
+  RETURN result;

 END;
 $$
 LANGUAGE plpgsql STABLE;
 END;
 $$
 LANGUAGE plpgsql STABLE;


@@ -162,7 +224,7 @@ BEGIN
   {% if debug %}RAISE WARNING 'finding street for % %', poi_osm_type, poi_osm_id;{% endif %}
 
   -- Is this object part of an associatedStreet relation?
   {% if debug %}RAISE WARNING 'finding street for % %', poi_osm_type, poi_osm_id;{% endif %}
 
   -- Is this object part of an associatedStreet relation?

-  parent_place_id := find_associated_street(poi_osm_type, poi_osm_id);
+  parent_place_id := find_associated_street(poi_osm_type, poi_osm_id, bbox);

 
   IF parent_place_id is null THEN
     parent_place_id := find_parent_for_address(token_info, poi_partition, bbox);
 
   IF parent_place_id is null THEN
     parent_place_id := find_parent_for_address(token_info, poi_partition, bbox);


@@ -185,7 +247,7 @@ BEGIN
         RETURN location.place_id;
       END IF;
 
         RETURN location.place_id;
       END IF;
 

-      parent_place_id := find_associated_street('W', location.osm_id);
+      parent_place_id := find_associated_street('W', location.osm_id, bbox);

     END LOOP;
   END IF;
 
     END LOOP;
   END IF;
 


@@ -231,7 +293,11 @@ CREATE OR REPLACE FUNCTION find_linked_place(bnd placex)
   RETURNS placex
   AS $$
 DECLARE
   RETURNS placex
   AS $$
 DECLARE

+{% if db.middle_db_format == '1' %}

   relation_members TEXT[];
   relation_members TEXT[];

+{% else %}
+  relation_members JSONB;
+{% endif %}

   rel_member RECORD;
   linked_placex placex%ROWTYPE;
   bnd_name TEXT;
   rel_member RECORD;
   linked_placex placex%ROWTYPE;
   bnd_name TEXT;


@@ -415,24 +481,20 @@ BEGIN
     name_vector := array_merge(name_vector, hnr_vector);
   END IF;
 
     name_vector := array_merge(name_vector, hnr_vector);
   END IF;
 

-  IF is_place_addr THEN
-    addr_place_ids := token_addr_place_search_tokens(token_info);
-    IF not addr_place_ids <@ parent_name_vector THEN
-      -- make sure addr:place terms are always searchable
-      nameaddress_vector := array_merge(nameaddress_vector, addr_place_ids);
-      -- If there is a housenumber, also add the place name as a name,
-      -- so we can search it by the usual housenumber+place algorithms.
-      IF hnr_vector is not null THEN
-        name_vector := array_merge(name_vector, addr_place_ids);
-      END IF;
-    END IF;
-  END IF;
-

   -- Cheating here by not recomputing all terms but simply using the ones
   -- from the parent object.
   nameaddress_vector := array_merge(nameaddress_vector, parent_name_vector);
   nameaddress_vector := array_merge(nameaddress_vector, parent_address_vector);
 
   -- Cheating here by not recomputing all terms but simply using the ones
   -- from the parent object.
   nameaddress_vector := array_merge(nameaddress_vector, parent_name_vector);
   nameaddress_vector := array_merge(nameaddress_vector, parent_address_vector);
 

+  -- make sure addr:place terms are always searchable
+  IF is_place_addr THEN
+    addr_place_ids := token_addr_place_search_tokens(token_info);
+    IF hnr_vector is not null AND not addr_place_ids <@ parent_name_vector
+    THEN
+      name_vector := array_merge(name_vector, hnr_vector);
+    END IF;
+    nameaddress_vector := array_merge(nameaddress_vector, addr_place_ids);
+  END IF;

 END;
 $$
 LANGUAGE plpgsql;
 END;
 $$
 LANGUAGE plpgsql;


@@ -652,6 +714,12 @@ BEGIN
       NEW.country_code := NULL;
     END IF;
 
       NEW.country_code := NULL;
     END IF;
 

+    -- Simplify polygons with a very large memory footprint when they
+    -- do not take part in address computation.
+    IF NEW.rank_address = 0 THEN
+      NEW.geometry := simplify_large_polygons(NEW.geometry);
+    END IF;
+

   END IF;
 
   {% if debug %}RAISE WARNING 'placex_insert:END: % % % %',NEW.osm_type,NEW.osm_id,NEW.class,NEW.type;{% endif %}
   END IF;
 
   {% if debug %}RAISE WARNING 'placex_insert:END: % % % %',NEW.osm_type,NEW.osm_id,NEW.class,NEW.type;{% endif %}


@@ -659,10 +727,12 @@ BEGIN
 {% if not disable_diff_updates %}
   -- The following is not needed until doing diff updates, and slows the main index process down
 
 {% if not disable_diff_updates %}
   -- The following is not needed until doing diff updates, and slows the main index process down
 

-  IF NEW.rank_address > 0 THEN
+  IF NEW.rank_address between 2 and 27 THEN

     IF (ST_GeometryType(NEW.geometry) in ('ST_Polygon','ST_MultiPolygon') AND ST_IsValid(NEW.geometry)) THEN
       -- Performance: We just can't handle re-indexing for country level changes
     IF (ST_GeometryType(NEW.geometry) in ('ST_Polygon','ST_MultiPolygon') AND ST_IsValid(NEW.geometry)) THEN
       -- Performance: We just can't handle re-indexing for country level changes

-      IF st_area(NEW.geometry) < 1 THEN
+      IF (NEW.rank_address < 26 and st_area(NEW.geometry) < 1)
+         OR (NEW.rank_address >= 26 and st_area(NEW.geometry) < 0.01)
+      THEN

         -- mark items within the geometry for re-indexing
   --    RAISE WARNING 'placex poly insert: % % % %',NEW.osm_type,NEW.osm_id,NEW.class,NEW.type;
 
         -- mark items within the geometry for re-indexing
   --    RAISE WARNING 'placex poly insert: % % % %',NEW.osm_type,NEW.osm_id,NEW.class,NEW.type;
 


@@ -677,9 +747,11 @@ BEGIN
                     or name is not null
                     or (NEW.rank_address >= 16 and address ? 'place'));
       END IF;
                     or name is not null
                     or (NEW.rank_address >= 16 and address ? 'place'));
       END IF;

-    ELSE
+    ELSEIF ST_GeometryType(NEW.geometry) not in ('ST_LineString', 'ST_MultiLineString')
+           OR ST_Length(NEW.geometry) < 0.5
+    THEN

       -- mark nearby items for re-indexing, where 'nearby' depends on the features rank_search and is a complete guess :(
       -- mark nearby items for re-indexing, where 'nearby' depends on the features rank_search and is a complete guess :(

-      diameter := update_place_diameter(NEW.rank_search);
+      diameter := update_place_diameter(NEW.rank_address);

       IF diameter > 0 THEN
   --      RAISE WARNING 'placex point insert: % % % % %',NEW.osm_type,NEW.osm_id,NEW.class,NEW.type,diameter;
         IF NEW.rank_search >= 26 THEN
       IF diameter > 0 THEN
   --      RAISE WARNING 'placex point insert: % % % % %',NEW.osm_type,NEW.osm_id,NEW.class,NEW.type,diameter;
         IF NEW.rank_search >= 26 THEN


@@ -723,7 +795,11 @@ CREATE OR REPLACE FUNCTION placex_update()
 DECLARE
   i INTEGER;
   location RECORD;
 DECLARE
   i INTEGER;
   location RECORD;

+{% if db.middle_db_format == '1' %}

   relation_members TEXT[];
   relation_members TEXT[];

+{% else %}
+  relation_member JSONB;
+{% endif %}

 
   geom GEOMETRY;
   parent_address_level SMALLINT;
 
   geom GEOMETRY;
   parent_address_level SMALLINT;


@@ -768,6 +844,9 @@ BEGIN
   result := deleteLocationArea(NEW.partition, NEW.place_id, NEW.rank_search);
 
   NEW.extratags := NEW.extratags - 'linked_place'::TEXT;
   result := deleteLocationArea(NEW.partition, NEW.place_id, NEW.rank_search);
 
   NEW.extratags := NEW.extratags - 'linked_place'::TEXT;

+  IF NEW.extratags = ''::hstore THEN
+    NEW.extratags := NULL;
+  END IF;

 
   -- NEW.linked_place_id contains the precomputed linkee. Save this and restore
   -- the previous link status.
 
   -- NEW.linked_place_id contains the precomputed linkee. Save this and restore
   -- the previous link status.


@@ -942,6 +1021,7 @@ BEGIN
 
   -- waterway ways are linked when they are part of a relation and have the same class/type
   IF NEW.osm_type = 'R' and NEW.class = 'waterway' THEN
 
   -- waterway ways are linked when they are part of a relation and have the same class/type
   IF NEW.osm_type = 'R' and NEW.class = 'waterway' THEN

+{% if db.middle_db_format == '1' %}

       FOR relation_members IN select members from planet_osm_rels r where r.id = NEW.osm_id and r.parts != array[]::bigint[]
       LOOP
           FOR i IN 1..array_upper(relation_members, 1) BY 2 LOOP
       FOR relation_members IN select members from planet_osm_rels r where r.id = NEW.osm_id and r.parts != array[]::bigint[]
       LOOP
           FOR i IN 1..array_upper(relation_members, 1) BY 2 LOOP


@@ -960,12 +1040,35 @@ BEGIN
               END IF;
           END LOOP;
       END LOOP;
               END IF;
           END LOOP;
       END LOOP;

+{% else %}
+    FOR relation_member IN
+      SELECT value FROM planet_osm_rels r, LATERAL jsonb_array_elements(r.members)
+      WHERE r.id = NEW.osm_id
+    LOOP
+      IF relation_member->>'role' IN ('', 'main_stream', 'side_stream')
+         and relation_member->>'type' = 'W'
+      THEN
+        {% if debug %}RAISE WARNING 'waterway parent %, child %', NEW.osm_id, relation_member;{% endif %}
+        FOR linked_node_id IN
+          SELECT place_id FROM placex
+          WHERE osm_type = 'W' and osm_id = (relation_member->>'ref')::bigint
+                and class = NEW.class and type in ('river', 'stream', 'canal', 'drain', 'ditch')
+                and (relation_member->>'role' != 'side_stream' or NEW.name->'name' = name->'name')
+        LOOP
+          UPDATE placex SET linked_place_id = NEW.place_id WHERE place_id = linked_node_id;
+          {% if 'search_name' in db.tables %}
+            DELETE FROM search_name WHERE place_id = linked_node_id;
+          {% endif %}
+        END LOOP;
+      END IF;
+    END LOOP;
+{% endif %}

       {% if debug %}RAISE WARNING 'Waterway processed';{% endif %}
   END IF;
 
   NEW.importance := null;
   SELECT wikipedia, importance
       {% if debug %}RAISE WARNING 'Waterway processed';{% endif %}
   END IF;
 
   NEW.importance := null;
   SELECT wikipedia, importance

-    FROM compute_importance(NEW.extratags, NEW.country_code, NEW.osm_type, NEW.osm_id, NEW.centroid)
+    FROM compute_importance(NEW.extratags, NEW.country_code, NEW.rank_search, NEW.centroid)

     INTO NEW.wikipedia,NEW.importance;
 
 {% if debug %}RAISE WARNING 'Importance computed from wikipedia: %', NEW.importance;{% endif %}
     INTO NEW.wikipedia,NEW.importance;
 
 {% if debug %}RAISE WARNING 'Importance computed from wikipedia: %', NEW.importance;{% endif %}


@@ -976,7 +1079,7 @@ BEGIN
 
     {% if debug %}RAISE WARNING 'finding street for % %', NEW.osm_type, NEW.osm_id;{% endif %}
     NEW.parent_place_id := null;
 
     {% if debug %}RAISE WARNING 'finding street for % %', NEW.osm_type, NEW.osm_id;{% endif %}
     NEW.parent_place_id := null;

-    is_place_address := coalesce(not NEW.address ? 'street' and NEW.address ? 'place', FALSE);
+    is_place_address := not token_is_street_address(NEW.token_info);

 
     -- We have to find our parent road.
     NEW.parent_place_id := find_parent_for_poi(NEW.osm_type, NEW.osm_id,
 
     -- We have to find our parent road.
     NEW.parent_place_id := find_parent_for_poi(NEW.osm_type, NEW.osm_id,


@@ -993,7 +1096,7 @@ BEGIN
       SELECT p.country_code, p.postcode, p.name FROM placex p
        WHERE p.place_id = NEW.parent_place_id INTO location;
 
       SELECT p.country_code, p.postcode, p.name FROM placex p
        WHERE p.place_id = NEW.parent_place_id INTO location;
 

-      IF is_place_address THEN
+      IF is_place_address and NEW.address ? 'place' THEN

         -- Check if the addr:place tag is part of the parent name
         SELECT count(*) INTO i
           FROM svals(location.name) AS pname WHERE pname = NEW.address->'place';
         -- Check if the addr:place tag is part of the parent name
         SELECT count(*) INTO i
           FROM svals(location.name) AS pname WHERE pname = NEW.address->'place';


@@ -1047,7 +1150,7 @@ BEGIN
   IF linked_place is not null THEN
     -- Recompute the ranks here as the ones from the linked place might
     -- have been shifted to accommodate surrounding boundaries.
   IF linked_place is not null THEN
     -- Recompute the ranks here as the ones from the linked place might
     -- have been shifted to accommodate surrounding boundaries.

-    SELECT place_id, osm_id, class, type, extratags,
+    SELECT place_id, osm_id, class, type, extratags, rank_search,

            centroid, geometry,
            (compute_place_rank(country_code, osm_type, class, type, admin_level,
                               (extratags->'capital') = 'yes', null)).*
            centroid, geometry,
            (compute_place_rank(country_code, osm_type, class, type, admin_level,
                               (extratags->'capital') = 'yes', null)).*


@@ -1088,7 +1191,7 @@ BEGIN
 
     SELECT wikipedia, importance
       FROM compute_importance(location.extratags, NEW.country_code,
 
     SELECT wikipedia, importance
       FROM compute_importance(location.extratags, NEW.country_code,

-                              'N', location.osm_id, NEW.centroid)
+                              location.rank_search, NEW.centroid)

       INTO linked_wikipedia,linked_importance;
 
     -- Use the maximum importance if one could be computed from the linked object.
       INTO linked_wikipedia,linked_importance;
 
     -- Use the maximum importance if one could be computed from the linked object.


@@ -1100,7 +1203,7 @@ BEGIN
   ELSE
     -- No linked place? As a last resort check if the boundary is tagged with
     -- a place type and adapt the rank address.
   ELSE
     -- No linked place? As a last resort check if the boundary is tagged with
     -- a place type and adapt the rank address.

-    IF NEW.rank_address > 0 and NEW.extratags ? 'place' THEN
+    IF NEW.rank_address between 4 and 25 and NEW.extratags ? 'place' THEN

       SELECT address_rank INTO place_address_level
         FROM compute_place_rank(NEW.country_code, 'A', 'place',
                                 NEW.extratags->'place', 0::SMALLINT, False, null);
       SELECT address_rank INTO place_address_level
         FROM compute_place_rank(NEW.country_code, 'A', 'place',
                                 NEW.extratags->'place', 0::SMALLINT, False, null);


@@ -1162,6 +1265,8 @@ BEGIN
     END IF;
   ELSEIF NEW.rank_address > 25 THEN
     max_rank := 25;
     END IF;
   ELSEIF NEW.rank_address > 25 THEN
     max_rank := 25;

+  ELSEIF NEW.class in ('place','boundary') and NEW.type in ('postcode','postal_code') THEN
+    max_rank := NEW.rank_search;

   ELSE
     max_rank := NEW.rank_address;
   END IF;
   ELSE
     max_rank := NEW.rank_address;
   END IF;


@@ -1210,8 +1315,14 @@ BEGIN
     {% endif %}
   END IF;
 
     {% endif %}
   END IF;
 

-  IF NEW.postcode is null AND NEW.rank_search > 8 THEN
-    NEW.postcode := get_nearest_postcode(NEW.country_code, NEW.geometry);
+  IF NEW.postcode is null AND NEW.rank_search > 8
+     AND (NEW.rank_address > 0
+          OR ST_GeometryType(NEW.geometry) not in ('ST_LineString','ST_MultiLineString')
+          OR ST_Length(NEW.geometry) < 0.02)
+  THEN
+    NEW.postcode := get_nearest_postcode(NEW.country_code,
+                                         CASE WHEN NEW.rank_address > 25
+                                              THEN NEW.centroid ELSE NEW.geometry END);

   END IF;
 
   {% if debug %}RAISE WARNING 'place update % % finished.', NEW.osm_type, NEW.osm_id;{% endif %}
   END IF;
 
   {% if debug %}RAISE WARNING 'place update % % finished.', NEW.osm_type, NEW.osm_id;{% endif %}


@@ -1292,6 +1403,8 @@ BEGIN
 
   {% if debug %}RAISE WARNING 'placex_delete:12 % %',OLD.osm_type,OLD.osm_id;{% endif %}
 
 
   {% if debug %}RAISE WARNING 'placex_delete:12 % %',OLD.osm_type,OLD.osm_id;{% endif %}
 

+  UPDATE location_postcode SET indexed_status = 2 WHERE parent_place_id = OLD.place_id;
+

   RETURN OLD;
 
 END;
   RETURN OLD;
 
 END;