Merge pull request #3424 from lonvia/importance-csc-import

[nominatim.git] / lib-sql / tables.sql

diff --git a/lib-sql/tables.sql b/lib-sql/tables.sql
index 609472ecb78f9bdbaecf2414fc8ec00fa47d368b..d3bc972a5e94e053c17b06b010627836935385f7 100644 (file)
--- a/lib-sql/tables.sql
+++ b/lib-sql/tables.sql
@@ -1,3 +1,10 @@
+-- SPDX-License-Identifier: GPL-2.0-only
+--
+-- This file is part of Nominatim. (https://nominatim.org)
+--
+-- Copyright (C) 2022 by the Nominatim developer community.
+-- For a full list of authors see the git log.
+

 drop table if exists import_status;
 CREATE TABLE import_status (
   lastimportdate timestamp with time zone NOT NULL,
 drop table if exists import_status;
 CREATE TABLE import_status (
   lastimportdate timestamp with time zone NOT NULL,


@@ -38,27 +45,11 @@ GRANT SELECT ON TABLE country_name TO "{{config.DATABASE_WEBUSER}}";
 
 DROP TABLE IF EXISTS nominatim_properties;
 CREATE TABLE nominatim_properties (
 
 DROP TABLE IF EXISTS nominatim_properties;
 CREATE TABLE nominatim_properties (

-    property TEXT,
+    property TEXT NOT NULL,

     value TEXT
 );
 GRANT SELECT ON TABLE nominatim_properties TO "{{config.DATABASE_WEBUSER}}";
 
     value TEXT
 );
 GRANT SELECT ON TABLE nominatim_properties TO "{{config.DATABASE_WEBUSER}}";
 

-drop table IF EXISTS word;
-CREATE TABLE word (
-  word_id INTEGER,
-  word_token text,
-  word text,
-  class text,
-  type text,
-  country_code varchar(2),
-  search_name_count INTEGER,
-  operator TEXT
-  ) {{db.tablespace.search_data}};
-CREATE INDEX idx_word_word_token on word USING BTREE (word_token) {{db.tablespace.search_index}};
-GRANT SELECT ON word TO "{{config.DATABASE_WEBUSER}}" ;
-DROP SEQUENCE IF EXISTS seq_word;
-CREATE SEQUENCE seq_word start 1;
-

 drop table IF EXISTS location_area CASCADE;
 CREATE TABLE location_area (
   place_id BIGINT,
 drop table IF EXISTS location_area CASCADE;
 CREATE TABLE location_area (
   place_id BIGINT,


@@ -89,9 +80,9 @@ CREATE TABLE location_property_tiger (
   parent_place_id BIGINT,
   startnumber INTEGER,
   endnumber INTEGER,
   parent_place_id BIGINT,
   startnumber INTEGER,
   endnumber INTEGER,

+  step SMALLINT,

   partition SMALLINT,
   linegeo GEOMETRY,
   partition SMALLINT,
   linegeo GEOMETRY,

-  interpolationtype TEXT,

   postcode TEXT);
 GRANT SELECT ON location_property_tiger TO "{{config.DATABASE_WEBUSER}}";
 
   postcode TEXT);
 GRANT SELECT ON location_property_tiger TO "{{config.DATABASE_WEBUSER}}";
 


@@ -104,17 +95,19 @@ CREATE TABLE location_property_osmline (
     indexed_date TIMESTAMP,
     startnumber INTEGER,
     endnumber INTEGER,
     indexed_date TIMESTAMP,
     startnumber INTEGER,
     endnumber INTEGER,

+    step SMALLINT,

     partition SMALLINT,
     indexed_status SMALLINT,
     linegeo GEOMETRY,
     partition SMALLINT,
     indexed_status SMALLINT,
     linegeo GEOMETRY,

-    interpolationtype TEXT,

     address HSTORE,
     address HSTORE,

+    token_info JSONB, -- custom column for tokenizer use only

     postcode TEXT,
     country_code VARCHAR(2)
   ){{db.tablespace.search_data}};
 CREATE UNIQUE INDEX idx_osmline_place_id ON location_property_osmline USING BTREE (place_id) {{db.tablespace.search_index}};
 CREATE INDEX idx_osmline_geometry_sector ON location_property_osmline USING BTREE (geometry_sector) {{db.tablespace.address_index}};
     postcode TEXT,
     country_code VARCHAR(2)
   ){{db.tablespace.search_data}};
 CREATE UNIQUE INDEX idx_osmline_place_id ON location_property_osmline USING BTREE (place_id) {{db.tablespace.search_index}};
 CREATE INDEX idx_osmline_geometry_sector ON location_property_osmline USING BTREE (geometry_sector) {{db.tablespace.address_index}};

-CREATE INDEX idx_osmline_linegeo ON location_property_osmline USING GIST (linegeo) {{db.tablespace.search_index}};
+CREATE INDEX idx_osmline_linegeo ON location_property_osmline USING GIST (linegeo) {{db.tablespace.search_index}}
+  WHERE startnumber is not null;

 GRANT SELECT ON location_property_osmline TO "{{config.DATABASE_WEBUSER}}";
 
 drop table IF EXISTS search_name;
 GRANT SELECT ON location_property_osmline TO "{{config.DATABASE_WEBUSER}}";
 
 drop table IF EXISTS search_name;


@@ -144,7 +137,9 @@ CREATE TABLE place_addressline (
   ) {{db.tablespace.search_data}};
 CREATE INDEX idx_place_addressline_place_id on place_addressline USING BTREE (place_id) {{db.tablespace.search_index}};
 
   ) {{db.tablespace.search_data}};
 CREATE INDEX idx_place_addressline_place_id on place_addressline USING BTREE (place_id) {{db.tablespace.search_index}};
 

-drop table if exists placex;
+---------  PLACEX - storage for all indexed places -----------------
+
+DROP TABLE IF EXISTS placex;

 CREATE TABLE placex (
   place_id BIGINT NOT NULL,
   parent_place_id BIGINT,
 CREATE TABLE placex (
   place_id BIGINT NOT NULL,
   parent_place_id BIGINT,


@@ -158,27 +153,76 @@ CREATE TABLE placex (
   indexed_status SMALLINT,
   LIKE place INCLUDING CONSTRAINTS,
   wikipedia TEXT, -- calculated wikipedia article name (language:title)
   indexed_status SMALLINT,
   LIKE place INCLUDING CONSTRAINTS,
   wikipedia TEXT, -- calculated wikipedia article name (language:title)

+  token_info JSONB, -- custom column for tokenizer use only

   country_code varchar(2),
   housenumber TEXT,
   postcode TEXT,
   centroid GEOMETRY(Geometry, 4326)
   ) {{db.tablespace.search_data}};
   country_code varchar(2),
   housenumber TEXT,
   postcode TEXT,
   centroid GEOMETRY(Geometry, 4326)
   ) {{db.tablespace.search_data}};

+

 CREATE UNIQUE INDEX idx_place_id ON placex USING BTREE (place_id) {{db.tablespace.search_index}};
 CREATE UNIQUE INDEX idx_place_id ON placex USING BTREE (place_id) {{db.tablespace.search_index}};

-CREATE INDEX idx_placex_osmid ON placex USING BTREE (osm_type, osm_id) {{db.tablespace.search_index}};
-CREATE INDEX idx_placex_linked_place_id ON placex USING BTREE (linked_place_id) {{db.tablespace.address_index}} WHERE linked_place_id IS NOT NULL;
-CREATE INDEX idx_placex_rank_search ON placex USING BTREE (rank_search, geometry_sector) {{db.tablespace.address_index}};
-CREATE INDEX idx_placex_geometry ON placex USING GIST (geometry) {{db.tablespace.search_index}};
+{% for osm_type in ('N', 'W', 'R') %}
+CREATE INDEX idx_placex_osmid_{{osm_type | lower}} ON placex
+  USING BTREE (osm_id) {{db.tablespace.search_index}}
+  WHERE osm_type = '{{osm_type}}';
+{% endfor %}
+
+-- Usage: - removing linkage status on update
+--        - lookup linked places for /details
+CREATE INDEX idx_placex_linked_place_id ON placex
+  USING BTREE (linked_place_id) {{db.tablespace.address_index}}
+  WHERE linked_place_id IS NOT NULL;
+
+-- Usage: - check that admin boundaries do not overtake each other rank-wise
+--        - check that place node in a admin boundary with the same address level
+--        - boundary is not completely contained in a place area
+--        - parenting of large-area or unparentable features
+CREATE INDEX idx_placex_geometry_address_area_candidates ON placex
+  USING gist (geometry) {{db.tablespace.address_index}}
+  WHERE rank_address between 1 and 25
+        and ST_GeometryType(geometry) in ('ST_Polygon','ST_MultiPolygon');
+
+-- Usage: - POI is within building with housenumber
+CREATE INDEX idx_placex_geometry_buildings ON placex
+  USING {{postgres.spgist_geom}} (geometry) {{db.tablespace.address_index}}
+  WHERE address is not null and rank_search = 30
+        and ST_GeometryType(geometry) in ('ST_Polygon','ST_MultiPolygon');
+
+-- Usage: - linking of similar named places to boundaries
+--        - linking of place nodes with same type to boundaries

 CREATE INDEX idx_placex_geometry_placenode ON placex
 CREATE INDEX idx_placex_geometry_placenode ON placex

-  USING GIST (geometry) {{db.tablespace.search_index}}
+  USING {{postgres.spgist_geom}} (geometry) {{db.tablespace.address_index}}

   WHERE osm_type = 'N' and rank_search < 26
   WHERE osm_type = 'N' and rank_search < 26

-        and class = 'place' and type != 'postcode' and linked_place_id is null;
-CREATE INDEX idx_placex_wikidata on placex USING BTREE ((extratags -> 'wikidata')) {{db.tablespace.address_index}} WHERE extratags ? 'wikidata' and class = 'place' and osm_type = 'N' and rank_search < 26;
+        and class = 'place' and type != 'postcode';
+
+-- Usage: - is node part of a way?
+--        - find parent of interpolation spatially
+CREATE INDEX idx_placex_geometry_lower_rank_ways ON placex
+  USING {{postgres.spgist_geom}} (geometry) {{db.tablespace.address_index}}
+  WHERE osm_type = 'W' and rank_search >= 26;
+
+-- Usage: - linking place nodes by wikidata tag to boundaries
+CREATE INDEX idx_placex_wikidata on placex
+  USING BTREE ((extratags -> 'wikidata')) {{db.tablespace.address_index}}
+  WHERE extratags ? 'wikidata' and class = 'place'
+        and osm_type = 'N' and rank_search < 26;
+
+-- The following two indexes function as a todo list for indexing.
+
+CREATE INDEX idx_placex_rank_address_sector ON placex
+  USING BTREE (rank_address, geometry_sector) {{db.tablespace.address_index}}
+  WHERE indexed_status > 0;
+
+CREATE INDEX idx_placex_rank_boundaries_sector ON placex
+  USING BTREE (rank_search, geometry_sector) {{db.tablespace.address_index}}
+  WHERE class = 'boundary' and type = 'administrative'
+        and indexed_status > 0;
+

 
 DROP SEQUENCE IF EXISTS seq_place;
 CREATE SEQUENCE seq_place start 1;
 GRANT SELECT on placex to "{{config.DATABASE_WEBUSER}}" ;
 GRANT SELECT on place_addressline to "{{config.DATABASE_WEBUSER}}" ;
 
 DROP SEQUENCE IF EXISTS seq_place;
 CREATE SEQUENCE seq_place start 1;
 GRANT SELECT on placex to "{{config.DATABASE_WEBUSER}}" ;
 GRANT SELECT on place_addressline to "{{config.DATABASE_WEBUSER}}" ;

-GRANT SELECT ON seq_word to "{{config.DATABASE_WEBUSER}}" ;

 GRANT SELECT ON planet_osm_ways to "{{config.DATABASE_WEBUSER}}" ;
 GRANT SELECT ON planet_osm_rels to "{{config.DATABASE_WEBUSER}}" ;
 GRANT SELECT on location_area to "{{config.DATABASE_WEBUSER}}" ;
 GRANT SELECT ON planet_osm_ways to "{{config.DATABASE_WEBUSER}}" ;
 GRANT SELECT ON planet_osm_rels to "{{config.DATABASE_WEBUSER}}" ;
 GRANT SELECT on location_area to "{{config.DATABASE_WEBUSER}}" ;


@@ -229,34 +273,31 @@ GRANT SELECT ON import_polygon_delete TO "{{config.DATABASE_WEBUSER}}";
 DROP SEQUENCE IF EXISTS file;
 CREATE SEQUENCE file start 1;
 
 DROP SEQUENCE IF EXISTS file;
 CREATE SEQUENCE file start 1;
 

--- null table so it won't error
--- deliberately no drop - importing the table is expensive and static, if it is already there better to avoid removing it
-CREATE TABLE wikipedia_article (
-    language text NOT NULL,
-    title text NOT NULL,
-    langcount integer,
-    othercount integer,
-    totalcount integer,
-    lat double precision,
-    lon double precision,
-    importance double precision,
-    osm_type character(1),
-    osm_id bigint,
-    wd_page_title text,
-    instance_of text
-);
-ALTER TABLE ONLY wikipedia_article ADD CONSTRAINT wikipedia_article_pkey PRIMARY KEY (language, title);
-CREATE INDEX idx_wikipedia_article_osm_id ON wikipedia_article USING btree (osm_type, osm_id);
-
-CREATE TABLE wikipedia_redirect (
-    language text,
-    from_title text,
-    to_title text
-);
-ALTER TABLE ONLY wikipedia_redirect ADD CONSTRAINT wikipedia_redirect_pkey PRIMARY KEY (language, from_title);
+{% if 'wikimedia_importance' not in db.tables and 'wikipedia_article' not in db.tables %}
+-- create dummy tables here, if nothing was imported
+CREATE TABLE wikimedia_importance (
+  language TEXT NOT NULL,
+  title TEXT NOT NULL,
+  importance double precision NOT NULL,
+  wikidata TEXT
+)  {{db.tablespace.address_data}};
+{% endif %}

 
 -- osm2pgsql does not create indexes on the middle tables for Nominatim
 -- Add one for lookup of associated street relations.
 
 -- osm2pgsql does not create indexes on the middle tables for Nominatim
 -- Add one for lookup of associated street relations.

-CREATE INDEX planet_osm_rels_parts_associated_idx ON planet_osm_rels USING gin(parts) WHERE tags @> ARRAY['associatedStreet'];
+{% if db.middle_db_format == '1' %}
+CREATE INDEX planet_osm_rels_parts_associated_idx ON planet_osm_rels USING gin(parts)
+  {{db.tablespace.address_index}}
+  WHERE tags @> ARRAY['associatedStreet'];
+{% else %}
+CREATE INDEX planet_osm_rels_relation_members_idx ON planet_osm_rels USING gin(planet_osm_member_ids(members, 'R'::character(1)))
+  WITH (fastupdate=off)
+  {{db.tablespace.address_index}};
+{% endif %}
+
+-- Needed for lookups if a node is part of an interpolation.
+CREATE INDEX IF NOT EXISTS idx_place_interpolations
+    ON place USING gist(geometry) {{db.tablespace.address_index}}
+    WHERE osm_type = 'W' and address ? 'interpolation';

 
 GRANT SELECT ON table country_osm_grid to "{{config.DATABASE_WEBUSER}}";
 
 GRANT SELECT ON table country_osm_grid to "{{config.DATABASE_WEBUSER}}";