ICU: better letter identification in normalization

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

diff --git a/lib-sql/tables.sql b/lib-sql/tables.sql
index d15e42c445eebf71d5cbc1d0b005ee4f1ad3a6bc..538286b841faff49294b6fff76bb84e0fb13a808 100644 (file)
--- a/lib-sql/tables.sql
+++ b/lib-sql/tables.sql
@@ -1,10 +1,17 @@
+-- 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,
   sequence_id integer,
   indexed boolean
   );
 drop table if exists import_status;
 CREATE TABLE import_status (
   lastimportdate timestamp with time zone NOT NULL,
   sequence_id integer,
   indexed boolean
   );

-GRANT SELECT ON import_status TO "{www-user}" ;
+GRANT SELECT ON import_status TO "{{config.DATABASE_WEBUSER}}" ;

 
 drop table if exists import_osmosis_log;
 CREATE TABLE import_osmosis_log (
 
 drop table if exists import_osmosis_log;
 CREATE TABLE import_osmosis_log (


@@ -30,27 +37,18 @@ CREATE TABLE new_query_log (
   secret text
   );
 CREATE INDEX idx_new_query_log_starttime ON new_query_log USING BTREE (starttime);
   secret text
   );
 CREATE INDEX idx_new_query_log_starttime ON new_query_log USING BTREE (starttime);

-GRANT INSERT ON new_query_log TO "{www-user}" ;
-GRANT UPDATE ON new_query_log TO "{www-user}" ;
-GRANT SELECT ON new_query_log TO "{www-user}" ;
+GRANT INSERT ON new_query_log TO "{{config.DATABASE_WEBUSER}}" ;
+GRANT UPDATE ON new_query_log TO "{{config.DATABASE_WEBUSER}}" ;
+GRANT SELECT ON new_query_log TO "{{config.DATABASE_WEBUSER}}" ;

 
 

-GRANT SELECT ON TABLE country_name TO "{www-user}";
+GRANT SELECT ON TABLE country_name 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
-  ) {ts:search-data};
-CREATE INDEX idx_word_word_token on word USING BTREE (word_token) {ts:search-index};
-GRANT SELECT ON word TO "{www-user}" ;
-DROP SEQUENCE IF EXISTS seq_word;
-CREATE SEQUENCE seq_word start 1;
+DROP TABLE IF EXISTS nominatim_properties;
+CREATE TABLE nominatim_properties (
+    property TEXT,
+    value TEXT
+);
+GRANT SELECT ON TABLE nominatim_properties TO "{{config.DATABASE_WEBUSER}}";

 
 drop table IF EXISTS location_area CASCADE;
 CREATE TABLE location_area (
 
 drop table IF EXISTS location_area CASCADE;
 CREATE TABLE location_area (


@@ -73,36 +71,20 @@ CREATE TABLE location_area_country (
   place_id BIGINT,
   country_code varchar(2),
   geometry GEOMETRY(Geometry, 4326)
   place_id BIGINT,
   country_code varchar(2),
   geometry GEOMETRY(Geometry, 4326)

-  ) {ts:address-data};
-CREATE INDEX idx_location_area_country_geometry ON location_area_country USING GIST (geometry) {ts:address-index};
-
-
-drop table IF EXISTS location_property CASCADE;
-CREATE TABLE location_property (
-  place_id BIGINT,
-  parent_place_id BIGINT,
-  partition SMALLINT,
-  housenumber TEXT,
-  postcode TEXT,
-  centroid GEOMETRY(Point, 4326)
-  );
+  ) {{db.tablespace.address_data}};
+CREATE INDEX idx_location_area_country_geometry ON location_area_country USING GIST (geometry) {{db.tablespace.address_index}};

 
 

-CREATE TABLE location_property_aux () INHERITS (location_property);
-CREATE INDEX idx_location_property_aux_place_id ON location_property_aux USING BTREE (place_id);
-CREATE INDEX idx_location_property_aux_parent_place_id ON location_property_aux USING BTREE (parent_place_id);
-CREATE INDEX idx_location_property_aux_housenumber_parent_place_id ON location_property_aux USING BTREE (parent_place_id, housenumber);
-GRANT SELECT ON location_property_aux TO "{www-user}";

 
 CREATE TABLE location_property_tiger (
   place_id BIGINT,
   parent_place_id BIGINT,
   startnumber INTEGER,
   endnumber INTEGER,
 
 CREATE TABLE location_property_tiger (
   place_id BIGINT,
   parent_place_id BIGINT,
   startnumber INTEGER,
   endnumber INTEGER,

+  step SMALLINT,

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

-  interpolationtype TEXT,

   postcode TEXT);
   postcode TEXT);

-GRANT SELECT ON location_property_tiger TO "{www-user}";
+GRANT SELECT ON location_property_tiger TO "{{config.DATABASE_WEBUSER}}";

 
 drop table if exists location_property_osmline;
 CREATE TABLE location_property_osmline (
 
 drop table if exists location_property_osmline;
 CREATE TABLE location_property_osmline (


@@ -113,20 +95,23 @@ 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)
     postcode TEXT,
     country_code VARCHAR(2)

-  ){ts:search-data};
-CREATE UNIQUE INDEX idx_osmline_place_id ON location_property_osmline USING BTREE (place_id) {ts:search-index};
-CREATE INDEX idx_osmline_geometry_sector ON location_property_osmline USING BTREE (geometry_sector) {ts:address-index};
-CREATE INDEX idx_osmline_linegeo ON location_property_osmline USING GIST (linegeo) {ts:search-index};
-GRANT SELECT ON location_property_osmline TO "{www-user}";
+  ){{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}}
+  WHERE startnumber is not null;
+GRANT SELECT ON location_property_osmline TO "{{config.DATABASE_WEBUSER}}";

 
 drop table IF EXISTS search_name;
 
 drop table IF EXISTS search_name;

+{% if not db.reverse_only %}

 CREATE TABLE search_name (
   place_id BIGINT,
   importance FLOAT,
 CREATE TABLE search_name (
   place_id BIGINT,
   importance FLOAT,


@@ -136,8 +121,10 @@ CREATE TABLE search_name (
   nameaddress_vector integer[],
   country_code varchar(2),
   centroid GEOMETRY(Geometry, 4326)
   nameaddress_vector integer[],
   country_code varchar(2),
   centroid GEOMETRY(Geometry, 4326)

-  ) {ts:search-data};
-CREATE INDEX idx_search_name_place_id ON search_name USING BTREE (place_id) {ts:search-index};
+  ) {{db.tablespace.search_data}};
+CREATE INDEX idx_search_name_place_id ON search_name USING BTREE (place_id) {{db.tablespace.search_index}};
+GRANT SELECT ON search_name to "{{config.DATABASE_WEBUSER}}" ;
+{% endif %}

 
 drop table IF EXISTS place_addressline;
 CREATE TABLE place_addressline (
 
 drop table IF EXISTS place_addressline;
 CREATE TABLE place_addressline (


@@ -147,8 +134,8 @@ CREATE TABLE place_addressline (
   cached_rank_address SMALLINT,
   fromarea boolean,
   isaddress boolean
   cached_rank_address SMALLINT,
   fromarea boolean,
   isaddress boolean

-  ) {ts:search-data};
-CREATE INDEX idx_place_addressline_place_id on place_addressline USING BTREE (place_id) {ts: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;
 CREATE TABLE placex (
 
 drop table if exists placex;
 CREATE TABLE placex (


@@ -164,28 +151,34 @@ 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)
   country_code varchar(2),
   housenumber TEXT,
   postcode TEXT,
   centroid GEOMETRY(Geometry, 4326)

-  ) {ts:search-data};
-CREATE UNIQUE INDEX idx_place_id ON placex USING BTREE (place_id) {ts:search-index};
-CREATE INDEX idx_placex_osmid ON placex USING BTREE (osm_type, osm_id) {ts:search-index};
-CREATE INDEX idx_placex_linked_place_id ON placex USING BTREE (linked_place_id) {ts:address-index} WHERE linked_place_id IS NOT NULL;
-CREATE INDEX idx_placex_rank_search ON placex USING BTREE (rank_search, geometry_sector) {ts:address-index};
-CREATE INDEX idx_placex_geometry ON placex USING GIST (geometry) {ts:search-index};
-CREATE INDEX idx_placex_adminname on placex USING BTREE (make_standard_name(name->'name')) {ts:address-index} WHERE osm_type='N' and rank_search < 26;
-CREATE INDEX idx_placex_wikidata on placex USING BTREE ((extratags -> 'wikidata')) {ts:address-index} WHERE extratags ? 'wikidata' and class = 'place' and osm_type = 'N' and rank_search < 26;
+  ) {{db.tablespace.search_data}};
+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}};
+CREATE INDEX idx_placex_geometry_buildings ON placex
+  USING {{postgres.spgist_geom}} (geometry) {{db.tablespace.search_index}}
+  WHERE address is not null and rank_search = 30
+        and ST_GeometryType(geometry) in ('ST_Polygon','ST_MultiPolygon');
+CREATE INDEX idx_placex_geometry_placenode ON placex
+  USING {{postgres.spgist_geom}} (geometry) {{db.tablespace.search_index}}
+  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;

 
 DROP SEQUENCE IF EXISTS seq_place;
 CREATE SEQUENCE seq_place start 1;
 
 DROP SEQUENCE IF EXISTS seq_place;
 CREATE SEQUENCE seq_place start 1;

-GRANT SELECT on placex to "{www-user}" ;
-GRANT SELECT ON search_name to "{www-user}" ;
-GRANT SELECT on place_addressline to "{www-user}" ;
-GRANT SELECT ON seq_word to "{www-user}" ;
-GRANT SELECT ON planet_osm_ways to "{www-user}" ;
-GRANT SELECT ON planet_osm_rels to "{www-user}" ;
-GRANT SELECT on location_area to "{www-user}" ;
+GRANT SELECT on placex to "{{config.DATABASE_WEBUSER}}" ;
+GRANT SELECT on place_addressline 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}}" ;

 
 -- Table for synthetic postcodes.
 DROP TABLE IF EXISTS location_postcode;
 
 -- Table for synthetic postcodes.
 DROP TABLE IF EXISTS location_postcode;


@@ -200,8 +193,9 @@ CREATE TABLE location_postcode (
   postcode TEXT,
   geometry GEOMETRY(Geometry, 4326)
   );
   postcode TEXT,
   geometry GEOMETRY(Geometry, 4326)
   );

-CREATE INDEX idx_postcode_geometry ON location_postcode USING GIST (geometry) {ts:address-index};
-GRANT SELECT ON location_postcode TO "{www-user}" ;
+CREATE UNIQUE INDEX idx_postcode_id ON location_postcode USING BTREE (place_id) {{db.tablespace.search_index}};
+CREATE INDEX idx_postcode_geometry ON location_postcode USING GIST (geometry) {{db.tablespace.address_index}};
+GRANT SELECT ON location_postcode TO "{{config.DATABASE_WEBUSER}}" ;

 
 DROP TABLE IF EXISTS import_polygon_error;
 CREATE TABLE import_polygon_error (
 
 DROP TABLE IF EXISTS import_polygon_error;
 CREATE TABLE import_polygon_error (


@@ -217,7 +211,7 @@ CREATE TABLE import_polygon_error (
   newgeometry GEOMETRY(Geometry, 4326)
   );
 CREATE INDEX idx_import_polygon_error_osmid ON import_polygon_error USING BTREE (osm_type, osm_id);
   newgeometry GEOMETRY(Geometry, 4326)
   );
 CREATE INDEX idx_import_polygon_error_osmid ON import_polygon_error USING BTREE (osm_type, osm_id);

-GRANT SELECT ON import_polygon_error TO "{www-user}";
+GRANT SELECT ON import_polygon_error TO "{{config.DATABASE_WEBUSER}}";

 
 DROP TABLE IF EXISTS import_polygon_delete;
 CREATE TABLE import_polygon_delete (
 
 DROP TABLE IF EXISTS import_polygon_delete;
 CREATE TABLE import_polygon_delete (


@@ -227,7 +221,7 @@ CREATE TABLE import_polygon_delete (
   type TEXT NOT NULL
   );
 CREATE INDEX idx_import_polygon_delete_osmid ON import_polygon_delete USING BTREE (osm_type, osm_id);
   type TEXT NOT NULL
   );
 CREATE INDEX idx_import_polygon_delete_osmid ON import_polygon_delete USING BTREE (osm_type, osm_id);

-GRANT SELECT ON import_polygon_delete TO "{www-user}";
+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;


@@ -261,3 +255,10 @@ ALTER TABLE ONLY wikipedia_redirect ADD CONSTRAINT wikipedia_redirect_pkey PRIMA
 -- 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'];
 -- 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'];

+
+-- 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}}";