Merge pull request #3986 from lonvia/rework-tiger-tests

Rework unit tests for import of tiger data

CONTRIBUTING.md

@@ -42,6 +42,15 @@ description or in documentation need to
    sufficient. You need to show that the code actually solves the problem
    the PR claims to solve.
 
+## Getting Started with Development
+
+Please see the development section of the Nominatim documentation for
+
+* [an architecture overview](https://nominatim.org/release-docs/develop/develop/overview/)
+  and backgrounds on some of the algorithms
+* [how to set up a development environment](https://nominatim.org/release-docs/develop/develop/Development-Environment/)
+* and background on [how tests are organised](https://nominatim.org/release-docs/develop/develop/Testing/)
+
 
 ## Coding style
 

docs/admin/Deployment-Python.md

@@ -10,14 +10,14 @@ Nominatim. Please refer to the documentation of
 [Nginx](https://nginx.org/en/docs/) for background information on how
 to configure it.
 
-!!! Note
-    Throughout this page, we assume your Nominatim project directory is
-    located in `/srv/nominatim-project`. If you have put it somewhere else,
-    you need to adjust the commands and configuration accordingly.
-
-
 ### Installing the required packages
 
+!!! warning
+    ASGI support in gunicorn requires at least version 25.0. If you need
+    to work with an older version of gunicorn, please refer to
+    [older Nominatim deployment documentation](https://nominatim.org/release-docs/5.2/admin/Deployment-Python/)
+    to learn how to run gunicorn with uvicorn.
+
 The Nominatim frontend is best run from its own virtual environment. If
 you have already created one for the database backend during the
 [installation](Installation.md#building-nominatim), you can use that. Otherwise
@@ -37,23 +37,27 @@ cd Nominatim
 ```
 
 The recommended way to deploy a Python ASGI application is to run
-the ASGI runner [uvicorn](https://www.uvicorn.org/)
-together with [gunicorn](https://gunicorn.org/) HTTP server. We use
+the [gunicorn](https://gunicorn.org/) HTTP server. We use
 Falcon here as the web framework.
 
 Add the necessary packages to your virtual environment:
 
 ``` sh
-/srv/nominatim-venv/bin/pip install falcon uvicorn gunicorn
+/srv/nominatim-venv/bin/pip install falcon gunicorn
 ```
 
 ### Setting up Nominatim as a systemd job
 
+!!! Note
+    These instructions assume your Nominatim project directory is
+    located in `/srv/nominatim-project`. If you have put it somewhere else,
+    you need to adjust the commands and configuration accordingly.
+
 Next you need to set up the service that runs the Nominatim frontend. This is
 easiest done with a systemd job.
 
 First you need to tell systemd to create a socket file to be used by
-hunicorn. Create the following file `/etc/systemd/system/nominatim.socket`:
+gunicorn. Create the following file `/etc/systemd/system/nominatim.socket`:
 
 ``` systemd
 [Unit]
@@ -81,10 +85,8 @@ Type=simple
 User=www-data
 Group=www-data
 WorkingDirectory=/srv/nominatim-project
-ExecStart=/srv/nominatim-venv/bin/gunicorn -b unix:/run/nominatim.sock -w 4 -k uvicorn.workers.UvicornWorker "nominatim_api.server.falcon.server:run_wsgi()"
+ExecStart=/srv/nominatim-venv/bin/gunicorn -b unix:/run/nominatim.sock -w 4 --worker-class asgi --protocol uwsgi --worker-connections 1000 "nominatim_api.server.falcon.server:run_wsgi()"
 ExecReload=/bin/kill -s HUP $MAINPID
-StandardOutput=append:/var/log/gunicorn-nominatim.log
-StandardError=inherit
 PrivateTmp=true
 TimeoutStopSec=5
 KillMode=mixed
@@ -96,7 +98,10 @@ WantedBy=multi-user.target
 This sets up gunicorn with 4 workers (`-w 4` in ExecStart). Each worker runs
 its own Python process using
 [`NOMINATIM_API_POOL_SIZE`](../customize/Settings.md#nominatim_api_pool_size)
-connections to the database to serve requests in parallel.
+connections to the database to serve requests in parallel. The parameter
+`--worker-connections` restricts how many requests gunicorn will queue for
+each worker. This can help distribute work better when the server is under
+high load.
 
 Make the new services known to systemd and start it:
 
@@ -108,13 +113,15 @@ sudo systemctl enable nominatim.service
 sudo systemctl start nominatim.service
 ```
 
-This sets the service up, so that Nominatim is automatically started
+This sets the service up so that Nominatim is automatically started
 on reboot.
 
 ### Configuring nginx
 
 To make the service available to the world, you need to proxy it through
-nginx. Add the following definition to the default configuration:
+nginx. We use the binary uwsgi protocol to speed up communication
+between nginx and gunicorn. Add the following definition to the default
+configuration:
 
 ``` nginx
 upstream nominatim_service {
@@ -129,11 +136,8 @@ server {
     index /search;
 
     location / {
-            proxy_set_header Host $http_host;
-            proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
-            proxy_set_header X-Forwarded-Proto $scheme;
-            proxy_redirect off;
-            proxy_pass http://nominatim_service;
+        uwsgi_pass nominatim_service;
+        include uwsgi_params;
     }
 }
 ```

docs/develop/Development-Environment.md

@@ -56,7 +56,7 @@ The easiest way, to handle these Python dependencies is to run your
 development from within a virtual environment.
 
 ```sh
-sudo apt install libsqlite3-mod-spatialite osm2pgsql \
+sudo apt install build-essential libsqlite3-mod-spatialite osm2pgsql \
                  postgresql-postgis postgresql-postgis-scripts \
                  pkg-config libicu-dev virtualenv
 ```
@@ -68,11 +68,11 @@ virtualenv ~/nominatim-dev-venv
 ~/nominatim-dev-venv/bin/pip install\
     psutil 'psycopg[binary]' PyICU SQLAlchemy \
     python-dotenv jinja2 pyYAML \
-    mkdocs 'mkdocstrings[python]' mkdocs-gen-files \
+    mkdocs 'mkdocstrings[python]' mkdocs-gen-files mkdocs-material \
     pytest pytest-asyncio pytest-bdd flake8 \
     types-jinja2 types-markupsafe types-psutil types-psycopg2 \
     types-pygments types-pyyaml types-requests types-ujson \
-    types-urllib3 typing-extensions unicorn falcon starlette \
+    types-urllib3 typing-extensions gunicorn falcon starlette \
     uvicorn mypy osmium aiosqlite mwparserfromhell
 ```
 

docs/mk_install_instructions.py

@@ -13,7 +13,8 @@ for infile in VAGRANT_PATH.glob('Install-on-*.sh'):
     outfile = f"admin/{infile.stem}.md"
     title = infile.stem.replace('-', ' ')
 
-    with mkdocs_gen_files.open(outfile, "w") as outfd, infile.open() as infd:
+    with mkdocs_gen_files.open(outfile, "w", encoding='utf-8') as outfd, \
+            infile.open(encoding='utf-8') as infd:
         print("#", title, file=outfd)
         has_empty = False
         for line in infd:

lib-sql/functions/placex_triggers.sql

@@ -29,6 +29,7 @@ DECLARE
   location RECORD;
   result prepare_update_info;
   extra_names HSTORE;
+  default_language VARCHAR(10);
 BEGIN
   IF not p.address ? '_inherited' THEN
     result.address := p.address;
@@ -85,6 +86,13 @@ BEGIN
 
     IF location.name is not NULL THEN
       {% if debug %}RAISE WARNING 'Names original: %, location: %', result.name, location.name;{% endif %}
+
+      -- Add the linked-place (e.g. city) name as a searchable placename in the default language (if any)
+      default_language := get_country_language_code(location.country_code);
+      IF default_language is not NULL AND NOT location.name ? ('name:' || default_language) THEN
+        location.name := location.name || hstore('name:' || default_language, location.name->'name');
+      END IF;
+
       -- 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
@@ -672,7 +680,7 @@ CREATE OR REPLACE FUNCTION placex_insert()
   AS $$
 DECLARE
   postcode TEXT;
-  result BOOLEAN;
+  result INT;
   is_area BOOLEAN;
   country_code VARCHAR(2);
   diameter FLOAT;
@@ -777,11 +785,12 @@ BEGIN
 
 
    -- add to tables for special search
-   -- Note: won't work on initial import because the classtype tables
-   -- do not yet exist. It won't hurt either.
   classtable := 'place_classtype_' || NEW.class || '_' || NEW.type;
-  SELECT count(*)>0 FROM pg_tables WHERE tablename = classtable and schemaname = current_schema() INTO result;
-  IF result THEN
+  SELECT count(*) INTO result
+    FROM pg_tables
+    WHERE classtable NOT SIMILAR TO '%\W%'
+          AND tablename = classtable and schemaname = current_schema();
+  IF result > 0 THEN
     EXECUTE 'INSERT INTO ' || classtable::regclass || ' (place_id, centroid) VALUES ($1,$2)' 
     USING NEW.place_id, NEW.centroid;
   END IF;
@@ -1337,6 +1346,7 @@ CREATE OR REPLACE FUNCTION placex_delete()
   AS $$
 DECLARE
   b BOOLEAN;
+  result INT;
   classtable TEXT;
 BEGIN
   -- RAISE WARNING 'placex_delete % %',OLD.osm_type,OLD.osm_id;
@@ -1395,8 +1405,12 @@ BEGIN
 
   -- remove from tables for special search
   classtable := 'place_classtype_' || OLD.class || '_' || OLD.type;
-  SELECT count(*)>0 FROM pg_tables WHERE tablename = classtable and schemaname = current_schema() INTO b;
-  IF b THEN
+  SELECT count(*) INTO result
+    FROM pg_tables
+    WHERE classtable NOT SIMILAR TO '%\W%'
+          AND tablename = classtable and schemaname = current_schema();
+
+  IF result > 0 THEN
     EXECUTE 'DELETE FROM ' || classtable::regclass || ' WHERE place_id = $1' USING OLD.place_id;
   END IF;
 

lib-sql/tables.sql

@@ -5,276 +5,21 @@
 -- Copyright (C) 2026 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_osmosis_log;
-CREATE TABLE import_osmosis_log (
-  batchend timestamp,
-  batchseq integer,
-  batchsize bigint,
-  starttime timestamp,
-  endtime timestamp,
-  event text
-  );
-
-DROP TABLE IF EXISTS nominatim_properties;
-CREATE TABLE nominatim_properties (
-    property TEXT NOT NULL,
-    value TEXT
-);
-
-drop table IF EXISTS location_area CASCADE;
-CREATE TABLE location_area (
-  place_id BIGINT NOT NULL,
-  keywords INTEGER[] NOT NULL,
-  partition SMALLINT NOT NULL,
-  rank_search SMALLINT NOT NULL,
-  rank_address SMALLINT NOT NULL,
-  country_code VARCHAR(2),
-  isguess BOOL NOT NULL,
-  postcode TEXT,
-  centroid GEOMETRY(Point, 4326) NOT NULL,
-  geometry GEOMETRY(Geometry, 4326) NOT NULL
-  );
-
-CREATE TABLE location_area_large () INHERITS (location_area);
-
-DROP TABLE IF EXISTS location_area_country;
-CREATE TABLE location_area_country (
-  place_id BIGINT NOT NULL,
-  country_code varchar(2) NOT NULL,
-  geometry GEOMETRY(Geometry, 4326) NOT NULL
-  ) {{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_tiger (
-  place_id BIGINT NOT NULL,
-  parent_place_id BIGINT,
-  startnumber INTEGER NOT NULL,
-  endnumber INTEGER NOT NULL,
-  step SMALLINT NOT NULL,
-  partition SMALLINT NOT NULL,
-  linegeo GEOMETRY NOT NULL,
-  postcode TEXT);
-
-drop table if exists location_property_osmline;
-CREATE TABLE location_property_osmline (
-    place_id BIGINT NOT NULL,
-    osm_id BIGINT NOT NULL,
-    parent_place_id BIGINT,
-    geometry_sector INTEGER NOT NULL,
-    indexed_date TIMESTAMP,
-    startnumber INTEGER,
-    endnumber INTEGER,
-    step SMALLINT,
-    partition SMALLINT NOT NULL,
-    indexed_status SMALLINT NOT NULL,
-    linegeo GEOMETRY NOT NULL,
-    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}};
-CREATE INDEX idx_osmline_linegeo ON location_property_osmline USING GIST (linegeo) {{db.tablespace.search_index}}
-  WHERE startnumber is not null;
-
-drop table IF EXISTS search_name;
-{% if not db.reverse_only %}
-CREATE TABLE search_name (
-  place_id BIGINT NOT NULL,
-  importance FLOAT NOT NULL,
-  search_rank SMALLINT NOT NULL,
-  address_rank SMALLINT NOT NULL,
-  name_vector integer[] NOT NULL,
-  nameaddress_vector integer[] NOT NULL,
-  country_code varchar(2),
-  centroid GEOMETRY(Geometry, 4326) NOT NULL
-  ) {{db.tablespace.search_data}};
-CREATE UNIQUE INDEX idx_search_name_place_id
-  ON search_name USING BTREE (place_id) {{db.tablespace.search_index}};
-{% endif %}
-
-drop table IF EXISTS place_addressline;
-CREATE TABLE place_addressline (
-  place_id BIGINT NOT NULL,
-  address_place_id BIGINT NOT NULL,
-  distance FLOAT NOT NULL,
-  cached_rank_address SMALLINT NOT NULL,
-  fromarea boolean NOT NULL,
-  isaddress boolean NOT NULL
-  ) {{db.tablespace.search_data}};
-CREATE INDEX idx_place_addressline_place_id on place_addressline USING BTREE (place_id) {{db.tablespace.search_index}};
-
----------  PLACEX - storage for all indexed places -----------------
-
-DROP TABLE IF EXISTS placex;
-CREATE TABLE placex (
-  place_id BIGINT NOT NULL,
-  parent_place_id BIGINT,
-  linked_place_id BIGINT,
-  importance FLOAT,
-  indexed_date TIMESTAMP,
-  geometry_sector INTEGER NOT NULL,
-  rank_address SMALLINT NOT NULL,
-  rank_search SMALLINT NOT NULL,
-  partition SMALLINT NOT NULL,
-  indexed_status SMALLINT NOT NULL,
-  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) NOT NULL
-  ) {{db.tablespace.search_data}};
-
-CREATE UNIQUE INDEX idx_place_id ON placex USING BTREE (place_id) {{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 SPGIST (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
-  USING SPGIST (geometry) {{db.tablespace.address_index}}
-  WHERE osm_type = 'N' and rank_search < 26 and class = 'place';
-
--- Usage: - is node part of a way?
---        - find parent of interpolation spatially
-CREATE INDEX idx_placex_geometry_lower_rank_ways ON placex
-  USING SPGIST (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;
 
--- Table for synthetic postcodes.
-DROP TABLE IF EXISTS location_postcodes;
-CREATE TABLE location_postcodes (
-  place_id BIGINT NOT NULL,
-  parent_place_id BIGINT,
-  osm_id BIGINT,
-  rank_search SMALLINT NOT NULL,
-  indexed_status SMALLINT NOT NULL,
-  indexed_date TIMESTAMP,
-  country_code varchar(2) NOT NULL,
-  postcode TEXT NOT NULL,
-  centroid GEOMETRY(Geometry, 4326) NOT NULL,
-  geometry GEOMETRY(Geometry, 4326) NOT NULL
-  );
-CREATE UNIQUE INDEX idx_location_postcodes_id ON location_postcodes
-  USING BTREE (place_id) {{db.tablespace.search_index}};
-CREATE INDEX idx_location_postcodes_geometry ON location_postcodes
-  USING GIST (geometry) {{db.tablespace.search_index}};
-CREATE INDEX IF NOT EXISTS idx_location_postcodes_postcode
-  ON location_postcodes USING BTREE (postcode, country_code)
-  {{db.tablespace.search_index}};
-CREATE INDEX IF NOT EXISTS idx_location_postcodes_osmid
-  ON location_postcodes USING BTREE (osm_id) {{db.tablespace.search_index}};
-
--- Table to store location of entrance nodes
-DROP TABLE IF EXISTS placex_entrance;
-CREATE TABLE placex_entrance (
-  place_id BIGINT NOT NULL,
-  osm_id BIGINT NOT NULL,
-  type TEXT NOT NULL,
-  location GEOMETRY(Point, 4326) NOT NULL,
-  extratags HSTORE
-  );
-CREATE UNIQUE INDEX idx_placex_entrance_place_id_osm_id ON placex_entrance
-  USING BTREE (place_id, osm_id) {{db.tablespace.search_index}};
-
--- Create an index on the place table for lookups to populate the entrance
--- table
-CREATE INDEX IF NOT EXISTS idx_placex_entrance_lookup ON place
-  USING BTREE (osm_id)
-  WHERE class IN ('routing:entrance', 'entrance');
-
-DROP TABLE IF EXISTS import_polygon_error;
-CREATE TABLE import_polygon_error (
-  osm_id BIGINT,
-  osm_type CHAR(1),
-  class TEXT NOT NULL,
-  type TEXT NOT NULL,
-  name HSTORE,
-  country_code varchar(2),
-  updated timestamp,
-  errormessage text,
-  prevgeometry GEOMETRY(Geometry, 4326),
-  newgeometry GEOMETRY(Geometry, 4326)
-  );
-CREATE INDEX idx_import_polygon_error_osmid ON import_polygon_error USING BTREE (osm_type, osm_id);
-
-DROP TABLE IF EXISTS import_polygon_delete;
-CREATE TABLE import_polygon_delete (
-  osm_id BIGINT,
-  osm_type CHAR(1),
-  class TEXT NOT NULL,
-  type TEXT NOT NULL
-  );
-CREATE INDEX idx_import_polygon_delete_osmid ON import_polygon_delete USING BTREE (osm_type, osm_id);
-
-DROP SEQUENCE IF EXISTS file;
-CREATE SEQUENCE file start 1;
-
-{% 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 %}
+{% include('tables/status.sql') %}
+{% include('tables/nominatim_properties.sql') %}
+{% include('tables/location_area.sql') %}
+{% include('tables/tiger.sql') %}
+{% include('tables/interpolation.sql') %}
+{% include('tables/search_name.sql') %}
+{% include('tables/addressline.sql') %}
+{% include('tables/placex.sql') %}
+{% include('tables/postcodes.sql') %}
+{% include('tables/entrance.sql') %}
+{% include('tables/import_reports.sql') %}
+{% include('tables/importance_tables.sql') %}
 
 -- osm2pgsql does not create indexes on the middle tables for Nominatim
 -- Add one for lookup of associated street relations.

lib-sql/tables/addressline.sql

@@ -0,0 +1,20 @@
+-- SPDX-License-Identifier: GPL-2.0-only
+--
+-- This file is part of Nominatim. (https://nominatim.org)
+--
+-- Copyright (C) 2026 by the Nominatim developer community.
+-- For a full list of authors see the git log.
+
+DROP TABLE IF EXISTS place_addressline;
+
+CREATE TABLE place_addressline (
+  place_id BIGINT NOT NULL,
+  address_place_id BIGINT NOT NULL,
+  distance FLOAT NOT NULL,
+  cached_rank_address SMALLINT NOT NULL,
+  fromarea boolean NOT NULL,
+  isaddress boolean NOT NULL
+  ) {{db.tablespace.search_data}};
+
+CREATE INDEX idx_place_addressline_place_id ON place_addressline
+  USING BTREE (place_id) {{db.tablespace.search_index}};

lib-sql/tables/entrance.sql

@@ -0,0 +1,20 @@
+-- SPDX-License-Identifier: GPL-2.0-only
+--
+-- This file is part of Nominatim. (https://nominatim.org)
+--
+-- Copyright (C) 2026 by the Nominatim developer community.
+-- For a full list of authors see the git log.
+
+-- Table to store location of entrance nodes
+DROP TABLE IF EXISTS placex_entrance;
+
+CREATE TABLE placex_entrance (
+  place_id BIGINT NOT NULL,
+  osm_id BIGINT NOT NULL,
+  type TEXT NOT NULL,
+  location GEOMETRY(Point, 4326) NOT NULL,
+  extratags HSTORE
+  );
+
+CREATE UNIQUE INDEX idx_placex_entrance_place_id_osm_id ON placex_entrance
+  USING BTREE (place_id, osm_id) {{db.tablespace.search_index}};

lib-sql/tables/import_reports.sql

@@ -0,0 +1,35 @@
+-- SPDX-License-Identifier: GPL-2.0-only
+--
+-- This file is part of Nominatim. (https://nominatim.org)
+--
+-- Copyright (C) 2026 by the Nominatim developer community.
+-- For a full list of authors see the git log.
+
+DROP TABLE IF EXISTS import_polygon_error;
+CREATE TABLE import_polygon_error (
+  osm_id BIGINT,
+  osm_type CHAR(1),
+  class TEXT NOT NULL,
+  type TEXT NOT NULL,
+  name HSTORE,
+  country_code varchar(2),
+  updated timestamp,
+  errormessage text,
+  prevgeometry GEOMETRY(Geometry, 4326),
+  newgeometry GEOMETRY(Geometry, 4326)
+  );
+
+CREATE INDEX idx_import_polygon_error_osmid ON import_polygon_error
+  USING BTREE (osm_type, osm_id);
+
+
+DROP TABLE IF EXISTS import_polygon_delete;
+CREATE TABLE import_polygon_delete (
+  osm_id BIGINT,
+  osm_type CHAR(1),
+  class TEXT NOT NULL,
+  type TEXT NOT NULL
+  );
+
+CREATE INDEX idx_import_polygon_delete_osmid ON import_polygon_delete
+  USING BTREE (osm_type, osm_id);

lib-sql/tables/importance_tables.sql

@@ -0,0 +1,16 @@
+-- SPDX-License-Identifier: GPL-2.0-only
+--
+-- This file is part of Nominatim. (https://nominatim.org)
+--
+-- Copyright (C) 2026 by the Nominatim developer community.
+-- For a full list of authors see the git log.
+
+{% 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 %}

lib-sql/tables/interpolation.sql

@@ -0,0 +1,34 @@
+-- SPDX-License-Identifier: GPL-2.0-only
+--
+-- This file is part of Nominatim. (https://nominatim.org)
+--
+-- Copyright (C) 2026 by the Nominatim developer community.
+-- For a full list of authors see the git log.
+
+DROP TABLE IF EXISTS location_property_osmline;
+CREATE TABLE location_property_osmline (
+    place_id BIGINT NOT NULL,
+    osm_id BIGINT NOT NULL,
+    parent_place_id BIGINT,
+    geometry_sector INTEGER NOT NULL,
+    indexed_date TIMESTAMP,
+    startnumber INTEGER,
+    endnumber INTEGER,
+    step SMALLINT,
+    partition SMALLINT NOT NULL,
+    indexed_status SMALLINT NOT NULL,
+    linegeo GEOMETRY NOT NULL,
+    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}};
+CREATE INDEX idx_osmline_linegeo ON location_property_osmline
+  USING GIST (linegeo) {{db.tablespace.search_index}}
+  WHERE startnumber is not null;
+

lib-sql/tables/location_area.sql

@@ -0,0 +1,32 @@
+-- SPDX-License-Identifier: GPL-2.0-only
+--
+-- This file is part of Nominatim. (https://nominatim.org)
+--
+-- Copyright (C) 2026 by the Nominatim developer community.
+-- For a full list of authors see the git log.
+
+DROP TABLE IF EXISTS location_area CASCADE;
+CREATE TABLE location_area (
+  place_id BIGINT NOT NULL,
+  keywords INTEGER[] NOT NULL,
+  partition SMALLINT NOT NULL,
+  rank_search SMALLINT NOT NULL,
+  rank_address SMALLINT NOT NULL,
+  country_code VARCHAR(2),
+  isguess BOOL NOT NULL,
+  postcode TEXT,
+  centroid GEOMETRY(Point, 4326) NOT NULL,
+  geometry GEOMETRY(Geometry, 4326) NOT NULL
+  );
+
+CREATE TABLE location_area_large () INHERITS (location_area);
+
+DROP TABLE IF EXISTS location_area_country;
+CREATE TABLE location_area_country (
+  place_id BIGINT NOT NULL,
+  country_code varchar(2) NOT NULL,
+  geometry GEOMETRY(Geometry, 4326) NOT NULL
+  ) {{db.tablespace.address_data}};
+
+CREATE INDEX idx_location_area_country_geometry ON location_area_country
+  USING GIST (geometry) {{db.tablespace.address_index}};

lib-sql/tables/nominatim_properties.sql

@@ -0,0 +1,12 @@
+-- SPDX-License-Identifier: GPL-2.0-only
+--
+-- This file is part of Nominatim. (https://nominatim.org)
+--
+-- Copyright (C) 2026 by the Nominatim developer community.
+-- For a full list of authors see the git log.
+
+DROP TABLE IF EXISTS nominatim_properties;
+CREATE TABLE nominatim_properties (
+    property TEXT NOT NULL,
+    value TEXT
+);

lib-sql/tables/placex.sql

@@ -0,0 +1,87 @@
+-- SPDX-License-Identifier: GPL-2.0-only
+--
+-- This file is part of Nominatim. (https://nominatim.org)
+--
+-- Copyright (C) 2026 by the Nominatim developer community.
+-- For a full list of authors see the git log.
+
+-- placex - main table for searchable places
+
+DROP TABLE IF EXISTS placex;
+CREATE TABLE placex (
+  place_id BIGINT NOT NULL,
+  parent_place_id BIGINT,
+  linked_place_id BIGINT,
+  importance FLOAT,
+  indexed_date TIMESTAMP,
+  geometry_sector INTEGER NOT NULL,
+  rank_address SMALLINT NOT NULL,
+  rank_search SMALLINT NOT NULL,
+  partition SMALLINT NOT NULL,
+  indexed_status SMALLINT NOT NULL,
+  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) NOT NULL
+  ) {{db.tablespace.search_data}};
+
+CREATE UNIQUE INDEX idx_place_id ON placex USING BTREE (place_id) {{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 SPGIST (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
+  USING SPGIST (geometry) {{db.tablespace.address_index}}
+  WHERE osm_type = 'N' and rank_search < 26 and class = 'place';
+
+-- Usage: - is node part of a way?
+--        - find parent of interpolation spatially
+CREATE INDEX idx_placex_geometry_lower_rank_ways ON placex
+  USING SPGIST (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;
+

lib-sql/tables/postcodes.sql

@@ -0,0 +1,30 @@
+-- SPDX-License-Identifier: GPL-2.0-only
+--
+-- This file is part of Nominatim. (https://nominatim.org)
+--
+-- Copyright (C) 2026 by the Nominatim developer community.
+-- For a full list of authors see the git log.
+
+DROP TABLE IF EXISTS location_postcodes;
+CREATE TABLE location_postcodes (
+  place_id BIGINT NOT NULL,
+  parent_place_id BIGINT,
+  osm_id BIGINT,
+  rank_search SMALLINT NOT NULL,
+  indexed_status SMALLINT NOT NULL,
+  indexed_date TIMESTAMP,
+  country_code varchar(2) NOT NULL,
+  postcode TEXT NOT NULL,
+  centroid GEOMETRY(Geometry, 4326) NOT NULL,
+  geometry GEOMETRY(Geometry, 4326) NOT NULL
+  );
+
+CREATE UNIQUE INDEX idx_location_postcodes_id ON location_postcodes
+  USING BTREE (place_id) {{db.tablespace.search_index}};
+CREATE INDEX idx_location_postcodes_geometry ON location_postcodes
+  USING GIST (geometry) {{db.tablespace.search_index}};
+CREATE INDEX IF NOT EXISTS idx_location_postcodes_postcode ON location_postcodes
+  USING BTREE (postcode, country_code) {{db.tablespace.search_index}};
+CREATE INDEX IF NOT EXISTS idx_location_postcodes_osmid ON location_postcodes
+  USING BTREE (osm_id) {{db.tablespace.search_index}};
+

lib-sql/tables/search_name.sql

@@ -0,0 +1,26 @@
+-- SPDX-License-Identifier: GPL-2.0-only
+--
+-- This file is part of Nominatim. (https://nominatim.org)
+--
+-- Copyright (C) 2026 by the Nominatim developer community.
+-- For a full list of authors see the git log.
+
+DROP TABLE IF EXISTS search_name;
+
+{% if not create_reverse_only %}
+
+CREATE TABLE search_name (
+  place_id BIGINT NOT NULL,
+  importance FLOAT NOT NULL,
+  search_rank SMALLINT NOT NULL,
+  address_rank SMALLINT NOT NULL,
+  name_vector integer[] NOT NULL,
+  nameaddress_vector integer[] NOT NULL,
+  country_code varchar(2),
+  centroid GEOMETRY(Geometry, 4326) NOT NULL
+  ) {{db.tablespace.search_data}};
+
+CREATE UNIQUE INDEX idx_search_name_place_id
+  ON search_name USING BTREE (place_id) {{db.tablespace.search_index}};
+
+{% endif %}

lib-sql/tables/status.sql

@@ -0,0 +1,23 @@
+-- SPDX-License-Identifier: GPL-2.0-only
+--
+-- This file is part of Nominatim. (https://nominatim.org)
+--
+-- Copyright (C) 2026 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_osmosis_log;
+CREATE TABLE import_osmosis_log (
+  batchend TIMESTAMP,
+  batchseq INTEGER,
+  batchsize BIGINT,
+  starttime TIMESTAMP,
+  endtime TIMESTAMP,
+  event TEXT
+  );

lib-sql/tables/tiger.sql

@@ -0,0 +1,17 @@
+-- SPDX-License-Identifier: GPL-2.0-only
+--
+-- This file is part of Nominatim. (https://nominatim.org)
+--
+-- Copyright (C) 2026 by the Nominatim developer community.
+-- For a full list of authors see the git log.
+
+DROP TABLE IF EXISTS location_property_tiger;
+CREATE TABLE location_property_tiger (
+  place_id BIGINT NOT NULL,
+  parent_place_id BIGINT,
+  startnumber INTEGER NOT NULL,
+  endnumber INTEGER NOT NULL,
+  step SMALLINT NOT NULL,
+  partition SMALLINT NOT NULL,
+  linegeo GEOMETRY NOT NULL,
+  postcode TEXT);

src/nominatim_db/config.py

@@ -2,7 +2,7 @@
 #
 # This file is part of Nominatim. (https://nominatim.org)
 #
-# Copyright (C) 2025 by the Nominatim developer community.
+# Copyright (C) 2026 by the Nominatim developer community.
 # For a full list of authors see the git log.
 """
 Nominatim configuration accessor.
@@ -12,6 +12,7 @@ import importlib.util
 import logging
 import os
 import sys
+import re
 from pathlib import Path
 import json
 import yaml
@@ -80,6 +81,10 @@ class Configuration:
         self.lib_dir = _LibDirs()
         self._private_plugins: Dict[str, object] = {}
 
+        if re.fullmatch(r'[\w-]+', self.DATABASE_WEBUSER) is None:
+            raise UsageError("Misconfigured DATABASE_WEBUSER. "
+                             "Only alphnumberic characters, - and _ are allowed.")
+
     def set_libdirs(self, **kwargs: StrPath) -> None:
         """ Set paths to library functions and data.
         """

src/nominatim_db/db/query_pool.py

@@ -38,6 +38,7 @@ class QueryPool:
         """ Schedule a query for execution.
         """
         if self.is_cancelled:
+            self.clear_queue()
             await self.finish()
             return
 
@@ -47,6 +48,7 @@ class QueryPool:
         await asyncio.sleep(0)
 
         if self.is_cancelled:
+            self.clear_queue()
             await self.finish()
 
     async def finish(self) -> None:

src/nominatim_db/db/sql_preprocessor.py

@@ -2,12 +2,13 @@
 #
 # This file is part of Nominatim. (https://nominatim.org)
 #
-# Copyright (C) 2024 by the Nominatim developer community.
+# Copyright (C) 2026 by the Nominatim developer community.
 # For a full list of authors see the git log.
 """
 Preprocessing of SQL files.
 """
 from typing import Set, Dict, Any, cast
+import re
 
 import jinja2
 
@@ -34,7 +35,9 @@ def _get_tables(conn: Connection) -> Set[str]:
     with conn.cursor() as cur:
         cur.execute("SELECT tablename FROM pg_tables WHERE schemaname = 'public'")
 
-        return set((row[0] for row in list(cur)))
+        # paranoia check: make sure we don't get table names that cause
+        # an SQL injection later
+        return {row[0] for row in list(cur) if re.fullmatch(r'\w+', row[0])}
 
 
 def _get_middle_db_format(conn: Connection, tables: Set[str]) -> str:

src/nominatim_db/indexer/indexer.py

@@ -56,10 +56,10 @@ class Indexer:
                         cur.execute('ANALYZE')
 
             while True:
-                if await self.index_by_rank(0, 4) > 0:
+                if await self.index_by_rank(1, 4) > 0:
                     _analyze()
 
-                if await self.index_boundaries(0, 30) > 100:
+                if await self.index_boundaries() > 100:
                     _analyze()
 
                 if await self.index_by_rank(5, 25) > 100:
@@ -68,13 +68,16 @@ class Indexer:
                 if await self.index_by_rank(26, 30) > 1000:
                     _analyze()
 
+                # Special case: rank zero depends on the previously-indexed [1..30] ranks
+                await self.index_by_rank(0, 0)
+
                 if await self.index_postcodes() > 100:
                     _analyze()
 
                 if not self.has_pending():
                     break
 
-    async def index_boundaries(self, minrank: int, maxrank: int) -> int:
+    async def index_boundaries(self, minrank: int = 0, maxrank: int = 30) -> int:
         """ Index only administrative boundaries within the given rank range.
         """
         total = 0
@@ -147,8 +150,11 @@ class Indexer:
                 total += await self._index(runners.RankRunner(rank, analyzer),
                                            batch=batch, total_tuples=total_tuples.get(rank, 0))
 
-            if maxrank == 30:
+            # Special case: rank zero depends on ranks [1..30]
+            if minrank == 0:
                 total += await self._index(runners.RankRunner(0, analyzer))
+
+            if maxrank == 30:
                 total += await self._index(runners.InterpolationRunner(analyzer), batch=20)
 
         return total

src/nominatim_db/tokenizer/icu_tokenizer.py

@@ -2,7 +2,7 @@
 #
 # This file is part of Nominatim. (https://nominatim.org)
 #
-# Copyright (C) 2025 by the Nominatim developer community.
+# Copyright (C) 2026 by the Nominatim developer community.
 # For a full list of authors see the git log.
 """
 Tokenizer implementing normalisation as used before Nominatim 4 but using
@@ -294,13 +294,12 @@ class ICUTokenizer(AbstractTokenizer):
         with connect(self.dsn) as conn:
             drop_tables(conn, 'word')
             with conn.cursor() as cur:
-                cur.execute(f"ALTER TABLE {old} RENAME TO word")
-                for idx in ('word_token', 'word_id'):
-                    cur.execute(f"""ALTER INDEX idx_{old}_{idx}
-                                      RENAME TO idx_word_{idx}""")
-                for name, _ in WORD_TYPES:
-                    cur.execute(f"""ALTER INDEX idx_{old}_{name}
-                                    RENAME TO idx_word_{name}""")
+                cur.execute(pysql.SQL("ALTER TABLE {} RENAME TO word")
+                                 .format(pysql.Identifier(old)))
+                for idx in ['word_token', 'word_id'] + [n[0] for n in WORD_TYPES]:
+                    cur.execute(pysql.SQL("ALTER INDEX {} RENAME TO {}")
+                                     .format(pysql.Identifier(f"idx_{old}_{idx}"),
+                                             pysql.Identifier(f"idx_word_{idx}")))
             conn.commit()
 
 

src/nominatim_db/tools/database_import.py

@@ -152,12 +152,11 @@ def create_tables(conn: Connection, config: Configuration, reverse_only: bool =
         When `reverse_only` is True, then the main table for searching will
         be skipped and only reverse search is possible.
     """
-    sql = SQLPreprocessor(conn, config)
-    sql.env.globals['db']['reverse_only'] = reverse_only
+    SQLPreprocessor(conn, config).run_sql_file(conn, 'tables.sql',
+                                               create_reverse_only=reverse_only)
 
-    sql.run_sql_file(conn, 'tables.sql')
-
-    sql.run_sql_file(conn, 'grants.sql')
+    # reinitiate the preprocessor to get all the newly created tables
+    SQLPreprocessor(conn, config).run_sql_file(conn, 'grants.sql')
 
 
 def create_table_triggers(conn: Connection, config: Configuration) -> None:
@@ -195,7 +194,7 @@ def truncate_data_tables(conn: Connection) -> None:
                        WHERE tablename LIKE 'location_road_%'""")
 
         for table in [r[0] for r in list(cur)]:
-            cur.execute('TRUNCATE ' + table)
+            cur.execute(pysql.SQL('TRUNCATE {}').format(pysql.Identifier(table)))
 
     conn.commit()
 

src/nominatim_db/tools/postcodes.py

@@ -159,7 +159,7 @@ class _PostcodeCollector:
 
         if fname.is_file():
             LOG.info("Using external postcode file '%s'.", fname)
-            return gzip.open(fname, 'rt')
+            return gzip.open(fname, 'rt', encoding='utf-8')
 
         return None
 

src/nominatim_db/tools/refresh.py

@@ -141,7 +141,9 @@ def import_importance_csv(dsn: str, data_file: Path) -> int:
 
             copy_cmd = """COPY wikimedia_importance(language, title, importance, wikidata)
                           FROM STDIN"""
-            with gzip.open(str(data_file), 'rt') as fd, cur.copy(copy_cmd) as copy:
+            with gzip.open(
+                    str(data_file), 'rt', encoding='utf-8') as fd, \
+                    cur.copy(copy_cmd) as copy:
                 for row in csv.DictReader(fd, delimiter='\t', quotechar='|'):
                     wd_id = int(row['wikidata_id'][1:])
                     copy.write_row((row['language'],

test/bdd/features/db/import/linking.feature

@@ -297,9 +297,8 @@ Feature: Linking of places
          | R1         | LabelPlace |
 
 
-    @skip
     Scenario: Linked places expand default language names
-        Given the grid
+        Given the grid with origin CO
             | 1 |   | 2 |
             |   | 9 |   |
             | 4 |   | 3 |

test/bdd/test_osm2pgsql.py

@@ -43,7 +43,7 @@ def opl_writer(tmp_path, node_grid):
     def _write(data):
         fname = tmp_path / f"test_osm_{nr[0]}.opl"
         nr[0] += 1
-        with fname.open('wt') as fd:
+        with fname.open('wt', encoding='utf-8') as fd:
             for line in data.split('\n'):
                 if line.startswith('n') and ' x' not in line:
                     coord = node_grid.get(line[1:].split(' ')[0]) \
@@ -59,7 +59,7 @@ def opl_writer(tmp_path, node_grid):
 @given('the lua style file', target_fixture='osm2pgsql_options')
 def set_lua_style_file(osm2pgsql_options, docstring, tmp_path):
     style = tmp_path / 'custom.lua'
-    style.write_text(docstring)
+    style.write_text(docstring, encoding='utf-8')
     osm2pgsql_options['osm2pgsql_style'] = str(style)
 
     return osm2pgsql_options

test/python/api/search/test_postcode_parser.py

@@ -58,7 +58,7 @@ gb:
     pattern: "(l?ld[A-Z0-9]?) ?(dll)"
     output: \1 \2
 
-    """)
+    """, encoding='utf-8')
 
     return project_env
 

test/python/cli/test_cli.py

@@ -91,8 +91,9 @@ class TestCliWithDb:
         postcode_mock = async_mock_func_factory(nominatim_db.indexer.indexer.Indexer,
                                                 'index_postcodes')
 
+        has_pending_retvals = [True, False]
         monkeypatch.setattr(nominatim_db.indexer.indexer.Indexer, 'has_pending',
-                            [False, True].pop)
+                            lambda *args, **kwargs: has_pending_retvals.pop(0))
 
         assert self.call_nominatim('index', *params) == 0
 

test/python/config/test_config.py

@@ -2,7 +2,7 @@
 #
 # This file is part of Nominatim. (https://nominatim.org)
 #
-# Copyright (C) 2025 by the Nominatim developer community.
+# Copyright (C) 2026 by the Nominatim developer community.
 # For a full list of authors see the git log.
 """
 Test for loading dotenv configuration.
@@ -48,7 +48,7 @@ def test_no_project_dir(make_config):
 @pytest.mark.parametrize("val", ('apache', '"apache"'))
 def test_prefer_project_setting_over_default(make_config, val, tmp_path):
     envfile = tmp_path / '.env'
-    envfile.write_text('NOMINATIM_DATABASE_WEBUSER={}\n'.format(val))
+    envfile.write_text('NOMINATIM_DATABASE_WEBUSER={}\n'.format(val), encoding='utf-8')
 
     config = make_config(tmp_path)
 
@@ -57,7 +57,7 @@ def test_prefer_project_setting_over_default(make_config, val, tmp_path):
 
 def test_prefer_os_environ_over_project_setting(make_config, monkeypatch, tmp_path):
     envfile = tmp_path / '.env'
-    envfile.write_text('NOMINATIM_DATABASE_WEBUSER=apache\n')
+    envfile.write_text('NOMINATIM_DATABASE_WEBUSER=apache\n', encoding='utf-8')
 
     monkeypatch.setenv('NOMINATIM_DATABASE_WEBUSER', 'nobody')
 
@@ -68,13 +68,13 @@ def test_prefer_os_environ_over_project_setting(make_config, monkeypatch, tmp_pa
 
 def test_prefer_os_environ_can_unset_project_setting(make_config, monkeypatch, tmp_path):
     envfile = tmp_path / '.env'
-    envfile.write_text('NOMINATIM_DATABASE_WEBUSER=apache\n')
+    envfile.write_text('NOMINATIM_OSM2PGSQL_BINARY=osm2pgsql\n', encoding='utf-8')
 
-    monkeypatch.setenv('NOMINATIM_DATABASE_WEBUSER', '')
+    monkeypatch.setenv('NOMINATIM_OSM2PGSQL_BINARY', '')
 
     config = make_config(tmp_path)
 
-    assert config.DATABASE_WEBUSER == ''
+    assert config.OSM2PGSQL_BINARY == ''
 
 
 def test_get_os_env_add_defaults(make_config, monkeypatch):
@@ -232,7 +232,7 @@ def test_get_import_style_intern(make_config, src_dir, monkeypatch):
 
 def test_get_import_style_extern_relative(make_config_path, monkeypatch):
     config = make_config_path()
-    (config.project_dir / 'custom.style').write_text('x')
+    (config.project_dir / 'custom.style').write_text('x', encoding='utf-8')
 
     monkeypatch.setenv('NOMINATIM_IMPORT_STYLE', 'custom.style')
 
@@ -243,7 +243,7 @@ def test_get_import_style_extern_absolute(make_config, tmp_path, monkeypatch):
     config = make_config()
     cfgfile = tmp_path / 'test.style'
 
-    cfgfile.write_text('x')
+    cfgfile.write_text('x', encoding='utf-8')
 
     monkeypatch.setenv('NOMINATIM_IMPORT_STYLE', str(cfgfile))
 
@@ -254,10 +254,10 @@ def test_load_subconf_from_project_dir(make_config_path):
     config = make_config_path()
 
     testfile = config.project_dir / 'test.yaml'
-    testfile.write_text('cow: muh\ncat: miau\n')
+    testfile.write_text('cow: muh\ncat: miau\n', encoding='utf-8')
 
     testfile = config.config_dir / 'test.yaml'
-    testfile.write_text('cow: miau\ncat: muh\n')
+    testfile.write_text('cow: miau\ncat: muh\n', encoding='utf-8')
 
     rules = config.load_sub_configuration('test.yaml')
 
@@ -268,7 +268,7 @@ def test_load_subconf_from_settings_dir(make_config_path):
     config = make_config_path()
 
     testfile = config.config_dir / 'test.yaml'
-    testfile.write_text('cow: muh\ncat: miau\n')
+    testfile.write_text('cow: muh\ncat: miau\n', encoding='utf-8')
 
     rules = config.load_sub_configuration('test.yaml')
 
@@ -280,7 +280,7 @@ def test_load_subconf_empty_env_conf(make_config_path, monkeypatch):
     config = make_config_path()
 
     testfile = config.config_dir / 'test.yaml'
-    testfile.write_text('cow: muh\ncat: miau\n')
+    testfile.write_text('cow: muh\ncat: miau\n', encoding='utf-8')
 
     rules = config.load_sub_configuration('test.yaml', config='MY_CONFIG')
 
@@ -291,8 +291,8 @@ def test_load_subconf_env_absolute_found(make_config_path, monkeypatch, tmp_path
     monkeypatch.setenv('NOMINATIM_MY_CONFIG', str(tmp_path / 'other.yaml'))
     config = make_config_path()
 
-    (config.config_dir / 'test.yaml').write_text('cow: muh\ncat: miau\n')
-    (tmp_path / 'other.yaml').write_text('dog: muh\nfrog: miau\n')
+    (config.config_dir / 'test.yaml').write_text('cow: muh\ncat: miau\n', encoding='utf-8')
+    (tmp_path / 'other.yaml').write_text('dog: muh\nfrog: miau\n', encoding='utf-8')
 
     rules = config.load_sub_configuration('test.yaml', config='MY_CONFIG')
 
@@ -303,7 +303,7 @@ def test_load_subconf_env_absolute_not_found(make_config_path, monkeypatch, tmp_
     monkeypatch.setenv('NOMINATIM_MY_CONFIG', str(tmp_path / 'other.yaml'))
     config = make_config_path()
 
-    (config.config_dir / 'test.yaml').write_text('cow: muh\ncat: miau\n')
+    (config.config_dir / 'test.yaml').write_text('cow: muh\ncat: miau\n', encoding='utf-8')
 
     with pytest.raises(UsageError, match='Config file not found.'):
         config.load_sub_configuration('test.yaml', config='MY_CONFIG')
@@ -314,8 +314,8 @@ def test_load_subconf_env_relative_found(make_config_path, monkeypatch, location
     monkeypatch.setenv('NOMINATIM_MY_CONFIG', 'other.yaml')
     config = make_config_path()
 
-    (config.config_dir / 'test.yaml').write_text('cow: muh\ncat: miau\n')
-    (getattr(config, location) / 'other.yaml').write_text('dog: bark\n')
+    (config.config_dir / 'test.yaml').write_text('cow: muh\ncat: miau\n', encoding='utf-8')
+    (getattr(config, location) / 'other.yaml').write_text('dog: bark\n', encoding='utf-8')
 
     rules = config.load_sub_configuration('test.yaml', config='MY_CONFIG')
 
@@ -326,7 +326,7 @@ def test_load_subconf_env_relative_not_found(make_config_path, monkeypatch):
     monkeypatch.setenv('NOMINATIM_MY_CONFIG', 'other.yaml')
     config = make_config_path()
 
-    (config.config_dir / 'test.yaml').write_text('cow: muh\ncat: miau\n')
+    (config.config_dir / 'test.yaml').write_text('cow: muh\ncat: miau\n', encoding='utf-8')
 
     with pytest.raises(UsageError, match='Config file not found.'):
         config.load_sub_configuration('test.yaml', config='MY_CONFIG')
@@ -335,7 +335,7 @@ def test_load_subconf_env_relative_not_found(make_config_path, monkeypatch):
 def test_load_subconf_json(make_config_path):
     config = make_config_path()
 
-    (config.project_dir / 'test.json').write_text('{"cow": "muh", "cat": "miau"}')
+    (config.project_dir / 'test.json').write_text('{"cow": "muh", "cat": "miau"}', encoding='utf-8')
 
     rules = config.load_sub_configuration('test.json')
 
@@ -352,7 +352,7 @@ def test_load_subconf_not_found(make_config_path):
 def test_load_subconf_env_unknown_format(make_config_path):
     config = make_config_path()
 
-    (config.project_dir / 'test.xml').write_text('<html></html>')
+    (config.project_dir / 'test.xml').write_text('<html></html>', encoding='utf-8')
 
     with pytest.raises(UsageError, match='unknown format'):
         config.load_sub_configuration('test.xml')
@@ -362,8 +362,8 @@ def test_load_subconf_include_absolute(make_config_path, tmp_path):
     config = make_config_path()
 
     testfile = config.config_dir / 'test.yaml'
-    testfile.write_text(f'base: !include {tmp_path}/inc.yaml\n')
-    (tmp_path / 'inc.yaml').write_text('first: 1\nsecond: 2\n')
+    testfile.write_text(f'base: !include {tmp_path}/inc.yaml\n', encoding='utf-8')
+    (tmp_path / 'inc.yaml').write_text('first: 1\nsecond: 2\n', encoding='utf-8')
 
     rules = config.load_sub_configuration('test.yaml')
 
@@ -375,8 +375,8 @@ def test_load_subconf_include_relative(make_config_path, tmp_path, location):
     config = make_config_path()
 
     testfile = config.config_dir / 'test.yaml'
-    testfile.write_text('base: !include inc.yaml\n')
-    (getattr(config, location) / 'inc.yaml').write_text('first: 1\nsecond: 2\n')
+    testfile.write_text('base: !include inc.yaml\n', encoding='utf-8')
+    (getattr(config, location) / 'inc.yaml').write_text('first: 1\nsecond: 2\n', encoding='utf-8')
 
     rules = config.load_sub_configuration('test.yaml')
 
@@ -387,8 +387,8 @@ def test_load_subconf_include_bad_format(make_config_path):
     config = make_config_path()
 
     testfile = config.config_dir / 'test.yaml'
-    testfile.write_text('base: !include inc.txt\n')
-    (config.config_dir / 'inc.txt').write_text('first: 1\nsecond: 2\n')
+    testfile.write_text('base: !include inc.txt\n', encoding='utf-8')
+    (config.config_dir / 'inc.txt').write_text('first: 1\nsecond: 2\n', encoding='utf-8')
 
     with pytest.raises(UsageError, match='Cannot handle config file format.'):
         config.load_sub_configuration('test.yaml')
@@ -398,7 +398,7 @@ def test_load_subconf_include_not_found(make_config_path):
     config = make_config_path()
 
     testfile = config.config_dir / 'test.yaml'
-    testfile.write_text('base: !include inc.txt\n')
+    testfile.write_text('base: !include inc.txt\n', encoding='utf-8')
 
     with pytest.raises(UsageError, match='Config file not found.'):
         config.load_sub_configuration('test.yaml')
@@ -408,9 +408,9 @@ def test_load_subconf_include_recursive(make_config_path):
     config = make_config_path()
 
     testfile = config.config_dir / 'test.yaml'
-    testfile.write_text('base: !include inc.yaml\n')
-    (config.config_dir / 'inc.yaml').write_text('- !include more.yaml\n- upper\n')
-    (config.config_dir / 'more.yaml').write_text('- the end\n')
+    testfile.write_text('base: !include inc.yaml\n', encoding='utf-8')
+    (config.config_dir / 'inc.yaml').write_text('- !include more.yaml\n- upper\n', encoding='utf-8')
+    (config.config_dir / 'more.yaml').write_text('- the end\n', encoding='utf-8')
 
     rules = config.load_sub_configuration('test.yaml')
 

test/python/config/test_config_load_module.py

@@ -41,7 +41,7 @@ def test_load_default_module_with_hyphen(test_config):
 def test_load_plugin_module(test_config, tmp_path):
     (tmp_path / 'project' / 'testpath').mkdir()
     (tmp_path / 'project' / 'testpath' / 'mymod.py')\
-        .write_text("def my_test_function():\n  return 'gjwitlsSG42TG%'")
+        .write_text("def my_test_function():\n  return 'gjwitlsSG42TG%'", encoding='utf-8')
 
     module = test_config.load_plugin_module('testpath/mymod.py', 'private.something')
 
@@ -49,7 +49,7 @@ def test_load_plugin_module(test_config, tmp_path):
 
     # also test reloading module
     (tmp_path / 'project' / 'testpath' / 'mymod.py')\
-        .write_text("def my_test_function():\n  return 'hjothjorhj'")
+        .write_text("def my_test_function():\n  return 'hjothjorhj'", encoding='utf-8')
 
     module = test_config.load_plugin_module('testpath/mymod.py', 'private.something')
 
@@ -61,9 +61,9 @@ def test_load_external_library_module(test_config, tmp_path, monkeypatch):
     pythonpath = tmp_path / 'priv-python'
     pythonpath.mkdir()
     (pythonpath / MODULE_NAME).mkdir()
-    (pythonpath / MODULE_NAME / '__init__.py').write_text('')
+    (pythonpath / MODULE_NAME / '__init__.py').write_text('', encoding='utf-8')
     (pythonpath / MODULE_NAME / 'tester.py')\
-        .write_text("def my_test_function():\n  return 'gjwitlsSG42TG%'")
+        .write_text("def my_test_function():\n  return 'gjwitlsSG42TG%'", encoding='utf-8')
 
     monkeypatch.syspath_prepend(pythonpath)
 
@@ -73,7 +73,7 @@ def test_load_external_library_module(test_config, tmp_path, monkeypatch):
 
     # also test reloading module
     (pythonpath / MODULE_NAME / 'tester.py')\
-        .write_text("def my_test_function():\n  return 'dfigjreigj'")
+        .write_text("def my_test_function():\n  return 'dfigjreigj'", encoding='utf-8')
 
     module = test_config.load_plugin_module(f'{MODULE_NAME}.tester', 'private.something')
 

test/python/conftest.py

@@ -2,7 +2,7 @@
 #
 # This file is part of Nominatim. (https://nominatim.org)
 #
-# Copyright (C) 2025 by the Nominatim developer community.
+# Copyright (C) 2026 by the Nominatim developer community.
 # For a full list of authors see the git log.
 import itertools
 import sys
@@ -17,12 +17,11 @@ SRC_DIR = (Path(__file__) / '..' / '..' / '..').resolve()
 sys.path.insert(0, str(SRC_DIR / 'src'))
 
 from nominatim_db.config import Configuration
-from nominatim_db.db import connection
+from nominatim_db.db import connection, properties
 from nominatim_db.db.sql_preprocessor import SQLPreprocessor
 import nominatim_db.tokenizer.factory
 
 import dummy_tokenizer
-import mocks
 from cursor import CursorForTesting
 
 
@@ -60,7 +59,7 @@ def temp_db(monkeypatch):
 
     with psycopg.connect(dbname='postgres', autocommit=True) as conn:
         with conn.cursor() as cur:
-            cur.execute('DROP DATABASE IF EXISTS {}'.format(name))
+            cur.execute(pysql.SQL('DROP DATABASE IF EXISTS') + pysql.Identifier(name))
 
 
 @pytest.fixture
@@ -104,7 +103,9 @@ def table_factory(temp_db_conn):
     """
     def mk_table(name, definition='id INT', content=None):
         with psycopg.ClientCursor(temp_db_conn) as cur:
-            cur.execute('CREATE TABLE {} ({})'.format(name, definition))
+            cur.execute(pysql.SQL("CREATE TABLE {} ({})")
+                             .format(pysql.Identifier(name),
+                                     pysql.SQL(definition)))
             if content:
                 sql = pysql.SQL("INSERT INTO {} VALUES ({})")\
                            .format(pysql.Identifier(name),
@@ -130,28 +131,49 @@ def project_env(tmp_path):
 
 
 @pytest.fixture
-def property_table(table_factory, temp_db_conn):
-    table_factory('nominatim_properties', 'property TEXT, value TEXT')
-
-    return mocks.MockPropertyTable(temp_db_conn)
+def country_table(table_factory):
+    table_factory('country_name', 'partition INT, country_code varchar(2), name hstore')
 
 
 @pytest.fixture
-def status_table(table_factory):
+def country_row(country_table, temp_db_cursor):
+    def _add(partition=None, country=None, names=None):
+        temp_db_cursor.insert_row('country_name', partition=partition,
+                                  country_code=country, name=names)
+
+    return _add
+
+
+@pytest.fixture
+def load_sql(temp_db_conn, country_row):
+    proc = SQLPreprocessor(temp_db_conn, Configuration(None))
+
+    def _run(filename, **kwargs):
+        proc.run_sql_file(temp_db_conn, filename, **kwargs)
+
+    return _run
+
+
+@pytest.fixture
+def property_table(load_sql, temp_db_conn):
+    load_sql('tables/nominatim_properties.sql')
+
+    class _PropTable:
+        def set(self, name, value):
+            properties.set_property(temp_db_conn, name, value)
+
+        def get(self, name):
+            return properties.get_property(temp_db_conn, name)
+
+    return _PropTable()
+
+
+@pytest.fixture
+def status_table(load_sql):
     """ Create an empty version of the status table and
         the status logging table.
     """
-    table_factory('import_status',
-                  """lastimportdate timestamp with time zone NOT NULL,
-                     sequence_id integer,
-                     indexed boolean""")
-    table_factory('import_osmosis_log',
-                  """batchend timestamp,
-                     batchseq integer,
-                     batchsize bigint,
-                     starttime timestamp,
-                     endtime timestamp,
-                     event text""")
+    load_sql('tables/status.sql')
 
 
 @pytest.fixture
@@ -176,12 +198,14 @@ def place_row(place_table, temp_db_cursor):
         prerequisite to the fixture.
     """
     idseq = itertools.count(1001)
+
     def _insert(osm_type='N', osm_id=None, cls='amenity', typ='cafe', names=None,
-                admin_level=None, address=None, extratags=None, geom=None):
-        temp_db_cursor.execute("INSERT INTO place VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s)",
-                               (osm_id or next(idseq), osm_type, cls, typ, names,
-                                admin_level, address, extratags,
-                                geom or 'SRID=4326;POINT(0 0)'))
+                admin_level=None, address=None, extratags=None, geom='POINT(0 0)'):
+        args = {'osm_type': osm_type, 'osm_id': osm_id or next(idseq),
+                'class': cls, 'type': typ, 'name': names, 'admin_level': admin_level,
+                'address': address, 'extratags': extratags,
+                'geometry': _with_srid(geom)}
+        temp_db_cursor.insert_row('place', **args)
 
     return _insert
 
@@ -201,50 +225,104 @@ def place_postcode_table(temp_db_with_extensions, table_factory):
 
 @pytest.fixture
 def place_postcode_row(place_postcode_table, temp_db_cursor):
-    """ A factory for rows in the place table. The table is created as a
+    """ A factory for rows in the place_postcode table. The table is created as a
         prerequisite to the fixture.
     """
     idseq = itertools.count(5001)
+
     def _insert(osm_type='N', osm_id=None, postcode=None, country=None,
-                centroid=None, geom=None):
-        temp_db_cursor.execute("INSERT INTO place_postcode VALUES (%s, %s, %s, %s, %s, %s)",
-                               (osm_type, osm_id or next(idseq),
-                                postcode, country,
-                                _with_srid(centroid, 'POINT(12.0 4.0)'),
-                                _with_srid(geom)))
+                centroid='POINT(12.0 4.0)', geom=None):
+        temp_db_cursor.insert_row('place_postcode',
+                                  osm_type=osm_type, osm_id=osm_id or next(idseq),
+                                  postcode=postcode, country_code=country,
+                                  centroid=_with_srid(centroid),
+                                  geometry=_with_srid(geom))
 
     return _insert
 
 
 @pytest.fixture
-def placex_table(temp_db_with_extensions, temp_db_conn):
-    """ Create an empty version of the place table.
+def placex_table(temp_db_with_extensions, temp_db_conn, load_sql, place_table):
+    """ Create an empty version of the placex table.
     """
-    return mocks.MockPlacexTable(temp_db_conn)
+    load_sql('tables/placex.sql')
+    temp_db_conn.execute("CREATE SEQUENCE IF NOT EXISTS seq_place START 1")
 
 
 @pytest.fixture
-def osmline_table(temp_db_with_extensions, table_factory):
-    table_factory('location_property_osmline',
-                  """place_id BIGINT,
-                     osm_id BIGINT,
-                     parent_place_id BIGINT,
-                     geometry_sector INTEGER,
-                     indexed_date TIMESTAMP,
-                     startnumber INTEGER,
-                     endnumber INTEGER,
-                     partition SMALLINT,
-                     indexed_status SMALLINT,
-                     linegeo GEOMETRY,
-                     interpolationtype TEXT,
-                     address HSTORE,
-                     postcode TEXT,
-                     country_code VARCHAR(2)""")
+def placex_row(placex_table, temp_db_cursor):
+    """ A factory for rows in the placex table. The table is created as a
+        prerequisite to the fixture.
+    """
+    idseq = itertools.count(1001)
+
+    def _add(osm_type='N', osm_id=None, cls='amenity', typ='cafe', names=None,
+             admin_level=None, address=None, extratags=None, geom='POINT(10 4)',
+             country=None, housenumber=None, rank_search=30, rank_address=30,
+             centroid='POINT(10 4)', indexed_status=0, indexed_date=None):
+        args = {'place_id': pysql.SQL("nextval('seq_place')"),
+                'osm_type': osm_type, 'osm_id': osm_id or next(idseq),
+                'class': cls, 'type': typ, 'name': names, 'admin_level': admin_level,
+                'address': address, 'housenumber': housenumber,
+                'rank_search': rank_search, 'rank_address': rank_address,
+                'extratags': extratags,
+                'centroid': _with_srid(centroid), 'geometry': _with_srid(geom),
+                'country_code': country,
+                'indexed_status': indexed_status, 'indexed_date': indexed_date,
+                'partition': pysql.Literal(0), 'geometry_sector': pysql.Literal(1)}
+        return temp_db_cursor.insert_row('placex', **args)
+
+    return _add
 
 
 @pytest.fixture
-def sql_preprocessor_cfg(tmp_path, table_factory, temp_db_with_extensions):
-    table_factory('country_name', 'partition INT', ((0, ), (1, ), (2, )))
+def osmline_table(temp_db_with_extensions, load_sql):
+    load_sql('tables/interpolation.sql')
+
+
+@pytest.fixture
+def osmline_row(osmline_table, temp_db_cursor):
+    idseq = itertools.count(20001)
+
+    def _add(osm_id=None, geom='LINESTRING(12.0 11.0, 12.003 11.0)'):
+        return temp_db_cursor.insert_row(
+            'location_property_osmline',
+            place_id=pysql.SQL("nextval('seq_place')"),
+            osm_id=osm_id or next(idseq),
+            geometry_sector=pysql.Literal(20),
+            partition=pysql.Literal(0),
+            indexed_status=1,
+            linegeo=_with_srid(geom))
+
+    return _add
+
+
+@pytest.fixture
+def postcode_table(temp_db_with_extensions, load_sql):
+    load_sql('tables/postcodes.sql')
+
+
+@pytest.fixture
+def postcode_row(postcode_table, temp_db_cursor):
+    def _add(country, postcode, x=34.5, y=-9.33):
+        geom = _with_srid(f"POINT({x} {y})")
+        return temp_db_cursor.insert_row(
+            'location_postcodes',
+            place_id=pysql.SQL("nextval('seq_place')"),
+            indexed_status=pysql.Literal(1),
+            country_code=country, postcode=postcode,
+            centroid=geom,
+            rank_search=pysql.Literal(16),
+            geometry=('ST_Expand(%s::geometry, 0.005)', geom))
+
+    return _add
+
+
+@pytest.fixture
+def sql_preprocessor_cfg(tmp_path, table_factory, temp_db_with_extensions, country_row):
+    for part in range(3):
+        country_row(partition=part)
+
     cfg = Configuration(None)
     cfg.set_libdirs(sql=tmp_path)
     return cfg

test/python/cursor.py

@@ -2,12 +2,13 @@
 #
 # This file is part of Nominatim. (https://nominatim.org)
 #
-# Copyright (C) 2025 by the Nominatim developer community.
+# Copyright (C) 2026 by the Nominatim developer community.
 # For a full list of authors see the git log.
 """
 Specialised psycopg cursor with shortcut functions useful for testing.
 """
 import psycopg
+from psycopg import sql as pysql
 
 
 class CursorForTesting(psycopg.Cursor):
@@ -52,7 +53,49 @@ class CursorForTesting(psycopg.Cursor):
     def table_rows(self, table, where=None):
         """ Return the number of rows in the given table.
         """
-        if where is None:
-            return self.scalar('SELECT count(*) FROM ' + table)
+        sql = pysql.SQL('SELECT count(*) FROM') + pysql.Identifier(table)
+        if where is not None:
+            sql += pysql.SQL('WHERE') + pysql.SQL(where)
 
-        return self.scalar('SELECT count(*) FROM {} WHERE {}'.format(table, where))
+        return self.scalar(sql)
+
+    def insert_row(self, table, **data):
+        """ Insert a row into the given table.
+
+            'data' is a dictionary of column names and associated values.
+            When the value is a pysql.Literal or pysql.SQL, then the expression
+            will be inserted as is instead of loading the value. When the
+            value is a tuple, then the first element will be added as an
+            SQL expression for the value and the second element is treated
+            as the actual value to insert. The SQL expression must contain
+            a %s placeholder in that case.
+
+            If data contains a 'place_id' column, then the value of the
+            place_id column after insert is returned. Otherwise the function
+            returns nothing.
+        """
+        columns = []
+        placeholders = []
+        values = []
+        for k, v in data.items():
+            columns.append(pysql.Identifier(k))
+            if isinstance(v, tuple):
+                placeholders.append(pysql.SQL(v[0]))
+                values.append(v[1])
+            elif isinstance(v, (pysql.Literal, pysql.SQL)):
+                placeholders.append(v)
+            else:
+                placeholders.append(pysql.Placeholder())
+                values.append(v)
+
+        sql = pysql.SQL("INSERT INTO {table} ({columns}) VALUES({values})")\
+                   .format(table=pysql.Identifier(table),
+                           columns=pysql.SQL(',').join(columns),
+                           values=pysql.SQL(',').join(placeholders))
+
+        if 'place_id' in data:
+            sql += pysql.SQL('RETURNING place_id')
+
+        self.execute(sql, values)
+
+        return self.fetchone()[0] if 'place_id' in data else None

test/python/data/test_country_info.py

@@ -22,7 +22,8 @@ def loaded_country(def_config):
 def env_with_country_config(project_env):
 
     def _mk_config(cfg):
-        (project_env.project_dir / 'country_settings.yaml').write_text(dedent(cfg))
+        (project_env.project_dir / 'country_settings.yaml').write_text(
+            dedent(cfg), encoding='utf-8')
 
         return project_env
 
@@ -52,11 +53,10 @@ def test_setup_country_tables(src_dir, temp_db_with_extensions, dsn, temp_db_cur
 
 @pytest.mark.parametrize("languages", (None, ['fr', 'en']))
 def test_create_country_names(temp_db_with_extensions, temp_db_conn, temp_db_cursor,
-                              table_factory, tokenizer_mock, languages, loaded_country):
-
-    table_factory('country_name', 'country_code varchar(2), name hstore',
-                  content=(('us', '"name"=>"us1","name:af"=>"us2"'),
-                           ('fr', '"name"=>"Fra", "name:en"=>"Fren"')))
+                              country_row, tokenizer_mock, languages, loaded_country):
+    temp_db_cursor.execute('TRUNCATE country_name')
+    country_row(country='us', names={"name": "us1", "name:af": "us2"})
+    country_row(country='fr', names={"name": "Fra", "name:en": "Fren"})
 
     assert temp_db_cursor.scalar("SELECT count(*) FROM country_name") == 2
 

test/python/db/test_sql_preprocessor.py

@@ -22,7 +22,7 @@ def sql_factory(tmp_path):
           BEGIN
             {}
           END;
-          $$ LANGUAGE plpgsql IMMUTABLE;""".format(sql_body))
+          $$ LANGUAGE plpgsql IMMUTABLE;""".format(sql_body), encoding='utf-8')
         return 'test.sql'
 
     return _mk_sql
@@ -63,7 +63,7 @@ def test_load_file_with_params(sql_preprocessor, sql_factory, temp_db_conn, temp
 async def test_load_parallel_file(dsn, sql_preprocessor, tmp_path, temp_db_cursor):
     (tmp_path / 'test.sql').write_text("""
         CREATE TABLE foo (a TEXT);
-        CREATE TABLE foo2(a TEXT);""" + "\n---\nCREATE TABLE bar (b INT);")
+        CREATE TABLE foo2(a TEXT);""" + "\n---\nCREATE TABLE bar (b INT);", encoding='utf-8')
 
     await sql_preprocessor.run_parallel_sql_file(dsn, 'test.sql', num_threads=4)
 

test/python/db/test_utils.py

@@ -15,7 +15,8 @@ from nominatim_db.errors import UsageError
 
 def test_execute_file_success(dsn, temp_db_cursor, tmp_path):
     tmpfile = tmp_path / 'test.sql'
-    tmpfile.write_text('CREATE TABLE test (id INT);\nINSERT INTO test VALUES(56);')
+    tmpfile.write_text(
+        'CREATE TABLE test (id INT);\nINSERT INTO test VALUES(56);', encoding='utf-8')
 
     db_utils.execute_file(dsn, tmpfile)
 
@@ -29,7 +30,7 @@ def test_execute_file_bad_file(dsn, tmp_path):
 
 def test_execute_file_bad_sql(dsn, tmp_path):
     tmpfile = tmp_path / 'test.sql'
-    tmpfile.write_text('CREATE STABLE test (id INT)')
+    tmpfile.write_text('CREATE STABLE test (id INT)', encoding='utf-8')
 
     with pytest.raises(UsageError):
         db_utils.execute_file(dsn, tmpfile)
@@ -37,14 +38,14 @@ def test_execute_file_bad_sql(dsn, tmp_path):
 
 def test_execute_file_bad_sql_ignore_errors(dsn, tmp_path):
     tmpfile = tmp_path / 'test.sql'
-    tmpfile.write_text('CREATE STABLE test (id INT)')
+    tmpfile.write_text('CREATE STABLE test (id INT)', encoding='utf-8')
 
     db_utils.execute_file(dsn, tmpfile, ignore_errors=True)
 
 
 def test_execute_file_with_pre_code(dsn, tmp_path, temp_db_cursor):
     tmpfile = tmp_path / 'test.sql'
-    tmpfile.write_text('INSERT INTO test VALUES(4)')
+    tmpfile.write_text('INSERT INTO test VALUES(4)', encoding='utf-8')
 
     db_utils.execute_file(dsn, tmpfile, pre_code='CREATE TABLE test (id INT)')
 
@@ -53,7 +54,7 @@ def test_execute_file_with_pre_code(dsn, tmp_path, temp_db_cursor):
 
 def test_execute_file_with_post_code(dsn, tmp_path, temp_db_cursor):
     tmpfile = tmp_path / 'test.sql'
-    tmpfile.write_text('CREATE TABLE test (id INT)')
+    tmpfile.write_text('CREATE TABLE test (id INT)', encoding='utf-8')
 
     db_utils.execute_file(dsn, tmpfile, post_code='INSERT INTO test VALUES(23)')
 

test/python/indexer/test_indexing.py

@@ -1,13 +1,12 @@
-# SPDX-License-Identifier: GPL-3.0-or-later
 #
 # This file is part of Nominatim. (https://nominatim.org)
 #
-# Copyright (C) 2025 by the Nominatim developer community.
+# Copyright (C) 2026 by the Nominatim developer community.
 # For a full list of authors see the git log.
 """
 Tests for running the indexing.
 """
-import itertools
+
 import pytest
 import pytest_asyncio  # noqa
 
@@ -15,129 +14,57 @@ from nominatim_db.indexer import indexer
 from nominatim_db.tokenizer import factory
 
 
-class IndexerTestDB:
+class TestIndexing:
+    @pytest.fixture(autouse=True)
+    def setup(self, temp_db_conn, project_env, tokenizer_mock,
+              placex_table, postcode_table, osmline_table):
+        self.conn = temp_db_conn
+        temp_db_conn.execute("""
+            CREATE OR REPLACE FUNCTION date_update() RETURNS TRIGGER AS $$
+            BEGIN
+              IF NEW.indexed_status = 0 and OLD.indexed_status != 0 THEN
+                NEW.indexed_date = now();
+              END IF;
+              RETURN NEW;
+            END; $$ LANGUAGE plpgsql;
 
-    def __init__(self, conn):
-        self.placex_id = itertools.count(100000)
-        self.osmline_id = itertools.count(500000)
-        self.postcode_id = itertools.count(700000)
+            DROP TYPE IF EXISTS prepare_update_info CASCADE;
+            CREATE TYPE prepare_update_info AS (
+                         name HSTORE,
+                         address HSTORE,
+                         rank_address SMALLINT,
+                         country_code TEXT,
+                         class TEXT,
+                         type TEXT,
+                         linked_place_id BIGINT
+                       );
+            CREATE OR REPLACE FUNCTION placex_indexing_prepare(p placex,
+                                                 OUT result prepare_update_info) AS $$
+            BEGIN
+              result.address := p.address;
+              result.name := p.name;
+              result.class := p.class;
+              result.type := p.type;
+              result.country_code := p.country_code;
+              result.rank_address := p.rank_address;
+            END; $$ LANGUAGE plpgsql STABLE;
 
-        self.conn = conn
-        self.conn.autocimmit = True
-        with self.conn.cursor() as cur:
-            cur.execute("""CREATE TABLE placex (place_id BIGINT,
-                                                name HSTORE,
-                                                class TEXT,
-                                                type TEXT,
-                                                linked_place_id BIGINT,
-                                                rank_address SMALLINT,
-                                                rank_search SMALLINT,
-                                                indexed_status SMALLINT,
-                                                indexed_date TIMESTAMP,
-                                                partition SMALLINT,
-                                                admin_level SMALLINT,
-                                                country_code TEXT,
-                                                address HSTORE,
-                                                token_info JSONB,
-                                                geometry_sector INTEGER)""")
-            cur.execute("""CREATE TABLE location_property_osmline (
-                               place_id BIGINT,
-                               osm_id BIGINT,
-                               address HSTORE,
-                               token_info JSONB,
-                               indexed_status SMALLINT,
-                               indexed_date TIMESTAMP,
-                               geometry_sector INTEGER)""")
-            cur.execute("""CREATE TABLE location_postcodes (
-                               place_id BIGINT,
-                               indexed_status SMALLINT,
-                               indexed_date TIMESTAMP,
-                               country_code varchar(2),
-                               postcode TEXT)""")
-            cur.execute("""CREATE OR REPLACE FUNCTION date_update() RETURNS TRIGGER
-                           AS $$
-                           BEGIN
-                             IF NEW.indexed_status = 0 and OLD.indexed_status != 0 THEN
-                               NEW.indexed_date = now();
-                             END IF;
-                             RETURN NEW;
-                           END; $$ LANGUAGE plpgsql;""")
-            cur.execute("DROP TYPE IF EXISTS prepare_update_info CASCADE")
-            cur.execute("""CREATE TYPE prepare_update_info AS (
-                             name HSTORE,
-                             address HSTORE,
-                             rank_address SMALLINT,
-                             country_code TEXT,
-                             class TEXT,
-                             type TEXT,
-                             linked_place_id BIGINT
-                           )""")
-            cur.execute("""CREATE OR REPLACE FUNCTION placex_indexing_prepare(p placex,
-                                                     OUT result prepare_update_info)
-                           AS $$
-                           BEGIN
-                             result.address := p.address;
-                             result.name := p.name;
-                             result.class := p.class;
-                             result.type := p.type;
-                             result.country_code := p.country_code;
-                             result.rank_address := p.rank_address;
-                           END;
-                           $$ LANGUAGE plpgsql STABLE;
-                        """)
-            cur.execute("""CREATE OR REPLACE FUNCTION
-                             get_interpolation_address(in_address HSTORE, wayid BIGINT)
-                           RETURNS HSTORE AS $$
-                           BEGIN
-                             RETURN in_address;
-                           END;
-                           $$ LANGUAGE plpgsql STABLE;
-                        """)
+            CREATE OR REPLACE FUNCTION get_interpolation_address(in_address HSTORE, wayid BIGINT)
+            RETURNS HSTORE AS $$ SELECT in_address $$ LANGUAGE sql STABLE;
+        """)
 
-            for table in ('placex', 'location_property_osmline', 'location_postcodes'):
-                cur.execute("""CREATE TRIGGER {0}_update BEFORE UPDATE ON {0}
-                               FOR EACH ROW EXECUTE PROCEDURE date_update()
-                            """.format(table))
+        for table in ('placex', 'location_property_osmline', 'location_postcodes'):
+            temp_db_conn.execute("""CREATE TRIGGER {0}_update BEFORE UPDATE ON {0}
+                                    FOR EACH ROW EXECUTE PROCEDURE date_update()
+                                 """.format(table))
+
+        self.tokenizer = factory.create_tokenizer(project_env)
 
     def scalar(self, query):
         with self.conn.cursor() as cur:
             cur.execute(query)
             return cur.fetchone()[0]
 
-    def add_place(self, cls='place', typ='locality',
-                  rank_search=30, rank_address=30, sector=20):
-        next_id = next(self.placex_id)
-        with self.conn.cursor() as cur:
-            cur.execute("""INSERT INTO placex
-                              (place_id, class, type, rank_search, rank_address,
-                               indexed_status, geometry_sector)
-                              VALUES (%s, %s, %s, %s, %s, 1, %s)""",
-                        (next_id, cls, typ, rank_search, rank_address, sector))
-        return next_id
-
-    def add_admin(self, **kwargs):
-        kwargs['cls'] = 'boundary'
-        kwargs['typ'] = 'administrative'
-        return self.add_place(**kwargs)
-
-    def add_osmline(self, sector=20):
-        next_id = next(self.osmline_id)
-        with self.conn.cursor() as cur:
-            cur.execute("""INSERT INTO location_property_osmline
-                              (place_id, osm_id, indexed_status, geometry_sector)
-                              VALUES (%s, %s, 1, %s)""",
-                        (next_id, next_id, sector))
-        return next_id
-
-    def add_postcode(self, country, postcode):
-        next_id = next(self.postcode_id)
-        with self.conn.cursor() as cur:
-            cur.execute("""INSERT INTO location_postcodes
-                            (place_id, indexed_status, country_code, postcode)
-                            VALUES (%s, 1, %s, %s)""",
-                        (next_id, country, postcode))
-        return next_id
-
     def placex_unindexed(self):
         return self.scalar('SELECT count(*) from placex where indexed_status > 0')
 
@@ -145,148 +72,133 @@ class IndexerTestDB:
         return self.scalar("""SELECT count(*) from location_property_osmline
                               WHERE indexed_status > 0""")
 
+    @pytest.mark.parametrize("threads", [1, 15])
+    @pytest.mark.asyncio
+    async def test_index_all_by_rank(self, dsn, threads, placex_row, osmline_row):
+        for rank in range(31):
+            placex_row(rank_address=rank, rank_search=rank, indexed_status=1)
+        osmline_row()
 
-@pytest.fixture
-def test_db(temp_db_conn):
-    yield IndexerTestDB(temp_db_conn)
+        assert self.placex_unindexed() == 31
+        assert self.osmline_unindexed() == 1
 
+        idx = indexer.Indexer(dsn, self.tokenizer, threads)
+        await idx.index_by_rank(0, 30)
 
-@pytest.fixture
-def test_tokenizer(tokenizer_mock, project_env):
-    return factory.create_tokenizer(project_env)
+        assert self.placex_unindexed() == 0
+        assert self.osmline_unindexed() == 0
 
+        assert self.scalar("""SELECT count(*) from placex
+                                 WHERE indexed_status = 0 and indexed_date is null""") == 0
+        # ranks come in order of rank address
+        assert self.scalar("""
+            SELECT count(*) FROM placex p WHERE rank_address > 0
+              AND indexed_date >= (SELECT min(indexed_date) FROM placex o
+                                   WHERE p.rank_address < o.rank_address)""") == 0
+        # placex address ranked objects come before interpolations
+        assert self.scalar(
+            """SELECT count(*) FROM placex WHERE rank_address > 0
+                 AND indexed_date >
+                       (SELECT min(indexed_date) FROM location_property_osmline)""") == 0
+        # rank 0 comes after all other placex objects
+        assert self.scalar(
+            """SELECT count(*) FROM placex WHERE rank_address > 0
+                 AND indexed_date >
+                       (SELECT min(indexed_date) FROM placex WHERE rank_address = 0)""") == 0
 
-@pytest.mark.parametrize("threads", [1, 15])
-@pytest.mark.asyncio
-async def test_index_all_by_rank(test_db, threads, test_tokenizer):
-    for rank in range(31):
-        test_db.add_place(rank_address=rank, rank_search=rank)
-    test_db.add_osmline()
+    @pytest.mark.parametrize("threads", [1, 15])
+    @pytest.mark.asyncio
+    async def test_index_partial_without_30(self, dsn, threads, placex_row, osmline_row):
+        for rank in range(31):
+            placex_row(rank_address=rank, rank_search=rank, indexed_status=1)
+        osmline_row()
 
-    assert test_db.placex_unindexed() == 31
-    assert test_db.osmline_unindexed() == 1
+        assert self.placex_unindexed() == 31
+        assert self.osmline_unindexed() == 1
 
-    idx = indexer.Indexer('dbname=test_nominatim_python_unittest', test_tokenizer, threads)
-    await idx.index_by_rank(0, 30)
+        idx = indexer.Indexer(dsn, self.tokenizer, threads)
+        await idx.index_by_rank(4, 15)
 
-    assert test_db.placex_unindexed() == 0
-    assert test_db.osmline_unindexed() == 0
+        assert self.placex_unindexed() == 19
+        assert self.osmline_unindexed() == 1
 
-    assert test_db.scalar("""SELECT count(*) from placex
-                             WHERE indexed_status = 0 and indexed_date is null""") == 0
-    # ranks come in order of rank address
-    assert test_db.scalar("""
-        SELECT count(*) FROM placex p WHERE rank_address > 0
-          AND indexed_date >= (SELECT min(indexed_date) FROM placex o
-                               WHERE p.rank_address < o.rank_address)""") == 0
-    # placex address ranked objects come before interpolations
-    assert test_db.scalar(
-        """SELECT count(*) FROM placex WHERE rank_address > 0
-             AND indexed_date >
-                   (SELECT min(indexed_date) FROM location_property_osmline)""") == 0
-    # rank 0 comes after all other placex objects
-    assert test_db.scalar(
-        """SELECT count(*) FROM placex WHERE rank_address > 0
-             AND indexed_date >
-                   (SELECT min(indexed_date) FROM placex WHERE rank_address = 0)""") == 0
+        assert self.scalar("""
+                        SELECT count(*) FROM placex
+                          WHERE indexed_status = 0 AND not rank_address between 4 and 15""") == 0
 
+    @pytest.mark.parametrize("threads", [1, 15])
+    @pytest.mark.asyncio
+    async def test_index_partial_with_30(self, dsn, threads, placex_row, osmline_row):
+        for rank in range(31):
+            placex_row(rank_address=rank, rank_search=rank, indexed_status=1)
+        osmline_row()
 
-@pytest.mark.parametrize("threads", [1, 15])
-@pytest.mark.asyncio
-async def test_index_partial_without_30(test_db, threads, test_tokenizer):
-    for rank in range(31):
-        test_db.add_place(rank_address=rank, rank_search=rank)
-    test_db.add_osmline()
+        assert self.placex_unindexed() == 31
+        assert self.osmline_unindexed() == 1
 
-    assert test_db.placex_unindexed() == 31
-    assert test_db.osmline_unindexed() == 1
+        idx = indexer.Indexer(dsn, self.tokenizer, threads)
+        await idx.index_by_rank(28, 30)
 
-    idx = indexer.Indexer('dbname=test_nominatim_python_unittest',
-                          test_tokenizer, threads)
-    await idx.index_by_rank(4, 15)
+        assert self.placex_unindexed() == 28
+        assert self.osmline_unindexed() == 0
 
-    assert test_db.placex_unindexed() == 19
-    assert test_db.osmline_unindexed() == 1
+        assert self.scalar("""
+                        SELECT count(*) FROM placex
+                          WHERE indexed_status = 0 AND rank_address between 0 and 27""") == 0
 
-    assert test_db.scalar("""
-                    SELECT count(*) FROM placex
-                      WHERE indexed_status = 0 AND not rank_address between 4 and 15""") == 0
+    @pytest.mark.parametrize("threads", [1, 15])
+    @pytest.mark.asyncio
+    async def test_index_boundaries(self, dsn, threads, placex_row, osmline_row):
+        for rank in range(4, 10):
+            placex_row(cls='boundary', typ='administrative',
+                       rank_address=rank, rank_search=rank, indexed_status=1)
+        for rank in range(31):
+            placex_row(rank_address=rank, rank_search=rank, indexed_status=1)
+        osmline_row()
 
+        assert self.placex_unindexed() == 37
+        assert self.osmline_unindexed() == 1
 
-@pytest.mark.parametrize("threads", [1, 15])
-@pytest.mark.asyncio
-async def test_index_partial_with_30(test_db, threads, test_tokenizer):
-    for rank in range(31):
-        test_db.add_place(rank_address=rank, rank_search=rank)
-    test_db.add_osmline()
+        idx = indexer.Indexer(dsn, self.tokenizer, threads)
+        await idx.index_boundaries()
 
-    assert test_db.placex_unindexed() == 31
-    assert test_db.osmline_unindexed() == 1
+        assert self.placex_unindexed() == 31
+        assert self.osmline_unindexed() == 1
 
-    idx = indexer.Indexer('dbname=test_nominatim_python_unittest', test_tokenizer, threads)
-    await idx.index_by_rank(28, 30)
+        assert self.scalar("""
+                        SELECT count(*) FROM placex
+                          WHERE indexed_status = 0 AND class != 'boundary'""") == 0
 
-    assert test_db.placex_unindexed() == 27
-    assert test_db.osmline_unindexed() == 0
+    @pytest.mark.parametrize("threads", [1, 15])
+    @pytest.mark.asyncio
+    async def test_index_postcodes(self, dsn, threads, postcode_row):
+        for postcode in range(1000):
+            postcode_row(country='de', postcode=postcode)
+        for postcode in range(32000, 33000):
+            postcode_row(country='us', postcode=postcode)
 
-    assert test_db.scalar("""
-                    SELECT count(*) FROM placex
-                      WHERE indexed_status = 0 AND rank_address between 1 and 27""") == 0
+        idx = indexer.Indexer(dsn, self.tokenizer, threads)
+        await idx.index_postcodes()
 
+        assert self.scalar("""SELECT count(*) FROM location_postcodes
+                                      WHERE indexed_status != 0""") == 0
 
-@pytest.mark.parametrize("threads", [1, 15])
-@pytest.mark.asyncio
-async def test_index_boundaries(test_db, threads, test_tokenizer):
-    for rank in range(4, 10):
-        test_db.add_admin(rank_address=rank, rank_search=rank)
-    for rank in range(31):
-        test_db.add_place(rank_address=rank, rank_search=rank)
-    test_db.add_osmline()
+    @pytest.mark.parametrize("analyse", [True, False])
+    @pytest.mark.asyncio
+    async def test_index_full(self, dsn, analyse, placex_row, osmline_row, postcode_row):
+        for rank in range(4, 10):
+            placex_row(cls='boundary', typ='administrative',
+                       rank_address=rank, rank_search=rank, indexed_status=1)
+        for rank in range(31):
+            placex_row(rank_address=rank, rank_search=rank, indexed_status=1)
+        osmline_row()
+        for postcode in range(1000):
+            postcode_row(country='de', postcode=postcode)
 
-    assert test_db.placex_unindexed() == 37
-    assert test_db.osmline_unindexed() == 1
+        idx = indexer.Indexer(dsn, self.tokenizer, 4)
+        await idx.index_full(analyse=analyse)
 
-    idx = indexer.Indexer('dbname=test_nominatim_python_unittest', test_tokenizer, threads)
-    await idx.index_boundaries(0, 30)
-
-    assert test_db.placex_unindexed() == 31
-    assert test_db.osmline_unindexed() == 1
-
-    assert test_db.scalar("""
-                    SELECT count(*) FROM placex
-                      WHERE indexed_status = 0 AND class != 'boundary'""") == 0
-
-
-@pytest.mark.parametrize("threads", [1, 15])
-@pytest.mark.asyncio
-async def test_index_postcodes(test_db, threads, test_tokenizer):
-    for postcode in range(1000):
-        test_db.add_postcode('de', postcode)
-    for postcode in range(32000, 33000):
-        test_db.add_postcode('us', postcode)
-
-    idx = indexer.Indexer('dbname=test_nominatim_python_unittest', test_tokenizer, threads)
-    await idx.index_postcodes()
-
-    assert test_db.scalar("""SELECT count(*) FROM location_postcodes
-                                  WHERE indexed_status != 0""") == 0
-
-
-@pytest.mark.parametrize("analyse", [True, False])
-@pytest.mark.asyncio
-async def test_index_full(test_db, analyse, test_tokenizer):
-    for rank in range(4, 10):
-        test_db.add_admin(rank_address=rank, rank_search=rank)
-    for rank in range(31):
-        test_db.add_place(rank_address=rank, rank_search=rank)
-    test_db.add_osmline()
-    for postcode in range(1000):
-        test_db.add_postcode('de', postcode)
-
-    idx = indexer.Indexer('dbname=test_nominatim_python_unittest', test_tokenizer, 4)
-    await idx.index_full(analyse=analyse)
-
-    assert test_db.placex_unindexed() == 0
-    assert test_db.osmline_unindexed() == 0
-    assert test_db.scalar("""SELECT count(*) FROM location_postcodes
-                             WHERE indexed_status != 0""") == 0
+        assert self.placex_unindexed() == 0
+        assert self.osmline_unindexed() == 0
+        assert self.scalar("""SELECT count(*) FROM location_postcodes
+                                 WHERE indexed_status != 0""") == 0

test/python/mocks.py

@@ -1,85 +0,0 @@
-# SPDX-License-Identifier: GPL-3.0-or-later
-#
-# This file is part of Nominatim. (https://nominatim.org)
-#
-# Copyright (C) 2025 by the Nominatim developer community.
-# For a full list of authors see the git log.
-"""
-Custom mocks for testing.
-"""
-import itertools
-
-from nominatim_db.db import properties
-
-
-class MockPlacexTable:
-    """ A placex table for testing.
-    """
-    def __init__(self, conn):
-        self.idseq = itertools.count(10000)
-        self.conn = conn
-        with conn.cursor() as cur:
-            cur.execute("""CREATE TABLE placex (
-                               place_id BIGINT,
-                               parent_place_id BIGINT,
-                               linked_place_id BIGINT,
-                               importance FLOAT,
-                               indexed_date TIMESTAMP,
-                               geometry_sector INTEGER,
-                               rank_address SMALLINT,
-                               rank_search SMALLINT,
-                               partition SMALLINT,
-                               indexed_status SMALLINT,
-                               osm_id int8,
-                               osm_type char(1),
-                               class text,
-                               type text,
-                               name hstore,
-                               admin_level smallint,
-                               address hstore,
-                               extratags hstore,
-                               token_info jsonb,
-                               geometry Geometry(Geometry,4326),
-                               wikipedia TEXT,
-                               country_code varchar(2),
-                               housenumber TEXT,
-                               postcode TEXT,
-                               centroid GEOMETRY(Geometry, 4326))""")
-            cur.execute("CREATE SEQUENCE IF NOT EXISTS seq_place")
-        conn.commit()
-
-    def add(self, osm_type='N', osm_id=None, cls='amenity', typ='cafe', names=None,
-            admin_level=None, address=None, extratags=None, geom='POINT(10 4)',
-            country=None, housenumber=None, rank_search=30, centroid=None):
-        with self.conn.cursor() as cur:
-            cur.execute("""INSERT INTO placex (place_id, osm_type, osm_id, class,
-                                               type, name, admin_level, address,
-                                               housenumber, rank_search,
-                                               extratags, centroid, geometry, country_code)
-                            VALUES(nextval('seq_place'), %s, %s, %s, %s, %s, %s,
-                                   %s, %s, %s, %s, %s, %s, %s)
-                            RETURNING place_id""",
-                        (osm_type, osm_id or next(self.idseq), cls, typ, names,
-                         admin_level, address, housenumber, rank_search,
-                         extratags, centroid, 'SRID=4326;' + geom,
-                         country))
-            place_id = cur.fetchone()[0]
-        self.conn.commit()
-        return place_id
-
-
-class MockPropertyTable:
-    """ A property table for testing.
-    """
-    def __init__(self, conn):
-        self.conn = conn
-
-    def set(self, name, value):
-        """ Set a property in the table to the given value.
-        """
-        properties.set_property(self.conn, name, value)
-
-    def get(self, name):
-        """ Set a property in the table to the given value.
-        """
-        return properties.get_property(self.conn, name)

test/python/tokenizer/test_icu.py

@@ -2,7 +2,7 @@
 #
 # This file is part of Nominatim. (https://nominatim.org)
 #
-# Copyright (C) 2025 by the Nominatim developer community.
+# Copyright (C) 2026 by the Nominatim developer community.
 # For a full list of authors see the git log.
 """
 Tests for ICU tokenizer.
@@ -15,7 +15,6 @@ import pytest
 from nominatim_db.tokenizer import icu_tokenizer
 import nominatim_db.tokenizer.icu_rule_loader
 from nominatim_db.db import properties
-from nominatim_db.db.sql_preprocessor import SQLPreprocessor
 from nominatim_db.data.place_info import PlaceInfo
 
 from mock_icu_word_table import MockIcuWordTable
@@ -31,7 +30,7 @@ def test_config(project_env, tmp_path):
     sqldir = tmp_path / 'sql'
     sqldir.mkdir()
     (sqldir / 'tokenizer').mkdir()
-    (sqldir / 'tokenizer' / 'icu_tokenizer.sql').write_text("SELECT 'a'")
+    (sqldir / 'tokenizer' / 'icu_tokenizer.sql').write_text("SELECT 'a'", encoding='utf-8')
 
     project_env.lib_dir.sql = sqldir
 
@@ -58,7 +57,7 @@ def db_prop(temp_db_conn):
 def analyzer(tokenizer_factory, test_config, monkeypatch,
              temp_db_with_extensions, tmp_path):
     sql = tmp_path / 'sql' / 'tokenizer' / 'icu_tokenizer.sql'
-    sql.write_text("SELECT 'a';")
+    sql.write_text("SELECT 'a';", encoding='utf-8')
 
     monkeypatch.setenv('NOMINATIM_TERM_NORMALIZATION', ':: lower();')
     tok = tokenizer_factory()
@@ -80,7 +79,8 @@ def analyzer(tokenizer_factory, test_config, monkeypatch,
         if with_postcode:
             cfgstr['token-analysis'].append({'id': '@postcode',
                                              'analyzer': 'postcodes'})
-        (test_config.project_dir / 'icu_tokenizer.yaml').write_text(yaml.dump(cfgstr))
+        (test_config.project_dir / 'icu_tokenizer.yaml').write_text(
+            yaml.dump(cfgstr), encoding='utf-8')
         tok.loader = nominatim_db.tokenizer.icu_rule_loader.ICURuleLoader(test_config)
 
         return tok.name_analyzer()
@@ -89,13 +89,9 @@ def analyzer(tokenizer_factory, test_config, monkeypatch,
 
 
 @pytest.fixture
-def sql_functions(temp_db_conn, def_config, src_dir):
-    orig_sql = def_config.lib_dir.sql
-    def_config.lib_dir.sql = src_dir / 'lib-sql'
-    sqlproc = SQLPreprocessor(temp_db_conn, def_config)
-    sqlproc.run_sql_file(temp_db_conn, 'functions/utils.sql')
-    sqlproc.run_sql_file(temp_db_conn, 'tokenizer/icu_tokenizer.sql')
-    def_config.lib_dir.sql = orig_sql
+def sql_functions(load_sql):
+    load_sql('functions/utils.sql')
+    load_sql('tokenizer/icu_tokenizer.sql')
 
 
 @pytest.fixture
@@ -190,7 +186,7 @@ def test_update_sql_functions(db_prop, temp_db_cursor,
     table_factory('test', 'txt TEXT')
 
     func_file = test_config.lib_dir.sql / 'tokenizer' / 'icu_tokenizer.sql'
-    func_file.write_text("""INSERT INTO test VALUES (1133)""")
+    func_file.write_text("""INSERT INTO test VALUES (1133)""", encoding='utf-8')
 
     tok.update_sql_functions(test_config)
 
@@ -652,22 +648,21 @@ class TestUpdateWordTokens:
         self.tok.update_word_tokens()
         assert word_table.count_housenumbers() == 1
 
-    def test_keep_housenumbers_from_placex_table(self, add_housenumber, word_table,
-                                                 placex_table):
+    def test_keep_housenumbers_from_placex_table(self, add_housenumber, word_table, placex_row):
         add_housenumber(9999, '5432a')
         add_housenumber(9990, '34z')
-        placex_table.add(housenumber='34z')
-        placex_table.add(housenumber='25432a')
+        placex_row(housenumber='34z')
+        placex_row(housenumber='25432a')
 
         assert word_table.count_housenumbers() == 2
         self.tok.update_word_tokens()
         assert word_table.count_housenumbers() == 1
 
     def test_keep_housenumbers_from_placex_table_hnr_list(self, add_housenumber,
-                                                          word_table, placex_table):
+                                                          word_table, placex_row):
         add_housenumber(9991, '9 b')
         add_housenumber(9990, '34z')
-        placex_table.add(housenumber='9 a;9 b;9 c')
+        placex_row(housenumber='9 a;9 b;9 c')
 
         assert word_table.count_housenumbers() == 2
         self.tok.update_word_tokens()

test/python/tokenizer/test_icu_rule_loader.py

@@ -27,7 +27,8 @@ class TestIcuRuleLoader:
         self.project_env = project_env
 
     def write_config(self, content):
-        (self.project_env.project_dir / 'icu_tokenizer.yaml').write_text(dedent(content))
+        (self.project_env.project_dir / 'icu_tokenizer.yaml').write_text(
+            dedent(content), encoding='utf-8')
 
     def config_rules(self, *variants):
         content = dedent("""\
@@ -119,7 +120,7 @@ class TestIcuRuleLoader:
                   variants:
             """)
         transpath = self.project_env.project_dir / ('transliteration.yaml')
-        transpath.write_text('- "x > y"')
+        transpath.write_text('- "x > y"', encoding='utf-8')
 
         loader = ICURuleLoader(self.project_env)
         rules = loader.get_transliteration_rules()

test/python/tools/conftest.py

@@ -21,7 +21,7 @@ if [ "$*" = "--version" ]; then
 else
   echo "$@"
 fi
-    """)
+    """, encoding='utf-8')
     osm2pgsql_exec.chmod(0o777)
 
     return dict(osm2pgsql=str(osm2pgsql_exec),

test/python/tools/test_admin.py

@@ -2,17 +2,17 @@
 #
 # This file is part of Nominatim. (https://nominatim.org)
 #
-# Copyright (C) 2025 by the Nominatim developer community.
+# Copyright (C) 2026 by the Nominatim developer community.
 # For a full list of authors see the git log.
 """
 Tests for maintenance and analysis functions.
 """
 import pytest
+import datetime as dt
 
 from nominatim_db.errors import UsageError
 from nominatim_db.tools import admin
 from nominatim_db.tokenizer import factory
-from nominatim_db.db.sql_preprocessor import SQLPreprocessor
 
 
 @pytest.fixture(autouse=True)
@@ -61,15 +61,14 @@ def test_analyse_indexing_unknown_osmid(project_env):
         admin.analyse_indexing(project_env, osm_id='W12345674')
 
 
-def test_analyse_indexing_with_place_id(project_env, temp_db_cursor):
-    temp_db_cursor.execute("INSERT INTO placex (place_id) VALUES(12345)")
+def test_analyse_indexing_with_place_id(project_env, placex_row):
+    place_id = placex_row()
 
-    admin.analyse_indexing(project_env, place_id=12345)
+    admin.analyse_indexing(project_env, place_id=place_id)
 
 
-def test_analyse_indexing_with_osm_id(project_env, temp_db_cursor):
-    temp_db_cursor.execute("""INSERT INTO placex (place_id, osm_type, osm_id)
-                              VALUES(9988, 'N', 10000)""")
+def test_analyse_indexing_with_osm_id(project_env, placex_row):
+    placex_row(osm_type='N', osm_id=10000)
 
     admin.analyse_indexing(project_env, osm_id='N10000')
 
@@ -77,8 +76,8 @@ def test_analyse_indexing_with_osm_id(project_env, temp_db_cursor):
 class TestAdminCleanDeleted:
 
     @pytest.fixture(autouse=True)
-    def setup_polygon_delete(self, project_env, table_factory, place_table,
-                             osmline_table, temp_db_cursor, temp_db_conn, def_config, src_dir):
+    def setup_polygon_delete(self, project_env, table_factory, place_table, placex_row,
+                             osmline_table, temp_db_cursor, load_sql):
         """ Set up place_force_delete function and related tables
         """
         self.project_env = project_env
@@ -91,12 +90,15 @@ class TestAdminCleanDeleted:
                       ((100, 'N', 'boundary', 'administrative'),
                        (145, 'N', 'boundary', 'administrative'),
                        (175, 'R', 'landcover', 'grass')))
-        temp_db_cursor.execute("""
-            INSERT INTO placex (place_id, osm_id, osm_type, class, type,
-                                indexed_date, indexed_status)
-            VALUES(1, 100, 'N', 'boundary', 'administrative', current_date - INTERVAL '1 month', 1),
-                  (2, 145, 'N', 'boundary', 'administrative', current_date - INTERVAL '3 month', 1),
-                  (3, 175, 'R', 'landcover', 'grass', current_date - INTERVAL '3 months', 1)""")
+
+        now = dt.datetime.now()
+        placex_row(osm_type='N', osm_id=100, cls='boundary', typ='administrative',
+                   indexed_status=1, indexed_date=now - dt.timedelta(days=30))
+        placex_row(osm_type='N', osm_id=145, cls='boundary', typ='administrative',
+                   indexed_status=1, indexed_date=now - dt.timedelta(days=90))
+        placex_row(osm_type='R', osm_id=175, cls='landcover', typ='grass',
+                   indexed_status=1, indexed_date=now - dt.timedelta(days=90))
+
         # set up tables and triggers for utils function
         table_factory('place_to_be_deleted',
                       """osm_id BIGINT,
@@ -104,7 +106,6 @@ class TestAdminCleanDeleted:
                       class TEXT NOT NULL,
                       type TEXT NOT NULL,
                       deferred BOOLEAN""")
-        table_factory('country_name', 'partition INT')
         table_factory('import_polygon_error', """osm_id BIGINT,
                       osm_type CHAR(1),
                       class TEXT NOT NULL,
@@ -115,11 +116,7 @@ class TestAdminCleanDeleted:
                                $$ LANGUAGE plpgsql;""")
         temp_db_cursor.execute("""CREATE TRIGGER place_before_delete BEFORE DELETE ON place
                                FOR EACH ROW EXECUTE PROCEDURE place_delete();""")
-        orig_sql = def_config.lib_dir.sql
-        def_config.lib_dir.sql = src_dir / 'lib-sql'
-        sqlproc = SQLPreprocessor(temp_db_conn, def_config)
-        sqlproc.run_sql_file(temp_db_conn, 'functions/utils.sql')
-        def_config.lib_dir.sql = orig_sql
+        load_sql('functions/utils.sql')
 
     def test_admin_clean_deleted_no_records(self):
         admin.clean_deleted_relations(self.project_env, age='1 year')

test/python/tools/test_database_import.py

@@ -2,7 +2,7 @@
 #
 # This file is part of Nominatim. (https://nominatim.org)
 #
-# Copyright (C) 2025 by the Nominatim developer community.
+# Copyright (C) 2026 by the Nominatim developer community.
 # For a full list of authors see the git log.
 """
 Tests for functions to import a new database.
@@ -25,12 +25,14 @@ class TestDatabaseSetup:
     def setup_nonexistant_db(self):
         with psycopg.connect(dbname='postgres', autocommit=True) as conn:
             with conn.cursor() as cur:
-                cur.execute(f'DROP DATABASE IF EXISTS {self.DBNAME}')
+                cur.execute(pysql.SQL('DROP DATABASE IF EXISTS ')
+                            + pysql.Identifier(self.DBNAME))
 
             yield True
 
             with conn.cursor() as cur:
-                cur.execute(f'DROP DATABASE IF EXISTS {self.DBNAME}')
+                cur.execute(pysql.SQL('DROP DATABASE IF EXISTS ')
+                            + pysql.Identifier(self.DBNAME))
 
     @pytest.fixture
     def cursor(self):
@@ -62,7 +64,7 @@ class TestDatabaseSetup:
     def test_create_db_missing_ro_user(self):
         with pytest.raises(UsageError, match='Missing read-only user.'):
             database_import.setup_database_skeleton(f'dbname={self.DBNAME}',
-                                                    rouser='sdfwkjkjgdugu2;jgsafkljas;')
+                                                    rouser='sdfwkjkjgdugu2jgsafkljas')
 
     def test_setup_extensions_old_postgis(self, monkeypatch):
         monkeypatch.setattr(database_import, 'POSTGIS_REQUIRED_VERSION', (50, 50))
@@ -96,7 +98,7 @@ def test_import_osm_data_multifile(table_factory, tmp_path, osm2pgsql_options, c
 
     files = [tmp_path / 'file1.osm', tmp_path / 'file2.osm']
     for f in files:
-        f.write_text('test')
+        f.write_text('test', encoding='utf-8')
 
     database_import.import_osm_data(files, osm2pgsql_options)
     captured = capfd.readouterr()
@@ -124,7 +126,7 @@ def test_import_osm_data_drop(table_factory, temp_db_cursor, tmp_path, osm2pgsql
     table_factory('planet_osm_nodes')
 
     flatfile = tmp_path / 'flatfile'
-    flatfile.write_text('touch')
+    flatfile.write_text('touch', encoding='utf-8')
 
     osm2pgsql_options['flatnode_file'] = str(flatfile.resolve())
 
@@ -168,14 +170,41 @@ def test_truncate_database_tables(temp_db_conn, temp_db_cursor, table_factory, w
 @pytest.mark.asyncio
 async def test_load_data(dsn, place_row, placex_table, osmline_table,
                          temp_db_cursor, threads):
-    for func in ('precompute_words', 'getorcreate_housenumber_id', 'make_standard_name'):
-        temp_db_cursor.execute(pysql.SQL("""CREATE FUNCTION {} (src TEXT)
-                                            RETURNS TEXT AS $$ SELECT 'a'::TEXT $$ LANGUAGE SQL
-                                         """).format(pysql.Identifier(func)))
     for oid in range(100, 130):
         place_row(osm_id=oid)
     place_row(osm_type='W', osm_id=342, cls='place', typ='houses',
-              geom='SRID=4326;LINESTRING(0 0, 10 10)')
+              geom='LINESTRING(0 0, 10 10)')
+
+    temp_db_cursor.execute("""
+        CREATE OR REPLACE FUNCTION placex_insert() RETURNS TRIGGER AS $$
+        BEGIN
+          NEW.place_id := nextval('seq_place');
+          NEW.indexed_status := 1;
+          NEW.centroid := ST_Centroid(NEW.geometry);
+          NEW.partition := 0;
+          NEW.geometry_sector := 2424;
+          NEW.rank_address := 30;
+          NEW.rank_search := 30;
+        RETURN NEW;
+        END; $$ LANGUAGE plpgsql STABLE PARALLEL SAFE;
+
+        CREATE OR REPLACE FUNCTION osmline_insert() RETURNS TRIGGER AS $$
+        BEGIN
+          NEW.place_id := nextval('seq_place');
+          IF NEW.indexed_status IS NULL THEN
+            NEW.indexed_status := 1;
+            NEW.partition := 0;
+            NEW.geometry_sector := 2424;
+          END IF;
+        RETURN NEW;
+        END; $$ LANGUAGE plpgsql STABLE PARALLEL SAFE;
+
+        CREATE TRIGGER placex_before_insert BEFORE INSERT ON placex
+        FOR EACH ROW EXECUTE PROCEDURE placex_insert();
+
+        CREATE TRIGGER osmline_before_insert BEFORE INSERT ON location_property_osmline
+        FOR EACH ROW EXECUTE PROCEDURE osmline_insert();
+    """)
 
     await database_import.load_data(dsn, threads)
 
@@ -193,7 +222,7 @@ class TestSetupSQL:
         self.config = def_config
 
     def write_sql(self, fname, content):
-        (self.config.lib_dir.sql / fname).write_text(content)
+        (self.config.lib_dir.sql / fname).write_text(content, encoding='utf-8')
 
     @pytest.mark.parametrize("reverse", [True, False])
     def test_create_tables(self, temp_db_conn, temp_db_cursor, reverse):

test/python/tools/test_freeze.py

@@ -54,7 +54,7 @@ def test_drop_flatnode_file_file_already_gone(tmp_path):
 
 def test_drop_flatnode_file_delete(tmp_path):
     flatfile = tmp_path / 'flatnode.store'
-    flatfile.write_text('Some content')
+    flatfile.write_text('Some content', encoding="utf-8")
 
     freeze.drop_flatnode_file(flatfile)
 

test/python/tools/test_import_special_phrases.py

@@ -2,7 +2,7 @@
 #
 # This file is part of Nominatim. (https://nominatim.org)
 #
-# Copyright (C) 2025 by the Nominatim developer community.
+# Copyright (C) 2026 by the Nominatim developer community.
 # For a full list of authors see the git log.
 """
     Tests for import special phrases methods
@@ -30,7 +30,7 @@ def xml_wiki_content(src_dir):
         return the content of the static xml test file.
     """
     xml_test_content = src_dir / 'test' / 'testdata' / 'special_phrases_test_content.txt'
-    return xml_test_content.read_text()
+    return xml_test_content.read_text(encoding='utf-8')
 
 
 @pytest.fixture
@@ -125,9 +125,8 @@ def test_grant_access_to_web_user(temp_db_conn, temp_db_cursor, table_factory,
                               phrase_class, phrase_type)
 
 
-def test_create_place_classtype_table_and_indexes(
-        temp_db_cursor, def_config, placex_table,
-        sp_importer, temp_db_conn, monkeypatch):
+def test_create_place_classtype_table_and_indexes(temp_db_cursor, def_config, placex_row,
+                                                  sp_importer, temp_db_conn, monkeypatch):
     """
         Test that _create_place_classtype_table_and_indexes()
         create the right place_classtype tables and place_id indexes
@@ -136,7 +135,7 @@ def test_create_place_classtype_table_and_indexes(
     """
     pairs = set([('class1', 'type1'), ('class2', 'type2')])
     for pair in pairs:
-        placex_table.add(cls=pair[0], typ=pair[1])   # adding to db
+        placex_row(cls=pair[0], typ=pair[1])   # adding to db
     sp_importer._create_classtype_table_and_indexes(pairs)
     temp_db_conn.commit()
 
@@ -178,7 +177,7 @@ def test_remove_non_existent_tables_from_db(sp_importer, default_phrases,
 
 @pytest.mark.parametrize("should_replace", [(True), (False)])
 def test_import_phrases(monkeypatch, temp_db_cursor, def_config, sp_importer,
-                        placex_table, table_factory, tokenizer_mock,
+                        placex_row, table_factory, tokenizer_mock,
                         xml_wiki_content, should_replace):
     """
         Check that the main import_phrases() method is well executed.
@@ -199,8 +198,8 @@ def test_import_phrases(monkeypatch, temp_db_cursor, def_config, sp_importer,
     type_test = 'zip_line'
 
     tokenizer = tokenizer_mock()
-    placex_table.add(cls=class_test, typ=type_test)  # in db for special phrase filtering
-    placex_table.add(cls='amenity', typ='animal_shelter')  # in db for special phrase filtering
+    placex_row(cls=class_test, typ=type_test)  # in db for special phrase filtering
+    placex_row(cls='amenity', typ='animal_shelter')  # in db for special phrase filtering
     sp_importer.import_phrases(tokenizer, should_replace)
 
     assert len(tokenizer.analyser_cache['special_phrases']) == 19
@@ -257,7 +256,7 @@ def check_placeid_and_centroid_indexes(temp_db_cursor, phrase_class, phrase_type
 
 @pytest.mark.parametrize("should_replace", [(True), (False)])
 def test_import_phrases_special_phrase_filtering(monkeypatch, temp_db_cursor, def_config,
-                                                 sp_importer, placex_table, tokenizer_mock,
+                                                 sp_importer, placex_row, tokenizer_mock,
                                                  xml_wiki_content, should_replace):
 
     monkeypatch.setattr('nominatim_db.tools.special_phrases.sp_wiki_loader._get_wiki_content',
@@ -266,7 +265,7 @@ def test_import_phrases_special_phrase_filtering(monkeypatch, temp_db_cursor, de
     class_test = 'aerialway'
     type_test = 'zip_line'
 
-    placex_table.add(cls=class_test, typ=type_test)  # add to the database to make valid
+    placex_row(cls=class_test, typ=type_test)  # add to the database to make valid
     tokenizer = tokenizer_mock()
     sp_importer.import_phrases(tokenizer, should_replace)
 
@@ -276,11 +275,11 @@ def test_import_phrases_special_phrase_filtering(monkeypatch, temp_db_cursor, de
     assert check_grant_access(temp_db_cursor, def_config.DATABASE_WEBUSER, class_test, type_test)
 
 
-def test_get_classtype_pairs_directly(placex_table, temp_db_conn, sp_importer):
+def test_get_classtype_pairs_directly(placex_row, temp_db_conn, sp_importer):
     for _ in range(101):
-        placex_table.add(cls='highway', typ='residential')
+        placex_row(cls='highway', typ='residential')
     for _ in range(99):
-        placex_table.add(cls='amenity', typ='toilet')
+        placex_row(cls='amenity', typ='toilet')
 
     temp_db_conn.commit()
 

test/python/tools/test_postcodes.py

@@ -2,7 +2,7 @@
 #
 # This file is part of Nominatim. (https://nominatim.org)
 #
-# Copyright (C) 2025 by the Nominatim developer community.
+# Copyright (C) 2026 by the Nominatim developer community.
 # For a full list of authors see the git log.
 """
 Tests for functions to maintain the artificial postcode table.
@@ -75,20 +75,18 @@ class MockPostcodeTable:
 @pytest.fixture
 def postcode_table(def_config, temp_db_conn, placex_table, table_factory):
     country_info.setup_country_config(def_config)
-    table_factory('country_name', 'partition INT', ((0, ), (1, ), (2, )))
     return MockPostcodeTable(temp_db_conn, def_config)
 
 
 @pytest.fixture
-def insert_implicit_postcode(placex_table, place_postcode_row):
+def insert_implicit_postcode(placex_row, place_postcode_row):
     """ Insert data into the placex and place table
         which can then be used to compute one postcode.
     """
     def _insert_implicit_postcode(osm_id, country, geometry, postcode, in_placex=False):
         if in_placex:
-            placex_table.add(osm_id=osm_id, country=country, geom=geometry,
-                             centroid=f'SRID=4326;{geometry}',
-                             address={'postcode': postcode})
+            placex_row(osm_id=osm_id, country=country, geom=geometry,
+                       centroid=geometry, address={'postcode': postcode})
         else:
             place_postcode_row(osm_id=osm_id, centroid=geometry,
                                country=country, postcode=postcode)
@@ -245,7 +243,7 @@ def test_postcodes_extern(postcode_update, postcode_table, tmp_path,
     insert_implicit_postcode(1, 'xx', 'POINT(10 12)', 'AB 4511')
 
     extfile = tmp_path / 'xx_postcodes.csv'
-    extfile.write_text("postcode,lat,lon\nAB 4511,-4,-1\nCD 4511,-5, -10")
+    extfile.write_text("postcode,lat,lon\nAB 4511,-4,-1\nCD 4511,-5, -10", encoding='utf-8')
 
     if gzipped:
         subprocess.run(['gzip', str(extfile)])
@@ -262,7 +260,7 @@ def test_postcodes_extern_bad_column(postcode_update, postcode_table, tmp_path,
     insert_implicit_postcode(1, 'xx', 'POINT(10 12)', 'AB 4511')
 
     extfile = tmp_path / 'xx_postcodes.csv'
-    extfile.write_text("postode,lat,lon\nAB 4511,-4,-1\nCD 4511,-5, -10")
+    extfile.write_text("postode,lat,lon\nAB 4511,-4,-1\nCD 4511,-5, -10", encoding='utf-8')
 
     postcode_update(tmp_path)
 
@@ -274,7 +272,8 @@ def test_postcodes_extern_bad_number(postcode_update, insert_implicit_postcode,
     insert_implicit_postcode(1, 'xx', 'POINT(10 12)', 'AB 4511')
 
     extfile = tmp_path / 'xx_postcodes.csv'
-    extfile.write_text("postcode,lat,lon\nXX 4511,-4,NaN\nCD 4511,-5, -10\n34,200,0")
+    extfile.write_text(
+        "postcode,lat,lon\nXX 4511,-4,NaN\nCD 4511,-5, -10\n34,200,0", encoding='utf-8')
 
     postcode_update(tmp_path)
 

test/python/tools/test_refresh.py

@@ -42,8 +42,8 @@ def test_refresh_import_wikipedia(dsn, src_dir, table_factory, temp_db_cursor, r
 
 
 @pytest.mark.parametrize('osm_type', ('N', 'W', 'R'))
-def test_invalidate_osm_object_simple(placex_table, osm_type, temp_db_conn, temp_db_cursor):
-    placex_table.add(osm_type=osm_type, osm_id=57283)
+def test_invalidate_osm_object_simple(placex_row, osm_type, temp_db_conn, temp_db_cursor):
+    placex_row(osm_type=osm_type, osm_id=57283)
 
     refresh.invalidate_osm_object(osm_type, 57283, temp_db_conn, recursive=False)
     temp_db_conn.commit()
@@ -53,8 +53,8 @@ def test_invalidate_osm_object_simple(placex_table, osm_type, temp_db_conn, temp
                                       (osm_type, 57283))
 
 
-def test_invalidate_osm_object_nonexisting_simple(placex_table, temp_db_conn, temp_db_cursor):
-    placex_table.add(osm_type='W', osm_id=57283)
+def test_invalidate_osm_object_nonexisting_simple(placex_row, temp_db_conn, temp_db_cursor):
+    placex_row(osm_type='W', osm_id=57283)
 
     refresh.invalidate_osm_object('N', 57283, temp_db_conn, recursive=False)
     temp_db_conn.commit()
@@ -64,8 +64,8 @@ def test_invalidate_osm_object_nonexisting_simple(placex_table, temp_db_conn, te
 
 
 @pytest.mark.parametrize('osm_type', ('N', 'W', 'R'))
-def test_invalidate_osm_object_recursive(placex_table, osm_type, temp_db_conn, temp_db_cursor):
-    placex_table.add(osm_type=osm_type, osm_id=57283)
+def test_invalidate_osm_object_recursive(placex_row, osm_type, temp_db_conn, temp_db_cursor):
+    placex_row(osm_type=osm_type, osm_id=57283)
 
     temp_db_cursor.execute("""CREATE OR REPLACE FUNCTION place_force_update(placeid BIGINT)
                               RETURNS BOOLEAN AS $$

test/python/tools/test_refresh_address_levels.py

@@ -22,7 +22,7 @@ def test_load_ranks_def_config(temp_db_conn, temp_db_cursor, def_config):
 
 def test_load_ranks_from_project_dir(project_env, temp_db_conn, temp_db_cursor):
     test_file = project_env.project_dir / 'address-levels.json'
-    test_file.write_text('[{"tags":{"place":{"sea":2}}}]')
+    test_file.write_text('[{"tags":{"place":{"sea":2}}}]', encoding='utf-8')
 
     load_address_levels_from_config(temp_db_conn, project_env)
 
@@ -31,7 +31,7 @@ def test_load_ranks_from_project_dir(project_env, temp_db_conn, temp_db_cursor):
 
 def test_load_ranks_from_broken_file(project_env, temp_db_conn):
     test_file = project_env.project_dir / 'address-levels.json'
-    test_file.write_text('[{"tags":"place":{"sea":2}}}]')
+    test_file.write_text('[{"tags":"place":{"sea":2}}}]', encoding='utf-8')
 
     with pytest.raises(json.decoder.JSONDecodeError):
         load_address_levels_from_config(temp_db_conn, project_env)

test/python/tools/test_refresh_create_functions.py

@@ -21,7 +21,7 @@ class TestCreateFunctions:
 
     def write_functions(self, content):
         sqlfile = self.config.lib_dir.sql / 'functions.sql'
-        sqlfile.write_text(content)
+        sqlfile.write_text(content, encoding='utf-8')
 
     def test_create_functions(self, temp_db_cursor):
         self.write_functions("""CREATE OR REPLACE FUNCTION test() RETURNS INTEGER

test/python/tools/test_refresh_wiki_data.py

@@ -2,7 +2,7 @@
 #
 # This file is part of Nominatim. (https://nominatim.org)
 #
-# Copyright (C) 2025 by the Nominatim developer community.
+# Copyright (C) 2026 by the Nominatim developer community.
 # For a full list of authors see the git log.
 """
 Tests for correctly assigning wikipedia pages to places.
@@ -20,7 +20,7 @@ from nominatim_db.tools.refresh import (import_wikipedia_articles,
 @pytest.fixture
 def wiki_csv(tmp_path, sql_preprocessor):
     def _import(data):
-        with gzip.open(tmp_path / 'wikimedia-importance.csv.gz', mode='wt') as fd:
+        with gzip.open(tmp_path / 'wikimedia-importance.csv.gz', mode='wt', encoding='utf-8') as fd:
             writer = csv.DictWriter(fd, fieldnames=['language', 'type', 'title',
                                                     'importance', 'wikidata_id'],
                                     delimiter='\t', quotechar='|')
@@ -38,7 +38,7 @@ def wiki_csv(tmp_path, sql_preprocessor):
                                    {'wikipedia': 'en:Test'},
                                    {'wikidata': 'Q123'}])
 def test_wikipedia(dsn, temp_db_conn, temp_db_cursor, table_factory,
-                   def_config, wiki_csv, placex_table, extra):
+                   def_config, wiki_csv, placex_row, extra):
     import_wikipedia_articles(dsn, wiki_csv([('en', 'Test', 0.3, 'Q123')]))
     create_functions(temp_db_conn, def_config)
 
@@ -46,7 +46,7 @@ def test_wikipedia(dsn, temp_db_conn, temp_db_cursor, table_factory,
         'SELECT language, title, importance, wikidata FROM wikimedia_importance')
     assert content == set([('en', 'Test', 0.3, 'Q123')])
 
-    place_id = placex_table.add(osm_id=12, extratags=extra)
+    place_id = placex_row(osm_id=12, extratags=extra)
     table_factory('search_name',
                   'place_id BIGINT, importance FLOAT',
                   [(place_id, 0.2)])
@@ -61,11 +61,11 @@ def test_wikipedia(dsn, temp_db_conn, temp_db_cursor, table_factory,
 
 
 def test_wikipedia_no_match(dsn, temp_db_conn, temp_db_cursor, def_config, wiki_csv,
-                            placex_table, table_factory):
+                            placex_row, table_factory):
     import_wikipedia_articles(dsn, wiki_csv([('de', 'Test', 0.3, 'Q123')]))
     create_functions(temp_db_conn, def_config)
 
-    place_id = placex_table.add(osm_id=12, extratags={'wikipedia': 'en:Test'}, rank_search=10)
+    place_id = placex_row(osm_id=12, extratags={'wikipedia': 'en:Test'}, rank_search=10)
     table_factory('search_name',
                   'place_id BIGINT, importance FLOAT',
                   [(place_id, 0.2)])

test/python/tools/test_sp_importer.py

@@ -1,69 +1,70 @@
+# SPDX-License-Identifier: GPL-3.0-or-later
+#
+# This file is part of Nominatim. (https://nominatim.org)
+#
+# Copyright (C) 2026 by the Nominatim developer community.
+# For a full list of authors see the git log.
+
 from nominatim_db.tools.special_phrases.sp_importer import SPImporter
 
 
 # Testing Database Class Pair Retrival using Conftest.py and placex
-def test_get_classtype_pair_data(placex_table, def_config, temp_db_conn):
+def test_get_classtype_pair_data(placex_row, def_config, temp_db_conn):
     for _ in range(100):
-        placex_table.add(cls='highway', typ='motorway')  # edge case 100
+        placex_row(cls='highway', typ='motorway')  # edge case 100
 
     for _ in range(99):
-        placex_table.add(cls='amenity', typ='prison')  # edge case 99
+        placex_row(cls='amenity', typ='prison')  # edge case 99
 
     for _ in range(150):
-        placex_table.add(cls='tourism', typ='hotel')
+        placex_row(cls='tourism', typ='hotel')
 
     importer = SPImporter(config=def_config, conn=temp_db_conn, sp_loader=None)
 
     result = importer.get_classtype_pairs(min=100)
 
-    expected = {
+    assert result == {
         ("highway", "motorway"),
         ("tourism", "hotel")
     }
 
-    assert result == expected, f"Expected {expected}, got {result}"
 
-
-def test_get_classtype_pair_data_more(placex_table, def_config, temp_db_conn):
+def test_get_classtype_pair_data_more(placex_row, def_config, temp_db_conn):
     for _ in range(99):
-        placex_table.add(cls='emergency', typ='firehydrant')  # edge case 99, not included
+        placex_row(cls='emergency', typ='firehydrant')  # edge case 99, not included
 
     for _ in range(199):
-        placex_table.add(cls='amenity', typ='prison')
+        placex_row(cls='amenity', typ='prison')
 
     for _ in range(3478):
-        placex_table.add(cls='tourism', typ='hotel')
+        placex_row(cls='tourism', typ='hotel')
 
     importer = SPImporter(config=def_config, conn=temp_db_conn, sp_loader=None)
 
     result = importer.get_classtype_pairs(min=100)
 
-    expected = {
+    assert result == {
         ("amenity", "prison"),
         ("tourism", "hotel")
     }
 
-    assert result == expected, f"Expected {expected}, got {result}"
 
-
-def test_get_classtype_pair_data_default(placex_table, def_config, temp_db_conn):
+def test_get_classtype_pair_data_default(placex_row, def_config, temp_db_conn):
     for _ in range(1):
-        placex_table.add(cls='emergency', typ='firehydrant')
+        placex_row(cls='emergency', typ='firehydrant')
 
     for _ in range(199):
-        placex_table.add(cls='amenity', typ='prison')
+        placex_row(cls='amenity', typ='prison')
 
     for _ in range(3478):
-        placex_table.add(cls='tourism', typ='hotel')
+        placex_row(cls='tourism', typ='hotel')
 
     importer = SPImporter(config=def_config, conn=temp_db_conn, sp_loader=None)
 
     result = importer.get_classtype_pairs()
 
-    expected = {
+    assert result == {
         ("amenity", "prison"),
         ("tourism", "hotel"),
         ("emergency", "firehydrant")
     }
-
-    assert result == expected, f"Expected {expected}, got {result}"

test/python/tools/test_sp_wiki_loader.py

@@ -21,7 +21,7 @@ def sp_wiki_loader(src_dir, monkeypatch, def_config):
 
     def _mock_wiki_content(lang):
         xml_test_content = src_dir / 'test' / 'testdata' / 'special_phrases_test_content.txt'
-        return xml_test_content.read_text()
+        return xml_test_content.read_text(encoding='utf-8')
 
     monkeypatch.setattr('nominatim_db.tools.special_phrases.sp_wiki_loader._get_wiki_content',
                         _mock_wiki_content)

test/python/tools/test_tiger_data.py

@@ -2,7 +2,7 @@
 #
 # This file is part of Nominatim. (https://nominatim.org)
 #
-# Copyright (C) 2025 by the Nominatim developer community.
+# Copyright (C) 2026 by the Nominatim developer community.
 # For a full list of authors see the git log.
 """
 Test for tiger data function
@@ -13,59 +13,10 @@ from textwrap import dedent
 import pytest
 import pytest_asyncio  # noqa: F401
 
-from nominatim_db.db.connection import execute_scalar
-from nominatim_db.tools import tiger_data, freeze
+from nominatim_db.tools import tiger_data
 from nominatim_db.errors import UsageError
 
 
-class MockTigerTable:
-
-    def __init__(self, conn):
-        self.conn = conn
-        with conn.cursor() as cur:
-            cur.execute("""CREATE TABLE tiger (linegeo GEOMETRY,
-                                               start INTEGER,
-                                               stop INTEGER,
-                                               interpol TEXT,
-                                               token_info JSONB,
-                                               postcode TEXT)""")
-
-            # We need this table to determine if the database is frozen or not
-            cur.execute("CREATE TABLE place (number INTEGER)")
-            # We need this table to determine if the database is in reverse-only mode
-            cur.execute("CREATE TABLE search_name (place_id BIGINT)")
-
-    def count(self):
-        return execute_scalar(self.conn, "SELECT count(*) FROM tiger")
-
-    def row(self):
-        with self.conn.cursor() as cur:
-            cur.execute("SELECT * FROM tiger LIMIT 1")
-            return cur.fetchone()
-
-
-@pytest.fixture
-def tiger_table(def_config, temp_db_conn, sql_preprocessor,
-                temp_db_with_extensions, tmp_path):
-    def_config.lib_dir.sql = tmp_path / 'sql'
-    def_config.lib_dir.sql.mkdir()
-
-    (def_config.lib_dir.sql / 'tiger_import_start.sql').write_text(
-        """CREATE OR REPLACE FUNCTION tiger_line_import(linegeo GEOMETRY, start INTEGER,
-                                                        stop INTEGER, interpol TEXT,
-                                                        token_info JSONB, postcode TEXT)
-           RETURNS INTEGER AS $$
-            INSERT INTO tiger VALUES(linegeo, start, stop, interpol, token_info, postcode)
-            RETURNING 1
-           $$ LANGUAGE SQL;""")
-    (def_config.lib_dir.sql / 'tiger_import_finish.sql').write_text(
-        """DROP FUNCTION tiger_line_import (linegeo GEOMETRY, in_startnumber INTEGER,
-                                 in_endnumber INTEGER, interpolationtype TEXT,
-                                 token_info JSONB, in_postcode TEXT);""")
-
-    return MockTigerTable(temp_db_conn)
-
-
 @pytest.fixture
 def csv_factory(tmp_path):
     def _mk_file(fname, hnr_from=1, hnr_to=9, interpol='odd', street='Main St',
@@ -75,112 +26,115 @@ def csv_factory(tmp_path):
         from;to;interpolation;street;city;state;postcode;geometry
         {};{};{};{};{};{};{};{}
         """.format(hnr_from, hnr_to, interpol, street, city, state,
-                   postcode, geometry)))
+                   postcode, geometry)), encoding='utf-8')
 
     return _mk_file
 
 
-@pytest.mark.parametrize("threads", (1, 5))
-@pytest.mark.asyncio
-async def test_add_tiger_data(def_config, src_dir, tiger_table, tokenizer_mock, threads):
-    await tiger_data.add_tiger_data(str(src_dir / 'test' / 'testdb' / 'tiger'),
-                                    def_config, threads, tokenizer_mock())
+class TestTiger:
 
-    assert tiger_table.count() == 6213
+    @pytest.fixture(autouse=True)
+    def setup(self, temp_db_conn, placex_row, load_sql):
+        load_sql('tables/search_name.sql', create_reverse_only=False)
+        load_sql('tables/tiger.sql')
 
+        # fake parent roads
+        for x in range(-870, -863):
+            for y in range(323, 328):
+                placex_row(rank_search=26, rank_address=26,
+                           geom=f"LINESTRING({x/10 - 0.1} {y/10}, {x/10 + 0.1} {y/10})")
 
-@pytest.mark.parametrize("threads", (1, 5))
-@pytest.mark.asyncio
-async def test_add_tiger_data_database_frozen(def_config, src_dir, temp_db_conn, tiger_table,
-                                              tokenizer_mock, threads):
-    freeze.drop_update_tables(temp_db_conn)
+        temp_db_conn.execute("""
+            CREATE OR REPLACE FUNCTION get_partition(cc VARCHAR(10)) RETURNS INTEGER AS $$
+              SELECT 0;
+            $$ LANGUAGE sql;
+            CREATE OR REPLACE FUNCTION token_matches_street(i JSONB, s INT[]) RETURNS BOOLEAN AS $$
+             SELECT false
+            $$ LANGUAGE SQL IMMUTABLE STRICT PARALLEL SAFE;
+        """)
 
-    await tiger_data.add_tiger_data(str(src_dir / 'test' / 'testdb' / 'tiger'),
-                                    def_config, threads, tokenizer_mock())
-
-    assert tiger_table.count() == 6213
-
-
-@pytest.mark.asyncio
-async def test_add_tiger_data_reverse_only(def_config, src_dir, temp_db_conn, tiger_table,
-                                           tokenizer_mock):
-    with temp_db_conn.cursor() as cur:
-        cur.execute("DROP TABLE search_name")
-    temp_db_conn.commit()
-
-    with pytest.raises(UsageError,
-                       match="Cannot perform tiger import: required tables are missing. "
-                       "See https://github.com/osm-search/Nominatim/issues/2463 for details."):
+    @pytest.mark.parametrize("threads", (1, 5))
+    @pytest.mark.asyncio
+    async def test_add_tiger_data_database_frozen(self, def_config, src_dir, temp_db_cursor,
+                                                  tokenizer_mock, threads):
         await tiger_data.add_tiger_data(str(src_dir / 'test' / 'testdb' / 'tiger'),
-                                        def_config, 1, tokenizer_mock())
+                                        def_config, threads, tokenizer_mock())
 
-    assert tiger_table.count() == 0
+        assert temp_db_cursor.table_rows('location_property_tiger') == 6209
 
+    @pytest.mark.asyncio
+    async def test_add_tiger_data_reverse_only(self, def_config, src_dir, temp_db_cursor,
+                                               tokenizer_mock):
+        temp_db_cursor.execute("DROP TABLE search_name")
 
-@pytest.mark.asyncio
-async def test_add_tiger_data_no_files(def_config, tiger_table, tokenizer_mock,
-                                       tmp_path):
-    await tiger_data.add_tiger_data(str(tmp_path), def_config, 1, tokenizer_mock())
+        with pytest.raises(UsageError,
+                           match="Cannot perform tiger import: required tables are missing. "
+                           "See https://github.com/osm-search/Nominatim/issues/2463 for details."):
+            await tiger_data.add_tiger_data(str(src_dir / 'test' / 'testdb' / 'tiger'),
+                                            def_config, 1, tokenizer_mock())
 
-    assert tiger_table.count() == 0
+        assert temp_db_cursor.table_rows('location_property_tiger') == 0
 
+    @pytest.mark.asyncio
+    async def test_add_tiger_data_no_files(self, def_config, temp_db_cursor, tokenizer_mock,
+                                           tmp_path):
+        await tiger_data.add_tiger_data(str(tmp_path), def_config, 1, tokenizer_mock())
 
-@pytest.mark.asyncio
-async def test_add_tiger_data_bad_file(def_config, tiger_table, tokenizer_mock,
-                                       tmp_path):
-    sqlfile = tmp_path / '1010.csv'
-    sqlfile.write_text("""Random text""")
+        assert temp_db_cursor.table_rows('location_property_tiger') == 0
 
-    await tiger_data.add_tiger_data(str(tmp_path), def_config, 1, tokenizer_mock())
+    @pytest.mark.asyncio
+    async def test_add_tiger_data_bad_file(self, def_config, temp_db_cursor, tokenizer_mock,
+                                           tmp_path):
+        sqlfile = tmp_path / '1010.csv'
+        sqlfile.write_text('Random text', encoding='utf-8')
 
-    assert tiger_table.count() == 0
+        await tiger_data.add_tiger_data(str(tmp_path), def_config, 1, tokenizer_mock())
 
+        assert temp_db_cursor.table_rows('location_property_tiger') == 0
 
-@pytest.mark.asyncio
-async def test_add_tiger_data_hnr_nan(def_config, tiger_table, tokenizer_mock,
-                                      csv_factory, tmp_path):
-    csv_factory('file1', hnr_from=99)
-    csv_factory('file2', hnr_from='L12')
-    csv_factory('file3', hnr_to='12.4')
+    @pytest.mark.asyncio
+    async def test_add_tiger_data_hnr_nan(self, def_config, temp_db_cursor, tokenizer_mock,
+                                          csv_factory, tmp_path):
+        csv_factory('file1', hnr_to=99)
+        csv_factory('file2', hnr_from='L12')
+        csv_factory('file3', hnr_to='12.4')
 
-    await tiger_data.add_tiger_data(str(tmp_path), def_config, 1, tokenizer_mock())
+        await tiger_data.add_tiger_data(str(tmp_path), def_config, 1, tokenizer_mock())
 
-    assert tiger_table.count() == 1
-    assert tiger_table.row().start == 99
+        rows = temp_db_cursor.row_set("""
+            SELECT startnumber, endnumber FROM location_property_tiger""")
 
+        assert rows == {(1, 99)}
 
-@pytest.mark.parametrize("threads", (1, 5))
-@pytest.mark.asyncio
-async def test_add_tiger_data_tarfile(def_config, tiger_table, tokenizer_mock,
-                                      tmp_path, src_dir, threads):
-    tar = tarfile.open(str(tmp_path / 'sample.tar.gz'), "w:gz")
-    tar.add(str(src_dir / 'test' / 'testdb' / 'tiger' / '01001.csv'))
-    tar.close()
+    @pytest.mark.parametrize("threads", (1, 5))
+    @pytest.mark.asyncio
+    async def test_add_tiger_data_tarfile(self, def_config, temp_db_cursor, tokenizer_mock,
+                                          tmp_path, src_dir, threads):
+        tar = tarfile.open(str(tmp_path / 'sample.tar.gz'), "w:gz")
+        tar.add(str(src_dir / 'test' / 'testdb' / 'tiger' / '01001.csv'))
+        tar.close()
 
-    await tiger_data.add_tiger_data(str(tmp_path / 'sample.tar.gz'), def_config, threads,
-                                    tokenizer_mock())
+        await tiger_data.add_tiger_data(str(tmp_path / 'sample.tar.gz'), def_config, threads,
+                                        tokenizer_mock())
 
-    assert tiger_table.count() == 6213
+        assert temp_db_cursor.table_rows('location_property_tiger') == 6209
 
+    @pytest.mark.asyncio
+    async def test_add_tiger_data_bad_tarfile(self, def_config, tokenizer_mock, tmp_path):
+        tarfile = tmp_path / 'sample.tar.gz'
+        tarfile.write_text("""Random text""", encoding='utf-8')
 
-@pytest.mark.asyncio
-async def test_add_tiger_data_bad_tarfile(def_config, tiger_table, tokenizer_mock,
-                                          tmp_path):
-    tarfile = tmp_path / 'sample.tar.gz'
-    tarfile.write_text("""Random text""")
+        with pytest.raises(UsageError):
+            await tiger_data.add_tiger_data(str(tarfile), def_config, 1, tokenizer_mock())
 
-    with pytest.raises(UsageError):
-        await tiger_data.add_tiger_data(str(tarfile), def_config, 1, tokenizer_mock())
+    @pytest.mark.asyncio
+    async def test_add_tiger_data_empty_tarfile(self, def_config, temp_db_cursor, tokenizer_mock,
+                                                tmp_path):
+        tar = tarfile.open(str(tmp_path / 'sample.tar.gz'), "w:gz")
+        tar.add(__file__)
+        tar.close()
 
+        await tiger_data.add_tiger_data(str(tmp_path / 'sample.tar.gz'), def_config, 1,
+                                        tokenizer_mock())
 
-@pytest.mark.asyncio
-async def test_add_tiger_data_empty_tarfile(def_config, tiger_table, tokenizer_mock,
-                                            tmp_path):
-    tar = tarfile.open(str(tmp_path / 'sample.tar.gz'), "w:gz")
-    tar.add(__file__)
-    tar.close()
-
-    await tiger_data.add_tiger_data(str(tmp_path / 'sample.tar.gz'), def_config, 1,
-                                    tokenizer_mock())
-
-    assert tiger_table.count() == 0
+        assert temp_db_cursor.table_rows('location_property_tiger') == 0