Merge pull request #3901 from AyushDharDubey/fix/issue_3829-use-mwparserfromhell-to-parse-sp-wiki-page

Replace regex with `mwparserfromhell` based MW WikiCode Parsing for Special Phrases

.github/actions/build-nominatim/action.yml

@@ -22,7 +22,7 @@ runs:
 
         - name: Install prerequisites from apt
           run: |
-            sudo apt-get install -y -qq python3-icu python3-datrie python3-jinja2 python3-psutil python3-dotenv python3-yaml python3-sqlalchemy python3-psycopg python3-asyncpg
+            sudo apt-get install -y -qq python3-icu python3-datrie python3-jinja2 python3-psutil python3-dotenv python3-yaml python3-sqlalchemy python3-psycopg python3-asyncpg python3-mwparserfromhell
           shell: bash
           if: inputs.dependencies == 'apt'
 

docs/admin/Installation.md

@@ -37,6 +37,7 @@ Furthermore the following Python libraries are required:
   * [Jinja2](https://palletsprojects.com/p/jinja/)
   * [PyICU](https://pypi.org/project/PyICU/)
   * [PyYaml](https://pyyaml.org/) (5.1+)
+  * [mwparserfromhell](https://github.com/earwig/mwparserfromhell/)
 
 These will be installed automatically when using pip installation.
 

docs/develop/Development-Environment.md

@@ -73,7 +73,7 @@ virtualenv ~/nominatim-dev-venv
     types-jinja2 types-markupsafe types-psutil types-psycopg2 \
     types-pygments types-pyyaml types-requests types-ujson \
     types-urllib3 typing-extensions unicorn falcon starlette \
-    uvicorn mypy osmium aiosqlite
+    uvicorn mypy osmium aiosqlite mwparserfromhell
 ```
 
 Now enter the virtual environment whenever you want to develop:

docs/develop/Testing.md

@@ -52,6 +52,15 @@ To run the functional tests, do
 
     pytest test/bdd
 
+You can run a single feature file using expression matching:
+
+    pytest test/bdd -k osm2pgsql/import/entrances.feature
+
+This even works for running single tests by adding the line number of the
+scenario header like that:
+
+    pytest test/bdd -k 'osm2pgsql/import/entrances.feature and L4'
+
 The BDD tests create databases for the tests. You can set name of the databases
 through configuration variables in your `pytest.ini`:
 

lib-lua/themes/nominatim/presets.lua

@@ -117,6 +117,7 @@ module.MAIN_TAGS.all_boundaries = {
     boundary = {'named',
                 place = 'delete',
                 land_area = 'delete',
+                protected_area = 'fallback',
                 postal_code = 'always'},
     landuse = 'fallback',
     place = 'always'
@@ -198,7 +199,7 @@ module.MAIN_TAGS_POIS = function (group)
                 no = group},
     landuse = {cemetery = 'always'},
     leisure = {'always',
-               nature_reserve = 'fallback',
+               nature_reserve = 'named',
                swimming_pool = 'named',
                garden = 'named',
                common = 'named',
@@ -321,7 +322,6 @@ module.NAME_TAGS = {}
 
 module.NAME_TAGS.core = {main = {'name', 'name:*',
                                  'int_name', 'int_name:*',
-                                 'nat_name', 'nat_name:*',
                                  'reg_name', 'reg_name:*',
                                  'loc_name', 'loc_name:*',
                                  'old_name', 'old_name:*',

lib-sql/functions/placex_triggers.sql

@@ -341,6 +341,22 @@ BEGIN
     END IF;
   END IF;
 
+  IF bnd.extratags ? 'wikidata' THEN
+    FOR linked_placex IN
+      SELECT * FROM placex
+      WHERE placex.class = 'place' AND placex.osm_type = 'N'
+        AND placex.extratags ? 'wikidata' -- needed to select right index
+        AND placex.extratags->'wikidata' = bnd.extratags->'wikidata'
+        AND (placex.linked_place_id is null or placex.linked_place_id = bnd.place_id)
+        AND placex.rank_search < 26
+        AND _st_covers(bnd.geometry, placex.geometry)
+      ORDER BY lower(name->'name') = bnd_name desc
+    LOOP
+      {% if debug %}RAISE WARNING 'Found wikidata-matching place node %', linked_placex.osm_id;{% endif %}
+      RETURN linked_placex;
+    END LOOP;
+  END IF;
+
   -- If extratags has a place tag, look for linked nodes by their place type.
   -- Area and node still have to have the same name.
   IF bnd.extratags ? 'place' and bnd.extratags->'place' != 'postcode'
@@ -361,22 +377,6 @@ BEGIN
     END LOOP;
   END IF;
 
-  IF bnd.extratags ? 'wikidata' THEN
-    FOR linked_placex IN
-      SELECT * FROM placex
-      WHERE placex.class = 'place' AND placex.osm_type = 'N'
-        AND placex.extratags ? 'wikidata' -- needed to select right index
-        AND placex.extratags->'wikidata' = bnd.extratags->'wikidata'
-        AND (placex.linked_place_id is null or placex.linked_place_id = bnd.place_id)
-        AND placex.rank_search < 26
-        AND _st_covers(bnd.geometry, placex.geometry)
-      ORDER BY lower(name->'name') = bnd_name desc
-    LOOP
-      {% if debug %}RAISE WARNING 'Found wikidata-matching place node %', linked_placex.osm_id;{% endif %}
-      RETURN linked_placex;
-    END LOOP;
-  END IF;
-
   -- Name searches can be done for ways as well as relations
   IF bnd_name is not null THEN
     {% if debug %}RAISE WARNING 'Looking for nodes with matching names';{% endif %}
@@ -874,7 +874,7 @@ BEGIN
   -- Remove linkage, if we have computed a different new linkee.
   UPDATE placex SET linked_place_id = null, indexed_status = 2
     WHERE linked_place_id = NEW.place_id
-          and (linked_place is null or linked_place_id != linked_place);
+          and (linked_place is null or place_id != linked_place);
   -- update not necessary for osmline, cause linked_place_id does not exist
 
   -- Postcodes are just here to compute the centroids. They are not searchable

packaging/nominatim-db/pyproject.toml

@@ -15,12 +15,13 @@ classifiers = [
     "Operating System :: OS Independent",
 ]
 dependencies = [
-    "psycopg",
+    "psycopg != 3.3.0",
     "python-dotenv",
     "jinja2",
     "pyYAML>=5.1",
     "psutil",
-    "PyICU"
+    "PyICU",
+    "mwparserfromhell"
 ]
 dynamic = ["version"]
 

src/nominatim_api/result_formatting.py

@@ -10,7 +10,7 @@ Helper classes and functions for formatting results into API responses.
 from typing import Type, TypeVar, Dict, List, Callable, Any, Mapping, Optional, cast
 from collections import defaultdict
 from pathlib import Path
-import importlib
+import importlib.util
 
 from .server.content_types import CONTENT_JSON
 

src/nominatim_api/reverse.py

@@ -157,16 +157,19 @@ class ReverseGeocoder:
             include.extend(('natural', 'water', 'waterway'))
         return table.c.class_.in_(tuple(include))
 
-    async def _find_closest_street_or_poi(self, distance: float) -> Optional[SaRow]:
-        """ Look up the closest rank 26+ place in the database, which
-            is closer than the given distance.
+    async def _find_closest_street_or_pois(self, distance: float,
+                                           fuzziness: float) -> list[SaRow]:
+        """ Look up the closest rank 26+ place in the database.
+            The function finds the object that is closest to the reverse
+            search point as well as all objects within 'fuzziness' distance
+            to that best result.
         """
         t = self.conn.t.placex
 
         # PostgreSQL must not get the distance as a parameter because
         # there is a danger it won't be able to properly estimate index use
         # when used with prepared statements
-        diststr = sa.text(f"{distance}")
+        diststr = sa.text(f"{distance + fuzziness}")
 
         sql: SaLambdaSelect = sa.lambda_stmt(
             lambda: _select_from_placex(t)
@@ -174,9 +177,7 @@ class ReverseGeocoder:
             .where(t.c.indexed_status == 0)
             .where(t.c.linked_place_id == None)
             .where(sa.or_(sa.not_(t.c.geometry.is_area()),
-                          t.c.centroid.ST_Distance(WKT_PARAM) < diststr))
-            .order_by('distance')
-            .limit(2))
+                          t.c.centroid.ST_Distance(WKT_PARAM) < diststr)))
 
         if self.has_geometries():
             sql = self._add_geometry_columns(sql, t.c.geometry)
@@ -198,24 +199,44 @@ class ReverseGeocoder:
                                     self._filter_by_layer(t)))
 
         if not restrict:
-            return None
+            return []
 
-        sql = sql.where(sa.or_(*restrict))
+        inner = sql.where(sa.or_(*restrict)) \
+                   .add_columns(t.c.geometry.label('_geometry')) \
+                   .subquery()
 
-        # If the closest object is inside an area, then check if there is a
-        # POI node nearby and return that.
-        prev_row = None
-        for row in await self.conn.execute(sql, self.bind_params):
-            if prev_row is None:
-                if row.rank_search <= 27 or row.osm_type == 'N' or row.distance > 0:
-                    return row
-                prev_row = row
-            else:
-                if row.rank_search > 27 and row.osm_type == 'N'\
-                   and row.distance < 0.0001:
-                    return row
+        # Use a window function to get the closest results to the best result.
+        windowed = sa.select(inner,
+                             sa.func.first_value(inner.c.distance)
+                                    .over(order_by=inner.c.distance)
+                                    .label('_min_distance'),
+                             sa.func.first_value(
+                                        sa.case((inner.c.rank_search <= 27,
+                                                 inner.c._geometry.ST_ClosestPoint(WKT_PARAM)),
+                                                else_=None))
+                                    .over(order_by=inner.c.distance)
+                                    .label('_closest_point'),
+                             sa.func.first_value(sa.case((sa.or_(inner.c.rank_search <= 27,
+                                                                 inner.c.osm_type == 'N'), None),
+                                                         else_=inner.c._geometry))
+                                    .over(order_by=inner.c.distance)
+                                    .label('_best_geometry')) \
+                     .subquery()
 
-        return prev_row
+        outer = sa.select(*(c for c in windowed.c if not c.key.startswith('_')),
+                          sa.case((sa.or_(windowed.c._closest_point == None,
+                                          windowed.c.housenumber == None), None),
+                                  else_=windowed.c.centroid.ST_Distance(windowed.c._closest_point))
+                            .label('distance_from_best'),
+                          sa.case((sa.or_(windowed.c._best_geometry == None,
+                                          windowed.c.rank_search <= 27,
+                                          windowed.c.osm_type != 'N'), False),
+                                  else_=windowed.c.centroid.ST_CoveredBy(windowed.c._best_geometry))
+                            .label('best_inside')) \
+                  .where(windowed.c.distance < windowed.c._min_distance + fuzziness) \
+                  .order_by(windowed.c.distance)
+
+        return list(await self.conn.execute(outer, self.bind_params))
 
     async def _find_housenumber_for_street(self, parent_place_id: int) -> Optional[SaRow]:
         t = self.conn.t.placex
@@ -301,55 +322,69 @@ class ReverseGeocoder:
         """ Find a street or POI/address for the given WKT point.
         """
         log().section('Reverse lookup on street/address level')
-        distance = 0.006
-        parent_place_id = None
-
-        row = await self._find_closest_street_or_poi(distance)
         row_func: RowFunc = nres.create_from_placex_row
-        log().var_dump('Result (street/building)', row)
+        distance = 0.006
 
-        # If the closest result was a street, but an address was requested,
-        # check for a housenumber nearby which is part of the street.
-        if row is not None:
-            if self.max_rank > 27 \
-               and self.layer_enabled(DataLayer.ADDRESS) \
-               and row.rank_address <= 27:
-                distance = 0.001
-                parent_place_id = row.place_id
-                log().comment('Find housenumber for street')
-                addr_row = await self._find_housenumber_for_street(parent_place_id)
-                log().var_dump('Result (street housenumber)', addr_row)
-
-                if addr_row is not None:
-                    row = addr_row
-                    row_func = nres.create_from_placex_row
-                    distance = addr_row.distance
-                elif row.country_code == 'us' and parent_place_id is not None:
-                    log().comment('Find TIGER housenumber for street')
-                    addr_row = await self._find_tiger_number_for_street(parent_place_id)
-                    log().var_dump('Result (street Tiger housenumber)', addr_row)
-
-                    if addr_row is not None:
-                        row_func = cast(RowFunc,
-                                        functools.partial(nres.create_from_tiger_row,
-                                                          osm_type=row.osm_type,
-                                                          osm_id=row.osm_id))
-                        row = addr_row
-            else:
+        result = None
+        hnr_distance = None
+        parent_street = None
+        for row in await self._find_closest_street_or_pois(distance, 0.001):
+            if result is None:
+                log().var_dump('Closest result', row)
+                result = row
+                if self.max_rank > 27 \
+                        and self.layer_enabled(DataLayer.ADDRESS) \
+                        and result.rank_address <= 27:
+                    parent_street = result.place_id
+                    distance = 0.001
+                else:
+                    distance = row.distance
+            # If the closest result was a street but an address was requested,
+            # see if we can refine the result with a housenumber closeby.
+            elif parent_street is not None \
+                    and row.distance_from_best is not None \
+                    and row.distance_from_best < 0.001 \
+                    and (hnr_distance is None or hnr_distance > row.distance_from_best) \
+                    and row.parent_place_id == parent_street:
+                log().var_dump('Housenumber to closest result', row)
+                result = row
+                hnr_distance = row.distance_from_best
                 distance = row.distance
+            # If the closest object is inside an area, then check if there is
+            # a POI nearby and return that with preference.
+            elif result.osm_type != 'N' and result.rank_search > 27 \
+                    and result.distance == 0 \
+                    and row.best_inside:
+                log().var_dump('POI near closest result area', row)
+                result = row
+                break  # it can't get better than that, everything else is farther away
+
+        # For the US also check the TIGER data, when no housenumber/POI was found.
+        if result is not None and parent_street is not None and hnr_distance is None \
+                and result.country_code == 'us':
+            log().comment('Find TIGER housenumber for street')
+            addr_row = await self._find_tiger_number_for_street(parent_street)
+            log().var_dump('Result (street Tiger housenumber)', addr_row)
+
+            if addr_row is not None:
+                row_func = cast(RowFunc,
+                                functools.partial(nres.create_from_tiger_row,
+                                                  osm_type=row.osm_type,
+                                                  osm_id=row.osm_id))
+                result = addr_row
 
         # Check for an interpolation that is either closer than our result
         # or belongs to a close street found.
-        if self.max_rank > 27 and self.layer_enabled(DataLayer.ADDRESS):
+        # No point in doing this when the result is already inside a building,
+        # i.e. when the distance is already 0.
+        if self.max_rank > 27 and self.layer_enabled(DataLayer.ADDRESS) and distance > 0:
             log().comment('Find interpolation for street')
-            addr_row = await self._find_interpolation_for_street(parent_place_id,
-                                                                 distance)
+            addr_row = await self._find_interpolation_for_street(parent_street, distance)
             log().var_dump('Result (street interpolation)', addr_row)
             if addr_row is not None:
-                row = addr_row
-                row_func = nres.create_from_osmline_row
+                return addr_row, nres.create_from_osmline_row
 
-        return row, row_func
+        return result, row_func
 
     async def _lookup_area_address(self) -> Optional[SaRow]:
         """ Lookup large addressable areas for the given WKT point.

src/nominatim_api/search/db_search_builder.py

@@ -374,7 +374,7 @@ class SearchBuilder:
             tokens = self.get_country_tokens(assignment.country)
             if not tokens:
                 return None
-            sdata.set_strings('countries', tokens)
+            sdata.set_countries(tokens)
             sdata.penalty += self.query.get_in_word_penalty(assignment.country)
         elif self.details.countries:
             sdata.countries = dbf.WeightedStrings(self.details.countries,
@@ -413,7 +413,7 @@ class SearchBuilder:
         """
         tokens = self.query.get_tokens(trange, qmod.TOKEN_COUNTRY)
         if self.details.countries:
-            tokens = [t for t in tokens if t.lookup_word in self.details.countries]
+            tokens = [t for t in tokens if t.get_country() in self.details.countries]
 
         return tokens
 

src/nominatim_api/search/db_search_fields.py

@@ -244,6 +244,21 @@ class SearchData:
 
             setattr(self, field, wstrs)
 
+    def set_countries(self, tokens: List[Token]) -> None:
+        """ Set the WeightedStrings properties for countries. Multiple
+            entries for the same country are deduplicated and the minimum
+            penalty is used. Adapts the global penalty, so that the
+            minimum penalty is 0.
+        """
+        if tokens:
+            min_penalty = min(t.penalty for t in tokens)
+            self.penalty += min_penalty
+            countries: dict[str, float] = {}
+            for t in tokens:
+                cc = t.get_country()
+                countries[cc] = min(t.penalty - min_penalty, countries.get(cc, 10000))
+            self.countries = WeightedStrings(list(countries.keys()), list(countries.values()))
+
     def set_qualifiers(self, tokens: List[Token]) -> None:
         """ Set the qulaifier field from the given tokens.
         """

src/nominatim_api/search/icu_tokenizer.py

@@ -59,12 +59,16 @@ class ICUToken(qmod.Token):
         assert self.info
         return self.info.get('class', ''), self.info.get('type', '')
 
-    def rematch(self, norm: str) -> None:
+    def get_country(self) -> str:
+        assert self.info
+        return cast(str, self.info.get('cc', ''))
+
+    def match_penalty(self, norm: str) -> float:
         """ Check how well the token matches the given normalized string
             and add a penalty, if necessary.
         """
         if not self.lookup_word:
-            return
+            return 0.0
 
         seq = difflib.SequenceMatcher(a=self.lookup_word, b=norm)
         distance = 0
@@ -75,7 +79,7 @@ class ICUToken(qmod.Token):
                 distance += max((ato-afrom), (bto-bfrom))
             elif tag != 'equal':
                 distance += abs((ato-afrom) - (bto-bfrom))
-        self.penalty += (distance/len(self.lookup_word))
+        return (distance/len(self.lookup_word))
 
     @staticmethod
     def from_db_row(row: SaRow) -> 'ICUToken':
@@ -330,9 +334,10 @@ class ICUQueryAnalyzer(AbstractQueryAnalyzer):
             norm = ''.join(f"{n.term_normalized}{'' if n.btype == qmod.BREAK_TOKEN else ' '}"
                            for n in query.nodes[start + 1:end + 1]).strip()
             for ttype, tokens in tlist.items():
-                if ttype != qmod.TOKEN_COUNTRY:
-                    for token in tokens:
-                        cast(ICUToken, token).rematch(norm)
+                for token in tokens:
+                    itok = cast(ICUToken, token)
+                    itok.penalty += itok.match_penalty(norm) * \
+                        (1 if ttype in (qmod.TOKEN_WORD, qmod.TOKEN_PARTIAL) else 2)
 
     def compute_break_penalties(self, query: qmod.QueryStruct) -> None:
         """ Set the break penalties for the nodes in the query.

src/nominatim_api/search/query.py

@@ -127,6 +127,12 @@ class Token(ABC):
             category objects.
         """
 
+    @abstractmethod
+    def get_country(self) -> str:
+        """ Return the country code this tojen is associated with
+            (currently for country tokens only).
+        """
+
 
 @dataclasses.dataclass
 class TokenRange:

src/nominatim_api/server/falcon/server.py

@@ -7,6 +7,8 @@
 """
 Server implementation using the falcon webserver framework.
 """
+from __future__ import annotations
+
 from typing import Optional, Mapping, Any, List, cast
 from pathlib import Path
 import asyncio
@@ -161,7 +163,7 @@ class APIMiddleware:
 
     def __init__(self, project_dir: Path, environ: Optional[Mapping[str, str]]) -> None:
         self.api = NominatimAPIAsync(project_dir, environ)
-        self.app: Optional[App] = None
+        self.app: Optional[App[Request, Response]] = None
 
     @property
     def config(self) -> Configuration:
@@ -169,7 +171,7 @@ class APIMiddleware:
         """
         return self.api.config
 
-    def set_app(self, app: App) -> None:
+    def set_app(self, app: App[Request, Response]) -> None:
         """ Set the Falcon application this middleware is connected to.
         """
         self.app = app
@@ -193,7 +195,7 @@ class APIMiddleware:
 
 
 def get_application(project_dir: Path,
-                    environ: Optional[Mapping[str, str]] = None) -> App:
+                    environ: Optional[Mapping[str, str]] = None) -> App[Request, Response]:
     """ Create a Nominatim Falcon ASGI application.
     """
     apimw = APIMiddleware(project_dir, environ)
@@ -215,7 +217,7 @@ def get_application(project_dir: Path,
     return app
 
 
-def run_wsgi() -> App:
+def run_wsgi() -> App[Request, Response]:
     """ Entry point for uvicorn.
 
         Make sure uvicorn is run from the project directory.

src/nominatim_db/clicmd/setup.py

@@ -23,6 +23,7 @@ from ..tokenizer.base import AbstractTokenizer
 from ..version import NOMINATIM_VERSION
 from .args import NominatimArgs
 
+import time
 
 LOG = logging.getLogger()
 
@@ -86,6 +87,8 @@ class SetupAll:
         from ..tools import database_import, postcodes, freeze
         from ..indexer.indexer import Indexer
 
+        start_time = time.time()
+
         num_threads = args.threads or psutil.cpu_count() or 1
         country_info.setup_country_config(args.config)
 
@@ -138,6 +141,10 @@ class SetupAll:
         LOG.warning('Recompute word counts')
         tokenizer.update_statistics(args.config, threads=num_threads)
 
+        end_time = time.time()
+        elapsed = end_time - start_time
+        LOG.warning(f'Import completed successfully in {elapsed:.2f} seconds.')
+
         self._finalize_database(args.config.get_libpq_dsn(), args.offline)
 
         return 0

src/nominatim_db/config.py

@@ -197,7 +197,7 @@ class Configuration:
         if dsn.startswith('pgsql:'):
             return dict((p.split('=', 1) for p in dsn[6:].split(';')))
 
-        return conninfo_to_dict(dsn)
+        return conninfo_to_dict(dsn)  # type: ignore
 
     def get_import_style_file(self) -> Path:
         """ Return the import style file as a path object. Translates the

src/nominatim_db/data/postcode_format.py

@@ -29,6 +29,9 @@ class CountryPostcodeMatcher:
         self.norm_pattern = re.compile(f'\\s*(?:{country_code.upper()}[ -]?)?({pc_pattern})\\s*')
         self.pattern = re.compile(pc_pattern)
 
+        # We want to exclude 0000, 00-000, 000 00 etc
+        self.zero_pattern = re.compile(r'^[0\- ]+$')
+
         self.output = config.get('output', r'\g<0>')
 
     def match(self, postcode: str) -> Optional[Match[str]]:
@@ -40,7 +43,10 @@ class CountryPostcodeMatcher:
         normalized = self.norm_pattern.fullmatch(postcode.upper())
 
         if normalized:
-            return self.pattern.fullmatch(normalized.group(1))
+            match = self.pattern.fullmatch(normalized.group(1))
+            if match and self.zero_pattern.match(match.string):
+                return None
+            return match
 
         return None
 

src/nominatim_db/tokenizer/icu_tokenizer.py

@@ -475,20 +475,23 @@ class ICUNameAnalyzer(AbstractAnalyzer):
         assert self.conn is not None
         word_tokens = set()
         for name in names:
-            norm_name = self._search_normalized(name.name)
-            if norm_name:
-                word_tokens.add(norm_name)
+            norm_name = self._normalized(name.name)
+            token_name = self._search_normalized(name.name)
+            if norm_name and token_name:
+                word_tokens.add((token_name, norm_name))
 
         with self.conn.cursor() as cur:
             # Get existing names
-            cur.execute("""SELECT word_token, coalesce(info ? 'internal', false) as is_internal
+            cur.execute("""SELECT word_token,
+                                  word as lookup,
+                                  coalesce(info ? 'internal', false) as is_internal
                              FROM word
-                             WHERE type = 'C' and word = %s""",
+                             WHERE type = 'C' and info->>'cc' = %s""",
                         (country_code, ))
             # internal/external names
-            existing_tokens: Dict[bool, Set[str]] = {True: set(), False: set()}
+            existing_tokens: Dict[bool, Set[Tuple[str, str]]] = {True: set(), False: set()}
             for word in cur:
-                existing_tokens[word[1]].add(word[0])
+                existing_tokens[word[2]].add((word[0], word[1]))
 
             # Delete names that no longer exist.
             gone_tokens = existing_tokens[internal] - word_tokens
@@ -496,10 +499,10 @@ class ICUNameAnalyzer(AbstractAnalyzer):
                 gone_tokens.update(existing_tokens[False] & word_tokens)
             if gone_tokens:
                 cur.execute("""DELETE FROM word
-                               USING unnest(%s::text[]) as token
-                               WHERE type = 'C' and word = %s
-                                     and word_token = token""",
-                            (list(gone_tokens), country_code))
+                               USING jsonb_array_elements(%s) as data
+                               WHERE type = 'C' and info->>'cc' = %s
+                                     and word_token = data->>0 and word = data->>1""",
+                            (Jsonb(list(gone_tokens)), country_code))
 
             # Only add those names that are not yet in the list.
             new_tokens = word_tokens - existing_tokens[True]
@@ -508,15 +511,17 @@ class ICUNameAnalyzer(AbstractAnalyzer):
             if new_tokens:
                 if internal:
                     sql = """INSERT INTO word (word_token, type, word, info)
-                               (SELECT token, 'C', %s, '{"internal": "yes"}'
-                                  FROM unnest(%s::text[]) as token)
+                               (SELECT data->>0, 'C', data->>1,
+                                       jsonb_build_object('internal', 'yes', 'cc', %s::text)
+                                  FROM jsonb_array_elements(%s) as data)
                            """
                 else:
-                    sql = """INSERT INTO word (word_token, type, word)
-                                   (SELECT token, 'C', %s
-                                    FROM unnest(%s::text[]) as token)
+                    sql = """INSERT INTO word (word_token, type, word, info)
+                                   (SELECT data->>0, 'C', data->>1,
+                                           jsonb_build_object('cc', %s::text)
+                                    FROM  jsonb_array_elements(%s) as data)
                           """
-                cur.execute(sql, (country_code, list(new_tokens)))
+                cur.execute(sql, (country_code, Jsonb(list(new_tokens))))
 
     def process_place(self, place: PlaceInfo) -> Mapping[str, Any]:
         """ Determine tokenizer information about the given place.

src/nominatim_db/tools/migration.py

@@ -2,7 +2,7 @@
 #
 # This file is part of Nominatim. (https://nominatim.org)
 #
-# Copyright (C) 2024 by the Nominatim developer community.
+# Copyright (C) 2025 by the Nominatim developer community.
 # For a full list of authors see the git log.
 """
 Functions for database migration to newer software versions.
@@ -18,6 +18,7 @@ from ..db.connection import connect, Connection, \
 from ..db.sql_preprocessor import SQLPreprocessor
 from ..version import NominatimVersion, NOMINATIM_VERSION, parse_version
 from ..tokenizer import factory as tokenizer_factory
+from ..data.country_info import create_country_names, setup_country_config
 from . import refresh
 
 LOG = logging.getLogger()
@@ -156,3 +157,25 @@ def create_place_entrance_table(conn: Connection, config: Configuration, **_: An
             CREATE UNIQUE INDEX place_entrance_osm_id_idx ON place_entrance
               USING BTREE (osm_id);
               """)
+
+
+@_migration(5, 2, 99, 1)
+def convert_country_tokens(conn: Connection, config: Configuration, **_: Any) -> None:
+    """ Convert country word tokens
+
+        Country tokens now save the country in the info field instead of the
+        word. This migration removes all country tokens from the word table
+        and reimports the default country name. This means that custom names
+        are lost. If you need them back, invalidate the OSM objects containing
+        the names by setting indexed_status to 2 and then reindex the database.
+    """
+    tokenizer = tokenizer_factory.get_tokenizer_for_db(config)
+    # There is only one tokenizer at the time of migration, so we make
+    # some assumptions here about the structure of the database. This will
+    # fail if somebody has written a custom tokenizer.
+    with conn.cursor() as cur:
+        cur.execute("DELETE FROM word WHERE type = 'C'")
+    conn.commit()
+
+    setup_country_config(config)
+    create_country_names(conn, tokenizer, config.get_str_list('LANGUAGES'))

src/nominatim_db/tools/special_phrases/sp_wiki_loader.py

@@ -11,6 +11,8 @@ from typing import Iterable
 import re
 import logging
 
+import mwparserfromhell
+
 from ...config import Configuration
 from ...utils.url_utils import get_url
 from .special_phrase import SpecialPhrase
@@ -36,10 +38,6 @@ class SPWikiLoader:
     """
     def __init__(self, config: Configuration) -> None:
         self.config = config
-        # Compile the regex here to increase performances.
-        self.occurence_pattern = re.compile(
-            r'\| *([^\|]+) *\|\| *([^\|]+) *\|\| *([^\|]+) *\|\| *([^\|]+) *\|\| *([\-YN])'
-        )
         # Hack around a bug where building=yes was imported with quotes into the wiki
         self.type_fix_pattern = re.compile(r'\"|"')
 
@@ -58,11 +56,21 @@ class SPWikiLoader:
             LOG.warning('Importing phrases for lang: %s...', lang)
             loaded_xml = _get_wiki_content(lang)
 
-            # One match will be of format [label, class, type, operator, plural]
-            matches = self.occurence_pattern.findall(loaded_xml)
+            wikicode = mwparserfromhell.parse(loaded_xml)
 
-            for match in matches:
-                yield SpecialPhrase(match[0],
-                                    match[1],
-                                    self.type_fix_pattern.sub('', match[2]),
-                                    match[3])
+            for table in wikicode.filter_tags(matches=lambda t: t.tag == 'table'):
+                for row in table.contents.filter_tags(matches=lambda t: t.tag == 'tr'):
+                    cells = list(row.contents.filter_tags(matches=lambda t: t.tag == 'td'))
+
+                    if len(cells) < 5:
+                        continue
+
+                    label = cells[0].contents.strip_code().strip()
+                    cls = cells[1].contents.strip_code().strip()
+                    typ = cells[2].contents.strip_code().strip()
+                    operator = cells[3].contents.strip_code().strip()
+
+                    yield SpecialPhrase(label,
+                                        cls,
+                                        self.type_fix_pattern.sub('', typ),
+                                        operator)

src/nominatim_db/version.py

@@ -55,7 +55,7 @@ def parse_version(version: str) -> NominatimVersion:
     return NominatimVersion(*[int(x) for x in parts[:2] + parts[2].split('-')])
 
 
-NOMINATIM_VERSION = parse_version('5.2.0-0')
+NOMINATIM_VERSION = parse_version('5.2.99-0')
 
 POSTGRESQL_REQUIRED_VERSION = (12, 0)
 POSTGIS_REQUIRED_VERSION = (3, 0)

test/bdd/conftest.py

@@ -9,6 +9,7 @@ Fixtures for BDD test steps
 """
 import sys
 import json
+import re
 from pathlib import Path
 
 import psycopg
@@ -20,7 +21,8 @@ sys.path.insert(0, str(SRC_DIR / 'src'))
 
 import pytest
 from pytest_bdd.parsers import re as step_parse
-from pytest_bdd import given, when, then
+from pytest_bdd import given, when, then, scenario
+from pytest_bdd.feature import get_features
 
 pytest.register_assert_rewrite('utils')
 
@@ -373,3 +375,57 @@ def check_place_missing_lines(db_conn, table, osm_type, osm_id, osm_class):
 
     with db_conn.cursor() as cur:
         assert cur.execute(sql, params).fetchone()[0] == 0
+
+
+if pytest.version_tuple >= (8, 0, 0):
+    def pytest_pycollect_makemodule(module_path, parent):
+        return BddTestCollector.from_parent(parent, path=module_path)
+
+
+class BddTestCollector(pytest.Module):
+
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
+
+    def collect(self):
+        for item in super().collect():
+            yield item
+
+        if hasattr(self.obj, 'PYTEST_BDD_SCENARIOS'):
+            for path in self.obj.PYTEST_BDD_SCENARIOS:
+                for feature in get_features([str(Path(self.path.parent, path).resolve())]):
+                    yield FeatureFile.from_parent(self,
+                                                  name=str(Path(path, feature.rel_filename)),
+                                                  path=Path(feature.filename),
+                                                  feature=feature)
+
+
+# borrowed from pytest-bdd: src/pytest_bdd/scenario.py
+def make_python_name(string: str) -> str:
+    """Make python attribute name out of a given string."""
+    string = re.sub(r"\W", "", string.replace(" ", "_"))
+    return re.sub(r"^\d+_*", "", string).lower()
+
+
+class FeatureFile(pytest.File):
+    class obj:
+        pass
+
+    def __init__(self, feature, **kwargs):
+        self.feature = feature
+        super().__init__(**kwargs)
+
+    def collect(self):
+        for sname, sobject in self.feature.scenarios.items():
+            class_name = f"L{sobject.line_number}"
+            test_name = "test_" + make_python_name(sname)
+
+            @scenario(self.feature.filename, sname)
+            def _test():
+                pass
+
+            tclass = type(class_name, (),
+                          {test_name: staticmethod(_test)})
+            setattr(self.obj, class_name, tclass)
+
+            yield pytest.Class.from_parent(self, name=class_name, obj=tclass)

test/bdd/features/db/query/reverse.feature

@@ -9,13 +9,32 @@ Feature: Reverse searches
         And the places
           | osm | class   | type       | geometry    |
           | W1  | aeroway | terminal   | (1,2,3,4,1) |
-          | N1  | amenity | restaurant | 9           |
+          | N9  | amenity | restaurant | 9           |
         When importing
         And reverse geocoding 1.0001,1.0001
         Then the result contains
          | object |
-         | N1  |
+         | N9  |
         When reverse geocoding 1.0003,1.0001
         Then the result contains
          | object |
          | W1  |
+
+
+    Scenario: Find closest housenumber for street matches
+        Given the 0.0001 grid with origin 1,1
+          |    | 1 |   |    |
+          |    |   | 2 |    |
+          | 10 |   |   | 11 |
+        And the places
+          | osm | class   | type     | name        | geometry |
+          | W1  | highway | service  | Goose Drive | 10,11    |
+          | N2  | tourism | art_work | Beauty      | 2        |
+        And the places
+          | osm | class | type  | housenr | geometry |
+          | N1  | place | house | 23      | 1        |
+        When importing
+        When reverse geocoding 1.0002,1.0002
+        Then the result contains
+          | object |
+          | N1 |

test/bdd/test_api.py

@@ -15,7 +15,7 @@ import xml.etree.ElementTree as ET
 
 import pytest
 from pytest_bdd.parsers import re as step_parse
-from pytest_bdd import scenarios, when, given, then
+from pytest_bdd import when, given, then
 
 from nominatim_db import cli
 from nominatim_db.config import Configuration
@@ -150,4 +150,8 @@ def parse_api_json_response(api_response, fmt, num):
     return result
 
 
-scenarios('features/api')
+if pytest.version_tuple >= (8, 0, 0):
+    PYTEST_BDD_SCENARIOS = ['features/api']
+else:
+    from pytest_bdd import scenarios
+    scenarios('features/api')

test/bdd/test_db.py

@@ -15,7 +15,7 @@ import re
 import psycopg
 
 import pytest
-from pytest_bdd import scenarios, when, then, given
+from pytest_bdd import when, then, given
 from pytest_bdd.parsers import re as step_parse
 
 from utils.place_inserter import PlaceColumn
@@ -276,4 +276,8 @@ def then_check_interpolation_table_negative(db_conn, oid):
         assert cur.fetchone()[0] == 0
 
 
-scenarios('features/db')
+if pytest.version_tuple >= (8, 0, 0):
+    PYTEST_BDD_SCENARIOS = ['features/db']
+else:
+    from pytest_bdd import scenarios
+    scenarios('features/db')

test/bdd/test_osm2pgsql.py

@@ -11,7 +11,7 @@ import asyncio
 import random
 
 import pytest
-from pytest_bdd import scenarios, when, then, given
+from pytest_bdd import when, then, given
 from pytest_bdd.parsers import re as step_parse
 
 from nominatim_db import cli
@@ -106,4 +106,8 @@ def check_place_content(db_conn, datatable, node_grid, table, exact):
     check_table_content(db_conn, table, datatable, grid=node_grid, exact=bool(exact))
 
 
-scenarios('features/osm2pgsql')
+if pytest.version_tuple >= (8, 0, 0):
+    PYTEST_BDD_SCENARIOS = ['features/osm2pgsql']
+else:
+    from pytest_bdd import scenarios
+    scenarios('features/osm2pgsql')

test/python/api/search/test_api_search_query.py

@@ -17,6 +17,9 @@ class MyToken(query.Token):
     def get_category(self):
         return 'this', 'that'
 
+    def get_country(self):
+        return 'cc'
+
 
 def mktoken(tid: int):
     return MyToken(penalty=3.0, token=tid, count=1, addr_count=1,

test/python/api/search/test_db_search_builder.py

@@ -2,12 +2,14 @@
 #
 # This file is part of Nominatim. (https://nominatim.org)
 #
-# Copyright (C) 2023 by the Nominatim developer community.
+# Copyright (C) 2025 by the Nominatim developer community.
 # For a full list of authors see the git log.
 """
 Tests for creating abstract searches from token assignments.
 """
+from typing import Optional
 import pytest
+import dataclasses
 
 from nominatim_api.search.query import Token, TokenRange, QueryStruct, Phrase
 import nominatim_api.search.query as qmod
@@ -17,10 +19,16 @@ from nominatim_api.types import SearchDetails
 import nominatim_api.search.db_searches as dbs
 
 
+@dataclasses.dataclass
 class MyToken(Token):
+    cc: Optional[str] = None
+
     def get_category(self):
         return 'this', 'that'
 
+    def get_country(self):
+        return self.cc
+
 
 def make_query(*args):
     q = QueryStruct([Phrase(qmod.PHRASE_ANY, '')])
@@ -30,18 +38,24 @@ def make_query(*args):
     q.add_node(qmod.BREAK_END, qmod.PHRASE_ANY)
 
     for start, tlist in enumerate(args):
-        for end, ttype, tinfo in tlist:
-            for tid, word in tinfo:
-                q.add_token(TokenRange(start, end), ttype,
-                            MyToken(penalty=0.5 if ttype == qmod.TOKEN_PARTIAL else 0.0,
-                                    token=tid, count=1, addr_count=1,
-                                    lookup_word=word))
+        for end, ttype, tinfos in tlist:
+            for tinfo in tinfos:
+                if isinstance(tinfo, tuple):
+                    q.add_token(TokenRange(start, end), ttype,
+                                MyToken(penalty=0.5 if ttype == qmod.TOKEN_PARTIAL else 0.0,
+                                        token=tinfo[0], count=1, addr_count=1,
+                                        lookup_word=tinfo[1]))
+                else:
+                    q.add_token(TokenRange(start, end), ttype, tinfo)
 
     return q
 
 
 def test_country_search():
-    q = make_query([(1, qmod.TOKEN_COUNTRY, [(2, 'de'), (3, 'en')])])
+    q = make_query([(1, qmod.TOKEN_COUNTRY, [
+        MyToken(penalty=0.0, token=2, count=1, addr_count=1, lookup_word='Germany', cc='de'),
+        MyToken(penalty=0.0, token=3, count=1, addr_count=1, lookup_word='UK', cc='en'),
+        ])])
     builder = SearchBuilder(q, SearchDetails())
 
     searches = list(builder.build(TokenAssignment(country=TokenRange(0, 1))))
@@ -55,7 +69,10 @@ def test_country_search():
 
 
 def test_country_search_with_country_restriction():
-    q = make_query([(1, qmod.TOKEN_COUNTRY, [(2, 'de'), (3, 'en')])])
+    q = make_query([(1, qmod.TOKEN_COUNTRY, [
+        MyToken(penalty=0.0, token=2, count=1, addr_count=1, lookup_word='Germany', cc='de'),
+        MyToken(penalty=0.0, token=3, count=1, addr_count=1, lookup_word='UK', cc='en'),
+    ])])
     builder = SearchBuilder(q, SearchDetails.from_kwargs({'countries': 'en,fr'}))
 
     searches = list(builder.build(TokenAssignment(country=TokenRange(0, 1))))
@@ -69,7 +86,10 @@ def test_country_search_with_country_restriction():
 
 
 def test_country_search_with_conflicting_country_restriction():
-    q = make_query([(1, qmod.TOKEN_COUNTRY, [(2, 'de'), (3, 'en')])])
+    q = make_query([(1, qmod.TOKEN_COUNTRY, [
+        MyToken(penalty=0.0, token=2, count=1, addr_count=1, lookup_word='Germany', cc='de'),
+        MyToken(penalty=0.0, token=3, count=1, addr_count=1, lookup_word='UK', cc='en'),
+    ])])
     builder = SearchBuilder(q, SearchDetails.from_kwargs({'countries': 'fr'}))
 
     searches = list(builder.build(TokenAssignment(country=TokenRange(0, 1))))
@@ -94,8 +114,11 @@ def test_postcode_search_simple():
 
 
 def test_postcode_with_country():
-    q = make_query([(1, qmod.TOKEN_POSTCODE, [(34, '2367')])],
-                   [(2, qmod.TOKEN_COUNTRY, [(1, 'xx')])])
+    q = make_query(
+        [(1, qmod.TOKEN_POSTCODE, [(34, '2367')])],
+        [(2, qmod.TOKEN_COUNTRY, [
+            MyToken(penalty=0.0, token=1, count=1, addr_count=1, lookup_word='none', cc='xx'),
+            ])])
     builder = SearchBuilder(q, SearchDetails())
 
     searches = list(builder.build(TokenAssignment(postcode=TokenRange(0, 1),

test/python/api/search/test_icu_query_analyzer.py

@@ -116,9 +116,11 @@ async def test_penalty_postcodes_and_housenumbers(conn, term, order):
 
     assert query.num_token_slots() == 1
 
-    torder = [(tl.tokens[0].penalty, tl.ttype) for tl in query.nodes[0].starting]
+    torder = [(min(t.penalty for t in tl.tokens), tl.ttype) for tl in query.nodes[0].starting]
     torder.sort()
 
+    print(torder)
+
     assert [t[1] for t in torder] == order
 
 

test/python/api/search/test_token_assignment.py

@@ -20,6 +20,9 @@ class MyToken(Token):
     def get_category(self):
         return 'this', 'that'
 
+    def get_country(self):
+        return 'cc'
+
 
 def make_query(*args):
     q = QueryStruct([Phrase(args[0][1], '')])

test/python/api/test_api_reverse.py

@@ -163,12 +163,12 @@ def test_reverse_housenumber_interpolation(apiobj, frontend, with_geom):
                       parent_place_id=990,
                       rank_search=30, rank_address=30,
                       housenumber='23',
-                      centroid=(10.0, 10.00002))
+                      centroid=(10.0, 10.0002))
     apiobj.add_osmline(place_id=992,
                        parent_place_id=990,
                        startnumber=1, endnumber=3, step=1,
-                       centroid=(10.0, 10.00001),
-                       geometry='LINESTRING(9.995 10.00001, 10.005 10.00001)')
+                       centroid=(10.0, 10.0001),
+                       geometry='LINESTRING(9.995 10.0001, 10.005 10.0001)')
     apiobj.add_placex(place_id=1990, class_='highway', type='service',
                       rank_search=27, rank_address=27,
                       name={'name': 'Other Street'},
@@ -177,8 +177,8 @@ def test_reverse_housenumber_interpolation(apiobj, frontend, with_geom):
     apiobj.add_osmline(place_id=1992,
                        parent_place_id=1990,
                        startnumber=1, endnumber=3, step=1,
-                       centroid=(10.0, 20.00001),
-                       geometry='LINESTRING(9.995 20.00001, 10.005 20.00001)')
+                       centroid=(10.0, 20.0001),
+                       geometry='LINESTRING(9.995 20.0001, 10.005 20.0001)')
 
     params = {'geometry_output': napi.GeometryFormat.TEXT} if with_geom else {}
 

test/python/api/test_api_search.py

@@ -99,7 +99,7 @@ def test_address_simple_places(apiobj, frontend, atype, address, search):
 
 
 def test_address_country(apiobj, frontend):
-    apiobj.add_word_table([(None, 'ro', 'C', 'ro', None)])
+    apiobj.add_word_table([(None, 'ro', 'C', 'ro', {'cc': 'ro'})])
     apiobj.add_country('ro', 'POLYGON((0 0, 0 1, 1 1, 1 0, 0 0))')
     apiobj.add_country_name('ro', {'name': 'România'})
 

test/python/mock_icu_word_table.py

@@ -10,6 +10,8 @@ of the table.
 """
 from nominatim_db.db.connection import execute_scalar
 
+from psycopg.types.json import Jsonb
+
 
 class MockIcuWordTable:
     """ A word table for testing using legacy word table structure.
@@ -42,11 +44,11 @@ class MockIcuWordTable:
                         """, (word_token, word, cls, typ, oper))
         self.conn.commit()
 
-    def add_country(self, country_code, word_token):
+    def add_country(self, country_code, word_token, lookup):
         with self.conn.cursor() as cur:
-            cur.execute("""INSERT INTO word (word_token, type, word)
-                           VALUES(%s, 'C', %s)""",
-                        (word_token, country_code))
+            cur.execute("""INSERT INTO word (word_token, type, word, info)
+                           VALUES(%s, 'C', %s, %s)""",
+                        (word_token, lookup, Jsonb({'cc': country_code})))
         self.conn.commit()
 
     def add_postcode(self, word_token, postcode):
@@ -93,7 +95,7 @@ class MockIcuWordTable:
 
     def get_country(self):
         with self.conn.cursor() as cur:
-            cur.execute("SELECT word, word_token FROM word WHERE type = 'C'")
+            cur.execute("SELECT info->>'cc', word_token, word FROM word WHERE type = 'C'")
             result = set((tuple(row) for row in cur))
             assert len(result) == cur.rowcount, "Word table has duplicates."
             return result

test/python/tokenizer/sanitizers/test_clean_postcodes.py

@@ -237,3 +237,9 @@ def test_postcode_default_pattern_pass(sanitize, postcode):
 @pytest.mark.sanitizer_params(convert_to_address=False, default_pattern='[A-Z0-9- ]{3,12}')
 def test_postcode_default_pattern_fail(sanitize, postcode):
     assert sanitize(country='an', postcode=postcode) == []
+
+
+@pytest.mark.parametrize("postcode", ('00000', '00-000', 'PL-00000', 'PL 00-000'))
+@pytest.mark.sanitizer_params(convert_to_address=False)
+def test_postcode_zeros(sanitize, postcode):
+    assert sanitize(country='pl', postcode=postcode) == []

test/python/tokenizer/test_icu.py

@@ -343,16 +343,18 @@ def test_add_country_names_new(analyzer, word_table):
     with analyzer() as anl:
         anl.add_country_names('es', {'name': 'Espagña', 'name:en': 'Spain'})
 
-    assert word_table.get_country() == {('es', 'ESPAGÑA'), ('es', 'SPAIN')}
+    assert word_table.get_country() == {('es', 'ESPAGÑA', 'Espagña'),
+                                        ('es', 'SPAIN', 'Spain')}
 
 
 def test_add_country_names_extend(analyzer, word_table):
-    word_table.add_country('ch', 'SCHWEIZ')
+    word_table.add_country('ch', 'SCHWEIZ', 'Schweiz')
 
     with analyzer() as anl:
         anl.add_country_names('ch', {'name': 'Schweiz', 'name:fr': 'Suisse'})
 
-    assert word_table.get_country() == {('ch', 'SCHWEIZ'), ('ch', 'SUISSE')}
+    assert word_table.get_country() == {('ch', 'SCHWEIZ', 'Schweiz'),
+                                        ('ch', 'SUISSE', 'Suisse')}
 
 
 class TestPlaceNames:
@@ -403,7 +405,7 @@ class TestPlaceNames:
         info = self.analyzer.process_place(place)
 
         self.expect_name_terms(info, '#norge', 'norge')
-        assert word_table.get_country() == {('no', 'NORGE')}
+        assert word_table.get_country() == {('no', 'NORGE', 'Norge')}
 
 
 class TestPlaceAddress:

test/python/tools/test_import_special_phrases.py

@@ -203,7 +203,7 @@ def test_import_phrases(monkeypatch, temp_db_cursor, def_config, sp_importer,
     placex_table.add(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']) == 18
+    assert len(tokenizer.analyser_cache['special_phrases']) == 19
 
     assert check_table_exist(temp_db_cursor, class_test, type_test)
     assert check_placeid_and_centroid_indexes(temp_db_cursor, class_test, type_test)

test/python/tools/test_sp_wiki_loader.py

@@ -54,4 +54,6 @@ def test_generate_phrases(sp_wiki_loader):
          ('Water near', 'amenity', 'drinking_water', 'near'),
          ('Embassy', 'amenity', 'embassy', '-'),
          ('Embassys', 'amenity', 'embassy', '-'),
-         ('Embassies', 'amenity', 'embassy', '-')}
+         ('Embassies', 'amenity', 'embassy', '-'),
+         # test for one-cell-per-line format
+         ('Coworkings near', 'amenity', 'coworking_space', 'near')}

test/testdata/special_phrases_test_content.txt

@@ -1,78 +1,120 @@
-<mediawiki xsi:schemaLocation="http://www.mediawiki.org/xml/export-0.11/ http://www.mediawiki.org/xml/export-0.11.xsd" version="0.11" xml:lang="en">
-<siteinfo>
-<sitename>OpenStreetMap Wiki</sitename>
-<dbname>wiki</dbname>
-<base>https://wiki.openstreetmap.org/wiki/Main_Page</base>
-<generator>MediaWiki 1.35.2</generator>
-<case>first-letter</case>
-<namespaces>
-<namespace key="-2" case="first-letter">Media</namespace>
-<namespace key="-1" case="first-letter">Special</namespace>
-<namespace key="0" case="first-letter"/>
-<namespace key="1" case="first-letter">Talk</namespace>
-<namespace key="2" case="first-letter">User</namespace>
-<namespace key="3" case="first-letter">User talk</namespace>
-<namespace key="4" case="first-letter">Wiki</namespace>
-<namespace key="5" case="first-letter">Wiki talk</namespace>
-<namespace key="6" case="first-letter">File</namespace>
-<namespace key="7" case="first-letter">File talk</namespace>
-<namespace key="8" case="first-letter">MediaWiki</namespace>
-<namespace key="9" case="first-letter">MediaWiki talk</namespace>
-<namespace key="10" case="first-letter">Template</namespace>
-<namespace key="11" case="first-letter">Template talk</namespace>
-<namespace key="12" case="first-letter">Help</namespace>
-<namespace key="13" case="first-letter">Help talk</namespace>
-<namespace key="14" case="first-letter">Category</namespace>
-<namespace key="15" case="first-letter">Category talk</namespace>
-<namespace key="120" case="first-letter">Item</namespace>
-<namespace key="121" case="first-letter">Item talk</namespace>
-<namespace key="122" case="first-letter">Property</namespace>
-<namespace key="123" case="first-letter">Property talk</namespace>
-<namespace key="200" case="first-letter">DE</namespace>
-<namespace key="201" case="first-letter">DE talk</namespace>
-<namespace key="202" case="first-letter">FR</namespace>
-<namespace key="203" case="first-letter">FR talk</namespace>
-<namespace key="204" case="first-letter">ES</namespace>
-<namespace key="205" case="first-letter">ES talk</namespace>
-<namespace key="206" case="first-letter">IT</namespace>
-<namespace key="207" case="first-letter">IT talk</namespace>
-<namespace key="208" case="first-letter">NL</namespace>
-<namespace key="209" case="first-letter">NL talk</namespace>
-<namespace key="210" case="first-letter">RU</namespace>
-<namespace key="211" case="first-letter">RU talk</namespace>
-<namespace key="212" case="first-letter">JA</namespace>
-<namespace key="213" case="first-letter">JA talk</namespace>
-<namespace key="710" case="first-letter">TimedText</namespace>
-<namespace key="711" case="first-letter">TimedText talk</namespace>
-<namespace key="828" case="first-letter">Module</namespace>
-<namespace key="829" case="first-letter">Module talk</namespace>
-<namespace key="2300" case="first-letter">Gadget</namespace>
-<namespace key="2301" case="first-letter">Gadget talk</namespace>
-<namespace key="2302" case="case-sensitive">Gadget definition</namespace>
-<namespace key="2303" case="case-sensitive">Gadget definition talk</namespace>
-</namespaces>
-</siteinfo>
-<page>
-<title>Nominatim/Special Phrases/EN</title>
-<ns>0</ns>
-<id>67365</id>
-<revision>
-<id>2100424</id>
-<parentid>2100422</parentid>
-<timestamp>2021-01-27T20:29:53Z</timestamp>
-<contributor>
-<username>Violaine Do</username>
-<id>88152</id>
-</contributor>
-<minor/>
-<comment>/* en */ add coworking amenity</comment>
-<origin>2100424</origin>
-<model>wikitext</model>
-<format>text/x-wiki</format>
-<text bytes="158218" sha1="cst5x7tt58izti1pxzgljf27tx8qjcj" xml:space="preserve">
-== en == {| class="wikitable sortable" |- ! Word / Phrase !! Key !! Value !! Operator !! Plural |- | Zip Line || aerialway || zip_line || - || N |- | Zip Lines || aerialway || zip_line || - || Y |- | Zip Line in || aerialway || zip_line || in || N |- | Zip Lines in || aerialway || zip_line || in || Y |- | Zip Line near || aerialway || zip_line || near || N |- | Animal shelter || amenity || animal_shelter || - || N |- | Animal shelters || amenity || animal_shelter || - || Y |- | Animal shelter in || amenity || animal_shelter || in || N |- | Animal shelters in || amenity || animal_shelter || in || Y |- | Animal shelter near || amenity || animal_shelter || near|| N |- | Animal shelters near || amenity || animal_shelter || NEAR|| Y |- | Drinking Water near || amenity || drinking_water || near || N |- | Water || amenity || drinking_water || - || N |- | Water in || amenity || drinking_water || In || N |- | Water near || amenity || drinking_water || near || N |- | Embassy || amenity || embassy || - || N |- | Embassys || amenity || "embassy" || - || Y |- | Embassies || amenity || embassy || - || Y |- |Coworkings near |amenity |coworking_space |near |Y |} [[Category:Word list]]
-</text>
-<sha1>cst5x7tt58izti1pxzgljf27tx8qjcj</sha1>
-</revision>
-</page>
+<mediawiki xmlns="http://www.mediawiki.org/xml/export-0.11/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.mediawiki.org/xml/export-0.11/ http://www.mediawiki.org/xml/export-0.11.xsd" version="0.11" xml:lang="en">
+  <siteinfo>
+    <sitename>OpenStreetMap Wiki</sitename>
+    <dbname>wiki</dbname>
+    <base>https://wiki.openstreetmap.org/wiki/Main_Page</base>
+    <generator>MediaWiki 1.43.5</generator>
+    <case>first-letter</case>
+    <namespaces>
+      <namespace key="-2" case="first-letter">Media</namespace>
+      <namespace key="-1" case="first-letter">Special</namespace>
+      <namespace key="0" case="first-letter"/>
+      <namespace key="1" case="first-letter">Talk</namespace>
+      <namespace key="2" case="first-letter">User</namespace>
+      <namespace key="3" case="first-letter">User talk</namespace>
+      <namespace key="4" case="first-letter">Wiki</namespace>
+      <namespace key="5" case="first-letter">Wiki talk</namespace>
+      <namespace key="6" case="first-letter">File</namespace>
+      <namespace key="7" case="first-letter">File talk</namespace>
+      <namespace key="8" case="first-letter">MediaWiki</namespace>
+      <namespace key="9" case="first-letter">MediaWiki talk</namespace>
+      <namespace key="10" case="first-letter">Template</namespace>
+      <namespace key="11" case="first-letter">Template talk</namespace>
+      <namespace key="12" case="first-letter">Help</namespace>
+      <namespace key="13" case="first-letter">Help talk</namespace>
+      <namespace key="14" case="first-letter">Category</namespace>
+      <namespace key="15" case="first-letter">Category talk</namespace>
+      <namespace key="120" case="first-letter">Item</namespace>
+      <namespace key="121" case="first-letter">Item talk</namespace>
+      <namespace key="122" case="first-letter">Property</namespace>
+      <namespace key="123" case="first-letter">Property talk</namespace>
+      <namespace key="200" case="first-letter">DE</namespace>
+      <namespace key="201" case="first-letter">DE talk</namespace>
+      <namespace key="202" case="first-letter">FR</namespace>
+      <namespace key="203" case="first-letter">FR talk</namespace>
+      <namespace key="204" case="first-letter">ES</namespace>
+      <namespace key="205" case="first-letter">ES talk</namespace>
+      <namespace key="206" case="first-letter">IT</namespace>
+      <namespace key="207" case="first-letter">IT talk</namespace>
+      <namespace key="208" case="first-letter">NL</namespace>
+      <namespace key="209" case="first-letter">NL talk</namespace>
+      <namespace key="210" case="first-letter">RU</namespace>
+      <namespace key="211" case="first-letter">RU talk</namespace>
+      <namespace key="212" case="first-letter">JA</namespace>
+      <namespace key="213" case="first-letter">JA talk</namespace>
+      <namespace key="710" case="first-letter">TimedText</namespace>
+      <namespace key="711" case="first-letter">TimedText talk</namespace>
+      <namespace key="828" case="first-letter">Module</namespace>
+      <namespace key="829" case="first-letter">Module talk</namespace>
+      <namespace key="3000" case="first-letter">Proposal</namespace>
+      <namespace key="3001" case="first-letter">Proposal talk</namespace>
+    </namespaces>
+  </siteinfo>
+  <page>
+    <title>Nominatim/Special Phrases/EN</title>
+    <ns>0</ns>
+    <id>67365</id>
+    <revision>
+      <id>2861977</id>
+      <parentid>2634159</parentid>
+      <timestamp>2025-06-02T14:00:52Z</timestamp>
+      <contributor>
+        <username>Lonvia</username>
+        <id>17191</id>
+      </contributor>
+      <comment>overgeneralized entry removed, phrases need to chosen so that all results with the given tag can be described with that phrase</comment>
+      <origin>2861977</origin>
+      <model>wikitext</model>
+      <format>text/x-wiki</format>
+      <text bytes="160765" sha1="0zlpuvnjs4io9e006rntbxm5b84kgst" xml:space="preserve">== en ==
+{| class="wikitable sortable"
+|-
+! Word / Phrase !! Key !! Value !! Operator !! Plural
+|-
+| Zip Line || aerialway || zip_line || - || N
+|-
+| Zip Lines || aerialway || zip_line || - || Y
+|-
+| Zip Line in || aerialway || zip_line || in || N
+|-
+| Zip Lines in || aerialway || zip_line || in || Y
+|-
+| Zip Line near || aerialway || zip_line || near || N
+|-
+| Animal shelter || amenity || animal_shelter || - || N
+|-
+| Animal shelters || amenity || animal_shelter || - || Y
+|-
+| Animal shelter in || amenity || animal_shelter || in || N
+|-
+| Animal shelters in || amenity || animal_shelter || in || Y
+|-
+| Animal shelter near || amenity || animal_shelter || near|| N
+|-
+| Animal shelters near || amenity || animal_shelter || NEAR|| Y
+|-
+| Drinking Water near || amenity || drinking_water || near || N
+|-
+| Water || amenity || drinking_water || - || N
+|-
+| Water in || amenity || drinking_water || In || N
+|-
+| Water near || amenity || drinking_water || near || N
+|-
+| Embassy || amenity || embassy || - || N
+|-
+| Embassys || amenity || "embassy" || - || Y
+|-
+| Embassies || amenity || embassy || - || Y
+|-
+| Coworkings near
+| amenity
+| coworking_space
+| near
+| Y
+|}
+[[Category:Word list]]</text>
+      <sha1>0zlpuvnjs4io9e006rntbxm5b84kgst</sha1>
+    </revision>
+  </page>
 </mediawiki>