Merge pull request #3385 from mtmail/docs-reverse-only

[nominatim.git] / nominatim / api / search / db_searches.py

diff --git a/nominatim/api/search/db_searches.py b/nominatim/api/search/db_searches.py
index a5461d6ad105fd4845955ffdeb6947dddcc12845..d74812e682a3453a55ea209c83ebf22a61e75a31 100644 (file)
--- a/nominatim/api/search/db_searches.py
+++ b/nominatim/api/search/db_searches.py
@@ -5,13 +5,12 @@
 # Copyright (C) 2023 by the Nominatim developer community.
 # For a full list of authors see the git log.
 """
 # Copyright (C) 2023 by the Nominatim developer community.
 # For a full list of authors see the git log.
 """

-Implementation of the acutal database accesses for forward search.
+Implementation of the actual database accesses for forward search.

 """
 """

-from typing import List, Tuple, AsyncIterator, Dict, Any, Callable
+from typing import List, Tuple, AsyncIterator, Dict, Any, Callable, cast

 import abc
 
 import sqlalchemy as sa
 import abc
 
 import sqlalchemy as sa

-from sqlalchemy.dialects.postgresql import array_agg

 
 from nominatim.typing import SaFromClause, SaScalarSelect, SaColumn, \
                              SaExpression, SaSelect, SaLambdaSelect, SaRow, SaBind
 
 from nominatim.typing import SaFromClause, SaScalarSelect, SaColumn, \
                              SaExpression, SaSelect, SaLambdaSelect, SaRow, SaBind


@@ -19,7 +18,7 @@ from nominatim.api.connection import SearchConnection
 from nominatim.api.types import SearchDetails, DataLayer, GeometryFormat, Bbox
 import nominatim.api.results as nres
 from nominatim.api.search.db_search_fields import SearchData, WeightedCategories
 from nominatim.api.types import SearchDetails, DataLayer, GeometryFormat, Bbox
 import nominatim.api.results as nres
 from nominatim.api.search.db_search_fields import SearchData, WeightedCategories

-from nominatim.db.sqlalchemy_types import Geometry
+from nominatim.db.sqlalchemy_types import Geometry, IntArray

 
 #pylint: disable=singleton-comparison,not-callable
 #pylint: disable=too-many-branches,too-many-arguments,too-many-locals,too-many-statements
 
 #pylint: disable=singleton-comparison,not-callable
 #pylint: disable=too-many-branches,too-many-arguments,too-many-locals,too-many-statements


@@ -110,7 +109,7 @@ def _add_geometry_columns(sql: SaLambdaSelect, col: SaColumn, details: SearchDet
 
 def _make_interpolation_subquery(table: SaFromClause, inner: SaFromClause,
                                  numerals: List[int], details: SearchDetails) -> SaScalarSelect:
 
 def _make_interpolation_subquery(table: SaFromClause, inner: SaFromClause,
                                  numerals: List[int], details: SearchDetails) -> SaScalarSelect:

-    all_ids = array_agg(table.c.place_id) # type: ignore[no-untyped-call]
+    all_ids = sa.func.ArrayAgg(table.c.place_id)

     sql = sa.select(all_ids).where(table.c.parent_place_id == inner.c.place_id)
 
     if len(numerals) == 1:
     sql = sa.select(all_ids).where(table.c.parent_place_id == inner.c.place_id)
 
     if len(numerals) == 1:


@@ -134,9 +133,7 @@ def _filter_by_layer(table: SaFromClause, layers: DataLayer) -> SaColumn:
         orexpr.append(no_index(table.c.rank_address).between(1, 30))
     elif layers & DataLayer.ADDRESS:
         orexpr.append(no_index(table.c.rank_address).between(1, 29))
         orexpr.append(no_index(table.c.rank_address).between(1, 30))
     elif layers & DataLayer.ADDRESS:
         orexpr.append(no_index(table.c.rank_address).between(1, 29))

-        orexpr.append(sa.and_(no_index(table.c.rank_address) == 30,
-                              sa.or_(table.c.housenumber != None,
-                                     table.c.address.has_key('addr:housename'))))
+        orexpr.append(sa.func.IsAddressPoint(table))

     elif layers & DataLayer.POI:
         orexpr.append(sa.and_(no_index(table.c.rank_address) == 30,
                               table.c.class_.not_in(('place', 'building'))))
     elif layers & DataLayer.POI:
         orexpr.append(sa.and_(no_index(table.c.rank_address) == 30,
                               table.c.class_.not_in(('place', 'building'))))


@@ -188,12 +185,21 @@ async def _get_placex_housenumbers(conn: SearchConnection,
         yield result
 
 
         yield result
 
 

+def _int_list_to_subquery(inp: List[int]) -> 'sa.Subquery':
+    """ Create a subselect that returns the given list of integers
+        as rows in the column 'nr'.
+    """
+    vtab = sa.func.JsonArrayEach(sa.type_coerce(inp, sa.JSON))\
+               .table_valued(sa.column('value', type_=sa.JSON))
+    return sa.select(sa.cast(sa.cast(vtab.c.value, sa.Text), sa.Integer).label('nr')).subquery()
+
+

 async def _get_osmline(conn: SearchConnection, place_ids: List[int],
                        numerals: List[int],
                        details: SearchDetails) -> AsyncIterator[nres.SearchResult]:
     t = conn.t.osmline
 async def _get_osmline(conn: SearchConnection, place_ids: List[int],
                        numerals: List[int],
                        details: SearchDetails) -> AsyncIterator[nres.SearchResult]:
     t = conn.t.osmline

-    values = sa.values(sa.Column('nr', sa.Integer()), name='housenumber')\
-               .data([(n,) for n in numerals])
+
+    values = _int_list_to_subquery(numerals)

     sql = sa.select(t.c.place_id, t.c.osm_id,
                     t.c.parent_place_id, t.c.address,
                     values.c.nr.label('housenumber'),
     sql = sa.select(t.c.place_id, t.c.osm_id,
                     t.c.parent_place_id, t.c.address,
                     values.c.nr.label('housenumber'),


@@ -216,8 +222,7 @@ async def _get_tiger(conn: SearchConnection, place_ids: List[int],
                      numerals: List[int], osm_id: int,
                      details: SearchDetails) -> AsyncIterator[nres.SearchResult]:
     t = conn.t.tiger
                      numerals: List[int], osm_id: int,
                      details: SearchDetails) -> AsyncIterator[nres.SearchResult]:
     t = conn.t.tiger

-    values = sa.values(sa.Column('nr', sa.Integer()), name='housenumber')\
-               .data([(n,) for n in numerals])
+    values = _int_list_to_subquery(numerals)

     sql = sa.select(t.c.place_id, t.c.parent_place_id,
                     sa.literal('W').label('osm_type'),
                     sa.literal(osm_id).label('osm_id'),
     sql = sa.select(t.c.place_id, t.c.parent_place_id,
                     sa.literal('W').label('osm_type'),
                     sa.literal(osm_id).label('osm_id'),


@@ -240,6 +245,7 @@ async def _get_tiger(conn: SearchConnection, place_ids: List[int],
 class AbstractSearch(abc.ABC):
     """ Encapuslation of a single lookup in the database.
     """
 class AbstractSearch(abc.ABC):
     """ Encapuslation of a single lookup in the database.
     """

+    SEARCH_PRIO: int = 2

 
     def __init__(self, penalty: float) -> None:
         self.penalty = penalty
 
     def __init__(self, penalty: float) -> None:
         self.penalty = penalty


@@ -312,7 +318,7 @@ class NearSearch(AbstractSearch):
 
         if table is None:
             # No classtype table available, do a simplified lookup in placex.
 
         if table is None:
             # No classtype table available, do a simplified lookup in placex.

-            table = conn.t.placex.alias('inner')
+            table = conn.t.placex

             sql = sa.select(table.c.place_id,
                             sa.func.min(tgeom.c.centroid.ST_Distance(table.c.centroid))
                               .label('dist'))\
             sql = sa.select(table.c.place_id,
                             sa.func.min(tgeom.c.centroid.ST_Distance(table.c.centroid))
                               .label('dist'))\


@@ -443,6 +449,8 @@ class PoiSearch(AbstractSearch):
 class CountrySearch(AbstractSearch):
     """ Search for a country name or country code.
     """
 class CountrySearch(AbstractSearch):
     """ Search for a country name or country code.
     """

+    SEARCH_PRIO = 0
+

     def __init__(self, sdata: SearchData) -> None:
         super().__init__(sdata.penalty)
         self.countries = sdata.countries
     def __init__(self, sdata: SearchData) -> None:
         super().__init__(sdata.penalty)
         self.countries = sdata.countries


@@ -476,7 +484,14 @@ class CountrySearch(AbstractSearch):
             result.bbox = Bbox.from_wkb(row.bbox)
             results.append(result)
 
             result.bbox = Bbox.from_wkb(row.bbox)
             results.append(result)
 

-        return results or await self.lookup_in_country_table(conn, details)
+        if not results:
+            results = await self.lookup_in_country_table(conn, details)
+
+        if results:
+            details.min_rank = min(5, details.max_rank)
+            details.max_rank = min(25, details.max_rank)
+
+        return results

 
 
     async def lookup_in_country_table(self, conn: SearchConnection,
 
 
     async def lookup_in_country_table(self, conn: SearchConnection,


@@ -573,7 +588,8 @@ class PostcodeSearch(AbstractSearch):
             tsearch = conn.t.search_name
             sql = sql.where(tsearch.c.place_id == t.c.parent_place_id)\
                      .where((tsearch.c.name_vector + tsearch.c.nameaddress_vector)
             tsearch = conn.t.search_name
             sql = sql.where(tsearch.c.place_id == t.c.parent_place_id)\
                      .where((tsearch.c.name_vector + tsearch.c.nameaddress_vector)

-                                     .contains(self.lookups[0].tokens))
+                                     .contains(sa.type_coerce(self.lookups[0].tokens,
+                                                              IntArray)))

 
         for ranking in self.rankings:
             penalty += ranking.sql_penalty(conn.t.search_name)
 
         for ranking in self.rankings:
             penalty += ranking.sql_penalty(conn.t.search_name)


@@ -586,10 +602,28 @@ class PostcodeSearch(AbstractSearch):
 
         results = nres.SearchResults()
         for row in await conn.execute(sql, _details_to_bind_params(details)):
 
         results = nres.SearchResults()
         for row in await conn.execute(sql, _details_to_bind_params(details)):

-            result = nres.create_from_postcode_row(row, nres.SearchResult)
+            p = conn.t.placex
+            placex_sql = _select_placex(p).add_columns(p.c.importance)\
+                             .where(sa.text("""class = 'boundary'
+                                               AND type = 'postal_code'
+                                               AND osm_type = 'R'"""))\
+                             .where(p.c.country_code == row.country_code)\
+                             .where(p.c.postcode == row.postcode)\
+                             .limit(1)
+
+            if details.geometry_output:
+                placex_sql = _add_geometry_columns(placex_sql, p.c.geometry, details)
+
+            for prow in await conn.execute(placex_sql, _details_to_bind_params(details)):
+                result = nres.create_from_placex_row(prow, nres.SearchResult)
+                break
+            else:
+                result = nres.create_from_postcode_row(row, nres.SearchResult)
+

             assert result
             assert result

-            result.accuracy = row.accuracy
-            results.append(result)
+            if result.place_id not in details.excluded:
+                result.accuracy = row.accuracy
+                results.append(result)

 
         return results
 
 
         return results
 


@@ -598,6 +632,8 @@ class PostcodeSearch(AbstractSearch):
 class PlaceSearch(AbstractSearch):
     """ Generic search for an address or named place.
     """
 class PlaceSearch(AbstractSearch):
     """ Generic search for an address or named place.
     """

+    SEARCH_PRIO = 1
+

     def __init__(self, extra_penalty: float, sdata: SearchData, expected_count: int) -> None:
         super().__init__(sdata.penalty + extra_penalty)
         self.countries = sdata.countries
     def __init__(self, extra_penalty: float, sdata: SearchData, expected_count: int) -> None:
         super().__init__(sdata.penalty + extra_penalty)
         self.countries = sdata.countries


@@ -609,104 +645,152 @@ class PlaceSearch(AbstractSearch):
         self.expected_count = expected_count
 
 
         self.expected_count = expected_count
 
 

-    async def lookup(self, conn: SearchConnection,
-                     details: SearchDetails) -> nres.SearchResults:
-        """ Find results for the search in the database.
+    def _inner_search_name_cte(self, conn: SearchConnection,
+                               details: SearchDetails) -> 'sa.CTE':
+        """ Create a subquery that preselects the rows in the search_name
+            table.

         """
         """

-        t = conn.t.placex
-        tsearch = conn.t.search_name
-
-        sql: SaLambdaSelect = sa.lambda_stmt(lambda:
-                  _select_placex(t).where(t.c.place_id == tsearch.c.place_id))
-
-
-        if details.geometry_output:
-            sql = _add_geometry_columns(sql, t.c.geometry, details)
+        t = conn.t.search_name

 
         penalty: SaExpression = sa.literal(self.penalty)
         for ranking in self.rankings:
 
         penalty: SaExpression = sa.literal(self.penalty)
         for ranking in self.rankings:

-            penalty += ranking.sql_penalty(tsearch)
+            penalty += ranking.sql_penalty(t)
+
+        sql = sa.select(t.c.place_id, t.c.search_rank, t.c.address_rank,
+                        t.c.country_code, t.c.centroid,
+                        t.c.name_vector, t.c.nameaddress_vector,
+                        sa.case((t.c.importance > 0, t.c.importance),
+                                else_=0.40001-(sa.cast(t.c.search_rank, sa.Float())/75))
+                          .label('importance'),
+                        penalty.label('penalty'))

 
         for lookup in self.lookups:
 
         for lookup in self.lookups:

-            sql = sql.where(lookup.sql_condition(tsearch))
+            sql = sql.where(lookup.sql_condition(t))

 
         if self.countries:
 
         if self.countries:

-            sql = sql.where(tsearch.c.country_code.in_(self.countries.values))
+            sql = sql.where(t.c.country_code.in_(self.countries.values))

 
         if self.postcodes:
             # if a postcode is given, don't search for state or country level objects
 
         if self.postcodes:
             # if a postcode is given, don't search for state or country level objects

-            sql = sql.where(tsearch.c.address_rank > 9)
-            tpc = conn.t.postcode
-            pcs = self.postcodes.values
-            if self.expected_count > 5000:
+            sql = sql.where(t.c.address_rank > 9)
+            if self.expected_count > 10000:

                 # Many results expected. Restrict by postcode.
                 # Many results expected. Restrict by postcode.

+                tpc = conn.t.postcode

                 sql = sql.where(sa.select(tpc.c.postcode)
                 sql = sql.where(sa.select(tpc.c.postcode)

-                                  .where(tpc.c.postcode.in_(pcs))
-                                  .where(tsearch.c.centroid.within_distance(tpc.c.geometry, 0.12))
+                                  .where(tpc.c.postcode.in_(self.postcodes.values))
+                                  .where(t.c.centroid.within_distance(tpc.c.geometry, 0.4))

                                   .exists())
 
                                   .exists())
 

-            # Less results, only have a preference for close postcodes
-            pc_near = sa.select(sa.func.min(tpc.c.geometry.ST_Distance(tsearch.c.centroid)))\
+        if details.viewbox is not None:
+            if details.bounded_viewbox:
+                sql = sql.where(t.c.centroid
+                                   .intersects(VIEWBOX_PARAM,
+                                               use_index=details.viewbox.area < 0.2))
+            elif not self.postcodes and not self.housenumbers and self.expected_count >= 10000:
+                sql = sql.where(t.c.centroid
+                                   .intersects(VIEWBOX2_PARAM,
+                                               use_index=details.viewbox.area < 0.5))
+
+        if details.near is not None and details.near_radius is not None:
+            if details.near_radius < 0.1:
+                sql = sql.where(t.c.centroid.within_distance(NEAR_PARAM,
+                                                             NEAR_RADIUS_PARAM))
+            else:
+                sql = sql.where(t.c.centroid
+                                   .ST_Distance(NEAR_PARAM) <  NEAR_RADIUS_PARAM)
+
+        if self.housenumbers:
+            sql = sql.where(t.c.address_rank.between(16, 30))
+        else:
+            if details.excluded:
+                sql = sql.where(_exclude_places(t))
+            if details.min_rank > 0:
+                sql = sql.where(sa.or_(t.c.address_rank >= MIN_RANK_PARAM,
+                                       t.c.search_rank >= MIN_RANK_PARAM))
+            if details.max_rank < 30:
+                sql = sql.where(sa.or_(t.c.address_rank <= MAX_RANK_PARAM,
+                                       t.c.search_rank <= MAX_RANK_PARAM))
+
+        inner = sql.limit(10000).order_by(sa.desc(sa.text('importance'))).subquery()
+
+        sql = sa.select(inner.c.place_id, inner.c.search_rank, inner.c.address_rank,
+                        inner.c.country_code, inner.c.centroid, inner.c.importance,
+                        inner.c.penalty)
+
+        # If the query is not an address search or has a geographic preference,
+        # preselect most important items to restrict the number of places
+        # that need to be looked up in placex.
+        if not self.housenumbers\
+           and (details.viewbox is None or details.bounded_viewbox)\
+           and (details.near is None or details.near_radius is not None)\
+           and not self.qualifiers:
+            sql = sql.add_columns(sa.func.first_value(inner.c.penalty - inner.c.importance)
+                                       .over(order_by=inner.c.penalty - inner.c.importance)
+                                       .label('min_penalty'))
+
+            inner = sql.subquery()
+
+            sql = sa.select(inner.c.place_id, inner.c.search_rank, inner.c.address_rank,
+                            inner.c.country_code, inner.c.centroid, inner.c.importance,
+                            inner.c.penalty)\
+                    .where(inner.c.penalty - inner.c.importance < inner.c.min_penalty + 0.5)
+
+        return sql.cte('searches')
+
+
+    async def lookup(self, conn: SearchConnection,
+                     details: SearchDetails) -> nres.SearchResults:
+        """ Find results for the search in the database.
+        """
+        t = conn.t.placex
+        tsearch = self._inner_search_name_cte(conn, details)
+
+        sql = _select_placex(t).join(tsearch, t.c.place_id == tsearch.c.place_id)
+
+        if details.geometry_output:
+            sql = _add_geometry_columns(sql, t.c.geometry, details)
+
+        penalty: SaExpression = tsearch.c.penalty
+
+        if self.postcodes:
+            tpc = conn.t.postcode
+            pcs = self.postcodes.values
+
+            pc_near = sa.select(sa.func.min(tpc.c.geometry.ST_Distance(t.c.centroid)))\

                       .where(tpc.c.postcode.in_(pcs))\
                       .scalar_subquery()
             penalty += sa.case((t.c.postcode.in_(pcs), 0.0),
                       .where(tpc.c.postcode.in_(pcs))\
                       .scalar_subquery()
             penalty += sa.case((t.c.postcode.in_(pcs), 0.0),

-                               else_=sa.func.coalesce(pc_near, 2.0))
+                               else_=sa.func.coalesce(pc_near, cast(SaColumn, 2.0)))

 
 

-        if details.viewbox is not None:
-            if details.bounded_viewbox:
-                sql = sql.where(tsearch.c.centroid
-                                         .intersects(VIEWBOX_PARAM,
-                                                     use_index=details.viewbox.area < 0.2))
-            elif self.expected_count >= 10000:
-                sql = sql.where(tsearch.c.centroid
-                                         .intersects(VIEWBOX2_PARAM,
-                                                     use_index=details.viewbox.area < 0.5))
-            else:
-                penalty += sa.case((t.c.geometry.intersects(VIEWBOX_PARAM, use_index=False), 0.0),
-                                   (t.c.geometry.intersects(VIEWBOX2_PARAM, use_index=False), 0.5),
-                                   else_=1.0)
+        if details.viewbox is not None and not details.bounded_viewbox:
+            penalty += sa.case((t.c.geometry.intersects(VIEWBOX_PARAM, use_index=False), 0.0),
+                               (t.c.geometry.intersects(VIEWBOX2_PARAM, use_index=False), 0.5),
+                               else_=1.0)

 
         if details.near is not None:
 
         if details.near is not None:

-            if details.near_radius is not None:
-                if details.near_radius < 0.1:
-                    sql = sql.where(tsearch.c.centroid.within_distance(NEAR_PARAM,
-                                                                       NEAR_RADIUS_PARAM))
-                else:
-                    sql = sql.where(tsearch.c.centroid
-                                             .ST_Distance(NEAR_PARAM) <  NEAR_RADIUS_PARAM)

             sql = sql.add_columns((-tsearch.c.centroid.ST_Distance(NEAR_PARAM))
                                       .label('importance'))
             sql = sql.order_by(sa.desc(sa.text('importance')))
         else:
             sql = sql.add_columns((-tsearch.c.centroid.ST_Distance(NEAR_PARAM))
                                       .label('importance'))
             sql = sql.order_by(sa.desc(sa.text('importance')))
         else:

-            if self.expected_count < 10000\
-               or (details.viewbox is not None and details.viewbox.area < 0.5):
-                sql = sql.order_by(
-                        penalty - sa.case((tsearch.c.importance > 0, tsearch.c.importance),
-                                    else_=0.75001-(sa.cast(tsearch.c.search_rank, sa.Float())/40)))
-            sql = sql.add_columns(t.c.importance)
+            sql = sql.order_by(penalty - tsearch.c.importance)
+            sql = sql.add_columns(tsearch.c.importance)

 
 
 
 

-        sql = sql.add_columns(penalty.label('accuracy'))
-
-        if self.expected_count < 10000:
-            sql = sql.order_by(sa.text('accuracy'))
+        sql = sql.add_columns(penalty.label('accuracy'))\
+                 .order_by(sa.text('accuracy'))

 
         if self.housenumbers:
 
         if self.housenumbers:

-            hnr_regexp = f"\\m({'|'.join(self.housenumbers.values)})\\M"
-            sql = sql.where(tsearch.c.address_rank.between(16, 30))\
-                     .where(sa.or_(tsearch.c.address_rank < 30,
-                                   t.c.housenumber.op('~*')(hnr_regexp)))
-
-            # Cross check for housenumbers, need to do that on a rather large
-            # set. Worst case there are 40.000 main streets in OSM.
-            inner = sql.limit(10000).subquery()
+            hnr_list = '|'.join(self.housenumbers.values)
+            inner = sql.where(sa.or_(tsearch.c.address_rank < 30,
+                                     sa.func.RegexpWord(hnr_list, t.c.housenumber)))\
+                       .subquery()

 
             # Housenumbers from placex
             thnr = conn.t.placex.alias('hnr')
 
             # Housenumbers from placex
             thnr = conn.t.placex.alias('hnr')

-            pid_list = array_agg(thnr.c.place_id) # type: ignore[no-untyped-call]
+            pid_list = sa.func.ArrayAgg(thnr.c.place_id)

             place_sql = sa.select(pid_list)\
                           .where(thnr.c.parent_place_id == inner.c.place_id)\
             place_sql = sa.select(pid_list)\
                           .where(thnr.c.parent_place_id == inner.c.place_id)\

-                          .where(thnr.c.housenumber.op('~*')(hnr_regexp))\
+                          .where(sa.func.RegexpWord(hnr_list, thnr.c.housenumber))\

                           .where(thnr.c.linked_place_id == None)\
                           .where(thnr.c.indexed_status == 0)
 
                           .where(thnr.c.linked_place_id == None)\
                           .where(thnr.c.indexed_status == 0)
 


@@ -747,14 +831,6 @@ class PlaceSearch(AbstractSearch):
                      .where(t.c.indexed_status == 0)
             if self.qualifiers:
                 sql = sql.where(self.qualifiers.sql_restrict(t))
                      .where(t.c.indexed_status == 0)
             if self.qualifiers:
                 sql = sql.where(self.qualifiers.sql_restrict(t))

-            if details.excluded:
-                sql = sql.where(_exclude_places(tsearch))
-            if details.min_rank > 0:
-                sql = sql.where(sa.or_(tsearch.c.address_rank >= MIN_RANK_PARAM,
-                                       tsearch.c.search_rank >= MIN_RANK_PARAM))
-            if details.max_rank < 30:
-                sql = sql.where(sa.or_(tsearch.c.address_rank <= MAX_RANK_PARAM,
-                                       tsearch.c.search_rank <= MAX_RANK_PARAM))

             if details.layers is not None:
                 sql = sql.where(_filter_by_layer(t, details.layers))
 
             if details.layers is not None:
                 sql = sql.where(_filter_by_layer(t, details.layers))