Merge remote-tracking branch 'upstream/master'

[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 5c1d98c9a60b611b38d96b0c6cb636132f0b4715..1f7eb0093a6bc8245bbe3b422084e4bcd25d73fd 100644 (file)
--- a/nominatim/api/search/db_searches.py
+++ b/nominatim/api/search/db_searches.py
@@ -111,7 +111,7 @@ def _filter_by_layer(table: SaFromClause, layers: DataLayer) -> SaColumn:
         orexpr.append(table.c.rank_address.between(1, 29))
         orexpr.append(sa.and_(table.c.rank_address == 30,
                               sa.or_(table.c.housenumber != None,
         orexpr.append(table.c.rank_address.between(1, 29))
         orexpr.append(sa.and_(table.c.rank_address == 30,
                               sa.or_(table.c.housenumber != None,

-                                     table.c.address.has_key('housename'))))
+                                     table.c.address.has_key('addr:housename'))))

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


@@ -271,7 +271,7 @@ class NearSearch(AbstractSearch):
         """
         table = await conn.get_class_table(*category)
 
         """
         table = await conn.get_class_table(*category)
 

-        t = conn.t.placex.alias('p')
+        t = conn.t.placex

         tgeom = conn.t.placex.alias('pgeom')
 
         sql = _select_placex(t).where(tgeom.c.place_id.in_(ids))\
         tgeom = conn.t.placex.alias('pgeom')
 
         sql = _select_placex(t).where(tgeom.c.place_id.in_(ids))\


@@ -287,10 +287,11 @@ class NearSearch(AbstractSearch):
             # radius for the lookup.
             sql = sql.join(table, t.c.place_id == table.c.place_id)\
                      .join(tgeom,
             # radius for the lookup.
             sql = sql.join(table, t.c.place_id == table.c.place_id)\
                      .join(tgeom,

-                           sa.case((sa.and_(tgeom.c.rank_address < 9,
-                                            tgeom.c.geometry.is_area()),
-                                    tgeom.c.geometry.ST_Contains(table.c.centroid)),
-                                   else_ = tgeom.c.centroid.ST_DWithin(table.c.centroid, 0.05)))\
+                           table.c.centroid.ST_CoveredBy(
+                               sa.case((sa.and_(tgeom.c.rank_address < 9,
+                                                tgeom.c.geometry.is_area()),
+                                        tgeom.c.geometry),
+                                       else_ = tgeom.c.centroid.ST_Expand(0.05))))\

                      .order_by(tgeom.c.centroid.ST_Distance(table.c.centroid))
 
         sql = sql.where(t.c.rank_address.between(MIN_RANK_PARAM, MAX_RANK_PARAM))
                      .order_by(tgeom.c.centroid.ST_Distance(table.c.centroid))
 
         sql = sql.where(t.c.rank_address.between(MIN_RANK_PARAM, MAX_RANK_PARAM))


@@ -316,7 +317,7 @@ class PoiSearch(AbstractSearch):
     """
     def __init__(self, sdata: SearchData) -> None:
         super().__init__(sdata.penalty)
     """
     def __init__(self, sdata: SearchData) -> None:
         super().__init__(sdata.penalty)

-        self.categories = sdata.qualifiers
+        self.qualifiers = sdata.qualifiers

         self.countries = sdata.countries
 
 
         self.countries = sdata.countries
 
 


@@ -338,7 +339,7 @@ class PoiSearch(AbstractSearch):
                            .order_by(t.c.centroid.ST_Distance(NEAR_PARAM)) \
                            .limit(LIMIT_PARAM)
 
                            .order_by(t.c.centroid.ST_Distance(NEAR_PARAM)) \
                            .limit(LIMIT_PARAM)
 

-            classtype = self.categories.values
+            classtype = self.qualifiers.values

             if len(classtype) == 1:
                 cclass, ctype = classtype[0]
                 sql: SaLambdaSelect = sa.lambda_stmt(lambda: _base_query()
             if len(classtype) == 1:
                 cclass, ctype = classtype[0]
                 sql: SaLambdaSelect = sa.lambda_stmt(lambda: _base_query()


@@ -357,7 +358,7 @@ class PoiSearch(AbstractSearch):
             rows.extend(await conn.execute(sql, bind_params))
         else:
             # use the class type tables
             rows.extend(await conn.execute(sql, bind_params))
         else:
             # use the class type tables

-            for category in self.categories.values:
+            for category in self.qualifiers.values:

                 table = await conn.get_class_table(*category)
                 if table is not None:
                     sql = _select_placex(t)\
                 table = await conn.get_class_table(*category)
                 if table is not None:
                     sql = _select_placex(t)\


@@ -383,7 +384,7 @@ class PoiSearch(AbstractSearch):
         for row in rows:
             result = nres.create_from_placex_row(row, nres.SearchResult)
             assert result
         for row in rows:
             result = nres.create_from_placex_row(row, nres.SearchResult)
             assert result

-            result.accuracy = self.penalty + self.categories.get_penalty((row.class_, row.type))
+            result.accuracy = self.penalty + self.qualifiers.get_penalty((row.class_, row.type))

             result.bbox = Bbox.from_wkb(row.bbox)
             results.append(result)
 
             result.bbox = Bbox.from_wkb(row.bbox)
             results.append(result)
 


@@ -405,9 +406,9 @@ class CountrySearch(AbstractSearch):
         t = conn.t.placex
 
         ccodes = self.countries.values
         t = conn.t.placex
 
         ccodes = self.countries.values

-        sql: SaLambdaSelect = sa.lambda_stmt(lambda: _select_placex(t)\
+        sql = _select_placex(t)\

                 .where(t.c.country_code.in_(ccodes))\
                 .where(t.c.country_code.in_(ccodes))\

-                .where(t.c.rank_address == 4))
+                .where(t.c.rank_address == 4)

 
         if details.geometry_output:
             sql = _add_geometry_columns(sql, t.c.geometry, details)
 
         if details.geometry_output:
             sql = _add_geometry_columns(sql, t.c.geometry, details)


@@ -426,6 +427,7 @@ class CountrySearch(AbstractSearch):
             result = nres.create_from_placex_row(row, nres.SearchResult)
             assert result
             result.accuracy = self.penalty + self.countries.get_penalty(row.country_code, 5.0)
             result = nres.create_from_placex_row(row, nres.SearchResult)
             assert result
             result.accuracy = self.penalty + self.countries.get_penalty(row.country_code, 5.0)

+            result.bbox = Bbox.from_wkb(row.bbox)

             results.append(result)
 
         return results or await self.lookup_in_country_table(conn, details)
             results.append(result)
 
         return results or await self.lookup_in_country_table(conn, details)


@@ -494,12 +496,11 @@ class PostcodeSearch(AbstractSearch):
         t = conn.t.postcode
         pcs = self.postcodes.values
 
         t = conn.t.postcode
         pcs = self.postcodes.values
 

-        sql: SaLambdaSelect = sa.lambda_stmt(lambda:
-                sa.select(t.c.place_id, t.c.parent_place_id,
+        sql = sa.select(t.c.place_id, t.c.parent_place_id,

                         t.c.rank_search, t.c.rank_address,
                         t.c.postcode, t.c.country_code,
                         t.c.rank_search, t.c.rank_address,
                         t.c.postcode, t.c.country_code,

-                        t.c.geometry.label('centroid'))
-                .where(t.c.postcode.in_(pcs)))
+                        t.c.geometry.label('centroid'))\
+                .where(t.c.postcode.in_(pcs))

 
         if details.geometry_output:
             sql = _add_geometry_columns(sql, t.c.geometry, details)
 
         if details.geometry_output:
             sql = _add_geometry_columns(sql, t.c.geometry, details)


@@ -608,7 +609,7 @@ class PlaceSearch(AbstractSearch):
             pcs = self.postcodes.values
             if self.expected_count > 1000:
                 # Many results expected. Restrict by postcode.
             pcs = self.postcodes.values
             if self.expected_count > 1000:
                 # Many results expected. Restrict by postcode.

-                sql = sql.where(lambda: sa.select(tpc.c.postcode)
+                sql = sql.where(sa.select(tpc.c.postcode)

                                   .where(tpc.c.postcode.in_(pcs))
                                   .where(tsearch.c.centroid.ST_DWithin(tpc.c.geometry, 0.12))
                                   .exists())
                                   .where(tpc.c.postcode.in_(pcs))
                                   .where(tsearch.c.centroid.ST_DWithin(tpc.c.geometry, 0.12))
                                   .exists())


@@ -622,7 +623,15 @@ class PlaceSearch(AbstractSearch):
 
         if details.viewbox is not None:
             if details.bounded_viewbox:
 
         if details.viewbox is not None:
             if details.bounded_viewbox:

-                sql = sql.where(tsearch.c.centroid.intersects(VIEWBOX_PARAM))
+                if details.viewbox.area < 0.2:
+                    sql = sql.where(tsearch.c.centroid.intersects(VIEWBOX_PARAM))
+                else:
+                    sql = sql.where(tsearch.c.centroid.ST_Intersects_no_index(VIEWBOX_PARAM))
+            elif self.expected_count >= 10000:
+                if details.viewbox.area < 0.5:
+                    sql = sql.where(tsearch.c.centroid.intersects(VIEWBOX2_PARAM))
+                else:
+                    sql = sql.where(tsearch.c.centroid.ST_Intersects_no_index(VIEWBOX2_PARAM))

             else:
                 penalty += sa.case((t.c.geometry.intersects(VIEWBOX_PARAM), 0.0),
                                    (t.c.geometry.intersects(VIEWBOX2_PARAM), 1.0),
             else:
                 penalty += sa.case((t.c.geometry.intersects(VIEWBOX_PARAM), 0.0),
                                    (t.c.geometry.intersects(VIEWBOX2_PARAM), 1.0),


@@ -630,18 +639,27 @@ class PlaceSearch(AbstractSearch):
 
         if details.near is not None:
             if details.near_radius is not None:
 
         if details.near is not None:
             if details.near_radius is not None:

-                sql = sql.where(tsearch.c.centroid.ST_DWithin(NEAR_PARAM, NEAR_RADIUS_PARAM))
-            sql = sql.add_columns(-tsearch.c.centroid.ST_Distance(NEAR_PARAM)
+                if details.near_radius < 0.1:
+                    sql = sql.where(tsearch.c.centroid.ST_DWithin(NEAR_PARAM, NEAR_RADIUS_PARAM))
+                else:
+                    sql = sql.where(tsearch.c.centroid.ST_DWithin_no_index(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:
                                       .label('importance'))
             sql = sql.order_by(sa.desc(sa.text('importance')))
         else:

-            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)))
+            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.add_columns(t.c.importance)
 
 

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

 
         if self.housenumbers:
             hnr_regexp = f"\\m({'|'.join(self.housenumbers.values)})\\M"
 
         if self.housenumbers:
             hnr_regexp = f"\\m({'|'.join(self.housenumbers.values)})\\M"


@@ -663,11 +681,12 @@ class PlaceSearch(AbstractSearch):
                           .where(thnr.c.indexed_status == 0)
 
             if details.excluded:
                           .where(thnr.c.indexed_status == 0)
 
             if details.excluded:

-                place_sql = place_sql.where(_exclude_places(thnr))
+                place_sql = place_sql.where(thnr.c.place_id.not_in(sa.bindparam('excluded')))

             if self.qualifiers:
                 place_sql = place_sql.where(self.qualifiers.sql_restrict(thnr))
 
             if self.qualifiers:
                 place_sql = place_sql.where(self.qualifiers.sql_restrict(thnr))
 

-            numerals = [int(n) for n in self.housenumbers.values if n.isdigit()]
+            numerals = [int(n) for n in self.housenumbers.values
+                        if n.isdigit() and len(n) < 8]

             interpol_sql: SaColumn
             tiger_sql: SaColumn
             if numerals and \
             interpol_sql: SaColumn
             tiger_sql: SaColumn
             if numerals and \