more unit tests for search

[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 f4684044c6fac08fffa05b6e205ffdd70c1020bd..eb4da5490e5f8ad6377cba288908fccdf9d2e79f 100644 (file)
--- a/nominatim/api/search/db_searches.py
+++ b/nominatim/api/search/db_searches.py
@@ -61,6 +61,7 @@ def _select_placex(t: SaFromClause) -> SaSelect:
                      t.c.housenumber, t.c.postcode, t.c.country_code,
                      t.c.importance, t.c.wikipedia,
                      t.c.parent_place_id, t.c.rank_address, t.c.rank_search,
                      t.c.housenumber, t.c.postcode, t.c.country_code,
                      t.c.importance, t.c.wikipedia,
                      t.c.parent_place_id, t.c.rank_address, t.c.rank_search,

+                     t.c.linked_place_id, t.c.admin_level,

                      t.c.centroid,
                      t.c.geometry.ST_Expand(0).label('bbox'))
 
                      t.c.centroid,
                      t.c.geometry.ST_Expand(0).label('bbox'))
 


@@ -111,7 +112,7 @@ 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 +272,7 @@ 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))\


@@ -427,6 +428,7 @@ 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)


@@ -447,7 +449,8 @@ class CountrySearch(AbstractSearch):
 
         sql = sa.select(tgrid.c.country_code,
                         tgrid.c.geometry.ST_Centroid().ST_Collect().ST_Centroid()
 
         sql = sa.select(tgrid.c.country_code,
                         tgrid.c.geometry.ST_Centroid().ST_Collect().ST_Centroid()

-                              .label('centroid'))\
+                              .label('centroid'),
+                        tgrid.c.geometry.ST_Collect().ST_Expand(0).label('bbox'))\

                 .where(tgrid.c.country_code.in_(self.countries.values))\
                 .group_by(tgrid.c.country_code)
 
                 .where(tgrid.c.country_code.in_(self.countries.values))\
                 .group_by(tgrid.c.country_code)
 


@@ -463,13 +466,17 @@ class CountrySearch(AbstractSearch):
                          + sa.func.coalesce(t.c.derived_name,
                                             sa.cast('', type_=conn.t.types.Composite))
                         ).label('name'),
                          + sa.func.coalesce(t.c.derived_name,
                                             sa.cast('', type_=conn.t.types.Composite))
                         ).label('name'),

-                        sub.c.centroid)\
+                        sub.c.centroid, sub.c.bbox)\

                 .join(sub, t.c.country_code == sub.c.country_code)
 
                 .join(sub, t.c.country_code == sub.c.country_code)
 

+        if details.geometry_output:
+            sql = _add_geometry_columns(sql, sub.c.centroid, details)
+

         results = nres.SearchResults()
         for row in await conn.execute(sql, _details_to_bind_params(details)):
             result = nres.create_from_country_row(row, nres.SearchResult)
             assert result
         results = nres.SearchResults()
         for row in await conn.execute(sql, _details_to_bind_params(details)):
             result = nres.create_from_country_row(row, nres.SearchResult)
             assert result

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

             result.accuracy = self.penalty + self.countries.get_penalty(row.country_code, 5.0)
             results.append(result)
 
             result.accuracy = self.penalty + self.countries.get_penalty(row.country_code, 5.0)
             results.append(result)
 


@@ -579,7 +586,7 @@ class PlaceSearch(AbstractSearch):
         sql: SaLambdaSelect = sa.lambda_stmt(lambda:
                   sa.select(t.c.place_id, t.c.osm_type, t.c.osm_id, t.c.name,
                             t.c.class_, t.c.type,
         sql: SaLambdaSelect = sa.lambda_stmt(lambda:
                   sa.select(t.c.place_id, t.c.osm_type, t.c.osm_id, t.c.name,
                             t.c.class_, t.c.type,

-                            t.c.address, t.c.extratags,
+                            t.c.address, t.c.extratags, t.c.admin_level,

                             t.c.housenumber, t.c.postcode, t.c.country_code,
                             t.c.wikipedia,
                             t.c.parent_place_id, t.c.rank_address, t.c.rank_search,
                             t.c.housenumber, t.c.postcode, t.c.country_code,
                             t.c.wikipedia,
                             t.c.parent_place_id, t.c.rank_address, t.c.rank_search,


@@ -626,6 +633,11 @@ class PlaceSearch(AbstractSearch):
                     sql = sql.where(tsearch.c.centroid.intersects(VIEWBOX_PARAM))
                 else:
                     sql = sql.where(tsearch.c.centroid.ST_Intersects_no_index(VIEWBOX_PARAM))
                     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),


@@ -638,17 +650,22 @@ class PlaceSearch(AbstractSearch):
                 else:
                     sql = sql.where(tsearch.c.centroid.ST_DWithin_no_index(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)
+            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"


@@ -674,7 +691,8 @@ class PlaceSearch(AbstractSearch):
             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 \