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 047b6220affa783a9219acace82c1abcd6da9cb7..232f816ef89609f050ea15e79f3651410222ef86 100644 (file)
--- a/nominatim/api/search/db_searches.py
+++ b/nominatim/api/search/db_searches.py
@@ -24,6 +24,13 @@ from nominatim.db.sqlalchemy_types import Geometry
 #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
 

+def no_index(expr: SaColumn) -> SaColumn:
+    """ Wrap the given expression, so that the query planner will
+        refrain from using the expression for index lookup.
+    """
+    return sa.func.coalesce(sa.null(), expr) # pylint: disable=not-callable
+
+

 def _details_to_bind_params(details: SearchDetails) -> Dict[str, Any]:
     """ Create a dictionary from search parameters that can be used
         as bind parameter for SQL execute.
 def _details_to_bind_params(details: SearchDetails) -> Dict[str, Any]:
     """ Create a dictionary from search parameters that can be used
         as bind parameter for SQL execute.


@@ -59,7 +66,7 @@ def _select_placex(t: SaFromClause) -> SaSelect:
                      t.c.class_, t.c.type,
                      t.c.address, t.c.extratags,
                      t.c.housenumber, t.c.postcode, t.c.country_code,
                      t.c.class_, t.c.type,
                      t.c.address, t.c.extratags,
                      t.c.housenumber, t.c.postcode, t.c.country_code,

-                     t.c.importance, t.c.wikipedia,
+                     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.parent_place_id, t.c.rank_address, t.c.rank_search,
                      t.c.linked_place_id, t.c.admin_level,
                      t.c.centroid,


@@ -73,13 +80,13 @@ def _add_geometry_columns(sql: SaLambdaSelect, col: SaColumn, details: SearchDet
         col = sa.func.ST_SimplifyPreserveTopology(col, details.geometry_simplification)
 
     if details.geometry_output & GeometryFormat.GEOJSON:
         col = sa.func.ST_SimplifyPreserveTopology(col, details.geometry_simplification)
 
     if details.geometry_output & GeometryFormat.GEOJSON:

-        out.append(sa.func.ST_AsGeoJSON(col).label('geometry_geojson'))
+        out.append(sa.func.ST_AsGeoJSON(col, 7).label('geometry_geojson'))

     if details.geometry_output & GeometryFormat.TEXT:
         out.append(sa.func.ST_AsText(col).label('geometry_text'))
     if details.geometry_output & GeometryFormat.KML:
     if details.geometry_output & GeometryFormat.TEXT:
         out.append(sa.func.ST_AsText(col).label('geometry_text'))
     if details.geometry_output & GeometryFormat.KML:

-        out.append(sa.func.ST_AsKML(col).label('geometry_kml'))
+        out.append(sa.func.ST_AsKML(col, 7).label('geometry_kml'))

     if details.geometry_output & GeometryFormat.SVG:
     if details.geometry_output & GeometryFormat.SVG:

-        out.append(sa.func.ST_AsSVG(col).label('geometry_svg'))
+        out.append(sa.func.ST_AsSVG(col, 0, 7).label('geometry_svg'))

 
     return sql.add_columns(*out)
 
 
     return sql.add_columns(*out)
 


@@ -107,14 +114,14 @@ def _make_interpolation_subquery(table: SaFromClause, inner: SaFromClause,
 def _filter_by_layer(table: SaFromClause, layers: DataLayer) -> SaColumn:
     orexpr: List[SaExpression] = []
     if layers & DataLayer.ADDRESS and layers & DataLayer.POI:
 def _filter_by_layer(table: SaFromClause, layers: DataLayer) -> SaColumn:
     orexpr: List[SaExpression] = []
     if layers & DataLayer.ADDRESS and layers & DataLayer.POI:

-        orexpr.append(table.c.rank_address.between(1, 30))
+        orexpr.append(no_index(table.c.rank_address).between(1, 30))

     elif layers & DataLayer.ADDRESS:
     elif layers & DataLayer.ADDRESS:

-        orexpr.append(table.c.rank_address.between(1, 29))
-        orexpr.append(sa.and_(table.c.rank_address == 30,
+        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'))))
     elif layers & DataLayer.POI:
                               sa.or_(table.c.housenumber != None,
                                      table.c.address.has_key('addr:housename'))))
     elif layers & DataLayer.POI:

-        orexpr.append(sa.and_(table.c.rank_address == 30,
+        orexpr.append(sa.and_(no_index(table.c.rank_address) == 30,

                               table.c.class_.not_in(('place', 'building'))))
 
     if layers & DataLayer.MANMADE:
                               table.c.class_.not_in(('place', 'building'))))
 
     if layers & DataLayer.MANMADE:


@@ -124,7 +131,7 @@ def _filter_by_layer(table: SaFromClause, layers: DataLayer) -> SaColumn:
         if not layers & DataLayer.NATURAL:
             exclude.extend(('natural', 'water', 'waterway'))
         orexpr.append(sa.and_(table.c.class_.not_in(tuple(exclude)),
         if not layers & DataLayer.NATURAL:
             exclude.extend(('natural', 'water', 'waterway'))
         orexpr.append(sa.and_(table.c.class_.not_in(tuple(exclude)),

-                              table.c.rank_address == 0))
+                              no_index(table.c.rank_address) == 0))

     else:
         include = []
         if layers & DataLayer.RAILWAY:
     else:
         include = []
         if layers & DataLayer.RAILWAY:


@@ -132,7 +139,7 @@ def _filter_by_layer(table: SaFromClause, layers: DataLayer) -> SaColumn:
         if layers & DataLayer.NATURAL:
             include.extend(('natural', 'water', 'waterway'))
         orexpr.append(sa.and_(table.c.class_.in_(tuple(include)),
         if layers & DataLayer.NATURAL:
             include.extend(('natural', 'water', 'waterway'))
         orexpr.append(sa.and_(table.c.class_.in_(tuple(include)),

-                              table.c.rank_address == 0))
+                              no_index(table.c.rank_address) == 0))

 
     if len(orexpr) == 1:
         return orexpr[0]
 
     if len(orexpr) == 1:
         return orexpr[0]


@@ -151,7 +158,8 @@ async def _get_placex_housenumbers(conn: SearchConnection,
                                    place_ids: List[int],
                                    details: SearchDetails) -> AsyncIterator[nres.SearchResult]:
     t = conn.t.placex
                                    place_ids: List[int],
                                    details: SearchDetails) -> AsyncIterator[nres.SearchResult]:
     t = conn.t.placex

-    sql = _select_placex(t).where(t.c.place_id.in_(place_ids))
+    sql = _select_placex(t).add_columns(t.c.importance)\
+                           .where(t.c.place_id.in_(place_ids))

 
     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)


@@ -248,9 +256,20 @@ class NearSearch(AbstractSearch):
 
         base.sort(key=lambda r: (r.accuracy, r.rank_search))
         max_accuracy = base[0].accuracy + 0.5
 
         base.sort(key=lambda r: (r.accuracy, r.rank_search))
         max_accuracy = base[0].accuracy + 0.5

+        if base[0].rank_address == 0:
+            min_rank = 0
+            max_rank = 0
+        elif base[0].rank_address < 26:
+            min_rank = 1
+            max_rank = min(25, base[0].rank_address + 4)
+        else:
+            min_rank = 26
+            max_rank = 30

         base = nres.SearchResults(r for r in base if r.source_table == nres.SourceTable.PLACEX
                                                      and r.accuracy <= max_accuracy
         base = nres.SearchResults(r for r in base if r.source_table == nres.SourceTable.PLACEX
                                                      and r.accuracy <= max_accuracy

-                                                     and r.bbox and r.bbox.area < 20)
+                                                     and r.bbox and r.bbox.area < 20
+                                                     and r.rank_address >= min_rank
+                                                     and r.rank_address <= max_rank)

 
         if base:
             baseids = [b.place_id for b in base[:5] if b.place_id]
 
         if base:
             baseids = [b.place_id for b in base[:5] if b.place_id]


@@ -272,30 +291,39 @@ class NearSearch(AbstractSearch):
         """
         table = await conn.get_class_table(*category)
 
         """
         table = await conn.get_class_table(*category)
 

-        t = conn.t.placex

         tgeom = conn.t.placex.alias('pgeom')
 
         tgeom = conn.t.placex.alias('pgeom')
 

-        sql = _select_placex(t).where(tgeom.c.place_id.in_(ids))\
-                               .where(t.c.class_ == category[0])\
-                               .where(t.c.type == category[1])
-

         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.

-            sql = sql.join(tgeom, t.c.geometry.ST_DWithin(tgeom.c.centroid, 0.01))\
-                     .order_by(tgeom.c.centroid.ST_Distance(t.c.centroid))
+            table = conn.t.placex.alias('inner')
+            sql = sa.select(table.c.place_id,
+                            sa.func.min(tgeom.c.centroid.ST_Distance(table.c.centroid))
+                              .label('dist'))\
+                    .join(tgeom, table.c.geometry.intersects(tgeom.c.centroid.ST_Expand(0.01)))\
+                    .where(table.c.class_ == category[0])\
+                    .where(table.c.type == category[1])

         else:
             # Use classtype table. We can afford to use a larger
             # radius for the lookup.
         else:
             # Use classtype table. We can afford to use a larger
             # radius for the lookup.

-            sql = sql.join(table, t.c.place_id == table.c.place_id)\
-                     .join(tgeom,
-                           table.c.centroid.ST_CoveredBy(
-                               sa.case((sa.and_(tgeom.c.rank_address < 9,
+            sql = sa.select(table.c.place_id,
+                            sa.func.min(tgeom.c.centroid.ST_Distance(table.c.centroid))
+                              .label('dist'))\
+                    .join(tgeom,
+                          table.c.centroid.ST_CoveredBy(
+                              sa.case((sa.and_(tgeom.c.rank_address > 9,

                                                 tgeom.c.geometry.is_area()),
                                                 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))
+                                       tgeom.c.geometry),
+                                      else_ = tgeom.c.centroid.ST_Expand(0.05))))
+
+        inner = sql.where(tgeom.c.place_id.in_(ids))\
+                   .group_by(table.c.place_id).subquery()

 
 

-        sql = sql.where(t.c.rank_address.between(MIN_RANK_PARAM, MAX_RANK_PARAM))
+        t = conn.t.placex
+        sql = _select_placex(t).add_columns((-inner.c.dist).label('importance'))\
+                               .join(inner, inner.c.place_id == t.c.place_id)\
+                               .order_by(inner.c.dist)
+
+        sql = sql.where(no_index(t.c.rank_address).between(MIN_RANK_PARAM, MAX_RANK_PARAM))

         if details.countries:
             sql = sql.where(t.c.country_code.in_(COUNTRIES_PARAM))
         if details.excluded:
         if details.countries:
             sql = sql.where(t.c.country_code.in_(COUNTRIES_PARAM))
         if details.excluded:


@@ -335,6 +363,8 @@ class PoiSearch(AbstractSearch):
             # simply search in placex table
             def _base_query() -> SaSelect:
                 return _select_placex(t) \
             # simply search in placex table
             def _base_query() -> SaSelect:
                 return _select_placex(t) \

+                           .add_columns((-t.c.centroid.ST_Distance(NEAR_PARAM))
+                                         .label('importance'))\

                            .where(t.c.linked_place_id == None) \
                            .where(t.c.geometry.ST_DWithin(NEAR_PARAM, NEAR_RADIUS_PARAM)) \
                            .order_by(t.c.centroid.ST_Distance(NEAR_PARAM)) \
                            .where(t.c.linked_place_id == None) \
                            .where(t.c.geometry.ST_DWithin(NEAR_PARAM, NEAR_RADIUS_PARAM)) \
                            .order_by(t.c.centroid.ST_Distance(NEAR_PARAM)) \


@@ -363,6 +393,7 @@ class PoiSearch(AbstractSearch):
                 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)\

+                               .add_columns(t.c.importance)\

                                .join(table, t.c.place_id == table.c.place_id)\
                                .where(t.c.class_ == category[0])\
                                .where(t.c.type == category[1])
                                .join(table, t.c.place_id == table.c.place_id)\
                                .where(t.c.class_ == category[0])\
                                .where(t.c.type == category[1])


@@ -408,6 +439,7 @@ class CountrySearch(AbstractSearch):
 
         ccodes = self.countries.values
         sql = _select_placex(t)\
 
         ccodes = self.countries.values
         sql = _select_placex(t)\

+                .add_columns(t.c.importance)\

                 .where(t.c.country_code.in_(ccodes))\
                 .where(t.c.rank_address == 4)
 
                 .where(t.c.country_code.in_(ccodes))\
                 .where(t.c.rank_address == 4)
 


@@ -449,7 +481,8 @@ 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)
 


@@ -465,13 +498,17 @@ 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)
 


@@ -513,8 +550,8 @@ class PostcodeSearch(AbstractSearch):
                 sql = sql.where(t.c.geometry.intersects(VIEWBOX_PARAM))
             else:
                 penalty += sa.case((t.c.geometry.intersects(VIEWBOX_PARAM), 0.0),
                 sql = sql.where(t.c.geometry.intersects(VIEWBOX_PARAM))
             else:
                 penalty += sa.case((t.c.geometry.intersects(VIEWBOX_PARAM), 0.0),

-                                   (t.c.geometry.intersects(VIEWBOX2_PARAM), 1.0),
-                                   else_=2.0)
+                                   (t.c.geometry.intersects(VIEWBOX2_PARAM), 0.5),
+                                   else_=1.0)

 
         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:


@@ -579,15 +616,7 @@ class PlaceSearch(AbstractSearch):
         tsearch = conn.t.search_name
 
         sql: SaLambdaSelect = sa.lambda_stmt(lambda:
         tsearch = conn.t.search_name
 
         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.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.centroid,
-                            t.c.geometry.ST_Expand(0).label('bbox'))
-                   .where(t.c.place_id == tsearch.c.place_id))
+                  _select_placex(t).where(t.c.place_id == tsearch.c.place_id))

 
 
         if details.geometry_output:
 
 
         if details.geometry_output:


@@ -635,8 +664,8 @@ class PlaceSearch(AbstractSearch):
                     sql = sql.where(tsearch.c.centroid.ST_Intersects_no_index(VIEWBOX2_PARAM))
             else:
                 penalty += sa.case((t.c.geometry.intersects(VIEWBOX_PARAM), 0.0),
                     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_=2.0)
+                                   (t.c.geometry.intersects(VIEWBOX2_PARAM), 0.5),
+                                   else_=1.0)

 
         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:


@@ -737,9 +766,6 @@ class PlaceSearch(AbstractSearch):
             assert result
             result.bbox = Bbox.from_wkb(row.bbox)
             result.accuracy = row.accuracy
             assert result
             result.bbox = Bbox.from_wkb(row.bbox)
             result.accuracy = row.accuracy

-            if not details.excluded or not result.place_id in details.excluded:
-                results.append(result)
-

             if self.housenumbers and row.rank_address < 30:
                 if row.placex_hnr:
                     subs = _get_placex_housenumbers(conn, row.placex_hnr, details)
             if self.housenumbers and row.rank_address < 30:
                 if row.placex_hnr:
                     subs = _get_placex_housenumbers(conn, row.placex_hnr, details)


@@ -759,6 +785,14 @@ class PlaceSearch(AbstractSearch):
                             sub.accuracy += 0.6
                         results.append(sub)
 
                             sub.accuracy += 0.6
                         results.append(sub)
 

-                result.accuracy += 1.0 # penalty for missing housenumber
+                # Only add the street as a result, if it meets all other
+                # filter conditions.
+                if (not details.excluded or result.place_id not in details.excluded)\
+                   and (not self.qualifiers or result.category in self.qualifiers.values)\
+                   and result.rank_address >= details.min_rank:
+                    result.accuracy += 1.0 # penalty for missing housenumber
+                    results.append(result)
+            else:
+                results.append(result)

 
         return results
 
         return results