reduce expected count for multi-part words

[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 34a4037a356b466fbb03b1e73c39583243620af7..1f7eb0093a6bc8245bbe3b422084e4bcd25d73fd 100644 (file)
--- a/nominatim/api/search/db_searches.py
+++ b/nominatim/api/search/db_searches.py
@@ -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))\


@@ -627,6 +627,11 @@ 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),


@@ -643,13 +648,18 @@ class PlaceSearch(AbstractSearch):
                                       .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"


@@ -675,7 +685,8 @@ 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 \