X-Git-Url: https://git.openstreetmap.org./nominatim.git/blobdiff_plain/964bc7fbe01bbd9c102d1c553b8f87cce3ab7a2c..9fc235d6706a92f615761d35690a4ad550045ea5:/nominatim/api/search/db_search_builder.py

diff --git a/nominatim/api/search/db_search_builder.py b/nominatim/api/search/db_search_builder.py
index 9d89736c..2a3153be 100644
--- a/nominatim/api/search/db_search_builder.py
+++ b/nominatim/api/search/db_search_builder.py
@@ -11,7 +11,7 @@ from typing import Optional, List, Tuple, Iterator
 import heapq
 
 from nominatim.api.types import SearchDetails, DataLayer
-from nominatim.api.search.query import QueryStruct, TokenType, TokenRange, BreakType
+from nominatim.api.search.query import QueryStruct, Token, TokenType, TokenRange, BreakType
 from nominatim.api.search.token_assignment import TokenAssignment
 import nominatim.api.search.db_search_fields as dbf
 import nominatim.api.search.db_searches as dbs
@@ -97,6 +97,10 @@ class SearchBuilder:
                 sdata.qualifiers = categories
                 categories = None
                 builder = self.build_poi_search(sdata)
+            elif assignment.housenumber:
+                hnr_tokens = self.query.get_tokens(assignment.housenumber,
+                                                   TokenType.HOUSENUMBER)
+                builder = self.build_housenumber_search(sdata, hnr_tokens, assignment.address)
             else:
                 builder = self.build_special_search(sdata, assignment.address,
                                                     bool(categories))
@@ -128,8 +132,8 @@ class SearchBuilder:
         """ Build abstract search queries for searches that do not involve
             a named place.
         """
-        if sdata.qualifiers or sdata.housenumbers:
-            # No special searches over housenumbers or qualifiers supported.
+        if sdata.qualifiers:
+            # No special searches over qualifiers supported.
             return
 
         if sdata.countries and not address and not sdata.postcodes \
@@ -137,12 +141,29 @@ class SearchBuilder:
             yield dbs.CountrySearch(sdata)
 
         if sdata.postcodes and (is_category or self.configured_for_postcode):
+            penalty = 0.0 if sdata.countries else 0.1
             if address:
                 sdata.lookups = [dbf.FieldLookup('nameaddress_vector',
                                                  [t.token for r in address
                                                   for t in self.query.get_partials_list(r)],
                                                  'restrict')]
-            yield dbs.PostcodeSearch(0.4, sdata)
+                penalty += 0.2
+            yield dbs.PostcodeSearch(penalty, sdata)
+
+
+    def build_housenumber_search(self, sdata: dbf.SearchData, hnrs: List[Token],
+                                 address: List[TokenRange]) -> Iterator[dbs.AbstractSearch]:
+        """ Build a simple address search for special entries where the
+            housenumber is the main name token.
+        """
+        partial_tokens: List[int] = []
+        for trange in address:
+            partial_tokens.extend(t.token for t in self.query.get_partials_list(trange))
+
+        sdata.lookups = [dbf.FieldLookup('name_vector', [t.token for t in hnrs], 'lookup_any'),
+                         dbf.FieldLookup('nameaddress_vector', partial_tokens, 'lookup_all')
+                        ]
+        yield dbs.PlaceSearch(0.05, sdata, sum(t.count for t in hnrs))
 
 
     def build_name_search(self, sdata: dbf.SearchData,
@@ -189,7 +210,9 @@ class SearchBuilder:
         exp_addr_count = min(t.count for t in addr_partials) if addr_partials else exp_name_count
         if exp_addr_count < 1000 and partials_indexed:
             # Lookup by address partials and restrict results through name terms.
-            yield penalty, exp_addr_count,\
+            # Give this a small penalty because lookups in the address index are
+            # more expensive
+            yield penalty + exp_addr_count/5000, exp_addr_count,\
                   [dbf.FieldLookup('name_vector', [t.token for t in name_partials], 'restrict'),
                    dbf.FieldLookup('nameaddress_vector', addr_tokens, 'lookup_all')]
             return
@@ -212,19 +235,21 @@ class SearchBuilder:
             yield penalty, sum(t.count for t in rare_names), lookup
 
         # To catch remaining results, lookup by name and address
-        if all(t.is_indexed for t in name_partials):
-            lookup = [dbf.FieldLookup('name_vector',
-                                      [t.token for t in name_partials], 'lookup_all')]
-        else:
-            # we don't have the partials, try with the non-rare names
-            non_rare_names = [t.token for t in name_fulls if t.count >= 1000]
-            if not non_rare_names:
-                return
-            lookup = [dbf.FieldLookup('name_vector', non_rare_names, 'lookup_any')]
-        if addr_tokens:
-            lookup.append(dbf.FieldLookup('nameaddress_vector', addr_tokens, 'lookup_all'))
-        yield penalty + 0.1 * max(0, 5 - len(name_partials) - len(addr_tokens)),\
-              min(exp_name_count, exp_addr_count), lookup
+        # We only do this if there is a reasonable number of results expected.
+        if min(exp_name_count, exp_addr_count) < 10000:
+            if all(t.is_indexed for t in name_partials):
+                lookup = [dbf.FieldLookup('name_vector',
+                                          [t.token for t in name_partials], 'lookup_all')]
+            else:
+                # we don't have the partials, try with the non-rare names
+                non_rare_names = [t.token for t in name_fulls if t.count >= 1000]
+                if not non_rare_names:
+                    return
+                lookup = [dbf.FieldLookup('name_vector', non_rare_names, 'lookup_any')]
+            if addr_tokens:
+                lookup.append(dbf.FieldLookup('nameaddress_vector', addr_tokens, 'lookup_all'))
+            yield penalty + 0.1 * max(0, 5 - len(name_partials) - len(addr_tokens)),\
+                  min(exp_name_count, exp_addr_count), lookup
 
 
     def get_name_ranking(self, trange: TokenRange) -> dbf.FieldRanking: