extend word statistics to address index

[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 254d2ca6703e8f20c4056a694b8a15c4353e841a..3f294de7c925ba5b2017bfd247496ef2c28c189c 100644 (file)
--- a/nominatim/api/search/db_searches.py
+++ b/nominatim/api/search/db_searches.py
@@ -5,7 +5,7 @@
 # Copyright (C) 2023 by the Nominatim developer community.
 # For a full list of authors see the git log.
 """
-Implementation of the acutal database accesses for forward search.
+Implementation of the actual database accesses for forward search.
 """
 from typing import List, Tuple, AsyncIterator, Dict, Any, Callable, cast
 import abc
@@ -245,6 +245,7 @@ async def _get_tiger(conn: SearchConnection, place_ids: List[int],
 class AbstractSearch(abc.ABC):
     """ Encapuslation of a single lookup in the database.
     """
+    SEARCH_PRIO: int = 2
 
     def __init__(self, penalty: float) -> None:
         self.penalty = penalty
@@ -448,6 +449,8 @@ class PoiSearch(AbstractSearch):
 class CountrySearch(AbstractSearch):
     """ Search for a country name or country code.
     """
+    SEARCH_PRIO = 0
+
     def __init__(self, sdata: SearchData) -> None:
         super().__init__(sdata.penalty)
         self.countries = sdata.countries
@@ -481,7 +484,14 @@ class CountrySearch(AbstractSearch):
             result.bbox = Bbox.from_wkb(row.bbox)
             results.append(result)
 
-        return results or await self.lookup_in_country_table(conn, details)
+        if not results:
+            results = await self.lookup_in_country_table(conn, details)
+
+        if results:
+            details.min_rank = min(5, details.max_rank)
+            details.max_rank = min(25, details.max_rank)
+
+        return results
 
 
     async def lookup_in_country_table(self, conn: SearchConnection,
@@ -592,10 +602,28 @@ class PostcodeSearch(AbstractSearch):
 
         results = nres.SearchResults()
         for row in await conn.execute(sql, _details_to_bind_params(details)):
-            result = nres.create_from_postcode_row(row, nres.SearchResult)
+            p = conn.t.placex
+            placex_sql = _select_placex(p).add_columns(p.c.importance)\
+                             .where(sa.text("""class = 'boundary'
+                                               AND type = 'postal_code'
+                                               AND osm_type = 'R'"""))\
+                             .where(p.c.country_code == row.country_code)\
+                             .where(p.c.postcode == row.postcode)\
+                             .limit(1)
+
+            if details.geometry_output:
+                placex_sql = _add_geometry_columns(placex_sql, p.c.geometry, details)
+
+            for prow in await conn.execute(placex_sql, _details_to_bind_params(details)):
+                result = nres.create_from_placex_row(prow, nres.SearchResult)
+                break
+            else:
+                result = nres.create_from_postcode_row(row, nres.SearchResult)
+
             assert result
-            result.accuracy = row.accuracy
-            results.append(result)
+            if result.place_id not in details.excluded:
+                result.accuracy = row.accuracy
+                results.append(result)
 
         return results
 
@@ -604,6 +632,8 @@ class PostcodeSearch(AbstractSearch):
 class PlaceSearch(AbstractSearch):
     """ Generic search for an address or named place.
     """
+    SEARCH_PRIO = 1
+
     def __init__(self, extra_penalty: float, sdata: SearchData, expected_count: int) -> None:
         super().__init__(sdata.penalty + extra_penalty)
         self.countries = sdata.countries
@@ -688,7 +718,7 @@ class PlaceSearch(AbstractSearch):
                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)))
+                                    else_=0.40001-(sa.cast(tsearch.c.search_rank, sa.Float())/75)))
             sql = sql.add_columns(t.c.importance)