remove restriction on frequent one word names

[nominatim.git] / nominatim / api / search / geocoder.py

diff --git a/nominatim/api/search/geocoder.py b/nominatim/api/search/geocoder.py
index 7ff3ed08af9dcfa23c8072d4d57152a253930007..775606aab755d6f68180e696828115c285a99f11 100644 (file)
--- a/nominatim/api/search/geocoder.py
+++ b/nominatim/api/search/geocoder.py
@@ -64,7 +64,7 @@ class ForwardGeocoder:
                     log().table_dump('Searches for assignment',
                                      _dump_searches(searches, query, num_searches))
                 num_searches = len(searches)
-            searches.sort(key=lambda s: s.penalty)
+            searches.sort(key=lambda s: (s.penalty, s.SEARCH_PRIO))
 
         return query, searches
 
@@ -79,12 +79,13 @@ class ForwardGeocoder:
 
         end_time = dt.datetime.now() + self.timeout
 
-        min_ranking = 1000.0
+        min_ranking = searches[0].penalty + 2.0
         prev_penalty = 0.0
         for i, search in enumerate(searches):
             if search.penalty > prev_penalty and (search.penalty > min_ranking or i > 20):
                 break
             log().table_dump(f"{i + 1}. Search", _dump_searches([search], query))
+            log().var_dump('Params', self.params)
             lookup_results = await search.lookup(self.conn, self.params)
             for result in lookup_results:
                 rhash = (result.source_table, result.place_id,
@@ -94,7 +95,7 @@ class ForwardGeocoder:
                     prevresult.accuracy = min(prevresult.accuracy, result.accuracy)
                 else:
                     results[rhash] = result
-                min_ranking = min(min_ranking, result.ranking + 0.5, search.penalty + 0.3)
+                min_ranking = min(min_ranking, result.accuracy * 1.2, 2.0)
             log().result_dump('Results', ((r.accuracy, r) for r in lookup_results))
             prev_penalty = search.penalty
             if dt.datetime.now() >= end_time:
@@ -103,19 +104,27 @@ class ForwardGeocoder:
         return SearchResults(results.values())
 
 
+    def pre_filter_results(self, results: SearchResults) -> SearchResults:
+        """ Remove results that are significantly worse than the
+            best match.
+        """
+        if results:
+            max_ranking = min(r.ranking for r in results) + 0.5
+            results = SearchResults(r for r in results if r.ranking < max_ranking)
+
+        return results
+
+
     def sort_and_cut_results(self, results: SearchResults) -> SearchResults:
         """ Remove badly matching results, sort by ranking and
             limit to the configured number of results.
         """
         if results:
-            min_ranking = min(r.ranking for r in results)
-            results = SearchResults(r for r in results if r.ranking < min_ranking + 0.5)
             results.sort(key=lambda r: r.ranking)
-
-        if results:
             min_rank = results[0].rank_search
+            min_ranking = results[0].ranking
             results = SearchResults(r for r in results
-                                    if r.ranking + 0.05 * (r.rank_search - min_rank)
+                                    if r.ranking + 0.03 * (r.rank_search - min_rank)
                                        < min_ranking + 0.5)
 
             results = SearchResults(results[:self.limit])
@@ -134,10 +143,14 @@ class ForwardGeocoder:
             return
 
         for result in results:
-            if not result.display_name:
+            # Negative importance indicates ordering by distance, which is
+            # more important than word matching.
+            if not result.display_name\
+               or (result.importance is not None and result.importance < 0):
                 continue
             distance = 0.0
-            norm = self.query_analyzer.normalize_text(result.display_name)
+            norm = self.query_analyzer.normalize_text(' '.join((result.display_name,
+                                                                result.country_code or '')))
             words = set((w for w in norm.split(' ') if w))
             if not words:
                 continue
@@ -169,6 +182,7 @@ class ForwardGeocoder:
             if query:
                 searches = [wrap_near_search(categories, s) for s in searches[:50]]
                 results = await self.execute_searches(query, searches)
+                results = self.pre_filter_results(results)
                 await add_result_details(self.conn, results, self.params)
                 log().result_dump('Preliminary Results', ((r.accuracy, r) for r in results))
                 results = self.sort_and_cut_results(results)
@@ -198,6 +212,7 @@ class ForwardGeocoder:
         if searches:
             # Execute SQL until an appropriate result is found.
             results = await self.execute_searches(query, searches[:50])
+            results = self.pre_filter_results(results)
             await add_result_details(self.conn, results, self.params)
             log().result_dump('Preliminary Results', ((r.accuracy, r) for r in results))
             self.rerank_by_query(query, results)