From: Sarah Hoffmann <lonvia@denofr.de>
Date: Sun, 26 Nov 2023 16:11:15 +0000 (+0100)
Subject: deduplicate categories/qualifiers
X-Git-Tag: v4.4.0~76^2~2
X-Git-Url: https://git.openstreetmap.org./nominatim.git/commitdiff_plain/47ca56f21b7da4ac8131c6f4101984a6532e7b39

deduplicate categories/qualifiers
---

diff --git a/nominatim/api/search/db_search_builder.py b/nominatim/api/search/db_search_builder.py
index 905b5c62..7826925a 100644
--- a/nominatim/api/search/db_search_builder.py
+++ b/nominatim/api/search/db_search_builder.py
@@ -7,7 +7,7 @@
 """
 Convertion from token assignment to an abstract DB search.
 """
-from typing import Optional, List, Tuple, Iterator
+from typing import Optional, List, Tuple, Iterator, Dict
 import heapq
 
 from nominatim.api.types import SearchDetails, DataLayer
@@ -339,12 +339,13 @@ class SearchBuilder:
             Returns None if no category search is requested.
         """
         if assignment.category:
-            tokens = [t for t in self.query.get_tokens(assignment.category,
-                                                       TokenType.CATEGORY)
-                      if not self.details.categories
-                         or t.get_category() in self.details.categories]
-            return dbf.WeightedCategories([t.get_category() for t in tokens],
-                                          [t.penalty for t in tokens])
+            tokens: Dict[Tuple[str, str], float] = {}
+            for t in self.query.get_tokens(assignment.category, TokenType.CATEGORY):
+                cat = t.get_category()
+                if (not self.details.categories or cat in self.details.categories)\
+                   and t.penalty < tokens.get(cat, 1000.0):
+                    tokens[cat] = t.penalty
+            return dbf.WeightedCategories(list(tokens.keys()), list(tokens.values()))
 
         if self.details.categories:
             return dbf.WeightedCategories(self.details.categories,
diff --git a/nominatim/api/search/db_search_fields.py b/nominatim/api/search/db_search_fields.py
index 612e9059..59af8260 100644
--- a/nominatim/api/search/db_search_fields.py
+++ b/nominatim/api/search/db_search_fields.py
@@ -7,7 +7,7 @@
 """
 Data structures for more complex fields in abstract search descriptions.
 """
-from typing import List, Tuple, Iterator, cast
+from typing import List, Tuple, Iterator, cast, Dict
 import dataclasses
 
 import sqlalchemy as sa
@@ -195,10 +195,17 @@ class SearchData:
         """ Set the qulaifier field from the given tokens.
         """
         if tokens:
-            min_penalty = min(t.penalty for t in tokens)
+            categories: Dict[Tuple[str, str], float] = {}
+            min_penalty = 1000.0
+            for t in tokens:
+                if t.penalty < min_penalty:
+                    min_penalty = t.penalty
+                cat = t.get_category()
+                if t.penalty < categories.get(cat, 1000.0):
+                    categories[cat] = t.penalty
             self.penalty += min_penalty
-            self.qualifiers = WeightedCategories([t.get_category() for t in tokens],
-                                                 [t.penalty - min_penalty for t in tokens])
+            self.qualifiers = WeightedCategories(list(categories.keys()),
+                                                 list(categories.values()))
 
 
     def set_ranking(self, rankings: List[FieldRanking]) -> None: