minimum counts for tokens should always be 1

to avoid accidental devision by 0.
osm-search · Apr 1, 2024 · 78c19bc · 78c19bc
1 parent e53eb79
commit 78c19bc
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 3 deletions.
diff --git a/nominatim/api/search/icu_tokenizer.py b/nominatim/api/search/icu_tokenizer.py
@@ -122,10 +122,10 @@ def from_db_row(row: SaRow) -> 'ICUToken':
         else:
             lookup_word = row.word_token
 
-        return ICUToken(penalty=penalty, token=row.word_id, count=count,
+        return ICUToken(penalty=penalty, token=row.word_id, count=max(1, count),
                         lookup_word=lookup_word, is_indexed=True,
                         word_token=row.word_token, info=row.info,
-                        addr_count=addr_count)
+                        addr_count=max(1, addr_count))
 
 
 

diff --git a/nominatim/api/search/legacy_tokenizer.py b/nominatim/api/search/legacy_tokenizer.py
@@ -209,7 +209,7 @@ def make_token(self, row: SaRow) -> Tuple[LegacyToken, qmod.TokenType]:
                 is_indexed = False
 
         return LegacyToken(penalty=penalty, token=row.word_id,
-                           count=row.search_name_count or 1,
+                           count=max(1, row.search_name_count or 1),
                            addr_count=1, # not supported
                            lookup_word=lookup_word,
                            word_token=row.word_token.strip(),