From: Sarah Hoffmann <lonvia@denofr.de>
Date: Mon, 18 Dec 2023 15:00:08 +0000 (+0100)
Subject: Merge remote-tracking branch 'upstream/master'
X-Git-Tag: deploy~29
X-Git-Url: https://git.openstreetmap.org./nominatim.git/commitdiff_plain/7b27c04b8392d0babe33cf53e2838b05ffbcbacf?hp=-c

Merge remote-tracking branch 'upstream/master'
---

7b27c04b8392d0babe33cf53e2838b05ffbcbacf
diff --combined nominatim/api/search/icu_tokenizer.py
index 06a06f34,eabd329d..ff1c3fee
--- a/nominatim/api/search/icu_tokenizer.py
+++ b/nominatim/api/search/icu_tokenizer.py
@@@ -22,6 -22,7 +22,7 @@@ from nominatim.api.connection import Se
  from nominatim.api.logging import log
  from nominatim.api.search import query as qmod
  from nominatim.api.search.query_analyzer_factory import AbstractQueryAnalyzer
+ from nominatim.db.sqlalchemy_types import Json
  
  
  DB_TO_TOKEN_TYPE = {
@@@ -159,7 -160,7 +160,7 @@@ class ICUQueryAnalyzer(AbstractQueryAna
                       sa.Column('word_token', sa.Text, nullable=False),
                       sa.Column('type', sa.Text, nullable=False),
                       sa.Column('word', sa.Text),
-                      sa.Column('info', self.conn.t.types.Json))
+                      sa.Column('info', Json))
  
  
      async def analyze_query(self, phrases: List[qmod.Phrase]) -> qmod.QueryStruct:
@@@ -207,12 -208,7 +208,12 @@@
              standardized form search will work with. All information removed
              at this stage is inevitably lost.
          """
 -        return cast(str, self.normalizer.transliterate(text))
 +        norm = cast(str, self.normalizer.transliterate(text))
 +        numspaces = norm.count(' ')
 +        if numspaces > 4 and len(norm) <= (numspaces + 1) * 3:
 +            return ''
 +
 +        return norm
  
  
      def split_query(self, query: qmod.QueryStruct) -> Tuple[QueryParts, WordDict]: