Merge remote-tracking branch 'upstream/master'

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

diff --git a/nominatim/api/search/icu_tokenizer.py b/nominatim/api/search/icu_tokenizer.py
index f259995db112bbbe537aaa3855f2d4d78e36f5e2..d3e34537a8d7c03585b16dac4a2136e80e77c8fd 100644 (file)
--- a/nominatim/api/search/icu_tokenizer.py
+++ b/nominatim/api/search/icu_tokenizer.py
@@ -83,7 +83,7 @@ class ICUToken(qmod.Token):
         seq = difflib.SequenceMatcher(a=self.lookup_word, b=norm)
         distance = 0
         for tag, afrom, ato, bfrom, bto in seq.get_opcodes():
-            if tag == 'delete' and (afrom == 0 or ato == len(self.lookup_word)):
+            if tag in ('delete', 'insert') and (afrom == 0 or ato == len(self.lookup_word)):
                 distance += 1
             elif tag == 'replace':
                 distance += max((ato-afrom), (bto-bfrom))
@@ -192,7 +192,12 @@ class ICUQueryAnalyzer(AbstractQueryAnalyzer):
             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]: