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..d2cdd96e16432d62f2b02d0fcbe390e060d905e1 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():
         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))
                 distance += 1
             elif tag == 'replace':
                 distance += max((ato-afrom), (bto-bfrom))


@@ -133,10 +133,19 @@ class ICUQueryAnalyzer(AbstractQueryAnalyzer):
     async def setup(self) -> None:
         """ Set up static data structures needed for the analysis.
         """
     async def setup(self) -> None:
         """ Set up static data structures needed for the analysis.
         """

-        rules = await self.conn.get_property('tokenizer_import_normalisation')
-        self.normalizer = Transliterator.createFromRules("normalization", rules)
-        rules = await self.conn.get_property('tokenizer_import_transliteration')
-        self.transliterator = Transliterator.createFromRules("transliteration", rules)
+        async def _make_normalizer() -> Any:
+            rules = await self.conn.get_property('tokenizer_import_normalisation')
+            return Transliterator.createFromRules("normalization", rules)
+
+        self.normalizer = await self.conn.get_cached_value('ICUTOK', 'normalizer',
+                                                           _make_normalizer)
+
+        async def _make_transliterator() -> Any:
+            rules = await self.conn.get_property('tokenizer_import_transliteration')
+            return Transliterator.createFromRules("transliteration", rules)
+
+        self.transliterator = await self.conn.get_cached_value('ICUTOK', 'transliterator',
+                                                               _make_transliterator)

 
         if 'word' not in self.conn.t.meta.tables:
             sa.Table('word', self.conn.t.meta,
 
         if 'word' not in self.conn.t.meta.tables:
             sa.Table('word', self.conn.t.meta,


@@ -192,7 +201,12 @@ class ICUQueryAnalyzer(AbstractQueryAnalyzer):
             standardized form search will work with. All information removed
             at this stage is inevitably lost.
         """
             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]:
 
 
     def split_query(self, query: qmod.QueryStruct) -> Tuple[QueryParts, WordDict]: