port legacy tokenizer to new postcode handling

[nominatim.git] / nominatim / tokenizer / legacy_tokenizer.py

diff --git a/nominatim/tokenizer/legacy_tokenizer.py b/nominatim/tokenizer/legacy_tokenizer.py
index 7b78b22a87066370bba513072b0ace30c7b7078a..36fd5722441a12e92d24434d5dc1317497dd27bc 100644 (file)
--- a/nominatim/tokenizer/legacy_tokenizer.py
+++ b/nominatim/tokenizer/legacy_tokenizer.py
@@ -467,15 +467,17 @@ class LegacyNameAnalyzer(AbstractAnalyzer):
             if key == 'postcode':
                 # Make sure the normalized postcode is present in the word table.
                 if re.search(r'[:,;]', value) is None:
             if key == 'postcode':
                 # Make sure the normalized postcode is present in the word table.
                 if re.search(r'[:,;]', value) is None:

-                    self._cache.add_postcode(self.conn,
-                                             self.normalize_postcode(value))
+                    norm_pc = self.normalize_postcode(value)
+                    token_info.set_postcode(norm_pc)
+                    self._cache.add_postcode(self.conn, norm_pc)

             elif key in ('housenumber', 'streetnumber', 'conscriptionnumber'):
                 hnrs.append(value)
             elif key == 'street':
                 token_info.add_street(self.conn, value)
             elif key == 'place':
                 token_info.add_place(self.conn, value)
             elif key in ('housenumber', 'streetnumber', 'conscriptionnumber'):
                 hnrs.append(value)
             elif key == 'street':
                 token_info.add_street(self.conn, value)
             elif key == 'place':
                 token_info.add_place(self.conn, value)

-            elif not key.startswith('_') and key not in ('country', 'full'):
+            elif not key.startswith('_') \
+                 and key not in ('country', 'full', 'inclusion'):

                 addr_terms.append((key, value))
 
         if hnrs:
                 addr_terms.append((key, value))
 
         if hnrs:


@@ -526,6 +528,11 @@ class _TokenInfo:
             self.data['hnr_tokens'], self.data['hnr'] = cur.fetchone()
 
 
             self.data['hnr_tokens'], self.data['hnr'] = cur.fetchone()
 
 

+    def set_postcode(self, postcode):
+        """ Set or replace the postcode token with the given value.
+        """
+        self.data['postcode'] = postcode
+

     def add_street(self, conn, street):
         """ Add addr:street match terms.
         """
     def add_street(self, conn, street):
         """ Add addr:street match terms.
         """