added additional languages for pakistan in country settings

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

diff --git a/nominatim/tokenizer/icu_tokenizer.py b/nominatim/tokenizer/icu_tokenizer.py
index b553dbc641d708175e8f7281f05cf14cf4673484..4678af66eb08d019b30e38bb8280da108083bd13 100644 (file)
--- a/nominatim/tokenizer/icu_tokenizer.py
+++ b/nominatim/tokenizer/icu_tokenizer.py
@@ -187,7 +187,7 @@ class LegacyICUTokenizer(AbstractTokenizer):
                 @define('CONST_Max_Word_Frequency', 10000000);
                 @define('CONST_Term_Normalization_Rules', "{self.loader.normalization_rules}");
                 @define('CONST_Transliteration', "{self.loader.get_search_rules()}");
-                require_once('{phpdir}/tokenizer/icu_tokenizer.php');"""))
+                require_once('{phpdir}/tokenizer/icu_tokenizer.php');"""), encoding='utf-8')
 
 
     def _save_config(self):
@@ -278,8 +278,7 @@ class LegacyICUNameAnalyzer(AbstractAnalyzer):
                + [(k, v, part_ids.get(v, None)) for k, v in partial_tokens.items()]
 
 
-    @staticmethod
-    def normalize_postcode(postcode):
+    def normalize_postcode(self, postcode):
         """ Convert the postcode to a standardized form.
 
             This function must yield exactly the same result as the SQL function
@@ -483,7 +482,7 @@ class LegacyICUNameAnalyzer(AbstractAnalyzer):
                 if not item.suffix:
                     token_info.add_place(self._compute_partial_tokens(item.name))
             elif not item.kind.startswith('_') and not item.suffix and \
-                 item.kind not in ('country', 'full'):
+                 item.kind not in ('country', 'full', 'inclusion'):
                 token_info.add_address_term(item.kind, self._compute_partial_tokens(item.name))