generalize filter-kind parameter for sanatizers

[nominatim.git] / nominatim / tokenizer / sanitizers / split_name_list.py

diff --git a/nominatim/tokenizer/sanitizers/split_name_list.py b/nominatim/tokenizer/sanitizers/split_name_list.py
index 86385985053ef2623c1c016d458c2d51ae420d44..b2a2045fd645c8ce8c42af33c2c8f74fcfcc240e 100644 (file)
--- a/nominatim/tokenizer/sanitizers/split_name_list.py
+++ b/nominatim/tokenizer/sanitizers/split_name_list.py
@@ -1,23 +1,24 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# This file is part of Nominatim. (https://nominatim.org)
+#
+# Copyright (C) 2022 by the Nominatim developer community.
+# For a full list of authors see the git log.

 """
 Sanitizer that splits lists of names into their components.
 
 Arguments:
     delimiters: Define the set of characters to be used for
 """
 Sanitizer that splits lists of names into their components.
 
 Arguments:
     delimiters: Define the set of characters to be used for

-                splitting the list. (default: `,;`)
+                splitting the list. (default: ',;')

 """
 """

-import re
-

 from nominatim.errors import UsageError
 from nominatim.errors import UsageError

+from nominatim.tokenizer.sanitizers.helpers import create_split_regex

 
 def create(func):
     """ Create a name processing function that splits name values with
         multiple values into their components.
     """
 
 def create(func):
     """ Create a name processing function that splits name values with
         multiple values into their components.
     """

-    delimiter_set = set(func.get('delimiters', ',;'))
-    if not delimiter_set:
-        raise UsageError("Set of delimiters in split-name-list sanitizer is empty.")
-
-    regexp = re.compile('\\s*[{}]\\s*'.format(''.join('\\' + d for d in delimiter_set)))
+    regexp = create_split_regex(func)

 
     def _process(obj):
         if not obj.names:
 
     def _process(obj):
         if not obj.names: