add consistent SPDX copyright headers

[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 93651f3e8b3283d1095c58d9b357332f24b6d7e6..3250c668a9d44b700c49f6c0903d1a064cad3810 100644 (file)
--- a/nominatim/tokenizer/sanitizers/split_name_list.py
+++ b/nominatim/tokenizer/sanitizers/split_name_list.py
@@ -1,15 +1,29 @@
+# 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.
 """
-Name processor that splits name values with multiple values into their components.
+Sanitizer that splits lists of names into their components.
+
+Arguments:
+    delimiters: Define the set of characters to be used for
+                splitting the list. (default: `,;`)
 """
 import re
 
+from nominatim.errors import UsageError
+
 def create(func):
     """ Create a name processing function that splits name values with
-        multiple values into their components. The optional parameter
-        'delimiters' can be used to define the characters that should be used
-        for splitting. The default is ',;'.
+        multiple values into their components.
     """
-    regexp = re.compile('[{}]'.format(func.get('delimiters', ',;')))
+    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)))
 
     def _process(obj):
         if not obj.names:
@@ -21,7 +35,7 @@ def create(func):
             if len(split_names) == 1:
                 new_names.append(name)
             else:
-                new_names.extend(name.clone(name=n) for n in split_names)
+                new_names.extend(name.clone(name=n) for n in split_names if n)
 
         obj.names = new_names