add lookup of postcdoe data

[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 3250c668a9d44b700c49f6c0903d1a064cad3810..7d0667b4e323ce1aa060c3f0ae2738505173a476 100644 (file)
--- a/nominatim/tokenizer/sanitizers/split_name_list.py
+++ b/nominatim/tokenizer/sanitizers/split_name_list.py
@@ -9,23 +9,20 @@ Sanitizer that splits lists of names into their components.
 
 Arguments:
     delimiters: Define the set of characters to be used for
 
 Arguments:
     delimiters: Define the set of characters to be used for

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

 """
 """

-import re
+from typing import Callable

 
 

-from nominatim.errors import UsageError
+from nominatim.tokenizer.sanitizers.base import ProcessInfo
+from nominatim.tokenizer.sanitizers.config import SanitizerConfig

 
 

-def create(func):
+def create(config: SanitizerConfig) -> Callable[[ProcessInfo], None]:

     """ Create a name processing function that splits name values with
         multiple values into their components.
     """
     """ 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 = config.get_delimiter()

 
 

-    regexp = re.compile('\\s*[{}]\\s*'.format(''.join('\\' + d for d in delimiter_set)))
-
-    def _process(obj):
+    def _process(obj: ProcessInfo) -> None:

         if not obj.names:
             return
 
         if not obj.names:
             return