mirror of
https://github.com/osm-search/Nominatim.git
synced 2026-02-16 15:47:58 +00:00
43 lines
1.2 KiB
Python
43 lines
1.2 KiB
Python
# 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
|
|
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.
|
|
"""
|
|
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:
|
|
return
|
|
|
|
new_names = []
|
|
for name in obj.names:
|
|
split_names = regexp.split(name.name)
|
|
if len(split_names) == 1:
|
|
new_names.append(name)
|
|
else:
|
|
new_names.extend(name.clone(name=n) for n in split_names if n)
|
|
|
|
obj.names = new_names
|
|
|
|
return _process
|