mirror of
https://github.com/osm-search/Nominatim.git
synced 2026-02-26 11:08:13 +00:00
8171fe4571
Sanatizer functions allow to transform name and address tags before they are handed to the tokenizer. Theses transformations are visible only for the tokenizer and thus only have an influence on the search terms and address match terms for a place. Currently two sanitizers are implemented which are responsible for splitting names with multiple values and removing bracket additions. Both was previously hard-coded in the tokenizer.
29 lines
855 B
Python
29 lines
855 B
Python
"""
|
|
Name processor that splits name values with multiple values into their components.
|
|
"""
|
|
import re
|
|
|
|
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 ',;'.
|
|
"""
|
|
regexp = re.compile('[{}]'.format(func.get('delimiters', ',;')))
|
|
|
|
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)
|
|
|
|
obj.names = new_names
|
|
|
|
return _process
|