hans/Nominatim
1
0
Fork 1
mirror of https://github.com/osm-search/Nominatim.git synced 2026-03-13 06:14:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

postcodes: strip leading country codes

Browse Source
This commit is contained in:
Sarah Hoffmann
2022-05-23 11:01:57 +02:00
parent 28ab2f6048
commit baee6f3de0
2 changed files with 11 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
nominatim/tokenizer/sanitizers/clean_postcodes.py
View File

@@ -29,8 +29,9 @@ class _PostcodeMatcher:
raise UsageError("Field 'pattern' required for 'postcode' "
f"for country '{country_code}'")
self.pattern = re.compile(config['pattern'].replace('d', '[0-9]')
.replace('l', '[A-Z]'))
pc_pattern = config['pattern'].replace('d', '[0-9]').replace('l', '[A-Z]')
self.pattern = re.compile(f'(?:{country_code.upper()}[ -]?)?({pc_pattern})')
def normalize(self, postcode):
@@ -39,7 +40,9 @@ class _PostcodeMatcher:
"""
normalized = postcode.strip().upper()
return normalized if self.pattern.fullmatch(normalized) else None
match = self.pattern.fullmatch(normalized)
return match.group(1) if match else None
class _PostcodeSanitizer:

8
test/python/tokenizer/sanitizers/test_clean_postcodes.py
View File

@@ -43,12 +43,14 @@ def test_postcode_no_country_drop(sanitize, country):
assert sanitize(country=country, postcode='23231') == []
@pytest.mark.parametrize("postcode", ('12345', ' 34009 '))
@pytest.mark.parametrize("postcode", ('12345', ' 12345 ', 'de 12345',
'DE12345', 'DE 12345', 'DE-12345'))
def test_postcode_pass_good_format(sanitize, postcode):
assert sanitize(country='de', postcode=postcode) == [('postcode', postcode.strip())]
assert sanitize(country='de', postcode=postcode) == [('postcode', '12345')]
@pytest.mark.parametrize("postcode", ('123456', '', ' ', '.....'))
@pytest.mark.parametrize("postcode", ('123456', '', ' ', '.....',
'DE 12345', 'DEF12345', 'CH 12345'))
@pytest.mark.sanitizer_params(convert_to_address=False)
def test_postcode_drop_bad_format(sanitize, postcode):
assert sanitize(country='de', postcode=postcode) == []