hans/Nominatim
1
0
Fork 1
mirror of https://github.com/osm-search/Nominatim.git synced 2026-02-26 11:08:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #3862 from mtmail/skip-all-zero-postcodes

Browse Source 
Postcode sanetizer now skips values which are only zeros
This commit is contained in:
Sarah Hoffmann
2025-10-31 10:36:05 +01:00
committed by GitHub
parent 6a2d2daad5 362088775f
commit 303ac42b47
2 changed files with 13 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
src/nominatim_db/data/postcode_format.py
View File

@@ -29,6 +29,9 @@ class CountryPostcodeMatcher:
self.norm_pattern = re.compile(f'\\s*(?:{country_code.upper()}[ -]?)?({pc_pattern})\\s*') self.norm_pattern = re.compile(f'\\s*(?:{country_code.upper()}[ -]?)?({pc_pattern})\\s*')
self.pattern = re.compile(pc_pattern) self.pattern = re.compile(pc_pattern)
# We want to exclude 0000, 00-000, 000 00 etc
self.zero_pattern = re.compile(r'^[0\- ]+$')
self.output = config.get('output', r'\g<0>') self.output = config.get('output', r'\g<0>')
def match(self, postcode: str) -> Optional[Match[str]]: def match(self, postcode: str) -> Optional[Match[str]]:
@@ -40,7 +43,10 @@ class CountryPostcodeMatcher:
normalized = self.norm_pattern.fullmatch(postcode.upper()) normalized = self.norm_pattern.fullmatch(postcode.upper())
if normalized: if normalized:
return self.pattern.fullmatch(normalized.group(1)) match = self.pattern.fullmatch(normalized.group(1))
if match and self.zero_pattern.match(match.string):
return None
return match
return None return None

6
test/python/tokenizer/sanitizers/test_clean_postcodes.py
View File

@@ -237,3 +237,9 @@ def test_postcode_default_pattern_pass(sanitize, postcode):
@pytest.mark.sanitizer_params(convert_to_address=False, default_pattern='[A-Z0-9- ]{3,12}') @pytest.mark.sanitizer_params(convert_to_address=False, default_pattern='[A-Z0-9- ]{3,12}')
def test_postcode_default_pattern_fail(sanitize, postcode): def test_postcode_default_pattern_fail(sanitize, postcode):
assert sanitize(country='an', postcode=postcode) == [] assert sanitize(country='an', postcode=postcode) == []
@pytest.mark.parametrize("postcode", ('00000', '00-000', 'PL-00000', 'PL 00-000'))
@pytest.mark.sanitizer_params(convert_to_address=False)
def test_postcode_zeros(sanitize, postcode):
assert sanitize(country='pl', postcode=postcode) == []