add japanese sanitizer

[nominatim.git] / nominatim / tokenizer / sanitizers / clean_postcodes.py

diff --git a/nominatim/tokenizer/sanitizers/clean_postcodes.py b/nominatim/tokenizer/sanitizers/clean_postcodes.py
index fbc46fa582215460f7f7e62f6fe63087b3019ab9..5eaea3917c7aea9a2e8047f773cd03ac17990d34 100644 (file)
--- a/nominatim/tokenizer/sanitizers/clean_postcodes.py
+++ b/nominatim/tokenizer/sanitizers/clean_postcodes.py
@@ -15,12 +15,20 @@ Arguments:
                         postcode centroids of a country but is still searchable.
                         When set to 'no', non-conforming postcodes are not
                         searchable either.
+    default-pattern:    Pattern to use, when there is none available for the
+                        country in question. Warning: will not be used for
+                        objects that have no country assigned. These are always
+                        assumed to have no postcode.
 """
+from typing import Callable, Optional, Tuple
+
 from nominatim.data.postcode_format import PostcodeFormatter
+from nominatim.tokenizer.sanitizers.base import ProcessInfo
+from nominatim.tokenizer.sanitizers.config import SanitizerConfig
 
 class _PostcodeSanitizer:
 
-    def __init__(self, config):
+    def __init__(self, config: SanitizerConfig) -> None:
         self.convert_to_address = config.get_bool('convert-to-address', True)
         self.matcher = PostcodeFormatter()
 
@@ -29,7 +37,7 @@ class _PostcodeSanitizer:
             self.matcher.set_default_pattern(default_pattern)
 
 
-    def __call__(self, obj):
+    def __call__(self, obj: ProcessInfo) -> None:
         if not obj.address:
             return
 
@@ -48,22 +56,25 @@ class _PostcodeSanitizer:
                 postcode.set_attr('variant', formatted[1])
 
 
-    def scan(self, postcode, country):
+    def scan(self, postcode: str, country: Optional[str]) -> Optional[Tuple[str, str]]:
         """ Check the postcode for correct formatting and return the
             normalized version. Returns None if the postcode does not
-            correspond to the oficial format of the given country.
+            correspond to the official format of the given country.
         """
         match = self.matcher.match(country, postcode)
         if match is None:
             return None
 
-        return self.matcher.normalize(country, match), ' '.join(match.groups())
+        assert country is not None
+
+        return self.matcher.normalize(country, match),\
+               ' '.join(filter(lambda p: p is not None, match.groups()))
 
 
 
 
-def create(config):
-    """ Create a housenumber processing function.
+def create(config: SanitizerConfig) -> Callable[[ProcessInfo], None]:
+    """ Create a function that filters postcodes by their officially allowed pattern.
     """
 
     return _PostcodeSanitizer(config)