Merge pull request #3383 from lonvia/window-searches

[nominatim.git] / nominatim / tokenizer / token_analysis / housenumbers.py

diff --git a/nominatim/tokenizer/token_analysis/housenumbers.py b/nominatim/tokenizer/token_analysis/housenumbers.py
index e3048a0912e5c20b0f71fca83472da55b4424b3f..a8ad3ecb3658d6f74a55caa305160477f081159e 100644 (file)
--- a/nominatim/tokenizer/token_analysis/housenumbers.py
+++ b/nominatim/tokenizer/token_analysis/housenumbers.py
@@ -11,6 +11,7 @@ and creates variants for them.
 from typing import Any, List, cast
 import re
 
 from typing import Any, List, cast
 import re
 

+from nominatim.data.place_name import PlaceName

 from nominatim.tokenizer.token_analysis.generic_mutation import MutationVariantGenerator
 
 RE_NON_DIGIT = re.compile('[^0-9]')
 from nominatim.tokenizer.token_analysis.generic_mutation import MutationVariantGenerator
 
 RE_NON_DIGIT = re.compile('[^0-9]')


@@ -42,14 +43,14 @@ class HousenumberTokenAnalysis:
 
         self.mutator = MutationVariantGenerator('␣', (' ', ''))
 
 
         self.mutator = MutationVariantGenerator('␣', (' ', ''))
 

-    def normalize(self, name: str) -> str:
+    def get_canonical_id(self, name: PlaceName) -> str:

         """ Return the normalized form of the housenumber.
         """
         # shortcut for number-only numbers, which make up 90% of the data.
         """ Return the normalized form of the housenumber.
         """
         # shortcut for number-only numbers, which make up 90% of the data.

-        if RE_NON_DIGIT.search(name) is None:
-            return name
+        if RE_NON_DIGIT.search(name.name) is None:
+            return name.name

 
 

-        norm = cast(str, self.trans.transliterate(self.norm.transliterate(name)))
+        norm = cast(str, self.trans.transliterate(self.norm.transliterate(name.name)))

         # If there is a significant non-numeric part, use as is.
         if RE_NAMED_PART.search(norm) is None:
             # Otherwise add optional spaces between digits and letters.
         # If there is a significant non-numeric part, use as is.
         if RE_NAMED_PART.search(norm) is None:
             # Otherwise add optional spaces between digits and letters.


@@ -61,7 +62,7 @@ class HousenumberTokenAnalysis:
 
         return norm
 
 
         return norm
 

-    def get_variants_ascii(self, norm_name: str) -> List[str]:
+    def compute_variants(self, norm_name: str) -> List[str]:

         """ Compute the spelling variants for the given normalized housenumber.
 
             Generates variants for optional spaces (marked with '␣').
         """ Compute the spelling variants for the given normalized housenumber.
 
             Generates variants for optional spaces (marked with '␣').