overhaul the token analysis interface

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

diff --git a/nominatim/tokenizer/token_analysis/postcodes.py b/nominatim/tokenizer/token_analysis/postcodes.py
index e105b132da9ce8ca4420a53bdd6d4f530fd58397..94e936459c0e12ad18aaf8025f73e4468e8ec8d1 100644 (file)
--- a/nominatim/tokenizer/token_analysis/postcodes.py
+++ b/nominatim/tokenizer/token_analysis/postcodes.py
@@ -8,47 +8,58 @@
 Specialized processor for postcodes. Supports a 'lookup' variant of the
 token, which produces variants with optional spaces.
 """
 Specialized processor for postcodes. Supports a 'lookup' variant of the
 token, which produces variants with optional spaces.
 """

+from typing import Any, List

 
 from nominatim.tokenizer.token_analysis.generic_mutation import MutationVariantGenerator
 
 from nominatim.tokenizer.token_analysis.generic_mutation import MutationVariantGenerator

+from nominatim.data.place_name import PlaceName

 
 ### Configuration section
 
 
 ### Configuration section
 

-def configure(rules, normalization_rules): # pylint: disable=W0613
+def configure(*_: Any) -> None:

     """ All behaviour is currently hard-coded.
     """
     return None
 
 ### Analysis section
 
     """ All behaviour is currently hard-coded.
     """
     return None
 
 ### Analysis section
 

-def create(normalizer, transliterator, config): # pylint: disable=W0613
+def create(normalizer: Any, transliterator: Any, config: None) -> 'PostcodeTokenAnalysis': # pylint: disable=W0613

     """ Create a new token analysis instance for this module.
     """
     return PostcodeTokenAnalysis(normalizer, transliterator)
 
     """ Create a new token analysis instance for this module.
     """
     return PostcodeTokenAnalysis(normalizer, transliterator)
 

+

 class PostcodeTokenAnalysis:
 class PostcodeTokenAnalysis:

-    """ Detects common housenumber patterns and normalizes them.
+    """ Special normalization and variant generation for postcodes.
+
+        This analyser must not be used with anything but postcodes as
+        it follows some special rules: the canonial ID is the form that
+        is used for the output. `compute_variants` then needs to ensure that
+        the generated variants once more follow the standard normalization
+        and transliteration, so that postcodes are correctly recognised by
+        the search algorithm.

     """
     """

-    def __init__(self, norm, trans):
+    def __init__(self, norm: Any, trans: Any) -> None:

         self.norm = norm
         self.trans = trans
 
         self.mutator = MutationVariantGenerator(' ', (' ', ''))
 
 
         self.norm = norm
         self.trans = trans
 
         self.mutator = MutationVariantGenerator(' ', (' ', ''))
 
 

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

         """ Return the standard form of the postcode.
         """
         """ Return the standard form of the postcode.
         """

-        return name.strip().upper()
+        return name.name.strip().upper()

 
 
 
 

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

         """ Compute the spelling variants for the given normalized postcode.
 
         """ Compute the spelling variants for the given normalized postcode.
 

-            The official form creates one variant. If a 'lookup version' is
-            given, then it will create variants with optional spaces.
+            Takes the canonical form of the postcode, normalizes it using the
+            standard rules and then creates variants of the result where
+            all spaces are optional.

         """
         # Postcodes follow their own transliteration rules.
         # Make sure at this point, that the terms are normalized in a way
         # that they are searchable with the standard transliteration rules.
         return [self.trans.transliterate(term) for term in
         """
         # Postcodes follow their own transliteration rules.
         # Make sure at this point, that the terms are normalized in a way
         # that they are searchable with the standard transliteration rules.
         return [self.trans.transliterate(term) for term in

-                self.mutator.generate([self.norm.transliterate(norm_name)])]
+                self.mutator.generate([self.norm.transliterate(norm_name)]) if term]