1 # SPDX-License-Identifier: GPL-2.0-only
3 # This file is part of Nominatim. (https://nominatim.org)
5 # Copyright (C) 2022 by the Nominatim developer community.
6 # For a full list of authors see the git log.
8 Specialized processor for postcodes. Supports a 'lookup' variant of the
9 token, which produces variants with optional spaces.
11 from typing import Any, List
13 from nominatim.tokenizer.token_analysis.generic_mutation import MutationVariantGenerator
14 from nominatim.data.place_name import PlaceName
16 ### Configuration section
18 def configure(*_: Any) -> None:
19 """ All behaviour is currently hard-coded.
25 def create(normalizer: Any, transliterator: Any, config: None) -> 'PostcodeTokenAnalysis': # pylint: disable=W0613
26 """ Create a new token analysis instance for this module.
28 return PostcodeTokenAnalysis(normalizer, transliterator)
31 class PostcodeTokenAnalysis:
32 """ Special normalization and variant generation for postcodes.
34 This analyser must not be used with anything but postcodes as
35 it follows some special rules: the canonial ID is the form that
36 is used for the output. `compute_variants` then needs to ensure that
37 the generated variants once more follow the standard normalization
38 and transliteration, so that postcodes are correctly recognised by
41 def __init__(self, norm: Any, trans: Any) -> None:
45 self.mutator = MutationVariantGenerator(' ', (' ', ''))
48 def get_canonical_id(self, name: PlaceName) -> str:
49 """ Return the standard form of the postcode.
51 return name.name.strip().upper()
54 def compute_variants(self, norm_name: str) -> List[str]:
55 """ Compute the spelling variants for the given normalized postcode.
57 Takes the canonical form of the postcode, normalizes it using the
58 standard rules and then creates variants of the result where
59 all spaces are optional.
61 # Postcodes follow their own transliteration rules.
62 # Make sure at this point, that the terms are normalized in a way
63 # that they are searchable with the standard transliteration rules.
64 return [self.trans.transliterate(term) for term in
65 self.mutator.generate([self.norm.transliterate(norm_name)]) if term]