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

handle postcodes properly on word table updates

Browse Source 
update_postcodes_from_db() needs to do the full postcode treatment
in order to derive the correct word table entries.
This commit is contained in:
Sarah Hoffmann
2022-06-21 22:05:35 +02:00
parent 5be320368c
commit 612d34930b
5 changed files with 214 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
nominatim/tokenizer/token_analysis/postcodes.py
View File

@@ -25,8 +25,18 @@ def create(normalizer, transliterator, config): # pylint: disable=W0613
"""
return PostcodeTokenAnalysis(normalizer, transliterator)
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: `normalize` doesn't necessarily
need to return a standard form as per normalization rules. It
needs to return the canonical form of the postcode that is also
used for output. `get_variants_ascii` 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):
self.norm = norm
@@ -44,11 +54,12 @@ class PostcodeTokenAnalysis:
def get_variants_ascii(self, norm_name):
""" 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
self.mutator.generate([self.norm.transliterate(norm_name)])]
self.mutator.generate([self.norm.transliterate(norm_name)]) if term]