hans/Nominatim
1
0
Fork 1
mirror of https://github.com/osm-search/Nominatim.git synced 2026-02-16 05:18:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

apply variants by languages

Browse Source 
Adds a tagger for names by language so that the analyzer of that
language is used. Thus variants are now only applied to names
in the specific language and only tag name tags, no longer to
reference-like tags.
This commit is contained in:
Sarah Hoffmann
2021-10-05 17:18:10 +02:00
parent d35400a7d7
commit 97a10ec218
8 changed files with 307 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
test/python/tokenizer/token_analysis/test_generic.py
View File

@@ -40,7 +40,7 @@ def cfgfile(def_config, tmp_path):
def get_normalized_variants(proc, name):
return proc.get_variants_ascii(proc.get_normalized(name))
return proc.analysis[None].get_variants_ascii(proc.normalizer.transliterate(name).strip())
def test_variants_empty(cfgfile):
@@ -99,6 +99,6 @@ def test_search_normalized(cfgfile):
config = cfgfile('~street => s,st', 'master => mstr')
proc = ICURuleLoader(config).make_token_analysis()
assert proc.get_search_normalized('Master Street') == 'master street'
assert proc.get_search_normalized('Earnes St') == 'earnes st'
assert proc.get_search_normalized('Nostreet') == 'nostreet'
assert proc.search.transliterate('Master Street').strip() == 'master street'
assert proc.search.transliterate('Earnes St').strip() == 'earnes st'
assert proc.search.transliterate('Nostreet').strip() == 'nostreet'