hans/Nominatim
1
0
Fork 1
mirror of https://github.com/osm-search/Nominatim.git synced 2026-03-12 05:44:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

move abbreviation computation into import phase

Browse Source 
This adds precomputation of abbreviated terms for names and removes
abbreviation of terms in the query. Basic import works but still
needs some thorough testing as well as speed improvements during
import.

New dependency for python library datrie.
This commit is contained in:
Sarah Hoffmann
2021-05-28 22:06:13 +02:00
parent 6ba00e6aee
commit 8413075249
10 changed files with 665 additions and 206 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
nominatim/tokenizer/legacy_tokenizer.py
View File

@@ -404,7 +404,7 @@ class LegacyNameAnalyzer:
FROM unnest(%s)n) y
WHERE NOT EXISTS(SELECT * FROM word
WHERE word_token = lookup_token and country_code = %s))
""", (country_code, names, country_code))
""", (country_code, list(names.values()), country_code))
def process_place(self, place):
@@ -422,7 +422,7 @@ class LegacyNameAnalyzer:
country_feature = place.get('country_feature')
if country_feature and re.fullmatch(r'[A-Za-z][A-Za-z]', country_feature):
self.add_country_names(country_feature.lower(), list(names.values()))
self.add_country_names(country_feature.lower(), names)
address = place.get('address')