safety-screen/Nominatim
1
0
Fork 0
forked from hans/Nominatim
Code Pull Requests Activity

more agressively reduce expected count for multi-word terms

Browse Source 
Improves searching of non-latin scripts with forced token spaces.
This commit is contained in:
Sarah Hoffmann
2025-03-31 11:06:21 +02:00
parent 46579f08e4
commit 51847ebfeb
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/nominatim_api/search/db_search_builder.py
View File

@@ -208,7 +208,7 @@ class SearchBuilder:
addr_partials = [t for r in address for t in self.query.get_partials_list(r)] addr_partials = [t for r in address for t in self.query.get_partials_list(r)]
addr_tokens = list({t.token for t in addr_partials}) addr_tokens = list({t.token for t in addr_partials})
exp_count = min(t.count for t in name_partials.values()) / (2**(len(name_partials) - 1)) exp_count = min(t.count for t in name_partials.values()) / (3**(len(name_partials) - 1))
if (len(name_partials) > 3 or exp_count < 8000): if (len(name_partials) > 3 or exp_count < 8000):
yield penalty, exp_count, dbf.lookup_by_names(list(name_partials.keys()), addr_tokens) yield penalty, exp_count, dbf.lookup_by_names(list(name_partials.keys()), addr_tokens)