hans/Nominatim
1
0
Fork 1
mirror of https://github.com/osm-search/Nominatim.git synced 2026-02-16 15:47:58 +00:00
Code Issues Packages Projects Releases Wiki Activity

avoid lookup via partials on frequent words

Browse Source 
Drops expensive searches via partials on terms like 'rue de'.

See #2979.
This commit is contained in:
Sarah Hoffmann
2023-07-05 14:07:11 +02:00
parent 3266daa8fd
commit cc45930ef9
2 changed files with 28 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
nominatim/api/search/db_search_builder.py
View File

@@ -235,19 +235,21 @@ class SearchBuilder:
yield penalty, sum(t.count for t in rare_names), lookup
# To catch remaining results, lookup by name and address
if all(t.is_indexed for t in name_partials):
lookup = [dbf.FieldLookup('name_vector',
[t.token for t in name_partials], 'lookup_all')]
else:
# we don't have the partials, try with the non-rare names
non_rare_names = [t.token for t in name_fulls if t.count >= 1000]
if not non_rare_names:
return
lookup = [dbf.FieldLookup('name_vector', non_rare_names, 'lookup_any')]
if addr_tokens:
lookup.append(dbf.FieldLookup('nameaddress_vector', addr_tokens, 'lookup_all'))
yield penalty + 0.1 * max(0, 5 - len(name_partials) - len(addr_tokens)),\
min(exp_name_count, exp_addr_count), lookup
# We only do this if there is a reasonable number of results expected.
if min(exp_name_count, exp_addr_count) < 10000:
if all(t.is_indexed for t in name_partials):
lookup = [dbf.FieldLookup('name_vector',
[t.token for t in name_partials], 'lookup_all')]
else:
# we don't have the partials, try with the non-rare names
non_rare_names = [t.token for t in name_fulls if t.count >= 1000]
if not non_rare_names:
return
lookup = [dbf.FieldLookup('name_vector', non_rare_names, 'lookup_any')]
if addr_tokens:
lookup.append(dbf.FieldLookup('nameaddress_vector', addr_tokens, 'lookup_all'))
yield penalty + 0.1 * max(0, 5 - len(name_partials) - len(addr_tokens)),\
min(exp_name_count, exp_addr_count), lookup
def get_name_ranking(self, trange: TokenRange) -> dbf.FieldRanking: