From f289db9bfe21c5a725e751be98e2b824026e2310 Mon Sep 17 00:00:00 2001 From: Sarah Hoffmann Date: Mon, 16 Sep 2024 12:21:14 +0200 Subject: [PATCH] lift restrictions on search with frequent terms slightly --- src/nominatim_api/search/db_search_builder.py | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) diff --git a/src/nominatim_api/search/db_search_builder.py b/src/nominatim_api/search/db_search_builder.py index 6453509e..0269cf1f 100644 --- a/src/nominatim_api/search/db_search_builder.py +++ b/src/nominatim_api/search/db_search_builder.py @@ -227,7 +227,7 @@ class SearchBuilder: yield penalty, exp_count, dbf.lookup_by_names(list(name_partials.keys()), addr_tokens) return - addr_count = min(t.addr_count for t in addr_partials) if addr_partials else 30000 + addr_count = min(t.addr_count for t in addr_partials) if addr_partials else 50000 # Partial term to frequent. Try looking up by rare full names first. name_fulls = self.query.get_tokens(name, TokenType.WORD) if name_fulls: @@ -235,7 +235,7 @@ class SearchBuilder: if partials_indexed: penalty += 1.2 * sum(t.penalty for t in addr_partials if not t.is_indexed) - if fulls_count < 50000 or addr_count < 30000: + if fulls_count < 80000 or addr_count < 50000: yield penalty,fulls_count / (2**len(addr_tokens)), \ self.get_full_name_ranking(name_fulls, addr_partials, fulls_count > 30000 / max(1, len(addr_tokens))) @@ -287,13 +287,7 @@ class SearchBuilder: # This might yield wrong results, nothing we can do about that. if use_lookup: addr_restrict_tokens = [] - addr_lookup_tokens = [] - for t in addr_partials: - if t.is_indexed: - if t.addr_count > 20000: - addr_restrict_tokens.append(t.token) - else: - addr_lookup_tokens.append(t.token) + addr_lookup_tokens = [t.token for t in addr_partials if t.is_indexed] else: addr_restrict_tokens = [t.token for t in addr_partials if t.is_indexed] addr_lookup_tokens = [] -- 2.39.5