Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

More tweaks for Python frontend search #3263

Merged
merged 3 commits into from
Nov 29, 2023
Merged

More tweaks for Python frontend search #3263

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
32e7b59
NearSearch needs to inherit penalty from inner search
lonvia Nov 28, 2023
0c72a43
use restrict for housenumber lookups with few numbers
lonvia Nov 25, 2023
3c7a28d
further restrict stop search criterion
lonvia Nov 29, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 10 additions & 3 deletions nominatim/api/search/db_search_builder.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -113,7 +113,10 @@ def build(self, assignment: TokenAssignment) -> Iterator[dbs.AbstractSearch]:
penalty = min(near_items.penalties)
near_items.penalties = [p - penalty for p in near_items.penalties]
for search in builder:
yield dbs.NearSearch(penalty + assignment.penalty, near_items, search)
search_penalty = search.penalty
search.penalty = 0.0
yield dbs.NearSearch(penalty + assignment.penalty + search_penalty,
near_items, search)
else:
for search in builder:
search.penalty += assignment.penalty
Expand Down Expand Up @@ -160,11 +163,15 @@ def build_housenumber_search(self, sdata: dbf.SearchData, hnrs: List[Token],
housenumber is the main name token.
"""
sdata.lookups = [dbf.FieldLookup('name_vector', [t.token for t in hnrs], 'lookup_any')]
expected_count = sum(t.count for t in hnrs)

partials = [t for trange in address
for t in self.query.get_partials_list(trange)]

if len(partials) != 1 or partials[0].count < 10000:
if expected_count < 8000:
sdata.lookups.append(dbf.FieldLookup('nameaddress_vector',
[t.token for t in partials], 'restrict'))
elif len(partials) != 1 or partials[0].count < 10000:
sdata.lookups.append(dbf.FieldLookup('nameaddress_vector',
[t.token for t in partials], 'lookup_all'))
else:
Expand All @@ -175,7 +182,7 @@ def build_housenumber_search(self, sdata: dbf.SearchData, hnrs: List[Token],
'lookup_any'))

sdata.housenumbers = dbf.WeightedStrings([], [])
yield dbs.PlaceSearch(0.05, sdata, sum(t.count for t in hnrs))
yield dbs.PlaceSearch(0.05, sdata, expected_count)


def build_name_search(self, sdata: dbf.SearchData,
Expand Down
4 changes: 2 additions & 2 deletions nominatim/api/search/geocoder.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -79,7 +79,7 @@ async def execute_searches(self, query: QueryStruct,

end_time = dt.datetime.now() + self.timeout

min_ranking = 1000.0
min_ranking = searches[0].penalty + 2.0
prev_penalty = 0.0
for i, search in enumerate(searches):
if search.penalty > prev_penalty and (search.penalty > min_ranking or i > 20):
Expand All @@ -94,7 +94,7 @@ async def execute_searches(self, query: QueryStruct,
prevresult.accuracy = min(prevresult.accuracy, result.accuracy)
else:
results[rhash] = result
min_ranking = min(min_ranking, result.ranking + 0.5, search.penalty + 0.3)
min_ranking = min(min_ranking, result.accuracy * 1.2)
log().result_dump('Results', ((r.accuracy, r) for r in lookup_results))
prev_penalty = search.penalty
if dt.datetime.now() >= end_time:
Expand Down