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
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:
'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,
# Partial term to frequent. Try looking up by rare full names first.
name_fulls = self.query.get_tokens(name, TokenType.WORD)
- fulls_count = sum(t.count for t in name_fulls)
- # At this point drop unindexed partials from the address.
- # This might yield wrong results, nothing we can do about that.
- if not partials_indexed:
- addr_tokens = [t.token for t in addr_partials if t.is_indexed]
- penalty += 1.2 * sum(t.penalty for t in addr_partials if not t.is_indexed)
- # Any of the full names applies with all of the partials from the address
- yield penalty, fulls_count / (2**len(addr_partials)),\
- dbf.lookup_by_any_name([t.token for t in name_fulls], addr_tokens,
- 'restrict' if fulls_count < 10000 else 'lookup_all')
+ if name_fulls:
+ fulls_count = sum(t.count for t in name_fulls)
+ # At this point drop unindexed partials from the address.
+ # This might yield wrong results, nothing we can do about that.
+ if not partials_indexed:
+ addr_tokens = [t.token for t in addr_partials if t.is_indexed]
+ penalty += 1.2 * sum(t.penalty for t in addr_partials if not t.is_indexed)
+ # Any of the full names applies with all of the partials from the address
+ yield penalty, fulls_count / (2**len(addr_partials)),\
+ dbf.lookup_by_any_name([t.token for t in name_fulls], addr_tokens,
+ 'restrict' if fulls_count < 10000 else 'lookup_all')
# To catch remaining results, lookup by name and address
# We only do this if there is a reasonable number of results expected.