X-Git-Url: https://git.openstreetmap.org./nominatim.git/blobdiff_plain/c42273a4db2d7b4fe05a0be9210901d35e038887..f71478e49c1a9462ca3b94a72d280581d98b8fff:/nominatim/api/search/db_search_builder.py?ds=sidebyside diff --git a/nominatim/api/search/db_search_builder.py b/nominatim/api/search/db_search_builder.py index c0c55a18..fc444aa2 100644 --- a/nominatim/api/search/db_search_builder.py +++ b/nominatim/api/search/db_search_builder.py @@ -11,11 +11,40 @@ from typing import Optional, List, Tuple, Iterator import heapq from nominatim.api.types import SearchDetails, DataLayer -from nominatim.api.search.query import QueryStruct, TokenType, TokenRange, BreakType +from nominatim.api.search.query import QueryStruct, Token, TokenType, TokenRange, BreakType from nominatim.api.search.token_assignment import TokenAssignment import nominatim.api.search.db_search_fields as dbf import nominatim.api.search.db_searches as dbs -from nominatim.api.logging import log + + +def wrap_near_search(categories: List[Tuple[str, str]], + search: dbs.AbstractSearch) -> dbs.NearSearch: + """ Create a new search that wraps the given search in a search + for near places of the given category. + """ + return dbs.NearSearch(penalty=search.penalty, + categories=dbf.WeightedCategories(categories, + [0.0] * len(categories)), + search=search) + + +def build_poi_search(category: List[Tuple[str, str]], + countries: Optional[List[str]]) -> dbs.PoiSearch: + """ Create a new search for places by the given category, possibly + constraint to the given countries. + """ + if countries: + ccs = dbf.WeightedStrings(countries, [0.0] * len(countries)) + else: + ccs = dbf.WeightedStrings([], []) + + class _PoiData(dbf.SearchData): + penalty = 0.0 + qualifiers = dbf.WeightedCategories(category, [0.0] * len(category)) + countries=ccs + + return dbs.PoiSearch(_PoiData()) + class SearchBuilder: """ Build the abstract search queries from token assignments. @@ -67,6 +96,10 @@ class SearchBuilder: sdata.qualifiers = categories categories = None builder = self.build_poi_search(sdata) + elif assignment.housenumber: + hnr_tokens = self.query.get_tokens(assignment.housenumber, + TokenType.HOUSENUMBER) + builder = self.build_housenumber_search(sdata, hnr_tokens, assignment.address) else: builder = self.build_special_search(sdata, assignment.address, bool(categories)) @@ -98,8 +131,8 @@ class SearchBuilder: """ Build abstract search queries for searches that do not involve a named place. """ - if sdata.qualifiers or sdata.housenumbers: - # No special searches over housenumbers or qualifiers supported. + if sdata.qualifiers: + # No special searches over qualifiers supported. return if sdata.countries and not address and not sdata.postcodes \ @@ -107,12 +140,38 @@ class SearchBuilder: yield dbs.CountrySearch(sdata) if sdata.postcodes and (is_category or self.configured_for_postcode): + penalty = 0.0 if sdata.countries else 0.1 if address: sdata.lookups = [dbf.FieldLookup('nameaddress_vector', [t.token for r in address for t in self.query.get_partials_list(r)], 'restrict')] - yield dbs.PostcodeSearch(0.4, sdata) + penalty += 0.2 + yield dbs.PostcodeSearch(penalty, sdata) + + + def build_housenumber_search(self, sdata: dbf.SearchData, hnrs: List[Token], + address: List[TokenRange]) -> Iterator[dbs.AbstractSearch]: + """ Build a simple address search for special entries where the + housenumber is the main name token. + """ + sdata.lookups = [dbf.FieldLookup('name_vector', [t.token for t in hnrs], 'lookup_any')] + + partials = [t for trange in address + for t in self.query.get_partials_list(trange)] + + if len(partials) != 1 or partials[0].count < 10000: + sdata.lookups.append(dbf.FieldLookup('nameaddress_vector', + [t.token for t in partials], 'lookup_all')) + else: + sdata.lookups.append( + dbf.FieldLookup('nameaddress_vector', + [t.token for t + in self.query.get_tokens(address[0], TokenType.WORD)], + 'lookup_any')) + + sdata.housenumbers = dbf.WeightedStrings([], []) + yield dbs.PlaceSearch(0.05, sdata, sum(t.count for t in hnrs)) def build_name_search(self, sdata: dbf.SearchData, @@ -121,8 +180,10 @@ class SearchBuilder: """ Build abstract search queries for simple name or address searches. """ if is_category or not sdata.housenumbers or self.configured_for_housenumbers: - sdata.rankings.append(self.get_name_ranking(name)) - name_penalty = sdata.rankings[-1].normalize_penalty() + ranking = self.get_name_ranking(name) + name_penalty = ranking.normalize_penalty() + if ranking.rankings: + sdata.rankings.append(ranking) for penalty, count, lookup in self.yield_lookups(name, address): sdata.lookups = lookup yield dbs.PlaceSearch(penalty + name_penalty, sdata, count) @@ -134,65 +195,63 @@ class SearchBuilder: be searched for. This takes into account how frequent the terms are and tries to find a lookup that optimizes index use. """ - penalty = 0.0 # extra penalty currently unused - + penalty = 0.0 # extra penalty name_partials = self.query.get_partials_list(name) - exp_name_count = min(t.count for t in name_partials) - addr_partials = [] - for trange in address: - addr_partials.extend(self.query.get_partials_list(trange)) + name_tokens = [t.token for t in name_partials] + + addr_partials = [t for r in address for t in self.query.get_partials_list(r)] addr_tokens = [t.token for t in addr_partials] + partials_indexed = all(t.is_indexed for t in name_partials) \ and all(t.is_indexed for t in addr_partials) + exp_count = min(t.count for t in name_partials) - if (len(name_partials) > 3 or exp_name_count < 1000) and partials_indexed: - # Lookup by name partials, use address partials to restrict results. - lookup = [dbf.FieldLookup('name_vector', - [t.token for t in name_partials], 'lookup_all')] - if addr_tokens: - lookup.append(dbf.FieldLookup('nameaddress_vector', addr_tokens, 'restrict')) - yield penalty, exp_name_count, lookup + if (len(name_partials) > 3 or exp_count < 1000) and partials_indexed: + yield penalty, exp_count, dbf.lookup_by_names(name_tokens, addr_tokens) return - exp_addr_count = min(t.count for t in addr_partials) if addr_partials else exp_name_count - if exp_addr_count < 1000 and partials_indexed: + exp_count = min(exp_count, min(t.count for t in addr_partials)) \ + if addr_partials else exp_count + if exp_count < 1000 and partials_indexed: # Lookup by address partials and restrict results through name terms. - yield penalty, exp_addr_count,\ - [dbf.FieldLookup('name_vector', [t.token for t in name_partials], 'restrict'), - dbf.FieldLookup('nameaddress_vector', addr_tokens, 'lookup_all')] + # Give this a small penalty because lookups in the address index are + # more expensive + yield penalty + exp_count/5000, exp_count,\ + dbf.lookup_by_addr(name_tokens, addr_tokens) return # Partial term to frequent. Try looking up by rare full names first. name_fulls = self.query.get_tokens(name, TokenType.WORD) - rare_names = list(filter(lambda t: t.count < 1000, name_fulls)) + rare_names = list(filter(lambda t: t.count < 10000, 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] - log().var_dump('before', penalty) penalty += 1.2 * sum(t.penalty for t in addr_partials if not t.is_indexed) - log().var_dump('after', penalty) if rare_names: # Any of the full names applies with all of the partials from the address - lookup = [dbf.FieldLookup('name_vector', [t.token for t in rare_names], 'lookup_any')] - if addr_tokens: - lookup.append(dbf.FieldLookup('nameaddress_vector', addr_tokens, 'restrict')) - yield penalty, sum(t.count for t in rare_names), lookup + yield penalty, sum(t.count for t in rare_names),\ + dbf.lookup_by_any_name([t.token for t in rare_names], addr_tokens) # 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 exp_count < 10000: + if all(t.is_indexed for t in name_partials): + lookup = [dbf.FieldLookup('name_vector', name_tokens, '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 >= 10000] + 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')) + penalty += 0.1 * max(0, 5 - len(name_partials) - len(addr_tokens)) + if len(rare_names) == len(name_fulls): + # if there already was a search for all full tokens, + # avoid this if anything has been found + penalty += 0.25 + yield penalty, exp_count, lookup def get_name_ranking(self, trange: TokenRange) -> dbf.FieldRanking: