X-Git-Url: https://git.openstreetmap.org./nominatim.git/blobdiff_plain/dcfb228c9a0035d72de6c3a66f7f329e72cd960e..b06f5fddcbe9c716afddde1e6d02df6f43ec1081:/nominatim/api/search/db_search_builder.py?ds=inline diff --git a/nominatim/api/search/db_search_builder.py b/nominatim/api/search/db_search_builder.py index 9ea0cfed..fd8cc7af 100644 --- a/nominatim/api/search/db_search_builder.py +++ b/nominatim/api/search/db_search_builder.py @@ -7,15 +7,15 @@ """ Convertion from token assignment to an abstract DB search. """ -from typing import Optional, List, Tuple, Iterator +from typing import Optional, List, Tuple, Iterator, Dict 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 +import nominatim.api.search.db_search_lookups as lookups def wrap_near_search(categories: List[Tuple[str, str]], @@ -90,27 +90,38 @@ class SearchBuilder: if sdata is None: return - categories = self.get_search_categories(assignment) + near_items = self.get_near_items(assignment) + if near_items is not None and not near_items: + return # impossible compbination of near items and category parameter if assignment.name is None: - if categories and not sdata.postcodes: - sdata.qualifiers = categories - categories = None + if near_items and not sdata.postcodes: + sdata.qualifiers = near_items + near_items = 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)) + bool(near_items)) else: builder = self.build_name_search(sdata, assignment.name, assignment.address, - bool(categories)) + bool(near_items)) - if categories: - penalty = min(categories.penalties) - categories.penalties = [p - penalty for p in categories.penalties] + if near_items: + penalty = min(near_items.penalties) + near_items.penalties = [p - penalty for p in near_items.penalties] for search in builder: - yield dbs.NearSearch(penalty, categories, search) + search_penalty = search.penalty + search.penalty = 0.0 + yield dbs.NearSearch(penalty + assignment.penalty + search_penalty, + near_items, search) else: - yield from builder + for search in builder: + search.penalty += assignment.penalty + yield search def build_poi_search(self, sdata: dbf.SearchData) -> Iterator[dbs.AbstractSearch]: @@ -128,8 +139,8 @@ 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 \ @@ -137,12 +148,42 @@ 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) + lookups.Restrict)] + 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], lookups.LookupAny)] + 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 expected_count < 8000: + sdata.lookups.append(dbf.FieldLookup('nameaddress_vector', + [t.token for t in partials], lookups.Restrict)) + elif len(partials) != 1 or partials[0].count < 10000: + sdata.lookups.append(dbf.FieldLookup('nameaddress_vector', + [t.token for t in partials], lookups.LookupAll)) + else: + sdata.lookups.append( + dbf.FieldLookup('nameaddress_vector', + [t.token for t + in self.query.get_tokens(address[0], TokenType.WORD)], + lookups.LookupAny)) + + sdata.housenumbers = dbf.WeightedStrings([], []) + yield dbs.PlaceSearch(0.05, sdata, expected_count) def build_name_search(self, sdata: dbf.SearchData, @@ -151,8 +192,10 @@ 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) @@ -164,65 +207,44 @@ 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) / (2**(len(name_partials) - 1)) - 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 - 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: - # 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')] + if (len(name_partials) > 3 or exp_count < 8000) and partials_indexed: + yield penalty, exp_count, dbf.lookup_by_names(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)) - # 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: + 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 - 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, fulls_count / (2**len(addr_partials)),\ + dbf.lookup_by_any_name([t.token for t in name_fulls], + addr_tokens, fulls_count > 10000) # 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. + exp_count = exp_count / (2**len(addr_partials)) if addr_partials else exp_count + if exp_count < 10000 and all(t.is_indexed for t in name_partials): + lookup = [dbf.FieldLookup('name_vector', name_tokens, lookups.LookupAll)] + if addr_tokens: + lookup.append(dbf.FieldLookup('nameaddress_vector', addr_tokens, lookups.LookupAll)) + penalty += 0.35 * max(0, 5 - len(name_partials) - len(addr_tokens)) + yield penalty, exp_count, lookup def get_name_ranking(self, trange: TokenRange) -> dbf.FieldRanking: @@ -310,8 +332,15 @@ class SearchBuilder: self.query.get_tokens(assignment.postcode, TokenType.POSTCODE)) if assignment.qualifier: - sdata.set_qualifiers(self.query.get_tokens(assignment.qualifier, - TokenType.QUALIFIER)) + tokens = self.query.get_tokens(assignment.qualifier, TokenType.QUALIFIER) + if self.details.categories: + tokens = [t for t in tokens if t.get_category() in self.details.categories] + if not tokens: + return None + sdata.set_qualifiers(tokens) + elif self.details.categories: + sdata.qualifiers = dbf.WeightedCategories(self.details.categories, + [0.0] * len(self.details.categories)) if assignment.address: sdata.set_ranking([self.get_addr_ranking(r) for r in assignment.address]) @@ -321,23 +350,22 @@ class SearchBuilder: return sdata - def get_search_categories(self, - assignment: TokenAssignment) -> Optional[dbf.WeightedCategories]: - """ Collect tokens for category search or use the categories + def get_near_items(self, assignment: TokenAssignment) -> Optional[dbf.WeightedCategories]: + """ Collect tokens for near items search or use the categories requested per parameter. Returns None if no category search is requested. """ - if assignment.category: - tokens = [t for t in self.query.get_tokens(assignment.category, - TokenType.CATEGORY) - if not self.details.categories - or t.get_category() in self.details.categories] - return dbf.WeightedCategories([t.get_category() for t in tokens], - [t.penalty for t in tokens]) - - if self.details.categories: - return dbf.WeightedCategories(self.details.categories, - [0.0] * len(self.details.categories)) + if assignment.near_item: + tokens: Dict[Tuple[str, str], float] = {} + for t in self.query.get_tokens(assignment.near_item, TokenType.NEAR_ITEM): + cat = t.get_category() + # The category of a near search will be that of near_item. + # Thus, if search is restricted to a category parameter, + # the two sets must intersect. + if (not self.details.categories or cat in self.details.categories)\ + and t.penalty < tokens.get(cat, 1000.0): + tokens[cat] = t.penalty + return dbf.WeightedCategories(list(tokens.keys()), list(tokens.values())) return None