nominatim/api/search/db_search_builder.py

   1 # SPDX-License-Identifier: GPL-3.0-or-later
   2 #
   3 # This file is part of Nominatim. (https://nominatim.org)
   4 #
   5 # Copyright (C) 2023 by the Nominatim developer community.
   6 # For a full list of authors see the git log.
   7 """
   8 Conversion from token assignment to an abstract DB search.
   9 """
  10 from typing import Optional, List, Tuple, Iterator, Dict
  11 import heapq
  12
  13 from nominatim.api.types import SearchDetails, DataLayer
  14 from nominatim.api.search.query import QueryStruct, Token, TokenType, TokenRange, BreakType
  15 from nominatim.api.search.token_assignment import TokenAssignment
  16 import nominatim.api.search.db_search_fields as dbf
  17 import nominatim.api.search.db_searches as dbs
  18 import nominatim.api.search.db_search_lookups as lookups
  19
  20
  21 def wrap_near_search(categories: List[Tuple[str, str]],
  22                      search: dbs.AbstractSearch) -> dbs.NearSearch:
  23     """ Create a new search that wraps the given search in a search
  24         for near places of the given category.
  25     """
  26     return dbs.NearSearch(penalty=search.penalty,
  27                           categories=dbf.WeightedCategories(categories,
  28                                                             [0.0] * len(categories)),
  29                           search=search)
  30
  31
  32 def build_poi_search(category: List[Tuple[str, str]],
  33                      countries: Optional[List[str]]) -> dbs.PoiSearch:
  34     """ Create a new search for places by the given category, possibly
  35         constraint to the given countries.
  36     """
  37     if countries:
  38         ccs = dbf.WeightedStrings(countries, [0.0] * len(countries))
  39     else:
  40         ccs = dbf.WeightedStrings([], [])
  41
  42     class _PoiData(dbf.SearchData):
  43         penalty = 0.0
  44         qualifiers = dbf.WeightedCategories(category, [0.0] * len(category))
  45         countries=ccs
  46
  47     return dbs.PoiSearch(_PoiData())
  48
  49
  50 class SearchBuilder:
  51     """ Build the abstract search queries from token assignments.
  52     """
  53
  54     def __init__(self, query: QueryStruct, details: SearchDetails) -> None:
  55         self.query = query
  56         self.details = details
  57
  58
  59     @property
  60     def configured_for_country(self) -> bool:
  61         """ Return true if the search details are configured to
  62             allow countries in the result.
  63         """
  64         return self.details.min_rank <= 4 and self.details.max_rank >= 4 \
  65                and self.details.layer_enabled(DataLayer.ADDRESS)
  66
  67
  68     @property
  69     def configured_for_postcode(self) -> bool:
  70         """ Return true if the search details are configured to
  71             allow postcodes in the result.
  72         """
  73         return self.details.min_rank <= 5 and self.details.max_rank >= 11\
  74                and self.details.layer_enabled(DataLayer.ADDRESS)
  75
  76
  77     @property
  78     def configured_for_housenumbers(self) -> bool:
  79         """ Return true if the search details are configured to
  80             allow addresses in the result.
  81         """
  82         return self.details.max_rank >= 30 \
  83                and self.details.layer_enabled(DataLayer.ADDRESS)
  84
  85
  86     def build(self, assignment: TokenAssignment) -> Iterator[dbs.AbstractSearch]:
  87         """ Yield all possible abstract searches for the given token assignment.
  88         """
  89         sdata = self.get_search_data(assignment)
  90         if sdata is None:
  91             return
  92
  93         near_items = self.get_near_items(assignment)
  94         if near_items is not None and not near_items:
  95             return # impossible compbination of near items and category parameter
  96
  97         if assignment.name is None:
  98             if near_items and not sdata.postcodes:
  99                 sdata.qualifiers = near_items
 100                 near_items = None
 101                 builder = self.build_poi_search(sdata)
 102             elif assignment.housenumber:
 103                 hnr_tokens = self.query.get_tokens(assignment.housenumber,
 104                                                    TokenType.HOUSENUMBER)
 105                 builder = self.build_housenumber_search(sdata, hnr_tokens, assignment.address)
 106             else:
 107                 builder = self.build_special_search(sdata, assignment.address,
 108                                                     bool(near_items))
 109         else:
 110             builder = self.build_name_search(sdata, assignment.name, assignment.address,
 111                                              bool(near_items))
 112
 113         if near_items:
 114             penalty = min(near_items.penalties)
 115             near_items.penalties = [p - penalty for p in near_items.penalties]
 116             for search in builder:
 117                 search_penalty = search.penalty
 118                 search.penalty = 0.0
 119                 yield dbs.NearSearch(penalty + assignment.penalty + search_penalty,
 120                                      near_items, search)
 121         else:
 122             for search in builder:
 123                 search.penalty += assignment.penalty
 124                 yield search
 125
 126
 127     def build_poi_search(self, sdata: dbf.SearchData) -> Iterator[dbs.AbstractSearch]:
 128         """ Build abstract search query for a simple category search.
 129             This kind of search requires an additional geographic constraint.
 130         """
 131         if not sdata.housenumbers \
 132            and ((self.details.viewbox and self.details.bounded_viewbox) or self.details.near):
 133             yield dbs.PoiSearch(sdata)
 134
 135
 136     def build_special_search(self, sdata: dbf.SearchData,
 137                              address: List[TokenRange],
 138                              is_category: bool) -> Iterator[dbs.AbstractSearch]:
 139         """ Build abstract search queries for searches that do not involve
 140             a named place.
 141         """
 142         if sdata.qualifiers:
 143             # No special searches over qualifiers supported.
 144             return
 145
 146         if sdata.countries and not address and not sdata.postcodes \
 147            and self.configured_for_country:
 148             yield dbs.CountrySearch(sdata)
 149
 150         if sdata.postcodes and (is_category or self.configured_for_postcode):
 151             penalty = 0.0 if sdata.countries else 0.1
 152             if address:
 153                 sdata.lookups = [dbf.FieldLookup('nameaddress_vector',
 154                                                  [t.token for r in address
 155                                                   for t in self.query.get_partials_list(r)],
 156                                                  lookups.Restrict)]
 157                 penalty += 0.2
 158             yield dbs.PostcodeSearch(penalty, sdata)
 159
 160
 161     def build_housenumber_search(self, sdata: dbf.SearchData, hnrs: List[Token],
 162                                  address: List[TokenRange]) -> Iterator[dbs.AbstractSearch]:
 163         """ Build a simple address search for special entries where the
 164             housenumber is the main name token.
 165         """
 166         sdata.lookups = [dbf.FieldLookup('name_vector', [t.token for t in hnrs], lookups.LookupAny)]
 167         expected_count = sum(t.count for t in hnrs)
 168
 169         partials = {t.token: t.count for trange in address
 170                        for t in self.query.get_partials_list(trange)}
 171
 172         if expected_count < 8000:
 173             sdata.lookups.append(dbf.FieldLookup('nameaddress_vector',
 174                                                  list(partials), lookups.Restrict))
 175         elif len(partials) != 1 or list(partials.values())[0] < 10000:
 176             sdata.lookups.append(dbf.FieldLookup('nameaddress_vector',
 177                                                  list(partials), lookups.LookupAll))
 178         else:
 179             addr_fulls = [t.token for t
 180                           in self.query.get_tokens(address[0], TokenType.WORD)]
 181             if len(addr_fulls) > 5:
 182                 return
 183             sdata.lookups.append(
 184                 dbf.FieldLookup('nameaddress_vector', addr_fulls, lookups.LookupAny))
 185
 186         sdata.housenumbers = dbf.WeightedStrings([], [])
 187         yield dbs.PlaceSearch(0.05, sdata, expected_count)
 188
 189
 190     def build_name_search(self, sdata: dbf.SearchData,
 191                           name: TokenRange, address: List[TokenRange],
 192                           is_category: bool) -> Iterator[dbs.AbstractSearch]:
 193         """ Build abstract search queries for simple name or address searches.
 194         """
 195         if is_category or not sdata.housenumbers or self.configured_for_housenumbers:
 196             ranking = self.get_name_ranking(name)
 197             name_penalty = ranking.normalize_penalty()
 198             if ranking.rankings:
 199                 sdata.rankings.append(ranking)
 200             for penalty, count, lookup in self.yield_lookups(name, address):
 201                 sdata.lookups = lookup
 202                 yield dbs.PlaceSearch(penalty + name_penalty, sdata, count)
 203
 204
 205     def yield_lookups(self, name: TokenRange, address: List[TokenRange])\
 206                           -> Iterator[Tuple[float, int, List[dbf.FieldLookup]]]:
 207         """ Yield all variants how the given name and address should best
 208             be searched for. This takes into account how frequent the terms
 209             are and tries to find a lookup that optimizes index use.
 210         """
 211         penalty = 0.0 # extra penalty
 212         name_partials = {t.token: t for t in self.query.get_partials_list(name)}
 213
 214         addr_partials = [t for r in address for t in self.query.get_partials_list(r)]
 215         addr_tokens = list({t.token for t in addr_partials})
 216
 217         partials_indexed = all(t.is_indexed for t in name_partials.values()) \
 218                            and all(t.is_indexed for t in addr_partials)
 219         exp_count = min(t.count for t in name_partials.values()) / (2**(len(name_partials) - 1))
 220
 221         if (len(name_partials) > 3 or exp_count < 8000) and partials_indexed:
 222             yield penalty, exp_count, dbf.lookup_by_names(list(name_partials.keys()), addr_tokens)
 223             return
 224
 225         # Partial term to frequent. Try looking up by rare full names first.
 226         name_fulls = self.query.get_tokens(name, TokenType.WORD)
 227         if name_fulls:
 228             fulls_count = sum(t.count for t in name_fulls)
 229             # At this point drop unindexed partials from the address.
 230             # This might yield wrong results, nothing we can do about that.
 231             if not partials_indexed:
 232                 addr_tokens = [t.token for t in addr_partials if t.is_indexed]
 233                 penalty += 1.2 * sum(t.penalty for t in addr_partials if not t.is_indexed)
 234             # Any of the full names applies with all of the partials from the address
 235             yield penalty, fulls_count / (2**len(addr_tokens)),\
 236                   dbf.lookup_by_any_name([t.token for t in name_fulls],
 237                                          addr_tokens,
 238                                          fulls_count > 30000 / max(1, len(addr_tokens)))
 239
 240         # To catch remaining results, lookup by name and address
 241         # We only do this if there is a reasonable number of results expected.
 242         exp_count = exp_count / (2**len(addr_tokens)) if addr_tokens else exp_count
 243         if exp_count < 10000 and all(t.is_indexed for t in name_partials.values()):
 244             lookup = [dbf.FieldLookup('name_vector', list(name_partials.keys()), lookups.LookupAll)]
 245             if addr_tokens:
 246                 lookup.append(dbf.FieldLookup('nameaddress_vector', addr_tokens, lookups.LookupAll))
 247             penalty += 0.35 * max(1 if name_fulls else 0.1,
 248                                   5 - len(name_partials) - len(addr_tokens))
 249             yield penalty, exp_count, lookup
 250
 251
 252     def get_name_ranking(self, trange: TokenRange,
 253                          db_field: str = 'name_vector') -> dbf.FieldRanking:
 254         """ Create a ranking expression for a name term in the given range.
 255         """
 256         name_fulls = self.query.get_tokens(trange, TokenType.WORD)
 257         ranks = [dbf.RankedTokens(t.penalty, [t.token]) for t in name_fulls]
 258         ranks.sort(key=lambda r: r.penalty)
 259         # Fallback, sum of penalty for partials
 260         name_partials = self.query.get_partials_list(trange)
 261         default = sum(t.penalty for t in name_partials) + 0.2
 262         return dbf.FieldRanking(db_field, default, ranks)
 263
 264
 265     def get_addr_ranking(self, trange: TokenRange) -> dbf.FieldRanking:
 266         """ Create a list of ranking expressions for an address term
 267             for the given ranges.
 268         """
 269         todo: List[Tuple[int, int, dbf.RankedTokens]] = []
 270         heapq.heappush(todo, (0, trange.start, dbf.RankedTokens(0.0, [])))
 271         ranks: List[dbf.RankedTokens] = []
 272
 273         while todo: # pylint: disable=too-many-nested-blocks
 274             neglen, pos, rank = heapq.heappop(todo)
 275             for tlist in self.query.nodes[pos].starting:
 276                 if tlist.ttype in (TokenType.PARTIAL, TokenType.WORD):
 277                     if tlist.end < trange.end:
 278                         chgpenalty = PENALTY_WORDCHANGE[self.query.nodes[tlist.end].btype]
 279                         if tlist.ttype == TokenType.PARTIAL:
 280                             penalty = rank.penalty + chgpenalty \
 281                                       + max(t.penalty for t in tlist.tokens)
 282                             heapq.heappush(todo, (neglen - 1, tlist.end,
 283                                                   dbf.RankedTokens(penalty, rank.tokens)))
 284                         else:
 285                             for t in tlist.tokens:
 286                                 heapq.heappush(todo, (neglen - 1, tlist.end,
 287                                                       rank.with_token(t, chgpenalty)))
 288                     elif tlist.end == trange.end:
 289                         if tlist.ttype == TokenType.PARTIAL:
 290                             ranks.append(dbf.RankedTokens(rank.penalty
 291                                                           + max(t.penalty for t in tlist.tokens),
 292                                                           rank.tokens))
 293                         else:
 294                             ranks.extend(rank.with_token(t, 0.0) for t in tlist.tokens)
 295                         if len(ranks) >= 10:
 296                             # Too many variants, bail out and only add
 297                             # Worst-case Fallback: sum of penalty of partials
 298                             name_partials = self.query.get_partials_list(trange)
 299                             default = sum(t.penalty for t in name_partials) + 0.2
 300                             ranks.append(dbf.RankedTokens(rank.penalty + default, []))
 301                             # Bail out of outer loop
 302                             todo.clear()
 303                             break
 304
 305         ranks.sort(key=lambda r: len(r.tokens))
 306         default = ranks[0].penalty + 0.3
 307         del ranks[0]
 308         ranks.sort(key=lambda r: r.penalty)
 309
 310         return dbf.FieldRanking('nameaddress_vector', default, ranks)
 311
 312
 313     def get_search_data(self, assignment: TokenAssignment) -> Optional[dbf.SearchData]:
 314         """ Collect the tokens for the non-name search fields in the
 315             assignment.
 316         """
 317         sdata = dbf.SearchData()
 318         sdata.penalty = assignment.penalty
 319         if assignment.country:
 320             tokens = self.get_country_tokens(assignment.country)
 321             if not tokens:
 322                 return None
 323             sdata.set_strings('countries', tokens)
 324         elif self.details.countries:
 325             sdata.countries = dbf.WeightedStrings(self.details.countries,
 326                                                   [0.0] * len(self.details.countries))
 327         if assignment.housenumber:
 328             sdata.set_strings('housenumbers',
 329                               self.query.get_tokens(assignment.housenumber,
 330                                                     TokenType.HOUSENUMBER))
 331         if assignment.postcode:
 332             sdata.set_strings('postcodes',
 333                               self.query.get_tokens(assignment.postcode,
 334                                                     TokenType.POSTCODE))
 335         if assignment.qualifier:
 336             tokens = self.get_qualifier_tokens(assignment.qualifier)
 337             if not tokens:
 338                 return None
 339             sdata.set_qualifiers(tokens)
 340         elif self.details.categories:
 341             sdata.qualifiers = dbf.WeightedCategories(self.details.categories,
 342                                                       [0.0] * len(self.details.categories))
 343
 344         if assignment.address:
 345             if not assignment.name and assignment.housenumber:
 346                 # housenumber search: the first item needs to be handled like
 347                 # a name in ranking or penalties are not comparable with
 348                 # normal searches.
 349                 sdata.set_ranking([self.get_name_ranking(assignment.address[0],
 350                                                          db_field='nameaddress_vector')]
 351                                   + [self.get_addr_ranking(r) for r in assignment.address[1:]])
 352             else:
 353                 sdata.set_ranking([self.get_addr_ranking(r) for r in assignment.address])
 354         else:
 355             sdata.rankings = []
 356
 357         return sdata
 358
 359
 360     def get_country_tokens(self, trange: TokenRange) -> List[Token]:
 361         """ Return the list of country tokens for the given range,
 362             optionally filtered by the country list from the details
 363             parameters.
 364         """
 365         tokens = self.query.get_tokens(trange, TokenType.COUNTRY)
 366         if self.details.countries:
 367             tokens = [t for t in tokens if t.lookup_word in self.details.countries]
 368
 369         return tokens
 370
 371
 372     def get_qualifier_tokens(self, trange: TokenRange) -> List[Token]:
 373         """ Return the list of qualifier tokens for the given range,
 374             optionally filtered by the qualifier list from the details
 375             parameters.
 376         """
 377         tokens = self.query.get_tokens(trange, TokenType.QUALIFIER)
 378         if self.details.categories:
 379             tokens = [t for t in tokens if t.get_category() in self.details.categories]
 380
 381         return tokens
 382
 383
 384     def get_near_items(self, assignment: TokenAssignment) -> Optional[dbf.WeightedCategories]:
 385         """ Collect tokens for near items search or use the categories
 386             requested per parameter.
 387             Returns None if no category search is requested.
 388         """
 389         if assignment.near_item:
 390             tokens: Dict[Tuple[str, str], float] = {}
 391             for t in self.query.get_tokens(assignment.near_item, TokenType.NEAR_ITEM):
 392                 cat = t.get_category()
 393                 # The category of a near search will be that of near_item.
 394                 # Thus, if search is restricted to a category parameter,
 395                 # the two sets must intersect.
 396                 if (not self.details.categories or cat in self.details.categories)\
 397                    and t.penalty < tokens.get(cat, 1000.0):
 398                     tokens[cat] = t.penalty
 399             return dbf.WeightedCategories(list(tokens.keys()), list(tokens.values()))
 400
 401         return None
 402
 403
 404 PENALTY_WORDCHANGE = {
 405     BreakType.START: 0.0,
 406     BreakType.END: 0.0,
 407     BreakType.PHRASE: 0.0,
 408     BreakType.WORD: 0.1,
 409     BreakType.PART: 0.2,
 410     BreakType.TOKEN: 0.4
 411 }