simplify handling of SQL lookup code for search_name

Use function classes which can be instantiated directly.
This commit is contained in:
Sarah Hoffmann
2023-12-06 10:37:06 +01:00
parent 8791c6cb69
commit b06f5fddcb
7 changed files with 139 additions and 62 deletions

View File

@@ -7,15 +7,17 @@
"""
Data structures for more complex fields in abstract search descriptions.
"""
from typing import List, Tuple, Iterator, cast, Dict
from typing import List, Tuple, Iterator, Dict, Type
import dataclasses
import sqlalchemy as sa
from nominatim.typing import SaFromClause, SaColumn, SaExpression
from nominatim.api.search.query import Token
import nominatim.api.search.db_search_lookups as lookups
from nominatim.utils.json_writer import JsonWriter
@dataclasses.dataclass
class WeightedStrings:
""" A list of strings together with a penalty.
@@ -152,18 +154,12 @@ class FieldLookup:
"""
column: str
tokens: List[int]
lookup_type: str
lookup_type: Type[lookups.LookupType]
def sql_condition(self, table: SaFromClause) -> SaColumn:
""" Create an SQL expression for the given match condition.
"""
col = table.c[self.column]
if self.lookup_type == 'lookup_all':
return col.contains(self.tokens)
if self.lookup_type == 'lookup_any':
return cast(SaColumn, col.overlaps(self.tokens))
return sa.func.coalesce(sa.null(), col).contains(self.tokens) # pylint: disable=not-callable
return self.lookup_type(table, self.column, self.tokens)
class SearchData:
@@ -229,22 +225,23 @@ def lookup_by_names(name_tokens: List[int], addr_tokens: List[int]) -> List[Fiel
""" Create a lookup list where name tokens are looked up via index
and potential address tokens are used to restrict the search further.
"""
lookup = [FieldLookup('name_vector', name_tokens, 'lookup_all')]
lookup = [FieldLookup('name_vector', name_tokens, lookups.LookupAll)]
if addr_tokens:
lookup.append(FieldLookup('nameaddress_vector', addr_tokens, 'restrict'))
lookup.append(FieldLookup('nameaddress_vector', addr_tokens, lookups.Restrict))
return lookup
def lookup_by_any_name(name_tokens: List[int], addr_tokens: List[int],
lookup_type: str) -> List[FieldLookup]:
use_index_for_addr: bool) -> List[FieldLookup]:
""" Create a lookup list where name tokens are looked up via index
and only one of the name tokens must be present.
Potential address tokens are used to restrict the search further.
"""
lookup = [FieldLookup('name_vector', name_tokens, 'lookup_any')]
lookup = [FieldLookup('name_vector', name_tokens, lookups.LookupAny)]
if addr_tokens:
lookup.append(FieldLookup('nameaddress_vector', addr_tokens, lookup_type))
lookup.append(FieldLookup('nameaddress_vector', addr_tokens,
lookups.LookupAll if use_index_for_addr else lookups.Restrict))
return lookup
@@ -253,5 +250,5 @@ def lookup_by_addr(name_tokens: List[int], addr_tokens: List[int]) -> List[Field
""" Create a lookup list where address tokens are looked up via index
and the name tokens are only used to restrict the search further.
"""
return [FieldLookup('name_vector', name_tokens, 'restrict'),
FieldLookup('nameaddress_vector', addr_tokens, 'lookup_all')]
return [FieldLookup('name_vector', name_tokens, lookups.Restrict),
FieldLookup('nameaddress_vector', addr_tokens, lookups.LookupAll)]