X-Git-Url: https://git.openstreetmap.org./nominatim.git/blobdiff_plain/4e4d29f653d4929f49536255314ec19264166ec6..7205491b8495e48c62b28373d1746e77d475582b:/nominatim/api/search/icu_tokenizer.py diff --git a/nominatim/api/search/icu_tokenizer.py b/nominatim/api/search/icu_tokenizer.py index 196fde2a..1c2565d1 100644 --- a/nominatim/api/search/icu_tokenizer.py +++ b/nominatim/api/search/icu_tokenizer.py @@ -8,7 +8,6 @@ Implementation of query analysis for the ICU tokenizer. """ from typing import Tuple, Dict, List, Optional, NamedTuple, Iterator, Any, cast -from copy import copy from collections import defaultdict import dataclasses import difflib @@ -22,6 +21,7 @@ from nominatim.api.connection import SearchConnection from nominatim.api.logging import log from nominatim.api.search import query as qmod from nominatim.api.search.query_analyzer_factory import AbstractQueryAnalyzer +from nominatim.db.sqlalchemy_types import Json DB_TO_TOKEN_TYPE = { @@ -159,7 +159,7 @@ class ICUQueryAnalyzer(AbstractQueryAnalyzer): sa.Column('word_token', sa.Text, nullable=False), sa.Column('type', sa.Text, nullable=False), sa.Column('word', sa.Text), - sa.Column('info', self.conn.t.types.Json)) + sa.Column('info', Json)) async def analyze_query(self, phrases: List[qmod.Phrase]) -> qmod.QueryStruct: @@ -184,13 +184,12 @@ class ICUQueryAnalyzer(AbstractQueryAnalyzer): if row.type == 'S': if row.info['op'] in ('in', 'near'): if trange.start == 0: - query.add_token(trange, qmod.TokenType.CATEGORY, token) + query.add_token(trange, qmod.TokenType.NEAR_ITEM, token) else: - query.add_token(trange, qmod.TokenType.QUALIFIER, token) - if trange.start == 0 or trange.end == query.num_token_slots(): - token = copy(token) - token.penalty += 0.1 * (query.num_token_slots()) - query.add_token(trange, qmod.TokenType.CATEGORY, token) + if trange.start == 0 and trange.end == query.num_token_slots(): + query.add_token(trange, qmod.TokenType.NEAR_ITEM, token) + else: + query.add_token(trange, qmod.TokenType.QUALIFIER, token) else: query.add_token(trange, DB_TO_TOKEN_TYPE[row.type], token)