283375/arcaea-offline
1
0
Fork 0
mirror of https://github.com/283375/arcaea-offline.git synced 2025-04-17 21:30:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

wip: searcher

Browse Source
This commit is contained in:
283375 2023-09-23 21:55:04 +08:00
parent c1f83eff55
commit 6ec3acb145
Signed by: 283375
SSH Key Fingerprint: SHA256:UcX0qg6ZOSDOeieKPGokA5h7soykG61nz2uxuQgVLSk
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
src/arcaea_offline/searcher.py
View File

@ -2,7 +2,7 @@ from typing import List, Union
from sqlalchemy import select from sqlalchemy import select
from sqlalchemy.orm import Session from sqlalchemy.orm import Session
from whoosh.analysis import LowercaseFilter, RegexTokenizer from whoosh.analysis import NgramFilter, StandardAnalyzer
from whoosh.fields import ID, KEYWORD, TEXT, Schema from whoosh.fields import ID, KEYWORD, TEXT, Schema
from whoosh.filedb.filestore import RamStorage from whoosh.filedb.filestore import RamStorage
from whoosh.qparser import FuzzyTermPlugin, MultifieldParser, OrGroup from whoosh.qparser import FuzzyTermPlugin, MultifieldParser, OrGroup
@ -13,7 +13,7 @@ from .utils.search_title import recover_search_title
class Searcher: class Searcher:
def __init__(self): def __init__(self):
self.text_analyzer = RegexTokenizer() | LowercaseFilter() self.text_analyzer = StandardAnalyzer() | NgramFilter(minsize=2, maxsize=5)
self.song_schema = Schema( self.song_schema = Schema(
song_id=ID(stored=True, unique=True), song_id=ID(stored=True, unique=True),
title=TEXT(analyzer=self.text_analyzer, spelling=True), title=TEXT(analyzer=self.text_analyzer, spelling=True),
@ -107,5 +107,5 @@ class Searcher:
query_string = f"{string}" query_string = f"{string}"
query = self.default_query_parser.parse(query_string) query = self.default_query_parser.parse(query_string)
with self.index.searcher() as searcher: with self.index.searcher() as searcher:
results = list(searcher.search(query, limit=limit)) results = searcher.search(query, limit=limit)
return results return [result.get("song_id") for result in results]