更多代码阅读及测试（ChineseAnalyzer for Whoosh 搜索引擎）

2021SC@SDUSC

---

测试代码：

# -*- coding: UTF-8 -*-
from __future__ import unicode_literals
import sys,os
sys.path.append("../")
from whoosh.index import create_in,open_dir
from whoosh.fields import *
from whoosh.qparser import QueryParser

from jieba.analyse.analyzer import ChineseAnalyzer

analyzer = ChineseAnalyzer()
print(analyzer.items)
schema = Schema(title=TEXT(stored=True), path=ID(stored=True), content=TEXT(stored=True, analyzer=analyzer))
if not os.path.exists("tmp"):
    os.mkdir("tmp")

ix = create_in("tmp", schema) # for create new index
#ix = open_dir("tmp") # for read only
writer = ix.writer()

writer.add_document(
    title="document1",
    path="/a",
    content="This is the first document we’ve added!"
)

writer.add_document(
    title="document2",
    path="/b",
    content="The second one 你 中文测试中文 is even more interesting! 吃水果"
)

writer.add_document(
    title="document3",
    path="/c",
    content="买水果然后来世博园。"
)

writer.add_document(
    title="document4",
    path="/c",
    content="工信处女干事每月经过下属科室都要亲口交代24口交换机等技术性器件的安装工作"
)

writer.add_document(
    title="document4",
    path="/c",
    content="咱俩交换一下吧。"
)

writer.commit()
searcher = ix.searcher()
parser = QueryParser("content", schema=ix.schema)

for keyword in ("水果世博园","你","first","中文","交换机","交换"):
    print("result of ",keyword)
    q = parser.parse(keyword)
    results = searcher.search(q)
    for hit in results:
        print(hit.highlights("content"))
    print("="*10)

for t in analyzer("我的好朋友是李明;我爱北京天安门;IBM和Microsoft; I have a dream. this is intetesting and interested me a lot"):
    print(t.text)

运行结果：

使用search(q)可以查找writer写入的句子中包含关键词q的句子。

analyzer(sentence)可以以search mode 将句子切分，并且有其stop_words，跳过这些词条。