Django jieba分词 Django实现whoosh搜索引擎使用jieba分词

pip install django-haystack
pip install jieba

# （注意：pip安装的是django-haystack，但是实际包的文件夹名字为haystack）
cd /usr/local/lib/python3.8/site-packages/haystack/backends/
# 创建并编辑ChineseAnalyzer.py文件
vim ChineseAnalyzer.py

import jieba
from whoosh.analysis import Tokenizer, Token


class ChineseTokenizer(Tokenizer):
  def __call__(self, 
         value,
         positions=False, 
         chars=False,
         keeporiginal=False, 
         removestops=True,
         start_pos=0, 
         start_char=0,
         mode='', 
         **kwargs):
  t = Token(positions, chars, removestops=removestops, mode=mode,**kwargs)
  seglist = jieba.cut(value, cut_all=True)
  for w in seglist:
    t.original = t.text = w
    t.boost = 1.0
    if positions:
      t.pos = start_pos + value.find(w)
    if chars:
      t.startchar = start_char + value.find(w)
      t.endchar = start_char + value.find(w) + len(w)
      yield t


def ChineseAnalyzer():
  return ChineseTokenizer()

cp whoosh_backend.py whoosh_cn_backend.py
vim whoosh_cn_backend.py

# 导入ChineseAnalyzer，并将原有的StemmingAnalyser替换为ChineseAnalyzer
from .ChineseAnalyzer import ChineseAnalyzer
# from whoosh.analysis import StemmingAnalyzer

# 全文搜索框架配置
HAYSTACK_CONNECTIONS = {
  'default': {
   # 使用whoosh引擎
   # 'ENGINE': 'haystack.backends.whoosh_backend.WhooshEngine',
   # 使用jieba分词
    'ENGINE': 'haystack.backends.whoosh_cn_backend.WhooshEngine',
   # 索引文件路径
    'PATH': os.path.join(BASE_DIR, 'whoosh_index'),
  },
}

python manage.py rebuild_index