Django中全文搜索(Full Text Search)的局限性和解决方案

import jieba

from haystack import indexes
from yourapp.models import YourModel

class YourModelIndex(indexes.SearchIndex, indexes.Indexable):
    text = indexes.CharField(document=True, use_template=True)

    def get_model(self):
        return YourModel

    def index_queryset(self, using=None):
        return self.get_model().objects.all()

    def prepare_text(self, obj):
        content = obj.content
        seg_list = jieba.cut(content, cut_all=False)
        return ' '.join(seg_list)

from haystack.query import SearchQuerySet
from haystack.views import SearchView
from haystack.backends.highlighting import Highlighter

class YourSearchView(SearchView):
    def extra_context(self):
        extra = super(YourSearchView, self).extra_context()
        sqs = self.searchqueryset
        highlighter = Highlighter(query=self.query)
        highlighted = [(result, highlighter.highlight(result.text)) for result in sqs]
        extra['results'] = highlighted
        return extra

from django.conf import settings
from elasticsearch import Elasticsearch

# 初始化Elasticsearch
es = Elasticsearch(settings.ELASTICSEARCH_URL)

# 创建索引
mapping = {
    'properties': {
        'content': {'type': 'text'},
    }
}
es.indices.create(index='yourindex', body=mapping)

# 索引数据
es.index(index='yourindex', body={
    'content': 'pidancode.com是一个编程学习网站，旨在帮助初学者快速入门。'
})

# 搜索数据
results = es.search(index='yourindex', body={
    'query': {
        'match': {
            'content': 'pidancode'
        }
    }
})['hits']['hits']

# 显示结果
for result in results:
    print(result['_source']['content'])