Django之whoosh搜索引擎

            #
             例如
            
MacBook:商品1,商品2,商品3
        

pip install django-haystack # 安装haystack框架
pip install whoosh         # 安装whoosh搜索引擎

INSTALLED_APPS = [
     # 注册haystack框架‘haystack‘
]

HAYSTACK_CONNECTIONS = {
    ‘default‘: {
        ‘ENGINE‘: ‘haystack.backends.whoosh_backend.WhooshEngine‘,
        ‘PATH‘: os.path.join(BASE_DIR, ‘whoosh_index‘),  # whoosh_index 文件夹不需要自己手动创建 会自动创建    }
}
# 添加此项，当数据库改变时，会自动更新索引，非常方便
HAYSTACK_SIGNAL_PROCESSOR = ‘haystack.signals.RealtimeSignalProcessor‘

urlpatterns = [
    ...
    url(r‘^search/‘, include(‘haystack.urls‘)),
]

            from haystack import indexes  # 导入索引from . import models   # 导入模型表class GoodsIndex(indexes.SearchIndex,indexes.Indexable):

    text = indexes.CharField(document=True,use_template=True)
    ‘‘‘
    document:指定了将模型类中的哪些字段建立索引
    use_template:在模板文件夹中创建文件夹指明具体的字段建立索引
    ‘‘‘def get_model(self):
        # 为那个模型表建立索引return models.GoodInfo

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

            #
             指定那些字段建立索引 
{{object.name}}   # 商品名称建立索引
{{object.desc}}   # 商品简介建立索引

python manage.py rebuild_index

            <
            form 
            action
            ="/search"
             method
            ="get"
            >
            <
            p
            >商品搜索:<input type="text" name="q"></p><p>提交:<input type="submit"></p></form><p>搜索关键字:{{ query }}</p><p>当前页page对象:{{ page }}</p><p>分页对象:{{ paginator }}</p><ul>
    {% for item in page %}
      <li> {{ item.object.name }}</li><li> {{ item.object.desc }}</li>
    {% endfor %}
</ul>

通过HAYSTACK_SEARCH_RESULTS_PER_PAGE 可以控制每页显示数量。

pip install jieba

            import
             jieba


split_data = ‘很好吃的草莓‘# 要被切割的数据
res = jieba.cut(split_data,cut_all=True)

print(res)  # <generator object Tokenizer.cut at 0x0000000009EA27D8> 拿到一个生成器for value in res:
    print(value)

            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()

            #
             顶部引入刚才添加的中文分词
            from .ChineseAnalyzer import ChineseAnalyzer 

# 在整个py文件中，查找 替换
analyzer=StemmingAnalyzer()

analyzer=ChineseAnalyzer()

HAYSTACK_CONNECTIONS = {
    ‘default‘: {
        # ‘ENGINE‘: ‘haystack.backends.whoosh_backend.WhooshEngine‘,  # 原来的默认的‘ENGINE‘: ‘haystack.backends.whoosh_cn_backend.WhooshEngine‘, # jieba搜索‘PATH‘: os.path.join(BASE_DIR, ‘whoosh_index‘),  # whoosh_index 文件夹不需要自己手动创建 会自动创建    }
}

python manage.py rebuild_index