[ Whoosh原生Python全文检索 ]

发表评论
152 views

Whoosh全文检索-Django配置

(https://django-haystack.readthedocs.io/en/master/tutorial.html#installation "haystack文档参考")

一. 安装

    pip install django-haystack
    pip install whoosh
    pip install jieba

二. 配置

  1. 创建一个新的app, 并在app目录下创建

    search_indexes.py 名字固定写法

from haystack import indexes
from article.models import Articles  # 需要索引的模型

# 创建索引的文件
class ArticleIndex(indexes.SearchIndex, indexes.Indexable):
    text = indexes.CharField(document=True, use_template=True)   # 索引只能一个字段

    def get_model(self):
        return Articles

    def index_queryset(self, using=None):
        return self.get_model().objects.all()  # 返回
  1. settings.py文件配置
INSTALLED_APPS = [
    ...
    'articles'
    'search_index',  # 新创建的app
    'haystack',  # 分词器
    ...
]

# 分词器配置
HAYSTACK_CONNECTIONS = {
    'default': {
        'ENGINE': 'haystack.backends.whoosh_cn_backend.WhooshEngine',   # 指定使用的分词语言
        'PATH': os.path.join(BASE_DIR, 'whoosh_index')      # 指定创建索引保存的位置， 会自动创建
    }
}
# 自动更新索引
HAYSTACK_SIGNAL_PROCESSOR = 'haystack.signals.RealtimeSignalProcessor'

三. 添加路由， 路由

主路由配置urls.py

from django.urls import path, include, re_path

urlpatterns = [
    ...
    path('', include('article.urls')),
    path('search_index/', include('search_index.urls')),  # 新建的App
    path('search/', include('haystack.urls')),  # 全文检索模块注册
    ...
]

新App路由urls.py

from django.urls import path
from .views import MySearchView

urlpatterns = [
    path('search/test/', MySearchView(), name='haystack_search')
]

新APP视图views.py

from haystack.views import SearchView
from django.http import HttpResponse
from django.core.paginator import Paginator


class MySearchView(SearchView):
    def build_page(self):
        print('进入搜索页面：')
        # 分页重写
        context = super(MySearchView, self).extra_context()  # 继承自带的context
        try:
            page_no = int(self.request.GET.get('page', 1))
        except Exception:
            return HttpResponse("Not a valid number for page.")

        if page_no < 1:
            return HttpResponse("Pages should be 1 or greater.")
        a = []
        for i in self.results:
            a.append(i.object)
        paginator = Paginator(a, 18)
        # print("--------")
        # print(page_no)
        page = paginator.page(page_no)
        print('搜索的商品信息：', page)
        return (paginator, page)

    def extra_context(self):
        context = super(MySearchView, self).extra_context()  # 继承自带的context
        context['title'] = '搜索'
        return context

给whoosh添加中文检索配置 在模块haystac.backends目录下创建 ChineseAnalyzer.py文件

    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()

在当前目录下复制一份whoosh_backend.py文件 名改名为whoosh_cn_backend.py再修改里内容

添加
from .ChineseAnalyzer import ChineseAnalyzer

替换
analyzer = StemmingAnalyzer()
换为
analyzer = ChineseAnalyzer()

四. 添加模板

索引模板固定写法. /templates/search/indexes/注册时的APP名字/创建索引用的模型名字小写_text.txt /templates/search/indexes/article/articles_text.txt

{{ object.title }}
{{ object.content }}

HTML模板固定写法 /templates/search/search.html

<ul class="goods_type_list clearfix">
    {% for result in page.object_list %}
        <li>
            <a href="/goods/detail/{{ result.object.id }}/"><img src="/upload/{{ result.object.gpic }}"></a>
            <h4><a href="/detail/{{ result.object.id }}/">{{ result.object.gtitle }}</a></h4>
            <div class="operate">
                <span class="prize">{{ result.object.gprice }}</span>
                <span class="unit">{{ result.object.gprice }}/{{ result.object.gunit }}</span>
                <a href="/cart/add{{result.object.id}}_1/" class="add_goods" title="加入购物车"></a>
            </div>
        </li>
    {% endfor %}
</ul>
<div class="pagenation">
    {% if page.has_previous %}
        <a href="/search?q={{query}}&page={{page.previous_page_number}}">&lt;上一页</a>
    {% else %}
        <a href="/search?q={{ query }}">&lt;上一页</a>
    {% endif %}
    {% if page.number <= 5 %}   <!--当前页面数小于5时-->
        {% for page_num in paginator.page_range %}
            {%if forloop.counter <= 5 %}
            <a href="/search?q={{query}}&page={{page_num}}"
               {% if page.number == page_num %}
               class="active"
               {% endif %}
            >{{ page_num }}</a>
            {%endif%}
        {% endfor %}
    {% else %}
        {% if page.number|add:1 > paginator.num_pages %}
            <a href="/search?q={{query}}&page={{page.number|add:-4}}">{{ page.number|add:-4}}</a>
        {% endif %}
        {% if page.number|add:2 > paginator.num_pages %}
            <a href="/search?q={{query}}&page={{page.number|add:-3}}">{{ page.number|add:-3}}</a>
        {% endif %}
        <a href="/search?q={{query}}&page={{page.number|add:-2}}" >{{ page.number|add:-2}}</a>
        <a href="/search?q={{query}}&page={{page.number|add:-1}}">{{ page.number|add:-1}}</a>
        <a href="/search?q={{query}}&page={{page.number}}" class="active">{{ page.number }}</a>
        {% if page.number|add:1 <= paginator.num_pages %}
            <a href="/search?q={{query}}&page={{page.number|add:1}}">{{ page.number|add:1}}</a>
        {% endif %}
        {% if page.number|add:2 <= paginator.num_pages %}
            <a href="/search?q={{query}}&page={{page.number|add:2}}">{{ page.number|add:2}}</a>
        {% endif %}
    {% endif %}

    {% if page.has_next %}
        <a href="/search?q={{query}}&page={{page.next_page_number}}">下一页&gt;</a>
    {% else %}
        <a href="/search?q={{query}}&page={{paginator.num_pages}}">下一页&gt;</a>
    {% endif %}
</div>
</div>

五. 迁移生成索引文件

python manage.py rebuild_index

# 可选(更新)
python manage.py update_index

6. 测试

/search/p=xxxxx