django-全文检索
全文检索不同于特定字段的模糊查询，使用全文检索的效率更高，并且能够对于中文进行分词处理
需要的第三方库：
- haystack：django的一个包，可以方便地对model里面的内容进行索引、搜索，设计为支持whoosh,solr,Xapian,Elasticsearc四种全文检索引擎后端，属于一种全文检索的框架
- whoosh：纯Python编写的全文搜索引擎，虽然性能比不上sphinx、xapian、Elasticsearc等，但是无二进制包，程序不会莫名其妙的崩溃，对于小型的站点，whoosh已经足够使用
- jieba：一款免费的中文分词包
操作
首先pip安装包
pip install django-haystack
pip install whoosh
pip install jieba
设置settings
添加应用：
INSTALLED_APPS = ( ... 'haystack', )
添加搜索引擎：
HAYSTACK_CONNECTIONS = { 'default': { 'ENGINE': 'haystack.backends.whoosh_cn_backend.WhooshEngine', 'PATH': os.path.join(BASE_DIR, 'whoosh_index'), } } #自动生成索引 HAYSTACK_SIGNAL_PROCESSOR = 'haystack.signals.RealtimeSignalProcessor'
#每一页显示多少数据
HAYSTACK_SEARCH_RESULTS_PER_PAGE = 18
添加url：
urlpatterns = [ ... url(r'^search/', include('haystack.urls')), ]
在应用目录下建立search_indexes.py
# coding=utf-8 from haystack import indexes from models import GoodsInfo class GoodsInfoIndex(indexes.SearchIndex, indexes.Indexable): text = indexes.CharField(document=True, use_template=True) def get_model(self): return GoodsInfo def index_queryset(self, using=None): return self.get_model().objects.all()
在目录“templates/search/indexes/应用名称/”下创建“模型类名称_text.txt”文件
#goodsinfo_text.txt，这里列出了要对哪些列的内容进行检索,模型类中的某些字段 {{ object.gName }} {{ object.gSubName }} {{ object.gDes }}
在目录“templates/search/”下建立search.html
<!DOCTYPE html>
<html>
<head>
<title></title>
</head>
<body>
{% if query %}
<h3>搜索结果如下：</h3>
{% for result in page.object_list %}
<a href="/{{ result.object.id }}/">{{ result.object.gName }}</a><br/>
{% empty %}
<p>没找到</p>
{% endfor %}
{% if page.has_previous or page.has_next %}
<div>
{% if page.has_previous %}<a href="?q={{ query }}&page={{ page.previous_page_number }}">{% endif %}« 上一页{% if page.has_previous %}</a>{% endif %}
|
{% if page.has_next %}<a href="?q={{ query }}&page={{ page.next_page_number }}">{% endif %}下一页 »{% if page.has_next %}</a>{% endif %}
</div>
{% endif %}
{% endif %}
</body>
</html>
建立ChineseAnalyzer.py文件
保存在haystack的安装文件夹下，路径如“/home/python/.virtualenvs/django_py2/lib/python2.7/site-packages/haystack/backends”
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()
复制whoosh_backend.py文件，改名为whoosh_cn_backend.py
from .ChineseAnalyzer import ChineseAnalyzer 查找 analyzer=StemmingAnalyzer() 改为 analyzer=ChineseAnalyzer()
生成索引
初始化索引：
python manage.py rebuild_index
在模板中创建搜索栏
<form method='get' action="/search/" target="_blank"> <input type="text" name="q"> <input type="submit" value="查询"> </form>
关于全文索引使用的固定参数一些说明：
我们打开haystack第三方包中的urls文件
haystack
----urls.py
# encoding: utf-8
from __future__ import absolute_import, division, print_function, unicode_literals
from django.conf.urls import url
from haystack.views import SearchView
urlpatterns = [
url(r'^$', SearchView(), name='haystack_search'),
]
然后进入haystack.views 文件
#这里将搜索显示的数据默认为20个
RESULTS_PER_PAGE = getattr(settings, 'HAYSTACK_SEARCH_RESULTS_PER_PAGE', 20)
#在search文件下的search template = 'search/search.html' extra_context = {} query = '' results = EmptySearchQuerySet() request = None form = None results_per_page = RESULTS_PER_PAGE
更多详情请看
haystack.views.py
# encoding: utf-8 from __future__ import absolute_import, division, print_function, unicode_literals from django.conf import settings from django.core.paginator import InvalidPage, Paginator from django.http import Http404 from django.shortcuts import render from haystack.forms import FacetedSearchForm, ModelSearchForm from haystack.query import EmptySearchQuerySet RESULTS_PER_PAGE = getattr(settings, 'HAYSTACK_SEARCH_RESULTS_PER_PAGE', 20) class SearchView(object): template = 'search/search.html' extra_context = {} query = '' results = EmptySearchQuerySet() request = None form = None results_per_page = RESULTS_PER_PAGE def __init__(self, template=None, load_all=True, form_class=None, searchqueryset=None, results_per_page=None): self.load_all = load_all self.form_class = form_class self.searchqueryset = searchqueryset if form_class is None: self.form_class = ModelSearchForm if not results_per_page is None: self.results_per_page = results_per_page if template: self.template = template def __call__(self, request): """ Generates the actual response to the search. Relies on internal, overridable methods to construct the response. """ self.request = request self.form = self.build_form() self.query = self.get_query() self.results = self.get_results() return self.create_response() def build_form(self, form_kwargs=None): """ Instantiates the form the class should use to process the search query. """ data = None kwargs = { 'load_all': self.load_all, } if form_kwargs: kwargs.update(form_kwargs) if len(self.request.GET): data = self.request.GET if self.searchqueryset is not None: kwargs['searchqueryset'] = self.searchqueryset return self.form_class(data, **kwargs) def get_query(self): """ Returns the query provided by the user. Returns an empty string if the query is invalid. """ if self.form.is_valid(): return self.form.cleaned_data['q'] return '' def get_results(self): """ Fetches the results via the form. Returns an empty list if there's no query to search with. """ return self.form.search() def build_page(self): """ Paginates the results appropriately. In case someone does not want to use Django's built-in pagination, it should be a simple matter to override this method to do what they would like. """ try: page_no = int(self.request.GET.get('page', 1)) except (TypeError, ValueError): raise Http404("Not a valid number for page.") if page_no < 1: raise Http404("Pages should be 1 or greater.") start_offset = (page_no - 1) * self.results_per_page self.results[start_offset:start_offset + self.results_per_page] paginator = Paginator(self.results, self.results_per_page) try: page = paginator.page(page_no) except InvalidPage: raise Http404("No such page!") return (paginator, page) def extra_context(self): """ Allows the addition of more context variables as needed. Must return a dictionary. """ return {} def get_context(self): (paginator, page) = self.build_page() context = { 'query': self.query, 'form': self.form, 'page': page, 'paginator': paginator, 'suggestion': None, } if hasattr(self.results, 'query') and self.results.query.backend.include_spelling: context['suggestion'] = self.form.get_suggestion() context.update(self.extra_context()) return context def create_response(self): """ Generates the actual HttpResponse to send back to the user. """ context = self.get_context() return render(self.request, self.template, context) def search_view_factory(view_class=SearchView, *args, **kwargs): def search_view(request): return view_class(*args, **kwargs)(request) return search_view class FacetedSearchView(SearchView): def __init__(self, *args, **kwargs): # Needed to switch out the default form class. if kwargs.get('form_class') is None: kwargs['form_class'] = FacetedSearchForm super(FacetedSearchView, self).__init__(*args, **kwargs) def build_form(self, form_kwargs=None): if form_kwargs is None: form_kwargs = {} # This way the form can always receive a list containing zero or more # facet expressions: form_kwargs['selected_facets'] = self.request.GET.getlist("selected_facets") return super(FacetedSearchView, self).build_form(form_kwargs) def extra_context(self): extra = super(FacetedSearchView, self).extra_context() extra['request'] = self.request extra['facets'] = self.results.facet_counts() return extra def basic_search(request, template='search/search.html', load_all=True, form_class=ModelSearchForm, searchqueryset=None, extra_context=None, results_per_page=None): """ A more traditional view that also demonstrate an alternative way to use Haystack. Useful as an example of for basing heavily custom views off of. Also has the benefit of thread-safety, which the ``SearchView`` class may not be. Template:: ``search/search.html`` Context:: * form An instance of the ``form_class``. (default: ``ModelSearchForm``) * page The current page of search results. * paginator A paginator instance for the results. * query The query received by the form. """ query = '' results = EmptySearchQuerySet() if request.GET.get('q'): form = form_class(request.GET, searchqueryset=searchqueryset, load_all=load_all) if form.is_valid(): query = form.cleaned_data['q'] results = form.search() else: form = form_class(searchqueryset=searchqueryset, load_all=load_all) paginator = Paginator(results, results_per_page or RESULTS_PER_PAGE) try: page = paginator.page(int(request.GET.get('page', 1))) except InvalidPage: raise Http404("No such page of results!") context = { 'form': form, 'page': page, 'paginator': paginator, 'query': query, 'suggestion': None, } if results.query.backend.include_spelling: context['suggestion'] = form.get_suggestion() if extra_context: context.update(extra_context) return render(request, template, context)
posted on 2018-06-26 21:57 weilanhanf 阅读(828) 评论(0) 编辑 收藏 举报
