Django Haystack 全文检索与关键词高亮的实现

[packages]
django = "~=2.2"
elasticsearch = ">=2,<3"

compose\
 local\
 production\
  django\
  nginx\

FROM elasticsearch:2.4.6-alpine

COPY ./compose/production/elasticsearch/elasticsearch-analysis-ik-1.10.6.zip /usr/share/elasticsearch/plugins/
RUN cd /usr/share/elasticsearch/plugins/ && mkdir ik && unzip elasticsearch-analysis-ik-1.10.6.zip -d ik/
RUN rm /usr/share/elasticsearch/plugins/elasticsearch-analysis-ik-1.10.6.zip

USER root
COPY ./compose/production/elasticsearch/elasticsearch.yml /usr/share/elasticsearch/config/
RUN chown elasticsearch:elasticsearch /usr/share/elasticsearch/config/elasticsearch.yml

USER elasticsearch

bootstrap.memory_lock: true
network.host: 0.0.0.0

version: '3'

volumes:
 database_local:
 esdata_local:

services:
 hellodjango_blog_tutorial_local:
 # 其它配置不变...
 depends_on:
  - elasticsearch_local

 elasticsearch_local:
 build:
  context: .
  dockerfile: ./compose/production/elasticsearch/Dockerfile
 image: elasticsearch_local
 container_name: elasticsearch_local
 volumes:
  - esdata_local:/usr/share/elasticsearch/data
 ports:
  - "9200:9200"
 environment:
  - "ES_JAVA_OPTS=-Xms512m -Xmx512m"
 ulimits:
  memlock:
  soft: -1
  hard: -1
  nproc: 65536
  nofile:
  soft: 65536
  hard: 65536

INSTALLED_APPS = [
 'django.contrib.admin',
 # 其它 app...
 'haystack',
 'blog',
 'comments',
]

# 搜索设置
HAYSTACK_CONNECTIONS = {
 'default': {
  'ENGINE': 'haystack.elasticsearch2_backend.Elasticsearch2SearchEngine',
  'URL': '',
  'INDEX_NAME': 'hellodjango_blog_tutorial',
 },
}
HAYSTACK_SEARCH_RESULTS_PER_PAGE = 10
HAYSTACK_SIGNAL_PROCESSOR = 'haystack.signals.RealtimeSignalProcessor'

HAYSTACK_CONNECTIONS['default']['URL'] = 'http://elasticsearch_local:9200/'

from haystack import indexes
from .models import Post


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

 def get_model(self):
  return Post

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

templates/search/indexes/blog/post_text.txt

{{ object.title }}
{{ object.body }}

urlpatterns = [
 # 其它...
 path('search/', include('haystack.urls')),
]

# path('search/', views.search, name='search'),

<form role="search" method="get" id="searchform" action="{% url 'haystack_search' %}">
 <input type="search" name="q" placeholder="搜索" required>
 <button type="submit"><span class="ion-ios-search-strong"></span></button>
</form>

{% extends 'base.html' %}
{% load highlight %}

{% block main %}
 {% if query %}
 {% for result in page.object_list %}
  <article class="post post-{{ result.object.pk }}">
  <header class="entry-header">
   <h1 class="entry-title">
   <a href="{{ result.object.get_absolute_url }}" rel="external nofollow" rel="external nofollow" rel="external nofollow" >{% highlight result.object.title with query %}</a>
   </h1>
   <div class="entry-meta">
     <span class="post-category">
      <a href="{% url 'blog:category' result.object.category.pk %}" rel="external nofollow" >
       {{ result.object.category.name }}</a></span>
   <span class="post-date"><a href="#" rel="external nofollow" rel="external nofollow" >
       <time class="entry-date" datetime="{{ result.object.created_time }}">
        {{ result.object.created_time }}</time></a></span>
   <span class="post-author"><a href="#" rel="external nofollow" rel="external nofollow" >{{ result.object.author }}</a></span>
   <span class="comments-link">
      <a href="{{ result.object.get_absolute_url }}#comment-area" rel="external nofollow" >
       {{ result.object.comment_set.count }} 评论</a></span>
   <span class="views-count"><a
     href="{{ result.object.get_absolute_url }}" rel="external nofollow" rel="external nofollow" rel="external nofollow" >{{ result.object.views }} 阅读</a></span>
   </div>
  </header>
  <div class="entry-content clearfix">
   <p>{% highlight result.object.body with query %}</p>
   <div class="read-more cl-effect-14">
   <a href="{{ result.object.get_absolute_url }}" rel="external nofollow" rel="external nofollow" rel="external nofollow" class="more-link">继续阅读 <span
     class="meta-nav">→</span></a>
   </div>
  </div>
  </article>
 {% empty %}
  <div class="no-post">没有搜索到你想要的结果！</div>
 {% endfor %}

 {% if page.has_previous or page.has_next %}
  <div class="text-center" style="margin-top: 30px">
  {% if page.has_previous %}
   <a href="?q={{ query }}&amp;page={{ page.previous_page_number }}" rel="external nofollow" >{% endif %}&laquo; Previous
  {% if page.has_previous %}</a>{% endif %}
  <span style="margin: 0 10px">|</span>
  {% if page.has_next %}<a href="?q={{ query }}&amp;page={{ page.next_page_number }}" rel="external nofollow" >{% endif %}Next
  &raquo;{% if page.has_next %}</a>{% endif %}
  </div>
 {% endif %}
 {% else %}
 请输入搜索关键词，例如 django
 {% endif %}
{% endblock main %}

# 使用默认值 
{% highlight result.summary with query %} 
 
# 这里我们为 {{ result.summary }} 里所有的 {{ query }} 指定了一个<div></div>标签，并且将class设置为highlight_me_please，这样就可以自己通过CSS为{{ query }}添加高亮效果了，怎么样，是不是很科学呢 
{% highlight result.summary with query html_tag "div" css_class "highlight_me_please" %} 
 
# 可以 max_length 限制最终{{ result.summary }} 被高亮处理后的长度
{% highlight result.summary with query max_length 40 %} 

<head>
 <title>Black &amp; White</title>
 ...
 <style>
  /* 搜索关键词高亮 */
  span.highlighted {
   color: red;
  }
 </style>
 ...
</head>

$ docker exec -it hellodjango_blog_tutorial_local python manage.py rebuild_index

from haystack.backends.elasticsearch2_backend import Elasticsearch2SearchBackend, Elasticsearch2SearchEngine

DEFAULT_FIELD_MAPPING = {'type': 'string', "analyzer": "ik_max_word", "search_analyzer": "ik_smart"}


class Elasticsearch2IkSearchBackend(Elasticsearch2SearchBackend):

 def __init__(self, *args, **kwargs):
  self.DEFAULT_SETTINGS['settings']['analysis']['analyzer']['ik_analyzer'] = {
   "type": "custom",
   "tokenizer": "ik_max_word",
  }
  super(Elasticsearch2IkSearchBackend, self).__init__(*args, **kwargs)


class Elasticsearch2IkSearchEngine(Elasticsearch2SearchEngine):
 backend = Elasticsearch2IkSearchBackend

# 搜索设置
HAYSTACK_CONNECTIONS = {
 'default': {
  'ENGINE': 'blog.elasticsearch2_ik_backend.Elasticsearch2IkSearchEngine',
  'URL': '',
  'INDEX_NAME': 'hellodjango_blog_tutorial',
 },
}
HAYSTACK_SEARCH_RESULTS_PER_PAGE = 10
HAYSTACK_SIGNAL_PROCESSOR = 'haystack.signals.RealtimeSignalProcessor'

from django.utils.html import strip_tags
from haystack.utils import Highlighter as HaystackHighlighter


class Highlighter(HaystackHighlighter):
 """
 自定义关键词高亮器，不截断过短的文本（例如文章标题）
 """

 def highlight(self, text_block):
  self.text_block = strip_tags(text_block)
  highlight_locations = self.find_highlightable_words()
  start_offset, end_offset = self.find_window(highlight_locations)
  if len(text_block) < self.max_length:
   start_offset = 0
  return self.render_html(highlight_locations, start_offset, end_offset)

HAYSTACK_CUSTOM_HIGHLIGHTER = 'blog.utils.Highlighter'

 elasticsearch:
 build:
  context: .
  dockerfile: ./compose/production/elasticsearch/Dockerfile
 image: hellodjango_blog_tutorial_elasticsearch
 container_name: hellodjango_blog_tutorial_elasticsearch
 volumes:
  - esdata:/usr/share/elasticsearch/data
 ports:
  - "9200:9200"
 environment:
  - "ES_JAVA_OPTS=-Xms512m -Xmx512m"
 ulimits:
  memlock:
  soft: -1
  hard: -1
  nproc: 65536
  nofile:
  soft: 65536
  hard: 65536

HAYSTACK_CONNECTIONS['default']['URL'] = 'http://hellodjango_blog_tutorial_elasticsearch:9200/'