全文搜索

blog/search_indexes.py

@@ -9,8 +9,9 @@
 
 
 class PostIndex(indexes.SearchIndex, indexes.Indexable):
+    # 文章内容
     text = indexes.CharField(document=True, use_template=True)
-    # 对title字段进行索引
+    # 对标题字段进行索引
     title = indexes.CharField(model_attr='title')
 
     def get_model(self):

blog/templates/blog/post_search_list.html

@@ -1,15 +1,12 @@
 {% extends 'mysite/base.html' %}
 {% load blog_tags %}
-{% load pagination_tags %}
 {% block content %}
     {% if list_header %}
         <div class="box">{{ list_header }}</div>
     {% endif %}
-    {% autopaginate posts 10 %}
     {% for post in posts %}
         <div class="post">
             <h2><a href="{% url 'blog.views.post_detail' pk=post.pk %}">{{ post.title }}</a></h2>
         </div>
     {% endfor %}
-    {% paginate %}
 {% endblock %}

blog/urls.py

@@ -4,7 +4,7 @@
 
 urlpatterns = [
     url(r'^$', post_list, name='home'),
-    # url(r'^posts/search/$', full_search, name='full_search'),
+    url(r'^posts/search/$', full_search, name='full_search'),
     url(r'^posts/tag/(?P<tag>\w+)$', post_list_by_tag, name='list_by_tag'),
     url(r'^posts/category/(?P<cg>\w+)$', post_list_by_category, name='list_by_cg'),
     url(r'^posts/archive/(?P<y>[0-9]{4})/(?P<m>[0-9]{1,2})$', post_list_by_ym, name='list_by_ym'),

blog/views.py

@@ -14,17 +14,17 @@
 import json
 
 
-# from haystack.forms import SearchForm
+from haystack.forms import SearchForm
 # import qiniu
 
 
-# def full_search(request):
-#     """全局搜索"""
-#     keywords = request.GET['q']
-#     sform = SearchForm(request.GET)
-#     posts = sform.search()
-#     return render(request, 'blog/post_search_list.html',
-#                   {'posts': posts, 'list_header': '关键字 \'{}\' 搜索结果'.format(keywords)})
+def full_search(request):
+    """全局搜索"""
+    keywords = request.GET['q']
+    sform = SearchForm(request.GET)
+    posts = sform.search()
+    return render(request, 'blog/post_search_list.html',
+                  {'posts': posts, 'list_header': '关键字 \'{}\' 搜索结果'.format(keywords)})
 
 
 def get_client_ip(request):

blog/whoosh_cn_backend.py

@@ -1,24 +1,27 @@
-from __future__ import unicode_literals
+# encoding: utf-8
+
+from __future__ import absolute_import, division, print_function, unicode_literals
+
 import os
 import re
 import shutil
 import threading
 import warnings
-from jieba.analyse import ChineseAnalyzer
 
 from django.conf import settings
 from django.core.exceptions import ImproperlyConfigured
-from django.db.models.loading import get_model
 from django.utils import six
 from django.utils.datetime_safe import datetime
-from haystack.backends import BaseEngine, BaseSearchBackend, BaseSearchQuery, log_query, EmptyResults
-from haystack.constants import ID, DJANGO_CT, DJANGO_ID
-from haystack.exceptions import MissingDependency, SearchBackendError
-from haystack.inputs import PythonData, Clean, Exact, Raw
+
+from haystack.backends import BaseEngine, BaseSearchBackend, BaseSearchQuery, EmptyResults, log_query
+from haystack.constants import DJANGO_CT, DJANGO_ID, ID
+from haystack.exceptions import MissingDependency, SearchBackendError, SkipDocument
+from haystack.inputs import Clean, Exact, PythonData, Raw
 from haystack.models import SearchResult
-from haystack.utils import get_identifier
 from haystack.utils import log as logging
-from haystack.utils import get_model_ct
+from haystack.utils import get_identifier, get_model_ct
+from haystack.utils.app_loading import haystack_get_model
+from jieba.analyse import ChineseAnalyzer
 
 try:
     import json
@@ -38,20 +41,21 @@
 except ImportError:
     raise MissingDependency("The 'whoosh' backend requires the installation of 'Whoosh'. Please refer to the documentation.")
 
+# Handle minimum requirement.
+if not hasattr(whoosh, '__version__') or whoosh.__version__ < (2, 5, 0):
+    raise MissingDependency("The 'whoosh' backend requires version 2.5.0 or greater.")
+
 # Bubble up the correct error.
 from whoosh import index
 from whoosh.analysis import StemmingAnalyzer
 from whoosh.fields import ID as WHOOSH_ID
-from whoosh.fields import Schema, IDLIST, TEXT, KEYWORD, NUMERIC, BOOLEAN, DATETIME, NGRAM, NGRAMWORDS
+from whoosh.fields import BOOLEAN, DATETIME, IDLIST, KEYWORD, NGRAM, NGRAMWORDS, NUMERIC, Schema, TEXT
 from whoosh.filedb.filestore import FileStorage, RamStorage
+from whoosh.highlight import highlight as whoosh_highlight
+from whoosh.highlight import ContextFragmenter, HtmlFormatter
 from whoosh.qparser import QueryParser
 from whoosh.searching import ResultsPage
 from whoosh.writing import AsyncWriter
-from whoosh.highlight import HtmlFormatter, highlight as whoosh_highlight, ContextFragmenter
-
-# Handle minimum requirement.
-if not hasattr(whoosh, '__version__') or whoosh.__version__ < (2, 5, 0):
-    raise MissingDependency("The 'whoosh' backend requires version 2.5.0 or greater.")
 
 
 DATETIME_REGEX = re.compile('^(?P<year>\d{4})-(?P<month>\d{2})-(?P<day>\d{2})T(?P<hour>\d{2}):(?P<minute>\d{2}):(?P<second>\d{2})(\.\d{3,6}Z?)?$')
@@ -189,32 +193,32 @@ def update(self, index, iterable, commit=True):
         writer = AsyncWriter(self.index)
 
         for obj in iterable:
-            doc = index.full_prepare(obj)
-
-            # Really make sure it's unicode, because Whoosh won't have it any
-            # other way.
-            for key in doc:
-                doc[key] = self._from_python(doc[key])
-
-            # Document boosts aren't supported in Whoosh 2.5.0+.
-            if 'boost' in doc:
-                del doc['boost']
-
             try:
-                writer.update_document(**doc)
-            except Exception as e:
-                if not self.silently_fail:
-                    raise
-
-                # We'll log the object identifier but won't include the actual object
-                # to avoid the possibility of that generating encoding errors while
-                # processing the log message:
-                self.log.error(u"%s while preparing object for update" % e.__class__.__name__, exc_info=True, extra={
-                    "data": {
-                        "index": index,
-                        "object": get_identifier(obj)
-                    }
-                })
+                doc = index.full_prepare(obj)
+            except SkipDocument:
+                self.log.debug(u"Indexing for object `%s` skipped", obj)
+            else:
+                # Really make sure it's unicode, because Whoosh won't have it any
+                # other way.
+                for key in doc:
+                    doc[key] = self._from_python(doc[key])
+
+                # Document boosts aren't supported in Whoosh 2.5.0+.
+                if 'boost' in doc:
+                    del doc['boost']
+
+                try:
+                    writer.update_document(**doc)
+                except Exception as e:
+                    if not self.silently_fail:
+                        raise
+
+                    # We'll log the object identifier but won't include the actual object
+                    # to avoid the possibility of that generating encoding errors while
+                    # processing the log message:
+                    self.log.error(u"%s while preparing object for update" % e.__class__.__name__,
+                                   exc_info=True, extra={"data": {"index": index,
+                                                                  "object": get_identifier(obj)}})
 
         if len(iterable) > 0:
             # For now, commit no matter what, as we run into locking issues otherwise.
@@ -233,16 +237,19 @@ def remove(self, obj_or_string, commit=True):
             if not self.silently_fail:
                 raise
 
-            self.log.error("Failed to remove document '%s' from Whoosh: %s", whoosh_id, e)
+            self.log.error("Failed to remove document '%s' from Whoosh: %s", whoosh_id, e, exc_info=True)
 
-    def clear(self, models=[], commit=True):
+    def clear(self, models=None, commit=True):
         if not self.setup_complete:
             self.setup()
 
         self.index = self.index.refresh()
 
+        if models is not None:
+            assert isinstance(models, (list, tuple))
+
         try:
-            if not models:
+            if models is None:
                 self.delete_index()
             else:
                 models_to_delete = []
@@ -255,7 +262,11 @@ def clear(self, models=[], commit=True):
             if not self.silently_fail:
                 raise
 
-            self.log.error("Failed to clear documents from Whoosh: %s", e)
+            if models is not None:
+                self.log.error("Failed to clear Whoosh index of models '%s': %s", ','.join(models_to_delete),
+                               e, exc_info=True)
+            else:
+                self.log.error("Failed to clear Whoosh index: %s", e, exc_info=True)
 
     def delete_index(self):
         # Per the Whoosh mailing list, if wiping out everything from the index,
@@ -603,7 +614,7 @@ def _process_results(self, raw_page, highlight=False, query_string='', spelling_
             score = raw_page.score(doc_offset) or 0
             app_label, model_name = raw_result[DJANGO_CT].split('.')
             additional_fields = {}
-            model = get_model(app_label, model_name)
+            model = haystack_get_model(app_label, model_name)
 
             if model and model in indexed_models:
                 for key, value in raw_result.items():

mysite/settings.py

@@ -40,7 +40,7 @@
     'django.contrib.staticfiles',
     'django.contrib.admin',
     # 'xadmin',
-    # 'haystack',
+    'haystack',
     'crispy_forms',
     'reversion',
     'blog',
@@ -148,13 +148,13 @@
 # SESSION_CACHE_ALIAS = 'default'
 
 # full text search
-# HAYSTACK_CONNECTIONS = {
-#     'default': {
-#         'ENGINE': 'blog.whoosh_cn_backend.WhooshEngine',
-#         'PATH': os.path.join(BASE_DIR, 'whoosh_index'),
-#     },
-# }
-# HAYSTACK_SIGNAL_PROCESSOR = 'haystack.signals.RealtimeSignalProcessor'
+HAYSTACK_CONNECTIONS = {
+    'default': {
+        'ENGINE': 'blog.whoosh_cn_backend.WhooshEngine',
+        'PATH': os.path.join(BASE_DIR, 'whoosh_index'),
+    },
+}
+HAYSTACK_SIGNAL_PROCESSOR = 'haystack.signals.RealtimeSignalProcessor'
 
 # A sample logging configuration. The only tangible logging
 # performed by this configuration is to send an email to

mysite/templates/mysite/base.html

@@ -54,7 +54,7 @@ <h1><a href="{% url 'blog.views.post_list' %}">{% trans 'Simple Blog'%}</a></h1>
     <!-- menus END -->
     <!-- searchbox START -->
     <div id="searchbox">
-        <form action="" method="get">
+        <form action="{% url 'blog.views.full_search' %}" method="get">
             <div class="content">
                 <label>
                     <input type="text" class="textfield searchtip" name="q" size="24" value="">

mysite/urls.py

@@ -5,6 +5,6 @@
 urlpatterns = [
     url('^', include('django.contrib.auth.urls')),
     url(r'^admin/', include(admin.site.urls)),
-    # url(r'^search/', include('haystack.urls')),
+    url(r'^search/', include('haystack.urls')),
     url(r'', include('blog.urls')),
 ]