[bug 721184, 716999] Fixes wiki indexing

Actively remove from the index and prevent from being indexed wiki documents
that are redirects or have no revisions.

apps/wiki/models.py

@@ -670,6 +670,16 @@ def extract_document(self):
             d['current'] = None
         return d
 
+    @classmethod
+    def index(cls, document, **kwargs):
+        # If there are no revisions or the current revision is a redirect,
+        # we want to remove it from the index.
+        if (document['current'] is None or
+            document['content'].startswith(REDIRECT_HTML)):
+            cls.unindex(document['id'])
+            return
+        super(cls, cls).index(document, **kwargs)
+
 
 register_for_indexing(Document, 'wiki')
 register_for_indexing(

apps/wiki/tests/test_es.py

@@ -2,15 +2,17 @@
 from nose.tools import eq_
 
 from sumo.tests import ElasticTestCase
-from wiki.tests import document
+from wiki.tests import document, revision
 from wiki.models import Document
+from wiki.config import REDIRECT_CONTENT
 
 
 class TestPostUpdate(ElasticTestCase):
     def test_add_and_delete(self):
         """Adding a doc should add it to the search index; deleting should
         delete it."""
         doc = document(save=True)
+        revision(document=doc, is_approved=True, save=True)
         self.refresh()
         eq_(elasticutils.S(Document).count(), 1)
 
@@ -21,12 +23,14 @@ def test_add_and_delete(self):
     def test_translations_get_parent_tags(self):
         doc1 = document(title=u'Audio too loud')
         doc1.save()
+        revision(document=doc1, is_approved=True, save=True)
         doc1.tags.add(u'desktop')
         doc1.tags.add(u'windows')
 
         doc2 = document(title=u'Audio too loud bork bork',
                         parent=doc1)
         doc2.save()
+        revision(document=doc2, is_approved=True, save=True)
         doc2.tags.add(u'badtag')
 
         # Verify the parent has the right tags.
@@ -45,6 +49,7 @@ def test_wiki_tags(self):
         tag = u'hiphop'
         eq_(elasticutils.S(Document).filter(tag=tag).count(), 0)
         doc = document(save=True)
+        revision(document=doc, is_approved=True, save=True)
         self.refresh()
         eq_(elasticutils.S(Document).filter(tag=tag).count(), 0)
         doc.tags.add(tag)
@@ -58,3 +63,33 @@ def test_wiki_tags(self):
         eq_(elasticutils.S(Document).filter().count(), 1)
 
         eq_(elasticutils.S(Document).filter(tag=tag).count(), 0)
+
+    def test_wiki_no_revisions(self):
+        """Don't index documents without approved revisions"""
+        # Create a document with no revisions and make sure the
+        # document is not in the index.
+        doc = document(save=True)
+        self.refresh()
+        eq_(elasticutils.S(Document).count(), 0)
+        # Create a revision that's not approved and make sure the
+        # document is still not in the index.
+        revision(document=doc, is_approved=False, save=True)
+        self.refresh()
+        eq_(elasticutils.S(Document).count(), 0)
+
+    def test_wiki_redirects(self):
+        """Make sure we don't index redirects"""
+        # First create a revision that doesn't have a redirect and
+        # make sure it's in the index.
+        doc = document(title=u'wool hats')
+        doc.save()
+        revision(document=doc, is_approved=True, save=True)
+        self.refresh()
+        eq_(elasticutils.S(Document).query('wool').count(), 1)
+
+        # Now create a revision that is a redirect and make sure the
+        # document is removed from the index.
+        revision(document=doc, content=REDIRECT_CONTENT, is_approved=True,
+                 save=True)
+        self.refresh()
+        eq_(elasticutils.S(Document).query('wool').count(), 0)