Revert "Merge pull request #4636 from rtfd/search_upgrade" (#4716)

This reverts commit 182ab8d, reversing
changes made to 6261427.

Author: ericholscher

.travis.yml

@@ -4,7 +4,7 @@ python:
   - 3.6
 sudo: false
 env:
-  - ES_VERSION=6.2.4 ES_DOWNLOAD_URL=https://artifacts.elastic.co/downloads/elasticsearch/elasticsearch-${ES_VERSION}.tar.gz
+  - ES_VERSION=1.3.9 ES_DOWNLOAD_URL=https://download.elastic.co/elasticsearch/elasticsearch/elasticsearch-${ES_VERSION}.tar.gz
 matrix:
   include:
     - python: 3.6

conftest.py

@@ -1,7 +1,5 @@
 # -*- coding: utf-8 -*-
 import pytest
-from django.conf import settings
-from rest_framework.test import APIClient
 
 try:
     # TODO: this file is read/executed even when called from ``readthedocsinc``,
@@ -46,7 +44,3 @@ def pytest_configure(config):
 @pytest.fixture(autouse=True)
 def settings_modification(settings):
     settings.CELERY_ALWAYS_EAGER = True
-
-@pytest.fixture
-def api_client():
-    return APIClient()

docs/custom_installs/elasticsearch.rst

@@ -0,0 +1,108 @@
+==========================================
+Enabling Elasticsearch on the local server
+==========================================
+
+Read the Docs has been using Elasticsearch for indexing and searching. To enable this on your local installation, you need to install elasticsearch and run the Elastic server locally. 
+
+Installation has been mainly divided into following steps.
+
+Installing Java
+---------------
+
+Elasticsearch requires Java 8 or later. Use `Oracle official documentation <http://www.oracle.com/technetwork/java/javase/downloads/index.html>`_. 
+or opensource distribution like `OpenJDK <http://openjdk.java.net/install/>`_.
+
+After installing java, verify the installation by,::
+
+    $ java -version
+
+The result should be something like this::
+
+    openjdk version "1.8.0_151"
+    OpenJDK Runtime Environment (build 1.8.0_151-8u151-b12-0ubuntu0.16.04.2-b12)
+    OpenJDK 64-Bit Server VM (build 25.151-b12, mixed mode)
+
+
+Downloading and installing Elasticsearch
+----------------------------------------
+
+Elasticsearch can be downloaded directly from elastic.co. For Ubuntu, it's best to use the deb (Debian) package which will install everything you need to run Elasticsearch.
+
+RTD currently uses elasticsearch 1.x which can be easily downloaded and installed from `elastic.co 
+<https://www.elastic.co/downloads/past-releases/elasticsearch-1-3-8/>`_.
+
+Install the downloaded package by following command::
+
+    $ sudo apt install .{path-to-downloaded-file}/elasticsearch-1.3.8.deb
+
+Custom setup
+------------
+
+You need the icu plugin::
+
+    $ elasticsearch/bin/plugin -install elasticsearch/elasticsearch-analysis-icu/2.3.0
+
+Running Elasticsearch from command line
+---------------------------------------
+
+Elasticsearch is not started automatically after installation. How to start and stop Elasticsearch depends on whether your system uses SysV init or systemd (used by newer distributions). You can tell which is being used by running this command::
+
+    $ ps -p 1   
+
+**Running Elasticsearch with SysV init**
+
+Use the ``update-rc.d command`` to configure Elasticsearch to start automatically when the system boots up::
+
+    $ sudo update-rc.d elasticsearch defaults 95 10
+
+Elasticsearch can be started and stopped using the service command::
+
+    $ sudo -i service elasticsearch start
+    $ sudo -i service elasticsearch stop
+
+If Elasticsearch fails to start for any reason, it will print the reason for failure to STDOUT. Log files can be found in /var/log/elasticsearch/.
+
+**Running Elasticsearch with systemd**
+
+To configure Elasticsearch to start automatically when the system boots up, run the following commands::
+
+    $ sudo /bin/systemctl daemon-reload
+    $ sudo /bin/systemctl enable elasticsearch.service
+
+Elasticsearch can be started and stopped as follows::
+
+    $ sudo systemctl start elasticsearch.service
+    $ sudo systemctl stop elasticsearch.service
+
+To verify run::
+
+    $ curl http://localhost:9200
+
+
+You should get something like::
+
+    {
+        status: 200,
+        name: "Amina Synge",
+        version: {
+            number: "1.3.8",
+            build_hash: "475733ee0837fba18c00c3ee76cd49a08755550c",
+            build_timestamp: "2015-02-11T14:45:42Z",
+            build_snapshot: false,
+            lucene_version: "4.9"
+        },
+        tagline: "You Know, for Search"
+    }
+
+Index the data available at RTD database
+----------------------------------------
+
+You need to create the indexes::
+
+    $ python manage.py provision_elasticsearch
+
+In order to search through the RTD database, you need to index it into the elasticsearch index:: 
+
+    $ python manage.py reindex_elasticsearch
+
+You are ready to go!

docs/development/search.rst

@@ -96,7 +96,6 @@ Information about development is also available:
 
    changelog
    install
-   development/search
    architecture
    tests
    docs

docs/index.rst

@@ -57,7 +57,7 @@ need to install Python 2.7 with virtualenv in your system as well.
    If you want full support for searching inside your Read the Docs
    site you will need to install Elasticsearch_.
 
-   Follow :doc:`/development/search` documentation for more instruction.
+   Ubuntu users could install this package by following :doc:`/custom_installs/elasticsearch`.
 
 .. note::
 

docs/install.rst

@@ -100,81 +100,3 @@ ALLOW_ADMIN
 Default: :djangosetting:`ALLOW_ADMIN`
 
 Whether to include `django.contrib.admin` in the URL's.
-
-
-ELASTICSEARCH_DSL
------------------
-
-Default:
-
-.. code-block:: python
-
-   {
-      'default': {
-         'hosts': '127.0.0.1:9200'
-      },
-   }
-
-Settings for elasticsearch connection.
-This settings then pass to `elasticsearch-dsl-py.connections.configure`_
-
-
-ES_INDEXES
-----------
-
-Default:
-
-.. code-block:: python
-
-   {
-        'project': {
-            'name': 'project_index',
-            'settings': {'number_of_shards': 5,
-                         'number_of_replicas': 0
-                         }
-        },
-        'page': {
-            'name': 'page_index',
-            'settings': {
-                'number_of_shards': 5,
-                'number_of_replicas': 0,
-            }
-        },
-    }
-
-Define the elasticsearch name and settings of all the index separately.
-The key is the type of index, like ``project`` or ``page`` and the value is another
-dictionary containing ``name`` and ``settings``. Here the ``name`` is the index name
-and the ``settings`` is used for configuring the particular index.
-
-
-ES_TASK_CHUNK_SIZE
-------------------
-
-Default: :djangosetting:`ES_TASK_CHUNK_SIZE`
-
-The maximum number of data send to each elasticsearch indexing celery task.
-This has been used while running ``elasticsearch_reindex`` management command.
-
-
-ES_PAGE_IGNORE_SIGNALS
-----------------------
-
-Default: ``False``
-
-This settings is used to determine whether to index each page separately into elasticsearch.
-If the setting is ``True``, each ``HTML`` page will not be indexed separately but will be
-indexed by bulk indexing.
-
-
-ELASTICSEARCH_DSL_AUTOSYNC
---------------------------
-
-Default: ``True``
-
-This setting is used for automatically indexing objects to elasticsearch.
-``False`` by default in development so it is possible to create
-project and build documentations without having elasticsearch.
-
-
-.. _elasticsearch-dsl-py.connections.configure: https://elasticsearch-dsl.readthedocs.io/en/stable/configuration.html#multiple-clusters

docs/settings.rst

@@ -0,0 +1,33 @@
+"""Provision Elastic Search"""
+
+from __future__ import absolute_import
+import logging
+
+from django.core.management.base import BaseCommand
+
+from readthedocs.search.indexes import Index, PageIndex, ProjectIndex, SectionIndex
+
+log = logging.getLogger(__name__)
+
+
+class Command(BaseCommand):
+
+    help = __doc__
+
+    def handle(self, *args, **options):
+        """Provision new ES instance"""
+        index = Index()
+        index_name = index.timestamped_index()
+
+        log.info("Creating indexes..")
+        index.create_index(index_name)
+        index.update_aliases(index_name)
+
+        log.info("Updating mappings..")
+        proj = ProjectIndex()
+        proj.put_mapping()
+        page = PageIndex()
+        page.put_mapping()
+        sec = SectionIndex()
+        sec.put_mapping()
+        log.info("Done!")