diff --git a/.gitignore b/.gitignore index 828856f4c..069dfd35b 100644 --- a/.gitignore +++ b/.gitignore @@ -19,5 +19,8 @@ node_modules/ .tx/ +build/ +dist/ local/ +gh-pages/ searx.egg-info/ diff --git a/Makefile b/Makefile index 77ffe489f..b69202ba2 100644 --- a/Makefile +++ b/Makefile @@ -1,19 +1,28 @@ # -*- coding: utf-8; mode: makefile-gmake -*- +export GIT_URL=https://github.com/asciimoo/searx +export SEARX_URL=https://searx.me +export DOCS_URL=https://asciimoo.github.io/searx + PYOBJECTS = searx +DOC = docs PY_SETUP_EXTRAS ?= \[test\] include utils/makefile.include include utils/makefile.python +include utils/makefile.sphinx all: clean install PHONY += help help: @echo ' test - run developer tests' + @echo ' docs - build documentation' + @echo ' docs-live - autobuild HTML documentation while editing' @echo ' run - run developer instance' @echo ' install - developer install (./local)' @echo ' uninstall - uninstall (./local)' + @echo ' gh-pages - build docs & deploy on gh-pages branch' @echo '' @$(MAKE) -s -f utils/makefile.include make-help @echo '' @@ -40,6 +49,20 @@ run: pyenvinstall ) & $(PY_ENV)/bin/python ./searx/webapp.py +# docs +# ---- + +PHONY += docs +docs: pyenvinstall sphinx-doc + $(call cmd,sphinx,html,docs,docs) + +PHONY += docs-live +docs-live: pyenvinstall sphinx-live + $(call cmd,sphinx_autobuild,html,docs,docs) + +$(GH_PAGES):: + @echo "doc available at --> $(DOCS_URL)" + # test # ---- diff --git a/docs/_themes/searx/static/searx.css b/docs/_themes/searx/static/searx.css new file mode 100644 index 000000000..10f5b4eda --- /dev/null +++ b/docs/_themes/searx/static/searx.css @@ -0,0 +1,30 @@ +@import url("pocoo.css"); + +a, a.reference, a.footnote-reference { + color: #004b6b; + border-color: #004b6b; +} + +a:hover { + color: #6d4100; + border-color: #6d4100; +} + +p.version-warning { + background-color: #004b6b; +} + +div.sidebar { + background-color: whitesmoke; + border-color: lightsteelblue; + border-radius: 3pt; +} + +p.sidebar-title, .sidebar p { + margin: 6pt; +} + +.sidebar li { + list-style-type: disclosure-closed; +} + diff --git a/docs/_themes/searx/theme.conf b/docs/_themes/searx/theme.conf new file mode 100644 index 000000000..2d5f72e7d --- /dev/null +++ b/docs/_themes/searx/theme.conf @@ -0,0 +1,6 @@ +[theme] +inherit = pocoo +stylesheet = searx.css + +[options] +touch_icon = diff --git a/docs/admin/api.rst b/docs/admin/api.rst new file mode 100644 index 000000000..7804a8664 --- /dev/null +++ b/docs/admin/api.rst @@ -0,0 +1,96 @@ +.. _adminapi: + +================== +Administration API +================== + +Get configuration data +====================== + +.. code:: http + + GET /config HTTP/1.1 + +Sample response +--------------- + +.. code:: json + + { + "autocomplete": "", + "categories": [ + "map", + "it", + "images", + ], + "default_locale": "", + "default_theme": "oscar", + "engines": [ + { + "categories": [ + "map" + ], + "enabled": true, + "name": "openstreetmap", + "shortcut": "osm" + }, + { + "categories": [ + "it" + ], + "enabled": true, + "name": "arch linux wiki", + "shortcut": "al" + }, + { + "categories": [ + "images" + ], + "enabled": true, + "name": "google images", + "shortcut": "goi" + }, + { + "categories": [ + "it" + ], + "enabled": false, + "name": "bitbucket", + "shortcut": "bb" + }, + ], + "instance_name": "searx", + "locales": { + "de": "Deutsch (German)", + "en": "English", + "eo": "Esperanto (Esperanto)", + }, + "plugins": [ + { + "enabled": true, + "name": "HTTPS rewrite" + }, + { + "enabled": false, + "name": "Vim-like hotkeys" + } + ], + "safe_search": 0 + } + + +Embed search bar +================ + +The search bar can be embedded into websites. Just paste the example into the +HTML of the site. URL of the searx instance and values are customizable. + +.. code:: html + +
+ + + + + +
diff --git a/docs/admin/filtron.rst b/docs/admin/filtron.rst new file mode 100644 index 000000000..07dcb9bc5 --- /dev/null +++ b/docs/admin/filtron.rst @@ -0,0 +1,148 @@ +========================== +How to protect an instance +========================== + +Searx depens on external search services. To avoid the abuse of these services +it is advised to limit the number of requests processed by searx. + +An application firewall, ``filtron`` solves exactly this problem. Information +on how to install it can be found at the `project page of filtron +`__. + + +Sample configuration of filtron +=============================== + +An example configuration can be find below. This configuration limits the access +of: + +- scripts or applications (roboagent limit) +- webcrawlers (botlimit) +- IPs which send too many requests (IP limit) +- too many json, csv, etc. requests (rss/json limit) +- the same UserAgent of if too many requests (useragent limit) + +.. code:: json + + [{ + "name":"search request", + "filters":[ + "Param:q", + "Path=^(/|/search)$" + ], + "interval":"", + "limit":"", + "subrules":[ + { + "name":"roboagent limit", + "interval":"", + "limit":"", + "filters":[ + "Header:User-Agent=(curl|cURL|Wget|python-requests|Scrapy|FeedFetcher|Go-http-client)" + ], + "actions":[ + { + "name":"block", + "params":{ + "message":"Rate limit exceeded" + } + } + ] + }, + { + "name":"botlimit", + "limit":0, + "stop":true, + "filters":[ + "Header:User-Agent=(Googlebot|bingbot|Baiduspider|yacybot|YandexMobileBot|YandexBot|Yahoo! Slurp|MJ12bot|AhrefsBot|archive.org_bot|msnbot|MJ12bot|SeznamBot|linkdexbot|Netvibes|SMTBot|zgrab|James BOT)" + ], + "actions":[ + { + "name":"block", + "params":{ + "message":"Rate limit exceeded" + } + } + ] + }, + { + "name":"IP limit", + "interval":"", + "limit":"", + "stop":true, + "aggregations":[ + "Header:X-Forwarded-For" + ], + "actions":[ + { + "name":"block", + "params":{ + "message":"Rate limit exceeded" + } + } + ] + }, + { + "name":"rss/json limit", + "interval":"", + "limit":"", + "stop":true, + "filters":[ + "Param:format=(csv|json|rss)" + ], + "actions":[ + { + "name":"block", + "params":{ + "message":"Rate limit exceeded" + } + } + ] + }, + { + "name":"useragent limit", + "interval":"", + "limit":"", + "aggregations":[ + "Header:User-Agent" + ], + "actions":[ + { + "name":"block", + "params":{ + "message":"Rate limit exceeded" + } + } + ] + } + ] + }] + + + +Route request through filtron +============================= + +Filtron can be started using the following command: + +.. code:: sh + + $ filtron -rules rules.json + +It listens on ``127.0.0.1:4004`` and forwards filtered requests to +``127.0.0.1:8888`` by default. + +Use it along with ``nginx`` with the following example configuration. + +.. code:: nginx + + location / { + proxy_set_header Host $http_host; + proxy_set_header X-Real-IP $remote_addr; + proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for; + proxy_set_header X-Scheme $scheme; + proxy_pass http://127.0.0.1:4004/; + } + +Requests are coming from port 4004 going through filtron and then forwarded to +port 8888 where a searx is being run. diff --git a/docs/admin/index.rst b/docs/admin/index.rst new file mode 100644 index 000000000..f3a995769 --- /dev/null +++ b/docs/admin/index.rst @@ -0,0 +1,11 @@ +=========================== +Administrator documentation +=========================== + +.. toctree:: + :maxdepth: 1 + + installation + api + filtron + morty diff --git a/docs/admin/installation.rst b/docs/admin/installation.rst new file mode 100644 index 000000000..239ce0704 --- /dev/null +++ b/docs/admin/installation.rst @@ -0,0 +1,341 @@ +.. _installation: + +============ +Installation +============ + +.. contents:: + :depth: 3 + +Basic installation +================== + +Step by step installation for Debian/Ubuntu with virtualenv. For Ubuntu, be sure +to have enable universe repository. + +Install packages: + +.. code:: sh + + $ sudo -H apt-get install \ + git build-essential libxslt-dev \ + python-dev python-virtualenv python-babel \ + zlib1g-dev libffi-dev libssl-dev + +Install searx: + +.. code:: sh + + cd /usr/local + sudo -H git clone https://github.com/asciimoo/searx.git + sudo -H useradd searx -d /usr/local/searx + sudo -H chown searx:searx -R /usr/local/searx + +Install dependencies in a virtualenv: + +.. code:: sh + + cd /usr/local/searx + sudo -H -u searx -i + +.. code:: sh + + (searx)$ virtualenv searx-ve + (searx)$ . ./searx-ve/bin/activate + (searx)$ ./manage.sh update_packages + +Configuration +============== + +.. code:: sh + + sed -i -e "s/ultrasecretkey/`openssl rand -hex 16`/g" searx/settings.yml + +Edit searx/settings.yml if necessary. + +Check +===== + +Start searx: + +.. code:: sh + + python searx/webapp.py + +Go to http://localhost:8888 + +If everything works fine, disable the debug option in settings.yml: + +.. code:: sh + + sed -i -e "s/debug : True/debug : False/g" searx/settings.yml + +At this point searx is not demonized ; uwsgi allows this. + +You can exit the virtualenv and the searx user bash (enter exit command +twice). + +uwsgi +===== + +Install packages: + +.. code:: sh + + sudo -H apt-get install \ + uwsgi uwsgi-plugin-python + +Create the configuration file ``/etc/uwsgi/apps-available/searx.ini`` with this +content: + +.. code:: ini + + [uwsgi] + # Who will run the code + uid = searx + gid = searx + + # disable logging for privacy + disable-logging = true + + # Number of workers (usually CPU count) + workers = 4 + + # The right granted on the created socket + chmod-socket = 666 + + # Plugin to use and interpretor config + single-interpreter = true + master = true + plugin = python + lazy-apps = true + enable-threads = true + + # Module to import + module = searx.webapp + + # Virtualenv and python path + virtualenv = /usr/local/searx/searx-ve/ + pythonpath = /usr/local/searx/ + chdir = /usr/local/searx/searx/ + +Activate the uwsgi application and restart: + +.. code:: sh + + cd /etc/uwsgi/apps-enabled + ln -s ../apps-available/searx.ini + /etc/init.d/uwsgi restart + +Web server +========== + +with nginx +---------- + +If nginx is not installed (uwsgi will not work with the package +nginx-light): + +.. code:: sh + + sudo -H apt-get install nginx + +Hosted at / +~~~~~~~~~~~ + +Create the configuration file ``/etc/nginx/sites-available/searx`` with this +content: + +.. code:: nginx + + server { + listen 80; + server_name searx.example.com; + root /usr/local/searx; + + location / { + include uwsgi_params; + uwsgi_pass unix:/run/uwsgi/app/searx/socket; + } + } + +Create a symlink to sites-enabled: + +.. code:: sh + + sudo -H ln -s /etc/nginx/sites-available/searx /etc/nginx/sites-enabled/searx + +Restart service: + +.. code:: sh + + sudo -H service nginx restart + sudo -H service uwsgi restart + +from subdirectory URL (/searx) +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Add this configuration in the server config file +``/etc/nginx/sites-enabled/default``: + +.. code:: nginx + + location = /searx { rewrite ^ /searx/; } + location /searx { + try_files $uri @searx; + } + location @searx { + uwsgi_param SCRIPT_NAME /searx; + include uwsgi_params; + uwsgi_modifier1 30; + uwsgi_pass unix:/run/uwsgi/app/searx/socket; + } + + +**OR** using reverse proxy (Please, note that reverse proxy advised to be used +in case of single-user or low-traffic instances.) + +.. code:: nginx + + location /searx { + proxy_pass http://127.0.0.1:8888; + proxy_set_header Host $host; + proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for; + proxy_set_header X-Scheme $scheme; + proxy_set_header X-Script-Name /searx; + proxy_buffering off; + } + + +Enable ``base_url`` in ``searx/settings.yml`` + +.. code:: yaml + + base_url : http://your.domain.tld/searx/ + +Restart service: + +.. code:: sh + + sudo -H service nginx restart + sudo -H service uwsgi restart + +disable logs +^^^^^^^^^^^^ + +for better privacy you can disable nginx logs about searx. + +how to proceed: below ``uwsgi_pass`` in ``/etc/nginx/sites-available/default`` +add: + +.. code:: nginx + + access_log /dev/null; + error_log /dev/null; + +Restart service: + +.. code:: sh + + sudo -H service nginx restart + +with apache +----------- + +Add wsgi mod: + +.. code:: sh + + sudo -H apt-get install libapache2-mod-uwsgi + sudo -H a2enmod uwsgi + +Add this configuration in the file ``/etc/apache2/apache2.conf``: + +.. code:: apache + + + Options FollowSymLinks Indexes + SetHandler uwsgi-handler + uWSGISocket /run/uwsgi/app/searx/socket + + +Note that if your instance of searx is not at the root, you should change +```` by the location of your instance, like ````. + +Restart Apache: + +.. code:: sh + + sudo -H /etc/init.d/apache2 restart + +disable logs +~~~~~~~~~~~~ + +For better privacy you can disable Apache logs. + +.. warning:: + + You can only disable logs for the whole (virtual) server not for a specific + path. + +Go back to ``/etc/apache2/apache2.conf`` and above ```` add: + +.. code:: apache + + CustomLog /dev/null combined + +Restart Apache: + +.. code:: sh + + sudo -H /etc/init.d/apache2 restart + +How to update +============= + +.. code:: sh + + cd /usr/local/searx + sudo -H -u searx -i + +.. code:: sh + + (searx)$ . ./searx-ve/bin/activate + (searx)$ git stash + (searx)$ git pull origin master + (searx)$ git stash apply + (searx)$ ./manage.sh update_packages + +.. code:: sh + + sudo -H service uwsgi restart + +Docker +====== + +Make sure you have installed Docker. For instance, you can deploy searx like this: + +.. code:: sh + + docker pull wonderfall/searx + docker run -d --name searx -p $PORT:8888 wonderfall/searx + +Go to ``http://localhost:$PORT``. + +See https://hub.docker.com/r/wonderfall/searx/ for more informations. It's also +possible to build searx from the embedded Dockerfile. + +.. code:: sh + + git clone https://github.com/asciimoo/searx.git + cd searx + docker build -t whatever/searx . + +References +========== + +* https://about.okhin.fr/posts/Searx/ with some additions + +* How to: `Setup searx in a couple of hours with a free SSL certificate + `__ + diff --git a/docs/admin/morty.rst b/docs/admin/morty.rst new file mode 100644 index 000000000..7d7b34492 --- /dev/null +++ b/docs/admin/morty.rst @@ -0,0 +1,26 @@ +========================= +How to setup result proxy +========================= + +.. _morty: https://github.com/asciimoo/morty +.. _morty's README: https://github.com/asciimoo/morty + +By default searx can only act as an image proxy for result images, but it is +possible to proxify all the result URLs with an external service, morty_. + +To use this feature, morty has to be installed and activated in searx's +``settings.yml``. + +Add the following snippet to your ``settings.yml`` and restart searx: + +.. code:: yaml + + result_proxy: + url : http://127.0.0.1:3000/ + key : your_morty_proxy_key + +``url`` + Is the address of the running morty service. + +``key`` + Is an optional argument, see `morty's README`_ for more information. diff --git a/docs/blog/admin.rst b/docs/blog/admin.rst new file mode 100644 index 000000000..e95316192 --- /dev/null +++ b/docs/blog/admin.rst @@ -0,0 +1,43 @@ +============================================================= +Searx admin interface +============================================================= + +.. _searx-admin: https://github.com/kvch/searx-admin#searx-admin +.. _NLnet Foundation: https://nlnet.nl/ + + manage your instance from your browser + +.. sidebar:: Installation + + Installation guide can be found in the repository of searx-admin_. + +One of the biggest advantages of searx is being extremely customizable. But at +first it can be daunting to newcomers. A barrier of taking advantage of this +feature is our ugly settings file which is sometimes hard to understand and +edit. + +To make self-hosting searx more accessible a new tool is introduced, called +``searx-admin``. It is a web application which is capable of managing your +instance and manipulating its settings via a web UI. It aims to replace editing +of ``settings.yml`` for less experienced administrators or people who prefer +graphical admin interfaces. + +.. figure:: searx-admin-engines.png + :alt: Screenshot of engine list + + Configuration page of engines + +Since ``searx-admin`` acts as a supervisor for searx, we have decided to +implement it as a standalone tool instead of part of searx. Another reason for +making it a standalone tool is that the codebase and dependencies of searx +should not grow because of a fully optional feature, which does not affect +existing instances. + + +Acknowledgements +================ + +This development was sponsored by `NLnet Foundation`_. + +| Happy hacking. +| kvch // 2017.08.22 21:25 diff --git a/docs/blog/index.rst b/docs/blog/index.rst new file mode 100644 index 000000000..52fa3f126 --- /dev/null +++ b/docs/blog/index.rst @@ -0,0 +1,10 @@ +==== +Blog +==== + +.. toctree:: + :maxdepth: 1 + + python3 + admin + intro-offline diff --git a/docs/blog/intro-offline.rst b/docs/blog/intro-offline.rst new file mode 100644 index 000000000..f6e90de3a --- /dev/null +++ b/docs/blog/intro-offline.rst @@ -0,0 +1,77 @@ +=============================== +Preparation for offline engines +=============================== + +Offline engines +=============== + +To extend the functionality of searx, offline engines are going to be +introduced. An offline engine is an engine which does not need Internet +connection to perform a search and does not use HTTP to communicate. + +Offline engines can be configured as online engines, by adding those to the +`engines` list of :origin:`settings.yml `. Thus, searx +finds the engine file and imports it. + +Example skeleton for the new engines: + +.. code:: python + + from subprocess import PIPE, Popen + + categories = ['general'] + offline = True + + def init(settings): + pass + + def search(query, params): + process = Popen(['ls', query], stdout=PIPE) + return_code = process.wait() + if return_code != 0: + raise RuntimeError('non-zero return code', return_code) + + results = [] + line = process.stdout.readline() + while line: + result = parse_line(line) + results.append(results) + + line = process.stdout.readline() + + return results + + +Development progress +==================== + +First, a proposal has been created as a Github issue. Then it was moved to the +wiki as a design document. You can read it here: :wiki:`Offline-engines`. + +In this development step, searx core was prepared to accept and perform offline +searches. Offline search requests are scheduled together with regular offline +requests. + +As offline searches can return arbitrary results depending on the engine, the +current result templates were insufficient to present such results. Thus, a new +template is introduced which is caplable of presenting arbitrary key value pairs +as a table. You can check out the pull request for more details see +:pull:`1700`. + +Next steps +========== + +Today, it is possible to create/run an offline engine. However, it is going to be publicly available for everyone who knows the searx instance. So the next step is to introduce token based access for engines. This way administrators are able to limit the access to private engines. + +Acknowledgement +=============== + +This development was sponsored by `Search and Discovery Fund`_ of `NLnet Foundation`_ . + +.. _Search and Discovery Fund: https://nlnet.nl/discovery +.. _NLnet Foundation: https://nlnet.nl/ + + +| Happy hacking. +| kvch // 2019.10.21 17:03 + diff --git a/docs/blog/python3.rst b/docs/blog/python3.rst new file mode 100644 index 000000000..5bb7f1c80 --- /dev/null +++ b/docs/blog/python3.rst @@ -0,0 +1,68 @@ +============================ +Introducing Python 3 support +============================ + +.. _Python 2.7 clock: https://pythonclock.org/ + +.. sidebar:: Python 2.7 to 3 upgrade + + This chapter exists of historical reasons. Python 2.7 release schedule ends + (`Python 2.7 clock`_) after 11 years Python 3 exists + +As most operation systems are coming with Python3 installed by default. So it is +time for searx to support Python3. But don't worry support of Python2.7 won't be +dropped. + +.. image:: searxpy3.png + :scale: 50 % + :alt: hurray + :align: center + + +How to run searx using Python 3 +=============================== + +Please make sure that you run at least Python 3.5. + +To run searx, first a Python3 virtualenv should be created. After entering the +virtualenv, dependencies must be installed. Then run searx with python3 instead +of the usual python command. + +.. code:: sh + + virtualenv -p python3 venv3 + source venv3/bin/activate + pip3 install -r requirements.txt + python3 searx/webapp.py + + +If you want to run searx using Python2.7, you don't have to do anything +differently as before. + +Fun facts +========= + +- 115 files were changed when implementing the support for both Python versions. + +- All of the dependencies was compatible except for the robotframework used for + browser tests. Thus, these tests were migrated to splinter. So from now on + both versions are being tested on Travis and can be tested locally. + +If you found bugs +================= + +Please open an issue on `GitHub`_. Make sure that you mention your Python +version in your issue, so we can investigate it properly. + +.. _GitHub: https://github.com/asciimoo/searx/issues + +Acknowledgment +============== + +This development was sponsored by `NLnet Foundation`_. + +.. _NLnet Foundation: https://nlnet.nl/ + + +| Happy hacking. +| kvch // 2017.05.13 22:57 diff --git a/docs/blog/searx-admin-engines.png b/docs/blog/searx-admin-engines.png new file mode 100644 index 000000000..610bacdf7 Binary files /dev/null and b/docs/blog/searx-admin-engines.png differ diff --git a/docs/blog/searxpy3.png b/docs/blog/searxpy3.png new file mode 100644 index 000000000..8eeaeec55 Binary files /dev/null and b/docs/blog/searxpy3.png differ diff --git a/docs/conf.py b/docs/conf.py new file mode 100644 index 000000000..c0bd246ac --- /dev/null +++ b/docs/conf.py @@ -0,0 +1,83 @@ +# -*- coding: utf-8 -*- + +import sys, os +from searx.version import VERSION_STRING +from pallets_sphinx_themes import ProjectLink + +GIT_URL = os.environ.get("GIT_URL", "https://github.com/asciimoo/searx") +SEARX_URL = os.environ.get("SEARX_URL", "https://searx.me") +DOCS_URL = os.environ.get("DOCS_URL", "https://asciimoo.github.io/searx/") + +# Project -------------------------------------------------------------- + +project = u'searx' +copyright = u'2015-2019, Adam Tauber, Noémi Ványi' +author = u'Adam Tauber' +release, version = VERSION_STRING, VERSION_STRING + +# General -------------------------------------------------------------- + +master_doc = "index" +source_suffix = '.rst' + +# usage:: lorem :patch:`f373169` ipsum +extlinks = {} + +# upstream links +extlinks['wiki'] = ('https://github.com/asciimoo/searx/wiki/%s', ' ') +extlinks['pull'] = ('https://github.com/asciimoo/searx/pull/%s', 'PR ') + +# links to custom brand +extlinks['origin'] = (GIT_URL + '/blob/master/%s', 'git://') +extlinks['patch'] = (GIT_URL + '/commit/%s', '#') +extlinks['search'] = (SEARX_URL + '/%s', '#') +extlinks['docs'] = (DOCS_URL + '/%s', 'docs: ') + +extensions = [ + 'sphinx.ext.extlinks', + 'sphinx.ext.viewcode', + "sphinx.ext.autodoc", + "sphinx.ext.intersphinx", + "pallets_sphinx_themes", + "sphinx_issues", # https://github.com/sloria/sphinx-issues/blob/master/README.rst +] + +intersphinx_mapping = { + "python": ("https://docs.python.org/3/", None), + # "flask": ("https://flask.palletsprojects.com/", None), + # "werkzeug": ("https://werkzeug.palletsprojects.com/", None), + # "jinja": ("https://jinja.palletsprojects.com/", None), +} + +issues_github_path = "asciimoo/searx" + +# HTML ----------------------------------------------------------------- + +sys.path.append(os.path.abspath('_themes')) + +html_theme_path = ['_themes'] +html_theme = "searx" + +html_theme_options = {"index_sidebar_logo": True} +html_context = { + "project_links": [ + ProjectLink("Source", GIT_URL), + ProjectLink("Wiki", "https://github.com/asciimoo/searx/wiki"), + ProjectLink("Public instances", "https://github.com/asciimoo/searx/wiki/Searx-instances"), + ProjectLink("Twitter", "https://twitter.com/Searx_engine"), + ] +} +html_sidebars = { + "**": ["project.html", "relations.html", "searchbox.html"], +} +singlehtml_sidebars = {"index": ["project.html", "localtoc.html"]} +html_static_path = ["static"] +html_logo = "static/img/searx_logo_small.png" +html_title = "Searx Documentation ({})".format("Searx-{}.tex".format(VERSION_STRING)) +html_show_sourcelink = False + +# LaTeX ---------------------------------------------------------------- + +latex_documents = [ + (master_doc, "searx-{}.tex".format(VERSION_STRING), html_title, author, "manual") +] diff --git a/docs/dev/contribution_guide.rst b/docs/dev/contribution_guide.rst new file mode 100644 index 000000000..064f28e63 --- /dev/null +++ b/docs/dev/contribution_guide.rst @@ -0,0 +1,147 @@ +================= +How to contribute +================= + +Prime directives: Privacy, Hackability +====================================== + +Searx has two prime directives, **privacy-by-design and hackability** . The +hackability comes in three levels: + +- support of search engines +- plugins to alter search behaviour +- hacking searx itself + +Note the lack of "world domination" among the directives. Searx has no +intention of wide mass-adoption, rounded corners, etc. The prime directive +"privacy" deserves a separate chapter, as it's quite uncommon unfortunately. + +Privacy-by-design +----------------- + +Searx was born out of the need for a **privacy-respecting** search tool which +can be extended easily to maximize both, its search and its privacy protecting +capabilities. + +A few widely used features work differently or turned off by default or not +implemented at all **as a consequence of privacy-by-design**. + +If a feature reduces the privacy preserving aspects of searx, it should be +switched off by default or should not implemented at all. There are plenty of +search engines already providing such features. If a feature reduces the +protection of searx, users must be informed about the effect of choosing to +enable it. Features that protect privacy but differ from the expectations of +the user should also be explained. + +Also, if you think that something works weird with searx, it's might be because +of the tool you use is designed in a way to interfere with the privacy respect. +Submitting a bugreport to the vendor of the tool that misbehaves might be a good +feedback to reconsider the disrespect to its customers (e.g. ``GET`` vs ``POST`` +requests in various browsers). + +Remember the other prime directive of searx is to be hackable, so if the above +privacy concerns do not fancy you, simply fork it. + + *Happy hacking.* + +Code +==== + +.. _PEP8: https://www.python.org/dev/peps/pep-0008/ + + +In order to submit a patch, please follow the steps below: + +- Follow coding conventions. + + - PEP8_ standards apply, except the convention of line length + - Maximum line length is 120 characters + +- Check if your code breaks existing tests. If so, update the tests or fix your + code. + +- If your code can be unit-tested, add unit tests. + +- Add yourself to the :origin:`AUTHORS.rst` file. + +- Create a pull request. + +For more help on getting started with searx development, see :ref:`devquickstart`. + + +Translation +=========== + +Translation currently takes place on :ref:`transifex `. + +.. caution:: + + Please, do not update translation files in the repo. + + +Documentation +============= + +.. _Sphinx: http://www.sphinx-doc.org +.. _reST: http://www.sphinx-doc.org/en/master/usage/restructuredtext/basics.html + +.. sidebar:: The reST sources + + has been moved from ``gh-branch`` into ``master`` (:origin:`docs`). + +The documentation is built using Sphinx_. So in order to be able to generate +the required files, you have to install it on your system. Much easier, use +Makefile our targets. + +Here is an example which makes a complete rebuild: + +.. code:: sh + + $ make docs-clean docs + ... + The HTML pages are in dist/docs. + + +live build +---------- + +.. sidebar:: docs-clean + + It is recommended to assert a complete rebuild before deploying (use + ``docs-clean``). + +Live build is like WYSIWYG, If you want to edit the documentation, its +recommended to use. The Makefile target ``docs-live`` builds the docs, opens URL +in your favorite browser and rebuilds every time a reST file has been changed. + +.. code:: sh + + $ make docs-live + ... + The HTML pages are in dist/docs. + ... Serving on http://0.0.0.0:8080 + ... Start watching changes + + + +deploy on github.io +------------------- + +To deploy documentation at :docs:`github.io <.>` use Makefile target +``gh-pages``, which will builds the documentation, clones searx into a sub +folder ``gh-pages``, cleans it, copies the doc build into and runs all the +needed git add, commit and push: + +.. code:: sh + + $ make docs-clean gh-pages + ... + SPHINX docs --> file://<...>/dist/docs + The HTML pages are in dist/docs. + ... + Cloning into 'gh-pages' ... + ... + cd gh-pages; git checkout gh-pages >/dev/null + Switched to a new branch 'gh-pages' + ... + doc available at --> https://asciimoo.github.io/searx diff --git a/docs/dev/engine_overview.rst b/docs/dev/engine_overview.rst new file mode 100644 index 000000000..92405dc64 --- /dev/null +++ b/docs/dev/engine_overview.rst @@ -0,0 +1,265 @@ + +.. _engines-dev: + +=============== +Engine overview +=============== + +.. _metasearch-engine: https://en.wikipedia.org/wiki/Metasearch_engine + +searx is a metasearch-engine_, so it uses different search engines to provide +better results. + +Because there is no general search API which could be used for every search +engine, an adapter has to be built between searx and the external search +engines. Adapters are stored under the folder :origin:`searx/engines`. + +.. contents:: + :depth: 3 + :backlinks: entry + +general engine configuration +============================ + +It is required to tell searx the type of results the engine provides. The +arguments can be set in the engine file or in the settings file +(normally ``settings.yml``). The arguments in the settings file override +the ones in the engine file. + +It does not matter if an option is stored in the engine file or in the +settings. However, the standard way is the following: + + +engine file +----------- + +======================= =========== =========================================== +argument type information +======================= =========== =========================================== +categories list pages, in which the engine is working +paging boolean support multible pages +language_support boolean support language choosing +time_range_support boolean support search time range +offline boolean engine runs offline +======================= =========== =========================================== + + +settings.yml +------------ + +======================= =========== =========================================== +argument type information +======================= =========== =========================================== +name string name of search-engine +engine string name of searx-engine + (filename without ``.py``) +shortcut string shortcut of search-engine +timeout string specific timeout for search-engine +======================= =========== =========================================== + + +overrides +--------- + +A few of the options have default values in the engine, but are often +overwritten by the settings. If ``None`` is assigned to an option in the engine +file, it has to be redefined in the settings, otherwise searx will not start +with that engine. + +The naming of overrides is arbitrary. But the recommended overrides are the +following: + +======================= =========== =========================================== +argument type information +======================= =========== =========================================== +base_url string base-url, can be overwritten to use same + engine on other URL +number_of_results int maximum number of results per request +language string ISO code of language and country like en_US +api_key string api-key if required by engine +======================= =========== =========================================== + +example code +------------ + +.. code:: python + + # engine dependent config + categories = ['general'] + paging = True + language_support = True + + +making a request +================ + +To perform a search an URL have to be specified. In addition to specifying an +URL, arguments can be passed to the query. + +passed arguments +---------------- + +These arguments can be used to construct the search query. Furthermore, +parameters with default value can be redefined for special purposes. + +====================== ============ ======================================================================== +argument type default-value, information +====================== ============ ======================================================================== +url string ``''`` +method string ``'GET'`` +headers set ``{}`` +data set ``{}`` +cookies set ``{}`` +verify boolean ``True`` +headers.User-Agent string a random User-Agent +category string current category, like ``'general'`` +started datetime current date-time +pageno int current pagenumber +language string specific language code like ``'en_US'``, or ``'all'`` if unspecified +====================== ============ ======================================================================== + +parsed arguments +---------------- + +The function ``def request(query, params):`` always returns the ``params`` +variable. Inside searx, the following paramters can be used to specify a search +request: + +============ =========== ========================================================= +argument type information +============ =========== ========================================================= +url string requested url +method string HTTP request method +headers set HTTP header information +data set HTTP data information (parsed if ``method != 'GET'``) +cookies set HTTP cookies +verify boolean Performing SSL-Validity check +============ =========== ========================================================= + + +example code +------------ + +.. code:: python + + # search-url + base_url = 'https://example.com/' + search_string = 'search?{query}&page={page}' + + # do search-request + def request(query, params): + search_path = search_string.format( + query=urlencode({'q': query}), + page=params['pageno']) + + params['url'] = base_url + search_path + + return params + + +returned results +================ + +Searx is able to return results of different media-types. Currently the +following media-types are supported: + +- default_ +- images_ +- videos_ +- torrent_ +- map_ + +To set another media-type as default, the parameter ``template`` must be set to +the desired type. + +default +------- + +========================= ===================================================== +result-parameter information +========================= ===================================================== +url string, url of the result +title string, title of the result +content string, general result-text +publishedDate :py:class:`datetime.datetime`, time of publish +========================= ===================================================== + +images +------ + +To use this template, the parameter: + +========================= ===================================================== +result-parameter information +========================= ===================================================== +template is set to ``images.html`` +url string, url to the result site +title string, title of the result *(partly implemented)* +content *(partly implemented)* +publishedDate :py:class:`datetime.datetime`, + time of publish *(partly implemented)* +img\_src string, url to the result image +thumbnail\_src string, url to a small-preview image +========================= ===================================================== + +videos +------ + +========================= ===================================================== +result-parameter information +========================= ===================================================== +template is set to ``videos.html`` +url string, url of the result +title string, title of the result +content *(not implemented yet)* +publishedDate :py:class:`datetime.datetime`, time of publish +thumbnail string, url to a small-preview image +========================= ===================================================== + +torrent +------- + +.. _magnetlink: https://en.wikipedia.org/wiki/Magnet_URI_scheme + +========================= ===================================================== +result-parameter information +========================= ===================================================== +template is set to ``torrent.html`` +url string, url of the result +title string, title of the result +content string, general result-text +publishedDate :py:class:`datetime.datetime`, + time of publish *(not implemented yet)* +seed int, number of seeder +leech int, number of leecher +filesize int, size of file in bytes +files int, number of files +magnetlink string, magnetlink_ of the result +torrentfile string, torrentfile of the result +========================= ===================================================== + + +map +--- + +========================= ===================================================== +result-parameter information +========================= ===================================================== +url string, url of the result +title string, title of the result +content string, general result-text +publishedDate :py:class:`datetime.datetime`, time of publish +latitude latitude of result (in decimal format) +longitude longitude of result (in decimal format) +boundingbox boundingbox of result (array of 4. values + ``[lat-min, lat-max, lon-min, lon-max]``) +geojson geojson of result (http://geojson.org) +osm.type type of osm-object (if OSM-Result) +osm.id id of osm-object (if OSM-Result) +address.name name of object +address.road street name of object +address.house_number house number of object +address.locality city, place of object +address.postcode postcode of object +address.country country of object +========================= ===================================================== diff --git a/docs/dev/index.rst b/docs/dev/index.rst new file mode 100644 index 000000000..8e18066ca --- /dev/null +++ b/docs/dev/index.rst @@ -0,0 +1,13 @@ +======================= +Developer documentation +======================= + +.. toctree:: + :maxdepth: 1 + + quickstart + contribution_guide + engine_overview + search_api + plugins + translation diff --git a/docs/dev/plugins.rst b/docs/dev/plugins.rst new file mode 100644 index 000000000..e97bbeb4a --- /dev/null +++ b/docs/dev/plugins.rst @@ -0,0 +1,48 @@ +======= +Plugins +======= + +Plugins can extend or replace functionality of various components of searx. + +Example plugin +============== + +.. code:: python + + name = 'Example plugin' + description = 'This plugin extends the suggestions with the word "example"' + default_on = False # disabled by default + + js_dependencies = tuple() # optional, list of static js files + css_dependencies = tuple() # optional, list of static css files + + + # attach callback to the post search hook + # request: flask request object + # ctx: the whole local context of the post search hook + def post_search(request, ctx): + ctx['search'].suggestions.add('example') + return True + +Plugin entry points +=================== + +Entry points (hooks) define when a plugin runs. Right now only three hooks are +implemented. So feel free to implement a hook if it fits the behaviour of your +plugin. + +Pre search hook +--------------- + +Runs BEFORE the search request. Function to implement: ``pre_search`` + +Post search hook +---------------- + +Runs AFTER the search request. Function to implement: ``post_search`` + +Result hook +----------- + +Runs when a new result is added to the result list. Function to implement: +``on_result`` diff --git a/docs/dev/quickstart.rst b/docs/dev/quickstart.rst new file mode 100644 index 000000000..a4a37a266 --- /dev/null +++ b/docs/dev/quickstart.rst @@ -0,0 +1,110 @@ +.. _devquickstart: + +====================== +Development Quickstart +====================== + +This quickstart guide gets your environment set up with searx. Furthermore, it +gives a short introduction to the ``manage.sh`` script. + +How to setup your development environment +========================================= + +First, clone the source code of searx to the desired folder. In this case the +source is cloned to ``~/myprojects/searx``. Then create and activate the +searx-ve virtualenv and install the required packages using manage.sh. + +.. code:: sh + + cd ~/myprojects + git clone https://github.com/asciimoo/searx.git + cd searx + virtualenv searx-ve + . ./searx-ve/bin/activate + ./manage.sh update_dev_packages + + +How to run tests +================ + +Tests can be run using the ``manage.sh`` script. Following tests and checks are +available: + +- Unit tests +- Selenium tests +- PEP8 validation +- Unit test coverage check + +For example unit tests are run with the command below: + +.. code:: sh + + ./manage.sh unit_tests + +For further test options, please consult the help of the ``manage.sh`` script. + + +How to compile styles and javascript +==================================== + +.. _less: http://lesscss.org/ +.. _NodeJS: https://nodejs.org + +How to build styles +------------------- + +Less_ is required to build the styles of searx. Less_ can be installed using +either NodeJS_ or Apt. + +.. code:: sh + + sudo -H apt-get install nodejs + sudo -H npm install -g less + +OR + +.. code:: sh + + sudo -H apt-get install node-less + +After satisfying the requirements styles can be build using ``manage.sh`` + +.. code:: sh + + ./manage.sh styles + + +How to build the source of the oscar theme +========================================== + +.. _grunt: https://gruntjs.com/ + +Grunt_ must be installed in order to build the javascript sources. It depends on +NodeJS, so first Node has to be installed. + +.. code:: sh + + sudo -H apt-get install nodejs + sudo -H npm install -g grunt-cli + +After installing grunt, the files can be built using the following command: + +.. code:: sh + + ./manage.sh grunt_build + + +Tips for debugging/development +============================== + +Turn on debug logging + Whether you are working on a new engine or trying to eliminate a bug, it is + always a good idea to turn on debug logging. When debug logging is enabled a + stack trace appears, instead of the cryptic ``Internal Server Error`` + message. It can be turned on by setting ``debug: False`` to ``debug: True`` in + :origin:`settings.yml `. + +Run ``./manage.sh tests`` before creating a PR. + Failing build on Travis is common because of PEP8 checks. So a new commit + must be created containing these format fixes. This phase can be skipped if + ``./manage.sh tests`` is run locally before creating a PR. diff --git a/docs/dev/search_api.rst b/docs/dev/search_api.rst new file mode 100644 index 000000000..158cab7c5 --- /dev/null +++ b/docs/dev/search_api.rst @@ -0,0 +1,112 @@ +========== +Search API +========== + +The search supports both ``GET`` and ``POST``. + +Furthermore, two enpoints ``/`` and ``/search`` are available for querying. + + +``GET /`` + +``GET /search`` + +Parameters +========== + +``q`` : required + The search query. This string is passed to external search services. Thus, + searx supports syntax of each search service. For example, ``site:github.com + searx`` is a valid query for Google. However, if simply the query above is + passed to any search engine which does not filter its results based on this + syntax, you might not get the results you wanted. + + See more at :ref:`search-syntax` + +``categories`` : optional + Comma separated list, specifies the active search categories + +``engines``: optional + Comma separated list, specifies the active search engines. + +``lang``: default ``all`` + Code of the language. + +``pageno``: default ``1`` + Search page number. + +``time_range``: optional + [ ``day``, ``month``, ``year`` ] + + Time range of search for engines which support it. See if an engine supports + time range search in the preferences page of an instance. + +``format``: optional + [ ``json``, ``csv``, ``rss`` ] + + Output format of results. + +``results_on_new_tab``: default ``0`` + [ ``0``, ``1`` ] + + Open search results on new tab. + +``image_proxy``: default ``False`` + [ ``True``, ``False`` ] + + Proxy image results through searx. + +``autocomplete``: default *empty* + [ ``google``, ``dbpedia``, ``duckduckgo``, ``startpage``, ``wikipedia`` ] + + Service which completes words as you type. + +``safesearch``: default ``None`` + [ ``0``, ``1``, ``None`` ] + + Filter search results of engines which support safe search. See if an engine + supports safe search in the preferences page of an instance. + +``theme``: default ``oscar`` + [ ``oscar``, ``simple``, ``legacy``, ``pix-art``, ``courgette`` ] + + Theme of instance. + + Please note, available themes depend on an instance. It is possible that an + instance administrator deleted, created or renamed themes on his/her instance. + See the available options in the preferences page of the instance. + +``oscar-style``: default ``logicodev`` + [ ``pointhi``, ``logicodev`` ] + + Style of Oscar theme. It is only parsed if the theme of an instance is + ``oscar``. + + Please note, available styles depend on an instance. It is possible that an + instance administrator deleted, created or renamed styles on his/her + instance. See the available options in the preferences page of the instance. + +``enabled_plugins``: optional + List of enabled plugins. + + :default: ``HTTPS_rewrite``, ``Self_Informations``, + ``Search_on_category_select``, ``Tracker_URL_remover`` + + :values: [ ``DOAI_rewrite``, ``HTTPS_rewrite``, ``Infinite_scroll``, + ``Vim-like_hotkeys``, ``Self_Informations``, ``Tracker_URL_remover``, + ``Search_on_category_select`` ] + +``disabled_plugins``: optional + List of disabled plugins. + + :default: ``DOAI_rewrite``, ``Infinite_scroll``, ``Vim-like_hotkeys`` + :values: ``DOAI_rewrite``, ``HTTPS_rewrite``, ``Infinite_scroll``, + ``Vim-like_hotkeys``, ``Self_Informations``, ``Tracker_URL_remover``, + ``Search_on_category_select`` + +``enabled_engines``: optional : *all* :origin:`engines ` + List of enabled engines. + +``disabled_engines``: optional : *all* :origin:`engines ` + List of disabled engines. + diff --git a/docs/dev/translation.rst b/docs/dev/translation.rst new file mode 100644 index 000000000..86c4c843b --- /dev/null +++ b/docs/dev/translation.rst @@ -0,0 +1,71 @@ +.. _translation: + +=========== +Translation +=========== + +.. _searx@transifex: https://www.transifex.com/asciimoo/searx/ + +Translation currently takes place on `searx@transifex`_ + +Requirements +============ + +* Transifex account +* Installed CLI tool of Transifex + +Init Transifex project +====================== + +After installing ``transifex`` using pip, run the following command to +initialize the project. + +.. code:: sh + + tx init # Transifex instance: https://www.transifex.com/asciimoo/searx/ + + +After ``$HOME/.transifexrc`` is created, get a Transifex API key and insert it +into the configuration file. + +Create a configuration file for ``tx`` named ``$HOME/.tx/config``. + +.. code:: ini + + [main] + host = https://www.transifex.com + [searx.messagespo] + file_filter = searx/translations//LC_MESSAGES/messages.po + source_file = messages.pot + source_lang = en + type = PO + + +Then run ``tx set``: + +.. code:: shell + + tx set --auto-local -r searx.messagespo 'searx/translations//LC_MESSAGES/messages.po' \ + --source-lang en --type PO --source-file messages.pot --execute + + +Update translations +=================== + +To retrieve the latest translations, pull it from Transifex. + +.. code:: sh + + tx pull -a + +Then check the new languages. If strings translated are not enough, delete those +folders, because those should not be compiled. Call the command below to compile +the ``.po`` files. + +.. code:: shell + + pybabel compile -d searx/translations + + +After the compilation is finished commit the ``.po`` and ``.mo`` files and +create a PR. diff --git a/docs/index.rst b/docs/index.rst new file mode 100644 index 000000000..d9503fef6 --- /dev/null +++ b/docs/index.rst @@ -0,0 +1,32 @@ +================ +Welcome to searx +================ + +Search without being tracked. + +.. sidebar:: Features + + - Self hosted + - No user tracking + - No user profiling + - About 70 supported search engines + - Easy integration with any search engine + - Cookies are not used by default + - Secure, encrypted connections (HTTPS/SSL) + - Hosted by organizations, such as *La Quadrature du Net*, which promote + digital rights + +Searx is a free internet metasearch engine which aggregates results from more +than 70 search services. Users are neither tracked nor profiled. Additionally, +searx can be used over Tor for online anonymity. + +Get started with searx by using one of the :wiki:`Searx-instances`. If you +don't trust anyone, you can set up your own, see :ref:`installation`. + +.. toctree:: + :maxdepth: 2 + + user/index + admin/index + dev/index + blog/index diff --git a/docs/static/img/searx_logo_small.png b/docs/static/img/searx_logo_small.png new file mode 100644 index 000000000..083932686 Binary files /dev/null and b/docs/static/img/searx_logo_small.png differ diff --git a/docs/user/index.rst b/docs/user/index.rst new file mode 100644 index 000000000..b13aca216 --- /dev/null +++ b/docs/user/index.rst @@ -0,0 +1,9 @@ +================== +User documentation +================== + +.. toctree:: + :maxdepth: 1 + + search_syntax + own-instance diff --git a/docs/user/own-instance.rst b/docs/user/own-instance.rst new file mode 100644 index 000000000..a2f736562 --- /dev/null +++ b/docs/user/own-instance.rst @@ -0,0 +1,77 @@ +=========================== +Why use a private instance? +=========================== + +"Is it worth to run my own instance?" is a common question among searx users. +Before answering this question, see what options a searx user has. + +Public instances are open to everyone who has access to its URL. Usually, these +are operated by unknown parties (from the users' point of view). Private +instances can be used by a select group of people. It is for example a searx of +group of friends or a company which can be accessed through VPN. Also it can be +single user one which runs on the user's laptop. + +To gain more insight on how these instances work let's dive into how searx +protects its users. + +How does searx protect privacy? +=============================== + +Searx protects the privacy of its users in multiple ways regardless of the type +of the instance (private, public). Removal of private data from search requests +comes in three forms: + + 1. removal of private data from requests going to search services + 2. not forwarding anything from a third party services through search services + (e.g. advertisement) + 3. removal of private data from requests going to the result pages + +Removing private data means not sending cookies to external search engines and +generating a random browser profile for every request. Thus, it does not matter +if a public or private instance handles the request, because it is anonymized in +both cases. IP addresses will be the IP of the instance. But searx can be +configured to use proxy or Tor. `Result proxy +`__ is supported, too. + +Searx does not serve ads or tracking content unlike most search services. So +private data is not forwarded to third parties who might monetize it. Besides +protecting users from search services, both referring page and search query are +hidden from visited result pages. + + +What are the consequences of using public instances? +---------------------------------------------------- + +If someone uses a public instance, he/she has to trust the administrator of that +instance. This means that the user of the public instance does not know whether +his/her requests are logged, aggregated and sent or sold to a third party. + +Also, public instances without proper protection are more vulnerable to abusing +the search service, In this case the external service in exchange returns +CAPTCHAs or bans the IP of the instance. Thus, search requests return less +results. + +I see. What about private instances? +------------------------------------ + +If users run their own instances, everything is in their control: the source +code, logging settings and private data. Unknown instance administrators do not +have to be trusted. + +Furthermore, as the default settings of their instance is editable, there is no +need to use cookies to tailor searx to their needs. So preferences will not be +reset to defaults when clearing browser cookies. As settings are stored on +their computer, it will not be accessible to others as long as their computer is +not compromised. + +Conclusion +========== + +Always use an instance which is operated by people you trust. The privacy +features of searx are available to users no matter what kind of instance they +use. + +If someone is on the go or just wants to try searx for the first time public +instances are the best choices. Additionally, public instance are making a +world a better place, because those who cannot or do not want to run an +instance, have access to a privacy respecting search service. diff --git a/docs/user/search_syntax.rst b/docs/user/search_syntax.rst new file mode 100644 index 000000000..b738c7274 --- /dev/null +++ b/docs/user/search_syntax.rst @@ -0,0 +1,42 @@ + +.. _search-syntax: + +============= +Search syntax +============= + +Searx allows you to modify the default categories, engines and search language +via the search query. + +Prefix ``!`` + to set Category/engine + +Prefix: ``:`` + to set language + +Prefix: ``?`` + to add engines and categories to the currently selected categories + +Abbrevations of the engines and languages are also accepted. Engine/category +modifiers are chainable and inclusive (e.g. with :search:`!it !ddg !wp qwer +` search in IT category **and** duckduckgo +**and** wikipedia for ``qwer``). + +See the :search:`/preferences page ` for the list of engines, +categories and languages. + +Examples +======== + +Search in wikipedia for ``qwer``: + +- :search:`!wp qwer ` or +- :search:`!wikipedia qwer :search:` + +Image search: + +- :search:`!images Cthulhu ` + +Custom language in wikipedia: + +- :search:`:hu !wp hackerspace ` diff --git a/requirements-dev.txt b/requirements-dev.txt index 5e015a88a..0bdf20469 100644 --- a/requirements-dev.txt +++ b/requirements-dev.txt @@ -1,3 +1,6 @@ +pallets-sphinx-themes +Sphinx +sphinx-issues mock==2.0.0 nose2[coverage_plugin] cov-core==1.15.0 diff --git a/utils/makefile.python b/utils/makefile.python index 228eb3f80..4aa9d6b49 100644 --- a/utils/makefile.python +++ b/utils/makefile.python @@ -155,7 +155,7 @@ quiet_cmd_virtualenv = PYENV usage: $ source ./$@/bin/activate if [ ! -d "./$(PY_ENV)" ];then \ $(VIRTUALENV) $(VIRTUALENV_VERBOSE) $(VTENV_OPTS) $2; \ else \ - echo " PYENV using virtualenv from $2"; \ + echo "PYENV using virtualenv from $2"; \ fi # $2 path to lint @@ -263,7 +263,7 @@ pydebug: $(PY_ENV) # install / uninstall python objects into virtualenv (PYENV) pyenv-install: $(PY_ENV) @$(PY_ENV_BIN)/pip $(PIP_VERBOSE) install -e . - @echo " ACTIVATE $(call normpath,$(PY_ENV_ACT)) " + @echo "ACTIVATE $(call normpath,$(PY_ENV_ACT)) " pyenv-uninstall: $(PY_ENV) @$(PY_ENV_BIN)/pip $(PIP_VERBOSE) uninstall --yes . diff --git a/utils/makefile.sphinx b/utils/makefile.sphinx new file mode 100644 index 000000000..5cbc5ebdd --- /dev/null +++ b/utils/makefile.sphinx @@ -0,0 +1,215 @@ +# -*- coding: utf-8; mode: makefile-gmake -*- + +# You can set these variables from the command line. +SPHINXOPTS ?= +SPHINXBUILD ?= $(PY_ENV_BIN)/sphinx-build +SPHINX_CONF ?= conf.py + +DOCS_FOLDER ?= docs +DOCS_BUILD ?= build/docs +DOCS_DIST ?= dist/docs +GH_PAGES ?= gh-pages + +BOOKS_FOLDER ?= docs +BOOKS_DIST ?= dist/books + +ifeq ($(KBUILD_VERBOSE),1) + SPHINX_VERBOSE = "-v" +else + SPHINX_VERBOSE = +endif + +## SPHINXVERS variable +## =================== +## +## .. _requirement-specifiers: https://pip.pypa.io/en/stable/reference/pip_install/#requirement-specifiers +## +## Sphinx version to use, when building documentation. Set this when calling +## build target. The default value is empty (install latest), to select a +## specific version use a requirement-specifiers_. E.g. to build your target +## 'doc' with a select sphinx-doc_ version 1.7.9:: +## +## make SPHINXVERS='==1.7.9' docs +## +## To build with latest 1.7:: +## +## make SPHINXVERS='>=1.7,<1.8' docs +## +SPHINXVERS ?= + +docs-help: + @echo 'makefile.sphinx:' + @echo ' docs-clean - clean intermediate doc objects' + @echo ' $(GH_PAGES) - create & upload github pages' + @echo ' sphinx-pdf - run sphinx latex & pdf targets' + echo '' + @echo ' books/{name}.html : build only the HTML of document {name}' + @echo ' valid values for books/{name}.html are:' + @echo ' $(BOOKS_HTML)' | $(FMT) + @echo ' books/{name}.pdf : build only the PDF of document {name}' + @echo ' valid values for books/{name}.pdf are:' + @echo ' $(BOOKS_PDF) ' | $(FMT) + +# ------------------------------------------------------------------------------ +# requirements +# ------------------------------------------------------------------------------ + +sphinx-doc: $(PY_ENV) + @echo "PYENV installing Sphinx$(SPHINXVERS)" + $(Q)$(PY_ENV_BIN)/pip install $(PIP_VERBOSE) 'Sphinx$(SPHINXVERS)' + +sphinx-live: $(PY_ENV) + @echo "PYENV installing Sphinx$(SPHINXVERS)" + $(Q)$(PY_ENV_BIN)/pip install $(PIP_VERBOSE) 'Sphinx$(SPHINXVERS)' sphinx-autobuild + + +PHONY += msg-texlive texlive + +ifeq ($(shell which xelatex >/dev/null 2>&1; echo $$?), 1) +texlive: msg-TeXLive + $(error The 'xelatex' command was not found) +else +texlive: + @: +endif + +msg-texlive: + $(Q)echo "\n\ +The TeX/PDF output and the *math* extension require TexLive and latexmk:\n\n\ + Make sure you have a updated TeXLive with XeTeX engine installed, grab it\n\ + it from https://www.tug.org/texlive or install it from your package manager.\n\n\ + Install latexmk from your package manager or visit https://ctan.org/pkg/latexmk\n\n\ + Sphinx-doc produce (Xe)LaTeX files which might use additional TeX-packages\n\ + and fonts. To process these LaTeX files, a TexLive installation with the\n\ + additional packages is required. On debian based OS these requirements\n\ + are installed by::\n\n\ + sudo -H apt-get install\n\ + latexmk\n\ + texlive-base texlive-xetex texlive-latex-recommended\n\ + texlive-extra-utils dvipng ttf-dejavu\n" + +# ------------------------------------------------------------------------------ +# commands +# ------------------------------------------------------------------------------ + +# $2 sphinx builder e.g. "html" +# $3 path where configuration file (conf.py) is located +# $4 sourcedir +# $5 dest subfolder e.g. "man" for man pages at $(DOCS_DIST)/man + +quiet_cmd_sphinx = SPHINX $@ --> file://$(abspath $(DOCS_DIST)/$5) + cmd_sphinx = SPHINX_CONF=$(abspath $4/$(SPHINX_CONF))\ + $(SPHINXBUILD) $(SPHINX_VERBOSE) $(SPHINXOPTS)\ + -b $2 -c $3 -d $(DOCS_BUILD)/.doctrees $4 $(DOCS_DIST)/$5 + +quiet_cmd_sphinx_autobuild = SPHINX $@ --> file://$(abspath $(DOCS_DIST)/$5) + cmd_sphinx_autobuild = PATH="$(PY_ENV_BIN):$(PATH)" $(PY_ENV_BIN)/sphinx-autobuild $(SPHINX_VERBOSE) --poll -B --host 0.0.0.0 --port 8080 $(SPHINXOPTS)\ + -b $2 -c $3 -d $(DOCS_BUILD)/.doctrees $4 $(DOCS_DIST)/$5 + +quiet_cmd_sphinx_clean = CLEAN $@ + cmd_sphinx_clean = rm -rf $(DOCS_BUILD) $(DOCS_DIST) $(GH_PAGES)/* $(GH_PAGES)/.buildinfo + +# ------------------------------------------------------------------------------ +# targets +# ------------------------------------------------------------------------------ + +# build PDF of whole documentation in: $(DOCS_DIST)/pdf + +PHONY += sphinx-pdf +sphinx-pdf: sphinx-latex + $(Q)cd $(DOCS_BUILD)/latex/; make all-pdf + $(Q)mkdir -p $(DOCS_DIST)/pdf + $(Q)cp $(DOCS_BUILD)/latex/*.pdf $(DOCS_DIST)/pdf + @echo "SPHINX *.pdf --> file://$(abspath $(DOCS_DIST)/pdf)" + +PHONY += sphinx-latex +sphinx-latex: texlive sphinx-doc + $(SPHINXBUILD) $(SPHINX_VERBOSE) $(SPHINXOPTS)\ + -b latex \ + -c $(DOCS_FOLDER) \ + -d $(DOCS_BUILD)/.doctrees \ + $(DOCS_FOLDER) \ + $(DOCS_BUILD)/latex + +# Sphinx projects, we call them *books* (what is more common). Books are +# folders under $(BOOKS_FOLDER) containing a conf.py file. The HTML output goes +# to folder $(BOOKS_DIST)/ while PDF is placed (BOOKS_DIST)//pdf + +BOOKS=$(patsubst $(BOOKS_FOLDER)/%/conf.py,books/%,$(wildcard $(BOOKS_FOLDER)/*/conf.py)) + +# fine grained targets +BOOKS_HTML = $(patsubst %,%.html,$(BOOKS)) +BOOKS_CLEAN = $(patsubst %,%.clean,$(BOOKS)) +BOOKS_LATEX = $(patsubst %,%.latex,$(BOOKS)) +BOOKS_PDF = $(patsubst %,%.pdf,$(BOOKS)) +BOOKS_LIVE = $(patsubst %,%.live,$(BOOKS)) + +$(BOOKS_DIST): + mkdir -p $(BOOKS_DIST) + +PHONY += $(BOOKS_HTML) +$(BOOKS_HTML): sphinx-doc | $(BOOKS_DIST) + SPHINX_CONF=$(patsubst books/%.html,%,$@)/conf.py \ + $(SPHINXBUILD) $(SPHINX_VERBOSE) $(SPHINXOPTS)\ + -b html \ + -c $(DOCS_FOLDER) \ + -d $(DOCS_BUILD)/books/$(patsubst books/%.html,%,$@)/.doctrees \ + $(patsubst books/%.html,%,$@) \ + $(BOOKS_DIST)/$(patsubst books/%.html,%,$@) + @echo "SPHINX $@ --> file://$(abspath $(BOOKS_DIST)/$(patsubst books/%.html,%,$@))" + +PHONY += $(BOOKS_HTML) +$(BOOKS_LIVE): sphinx-live | $(BOOKS_DIST) + PATH="$(PY_ENV_BIN):$(PATH)" \ + SPHINX_CONF=$(patsubst books/%.live,%,$@)/conf.py \ + $(PY_ENV_BIN)/sphinx-autobuild --poll -B --host 0.0.0.0 --port 8080 $(SPHINX_VERBOSE) $(SPHINXOPTS)\ + -b html \ + -c $(DOCS_FOLDER) \ + -d $(DOCS_BUILD)/books/$(patsubst books/%.live,%,$@)/.doctrees \ + $(patsubst books/%.live,%,$@) \ + $(BOOKS_DIST)/$(patsubst books/%.live,%,$@) + +$(BOOKS_PDF): %.pdf : %.latex + $(Q)cd $(DOCS_BUILD)/latex/$(patsubst books/%.pdf,%,$@); make all-pdf + $(Q)mkdir -p $(BOOKS_DIST)/$(patsubst books/%.pdf,%,$@)/pdf + $(Q)cp -v $(DOCS_BUILD)/latex/$(patsubst books/%.pdf,%,$@)/*.pdf $(BOOKS_DIST)/$(patsubst books/%.pdf,%,$@)/pdf + @echo "SPHINX $@ --> file://$(abspath $(BOOKS_DIST)/$(patsubst books/%.pdf,%,$@))/pdf" + +PHONY += $(BOOKS_LATEX) +$(BOOKS_LATEX): sphinx-doc | $(BOOKS_DIST) + SPHINX_CONF=$(patsubst books/%.latex,%,$@)/conf.py \ + $(SPHINXBUILD) $(SPHINX_VERBOSE) $(SPHINXOPTS)\ + -b latex \ + -c $(DOCS_FOLDER) \ + -d $(DOCS_BUILD)/books/$(patsubst books/%.latex,%,$@)/.doctrees \ + $(patsubst books/%.latex,%,$@) \ + $(DOCS_BUILD)/latex/$(patsubst books/%.latex,%,$@) + @echo "SPHINX $@ --> file://$(abspath $(DOCS_BUILD)/latex/$(patsubst books/%.latex,%,$@))" + +$(BOOKS_CLEAN): + $(Q)rm -rf $(BOOKS_DIST)/$(patsubst books/%.clean,%,$@) \ + $(DOCS_BUILD)/books/$(patsubst books/%.clean,%,$@) \ + $(DOCS_BUILD)/latex/$(patsubst books/%.clean,%,$@) + +# github pages + +PHONY += $(GH_PAGES) +$(GH_PAGES):: + $(MAKE) docs + [ -d "gh-pages/.git" ] || git clone $(GIT_URL) gh-pages + -cd $(GH_PAGES); git checkout gh-pages >/dev/null + -cd $(GH_PAGES); ls -A | grep -v '.git$$' | xargs rm -rf + cp -r $(DOCS_DIST)/* $(GH_PAGES)/ + touch $(GH_PAGES)/.nojekyll + echo "" > $(GH_PAGES)/404.html + cd $(GH_PAGES);\ + git add --all . ;\ + git commit -m "gh-pages: updated" ;\ + git push origin gh-pages + + +PHONY += docs-clean +docs-clean: $(BOOKS_CLEAN) + $(call cmd,sphinx_clean) + +.PHONY: $(PHONY)