hazza/jupyterhub
1
0
Fork 0
mirror of https://github.com/jupyterhub/jupyterhub.git synced 2025-10-17 15:03:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' into busayo-ojo

Browse Source
This commit is contained in:
Min RK
2022-11-24 10:04:08 +01:00
committed by GitHub
parent 51c1ea1f7f d04c0c28c0
commit 8b471624ee
108 changed files with 1416 additions and 1163 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
.flake8
View File

@@ -3,14 +3,9 @@
# E: style errors
# W: style warnings
# C: complexity
# F401: module imported but unused
# F403: import *
# F811: redefinition of unused `name` from line `N`
# D: docstring warnings (unused pydocstyle extension)
# F841: local variable assigned but never used
# E402: module level import not at top of file
# I100: Import statements are in the wrong order
# I101: Imported names are in the wrong order. Should be
ignore = E, C, W, F401, F403, F811, F841, E402, I100, I101, D400
ignore = E, C, W, D, F841
builtins = c, get_config
exclude =
.cache,

12
.github/workflows/release.yml vendored
View File

@@ -108,10 +108,10 @@ jobs:
# https://github.com/docker/build-push-action/tree/v2.4.0#usage
# https://github.com/docker/build-push-action/blob/v2.4.0/docs/advanced/multi-platform.md
- name: Set up QEMU (for docker buildx)
uses: docker/setup-qemu-action@8b122486cedac8393e77aa9734c3528886e4a1a8 # associated tag: v1.0.2
uses: docker/setup-qemu-action@e81a89b1732b9c48d79cd809d8d81d79c4647a18 # associated tag: v1.0.2
- name: Set up Docker Buildx (for multi-arch builds)
uses: docker/setup-buildx-action@dc7b9719a96d48369863986a06765841d7ea23f6 # associated tag: v1.1.2
uses: docker/setup-buildx-action@8c0edbc76e98fa90f69d9a2c020dcb50019dc325
with:
# Allows pushing to registry on localhost:5000
driver-opts: network=host
@@ -149,7 +149,7 @@ jobs:
branchRegex: ^\w[\w-.]*$
- name: Build and push jupyterhub
uses: docker/build-push-action@c84f38281176d4c9cdb1626ffafcd6b3911b5d94
uses: docker/build-push-action@c56af957549030174b10d6867f20e78cfd7debc5
with:
context: .
platforms: linux/amd64,linux/arm64
@@ -170,7 +170,7 @@ jobs:
branchRegex: ^\w[\w-.]*$
- name: Build and push jupyterhub-onbuild
uses: docker/build-push-action@c84f38281176d4c9cdb1626ffafcd6b3911b5d94
uses: docker/build-push-action@c56af957549030174b10d6867f20e78cfd7debc5
with:
build-args: |
BASE_IMAGE=${{ fromJson(steps.jupyterhubtags.outputs.tags)[0] }}
@@ -191,7 +191,7 @@ jobs:
branchRegex: ^\w[\w-.]*$
- name: Build and push jupyterhub-demo
uses: docker/build-push-action@c84f38281176d4c9cdb1626ffafcd6b3911b5d94
uses: docker/build-push-action@c56af957549030174b10d6867f20e78cfd7debc5
with:
build-args: |
BASE_IMAGE=${{ fromJson(steps.onbuildtags.outputs.tags)[0] }}
@@ -215,7 +215,7 @@ jobs:
branchRegex: ^\w[\w-.]*$
- name: Build and push jupyterhub/singleuser
uses: docker/build-push-action@c84f38281176d4c9cdb1626ffafcd6b3911b5d94
uses: docker/build-push-action@c56af957549030174b10d6867f20e78cfd7debc5
with:
build-args: |
JUPYTERHUB_VERSION=${{ github.ref_type == 'tag' && github.ref_name || format('git:{0}', github.sha) }}

2
.github/workflows/test-docs.yml vendored
View File

@@ -55,7 +55,7 @@ jobs:
- name: Install requirements
run: |
pip install -r docs/requirements.txt pytest -e .
pip install -r docs/requirements.txt pytest
- name: pytest docs/
run: |

38
.github/workflows/test.yml vendored
View File

@@ -83,12 +83,13 @@ jobs:
db: mysql
- python: "3.10"
db: postgres
- python: "3.10"
- python: "3.11"
subdomain: subdomain
- python: "3.10"
- python: "3.11"
ssl: ssl
- python: "3.11.0-rc.1"
- python: "3.10"
- python: "3.11"
selenium: selenium
- python: "3.11"
main_dependencies: main_dependencies
steps:
@@ -139,16 +140,7 @@ jobs:
- name: Install Python dependencies
run: |
pip install --upgrade pip
if [[ "${{ matrix.python }}" == "3.11"* ]]; then
# greenlet is not actually required,
# but is an install dependency of sqlalchemy.
# It does not yet install on 3.11
# see: see https://github.com/gevent/gevent/issues/1867
pip install ./ci/mock-greenlet
fi
pip install --upgrade . -r dev-requirements.txt
pip install ".[test]"
if [ "${{ matrix.oldest_dependencies }}" != "" ]; then
# take any dependencies in requirements.txt such as tornado>=5.0
@@ -214,13 +206,25 @@ jobs:
DB=postgres bash ci/docker-db.sh
DB=postgres bash ci/init-db.sh
fi
- name: Setup Firefox
if: matrix.selenium
uses: browser-actions/setup-firefox@latest
with:
firefox-version: latest
- name: Setup Geckodriver
if: matrix.selenium
uses: browser-actions/setup-geckodriver@latest
- name: Configure selenium tests
if: matrix.selenium
run: echo "PYTEST_ADDOPTS=$PYTEST_ADDOPTS -m selenium" >> "${GITHUB_ENV}"
- name: Run pytest
run: |
pytest --maxfail=2 --cov=jupyterhub jupyterhub/tests
- name: Submit codecov report
run: |
codecov
- uses: codecov/codecov-action@v3
docker-build:
runs-on: ubuntu-20.04

15
.pre-commit-config.yaml
View File

@@ -11,12 +11,21 @@
repos:
# Autoformat: Python code, syntax patterns are modernized
- repo: https://github.com/asottile/pyupgrade
rev: v2.37.3
rev: v3.2.2
hooks:
- id: pyupgrade
args:
- --py36-plus
# Autoformat: Python code
- repo: https://github.com/PyCQA/autoflake
rev: v1.7.7
hooks:
- id: autoflake
# args ref: https://github.com/PyCQA/autoflake#advanced-usage
args:
- --in-place
# Autoformat: Python code
- repo: https://github.com/pycqa/isort
rev: 5.10.1
@@ -25,13 +34,13 @@ repos:
# Autoformat: Python code
- repo: https://github.com/psf/black
rev: 22.6.0
rev: 22.10.0
hooks:
- id: black
# Autoformat: markdown, yaml, javascript (see the file .prettierignore)
- repo: https://github.com/pre-commit/mirrors-prettier
rev: v2.7.1
rev: v3.0.0-alpha.4
hooks:
- id: prettier

11
.readthedocs.yaml
View File

@@ -1,3 +1,7 @@
# Configuration on how ReadTheDocs (RTD) builds our documentation
# ref: https://readthedocs.org/projects/jupyterhub/
# ref: https://docs.readthedocs.io/en/stable/config-file/v2.html
#
version: 2
sphinx:
@@ -11,10 +15,11 @@ build:
python:
install:
- method: pip
path: .
- requirements: docs/requirements.txt
formats:
# Adding htmlzip enables a Downloads section in the rendered website's RTD
# menu where the html build can be downloaded. This doesn't require any
# additional configuration in docs/source/conf.py.
#
- htmlzip
- epub

2
README.md
View File

@@ -190,7 +190,7 @@ this a good choice for **testing JupyterHub on your desktop or laptop**.
If you want to run docker on a computer that has a public IP then you should
(as in MUST) **secure it with ssl** by adding ssl options to your docker
configuration or by using a ssl enabled proxy.
configuration or by using an ssl enabled proxy.
[Mounting volumes](https://docs.docker.com/engine/admin/volumes/volumes/) will
allow you to **store data outside the docker image (host system) so it will be persistent**, even when you start

49
RELEASE.md
View File

@@ -1,39 +1,42 @@
# How to make a release
`jupyterhub` is a package [available on
PyPI](https://pypi.org/project/jupyterhub/) and
[conda-forge](https://conda-forge.org/).
These are instructions on how to make a release on PyPI.
The PyPI release is done automatically by CI when a tag is pushed.
`jupyterhub` is a package available on [PyPI][] and [conda-forge][].
These are instructions on how to make a release.
For you to follow along according to these instructions, you need:
## Pre-requisites
- To have push rights to the [jupyterhub GitHub
repository](https://github.com/jupyterhub/jupyterhub).
- Push rights to [jupyterhub/jupyterhub][]
- Push rights to [conda-forge/jupyterhub-feedstock][]
## Steps to make a release
1. Create a PR updating `docs/source/changelog.md` with [github-activity][] and
continue only when its merged.
```shell
pip install github-activity
github-activity --heading-level=3 jupyterhub/jupyterhub
```
1. Checkout main and make sure it is up to date.
```shell
ORIGIN=${ORIGIN:-origin} # set to the canonical remote, e.g. 'upstream' if 'origin' is not the official repo
git checkout main
git fetch $ORIGIN main
git reset --hard $ORIGIN/main
git fetch origin main
git reset --hard origin/main
```
1. Make sure `docs/source/changelog.md` is up-to-date.
[github-activity][] can help with this.
1. Update the version with `tbump`.
You can see what will happen without making any changes with `tbump --dry-run ${VERSION}`
1. Update the version, make commits, and push a git tag with `tbump`.
```shell
pip install tbump
tbump --dry-run ${VERSION}
tbump ${VERSION}
```
This will tag and publish a release,
which will be finished on CI.
Following this, the [CI system][] will build and publish a release.
1. Reset the version back to dev, e.g. `2.1.0.dev` after releasing `2.0.0`
@@ -42,9 +45,11 @@ For you to follow along according to these instructions, you need:
```
1. Following the release to PyPI, an automated PR should arrive to
[conda-forge/jupyterhub-feedstock][],
check for the tests to succeed on this PR and then merge it to successfully
update the package for `conda` on the conda-forge channel.
[conda-forge/jupyterhub-feedstock][] with instructions.
[github-activity]: https://github.com/choldgraf/github-activity
[pypi]: https://pypi.org/project/jupyterhub/
[conda-forge]: https://anaconda.org/conda-forge/jupyterhub
[jupyterhub/jupyterhub]: https://github.com/jupyterhub/jupyterhub
[conda-forge/jupyterhub-feedstock]: https://github.com/conda-forge/jupyterhub-feedstock
[github-activity]: https://github.com/executablebooks/github-activity
[ci system]: https://github.com/jupyterhub/jupyterhub/actions/workflows/release.yml

1
ci/check_sdist.py
View File

@@ -3,7 +3,6 @@
import sys
import tarfile
from tarfile import TarFile
expected_files = [
"docs/requirements.txt",

3
ci/mock-greenlet/greenlet.py
View File

@@ -1,3 +0,0 @@
__version__ = "22.0.0.dev0"
raise ImportError("Don't actually have greenlet")

13
ci/mock-greenlet/pyproject.toml
View File

@@ -1,13 +0,0 @@
[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"
[project]
name = "greenlet"
description = 'Mock greenlet to allow install on 3.11'
requires-python = ">=3.7"
dynamic = ["version"]
[tool.hatch.version]
path = "greenlet.py"

25
dev-requirements.txt
View File

@@ -1,25 +0,0 @@
-r requirements.txt
# temporary pin of attrs for jsonschema 0.3.0a1
# seems to be a pip bug
attrs>=17.4.0
beautifulsoup4
codecov
coverage
cryptography
html5lib # needed for beautifulsoup
jupyterlab >=3
mock
# nbclassic provides the '/tree/' handler, which we use in tests
# it is a transitive dependency via jupyterlab,
# but depend on it directly
nbclassic
pre-commit
pytest>=3.3
pytest-asyncio>=0.17
pytest-cov
requests-mock
tbump
# blacklist urllib3 releases affected by https://github.com/urllib3/urllib3/issues/1683
# I *think* this should only affect testing, not production
urllib3!=1.25.4,!=1.25.5
virtualenv

3
docs/Makefile
View File

@@ -63,6 +63,9 @@ scopes: source/rbac/scope-table.md
source/rbac/scope-table.md: source/rbac/generate-scope-table.py
python3 source/rbac/generate-scope-table.py
# If the pre-requisites for the html target is updated, also update the Read The
# Docs section in docs/source/conf.py.
#
html: metrics scopes
$(SPHINXBUILD) -b html $(ALLSPHINXOPTS) $(BUILDDIR)/html
@echo

1
docs/generate-metrics.py
View File

@@ -1,5 +1,4 @@
import os
from os.path import join
from pytablewriter import RstSimpleTableWriter
from pytablewriter.style import Style

15
docs/requirements.txt
View File

@@ -1,12 +1,21 @@
-r ../requirements.txt
# We install the jupyterhub package to help autodoc-traits inspect it and
# generate documentation.
#
# FIXME: If there is a way for this requirements.txt file to pass a flag that
# the build system can intercept to not build the javascript artifacts,
# then do so so. That would mean that installing the documentation can
# avoid needing node/npm installed.
#
--editable .
alabaster_jupyterhub
autodoc-traits
myst-parser
pre-commit
pydata-sphinx-theme
pytablewriter>=0.56
ruamel.yaml
sphinx>=1.7
sphinx>=4
sphinx-copybutton
sphinx-jsonschema
sphinxext-opengraph
sphinxext-rediraffe

11
docs/source/admin/log-messages.md
View File

@@ -8,19 +8,20 @@ log messages, what they mean and what are the most common causes that generated
### Example
Your log might display lines that seem cryptic
Your logs might be littered with lines that look scary
```
[W 2022-03-10 17:25:19.774 JupyterHub base:1349] Failing suspected API request to not-running server: /hub/user/<user-name>/api/metrics/v1
```
### Most likely cause
### Cause
The possible reason may be that the user's server has stopped running
but they still have a browser tab open. For example, you might have 3 tabs open and you shut
This likely means that the user's server has stopped running but they
still have a browser tab open. For example, you might have 3 tabs open and you shut
the server down via one.
The other possible reason could be that you closed your laptop and the server was culled for inactivity, then reopened the laptop!
Another possible reason could be that you closed your laptop and the server was culled for inactivity, then reopened the laptop!
However, the client-side code (JupyterLab, Classic Notebook, etc) doesn't interpret the shut-down server and continues to make some API requests.
JupyterHub's architecture means that the proxy routes all requests that
don't go to a running user server to the hub process itself. The hub
process then explicitly returns a failure response, so the client knows

63
docs/source/admin/upgrading.rst
View File

@@ -9,30 +9,31 @@ If you are using :ref:`a JupyterHub distribution <index/distributions>`, you
should consult the distribution's documentation on how to upgrade. This documentation is
for those who have set up their JupyterHub without using a distribution.
It is long because is pretty detailed! Most likely, upgrading
This documentation is lengthy because it is quite detailed. Most likely, upgrading
JupyterHub is painless, quick and with minimal user interruption.
The steps are discussed in detail, so if you get stuck at any step you can always refer to this guide.
Read the Changelog
==================
The `changelog <../changelog.html>`_ contains information on what has
changed with the new JupyterHub release, and any deprecation warnings.
The `changelog <../changelog.md>`_ contains information on what has
changed with the new JupyterHub release and any deprecation warnings.
Read these notes to familiarize yourself with the coming changes. There
might be new releases of authenticators & spawners you are using, so
might be new releases of the authenticators & spawners you use, so
read the changelogs for those too!
Notify your users
=================
If you are using the default configuration where ``configurable-http-proxy``
If you use the default configuration where ``configurable-http-proxy``
is managed by JupyterHub, your users will see service disruption during
the upgrade process. You should notify them, and pick a time to do the
upgrade where they will be least disrupted.
If you are using a different proxy, or running ``configurable-http-proxy``
If you use a different proxy or run ``configurable-http-proxy``
independent of JupyterHub, your users will be able to continue using notebook
servers they had already launched, but will not be able to launch new servers
nor sign in.
servers they had already launched, but will not be able to launch new servers or sign in.
Backup database & config
@@ -40,37 +41,37 @@ Backup database & config
Before doing an upgrade, it is critical to back up:
#. Your JupyterHub database (sqlite by default, or MySQL / Postgres
if you used those). If you are using sqlite (the default), you
should backup the ``jupyterhub.sqlite`` file.
#. Your JupyterHub database (SQLite by default, or MySQL / Postgres if you used those).
If you use SQLite (the default), you should backup the ``jupyterhub.sqlite`` file.
#. Your ``jupyterhub_config.py`` file.
#. Your user's home directories. This is unlikely to be affected directly by
a JupyterHub upgrade, but we recommend a backup since user data is very
critical.
#. Your users' home directories. This is unlikely to be affected directly by
a JupyterHub upgrade, but we recommend a backup since user data is critical.
Shutdown JupyterHub
===================
Shut down JupyterHub
====================
Shutdown the JupyterHub process. This would vary depending on how you
have set up JupyterHub to run. Most likely, it is using a process
Shut down the JupyterHub process. This would vary depending on how you
have set up JupyterHub to run. It is most likely using a process
supervisor of some sort (``systemd`` or ``supervisord`` or even ``docker``).
Use the supervisor specific command to stop the JupyterHub process.
Use the supervisor-specific command to stop the JupyterHub process.
Upgrade JupyterHub packages
===========================
There are two environments where the ``jupyterhub`` package is installed:
#. The *hub environment*, which is where the JupyterHub server process
#. The *hub environment*: where the JupyterHub server process
runs. This is started with the ``jupyterhub`` command, and is what
people generally think of as JupyterHub.
#. The *notebook user environments*. This is where the user notebook
#. The *notebook user environments*: where the user notebook
servers are launched from, and is probably custom to your own
installation. This could be just one environment (different from the
hub environment) that is shared by all users, one environment
per user, or same environment as the hub environment. The hub
per user, or the same environment as the hub environment. The hub
launched the ``jupyterhub-singleuser`` command in this environment,
which in turn starts the notebook server.
@@ -91,10 +92,8 @@ with:
conda install -c conda-forge jupyterhub==<version>
Where ``<version>`` is the version of JupyterHub you are upgrading to.
You should also check for new releases of the authenticator & spawner you
are using. You might wish to upgrade those packages too along with JupyterHub,
are using. You might wish to upgrade those packages, too, along with JupyterHub
or upgrade them separately.
Upgrade JupyterHub database
@@ -108,7 +107,7 @@ database. From the hub environment, in the same directory as your
jupyterhub upgrade-db
This should find the location of your database, and run necessary upgrades
This should find the location of your database, and run the necessary upgrades
for it.
SQLite database disadvantages
@@ -117,11 +116,11 @@ SQLite database disadvantages
SQLite has some disadvantages when it comes to upgrading JupyterHub. These
are:
- ``upgrade-db`` may not work, and you may need delete your database
- ``upgrade-db`` may not work, and you may need to delete your database
and start with a fresh one.
- ``downgrade-db`` **will not** work if you want to rollback to an
earlier version, so backup the ``jupyterhub.sqlite`` file before
upgrading
upgrading.
What happens if I delete my database?
-------------------------------------
@@ -136,10 +135,10 @@ resides only in the Hub database includes:
If the following conditions are true, you should be fine clearing the
Hub database and starting over:
- users specified in config file, or login using an external
- users specified in the config file, or login using an external
authentication provider (Google, GitHub, LDAP, etc)
- user servers are stopped during upgrade
- don't mind causing users to login again after upgrade
- user servers are stopped during the upgrade
- don't mind causing users to log in again after the upgrade
Start JupyterHub
================
@@ -147,7 +146,7 @@ Start JupyterHub
Once the database upgrade is completed, start the ``jupyterhub``
process again.
#. Log-in and start the server to make sure things work as
#. Log in and start the server to make sure things work as
expected.
#. Check the logs for any errors or deprecation warnings. You
might have to update your ``jupyterhub_config.py`` file to

308
docs/source/conf.py
View File

@@ -1,72 +1,70 @@
# Configuration file for Sphinx to build our documentation to HTML.
#
# Configuration reference: https://www.sphinx-doc.org/en/master/usage/configuration.html
#
import contextlib
import datetime
import io
import os
import sys
# Set paths
sys.path.insert(0, os.path.abspath('.'))
# -- General configuration ------------------------------------------------
# Minimal Sphinx version
needs_sphinx = '1.4'
# Sphinx extension modules
extensions = [
'sphinx.ext.autodoc',
'sphinx.ext.intersphinx',
'sphinx.ext.napoleon',
'autodoc_traits',
'sphinx_copybutton',
'sphinx-jsonschema',
'myst_parser',
]
myst_heading_anchors = 2
myst_enable_extensions = [
'colon_fence',
'deflist',
]
# The master toctree document.
master_doc = 'index'
# General information about the project.
project = 'JupyterHub'
copyright = '2016, Project Jupyter team'
author = 'Project Jupyter team'
# Autopopulate version
from os.path import dirname
docs = dirname(dirname(__file__))
root = dirname(docs)
sys.path.insert(0, root)
import jupyterhub
# The short X.Y version.
version = '%i.%i' % jupyterhub.version_info[:2]
# The full version, including alpha/beta/rc tags.
release = jupyterhub.__version__
language = "en"
exclude_patterns = []
pygments_style = 'sphinx'
todo_include_todos = False
# Set the default role so we can use `foo` instead of ``foo``
default_role = 'literal'
from contextlib import redirect_stdout
from io import StringIO
import subprocess
from docutils import nodes
from sphinx.directives.other import SphinxDirective
# -- Config -------------------------------------------------------------
import jupyterhub
from jupyterhub.app import JupyterHub
# create a temp instance of JupyterHub just to get the output of the generate-config
# and help --all commands.
# -- Project information -----------------------------------------------------
# ref: https://www.sphinx-doc.org/en/master/usage/configuration.html#project-information
#
project = "JupyterHub"
author = "Project Jupyter Contributors"
copyright = f"{datetime.date.today().year}, {author}"
version = "%i.%i" % jupyterhub.version_info[:2]
release = jupyterhub.__version__
# -- General Sphinx configuration --------------------------------------------
# ref: https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration
#
extensions = [
"sphinx.ext.autodoc",
"sphinx.ext.intersphinx",
"sphinx.ext.napoleon",
"autodoc_traits",
"sphinx_copybutton",
"sphinx-jsonschema",
"sphinxext.opengraph",
"sphinxext.rediraffe",
"myst_parser",
]
root_doc = "index"
source_suffix = [".md", ".rst"]
# default_role let's use use `foo` instead of ``foo`` in rST
default_role = "literal"
# -- MyST configuration ------------------------------------------------------
# ref: https://myst-parser.readthedocs.io/en/latest/configuration.html
#
myst_heading_anchors = 2
myst_enable_extensions = [
"colon_fence",
"deflist",
]
# -- Custom directives to generate documentation -----------------------------
# ref: https://myst-parser.readthedocs.io/en/latest/syntax/roles-and-directives.html
#
# We define custom directives to help us generate documentation using Python on
# demand when referenced from our documentation files.
#
# Create a temp instance of JupyterHub for use by two separate directive classes
# to get the output from using the "--generate-config" and "--help-all" CLI
# flags respectively.
#
jupyterhub_app = JupyterHub()
@@ -83,8 +81,8 @@ class ConfigDirective(SphinxDirective):
# The generated configuration file for this version
generated_config = jupyterhub_app.generate_config_file()
# post-process output
home_dir = os.environ['HOME']
generated_config = generated_config.replace(home_dir, '$HOME', 1)
home_dir = os.environ["HOME"]
generated_config = generated_config.replace(home_dir, "$HOME", 1)
par = nodes.literal_block(text=generated_config)
return [par]
@@ -100,39 +98,55 @@ class HelpAllDirective(SphinxDirective):
def run(self):
# The output of the help command for this version
buffer = StringIO()
with redirect_stdout(buffer):
jupyterhub_app.print_help('--help-all')
buffer = io.StringIO()
with contextlib.redirect_stdout(buffer):
jupyterhub_app.print_help("--help-all")
all_help = buffer.getvalue()
# post-process output
home_dir = os.environ['HOME']
all_help = all_help.replace(home_dir, '$HOME', 1)
home_dir = os.environ["HOME"]
all_help = all_help.replace(home_dir, "$HOME", 1)
par = nodes.literal_block(text=all_help)
return [par]
def setup(app):
app.add_css_file('custom.css')
app.add_directive('jupyterhub-generate-config', ConfigDirective)
app.add_directive('jupyterhub-help-all', HelpAllDirective)
app.add_css_file("custom.css")
app.add_directive("jupyterhub-generate-config", ConfigDirective)
app.add_directive("jupyterhub-help-all", HelpAllDirective)
source_suffix = ['.rst', '.md']
# source_encoding = 'utf-8-sig'
# -- Read The Docs -----------------------------------------------------------
#
# Since RTD runs sphinx-build directly without running "make html", we run the
# pre-requisite steps for "make html" from here if needed.
#
if os.environ.get("READTHEDOCS"):
docs = os.path.dirname(os.path.dirname(__file__))
subprocess.check_call(["make", "metrics", "scopes"], cwd=docs)
# -- Options for HTML output ----------------------------------------------
# The theme to use for HTML and HTML Help pages.
html_theme = 'pydata_sphinx_theme'
# -- Spell checking ----------------------------------------------------------
# ref: https://sphinxcontrib-spelling.readthedocs.io/en/latest/customize.html#configuration-options
#
# The "sphinxcontrib.spelling" extension is optionally enabled if its available.
#
try:
import sphinxcontrib.spelling # noqa
except ImportError:
pass
else:
extensions.append("sphinxcontrib.spelling")
spelling_word_list_filename = "spelling_wordlist.txt"
html_logo = '_static/images/logo/logo.png'
html_favicon = '_static/images/logo/favicon.ico'
# Paths that contain custom static files (such as style sheets)
html_static_path = ['_static']
htmlhelp_basename = 'JupyterHubdoc'
# -- Options for HTML output -------------------------------------------------
# ref: https://www.sphinx-doc.org/en/master/usage/configuration.html#options-for-html-output
#
html_logo = "_static/images/logo/logo.png"
html_favicon = "_static/images/logo/favicon.ico"
html_static_path = ["_static"]
html_theme = "pydata_sphinx_theme"
html_theme_options = {
"icon_links": [
{
@@ -149,111 +163,53 @@ html_theme_options = {
"use_edit_page_button": True,
"navbar_align": "left",
}
html_context = {
"github_user": "jupyterhub",
"github_repo": "jupyterhub",
"github_version": "main",
"doc_path": "docs",
"doc_path": "docs/source",
}
# -- Options for LaTeX output ---------------------------------------------
latex_elements = {
# 'papersize': 'letterpaper',
# 'pointsize': '10pt',
# 'preamble': '',
# 'figure_align': 'htbp',
}
# Grouping the document tree into LaTeX files. List of tuples
# (source start file, target name, title,
# author, documentclass [howto, manual, or own class]).
latex_documents = [
(
master_doc,
'JupyterHub.tex',
'JupyterHub Documentation',
'Project Jupyter team',
'manual',
)
# -- Options for linkcheck builder -------------------------------------------
# ref: https://www.sphinx-doc.org/en/master/usage/configuration.html#options-for-the-linkcheck-builder
#
linkcheck_ignore = [
r"(.*)github\.com(.*)#", # javascript based anchors
r"(.*)/#%21(.*)/(.*)", # /#!forum/jupyter - encoded anchor edge case
r"https://github.com/[^/]*$", # too many github usernames / searches in changelog
"https://github.com/jupyterhub/jupyterhub/pull/", # too many PRs in changelog
"https://github.com/jupyterhub/jupyterhub/compare/", # too many comparisons in changelog
]
linkcheck_anchors_ignore = [
"/#!",
"/#%21",
]
# latex_logo = None
# latex_use_parts = False
# latex_show_pagerefs = False
# latex_show_urls = False
# latex_appendices = []
# latex_domain_indices = True
# -- manual page output -------------------------------------------------
# One entry per manual page. List of tuples
# (source start file, name, description, authors, manual section).
man_pages = [(master_doc, 'jupyterhub', 'JupyterHub Documentation', [author], 1)]
# man_show_urls = False
# -- Texinfo output -----------------------------------------------------
# Grouping the document tree into Texinfo files. List of tuples
# (source start file, target name, title, author,
# dir menu entry, description, category)
texinfo_documents = [
(
master_doc,
'JupyterHub',
'JupyterHub Documentation',
author,
'JupyterHub',
'One line description of project.',
'Miscellaneous',
)
]
# texinfo_appendices = []
# texinfo_domain_indices = True
# texinfo_show_urls = 'footnote'
# texinfo_no_detailmenu = False
# -- Epub output --------------------------------------------------------
# Bibliographic Dublin Core info.
epub_title = project
epub_author = author
epub_publisher = author
epub_copyright = copyright
# A list of files that should not be packed into the epub file.
epub_exclude_files = ['search.html']
# -- Intersphinx ----------------------------------------------------------
# -- Intersphinx -------------------------------------------------------------
# ref: https://www.sphinx-doc.org/en/master/usage/extensions/intersphinx.html#configuration
#
intersphinx_mapping = {
'python': ('https://docs.python.org/3/', None),
'tornado': ('https://www.tornadoweb.org/en/stable/', None),
"python": ("https://docs.python.org/3/", None),
"tornado": ("https://www.tornadoweb.org/en/stable/", None),
}
# -- Options for the opengraph extension -------------------------------------
# ref: https://github.com/wpilibsuite/sphinxext-opengraph#options
#
# ogp_site_url is set automatically by RTD
ogp_image = "_static/logo.png"
ogp_use_first_image = True
# -- Read The Docs --------------------------------------------------------
on_rtd = os.environ.get('READTHEDOCS', None) == 'True'
if on_rtd:
# readthedocs.org uses their theme by default, so no need to specify it
# build both metrics and rest-api, since RTD doesn't run make
from subprocess import check_call as sh
sh(['make', 'metrics', 'scopes'], cwd=docs)
# -- Spell checking -------------------------------------------------------
try:
import sphinxcontrib.spelling
except ImportError:
pass
else:
extensions.append("sphinxcontrib.spelling")
spelling_word_list_filename = 'spelling_wordlist.txt'
# -- Options for the rediraffe extension -------------------------------------
# ref: https://github.com/wpilibsuite/sphinxext-rediraffe#readme
#
# This extensions help us relocated content without breaking links. If a
# document is moved internally, a redirect like should be configured below to
# help us not break links.
#
rediraffe_branch = "main"
rediraffe_redirects = {
# "old-file": "new-folder/new-file-name",
}

27
docs/source/contributing/community.md Normal file
View File

@@ -0,0 +1,27 @@
# Community communication channels
We use different channels of communication for different purposes. Whichever one you use will depend on what kind of communication you want to engage in.
## Discourse (recommended)
We use [Discourse](https://discourse.jupyter.org) for online discussions and support questions.
You can ask questions here if you are a first-time contributor to the JupyterHub project.
Everyone in the Jupyter community is welcome to bring ideas and questions there.
We recommend that you first use our Discourse as all past and current discussions on it are archived and searchable. Thus, all discussions remain useful and accessible to the whole community.
## Gitter
We use [our Gitter channel](https://gitter.im/jupyterhub/jupyterhub) for online, real-time text chat; a place for more ephemeral discussions. When you're not on Discourse, you can stop here to have other discussions on the fly.
## Github Issues
[Github issues](https://docs.github.com/en/issues/tracking-your-work-with-issues/about-issues) are used for most long-form project discussions, bug reports and feature requests.
- Issues related to a specific authenticator or spawner should be opened in the appropriate repository for the authenticator or spawner.
- If you are using a specific JupyterHub distribution (such as [Zero to JupyterHub on Kubernetes](http://github.com/jupyterhub/zero-to-jupyterhub-k8s) or [The Littlest JupyterHub](http://github.com/jupyterhub/the-littlest-jupyterhub/)), you should open issues directly in their repository.
- If you cannot find a repository to open your issue in, do not worry! Open the issue in the [main JupyterHub repository](https://github.com/jupyterhub/jupyterhub/) and our community will help you figure it out.
```{note}
Our community is distributed across the world in various timezones, so please be patient if you do not get a response immediately!
```

30
docs/source/contributing/community.rst
View File

@@ -1,30 +0,0 @@
.. _contributing/community:
================================
Community communication channels
================================
We use `Discourse <https://discourse.jupyter.org>` for online discussion.
Everyone in the Jupyter community is welcome to bring ideas and questions there.
In addition, we use `Gitter <https://gitter.im>`_ for online, real-time text chat,
a place for more ephemeral discussions.
The primary Gitter channel for JupyterHub is `jupyterhub/jupyterhub <https://gitter.im/jupyterhub/jupyterhub>`_.
Gitter isn't archived or searchable, so we recommend going to discourse first
to make sure that discussions are most useful and accessible to the community.
Remember that our community is distributed across the world in various
timezones, so be patient if you do not get an answer immediately!
GitHub issues are used for most long-form project discussions, bug reports
and feature requests. Issues related to a specific authenticator or
spawner should be directed to the appropriate repository for the
authenticator or spawner. If you are using a specific JupyterHub
distribution (such as `Zero to JupyterHub on Kubernetes <http://github.com/jupyterhub/zero-to-jupyterhub-k8s>`_
or `The Littlest JupyterHub <http://github.com/jupyterhub/the-littlest-jupyterhub/>`_),
you should open issues directly in their repository. If you can not
find a repository to open your issue in, do not worry! Create it in the `main
JupyterHub repository <https://github.com/jupyterhub/jupyterhub/>`_ and our
community will help you figure it out.
A `mailing list <https://groups.google.com/forum/#!forum/jupyter>`_ for all
of Project Jupyter exists, along with one for `teaching with Jupyter
<https://groups.google.com/forum/#!forum/jupyter-education>`_.

17
docs/source/contributing/docs.rst
View File

@@ -5,7 +5,7 @@ Contributing Documentation
==========================
Documentation is often more important than code. This page helps
you get set up on how to contribute documentation to JupyterHub.
you get set up on how to contribute to JupyterHub's documentation.
Building documentation locally
==============================
@@ -18,7 +18,7 @@ stored under the ``docs/source`` directory) and converts it into various
formats for people to read. To make sure the documentation you write or
change renders correctly, it is good practice to test it locally.
#. Make sure you have successfuly completed :ref:`contributing/setup`.
#. Make sure you have successfully completed :ref:`contributing/setup`.
#. Install the packages required to build the docs.
@@ -27,7 +27,7 @@ change renders correctly, it is good practice to test it locally.
python3 -m pip install -r docs/requirements.txt
#. Build the html version of the docs. This is the most commonly used
output format, so verifying it renders as you should is usually good
output format, so verifying it renders correctly is usually good
enough.
.. code-block:: bash
@@ -44,9 +44,14 @@ change renders correctly, it is good practice to test it locally.
.. tip::
On Windows, you can open a file from the terminal with ``start <path-to-file>``.
On macOS, you can do the same with ``open <path-to-file>``.
On Linux, you can do the same with ``xdg-open <path-to-file>``.
**On Windows**, you can open a file from the terminal with ``start <path-to-file>``.
**On macOS**, you can do the same with ``open <path-to-file>``.
**On Linux**, you can do the same with ``xdg-open <path-to-file>``.
After opening index.html in your browser you can just refresh the page whenever
you rebuild the docs via ``make html``
.. _contributing/docs/conventions:

2
docs/source/contributing/roadmap.md
View File

@@ -4,7 +4,7 @@ This roadmap collects "next steps" for JupyterHub. It is about creating a
shared understanding of the project's vision and direction amongst
the community of users, contributors, and maintainers.
The goal is to communicate priorities and upcoming release plans.
It is not a aimed at limiting contributions to what is listed here.
It is not aimed at limiting contributions to what is listed here.
## Using the roadmap

28
docs/source/contributing/setup.rst
View File

@@ -29,6 +29,9 @@ Install nodejs
If you have not installed NodeJS before, we recommend installing it in the ``miniconda`` environment you set up for Python.
You can do so with ``conda install nodejs``.
Many in the Jupyter community use [``nvm``](https://github.com/nvm-sh/nvm) to
managing node dependencies.
Install git
-----------
@@ -77,9 +80,9 @@ When developing JupyterHub, you would need to make changes and be able to instan
npm install -g configurable-http-proxy yarn
If you get an error that says ``Error: EACCES: permission denied``,
you might need to prefix the command with ``sudo``. If you do not
have access to sudo, you may instead run the following commands:
If you get an error that says ``Error: EACCES: permission denied``, you might need to prefix the command with ``sudo``.
``sudo`` may be required to perform a system-wide install.
If you do not have access to sudo, you may instead run the following commands:
.. code:: bash
@@ -94,12 +97,13 @@ When developing JupyterHub, you would need to make changes and be able to instan
conda install configurable-http-proxy yarn
4. Install the python packages required for JupyterHub development.
4. Install an editable version of JupyterHub and its requirements for
development and testing. This lets you edit JupyterHub code in a text editor
& restart the JupyterHub process to see your code changes immediately.
.. code:: bash
python3 -m pip install -r dev-requirements.txt
python3 -m pip install -r requirements.txt
python3 -m pip install --editable ".[test]"
5. Set up a database.
@@ -108,21 +112,13 @@ When developing JupyterHub, you would need to make changes and be able to instan
available via `Python <https://docs.python.org/3.5/library/sqlite3.html>`__.
See :doc:`/reference/database` for details on other supported databases.
6. Install the development version of JupyterHub. This lets you edit
JupyterHub code in a text editor & restart the JupyterHub process to
see your code changes immediately.
.. code:: bash
python3 -m pip install --editable .
7. You are now ready to start JupyterHub!
6. You are now ready to start JupyterHub!
.. code:: bash
jupyterhub
8. You can access JupyterHub from your browser at
7. You can access JupyterHub from your browser at
``http://localhost:8000`` now.
Happy developing!

49
docs/source/contributing/tests.rst
View File

@@ -4,19 +4,18 @@
Testing JupyterHub and linting code
===================================
Unit test help validate that JupyterHub works the way we think it does,
Unit testing helps to validate that JupyterHub works the way we think it does,
and continues to do so when changes occur. They also help communicate
precisely what we expect our code to do.
JupyterHub uses `pytest <https://pytest.org>`_ for all our tests. You
can find them under ``jupyterhub/tests`` directory in the git repository.
JupyterHub uses `pytest <https://pytest.org>`_ for all the tests. You
can find them under the `jupyterhub/tests <https://github.com/jupyterhub/jupyterhub/tree/main/jupyterhub/tests>`_ directory in the git repository.
Running the tests
==================
#. Make sure you have completed :ref:`contributing/setup`. You should be able
to start ``jupyterhub`` from the commandline & access it from your
web browser. This ensures that the dev environment is properly set
#. Make sure you have completed :ref:`contributing/setup`. Once completed, you should be able
to run ``jupyterhub`` on your command line and access JupyterHub from your browser at http://localhost:8000. Being able to run and access `jupyterhub` should mean that the dev environment is properly set
up for tests to run.
#. You can run all tests in JupyterHub
@@ -57,7 +56,7 @@ Running the tests
pytest -v jupyterhub/tests/test_api.py::test_shutdown
See the `pytest usage documentation <https://pytest.readthedocs.io/en/latest/usage.html>`_ for more details.
For more information, refer to the `pytest usage documentation <https://pytest.readthedocs.io/en/latest/usage.html>`_.
Test organisation
=================
@@ -98,8 +97,7 @@ And fixtures to add functionality or spawning behavior:
- ``bad_spawn``: enables the BadSpawner (a spawner that fails immediately)
- ``slow_bad_spawn``: enables the SlowBadSpawner (a spawner that fails after a short delay)
See the `pytest fixtures documentation <https://pytest.readthedocs.io/en/latest/fixture.html>`_
for how to use the existing fixtures, and how to create new ones.
For information on using the existing fixtures and creating new ones, refer to the `pytest fixtures documentation <https://pytest.readthedocs.io/en/latest/fixture.html>`_
Troubleshooting Test Failures
@@ -108,29 +106,34 @@ Troubleshooting Test Failures
All the tests are failing
-------------------------
Make sure you have completed all the steps in :ref:`contributing/setup` successfully, and
can launch ``jupyterhub`` from the terminal.
Make sure you have completed all the steps in :ref:`contributing/setup` successfully, and are able to access JupyterHub from your browser at http://localhost:8000 after starting ``jupyterhub`` in your command line.
Code formatting and linting
===========================
JupyterHub has adopted automatic code formatting and linting.
As long as your code is valid, the pre-commit hook should take care of how it should look.
You can invoke the pre-commit hook by hand at any time with:
JupyterHub automatically enforces code formatting. This means that pull requests
with changes breaking this formatting will receive a commit from pre-commit.ci
automatically.
To automatically format code locally, you can install pre-commit and register a
*git hook* to automatically check with pre-commit before you make a commit if
the formatting is okay.
.. code:: bash
pip install pre-commit
pre-commit install --install-hooks
To run pre-commit manually you would do:
.. code:: bash
# check for changes to code not yet committed
pre-commit run
which should run any autoformatting on your code and tell you about any errors it couldn't fix automatically.
You may also install `black integration <https://github.com/psf/black#editor-integration>`_
into your text editor to format code automatically.
If you have already committed files before running pre-commit you can fix everything using:
.. code:: bash
# check for changes also in already committed code
pre-commit run --all-files
And committing the changes.
You may also install `black integration <https://github.com/psf/black#editor-integration>`_
into your text editor to format code automatically.

6
docs/source/events/index.rst
View File

@@ -1,5 +1,5 @@
Eventlogging and Telemetry
==========================
Event logging and telemetry
===========================
JupyterHub can be configured to record structured events from a running server using Jupyter's `Telemetry System`_. The types of events that JupyterHub emits are defined by `JSON schemas`_ listed at the bottom of this page_.
@@ -15,7 +15,7 @@ Event logging is handled by its ``Eventlog`` object. This leverages Python's sta
To begin recording events, you'll need to set two configurations:
1. ``handlers``: tells the EventLog *where* to route your events. This trait is a list of Python logging handlers that route events to
1. ``handlers``: tells the EventLog *where* to route your events. This trait is a list of Python logging handlers that route events to the event log file.
2. ``allows_schemas``: tells the EventLog *which* events should be recorded. No events are emitted by default; all recorded events must be listed here.
Here's a basic example:

21
docs/source/gallery-jhub-deployments.md
View File

@@ -97,7 +97,7 @@ easy to do with RStudio too.
### University of Illinois
- https://datascience.business.illinois.edu (currently down; checked 04/26/19)
- https://datascience.business.illinois.edu (currently down; checked 10/26/22)
### IllustrisTNG Simulation Project
@@ -126,7 +126,7 @@ easy to do with RStudio too.
### Penn State University
- [Press release](https://news.psu.edu/story/523093/2018/05/24/new-open-source-web-apps-available-students-and-faculty): "New open-source web apps available for students and faculty" (but Hub is currently down; checked 04/26/19)
- [Press release](https://news.psu.edu/story/523093/2018/05/24/new-open-source-web-apps-available-students-and-faculty): "New open-source web apps available for students and faculty"
### University of Rochester CIRC
@@ -156,13 +156,13 @@ easy to do with RStudio too.
### Elucidata
- What's new in Jupyter Notebooks @[Elucidata](https://elucidata.io/):
- Using Jupyter Notebooks with Jupyterhub on GCP, managed by GKE - https://medium.com/elucidata/why-you-should-be-using-a-jupyter-notebook-8385a4ccd93d
- [Using Jupyter Notebooks with Jupyterhub on GCP, managed by GKE](https://medium.com/elucidata/why-you-should-be-using-a-jupyter-notebook-8385a4ccd93d)
## Service Providers
### AWS
- [running-jupyter-notebook-and-jupyterhub-on-amazon-emr](https://aws.amazon.com/blogs/big-data/running-jupyter-notebook-and-jupyterhub-on-amazon-emr/)
- [Run Jupyter Notebook and JupyterHub on Amazon EMR](https://aws.amazon.com/blogs/big-data/running-jupyter-notebook-and-jupyterhub-on-amazon-emr/)
### Google Cloud Platform
@@ -175,12 +175,12 @@ easy to do with RStudio too.
### Microsoft Azure
- https://docs.microsoft.com/en-us/azure/machine-learning/machine-learning-data-science-linux-dsvm-intro
- [Azure Data Science Virtual Machine release notes](https://docs.microsoft.com/en-us/azure/machine-learning/machine-learning-data-science-linux-dsvm-intro)
### Rackspace Carina
- https://getcarina.com/blog/learning-how-to-whale/
- http://carolynvanslyck.com/talk/carina/jupyterhub/#/
- http://carolynvanslyck.com/talk/carina/jupyterhub/#/ (but carolynvanslyck is currently down; checked 10/26/22)
### Hadoop
@@ -189,13 +189,14 @@ easy to do with RStudio too.
## Miscellaneous
- https://medium.com/@ybarraud/setting-up-jupyterhub-with-sudospawner-and-anaconda-844628c0dbee#.rm3yt87e1
- https://groups.google.com/forum/#!topic/jupyter/nkPSEeMr8c0 Mailing list UT deployment
- JupyterHub setup on Centos https://gist.github.com/johnrc/604971f7d41ebf12370bf5729bf3e0a4
- Deploy JupyterHub to Docker Swarm https://jupyterhub.surge.sh/#/welcome
- [Mailing list UT deployment](https://groups.google.com/forum/#!topic/jupyter/nkPSEeMr8c0)
- [JupyterHub setup on Centos](https://gist.github.com/johnrc/604971f7d41ebf12370bf5729bf3e0a4)
- [Deploy JupyterHub to Docker Swarm](https://jupyterhub.surge.sh/#/welcome)
- http://www.laketide.com/building-your-lab-part-3/
- http://estrellita.hatenablog.com/entry/2015/07/31/083202
- http://www.walkingrandomly.com/?p=5734
- https://wrdrd.com/docs/consulting/education-technology
- https://bitbucket.org/jackhale/fenics-jupyter
- [LinuxCluster blog](https://linuxcluster.wordpress.com/category/application/jupyterhub/)
- [Network Technology](https://arnesund.com/tag/jupyterhub/) [Spark Cluster on OpenStack with Multi-User Jupyter Notebook](https://arnesund.com/2015/09/21/spark-cluster-on-openstack-with-multi-user-jupyter-notebook/)
- [Network Technology](https://arnesund.com/tag/jupyterhub/)
- [Spark Cluster on OpenStack with Multi-User Jupyter Notebook](https://arnesund.com/2015/09/21/spark-cluster-on-openstack-with-multi-user-jupyter-notebook/)

12
docs/source/getting-started/authenticators-users-basics.md
View File

@@ -1,6 +1,6 @@
# Authentication and User Basics
The default Authenticator uses [PAM][] to authenticate system users with
The default Authenticator uses [PAM][] (Pluggable Authentication Module) to authenticate system users with
their username and password. With the default Authenticator, any user
with an account and password on the system will be allowed to login.
@@ -25,7 +25,7 @@ If this configuration value is not set, then **all authenticated users will be a
```{note}
As of JupyterHub 2.0, the full permissions of `admin_users`
should not be required.
Instead, you can assign [roles](https://jupyterhub.readthedocs.io/en/stable/rbac/roles.html#define-role-target) to users or groups
Instead, you can assign [roles](define-role-target) to users or groups
with only the scopes they require.
```
@@ -42,7 +42,7 @@ c.Authenticator.admin_users = {'mal', 'zoe'}
Users in the admin set are automatically added to the user `allowed_users` set,
if they are not already present.
Each authenticator may have different ways of determining whether a user is an
Each Authenticator may have different ways of determining whether a user is an
administrator. By default, JupyterHub uses the PAMAuthenticator which provides the
`admin_groups` option and can set administrator status based on a user
group. For example, we can let any user in the `wheel` group be an admin:
@@ -76,7 +76,7 @@ fresh.
## Use LocalAuthenticator to create system users
The `LocalAuthenticator` is a special kind of authenticator that has
The `LocalAuthenticator` is a special kind of Authenticator that has
the ability to manage users on the local system. When you try to add a
new user to the Hub, a `LocalAuthenticator` will check if the user
already exists. If you set the configuration value, `create_system_users`,
@@ -118,8 +118,8 @@ with any provider, is also available.
## Use DummyAuthenticator for testing
The `DummyAuthenticator` is a simple authenticator that
allows for any username/password unless a global password has been set. If
The `DummyAuthenticator` is a simple Authenticator that
allows for any username or password unless a global password has been set. If
set, it will allow for any username as long as the correct password is provided.
To set a global password, add this to the config file:

10
docs/source/getting-started/config-basics.md
View File

@@ -1,6 +1,6 @@
# Configuration Basics
The section contains basic information about configuring settings for a JupyterHub
This section contains basic information about configuring settings for a JupyterHub
deployment. The [Technical Reference](../reference/index)
documentation provides additional details.
@@ -49,7 +49,7 @@ that Jupyter uses.
## Configure using command line options
To display all command line options that are available for configuration:
To display all command line options that are available for configuration run the following command:
```bash
jupyterhub --help-all
@@ -77,11 +77,11 @@ jupyterhub --Spawner.notebook_dir='~/assignments'
## Configure for various deployment environments
The default authentication and process spawning mechanisms can be replaced, and
specific [authenticators](./authenticators-users-basics) and
[spawners](./spawners-basics) can be set in the configuration file.
specific [authenticators](authenticators-users-basics) and
[spawners](spawners-basics) can be set in the configuration file.
This enables JupyterHub to be used with a variety of authentication methods or
process control and deployment environments. [Some examples](../reference/config-examples),
meant as illustration, are:
meant as illustrations, are:
- Using GitHub OAuth instead of PAM with [OAuthenticator](https://github.com/jupyterhub/oauthenticator)
- Spawning single-user servers with Docker, using the [DockerSpawner](https://github.com/jupyterhub/dockerspawner)

2
docs/source/getting-started/institutional-faq.md
View File

@@ -78,7 +78,7 @@ gives administrators more control over their setup and hardware.
Because JupyterHub is an open-source, community-driven tool, it can be extended and
modified to fit an institution's needs. It plays nicely with the open source data science
stack, and can serve a variety of computing enviroments, user interfaces, and
stack, and can serve a variety of computing environments, user interfaces, and
computational hardware. It can also be deployed anywhere - on enterprise cloud infrastructure, on
High-Performance-Computing machines, on local hardware, or even on a single laptop, which
is not possible with most other tools for shared interactive computing.

6
docs/source/getting-started/networking-basics.md
View File

@@ -41,9 +41,9 @@ port.
## Set the Proxy's REST API communication URL (optional)
By default, this REST API listens on port 8001 of `localhost` only.
The Hub service talks to the proxy via a REST API on a secondary port. The
API URL can be configured separately to override the default settings.
By default, the proxy's REST API listens on port 8081 of `localhost` only.
The Hub service talks to the proxy via a REST API on a secondary port.
The REST API URL (hostname and port) can be configured separately and override the default settings.
### Set api_url

51
docs/source/getting-started/security-basics.rst
View File

@@ -5,17 +5,17 @@ Security settings
You should not run JupyterHub without SSL encryption on a public network.
Security is the most important aspect of configuring Jupyter. Three
configuration settings are the main aspects of security configuration:
Security is the most important aspect of configuring Jupyter.
Three (3) configuration settings are the main aspects of security configuration:
1. :ref:`SSL encryption <ssl-encryption>` (to enable HTTPS)
2. :ref:`Cookie secret <cookie-secret>` (a key for encrypting browser cookies)
3. Proxy :ref:`authentication token <authentication-token>` (used for the Hub and
other services to authenticate to the Proxy)
The Hub hashes all secrets (e.g., auth tokens) before storing them in its
The Hub hashes all secrets (e.g. auth tokens) before storing them in its
database. A loss of control over read-access to the database should have
minimal impact on your deployment; if your database has been compromised, it
minimal impact on your deployment. If your database has been compromised, it
is still a good idea to revoke existing tokens.
.. _ssl-encryption:
@@ -72,13 +72,13 @@ would be the needed configuration:
If SSL termination happens outside of the Hub
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
In certain cases, for example if the hub is running behind a reverse proxy, and
In certain cases, for example, if the hub is running behind a reverse proxy, and
`SSL termination is being provided by NGINX <https://www.nginx.com/resources/admin-guide/nginx-ssl-termination/>`_,
it is reasonable to run the hub without SSL.
To achieve this, simply omit the configuration settings
``c.JupyterHub.ssl_key`` and ``c.JupyterHub.ssl_cert``
(setting them to ``None`` does not have the same effect, and is an error).
To achieve this, remove ``c.JupyterHub.ssl_key`` and ``c.JupyterHub.ssl_cert``
from your configuration (setting them to ``None`` or an empty string does not
have the same effect, and will result in an error).
.. _authentication-token:
@@ -92,7 +92,7 @@ use an auth token.
The value of this token should be a random string (for example, generated by
``openssl rand -hex 32``). You can store it in the configuration file or an
environment variable
environment variable.
Generating and storing token in the configuration file
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -118,8 +118,8 @@ This environment variable needs to be visible to the Hub and Proxy.
Default if token is not set
~~~~~~~~~~~~~~~~~~~~~~~~~~~
If you don't set the Proxy authentication token, the Hub will generate a random
key itself, which means that any time you restart the Hub you **must also
If you do not set the Proxy authentication token, the Hub will generate a random
key itself. This means that any time you restart the Hub, you **must also
restart the Proxy**. If the proxy is a subprocess of the Hub, this should happen
automatically (this is the default configuration).
@@ -128,7 +128,7 @@ automatically (this is the default configuration).
Cookie secret
-------------
The cookie secret is an encryption key, used to encrypt the browser cookies
The cookie secret is an encryption key, used to encrypt the browser cookies,
which are used for authentication. Three common methods are described for
generating and configuring the cookie secret.
@@ -136,8 +136,8 @@ Generating and storing as a cookie secret file
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
The cookie secret should be 32 random bytes, encoded as hex, and is typically
stored in a ``jupyterhub_cookie_secret`` file. An example command to generate the
``jupyterhub_cookie_secret`` file is:
stored in a ``jupyterhub_cookie_secret`` file. Below, is an example command to generate the
``jupyterhub_cookie_secret`` file:
.. code-block:: bash
@@ -155,7 +155,7 @@ The location of the ``jupyterhub_cookie_secret`` file can be specified in the
If the cookie secret file doesn't exist when the Hub starts, a new cookie
secret is generated and stored in the file. The file must not be readable by
``group`` or ``other`` or the server won't start. The recommended permissions
``group`` or ``other``, otherwise the server won't start. The recommended permissions
for the cookie secret file are ``600`` (owner-only rw).
Generating and storing as an environment variable
@@ -176,8 +176,8 @@ the Hub starts.
Generating and storing as a binary string
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
You can also set the cookie secret in the configuration file
itself, ``jupyterhub_config.py``, as a binary string:
You can also set the cookie secret, as a binary string,
in the configuration file (``jupyterhub_config.py``) itself:
.. code-block:: python
@@ -198,7 +198,7 @@ jupyterhub-hub-login
~~~~~~~~~~~~~~~~~~~~
This is the login token used when visiting Hub-served pages that are
protected by authentication such as the main home, the spawn form, etc.
protected by authentication, such as the main home, the spawn form, etc.
If this cookie is set, then the user is logged in.
Resetting the Hub cookie secret effectively revokes this cookie.
@@ -209,7 +209,7 @@ jupyterhub-user-<username>
~~~~~~~~~~~~~~~~~~~~~~~~~~
This is the cookie used for authenticating with a single-user server.
It is set by the single-user server after OAuth with the Hub.
It is set by the single-user server, after OAuth with the Hub.
Effectively the same as ``jupyterhub-hub-login``, but for the
single-user server instead of the Hub. It contains an OAuth access token,
@@ -218,14 +218,13 @@ which is checked with the Hub to authenticate the browser.
Each OAuth access token is associated with a session id (see ``jupyterhub-session-id`` section
below).
To avoid hitting the Hub on every request, the authentication response
is cached. And to avoid a stale cache the cache key is comprised of both
the token and session id.
To avoid hitting the Hub on every request, the authentication response is cached.
The cache key is comprised of both the token and session id, to avoid a stale cache.
Resetting the Hub cookie secret effectively revokes this cookie.
This cookie is restricted to the path ``/user/<username>``, so that
only the user’s server receives it.
This cookie is restricted to the path ``/user/<username>``,
to ensure that only the user’s server receives it.
jupyterhub-session-id
~~~~~~~~~~~~~~~~~~~~~
@@ -235,7 +234,7 @@ shared by the Hub and single-user servers.
Its sole purpose is to coordinate the logout of the multiple OAuth cookies.
This cookie is set to ``/`` so all endpoints can receive it, or clear it, etc.
This cookie is set to ``/`` so all endpoints can receive it, clear it, etc.
jupyterhub-user-<username>-oauth-state
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -245,7 +244,7 @@ It is only set while OAuth between the single-user server and the Hub
is processing.
If you use your browser development tools, you should see this cookie
for a very brief moment before your are logged in,
for a very brief moment before you are logged in,
with an expiration date shorter than ``jupyterhub-hub-login`` or
``jupyterhub-user-<username>``.

19
docs/source/getting-started/services-basics.md
View File

@@ -24,7 +24,7 @@ Hub via the REST API.
## API Token basics
### Create an API token
### Step 1: Generate an API token
To run such an external service, an API token must be created and
provided to the service.
@@ -43,12 +43,12 @@ generating an API token is available from the JupyterHub user interface:
![API TOKEN success page](../images/token-request-success.png)
### Pass environment variable with token to the Hub
### Step 2: Pass environment variable with token to the Hub
In the case of `cull_idle_servers`, it is passed as the environment
variable called `JUPYTERHUB_API_TOKEN`.
### Use API tokens for services and tasks that require external access
### Step 3: Use API tokens for services and tasks that require external access
While API tokens are often associated with a specific user, API tokens
can be used by services that require external access for activities
@@ -62,12 +62,12 @@ c.JupyterHub.services = [
]
```
### Restart JupyterHub
### Step 4: Restart JupyterHub
Upon restarting JupyterHub, you should see a message like below in the
logs:
```
```none
Adding API token for <username>
```
@@ -78,16 +78,15 @@ single-user servers, and only cookies can be used for authentication.
0.8 supports using JupyterHub API tokens to authenticate to single-user
servers.
## Configure the idle culler to run as a Hub-Managed Service
## How to configure the idle culler to run as a Hub-Managed Service
Install the idle culler:
### Step 1: Install the idle culler:
```
pip install jupyterhub-idle-culler
```
In `jupyterhub_config.py`, add the following dictionary for the
`idle-culler` Service to the `c.JupyterHub.services` list:
### Step 2: In `jupyterhub_config.py`, add the following dictionary for the `idle-culler` Service to the `c.JupyterHub.services` list:
```python
c.JupyterHub.services = [
@@ -127,7 +126,7 @@ It now needs the scopes:
- `admin:servers` to start/stop servers
```
## Run `cull-idle` manually as a standalone script
## How to run `cull-idle` manually as a standalone script
Now you can run your script by providing it
the API token and it will authenticate through the REST API to

8
docs/source/getting-started/spawners-basics.md
View File

@@ -1,12 +1,12 @@
# Spawners and single-user notebook servers
Since the single-user server is an instance of `jupyter notebook`, an entire separate
multi-process application, there are many aspects of that server that can be configured, and a lot
A Spawner starts each single-user notebook server. Since the single-user server is an instance of `jupyter notebook`, an entire separate
multi-process application, many aspects of that server can be configured and there are a lot
of ways to express that configuration.
At the JupyterHub level, you can set some values on the Spawner. The simplest of these is
`Spawner.notebook_dir`, which lets you set the root directory for a user's server. This root
notebook directory is the highest level directory users will be able to access in the notebook
notebook directory is the highest-level directory users will be able to access in the notebook
dashboard. In this example, the root notebook directory is set to `~/notebooks`, where `~` is
expanded to the user's home directory.
@@ -20,7 +20,7 @@ You can also specify extra command line arguments to the notebook server with:
c.Spawner.args = ['--debug', '--profile=PHYS131']
```
This could be used to set the users default page for the single user server:
This could be used to set the user's default page for the single-user server:
```python
c.Spawner.args = ['--NotebookApp.default_url=/notebooks/Welcome.ipynb']

36
docs/source/index.rst
View File

@@ -2,31 +2,29 @@
JupyterHub
==========
`JupyterHub`_ is the best way to serve `Jupyter notebook`_ for multiple users.
It can be used in a class of students, a corporate data science group or scientific
`JupyterHub`_ is the best way to serve `Jupyter notebook`_ for multiple users.
Because JupyterHub manages a separate Jupyter environment for each user,
it can be used in a class of students, a corporate data science group, or a scientific
research group. It is a multi-user **Hub** that spawns, manages, and proxies multiple
instances of the single-user `Jupyter notebook`_ server.
To make life easier, JupyterHub has distributions. Be sure to
JupyterHub offers distributions for different use cases. Be sure to
take a look at them before continuing with the configuration of the broad
original system of `JupyterHub`_. Today, you can find two main cases:
original system of `JupyterHub`_. As of now, you can find two main cases:
1. If you need a simple case for a small amount of users (0-100) and single server
take a look at
`The Littlest JupyterHub <https://github.com/jupyterhub/the-littlest-jupyterhub>`__ distribution.
2. If you need to allow for even more users, a dynamic amount of servers can be used on a cloud,
take a look at the `Zero to JupyterHub with Kubernetes <https://github.com/jupyterhub/zero-to-jupyterhub-k8s>`__ .
1. `The Littlest JupyterHub <https://github.com/jupyterhub/the-littlest-jupyterhub>`__ distribution is suitable if you need a small number of users (1-100) and a single server with a simple environment.
2. `Zero to JupyterHub with Kubernetes <https://github.com/jupyterhub/zero-to-jupyterhub-k8s>`__ allows you to deploy dynamic servers on the cloud if you need even more users.
Four subsystems make up JupyterHub:
* a **Hub** (tornado process) that is the heart of JupyterHub
* a **configurable http proxy** (node-http-proxy) that receives the requests from the client's browser
* multiple **single-user Jupyter notebook servers** (Python/IPython/tornado) that are monitored by Spawners
* an **authentication class** that manages how users can access the system
* a **Configurable HTTP Proxy** (node-http-proxy) that receives the requests from the client's browser
* multiple **Single-User Jupyter Notebook Servers** (Python/IPython/tornado) that are monitored by Spawners
* an **Authentication Class** that manages how users can access the system
Besides these central pieces, you can add optional configurations through a `config.py` file and manage users kernels on an admin panel. A simplification of the whole system can be seen in the figure below:
Besides these central pieces, you can add optional configurations through a `config.py` file and manage users' environments through an admin panel. A simplification of the whole system can be seen in the figure below:
.. image:: images/jhub-fluxogram.jpeg
:alt: JupyterHub subsystems
@@ -56,17 +54,17 @@ Contents
Distributions
-------------
A JupyterHub **distribution** is tailored towards a particular set of
Each JupyterHub **distribution** is tailored toward a particular set of
use cases. These are generally easier to set up than setting up
JupyterHub from scratch, assuming they fit your use case.
The two popular ones are:
* `Zero to JupyterHub on Kubernetes <http://z2jh.jupyter.org>`_, for
running JupyterHub on top of `Kubernetes <https://k8s.io>`_. This
can scale to large number of machines & users.
* `The Littlest JupyterHub <http://tljh.jupyter.org>`_, for an easy
to set up & run JupyterHub supporting 1-100 users on a single machine.
* `Zero to JupyterHub on Kubernetes <http://z2jh.jupyter.org>`_, for
running JupyterHub on top of `Kubernetes <https://k8s.io>`_. This
can scale to a large number of machines & users.
Installation Guide
------------------
@@ -119,8 +117,8 @@ RBAC Reference
Contributing
------------
We want you to contribute to JupyterHub in ways that are most exciting
& useful to you. We value documentation, testing, bug reporting & code equally,
We welcome you to contribute to JupyterHub in ways that are most exciting
& useful to you. We value documentation, testing, bug reporting & code equally
and are glad to have your contributions in whatever form you wish :)
Our `Code of Conduct <https://github.com/jupyter/governance/blob/HEAD/conduct/code_of_conduct.md>`_

17
docs/source/quickstart-docker.rst
View File

@@ -1,10 +1,16 @@
Install JupyterHub with Docker
==============================
The JupyterHub `docker image <https://hub.docker.com/r/jupyterhub/jupyterhub/>`_ is the fastest way to set up Jupyterhub in your local development environment.
The ``JupyterHub`` docker image runs the Hub service only. It does not provide other Jupyter components such as Notebook installation, which are needed by the single-user servers.
To run the single-user servers, which may be on the same system as the Hub or not, Jupyter Notebook or Jupyter Lab must be installed.
.. note::
This ``jupyterhub/jupyterhub`` docker image is only an image for running
the Hub service itself. It does not provide the other Jupyter components,
such as Notebook installation, which are needed by the single-user servers.
To run the single-user servers, which may be on the same system as the Hub or
not, `JupyterLab <https://jupyterlab.readthedocs.io/>`_ or Jupyter Notebook must be installed.
.. important::
We strongly recommend that you follow the `Zero to JupyterHub`_ tutorial to
@@ -24,6 +30,7 @@ To pull the latest JupyterHub image and start the `jupyterhub` container, run th
docker run -d -p 8000:8000 --name jupyterhub jupyterhub/jupyterhub jupyterhub
This command exposes the Jupyter container on port:8000. Navigate to `http://localhost:8000` in a web browser to access the JupyterHub console.
You can stop and resume the container by running `docker stop` and `docker start` respectively.
@@ -39,9 +46,9 @@ You can stop and resume the container by running `docker stop` and `docker start
docker start <container-id>
If you are running Docker on a computer that has a public IP address, you must **secure it with ssl** by adding ssl options to your docker
configuration or using a ssl enabled proxy.
If you want to run docker on a computer that has a public IP then you should
(as in MUST) **secure it with ssl** by adding ssl options to your docker
configuration or using an ssl enabled proxy.
`Mounting volumes <https://docs.docker.com/engine/admin/volumes/volumes/>`_
enables you to persist and store the data generated by the docker container, even when you stop the container.

2
docs/source/rbac/roles.md
View File

@@ -1,5 +1,3 @@
(roles)=
# Roles
JupyterHub provides four (4) roles that are available by default:

33
docs/source/rbac/tech-implementation.md
View File

@@ -1,8 +1,8 @@
# Technical Implementation
Roles are stored in the database, where they are associated with users, services, etc., and can be added or modified as explained in {ref}`define-role-target` section. Users, services, groups, and tokens can gain, change, and lose roles. This is currently achieved via `jupyterhub_config.py` (see {ref}`define-role-target`) and will be made available via API in future. The latter will allow for changing a token's role, and thereby its permissions, without the need to issue a new token.
[Roles](roles) are stored in the database, where they are associated with users, services, and groups. Roles can be added or modified as explained in the {ref}`define-role-target` section. Users, services, groups, and tokens can gain, change, and lose roles. This is currently achieved via `jupyterhub_config.py` (see {ref}`define-role-target`) and will be made available via API in the future. The latter will allow for changing a user's role, and thereby its permissions, without the need to restart JupyterHub.
Roles and scopes utilities can be found in `roles.py` and `scopes.py` modules. Scope variables take on five different formats which is reflected throughout the utilities via specific nomenclature:
Roles and scopes utilities can be found in `roles.py` and `scopes.py` modules. Scope variables take on five different formats that are reflected throughout the utilities via specific nomenclature:
```{admonition} **Scope variable nomenclature**
:class: tip
@@ -11,22 +11,22 @@ Roles and scopes utilities can be found in `roles.py` and `scopes.py` modules. S
- _expanded scopes_ \
Set of fully expanded scopes without abbreviations (i.e., resolved metascopes, filters, and subscopes). E.g., `{"users:activity!user=charlie", "read:users:activity!user=charlie"}`.
- _parsed scopes_ \
Dictionary represenation of expanded scopes. E.g., `{"users:activity": {"user": ["charlie"]}, "read:users:activity": {"users": ["charlie"]}}`.
Dictionary representation of expanded scopes. E.g., `{"users:activity": {"user": ["charlie"]}, "read:users:activity": {"users": ["charlie"]}}`.
- _intersection_ \
Set of expanded scopes as intersection of 2 expanded scope sets.
- _identify scopes_ \
Set of expanded scopes needed for identify (whoami) endpoints.
Set of expanded scopes needed for identity (whoami) endpoints.
```
(resolving-roles-scopes-target)=
## Resolving roles and scopes
**Resolving roles** refers to determining which roles a user, service, or group has, extracting the list of scopes from each role and combining them into a single set of scopes.
**Resolving roles** involves determining which roles a user, service, or group has, extracting the list of scopes from each role and combining them into a single set of scopes.
**Resolving scopes** involves expanding scopes into all their possible subscopes (_expanded scopes_), parsing them into format used for access evaluation (_parsed scopes_) and, if applicable, comparing two sets of scopes (_intersection_). All procedures take into account the scope hierarchy, {ref}`vertical <vertical-filtering-target>` and {ref}`horizontal filtering <horizontal-filtering-target>`, limiting or elevated permissions (`read:<resource>` or `admin:<resource>`, respectively), and metascopes.
**Resolving scopes** involves expanding scopes into all their possible subscopes (_expanded scopes_), parsing them into the format used for access evaluation (_parsed scopes_) and, if applicable, comparing two sets of scopes (_intersection_). All procedures take into account the scope hierarchy, {ref}`vertical <vertical-filtering-target>` and {ref}`horizontal filtering <horizontal-filtering-target>`, limiting or elevated permissions (`read:<resource>` or `admin:<resource>`, respectively), and metascopes.
Roles and scopes are resolved on several occasions, for example when requesting an API token with specific scopes or making an API request. The following sections provide more details.
Roles and scopes are resolved on several occasions, for example when requesting an API token with specific scopes or when making an API request. The following sections provide more details.
(requesting-api-token-target)=
@@ -43,25 +43,24 @@ Prior to 3.0, tokens stored _roles_,
which meant their scopes were resolved on each request.
:::
API tokens grant access to JupyterHub's APIs. The RBAC framework allows for requesting tokens with specific permissions.
API tokens grant access to JupyterHub's APIs. The [RBAC framework](./index.md) allows for requesting tokens with specific permissions.
RBAC is involved in several stages of the OAuth token flow.
When requesting a token via the tokens API (`/users/:name/tokens`), or the token page (`/hub/token`),
if no scopes are requested, the token is issued with the permissions stored on the default `token` role
(providing the requester is allowed to create the token).
(provided the requester is allowed to create the token).
OAuth tokens are also requested via OAuth flow
If the token is requested with any scopes, the permissions of requesting entity are checked against the requested permissions to ensure the token would not grant its owner additional privileges.
If, due to modifications of permissions of the token or token owner,
at API request time a token has any scopes that its owner does not,
those scopes are removed.
If a token has any scopes that its owner does not possess
at the time of making the API request, those scopes are removed.
The API request is resolved without additional errors using the scope _intersection_;
the Hub logs a warning in this case (see {ref}`Figure 2 <api-request-chart>`).
Resolving a token's scope (yellow box in {ref}`Figure 1 <token-request-chart>`) corresponds to resolving all the token's owner roles (including the roles associated with their groups) and the token's own scopes into a set of scopes. The two sets are compared (Resolve the scopes box in orange in {ref}`Figure 1 <token-request-chart>`), taking into account the scope hierarchy.
Resolving a token's scope (yellow box in {ref}`Figure 1 <token-request-chart>`) corresponds to resolving all the roles of the token's owner (including the roles associated with their groups) and the token's own scopes into a set of scopes. The two sets are compared (Resolve the scopes box in orange in {ref}`Figure 1 <token-request-chart>`), taking into account the scope hierarchy.
If the token's scopes are a subset of the token owner's scopes, the token is issued with the requested scopes; if not, JupyterHub will raise an error.
{ref}`Figure 1 <token-request-chart>` below illustrates the steps involved. The orange rectangles highlight where in the process the roles and scopes are resolved.
@@ -75,10 +74,10 @@ Figure 1. Resolving roles and scopes during API token request
### Making an API request
With the RBAC framework, each authenticated JupyterHub API request is guarded by a scope decorator that specifies which scopes are required to gain the access to the API.
With the RBAC framework, each authenticated JupyterHub API request is guarded by a scope decorator that specifies which scopes are required in order to gain the access to the API.
When an API request is performed, the requesting API token's scopes are again intersected with its owner's (yellow box in {ref}`Figure 2 <api-request-chart>`) to ensure the token does not grant more permissions than its owner has at the request time (e.g., due to changing/losing roles).
If the owner's roles do not include some scopes of the token's scopes, only the _intersection_ of the token's and owner's scopes will be used. For example, using a token with scope `users` whose owner's role scope is `read:users:name` will result in only the `read:users:name` scope being passed on. In the case of no _intersection_, an empty set of scopes will be used.
When an API request is made, the requesting API token's scopes are again intersected with its owner's (yellow box in {ref}`Figure 2 <api-request-chart>`) to ensure that the token does not grant more permissions than its owner has at the request time (e.g., due to changing/losing roles).
If the owner's roles do not include some scopes of the token, only the _intersection_ of the token's and owner's scopes will be used. For example, using a token with scope `users` whose owner's role scope is `read:users:name` will result in only the `read:users:name` scope being passed on. In the case of no _intersection_, an empty set of scopes will be used.
The passed scopes are compared to the scopes required to access the API as follows:
@@ -86,7 +85,7 @@ The passed scopes are compared to the scopes required to access the API as follo
- if that is not the case, another check is utilized to determine if subscopes of the required API scopes can be found in the passed scope set:
- if found, the RBAC framework employs the {ref}`filtering <vertical-filtering-target>` procedures to refine the API response to access only resource attributes corresponding to the passed scopes. For example, providing a scope `read:users:activity!group=class-C` for the _GET /users_ API will return a list of user models from group `class-C` containing only the `last_activity` attribute for each user model
- if found, the RBAC framework employs the {ref}`filtering <vertical-filtering-target>` procedures to refine the API response to access only resource attributes corresponding to the passed scopes. For example, providing a scope `read:users:activity!group=class-C` for the `GET /users` API will return a list of user models from group `class-C` containing only the `last_activity` attribute for each user model
- if not found, the access to API is denied

4
docs/source/rbac/use-cases.md
View File

@@ -9,12 +9,12 @@ To determine which scopes a role should have, one can follow these steps:
5. Customize the scopes with filters if needed
6. Define the role with required scopes and assign to users/services/groups/tokens
Below, different use cases are presented on how to use the RBAC framework.
Below, different use cases are presented on how to use the [RBAC framework](./index.md)
## Service to cull idle servers
Finding and shutting down idle servers can save a lot of computational resources.
We can make use of [jupyterhub-idle-culler](https://github.com/jupyterhub/jupyterhub-idle-culler) to manage this for us.
**We can make use of [jupyterhub-idle-culler](https://github.com/jupyterhub/jupyterhub-idle-culler) to manage this for us.**
Below follows a short tutorial on how to add a cull-idle service in the RBAC system.
1. Install the cull-idle server script with `pip install jupyterhub-idle-culler`.

7
docs/source/reference/authenticators.md
View File

@@ -31,8 +31,7 @@ popular services:
- Okpy
- OpenShift
A generic implementation, which you can use for OAuth authentication
with any provider, is also available.
A [generic implementation](https://github.com/jupyterhub/oauthenticator/blob/master/oauthenticator/generic.py), which you can use for OAuth authentication with any provider, is also available.
## The Dummy Authenticator
@@ -165,7 +164,7 @@ setup(
```
If you have added this metadata to your package,
users can select your authenticator with the configuration:
admins can select your authenticator with the configuration:
```python
c.JupyterHub.authenticator_class = 'myservice'
@@ -298,7 +297,7 @@ all group-management via the API is disabled.
## pre_spawn_start and post_spawn_stop hooks
Authenticators uses two hooks, {meth}`.Authenticator.pre_spawn_start` and
Authenticators use two hooks, {meth}`.Authenticator.pre_spawn_start` and
{meth}`.Authenticator.post_spawn_stop(user, spawner)` to add pass additional state information
between the authenticator and a spawner. These hooks are typically used auth-related
startup, i.e. opening a PAM session, and auth-related cleanup, i.e. closing a

10
docs/source/reference/config-ghoauth.md
View File

@@ -5,15 +5,15 @@ deployment with the following assumptions:
- Running JupyterHub on a single cloud server
- Using SSL on the standard HTTPS port 443
- Using GitHub OAuth (using oauthenticator) for login
- Using GitHub OAuth (using [OAuthenticator](https://oauthenticator.readthedocs.io/en/latest)) for login
- Using the default spawner (to configure other spawners, uncomment and edit
`spawner_class` as well as follow the instructions for your desired spawner)
- Users exist locally on the server
- Users' notebooks to be served from `~/assignments` to allow users to browse
for notebooks within other users' home directories
- You want the landing page for each user to be a `Welcome.ipynb` notebook in
their assignments directory.
- All runtime files are put into `/srv/jupyterhub` and log files in `/var/log`.
their assignments directory
- All runtime files are put into `/srv/jupyterhub` and log files in `/var/log`
The `jupyterhub_config.py` file would have these settings:
@@ -69,7 +69,7 @@ c.Spawner.args = ['--NotebookApp.default_url=/notebooks/Welcome.ipynb']
```
Using the GitHub Authenticator requires a few additional
environment variable to be set prior to launching JupyterHub:
environment variables to be set prior to launching JupyterHub:
```bash
export GITHUB_CLIENT_ID=github_id
@@ -79,3 +79,5 @@ export CONFIGPROXY_AUTH_TOKEN=super-secret
# append log output to log file /var/log/jupyterhub.log
jupyterhub -f /etc/jupyterhub/jupyterhub_config.py &>> /var/log/jupyterhub.log
```
Visit the [Github OAuthenticator reference](https://oauthenticator.readthedocs.io/en/latest/api/gen/oauthenticator.github.html) to see the full list of options for configuring Github OAuth with JupyterHub.

56
docs/source/reference/config-proxy.md
View File

@@ -14,7 +14,7 @@ satisfy the following:
- After testing, the server in question should be able to score at least an A on the
Qualys SSL Labs [SSL Server Test](https://www.ssllabs.com/ssltest/)
Let's start out with needed JupyterHub configuration in `jupyterhub_config.py`:
Let's start out with the needed JupyterHub configuration in `jupyterhub_config.py`:
```python
# Force the proxy to only listen to connections to 127.0.0.1 (on port 8000)
@@ -30,15 +30,15 @@ This can take a few minutes:
openssl dhparam -out /etc/ssl/certs/dhparam.pem 4096
```
## nginx
## Nginx
This **`nginx` config file** is fairly standard fare except for the two
`location` blocks within the main section for HUB.DOMAIN.tld.
To create a new site for jupyterhub in your nginx config, make a new file
To create a new site for jupyterhub in your Nginx config, make a new file
in `sites.enabled`, e.g. `/etc/nginx/sites.enabled/jupyterhub.conf`:
```bash
# top-level http config for websocket headers
# Top-level HTTP config for WebSocket headers
# If Upgrade is defined, Connection = upgrade
# If Upgrade is empty, Connection = close
map $http_upgrade $connection_upgrade {
@@ -51,7 +51,7 @@ server {
listen 80;
server_name HUB.DOMAIN.TLD;
# Tell all requests to port 80 to be 302 redirected to HTTPS
# Redirect the request to HTTPS
return 302 https://$host$request_uri;
}
@@ -75,7 +75,7 @@ server {
ssl_stapling_verify on;
add_header Strict-Transport-Security max-age=15768000;
# Managing literal requests to the JupyterHub front end
# Managing literal requests to the JupyterHub frontend
location / {
proxy_pass http://127.0.0.1:8000;
proxy_set_header X-Real-IP $remote_addr;
@@ -101,10 +101,10 @@ server {
If `nginx` is not running on port 443, substitute `$http_host` for `$host` on
the lines setting the `Host` header.
`nginx` will now be the front facing element of JupyterHub on `443` which means
`nginx` will now be the front-facing element of JupyterHub on `443` which means
it is also free to bind other servers, like `NO_HUB.DOMAIN.TLD` to the same port
on the same machine and network interface. In fact, one can simply use the same
server blocks as above for `NO_HUB` and simply add line for the root directory
server blocks as above for `NO_HUB` and simply add a line for the root directory
of the site as well as the applicable location call:
```bash
@@ -112,7 +112,7 @@ server {
listen 80;
server_name NO_HUB.DOMAIN.TLD;
# Tell all requests to port 80 to be 302 redirected to HTTPS
# Redirect the request to HTTPS
return 302 https://$host$request_uri;
}
@@ -143,12 +143,12 @@ Now restart `nginx`, restart the JupyterHub, and enjoy accessing
`https://HUB.DOMAIN.TLD` while serving other content securely on
`https://NO_HUB.DOMAIN.TLD`.
### SELinux permissions for nginx
### SELinux permissions for Nginx
On distributions with SELinux enabled (e.g. Fedora), one may encounter permission errors
when the nginx service is started.
when the Nginx service is started.
We need to allow nginx to perform network relay and connect to the jupyterhub port. The
We need to allow Nginx to perform network relay and connect to the JupyterHub port. The
following commands do that:
```bash
@@ -157,26 +157,26 @@ setsebool -P httpd_can_network_relay 1
setsebool -P httpd_can_network_connect 1
```
Replace 8000 with the port the jupyterhub server is running from.
Replace 8000 with the port the JupyterHub server is running from.
## Apache
As with nginx above, you can use [Apache](https://httpd.apache.org) as the reverse proxy.
First, we will need to enable the apache modules that we are going to need:
As with Nginx above, you can use [Apache](https://httpd.apache.org) as the reverse proxy.
First, we will need to enable the Apache modules that we are going to need:
```bash
a2enmod ssl rewrite proxy headers proxy_http proxy_wstunnel
```
Our Apache configuration is equivalent to the nginx configuration above:
Our Apache configuration is equivalent to the Nginx configuration above:
- Redirect HTTP to HTTPS
- Good SSL Configuration
- Support for websockets on any proxied URL
- Support for WebSocket on any proxied URL
- JupyterHub is running locally at http://127.0.0.1:8000
```bash
# redirect HTTP to HTTPS
# Redirect HTTP to HTTPS
Listen 80
<VirtualHost HUB.DOMAIN.TLD:80>
ServerName HUB.DOMAIN.TLD
@@ -188,26 +188,26 @@ Listen 443
ServerName HUB.DOMAIN.TLD
# enable HTTP/2, if available
# Enable HTTP/2, if available
Protocols h2 http/1.1
# HTTP Strict Transport Security (mod_headers is required) (63072000 seconds)
Header always set Strict-Transport-Security "max-age=63072000"
# configure SSL
# Configure SSL
SSLEngine on
SSLCertificateFile /etc/letsencrypt/live/HUB.DOMAIN.TLD/fullchain.pem
SSLCertificateKeyFile /etc/letsencrypt/live/HUB.DOMAIN.TLD/privkey.pem
SSLOpenSSLConfCmd DHParameters /etc/ssl/certs/dhparam.pem
# intermediate configuration from ssl-config.mozilla.org (2022-03-03)
# Please note, that this configuration might be out-dated - please update it accordingly using https://ssl-config.mozilla.org/
# Intermediate configuration from SSL-config.mozilla.org (2022-03-03)
# Please note, that this configuration might be outdated - please update it accordingly using https://ssl-config.mozilla.org/
SSLProtocol all -SSLv3 -TLSv1 -TLSv1.1
SSLCipherSuite ECDHE-ECDSA-AES128-GCM-SHA256:ECDHE-RSA-AES128-GCM-SHA256:ECDHE-ECDSA-AES256-GCM-SHA384:ECDHE-RSA-AES256-GCM-SHA384:ECDHE-ECDSA-CHACHA20-POLY1305:ECDHE-RSA-CHACHA20-POLY1305:DHE-RSA-AES128-GCM-SHA256:DHE-RSA-AES256-GCM-SHA384
SSLHonorCipherOrder off
SSLSessionTickets off
# Use RewriteEngine to handle websocket connection upgrades
# Use RewriteEngine to handle WebSocket connection upgrades
RewriteEngine On
RewriteCond %{HTTP:Connection} Upgrade [NC]
RewriteCond %{HTTP:Upgrade} websocket [NC]
@@ -224,7 +224,7 @@ Listen 443
</VirtualHost>
```
In case of the need to run the jupyterhub under /jhub/ or other location please use the below configurations:
In case of the need to run JupyterHub under /jhub/ or another location please use the below configurations:
- JupyterHub running locally at http://127.0.0.1:8000/jhub/ or other location
@@ -240,8 +240,8 @@ httpd.conf amendments:
jupyterhub_config.py amendments:
```bash
--The public facing URL of the whole JupyterHub application.
--This is the address on which the proxy will bind. Sets protocol, ip, base_url
c.JupyterHub.bind_url = 'http://127.0.0.1:8000/jhub/'
```python
# The public facing URL of the whole JupyterHub application.
# This is the address on which the proxy will bind. Sets protocol, IP, base_url
c.JupyterHub.bind_url = 'http://127.0.0.1:8000/jhub/'
```

23
docs/source/reference/config-sudo.md
View File

@@ -6,10 +6,10 @@ Only do this if you are very sure you must.
## Overview
There are many Authenticators and Spawners available for JupyterHub. Some, such
as DockerSpawner or OAuthenticator, do not need any elevated permissions. This
There are many [Authenticators](../getting-started/authenticators-users-basics) and [Spawners](../getting-started/spawners-basics) available for JupyterHub. Some, such
as [DockerSpawner](https://github.com/jupyterhub/dockerspawner) or [OAuthenticator](https://github.com/jupyterhub/oauthenticator), do not need any elevated permissions. This
document describes how to get the full default behavior of JupyterHub while
running notebook servers as real system users on a shared system without
running notebook servers as real system users on a shared system, without
running the Hub itself as root.
Since JupyterHub needs to spawn processes as other users, the simplest way
@@ -69,7 +69,8 @@ Cmnd_Alias JUPYTER_CMD = /usr/local/bin/sudospawner
rhea ALL=(JUPYTER_USERS) NOPASSWD:JUPYTER_CMD
```
It might be useful to modify `secure_path` to add commands in path.
It might be useful to modify `secure_path` to add commands in path. (Search for
`secure_path` in the [sudo docs](https://www.sudo.ws/man/1.8.14/sudoers.man.html)
As an alternative to adding every user to the `/etc/sudoers` file, you can
use a group in the last line above, instead of `JUPYTER_USERS`:
@@ -90,7 +91,7 @@ $ adduser -G jupyterhub newuser
Test that the new user doesn't need to enter a password to run the sudospawner
command.
This should prompt for your password to switch to rhea, but _not_ prompt for
This should prompt for your password to switch to `rhea`, but _not_ prompt for
any password for the second switch. It should show some help output about
logging options:
@@ -119,7 +120,7 @@ the shadow password database.
### Shadow group (Linux)
**Note:** On Fedora based distributions there is no clear way to configure
**Note:** On [Fedora based distributions](https://fedoraproject.org/wiki/List_of_Fedora_remixes) there is no clear way to configure
the PAM database to allow sufficient access for authenticating with the target user's password
from JupyterHub. As a workaround we recommend use an
[alternative authentication method](https://github.com/jupyterhub/jupyterhub/wiki/Authenticators).
@@ -150,7 +151,7 @@ We want our new user to be able to read the shadow passwords, so add it to the s
$ sudo usermod -a -G shadow rhea
```
If you want jupyterhub to serve pages on a restricted port (such as port 80 for http),
If you want jupyterhub to serve pages on a restricted port (such as port 80 for HTTP),
then you will need to give `node` permission to do so:
```bash
@@ -158,6 +159,7 @@ sudo setcap 'cap_net_bind_service=+ep' /usr/bin/node
```
However, you may want to further understand the consequences of this.
([Further reading](http://man7.org/linux/man-pages/man7/capabilities.7.html))
You may also be interested in limiting the amount of CPU any process can use
on your server. `cpulimit` is a useful tool that is available for many Linux
@@ -167,7 +169,8 @@ instructions](http://ubuntuforums.org/showthread.php?t=992706).
### Shadow group (FreeBSD)
**NOTE:** This has not been tested and may not work as expected.
**NOTE:** This has not been tested on FreeBSD and may not work as expected on
the FreeBSD platform. _Do not use in production without verifying that it works properly!_
```bash
$ ls -l /etc/spwd.db /etc/master.passwd
@@ -226,7 +229,7 @@ And try logging in.
## Troubleshooting: SELinux
If you still get a generic `Permission denied` `PermissionError`, it's possible SELinux is blocking you.
Here's how you can make a module to allow this.
Here's how you can make a module to resolve this.
First, put this in a file named `sudo_exec_selinux.te`:
```bash
@@ -253,6 +256,6 @@ $ semodule -i sudo_exec_selinux.pp
## Troubleshooting: PAM session errors
If the PAM authentication doesn't work and you see errors for
`login:session-auth`, or similar, considering updating to a more recent version
`login:session-auth`, or similar, consider updating to a more recent version
of jupyterhub and disabling the opening of PAM sessions with
`c.PAMAuthenticator.open_sessions=False`.

117
docs/source/reference/config-user-env.md
View File

@@ -1,49 +1,47 @@
# Configuring user environments
Deploying JupyterHub means you are providing Jupyter notebook environments for
To deploy JupyterHub means you are providing Jupyter notebook environments for
multiple users. Often, this includes a desire to configure the user
environment in some way.
environment in a custom way.
Since the `jupyterhub-singleuser` server extends the standard Jupyter notebook
server, most configuration and documentation that applies to Jupyter Notebook
applies to the single-user environments. Configuration of user environments
typically does not occur through JupyterHub itself, but rather through system-
wide configuration of Jupyter, which is inherited by `jupyterhub-singleuser`.
typically does not occur through JupyterHub itself, but rather through system-wide
configuration of Jupyter, which is inherited by `jupyterhub-singleuser`.
**Tip:** When searching for configuration tips for JupyterHub user
environments, try removing JupyterHub from your search because there are a lot
more people out there configuring Jupyter than JupyterHub and the
configuration is the same.
**Tip:** When searching for configuration tips for JupyterHub user environments, you might want to remove JupyterHub from your search because there are a lot more people out there configuring Jupyter than JupyterHub and the configuration is the same.
This section will focus on user environments, including:
This section will focus on user environments, which includes the following:
- Installing packages
- Configuring Jupyter and IPython
- Installing kernelspecs
- Using containers vs. multi-user hosts
- [Installing packages](#installing-packages)
- [Configuring Jupyter and IPython](#configuring-jupyter-and-ipython)
- [Installing kernelspecs](#installing-kernelspecs)
- [Using containers vs. multi-user hosts](#multi-user-hosts-vs-containers)
## Installing packages
To make packages available to users, you generally will install packages
system-wide or in a shared environment.
To make packages available to users, you will typically install packages system-wide or in a shared environment.
This installation location should always be in the same environment that
This installation location should always be in the same environment where
`jupyterhub-singleuser` itself is installed in, and must be _readable and
executable_ by your users. If you want users to be able to install additional
packages, it must also be _writable_ by your users.
executable_ by your users. If you want your users to be able to install additional
packages, the installation location must also be _writable_ by your users.
If you are using a standard system Python install, you would use:
If you are using a standard Python installation on your system, use the following command:
```bash
sudo python3 -m pip install numpy
```
to install the numpy package in the default system Python 3 environment
to install the numpy package in the default Python 3 environment on your system
(typically `/usr/local`).
You may also use conda to install packages. If you do, you should make sure
that the conda environment has appropriate permissions for users to be able to
run Python code in the env.
run Python code in the env. The env must be _readable and executable_ by all
users. Additionally it must be _writeable_ if you want users to install
additional packages.
## Configuring Jupyter and IPython
@@ -51,15 +49,9 @@ run Python code in the env.
and [IPython](https://ipython.readthedocs.io/en/stable/development/config.html)
have their own configuration systems.
As a JupyterHub administrator, you will typically want to install and configure
environments for all JupyterHub users. For example, you wish for each student in
a class to have the same user environment configuration.
Jupyter and IPython support **"system-wide"** locations for configuration, which
is the logical place to put global configuration that you want to affect all
users. It's generally more efficient to configure user environments "system-wide",
and it's a good idea to avoid creating files in users' home directories.
As a JupyterHub administrator, you will typically want to install and configure environments for all JupyterHub users. For example, let's say you wish for each student in a class to have the same user environment configuration.
Jupyter and IPython support **"system-wide"** locations for configuration, which is the logical place to put global configuration that you want to affect all users. It's generally more efficient to configure user environments "system-wide", and it's a good practice to avoid creating files in the users' home directories.
The typical locations for these config files are:
- **system-wide** in `/etc/{jupyter|ipython}`
@@ -67,8 +59,7 @@ The typical locations for these config files are:
### Example: Enable an extension system-wide
For example, to enable the `cython` IPython extension for all of your users,
create the file `/etc/ipython/ipython_config.py`:
For example, to enable the `cython` IPython extension for all of your users, create the file `/etc/ipython/ipython_config.py`:
```python
c.InteractiveShellApp.extensions.append("cython")
@@ -77,21 +68,18 @@ c.InteractiveShellApp.extensions.append("cython")
### Example: Enable a Jupyter notebook configuration setting for all users
:::{note}
These examples configure the Jupyter ServerApp,
which is used by JupyterLab, the default in JupyterHub 2.0.
These examples configure the Jupyter ServerApp, which is used by JupyterLab, the default in JupyterHub 2.0.
If you are using the classing Jupyter Notebook server,
the same things should work,
with the following substitutions:
- Where you see `jupyter_server_config`, use `jupyter_notebook_config`
- Where you see `NotebookApp`, use `ServerApp`
- Search for `jupyter_server_config`, and replace with `jupyter_notebook_config`
- Search for `NotebookApp`, and replace with `ServerApp`
:::
To enable Jupyter notebook's internal idle-shutdown behavior (requires
notebook ≥ 5.4), set the following in the `/etc/jupyter/jupyter_server_config.py`
file:
To enable Jupyter notebook's internal idle-shutdown behavior (requires notebook ≥ 5.4), set the following in the `/etc/jupyter/jupyter_server_config.py` file:
```python
# shutdown the server after no activity for an hour
@@ -104,16 +92,14 @@ c.MappingKernelManager.cull_interval = 2 * 60
## Installing kernelspecs
You may have multiple Jupyter kernels installed and want to make sure that
they are available to all of your users. This means installing kernelspecs
either system-wide (e.g. in /usr/local/) or in the `sys.prefix` of JupyterHub
You may have multiple Jupyter kernels installed and want to make sure that they are available to all of your users. This means installing kernelspecs either system-wide (e.g. in /usr/local/) or in the `sys.prefix` of JupyterHub
itself.
Jupyter kernelspec installation is system wide by default, but some kernels
Jupyter kernelspec installation is system-wide by default, but some kernels
may default to installing kernelspecs in your home directory. These will need
to be moved system-wide to ensure that they are accessible.
You can see where your kernelspecs are with:
To see where your kernelspecs are, you can use the following command:
```bash
jupyter kernelspec list
@@ -121,8 +107,7 @@ jupyter kernelspec list
### Example: Installing kernels system-wide
Assuming I have a Python 2 and Python 3 environment that I want to make
sure are available, I can install their specs system-wide (in /usr/local) with:
Let's assume that I have a Python 2 and Python 3 environment that I want to make sure are available, I can install their specs **system-wide** (in /usr/local) using the following command:
```bash
/path/to/python3 -m ipykernel install --prefix=/usr/local
@@ -141,31 +126,25 @@ How you configure user environments for each category can differ a bit
depending on what Spawner you are using.
The first category is a **shared system (multi-user host)** where
each user has a JupyterHub account and a home directory as well as being
each user has a JupyterHub account, a home directory as well as being
a real system user. In this example, shared configuration and installation
must be in a 'system-wide' location, such as `/etc/` or `/usr/local`
must be in a 'system-wide' location, such as `/etc/`, or `/usr/local`
or a custom prefix such as `/opt/conda`.
When JupyterHub uses **container-based** Spawners (e.g. KubeSpawner or
DockerSpawner), the 'system-wide' environment is really the container image
which you are using for users.
DockerSpawner), the 'system-wide' environment is really the container image used for users.
In both cases, you want to _avoid putting configuration in user home
directories_ because users can change those configuration settings. Also,
home directories typically persist once they are created, so they are
difficult for admins to update later.
directories_ because users can change those configuration settings. Also, home directories typically persist once they are created, thereby making it difficult for admins to update later.
## Named servers
By default, in a JupyterHub deployment each user has exactly one server.
By default, in a JupyterHub deployment, each user has one server only.
JupyterHub can, however, have multiple servers per user.
This is most useful in deployments where users can configure the environment
in which their server will start (e.g. resource requests on an HPC cluster),
so that a given user can have multiple configurations running at the same time,
without having to stop and restart their one server.
This is mostly useful in deployments where users can configure the environment in which their server will start (e.g. resource requests on an HPC cluster), so that a given user can have multiple configurations running at the same time, without having to stop and restart their own server.
To allow named servers:
To allow named servers, include this code snippet in your config file:
```python
c.JupyterHub.allow_named_servers = True
@@ -181,15 +160,15 @@ as well as the admin page:
![named servers on the admin page](../images/named-servers-admin.png)
Named servers can be accessed, created, started, stopped, and deleted
from these pages. Activity tracking is now per-server as well.
from these pages. Activity tracking is now per server as well.
The number of named servers per user can be limited by setting a constant value:
To limit the number of **named server** per user by setting a constant value, include this code snippet in your config file:
```python
c.JupyterHub.named_server_limit_per_user = 5
```
or a callable/awaitable based on the handler object:
Alternatively, to use a callable/awaitable based on the handler object, include this code snippet in your config file:
```python
def named_server_limit_per_user_fn(handler):
@@ -207,12 +186,13 @@ If `named_server_limit_per_user` is set to `0`, no limit is enforced.
(classic-notebook-ui)=
## Switching back to classic notebook
## Switching back to the classic notebook
By default the single-user server launches JupyterLab,
By default, the single-user server launches JupyterLab,
which is based on [Jupyter Server][].
This is the default server when running JupyterHub ≥ 2.0.
You can switch to using the legacy Jupyter Notebook server by setting the `JUPYTERHUB_SINGLEUSER_APP` environment variable
To switch to using the legacy Jupyter Notebook server, you can set the `JUPYTERHUB_SINGLEUSER_APP` environment variable
(in the single-user environment) to:
```bash
@@ -223,19 +203,20 @@ export JUPYTERHUB_SINGLEUSER_APP='notebook.notebookapp.NotebookApp'
[jupyter notebook]: https://jupyter-notebook.readthedocs.io
:::{versionchanged} 2.0
JupyterLab is now the default singleuser UI, if available,
JupyterLab is now the default single-user UI, if available,
which is based on the [Jupyter Server][],
no longer the legacy [Jupyter Notebook][] server.
JupyterHub prior to 2.0 launched the legacy notebook server (`jupyter notebook`),
and Jupyter server could be selected by specifying
and the Jupyter server could be selected by specifying the following:
```python
# jupyterhub_config.py
c.Spawner.cmd = ["jupyter-labhub"]
```
or for an otherwise customized Jupyter Server app,
set the environment variable:
Alternatively, for an otherwise customized Jupyter Server app,
set the environment variable using the following command:
```bash
export JUPYTERHUB_SINGLEUSER_APP='jupyter_server.serverapp.ServerApp'

142
docs/source/reference/oauth.md
View File

@@ -1,26 +1,26 @@
# JupyterHub and OAuth
JupyterHub uses OAuth 2 internally as a mechanism for authenticating users.
JupyterHub uses [OAuth 2](https://oauth.net/2/) as an internal mechanism for authenticating users.
As such, JupyterHub itself always functions as an OAuth **provider**.
More on what that means [below](oauth-terms).
You can find out more about what that means [below](oauth-terms).
Additionally, JupyterHub is _often_ deployed with [oauthenticator](https://oauthenticator.readthedocs.io),
Additionally, JupyterHub is _often_ deployed with [OAuthenticator](https://oauthenticator.readthedocs.io),
where an external identity provider, such as GitHub or KeyCloak, is used to authenticate users.
When this is the case, there are _two_ nested oauth flows:
an _internal_ oauth flow where JupyterHub is the **provider**,
and and _external_ oauth flow, where JupyterHub is a **client**.
When this is the case, there are _two_ nested OAuth flows:
an _internal_ OAuth flow where JupyterHub is the **provider**,
and an _external_ OAuth flow, where JupyterHub is the **client**.
This means that when you are using JupyterHub, there is always _at least one_ and often two layers of OAuth involved in a user logging in and accessing their server.
Some relevant points:
The following points are noteworthy:
- Single-user servers _never_ need to communicate with or be aware of the upstream provider configured in your Authenticator.
As far as they are concerned, only JupyterHub is an OAuth provider,
As far as the servers are concerned, only JupyterHub is an OAuth provider,
and how users authenticate with the Hub itself is irrelevant.
- When talking to a single-user server,
- When interacting with a single-user server,
there are ~always two tokens:
a token issued to the server itself to communicate with the Hub API,
and a second per-user token in the browser to represent the completed login process and authorized permissions.
first, a token issued to the server itself to communicate with the Hub API,
and second, a per-user token in the browser to represent the completed login process and authorized permissions.
More on this [later](two-tokens).
(oauth-terms)=
@@ -28,66 +28,66 @@ Some relevant points:
## Key OAuth terms
Here are some key definitions to keep in mind when we are talking about OAuth.
You can also read more detail [here](https://www.oauth.com/oauth2-servers/definitions/).
You can also read more in detail [here](https://www.oauth.com/oauth2-servers/definitions/).
- **provider** the entity responsible for managing identity and authorization,
- **provider**: The entity responsible for managing identity and authorization;
always a web server.
JupyterHub is _always_ an oauth provider for JupyterHub's components.
When OAuthenticator is used, an external service, such as GitHub or KeyCloak, is also an oauth provider.
- **client** An entity that requests OAuth **tokens** on a user's behalf,
JupyterHub is _always_ an OAuth provider for JupyterHub's components.
When OAuthenticator is used, an external service, such as GitHub or KeyCloak, is also an OAuth provider.
- **client**: An entity that requests OAuth **tokens** on a user's behalf;
generally a web server of some kind.
OAuth **clients** are services that _delegate_ authentication and/or authorization
to an OAuth **provider**.
JupyterHub _services_ or single-user _servers_ are OAuth **clients** of the JupyterHub **provider**.
When OAuthenticator is used, JupyterHub is itself _also_ an OAuth **client** for the external oauth **provider**, e.g. GitHub.
- **browser** A user's web browser, which makes requests and stores things like cookies
- **token** The secret value used to represent a user's authorization. This is the final product of the OAuth process.
- **code** A short-lived temporary secret that the **client** exchanges
for a **token** at the conclusion of oauth,
in what's generally called the "oauth callback handler."
When OAuthenticator is used, JupyterHub is itself _also_ an OAuth **client** for the external OAuth **provider**, e.g. GitHub.
- **browser**: A user's web browser, which makes requests and stores things like cookies.
- **token**: The secret value used to represent a user's authorization. This is the final product of the OAuth process.
- **code**: A short-lived temporary secret that the **client** exchanges
for a **token** at the conclusion of OAuth,
in what's generally called the "OAuth callback handler."
## One oauth flow
OAuth **flow** is what we call the sequence of HTTP requests involved in authenticating a user and issuing a token, ultimately used for authorized access to a service or single-user server.
OAuth **flow** is what we call the sequence of HTTP requests involved in authenticating a user and issuing a token, ultimately used for authorizing access to a service or single-user server.
A single oauth flow generally goes like this:
A single OAuth flow typically goes like this:
### OAuth request and redirect
1. A **browser** makes an HTTP request to an oauth **client**.
2. There are no credentials, so the client _redirects_ the browser to an "authorize" page on the oauth **provider** with some extra information:
- the oauth **client id** of the client itself
- the **redirect uri** to be redirected back to after completion
1. A **browser** makes an HTTP request to an OAuth **client**.
2. There are no credentials, so the client _redirects_ the browser to an "authorize" page on the OAuth **provider** with some extra information:
- the OAuth **client ID** of the client itself.
- the **redirect URI** to be redirected back to after completion.
- the **scopes** requested, which the user should be presented with to confirm.
This is the "X would like to be able to Y on your behalf. Allow this?" page you see on all the "Login with ..." pages around the Internet.
3. During this authorize step,
the browser must be _authenticated_ with the provider.
This is often already stored in a cookie,
but if not the provider webapp must begin its _own_ authentication process before serving the authorization page.
This _may_ even begin another oauth flow!
This _may_ even begin another OAuth flow!
4. After the user tells the provider that they want to proceed with the authorization,
the provider records this authorization in a short-lived record called an **oauth code**.
5. Finally, the oauth provider redirects the browser _back_ to the oauth client's "redirect uri"
(or "oauth callback uri"),
with the oauth code in a url parameter.
the provider records this authorization in a short-lived record called an **OAuth code**.
5. Finally, the oauth provider redirects the browser _back_ to the oauth client's "redirect URI"
(or "OAuth callback URI"),
with the OAuth code in a URL parameter.
That's the end of the requests made between the **browser** and the **provider**.
That marks the end of the requests made between the **browser** and the **provider**.
### State after redirect
At this point:
- The browser is authenticated with the _provider_
- The user's authorized permissions are recorded in an _oauth code_
- The _provider_ knows that the given oauth client's requested permissions have been granted, but the client doesn't know this yet.
- All requests so far have been made directly by the browser.
No requests have originated at the client or provider.
- The browser is authenticated with the _provider_.
- The user's authorized permissions are recorded in an _OAuth code_.
- The _provider_ knows that the permissions requested by the OAuth client have been granted, but the client doesn't know this yet.
- All the requests so far have been made directly by the browser.
No requests have originated from the client or provider.
### OAuth Client Handles Callback Request
Now we get to finish the OAuth process.
Let's dig into what the oauth client does when it handles
the oauth callback request with the
At this stage, we get to finish the OAuth process.
Let's dig into what the OAuth client does when it handles
the OAuth callback request.
- The OAuth client receives the _code_ and makes an API request to the _provider_ to exchange the code for a real _token_.
This is the first direct request between the OAuth _client_ and the _provider_.
@@ -95,12 +95,12 @@ the oauth callback request with the
makes a second API request to the _provider_
to retrieve information about the owner of the token (the user).
This is the step where behavior diverges for different OAuth providers.
Up to this point, all oauth providers are the same, following the oauth specification.
However, oauth does not define a standard for exchanging tokens for information about their owner or permissions ([OpenID Connect](https://openid.net/connect/) does that),
Up to this point, all OAuth providers are the same, following the OAuth specification.
However, OAuth does not define a standard for issuing tokens in exchange for information about their owner or permissions ([OpenID Connect](https://openid.net/connect/) does that),
so this step may be different for each OAuth provider.
- Finally, the oauth client stores its own record that the user is authorized in a cookie.
- Finally, the OAuth client stores its own record that the user is authorized in a cookie.
This could be the token itself, or any other appropriate representation of successful authentication.
- Last of all, now that credentials have been established,
- Now that credentials have been established,
the browser can be redirected to the _original_ URL where it started,
to try the request again.
If the client wasn't able to keep track of the original URL all this time
@@ -113,24 +113,24 @@ So that's _one_ OAuth process.
## Full sequence of OAuth in JupyterHub
Let's go through the above oauth process in JupyterHub,
with specific examples of each HTTP request and what information is contained.
For bonus points, we are using the double-oauth example of JupyterHub configured with GitHubOAuthenticator.
Let's go through the above OAuth process in JupyterHub,
with specific examples of each HTTP request and what information it contains.
For bonus points, we are using the double-OAuth example of JupyterHub configured with GitHubOAuthenticator.
To disambiguate, we will call the OAuth process where JupyterHub is the **provider** "internal oauth,"
and the one with JupyterHub as a **client** "external oauth."
To disambiguate, we will call the OAuth process where JupyterHub is the **provider** "internal OAuth,"
and the one with JupyterHub as a **client** "external OAuth."
Our starting point:
- a user's single-user server is running. Let's call them `danez`
- jupyterhub is running with GitHub as an oauth provider (this means two full instances of oauth),
- Danez has a fresh browser session with no cookies yet
- Jupyterhub is running with GitHub as an OAuth provider (this means two full instances of OAuth),
- Danez has a fresh browser session with no cookies yet.
First request:
- browser->single-user server running JupyterLab or Jupyter Classic
- `GET /user/danez/notebooks/mynotebook.ipynb`
- no credentials, so single-user server (as an oauth **client**) starts internal oauth process with JupyterHub (the **provider**)
- no credentials, so single-user server (as an OAuth **client**) starts internal OAuth process with JupyterHub (the **provider**)
- response: 302 redirect -> `/hub/api/oauth2/authorize`
with:
- client-id=`jupyterhub-user-danez`
@@ -138,9 +138,9 @@ First request:
Second request, following redirect:
- browser->jupyterhub
- browser->JupyterHub
- `GET /hub/api/oauth2/authorize`
- no credentials, so jupyterhub starts external oauth process _with GitHub_
- no credentials, so JupyterHub starts external OAuth process _with GitHub_
- response: 302 redirect -> `https://github.com/login/oauth/authorize`
with:
- client-id=`jupyterhub-client-uuid`
@@ -154,8 +154,8 @@ c.JupyterHub.authenticator_class = 'github'
```
That means authenticating a request to the Hub itself starts
a _second_, external oauth process with GitHub as a provider.
This external oauth process is optional, though.
a _second_, external OAuth process with GitHub as a provider.
This external OAuth process is optional, though.
If you were using the default username+password PAMAuthenticator,
this redirect would have been to `/hub/login` instead, to present the user
with a login form.
@@ -171,7 +171,7 @@ Here, GitHub prompts for login and asks for confirmation of authorization
After successful authorization
(either by looking up a pre-existing authorization,
or recording it via form submission)
GitHub issues an **oauth code** and redirects to `/hub/oauth_callback?code=github-code`
GitHub issues an **OAuth code** and redirects to `/hub/oauth_callback?code=github-code`
Next request:
@@ -184,7 +184,7 @@ The first:
- JupyterHub->GitHub
- `POST https://github.com/login/oauth/access_token`
- request made with oauth **code** from url parameter
- request made with OAuth **code** from URL parameter
- response includes an access **token**
The second:
@@ -194,9 +194,9 @@ The second:
- request made with access **token** in the `Authorization` header
- response is the user model, including username, email, etc.
Now the external oauth callback request completes with:
Now the external OAuth callback request completes with:
- set cookie on `/hub/` path, recording jupyterhub authentication so we don't need to do external oauth with GitHub again for a while
- set cookie on `/hub/` path, recording jupyterhub authentication so we don't need to do external OAuth with GitHub again for a while
- redirect -> `/hub/api/oauth2/authorize`
🎉 At this point, we have completed our first OAuth flow! 🎉
@@ -211,14 +211,14 @@ Now, we get our first repeated request:
2. automatically accepts authorization (shortcut taken when a user is visiting their own server)
- redirect -> `/user/danez/oauth_callback?code=jupyterhub-code`
Here, we start the same oauth callback process as before, but at Danez's single-user server for the _internal_ oauth
Here, we start the same OAuth callback process as before, but at Danez's single-user server for the _internal_ OAuth.
- browser->single-user server
- `GET /user/danez/oauth_callback`
(in handler)
Inside the internal oauth callback handler,
Inside the internal OAuth callback handler,
Danez's server makes two API requests to JupyterHub:
The first:
@@ -271,15 +271,15 @@ To handle this, OAuth tokens and the various places they are stored can _expire_
which should have the same effect as no credentials,
and trigger the authorization process again.
In JupyterHub's internal oauth, we have these layers of information that can go stale:
In JupyterHub's internal OAuth, we have these layers of information that can go stale:
- The oauth client has a **cache** of Hub responses for tokens,
- The OAuth client has a **cache** of Hub responses for tokens,
so it doesn't need to make API requests to the Hub for every request it receives.
This cache has an expiry of five minutes by default,
and is governed by the configuration `HubAuth.cache_max_age` in the single-user server.
- The internal oauth token is stored in a cookie, which has its own expiry (default: 14 days),
- The internal OAuth token is stored in a cookie, which has its own expiry (default: 14 days),
governed by `JupyterHub.cookie_max_age_days`.
- The internal oauth token can also itself expire,
- The internal OAuth token itself can also expire,
which is by default the same as the cookie expiry,
since it makes sense for the token itself and the place it is stored to expire at the same time.
This is governed by `JupyterHub.cookie_max_age_days` first,
@@ -317,9 +317,9 @@ triggering the external login process anew before letting a user proceed.
- If the token has expired, but is still in the cookie:
when the token response cache expires,
the next time the server asks the hub about the token,
no user will be identified and the internal oauth process begins again.
no user will be identified and the internal OAuth process begins again.
- If the token _cookie_ expires, the next browser request will be made with no credentials,
and the internal oauth process will begin again.
and the internal OAuth process will begin again.
This will usually have the form of a transparent redirect browsers won't notice.
However, if this occurs on an API request in a long-lived page visit
such as a JupyterLab session, the API request may fail and require
@@ -352,7 +352,7 @@ Logging out of JupyterHub means clearing and revoking many of these credentials:
### A tale of two tokens
**TODO**: discuss API token issued to server at startup ($JUPYTERHUB_API_TOKEN)
and oauth-issued token in the cookie,
and OAuth-issued token in the cookie,
and some details of how JupyterLab currently deals with that.
They are different, and JupyterLab should be making requests using the token from the cookie,
not the token from the server,

15
docs/source/reference/proxy.md
View File

@@ -7,9 +7,12 @@ Hub manages by default as a subprocess (it can be run externally, as well, and
typically is in production deployments).
The upside to CHP, and why we use it by default, is that it's easy to install
and run (if you have nodejs, you are set!). The downsides are that it's a
single process and does not support any persistence of the routing table. So
if the proxy process dies, your whole JupyterHub instance is inaccessible
and run (if you have nodejs, you are set!). The downsides are that
- it's a single process and
- does not support any persistence of the routing table.
So if the proxy process dies, your whole JupyterHub instance is inaccessible
until the Hub notices, restarts the proxy, and restores the routing table. For
deployments that want to avoid such a single point of failure, or leverage
existing proxy infrastructure in their chosen deployment (such as Kubernetes
@@ -138,7 +141,7 @@ async def delete_route(self, routespec):
For retrieval, you only _need_ to implement a single method that retrieves all
routes. The return value for this function should be a dictionary, keyed by
`routespect`, of dicts whose keys are the same three arguments passed to
`routespec`, of dicts whose keys are the same three arguments passed to
`add_route` (`routespec`, `target`, `data`)
```python
@@ -204,7 +207,7 @@ setup(
```
If you have added this metadata to your package,
users can select your proxy with the configuration:
admins can select your authenticator with the configuration:
```python
c.JupyterHub.proxy_class = 'mything'
@@ -216,7 +219,7 @@ instead of the full
c.JupyterHub.proxy_class = 'mypackage:MyProxy'
```
previously required.
as previously required.
Additionally, configurable attributes for your proxy will
appear in jupyterhub help output and auto-generated configuration files
via `jupyterhub --generate-config`.

94
docs/source/reference/rest.md
View File

@@ -4,33 +4,36 @@
This section will give you information on:
- what you can do with the API
- create an API token
- add API tokens to the config files
- make an API request programmatically using the requests library
- learn more about JupyterHub's API
- What you can do with the API
- How to create an API token
- Assigning permissions to a token
- Updating to admin services
- Making an API request programmatically using the requests library
- Paginating API requests
- Enabling users to spawn multiple named-servers via the API
- Learn more about JupyterHub's API
Before we discuss about JupyterHub's REST API, you can learn about [REST APIs here](https://en.wikipedia.org/wiki/Representational_state_transfer). A REST
API provides a standard way for users to get and send information to the
Hub.
## What you can do with the API
Using the [JupyterHub REST API][], you can perform actions on the Hub,
such as:
- checking which users are active
- adding or removing users
- stopping or starting single user notebook servers
- authenticating services
- communicating with an individual Jupyter server's REST API
A [REST](https://en.wikipedia.org/wiki/Representational_state_transfer)
API provides a standard way for users to get and send information to the
Hub.
- Checking which users are active
- Adding or removing users
- Stopping or starting single user notebook servers
- Authenticating services
- Communicating with an individual Jupyter server's REST API
## Create an API token
To send requests using JupyterHub API, you must pass an API token with
To send requests using the JupyterHub API, you must pass an API token with
the request.
The preferred way of generating an API token is:
The preferred way of generating an API token is by running:
```bash
openssl rand -hex 32
@@ -40,8 +43,12 @@ This `openssl` command generates a potential token that can then be
added to JupyterHub using `.api_tokens` configuration setting in
`jupyterhub_config.py`.
Alternatively, use the `jupyterhub token` command to generate a token
for a specific hub user by passing the 'username':
```{note}
The api_tokens configuration has been softly deprecated since the introduction of services.
```
Alternatively, you can use the `jupyterhub token` command to generate a token
for a specific hub user by passing the **username**:
```bash
jupyterhub token <username>
@@ -53,9 +60,19 @@ it for the given user with the Hub's database.
In [version 0.8.0](../changelog.md), a token request page for
generating an API token is available from the JupyterHub user interface:
![Request API token page](../images/token-request.png)
:::{figure-md}
![API token success page](../images/token-request-success.png)
![token request page](../images/token-request.png)
JupyterHub's API token page
:::
:::{figure-md}
![token-request-success](../images/token-request-success.png)
JupyterHub's token page after successfully requesting a token.
:::
## Assigning permissions to a token
@@ -67,25 +84,26 @@ Prior to JupyterHub 2.0, there were two levels of permissions:
where a token would always have full permissions to do whatever its owner could do.
In JupyterHub 2.0,
specific permissions are now defined as 'scopes',
specific permissions are now defined as '**scopes**',
and can be assigned both at the user/service level,
and at the individual token level.
This allows e.g. a user with full admin permissions to request a token with limited permissions.
### Updating to admin services
## Updating to admin services
```{note}
The `api_tokens` configuration has been softly deprecated since the introduction of services.
We have no plans to remove it,
but deployments are encouraged to use service configuration instead.
```
If you have been using `api_tokens` to create an admin user
and a token for that user to perform some automations,
the services mechanism may be a better fit.
If you have the following configuration:
and the token for that user to perform some automations, then
the services' mechanism may be a better fit if you have the following configuration:
```python
c.JupyterHub.admin_users = {"service-admin",}
c.JupyterHub.admin_users = {"service-admin"}
c.JupyterHub.api_tokens = {
"secret-token": "service-admin",
}
@@ -103,9 +121,8 @@ c.JupyterHub.services = [
},
]
# roles are new in JupyterHub 2.0
# prior to 2.0, only 'admin': True or False
# was available
# roles were introduced in JupyterHub 2.0
# prior to 2.0, only "admin": True or False was available
c.JupyterHub.load_roles = [
{
@@ -125,7 +142,7 @@ c.JupyterHub.load_roles = [
The token will have the permissions listed in the role
(see [scopes][] for a list of available permissions),
but there will no longer be a user account created to house it.
The main noticeable difference is that there will be no notebook server associated with the account
The main noticeable difference between a user and a service is that there will be no notebook server associated with the account
and the service will not show up in the various user list pages and APIs.
## Make an API request
@@ -136,9 +153,8 @@ Authorization header.
### Use requests
Using the popular Python [requests](https://docs.python-requests.org)
library, here's example code to make an API request for the users of a JupyterHub
deployment. An API GET request is made, and the request sends an API token for
authorization. The response contains information about the users:
library, an API GET request is made, and the request sends an API token for
authorization. The response contains information about the users, here's example code to make an API request for the users of a JupyterHub deployment
```python
import requests
@@ -176,7 +192,8 @@ r.json()
```
The same API token can also authorize access to the [Jupyter Notebook REST API][]
provided by notebook servers managed by JupyterHub if it has the necessary `access:users:servers` scope:
provided by notebook servers managed by JupyterHub if it has the necessary `access:servers` scope.
(api-pagination)=
@@ -245,7 +262,7 @@ with your request, in which case a response will look like:
where the list results (same as pre-2.0) will be in `items`,
and pagination info will be in `_pagination`.
The `next` field will include the offset, limit, and URL for requesting the next page.
The `next` field will include the `offset`, `limit`, and `url` for requesting the next page.
`next` will be `null` if there is no next page.
Pagination is governed by two configuration options:
@@ -259,7 +276,7 @@ Pagination is enabled on the `GET /users`, `GET /groups`, and `GET /proxy` REST
## Enabling users to spawn multiple named-servers via the API
With JupyterHub version 0.8, support for multiple servers per user has landed.
Support for multiple servers per user was introduced in JupyterHub [version 0.8.](../changelog.md)
Prior to that, each user could only launch a single default server via the API
like this:
@@ -275,7 +292,7 @@ First you must enable named-servers by including the following setting in the `j
`c.JupyterHub.allow_named_servers = True`
If using the [zero-to-jupyterhub-k8s](https://github.com/jupyterhub/zero-to-jupyterhub-k8s) set-up to run JupyterHub,
If you are using the [zero-to-jupyterhub-k8s](https://github.com/jupyterhub/zero-to-jupyterhub-k8s) set-up to run JupyterHub,
then instead of editing the `jupyterhub_config.py` file directly, you could pass
the following as part of the `config.yaml` file, as per the [tutorial](https://zero-to-jupyterhub.readthedocs.io/en/latest/):
@@ -303,8 +320,9 @@ or kubernetes pods.
## Learn more about the API
You can see the full [JupyterHub REST API][] for details.
You can see the full [JupyterHub REST API][] for more details.
[openapi initiative]: https://www.openapis.org/
[jupyterhub rest api]: ./rest-api
[scopes]: ../rbac/scopes.md
[jupyter notebook rest api]: https://petstore3.swagger.io/?url=https://raw.githubusercontent.com/jupyter/notebook/HEAD/notebook/services/api/api.yaml

32
docs/source/reference/separate-proxy.md
View File

@@ -2,7 +2,7 @@
## Background
The thing which users directly connect to is the proxy, by default
The thing which users directly connect to is the proxy, which by default is
`configurable-http-proxy`. The proxy either redirects users to the
hub (for login and managing servers), or to their own single-user
servers. Thus, as long as the proxy stays running, access to existing
@@ -10,16 +10,15 @@ servers continues, even if the hub itself restarts or goes down.
When you first configure the hub, you may not even realize this
because the proxy is automatically managed by the hub. This is great
for getting started and even most use, but everytime you restart the
hub, all user connections also get restarted. But it's also simple to
for getting started and even most use-cases, although, everytime you restart the
hub, all user connections are also restarted. However, it is also simple to
run the proxy as a service separate from the hub, so that you are free
to reconfigure the hub while only interrupting users who are currently
actively starting the hub.
to reconfigure the hub while only interrupting users who are waiting for their notebook server to start.
starting their notebook server.
The default JupyterHub proxy is
[configurable-http-proxy](https://github.com/jupyterhub/configurable-http-proxy),
and that page has some docs. If you are using a different proxy, such
as Traefik, these instructions are probably not relevant to you.
[configurable-http-proxy](https://github.com/jupyterhub/configurable-http-proxy). If you are using a different proxy, such
as [Traefik](https://github.com/traefik/traefik), these instructions are probably not relevant to you.
## Configuration options
@@ -40,9 +39,14 @@ set to the URL which the hub uses to connect _to the proxy's API_.
## Proxy configuration
You need to configure a service to start the proxy. An example
command line for this is `configurable-http-proxy --ip=127.0.0.1 --port=8000 --api-ip=127.0.0.1 --api-port=8001 --default-target=http://localhost:8081 --error-target=http://localhost:8081/hub/error`. (Details for how to
do this is out of scope for this tutorial - for example it might be a
systemd service on within another docker cotainer). The proxy has no
command line argument for this is:
```bash
$ configurable-http-proxy --ip=127.0.0.1 --port=8000 --api-ip=127.0.0.1 --api-port=8001 --default-target=http://localhost:8081 --error-target=http://localhost:8081/hub/error
```
(Details on how to do this is out of the scope of this tutorial. For example, it might be a
systemd service configured within another docker container). The proxy has no
configuration files, all configuration is via the command line and
environment variables.
@@ -57,9 +61,9 @@ match the token given to `c.ConfigurableHTTPProxy.auth_token`.
You should check the [configurable-http-proxy
options](https://github.com/jupyterhub/configurable-http-proxy) to see
what other options are needed, for example SSL options. Note that
these are configured in the hub if the hub is starting the proxy - you
need to move the options to here.
what other options are needed, for example, SSL options. Note that
these options are configured in the hub if the hub is starting the proxy, so you
need to configure the options there.
## Docker image

179
docs/source/reference/server-api.md
View File

@@ -1,37 +1,32 @@
# Starting servers with the JupyterHub API
JupyterHub's [REST API][] allows launching servers on behalf of users
without ever interacting with the JupyterHub UI.
This allows you to build services launching Jupyter-based services for users
without relying on the JupyterHub UI at all,
enabling a variety of user/launch/lifecycle patterns not natively supported by JupyterHub,
without needing to develop all the server management features of JupyterHub Spawners and/or Authenticators.
[BinderHub][] is an example of such an application.
Sometimes, when working with applications such as [BinderHub](https://binderhub.readthedocs.io), it may be necessary to launch Jupyter-based services on behalf of your users.
Doing so can be achieved through JupyterHub's [REST API](../reference/rest.md), which allows one to launch and manage servers on behalf of users through API calls instead of the JupyterHub UI.
This way, you can take advantage of other user/launch/lifecycle patterns that are not natively supported by the JupyterHub UI, all without the need to develop the server management features of JupyterHub Spawners and/or Authenticators.
[binderhub]: https://binderhub.readthedocs.io
[rest api]: ../reference/rest.md
This tutorial goes through working with the JupyterHub API to manage servers for users.
In particular, it covers how to:
This document provides an example of working with the JupyterHub API to
manage servers for users.
In particular, we will cover how to:
1. [Check the status of servers](checking)
2. [Start servers](starting)
3. [Wait for servers to be ready](waiting)
4. [Communicate with servers](communicating)
5. [Stop servers](stopping)
1. [check status of servers](checking)
2. [start servers](starting)
3. [wait for servers to be ready](waiting)
4. [communicate with servers](communicating)
5. [stop servers](stopping)
At the end, we also provide sample Python code that can be used to implement these steps.
(checking)=
## Checking server status
Requesting information about a user includes a `servers` field,
which is a dictionary.
First, request information about a particular user using a GET request:
```
GET /hub/api/users/:username
```
The response you get will include a `servers` field, which is a dictionary, as shown in this JSON-formatted response:
**Required scope: `read:servers`**
```json
@@ -49,13 +44,9 @@ GET /hub/api/users/:username
}
```
If the `servers` dict is empty, the user has no running servers.
The keys of the `servers` dict are server names as strings.
Many JupyterHub deployments only use the 'default' server,
which has the empty string `''` for a name.
In this case, the servers dict will always have either zero or one elements.
Many JupyterHub deployments only use a 'default' server, represented as an empty string `''` for a name. An investigation of the `servers` field can yield one of two results. First, it can be empty as in the sample JSON response above. In such a case, the user has no running servers.
This is the servers dict when the user's default server is fully running and ready:
However, should the user have running servers, then the returned dict should contain various information, as shown in this response:
```json
"servers": {
@@ -75,34 +66,28 @@ This is the servers dict when the user's default server is fully running and rea
Key properties of a server:
name
: the server's name. Always the same as the key in `servers`
: the server's name. Always the same as the key in `servers`.
ready
: boolean. If true, the server can be expected to respond to requests at `url`.
pending
: `null` or a string indicating a transitional state (such as `start` or `stop`).
Will always be `null` if `ready` is true,
and will always be a string if `ready` is false.
Will always be `null` if `ready` is true or a string if false.
url
: The server's url (just the path, e.g. `/users/:name/:servername/`)
where the server can be accessed if `ready` is true.
: The server's url path (e.g. `/users/:name/:servername/`) where the server can be accessed if `ready` is true.
progress_url
: The API url path (starting with `/hub/api`)
where the progress API can be used to wait for the server to be ready.
See below for more details on the progress API.
: The API URL path (starting with `/hub/api`) where the progress API can be used to wait for the server to be ready.
last_activity
: ISO8601 timestamp indicating when activity was last observed on the server
: ISO8601 timestamp indicating when activity was last observed on the server.
started
: ISO801 timestamp indicating when the server was last started
: ISO801 timestamp indicating when the server was last started.
We've seen the `servers` model with no servers and with one `ready` server.
Here is what it looks like immediately after requesting a server launch,
while the server is not ready yet:
The two responses above are from a user with no servers and another with one `ready` server. The sample below is a response likely to be received when one requests a server launch while the server is not yet ready:
```json
"servers": {
@@ -119,11 +104,7 @@ while the server is not ready yet:
}
```
Note that `ready` is false and `pending` is `spawn`.
This means that the server is not ready
(attempting to access it may not work)
because it isn't finished spawning yet.
We'll get more into that below in [waiting for a server][].
Note that `ready` is `false` and `pending` has the value `spawn`, meaning that the server is not ready and attempting to access it may not work as it is still in the process of spawning. We'll get more into this below in [waiting for a server][].
[waiting for a server]: waiting
@@ -131,7 +112,7 @@ We'll get more into that below in [waiting for a server][].
## Starting servers
To start a server, make the request
To start a server, make this API request:
```
POST /hub/api/users/:username/servers/[:servername]
@@ -139,47 +120,35 @@ POST /hub/api/users/:username/servers/[:servername]
**Required scope: `servers`**
(omit servername for the default server)
Assuming the request was valid,
there are two possible responses:
Assuming the request was valid, there are two possible responses:
201 Created
: This status code means the launch completed and the server is ready.
It should be available at the server's URL immediately.
: This status code means the launch completed and the server is ready and is available at the server's URL immediately.
202 Accepted
: This is the more likely response,
and means that the server has begun launching,
but isn't immediately ready.
The server has `pending: 'spawn'` at this point.
_Aside: how quickly JupyterHub responds with `202 Accepted` is governed by the `slow_spawn_timeout` tornado setting._
: This is the more likely response, and means that the server has begun launching,
but is not immediately ready. As a result, the server shows `pending: 'spawn'` at this point and you should wait for it to start.
(waiting)=
## Waiting for a server
## Waiting for a server to start
If you are starting a server via the API,
there's a good change you want to know when it's ready.
There are two ways to do with:
After receiving a `202 Accepted` response, you have to wait for the server to start.
Two approaches can be applied to establish when the server is ready:
1. {ref}`Polling the server model <polling>`
2. the {ref}`progress API <progress>`
2. {ref}`Using the progress API <progress>`
(polling)=
### Polling the server model
The simplest way to check if a server is ready
is to request the user model.
The simplest way to check if a server is ready is to programmatically query the server model until two conditions are true:
If:
1. The server name is contained in the `servers` response, and
2. `servers['servername']['ready']` is true.
1. the server name is in the user's `servers` model, and
2. `servers['servername']['ready']` is true
A Python example, checking if a server is ready:
The Python code snippet below can be used to check if a server is ready:
```python
def server_ready(hub_url, user, server_name="", token):
@@ -206,14 +175,12 @@ You can keep making this check until `ready` is true.
(progress)=
### Progress API
### Using the progress API
The most _efficient_ way to wait for a server to start is the progress API.
The most _efficient_ way to wait for a server to start is by using the progress API.
The progress URL is available in the server model under `progress_url` and has the form `/hub/api/users/:user/servers/:servername/progress`.
The progress URL is available in the server model under `progress_url`,
and has the form `/hub/api/users/:user/servers/:servername/progress`.
_the default server progress can be accessed at `:user/servers//progress` or `:user/server/progress`_
The default server progress can be accessed at `:user/servers//progress` or `:user/server/progress` as demonstrated in the following GET request:
```
GET /hub/api/users/:user/servers/:servername/progress
@@ -221,8 +188,8 @@ GET /hub/api/users/:user/servers/:servername/progress
**Required scope: `read:servers`**
This is an [EventStream][] API.
In an event stream, messages are _streamed_ and delivered on lines of the form:
The progress API is an example of an [EventStream][] API.
Messages are _streamed_ and delivered in the form:
```
data: {"progress": 10, "message": "...", ...}
@@ -233,7 +200,7 @@ Lines that do not start with `data:` should be ignored.
[eventstream]: https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#examples
progress events have the form:
Progress events have the form:
```python
{
@@ -254,11 +221,10 @@ ready
: present and true only for the last event when the server is ready
url
: only present if `ready` is true; will be the server's url
: only present if `ready` is true; will be the server's URL
the progress API can be used even with fully ready servers.
If the server is ready,
there will only be one event that looks like:
The progress API can be used even with fully ready servers.
If the server is ready, there will only be one event, which will look like:
```json
{
@@ -270,9 +236,10 @@ there will only be one event that looks like:
}
```
where `ready` and `url` are the same as in the server model (`ready` will always be true).
where `ready` and `url` are the same as in the server model, and `ready` will always be true.
A typical complete stream from the event-stream API:
A significant advantage of the progress API is that it shows the status of the server through a stream of messages.
Below is an example of a typical complete stream from the API:
```
@@ -302,21 +269,21 @@ DELETE /hub/api/users/:user/servers/[:servername]
**Required scope: `servers`**
Like start, delete may not complete immediately.
The DELETE request has two possible response codes:
Similar to when starting a server, issuing the DELETE request above might not stop the server immediately.
Instead, the DELETE request has two possible response codes:
204 Deleted
: This status code means the delete completed and the server is fully stopped.
It will now be absent from the user `servers` model.
202 Accepted
: Like start, `202` means your request was accepted,
but is not yet complete.
: This code means your request was accepted but is not yet completely processed.
The server has `pending: 'stop'` at this point.
Unlike start, there is no progress API for stop.
To wait for stop to finish, you must poll the user model
and wait for the server to disappear from the user `servers` model.
There is no progress API for checking when a server actually stops.
The only way to wait for a server to stop is to poll it and wait for the server to disappear from the user `servers` model.
This Python code snippet can be used to stop a server and the wait for the process to complete:
```{literalinclude} ../../../examples/server-api/start-stop-server.py
:language: python
@@ -327,9 +294,8 @@ and wait for the server to disappear from the user `servers` model.
## Communicating with servers
JupyterHub tokens with the the `access:servers` scope
can be used to communicate with servers themselves.
This can be the same token you used to launch your service.
JupyterHub tokens with the `access:servers` scope can be used to communicate with servers themselves.
The tokens can be the same as those you used to launch your service.
```{note}
Access scopes are new in JupyterHub 2.0.
@@ -338,29 +304,26 @@ a token must be owned by the same user as the server,
*or* be an admin token if admin_access is enabled.
```
The URL returned from a server model is the url path suffix,
The URL returned from a server model is the URL path suffix,
e.g. `/user/:name/` to append to the jupyterhub base URL.
For instance, `{hub_url}{server_url}`,
where `hub_url` would be e.g. `http://127.0.0.1:8000` by default,
and `server_url` `/user/myname`,
for a full url of `http://127.0.0.1:8000/user/myname`.
The returned URL is of the form `{hub_url}{server_url}`,
where `hub_url` would be `http://127.0.0.1:8000` by default and `server_url` is `/user/myname`.
When combined, the two give a full URL of `http://127.0.0.1:8000/user/myname`.
## Python example
The JupyterHub repo includes a complete example in {file}`examples/server-api`
tying all this together.
that ties all theses steps together.
To summarize the steps:
In summary, the processes involved in managing servers on behalf of users are:
1. get user info from `/user/:name`
2. the server model includes a `ready` state to tell you if it's ready
3. if it's not ready, you can follow up with `progress_url` to wait for it
4. if it is ready, you can use the `url` field to link directly to the running server
1. Get user information from `/user/:name`.
2. The server model includes a `ready` state to tell you if it's ready.
3. If it's not ready, you can follow up with `progress_url` to wait for it.
4. If it is ready, you can use the `url` field to link directly to the running server.
The example demonstrates starting and stopping servers via the JupyterHub API,
including waiting for them to start via the progress API,
as well as waiting for them to stop via polling the user model.
The example below demonstrates starting and stopping servers via the JupyterHub API,
including waiting for them to start via the progress API and waiting for them to stop by polling the user model.
```{literalinclude} ../../../examples/server-api/start-stop-server.py
:language: python

23
docs/source/reference/services.md
View File

@@ -61,7 +61,7 @@ If a service is also to be managed by the Hub, it has a few extra options:
A **Hub-Managed Service** is started by the Hub, and the Hub is responsible
for the Service's actions. A Hub-Managed Service can only be a local
subprocess of the Hub. The Hub will take care of starting the process and
restarts it if it stops.
restart the service if the service stops.
While Hub-Managed Services share some similarities with notebook Spawners,
there are no plans for Hub-Managed Services to support the same spawning
@@ -186,7 +186,7 @@ information to the Service via the environment variables described above. A
flexible Service, whether managed by the Hub or not, can make use of these
same environment variables.
When you run a service that has a url, it will be accessible under a
When you run a service that has a URL, it will be accessible under a
`/services/` prefix, such as `https://myhub.horse/services/my-service/`. For
your service to route proxied requests properly, it must take
`JUPYTERHUB_SERVICE_PREFIX` into account when routing requests. For example, a
@@ -234,8 +234,17 @@ There are two levels of authentication with the Hub:
- {class}`.HubOAuth` - For services that should use oauth to authenticate with the Hub.
This should be used for any service that serves pages that should be visited with a browser.
To use HubAuth, you must set the `.api_token`, either programmatically when constructing the class,
or via the `JUPYTERHUB_API_TOKEN` environment variable.
To use HubAuth, you must set the `.api_token` instance variable. This can be
done either programmatically when constructing the class, or via the
`JUPYTERHUB_API_TOKEN` environment variable. A number of the examples in the
root of the jupyterhub git repository set the `JUPYTERHUB_API_TOKEN` variable
so consider having a look at those for futher reading
([cull-idle](https://github.com/jupyterhub/jupyterhub/tree/master/examples/cull-idle),
[external-oauth](https://github.com/jupyterhub/jupyterhub/tree/master/examples/external-oauth),
[service-notebook](https://github.com/jupyterhub/jupyterhub/tree/master/examples/service-notebook)
and [service-whoiami](https://github.com/jupyterhub/jupyterhub/tree/master/examples/service-whoami))
(TODO: Where is this API TOKen set?)
Most of the logic for authentication implementation is found in the
{meth}`.HubAuth.user_for_token` methods,
@@ -249,7 +258,7 @@ which makes a request of the Hub, and returns:
"name": "username",
"groups": ["list", "of", "groups"],
"scopes": [
"access:users:servers!server=username/",
"access:servers!server=username/",
],
}
```
@@ -268,7 +277,7 @@ you can access the token authenticating the current request with {meth}`.HubAuth
:::{versionchanged} 2.2
{meth}`.HubAuth.get_token` adds support for retrieving
tokens stored in tornado cookies after completion of OAuth.
tokens stored in tornado cookies after the completion of OAuth.
Previously, it only retrieved tokens from URL parameters or the Authorization header.
Passing `get_token(handler, in_cookie=False)` preserves this behavior.
:::
@@ -391,7 +400,7 @@ in which case the `scopes` field in this model should be checked on each access.
The default required scopes for access are available from `hub_auth.oauth_scopes` or `$JUPYTERHUB_OAUTH_ACCESS_SCOPES`.
An example of using an Externally-Managed Service and authentication is
in [nbviewer README][nbviewer example] section on securing the notebook viewer,
in the [nbviewer README][nbviewer example] section on securing the notebook viewer,
and an example of its configuration is found [here](https://github.com/jupyter/nbviewer/blob/ed942b10a52b6259099e2dd687930871dc8aac22/nbviewer/providers/base.py#L95).
nbviewer can also be run as a Hub-Managed Service as described [nbviewer README][nbviewer example]
section on securing the notebook viewer.

84
docs/source/reference/spawners.md
View File

@@ -4,9 +4,9 @@ A [Spawner][] starts each single-user notebook server.
The Spawner represents an abstract interface to a process,
and a custom Spawner needs to be able to take three actions:
- start the process
- poll whether the process is still running
- stop the process
- start a process
- poll whether a process is still running
- stop a process
## Examples
@@ -15,9 +15,9 @@ Some examples include:
- [DockerSpawner](https://github.com/jupyterhub/dockerspawner) for spawning user servers in Docker containers
- `dockerspawner.DockerSpawner` for spawning identical Docker containers for
each users
each user
- `dockerspawner.SystemUserSpawner` for spawning Docker containers with an
environment and home directory for each users
environment and home directory for each user
- both `DockerSpawner` and `SystemUserSpawner` also work with Docker Swarm for
launching containers on remote machines
- [SudoSpawner](https://github.com/jupyterhub/sudospawner) enables JupyterHub to
@@ -34,7 +34,7 @@ Some examples include:
### Spawner.start
`Spawner.start` should start the single-user server for a single user.
`Spawner.start` should start a single-user server for a single user.
Information about the user can be retrieved from `self.user`,
an object encapsulating the user's name, authentication, and server info.
@@ -69,13 +69,13 @@ via relaxing the `Spawner.start_timeout` config value.
#### Note on IPs and ports
`Spawner.ip` and `Spawner.port` attributes set the _bind_ url,
`Spawner.ip` and `Spawner.port` attributes set the _bind_ URL,
which the single-user server should listen on
(passed to the single-user process via the `JUPYTERHUB_SERVICE_URL` environment variable).
The _return_ value is the ip and port (or full url) the Hub should _connect to_.
The _return_ value is the IP and port (or full URL) the Hub should _connect to_.
These are not necessarily the same, and usually won't be in any Spawner that works with remote resources or containers.
The default for Spawner.ip, and Spawner.port is `127.0.0.1:{random}`,
The default for `Spawner.ip`, and `Spawner.port` is `127.0.0.1:{random}`,
which is appropriate for Spawners that launch local processes,
where everything is on localhost and each server needs its own port.
For remote or container Spawners, it will often make sense to use a different value,
@@ -111,7 +111,7 @@ class MySpawner(Spawner):
#### Exception handling
When `Spawner.start` raises an Exception, a message can be passed on to the user via the exception via a `.jupyterhub_html_message` or `.jupyterhub_message` attribute.
When `Spawner.start` raises an Exception, a message can be passed on to the user via the exception using a `.jupyterhub_html_message` or `.jupyterhub_message` attribute.
When the Exception has a `.jupyterhub_html_message` attribute, it will be rendered as HTML to the user.
@@ -121,11 +121,11 @@ If both attributes are not present, the Exception will be shown to the user as u
### Spawner.poll
`Spawner.poll` should check if the spawner is still running.
`Spawner.poll` checks if the spawner is still running.
It should return `None` if it is still running,
and an integer exit status, otherwise.
For the local process case, `Spawner.poll` uses `os.kill(PID, 0)`
In the case of local processes, `Spawner.poll` uses `os.kill(PID, 0)`
to check if the local process is still running. On Windows, it uses `psutil.pid_exists`.
### Spawner.stop
@@ -141,7 +141,7 @@ A JSON-able dictionary of state can be used to store persisted information.
Unlike start, stop, and poll methods, the state methods must not be coroutines.
For the single-process case, the Spawner state is only the process ID of the server:
In the case of single processes, the Spawner state is only the process ID of the server:
```python
def get_state(self):
@@ -267,8 +267,8 @@ Spawners mainly do one thing: launch a command in an environment.
The command-line is constructed from user configuration:
- Spawner.cmd (default: `['jupterhub-singleuser']`)
- Spawner.args (cli args to pass to the cmd, default: empty)
- Spawner.cmd (default: `['jupyterhub-singleuser']`)
- Spawner.args (CLI args to pass to the cmd, default: empty)
where the configuration:
@@ -283,7 +283,7 @@ would result in spawning the command:
my-singleuser-wrapper --debug --flag
```
The `Spawner.get_args()` method is how Spawner.args is accessed,
The `Spawner.get_args()` method is how `Spawner.args` is accessed,
and can be used by Spawners to customize/extend user-provided arguments.
Prior to 2.0, JupyterHub unconditionally added certain options _if specified_ to the command-line,
@@ -297,36 +297,36 @@ Additional variables can be specified via the `Spawner.environment` configuratio
The process environment is returned by `Spawner.get_env`, which specifies the following environment variables:
- JUPYTERHUB*SERVICE_URL - the \_bind* url where the server should launch its http server (`http://127.0.0.1:12345`).
This includes Spawner.ip and Spawner.port; _new in 2.0, prior to 2.0 ip,port were on the command-line and only if specified_
- JUPYTERHUB*SERVICE_URL - the \_bind* URL where the server should launch its HTTP server (`http://127.0.0.1:12345`).
This includes `Spawner.ip` and `Spawner.port`; _new in 2.0, prior to 2.0 IP, port were on the command-line and only if specified_
- JUPYTERHUB_SERVICE_PREFIX - the URL prefix the service will run on (e.g. `/user/name/`)
- JUPYTERHUB_USER - the JupyterHub user's username
- JUPYTERHUB_SERVER_NAME - the server's name, if using named servers (default server has an empty name)
- JUPYTERHUB_API_URL - the full url for the JupyterHub API (http://17.0.0.1:8001/hub/api)
- JUPYTERHUB_BASE_URL - the base url of the whole jupyterhub deployment, i.e. the bit before `hub/` or `user/`,
as set by c.JupyterHub.base_url (default: `/`)
- JUPYTERHUB_API_URL - the full URL for the JupyterHub API (http://17.0.0.1:8001/hub/api)
- JUPYTERHUB_BASE_URL - the base URL of the whole jupyterhub deployment, i.e. the bit before `hub/` or `user/`,
as set by `c.JupyterHub.base_url` (default: `/`)
- JUPYTERHUB_API_TOKEN - the API token the server can use to make requests to the Hub.
This is also the OAuth client secret.
- JUPYTERHUB_CLIENT_ID - the OAuth client ID for authenticating visitors.
- JUPYTERHUB_OAUTH_CALLBACK_URL - the callback URL to use in oauth, typically `/user/:name/oauth_callback`
- JUPYTERHUB_OAUTH_CALLBACK_URL - the callback URL to use in OAuth, typically `/user/:name/oauth_callback`
- JUPYTERHUB_OAUTH_ACCESS_SCOPES - the scopes required to access the server (called JUPYTERHUB_OAUTH_SCOPES prior to 3.0)
- JUPYTERHUB_OAUTH_CLIENT_ALLOWED_SCOPES - the scopes the service is allowed to request.
If no scopes are requested explicitly, these scopes will be requested.
Optional environment variables, depending on configuration:
- JUPYTERHUB*SSL*[KEYFILE|CERTFILE|CLIENT_CI] - SSL configuration, when internal_ssl is enabled
- JUPYTERHUB_ROOT_DIR - the root directory of the server (notebook directory), when Spawner.notebook_dir is defined (new in 2.0)
- JUPYTERHUB_DEFAULT_URL - the default URL for the server (for redirects from /user/:name/),
if Spawner.default_url is defined
(new in 2.0, previously passed via cli)
- JUPYTERHUB_DEBUG=1 - generic debug flag, sets maximum log level when Spawner.debug is True
(new in 2.0, previously passed via cli)
- JUPYTERHUB*SSL*[KEYFILE|CERTFILE|CLIENT_CI] - SSL configuration, when `internal_ssl` is enabled
- JUPYTERHUB_ROOT_DIR - the root directory of the server (notebook directory), when `Spawner.notebook_dir` is defined (new in 2.0)
- JUPYTERHUB_DEFAULT_URL - the default URL for the server (for redirects from `/user/:name/`),
if `Spawner.default_url` is defined
(new in 2.0, previously passed via CLI)
- JUPYTERHUB_DEBUG=1 - generic debug flag, sets maximum log level when `Spawner.debug` is True
(new in 2.0, previously passed via CLI)
- JUPYTERHUB_DISABLE_USER_CONFIG=1 - disable loading user config,
sets maximum log level when Spawner.debug is True (new in 2.0,
previously passed via cli)
sets maximum log level when `Spawner.debug` is True (new in 2.0,
previously passed via CLI)
- JUPYTERHUB*[MEM|CPU]*[LIMIT_GUARANTEE] - the values of cpu and memory limits and guarantees.
- JUPYTERHUB*[MEM|CPU]*[LIMIT_GUARANTEE] - the values of CPU and memory limits and guarantees.
These are not expected to be enforced by the process,
but are made available as a hint,
e.g. for resource monitoring extensions.
@@ -338,9 +338,10 @@ guarantees on resources, such as CPU and memory. To provide a consistent
experience for sysadmins and users, we provide a standard way to set and
discover these resource limits and guarantees, such as for memory and CPU.
For the limits and guarantees to be useful, **the spawner must implement
support for them**. For example, LocalProcessSpawner, the default
support for them**. For example, `LocalProcessSpawner`, the default
spawner, does not support limits and guarantees. One of the spawners
that supports limits and guarantees is the `systemdspawner`.
that supports limits and guarantees is the
[`systemdspawner`](https://github.com/jupyterhub/systemdspawner).
### Memory Limits & Guarantees
@@ -367,7 +368,7 @@ limits or guarantees are provided, and no environment values are set.
`c.Spawner.cpu_limit`: In supported spawners, you can set
`c.Spawner.cpu_limit` to limit the total number of cpu-cores that a
single-user notebook server can use. These can be fractional - `0.5` means 50%
of one CPU core, `4.0` is 4 cpu-cores, etc. This value is also set in the
of one CPU core, `4.0` is 4 CPU-cores, etc. This value is also set in the
single-user notebook server's environment variable `CPU_LIMIT`. The limit does
not claim that you will be able to use all the CPU up to your limit as other
higher priority applications might be taking up CPU.
@@ -400,9 +401,10 @@ container `ip` prior to starting and pass that to `.create_certs` (TODO: edit).
In general though, this method will not need to be changed and the default
`ip`/`dns` (localhost) info will suffice.
When `.create_certs` is run, it will `.create_certs` in a default, central
location specified by `c.JupyterHub.internal_certs_location`. For `Spawners`
that need access to these certs elsewhere (i.e. on another host altogether),
the `.move_certs` method can be overridden to move the certs appropriately.
Again, using `DockerSpawner` as an example, this would entail moving certs
to a directory that will get mounted into the container this spawner starts.
When `.create_certs` is run, it will create the certificates in a default,
central location specified by `c.JupyterHub.internal_certs_location`. For
`Spawners` that need access to these certs elsewhere (i.e. on another host
altogether), the `.move_certs` method can be overridden to move the certs
appropriately. Again, using `DockerSpawner` as an example, this would entail
moving certs to a directory that will get mounted into the container this
spawner starts.

2
docs/source/reference/templates.md
View File

@@ -84,5 +84,5 @@ template (for example, `login.html`) with:
```
Extending `page.html` puts the message on all pages, but note that
extending `page.html` take precedence over an extension of a specific
extending `page.html` takes precedence over an extension of a specific
page (unlike the variable-based approach above).

91
docs/source/reference/urls.md
View File

@@ -2,13 +2,13 @@
This document describes how JupyterHub routes requests.
This does not include the [REST API](./rest.md) urls.
This does not include the [REST API](./rest.md) URLs.
In general, all URLs can be prefixed with `c.JupyterHub.base_url` to
run the whole JupyterHub application on a prefix.
All authenticated handlers redirect to `/hub/login` to login users
prior to being redirected back to the originating page.
All authenticated handlers redirect to `/hub/login` to log-in users
before being redirected back to the originating page.
The returned request should preserve all query parameters.
## `/`
@@ -25,12 +25,12 @@ This is an authenticated URL.
This handler redirects users to the default URL of the application,
which defaults to the user's default server.
That is, it redirects to `/hub/spawn` if the user's server is not running,
or the server itself (`/user/:name`) if the server is running.
That is, the handler redirects to `/hub/spawn` if the user's server is not running,
or to the server itself (`/user/:name`) if the server is running.
This default url behavior can be customized in two ways:
This default URL behavior can be customized in two ways:
To redirect users to the JupyterHub home page (`/hub/home`)
First, to redirect users to the JupyterHub home page (`/hub/home`)
instead of spawning their server,
set `redirect_to_server` to False:
@@ -40,7 +40,7 @@ c.JupyterHub.redirect_to_server = False
This might be useful if you have a Hub where you expect
users to be managing multiple server configurations
and automatic spawning is not desirable.
but automatic spawning is not desirable.
Second, you can customise the landing page to any page you like,
such as a custom service you have deployed e.g. with course information:
@@ -57,7 +57,7 @@ By default, the Hub home page has just one or two buttons
for starting and stopping the user's server.
If named servers are enabled, there will be some additional
tools for management of named servers.
tools for management of the named servers.
_Version added: 1.0_ named server UI is new in 1.0.
@@ -65,34 +65,34 @@ _Version added: 1.0_ named server UI is new in 1.0.
This is the JupyterHub login page.
If you have a form-based username+password login,
such as the default PAMAuthenticator,
such as the default [PAMAuthenticator](https://en.wikipedia.org/wiki/Pluggable_authentication_module),
this page will render the login form.
![A login form](../images/login-form.png)
If login is handled by an external service,
e.g. with OAuth, this page will have a button,
declaring "Login with ..." which users can click
to login with the chosen service.
declaring "Log in with ..." which users can click
to log in with the chosen service.
![A login redirect button](../images/login-button.png)
If you want to skip the user-interaction to initiate logging in
via the button, you can set
If you want to skip the user interaction and initiate login
via the button, you can set:
```python
c.Authenticator.auto_login = True
```
This can be useful when the user is "already logged in" via some mechanism,
but a handshake via redirects is necessary to complete the authentication with JupyterHub.
This can be useful when the user is "already logged in" via some mechanism.
However, a handshake via `redirects` is necessary to complete the authentication with JupyterHub.
## `/hub/logout`
Visiting `/hub/logout` clears cookies from the current browser.
Visiting `/hub/logout` clears [cookies](https://en.wikipedia.org/wiki/HTTP_cookie) from the current browser.
Note that **logging out does not stop a user's server(s)** by default.
If you would like to shutdown user servers on logout,
If you would like to shut down user servers on logout,
you can enable this behavior with:
```python
@@ -105,8 +105,8 @@ does not mean the user is no longer actively using their server from another mac
## `/user/:username[/:servername]`
If a user's server is running, this URL is handled by the user's given server,
not the Hub.
The username is the first part and, if using named servers,
not by the Hub.
The username is the first part, and if using named servers,
the server name is the second part.
If the user's server is _not_ running, this will be redirected to `/hub/user/:username/...`
@@ -117,14 +117,15 @@ This URL indicates a request for a user server that is not running
(because `/user/...` would have been handled by the notebook server
if the specified server were running).
Handling this URL is the most complicated condition in JupyterHub,
because there can be many states:
Handling this URL depends on two conditions: whether a requested user is found
as a match and the state of the requested user's notebook server,
for example:
1. server is not active
1. the server is not active
a. user matches
b. user doesn't match
2. server is ready
3. server is pending, but not ready
2. the server is ready
3. the server is pending, but not ready
If the server is pending spawn,
the browser will be redirected to `/hub/spawn-pending/:username/:servername`
@@ -140,39 +141,37 @@ Some checks are performed and a delay is added before redirecting back to `/user
If something is really wrong, this can result in a redirect loop.
Visiting this page will never result in triggering the spawn of servers
without additional user action (i.e. clicking the link on the page)
without additional user action (i.e. clicking the link on the page).
![Visiting a URL for a server that's not running](../images/not-running.png)
_Version changed: 1.0_
Prior to 1.0, this URL itself was responsible for spawning servers,
and served the progress page if it was pending,
redirected to running servers, and
This was useful because it made sure that requested servers were restarted after they stopped,
but could also be harmful because unused servers would continuously be restarted if e.g.
an idle JupyterLab frontend were open pointed at it,
which constantly makes polling requests.
Prior to 1.0, this URL itself was responsible for spawning servers.
If the progress page was pending, the URL redirected it to running servers.
This was useful because it made sure that the requested servers were restarted after they stopped.
However, it could also be harmful because unused servers would continuously be restarted if e.g.
an idle JupyterLab frontend that constantly makes polling requests was openly pointed at it.
### Special handling of API requests
Requests to `/user/:username[/:servername]/api/...` are assumed to be
from applications connected to stopped servers.
These are failed with 503 and an informative JSON error message
indicating how to spawn the server.
This is meant to help applications such as JupyterLab
These requests fail with a `503` status code and an informative JSON error message
that indicates how to spawn the server.
This is meant to help applications such as JupyterLab,
that are connected to a server that has stopped.
_Version changed: 1.0_
JupyterHub 0.9 failed these API requests with status 404,
but 1.0 uses 503.
JupyterHub version 0.9 failed these API requests with status `404`,
but version 1.0 uses 503.
## `/user-redirect/...`
This URL is for sharing a URL that will redirect a user
The `/user-redirect/...` URL is for sharing a URL that will redirect a user
to a path on their own default server.
This is useful when users have the same file at the same URL on their servers,
This is useful when different users have the same file at the same URL on their servers,
and you want a single link to give to any user that will open that file on their server.
e.g. a link to `/user-redirect/notebooks/Index.ipynb`
@@ -194,7 +193,7 @@ that is intended to make it possible.
### `/hub/spawn[/:username[/:servername]]`
Requesting `/hub/spawn` will spawn the default server for the current user.
If `username` and optionally `servername` are specified,
If the `username` and optionally `servername` are specified,
then the specified server for the specified user will be spawned.
Once spawn has been requested,
the browser is redirected to `/hub/spawn-pending/...`.
@@ -207,7 +206,7 @@ and a POST request will trigger the actual spawn and redirect.
_Version added: 1.0_
1.0 adds the ability to specify username and servername.
1.0 adds the ability to specify `username` and `servername`.
Prior to 1.0, only `/hub/spawn` was recognized for the default server.
_Version changed: 1.0_
@@ -247,7 +246,7 @@ against the [JupyterHub REST API](./rest.md).
Administrators can take various administrative actions from this page:
1. add/remove users
2. grant admin privileges
3. start/stop user servers
4. shutdown JupyterHub itself
- add/remove users
- grant admin privileges
- start/stop user servers
- shutdown JupyterHub itself

26
docs/source/reference/websecurity.md
View File

@@ -5,7 +5,7 @@ The **Security Overview** section helps you learn about:
- the design of JupyterHub with respect to web security
- the semi-trusted user
- the available mitigations to protect untrusted users from each other
- the value of periodic security audits.
- the value of periodic security audits
This overview also helps you obtain a deeper understanding of how JupyterHub
works.
@@ -16,9 +16,9 @@ JupyterHub is designed to be a _simple multi-user server for modestly sized
groups_ of **semi-trusted** users. While the design reflects serving semi-trusted
users, JupyterHub is not necessarily unsuitable for serving **untrusted** users.
Using JupyterHub with **untrusted** users does mean more work by the
Using JupyterHub with **untrusted** users does mean more work for the
administrator. Much care is required to secure a Hub, with extra caution on
protecting users from each other as the Hub is serving untrusted users.
protecting users from each other, since the Hub serves untrusted users.
One aspect of JupyterHub's _design simplicity_ for **semi-trusted** users is that
the Hub and single-user servers are placed in a _single domain_, behind a
@@ -32,7 +32,7 @@ servers) as a single website (i.e. single domain).
To protect users from each other, a user must **never** be able to write arbitrary
HTML and serve it to another user on the Hub's domain. JupyterHub's
authentication setup prevents a user writing arbitrary HTML and serving it to
authentication setup prevents a user from writing arbitrary HTML and serving it to
another user because only the owner of a given single-user notebook server is
allowed to view user-authored pages served by the given single-user notebook
server.
@@ -47,7 +47,7 @@ ensure that:
- If the `PATH` is used to resolve the single-user executable (instead of
using an absolute path), a user **may not** create new files in any `PATH`
directory that precedes the directory containing `jupyterhub-singleuser`.
- A user may not modify environment variables (e.g. PATH, PYTHONPATH) for
- A user may not modify environment variables (e.g. `PATH`, `PYTHONPATH`) for
their single-user server.
- A user **may not** modify the configuration of the notebook server
(the `~/.jupyter` or `JUPYTER_CONFIG_DIR` directory).
@@ -58,7 +58,7 @@ If any additional services are run on the same domain as the Hub, the services
## Mitigate security issues
Several approaches to mitigating these issues with configuration
The several approaches to mitigating security issues with configuration
options provided by JupyterHub include:
### Enable subdomains
@@ -76,10 +76,10 @@ resolves the cross-site issues.
### Disable user config
If subdomains are not available or not desirable, JupyterHub provides a
If subdomains are unavailable or undesirable, JupyterHub provides a
configuration option `Spawner.disable_user_config`, which can be set to prevent
the user-owned configuration files from being loaded. After implementing this
option, PATHs and package installation and PATHs are the other things that the
option, `PATH`s and package installation are the other things that the
admin must enforce.
### Prevent spawners from evaluating shell configuration files
@@ -101,8 +101,8 @@ pose additional risk to the web application's security.
### Encrypt internal connections with SSL/TLS
By default, all communication on the server, between the proxy, hub, and single
-user notebooks is performed unencrypted. Setting the `internal_ssl` flag in
By default, all communications on the server, between the proxy, hub, and single
-user notebooks are performed unencrypted. Setting the `internal_ssl` flag in
`jupyterhub_config.py` secures the aforementioned routes. Turning this
feature on does require that the enabled `Spawner` can use the certificates
generated by the `Hub` (the default `LocalProcessSpawner` can, for instance).
@@ -119,8 +119,8 @@ extend to securing the `tcp` sockets as well.
## Security audits
We recommend that you do periodic reviews of your deployment's security. It's
good practice to keep JupyterHub, configurable-http-proxy, and nodejs
versions up to date.
good practice to keep [JupyterHub](https://readthedocs.org/projects/jupyterhub/), [configurable-http-proxy][], and [nodejs
versions](https://github.com/nodejs/Release) up to date.
A handy website for testing your deployment is
[Qualsys' SSL analyzer tool](https://www.ssllabs.com/ssltest/analyze.html).
@@ -129,7 +129,7 @@ A handy website for testing your deployment is
## Vulnerability reporting
If you believe you’ve found a security vulnerability in JupyterHub, or any
If you believe you have found a security vulnerability in JupyterHub, or any
Jupyter project, please report it to
[security@ipython.org](mailto:security@ipython.org). If you prefer to encrypt
your security reports, you can use [this PGP public

169
docs/source/troubleshooting.md
View File

@@ -1,35 +1,9 @@
# Troubleshooting
When troubleshooting, you may see unexpected behaviors or receive an error
message. This section provide links for identifying the cause of the
message. This section provides links for identifying the cause of the
problem and how to resolve it.
[_Behavior_](#behavior)
- JupyterHub proxy fails to start
- sudospawner fails to run
- What is the default behavior when none of the lists (admin, allowed,
allowed groups) are set?
- JupyterHub Docker container not accessible at localhost
[_Errors_](#errors)
- 500 error after spawning my single-user server
[_How do I...?_](#how-do-i)
- Use a chained SSL certificate
- Install JupyterHub without a network connection
- I want access to the whole filesystem, but still default users to their home directory
- How do I increase the number of pySpark executors on YARN?
- How do I use JupyterLab's prerelease version with JupyterHub?
- How do I set up JupyterHub for a workshop (when users are not known ahead of time)?
- How do I set up rotating daily logs?
- Toree integration with HDFS rack awareness script
- Where do I find Docker images and Dockerfiles related to JupyterHub?
[_Troubleshooting commands_](#troubleshooting-commands)
## Behavior
### JupyterHub proxy fails to start
@@ -40,9 +14,9 @@ If you have tried to start the JupyterHub proxy and it fails to start:
`c.JupyterHub.ip = '*'`; if it is, try `c.JupyterHub.ip = ''`
- Try starting with `jupyterhub --ip=0.0.0.0`
**Note**: If this occurs on Ubuntu/Debian, check that the you are using a
recent version of node. Some versions of Ubuntu/Debian come with a version
of node that is very old, and it is necessary to update node.
**Note**: If this occurs on Ubuntu/Debian, check that you are using a
recent version of [Node](https://nodejs.org). Some versions of Ubuntu/Debian come with a very old version
of Node and it is necessary to update Node.
### sudospawner fails to run
@@ -61,24 +35,24 @@ to the config file, `jupyterhub_config.py`.
### What is the default behavior when none of the lists (admin, allowed, allowed groups) are set?
When nothing is given for these lists, there will be no admins, and all users
who can authenticate on the system (i.e. all the unix users on the server with
who can authenticate on the system (i.e. all the Unix users on the server with
a password) will be allowed to start a server. The allowed username set lets you limit
this to a particular set of users, and admin_users lets you specify who
among them may use the admin interface (not necessary, unless you need to do
things like inspect other users' servers, or modify the user list at runtime).
things like inspect other users' servers or modify the user list at runtime).
### JupyterHub Docker container not accessible at localhost
### JupyterHub Docker container is not accessible at localhost
Even though the command to start your Docker container exposes port 8000
(`docker run -p 8000:8000 -d --name jupyterhub jupyterhub/jupyterhub jupyterhub`),
it is possible that the IP address itself is not accessible/visible. As a result
it is possible that the IP address itself is not accessible/visible. As a result,
when you try http://localhost:8000 in your browser, you are unable to connect
even though the container is running properly. One workaround is to explicitly
tell Jupyterhub to start at `0.0.0.0` which is visible to everyone. Try this
command:
`docker run -p 8000:8000 -d --name jupyterhub jupyterhub/jupyterhub jupyterhub --ip 0.0.0.0 --port 8000`
### How can I kill ports from JupyterHub managed services that have been orphaned?
### How can I kill ports from JupyterHub-managed services that have been orphaned?
I started JupyterHub + nbgrader on the same host without containers. When I try to restart JupyterHub + nbgrader with this configuration, errors appear that the service accounts cannot start because the ports are being used.
@@ -92,12 +66,12 @@ Where `<service_port>` is the port used by the nbgrader course service. This con
### Why am I getting a Spawn failed error message?
After successfully logging in to JupyterHub with a compatible authenticators, I get a 'Spawn failed' error message in the browser. The JupyterHub logs have `jupyterhub KeyError: "getpwnam(): name not found: <my_user_name>`.
After successfully logging in to JupyterHub with a compatible authenticator, I get a 'Spawn failed' error message in the browser. The JupyterHub logs have `jupyterhub KeyError: "getpwnam(): name not found: <my_user_name>`.
This issue occurs when the authenticator requires a local system user to exist. In these cases, you need to use a spawner
that does not require an existing system user account, such as `DockerSpawner` or `KubeSpawner`.
### How can I run JupyterHub with sudo but use my current env vars and virtualenv location?
### How can I run JupyterHub with sudo but use my current environment variables and virtualenv location?
When launching JupyterHub with `sudo jupyterhub` I get import errors and my environment variables don't work.
@@ -109,25 +83,11 @@ sudo MY_ENV=abc123 \
/srv/jupyterhub/jupyterhub
```
### How can I view the logs for JupyterHub or the user's Notebook servers when using the DockerSpawner?
Use `docker logs <container>` where `<container>` is the container name defined within `docker-compose.yml`. For example, to view the logs of the JupyterHub container use:
docker logs hub
By default, the user's notebook server is named `jupyter-<username>` where `username` is the user's username within JupyterHub's db. So if you wanted to see the logs for user `foo` you would use:
docker logs jupyter-foo
You can also tail logs to view them in real time using the `-f` option:
docker logs -f hub
## Errors
### 500 error after spawning my single-user server
### Error 500 after spawning my single-user server
You receive a 500 error when accessing the URL `/user/<your_name>/...`.
You receive a 500 error while accessing the URL `/user/<your_name>/...`.
This is often seen when your single-user server cannot verify your user cookie
with the Hub.
@@ -185,10 +145,10 @@ If you receive a 403 error, the API token for the single-user server is likely
invalid. Commonly, the 403 error is caused by resetting the JupyterHub
database (either removing jupyterhub.sqlite or some other action) while
leaving single-user servers running. This happens most frequently when using
DockerSpawner, because Docker's default behavior is to stop/start containers
which resets the JupyterHub database, rather than destroying and recreating
DockerSpawner because Docker's default behavior is to stop/start containers
that reset the JupyterHub database, rather than destroying and recreating
the container every time. This means that the same API token is used by the
server for its whole life, until the container is rebuilt.
server for its whole life until the container is rebuilt.
The fix for this Docker case is to remove any Docker containers seeing this
issue (typically all containers created before a certain point in time):
@@ -201,14 +161,14 @@ your server again.
##### Proxy settings (403 GET)
When your whole JupyterHub sits behind a organization proxy (_not_ a reverse proxy like NGINX as part of your setup and _not_ the configurable-http-proxy) the environment variables `HTTP_PROXY`, `HTTPS_PROXY`, `http_proxy` and `https_proxy` might be set. This confuses the jupyterhub-singleuser servers: When connecting to the Hub for authorization they connect via the proxy instead of directly connecting to the Hub on localhost. The proxy might deny the request (403 GET). This results in the singleuser server thinking it has a wrong auth token. To circumvent this you should add `<hub_url>,<hub_ip>,localhost,127.0.0.1` to the environment variables `NO_PROXY` and `no_proxy`.
When your whole JupyterHub sits behind an organization proxy (_not_ a reverse proxy like NGINX as part of your setup and _not_ the configurable-http-proxy) the environment variables `HTTP_PROXY`, `HTTPS_PROXY`, `http_proxy`, and `https_proxy` might be set. This confuses the JupyterHub single-user servers: When connecting to the Hub for authorization they connect via the proxy instead of directly connecting to the Hub on localhost. The proxy might deny the request (403 GET). This results in the single-user server thinking it has the wrong auth token. To circumvent this you should add `<hub_url>,<hub_ip>,localhost,127.0.0.1` to the environment variables `NO_PROXY` and `no_proxy`.
### Launching Jupyter Notebooks to run as an externally managed JupyterHub service with the `jupyterhub-singleuser` command returns a `JUPYTERHUB_API_TOKEN` error
[JupyterHub services](https://jupyterhub.readthedocs.io/en/stable/reference/services.html) allow processes to interact with JupyterHub's REST API. Example use-cases include:
- **Secure Testing**: provide a canonical Jupyter Notebook for testing production data to reduce the number of entry points into production systems.
- **Grading Assignments**: provide access to shared Jupyter Notebooks that may be used for management tasks such grading assignments.
- **Grading Assignments**: provide access to shared Jupyter Notebooks that may be used for management tasks such as grading assignments.
- **Private Dashboards**: share dashboards with certain group members.
If possible, try to run the Jupyter Notebook as an externally managed service with one of the provided [jupyter/docker-stacks](https://github.com/jupyter/docker-stacks).
@@ -222,7 +182,7 @@ If you launch a Jupyter Notebook with the `jupyterhub-singleuser` command direct
Did you launch it manually?
```
If you plan on testing `jupyterhub-singleuser` independently from JupyterHub, then you can set the api token environment variable. For example, if were to run the single-user Jupyter Notebook on the host, then:
If you plan on testing `jupyterhub-singleuser` independently from JupyterHub, then you can set the API token environment variable. For example, if you were to run the single-user Jupyter Notebook on the host, then:
export JUPYTERHUB_API_TOKEN=my_secret_token
jupyterhub-singleuser
@@ -256,7 +216,7 @@ You would then set in your `jupyterhub_config.py` file the `ssl_key` and
#### Example
Your certificate provider gives you the following files: `example_host.crt`,
`Entrust_L1Kroot.txt` and `Entrust_Root.txt`.
`Entrust_L1Kroot.txt`, and `Entrust_Root.txt`.
Concatenate the files appending the chain cert and root cert to your host cert:
@@ -289,7 +249,7 @@ with npmbox:
python3 -m pip wheel jupyterhub
npmbox configurable-http-proxy
### I want access to the whole filesystem, but still default users to their home directory
### I want access to the whole filesystem and still default users to their home directory
Setting the following in `jupyterhub_config.py` will configure access to
the entire filesystem and set the default to the user's home directory.
@@ -308,7 +268,7 @@ similar to this one:
provides additional information. The [pySpark configuration documentation](https://spark.apache.org/docs/0.9.0/configuration.html)
is also helpful for programmatic configuration examples.
### How do I use JupyterLab's prerelease version with JupyterHub?
### How do I use JupyterLab's pre-release version with JupyterHub?
While JupyterLab is still under active development, we have had users
ask about how to try out JupyterLab with JupyterHub.
@@ -321,7 +281,7 @@ For instance:
python3 -m pip install jupyterlab
jupyter serverextension enable --py jupyterlab --sys-prefix
The important thing is that jupyterlab is installed and enabled in the
The important thing is that JupyterLab is installed and enabled in the
single-user notebook server environment. For system users, this means
system-wide, as indicated above. For Docker containers, it means inside
the single-user docker image, etc.
@@ -334,14 +294,14 @@ notebook servers to default to JupyterLab:
### How do I set up JupyterHub for a workshop (when users are not known ahead of time)?
1. Set up JupyterHub using OAuthenticator for GitHub authentication
2. Configure admin list to have workshop leaders be listed with administrator privileges.
2. Configure the admin list to have workshop leaders listed with administrator privileges.
Users will need a GitHub account to login and be authenticated by the Hub.
Users will need a GitHub account to log in and be authenticated by the Hub.
### How do I set up rotating daily logs?
You can do this with [logrotate](https://linux.die.net/man/8/logrotate),
or pipe to `logger` to use syslog instead of directly to a file.
or pipe to `logger` to use Syslog instead of directly to a file.
For example, with this logrotate config file:
@@ -362,6 +322,51 @@ Or use syslog:
jupyterhub | logger -t jupyterhub
### Toree integration with HDFS rack awareness script
The Apache Toree kernel will have an issue when running with JupyterHub if the standard HDFS rack awareness script is used. This will materialize in the logs as a repeated WARN:
```bash
16/11/29 16:24:20 WARN ScriptBasedMapping: Exception running /etc/hadoop/conf/topology_script.py some.ip.address
ExitCodeException exitCode=1: File "/etc/hadoop/conf/topology_script.py", line 63
print rack
^
SyntaxError: Missing parentheses in call to 'print'
at `org.apache.hadoop.util.Shell.runCommand(Shell.java:576)`
```
In order to resolve this issue, there are two potential options.
1. Update HDFS core-site.xml, so the parameter "net.topology.script.file.name" points to a custom
script (e.g. /etc/hadoop/conf/custom_topology_script.py). Copy the original script and change the first line point
to a python two installation (e.g. /usr/bin/python).
2. In spark-env.sh add a Python 2 installation to your path (e.g. export PATH=/opt/anaconda2/bin:$PATH).
### Where do I find Docker images and Dockerfiles related to JupyterHub?
Docker images can be found at the [JupyterHub organization on DockerHub](https://hub.docker.com/u/jupyterhub/).
The Docker image [jupyterhub/singleuser](https://hub.docker.com/r/jupyterhub/singleuser/)
provides an example single-user notebook server for use with DockerSpawner.
Additional single-user notebook server images can be found at the [Jupyter
organization on DockerHub](https://hub.docker.com/r/jupyter/) and information
about each image at the [jupyter/docker-stacks repo](https://github.com/jupyter/docker-stacks).
### How can I view the logs for JupyterHub or the user's Notebook servers when using the DockerSpawner?
Use `docker logs <container>` where `<container>` is the container name defined within `docker-compose.yml`. For example, to view the logs of the JupyterHub container use:
docker logs hub
By default, the user's notebook server is named `jupyter-<username>` where `username` is the user's username within JupyterHub's db. So if you wanted to see the logs for user `foo` you would use:
docker logs jupyter-foo
You can also tail logs to view them in real-time using the `-f` option:
docker logs -f hub
## Troubleshooting commands
The following commands provide additional detail about installed packages,
@@ -385,35 +390,3 @@ jupyter kernelspec list
```bash
jupyterhub --debug
```
### Toree integration with HDFS rack awareness script
The Apache Toree kernel will an issue, when running with JupyterHub, if the standard HDFS
rack awareness script is used. This will materialize in the logs as a repeated WARN:
```bash
16/11/29 16:24:20 WARN ScriptBasedMapping: Exception running /etc/hadoop/conf/topology_script.py some.ip.address
ExitCodeException exitCode=1: File "/etc/hadoop/conf/topology_script.py", line 63
print rack
^
SyntaxError: Missing parentheses in call to 'print'
at `org.apache.hadoop.util.Shell.runCommand(Shell.java:576)`
```
In order to resolve this issue, there are two potential options.
1. Update HDFS core-site.xml, so the parameter "net.topology.script.file.name" points to a custom
script (e.g. /etc/hadoop/conf/custom_topology_script.py). Copy the original script and change the first line point
to a python two installation (e.g. /usr/bin/python).
2. In spark-env.sh add a Python 2 installation to your path (e.g. export PATH=/opt/anaconda2/bin:$PATH).
### Where do I find Docker images and Dockerfiles related to JupyterHub?
Docker images can be found at the [JupyterHub organization on DockerHub](https://hub.docker.com/u/jupyterhub/).
The Docker image [jupyterhub/singleuser](https://hub.docker.com/r/jupyterhub/singleuser/)
provides an example single user notebook server for use with DockerSpawner.
Additional single user notebook server images can be found at the [Jupyter
organization on DockerHub](https://hub.docker.com/r/jupyter/) and information
about each image at the [jupyter/docker-stacks repo](https://github.com/jupyter/docker-stacks).

4
examples/bootstrap-script/README.md
View File

@@ -9,7 +9,7 @@ _Providing writeable storage for LDAP users_
Your Jupyterhub is configured to use the LDAPAuthenticator and DockerSpawer.
- The user has no file directory on the host since your are using LDAP.
- The user has no file directory on the host since you are using LDAP.
- When a user has no directory and DockerSpawner wants to mount a volume,
the spawner will use docker to create a directory.
Since the docker daemon is running as root, the generated directory for the volume
@@ -23,7 +23,7 @@ Another use would be to copy initial content, such as tutorial files or referenc
material, into the user's space when a notebook server is newly spawned.
You can define your own bootstrap process by implementing a `pre_spawn_hook` on any spawner.
The Spawner itself is passed as parameter to your hook and you can easily get the contextual information out of the spawning process.
The Spawner itself is passed as a parameter to your hook and you can easily get the contextual information out of the spawning process.
Similarly, there may be cases where you would like to clean up after a spawner stops.
You may implement a `post_stop_hook` that is always executed after the spawner stops.

18
examples/service-announcement/README.md
View File

@@ -6,12 +6,28 @@ that appear when JupyterHub renders pages.
To run the service as a hub-managed service simply include in your JupyterHub
configuration file something like:
:notebook:**Info**: You can run the announcement service example from the `examples`
directory, using one of the several services provided by JupyterHub.
```python
import sys
from pathlib import Path
# absolute path to announcement.py
announcement_py = str(Path(__file__).parent.joinpath("announcement.py").resolve())
#ensure get_config() is added in
c = get_config()
...
..
c.JupyterHub.services = [
{
'name': 'announcement',
'url': 'http://127.0.0.1:8888',
'command': [sys.executable, "-m", "announcement", "--port", "8888"],
'command': [sys.executable, announcement_py, "--port", "8888"],
}
]
```

2
examples/service-announcement/jupyterhub_config.py
View File

@@ -1,5 +1,7 @@
import sys
c = get_config()
# To run the announcement service managed by the hub, add this.
port = 9999

2
examples/service-fastapi/app/__init__.py
View File

@@ -1 +1,3 @@
from .app import app
__all__ = ["app"]

2
examples/service-fastapi/app/service.py
View File

@@ -51,7 +51,7 @@ async def me(user: User = Depends(get_current_user)):
@router.get("/debug")
async def index(request: Request, user: User = Depends(get_current_user)):
async def debug(request: Request, user: User = Depends(get_current_user)):
"""
Authenticated function that returns a few pieces of debug
* Environ of the service process

6
jsx/README.md
View File

@@ -23,7 +23,7 @@ This app is written in JSX, and then transpiled into an ES5 bundle with Babel an
#### Centralized state and data management with Redux:
The app use Redux throughout the components via the `useSelector` and `useDispatch` hooks to store and update user and group data from the API. With Redux, this data is available to any connected component. This means that if one component recieves new data, they all do.
The app uses Redux throughout the components via the `useSelector` and `useDispatch` hooks to store and update user and group data from the API. With Redux, this data is available to any connected component. This means that if one component receives new data, they all do.
#### API functions
@@ -31,7 +31,7 @@ All API functions used by the front end are packaged as a library of props withi
#### Pagination
Indicies of paginated user and group data is stored in a `page` variable in the query string, as well as the `user_page` / `group_page` state variables in Redux. This allows the app to maintain two sources of truth, as well as protect the admin user's place in the collection on page reload. Limit is constant at this point and is held in the Redux state.
Indicies of paginated user and group data are stored in a `page` variable in the query string, as well as the `user_page` / `group_page` state variables in Redux. This allows the app to maintain two sources of truth, as well as protect the admin user's place in the collection on page reload. The limit is constant at this point and is held in the Redux state.
On updates to the paginated data, the app can respond in one of two ways. If a user/group record is either added or deleted, the pagination will reset and data will be pulled back with no offset. Alternatively, if a record is modified, the offset will remain and the change will be shown.
@@ -55,7 +55,7 @@ startServer().then(() => {
.then((data) => dispatchPageChange(data, page));
});
// Alternatively, a new user was added, user data is being refreshed from offset 0.
// Alternatively, a new user was added, and user data is being refreshed from offset 0.
addUser().then(() => {
updateUsers(0, limit)
// After data is fetched, the Redux store is updated with the data and asserts page 0.

6
jsx/src/components/AddUser/AddUser.jsx
View File

@@ -98,13 +98,13 @@ const AddUser = (props) => {
.then((data) => dispatchPageChange(data, 0))
.then(() => history.push("/"))
.catch(() =>
setErrorAlert(`Failed to update users.`)
setErrorAlert(`Failed to update users.`),
)
: setErrorAlert(
`Failed to create user. ${
data.status == 409 ? "User already exists." : ""
}`
)
}`,
),
)
.catch(() => setErrorAlert(`Failed to create user.`));
}}

2
jsx/src/components/AddUser/AddUser.test.js
View File

@@ -131,7 +131,7 @@ test("Shows a more specific UI error dialogue when user creation returns an impr
});
let errorDialog = screen.getByText(
"Failed to create user. User already exists."
"Failed to create user. User already exists.",
);
expect(errorDialog).toBeVisible();

4
jsx/src/components/CreateGroup/CreateGroup.jsx
View File

@@ -81,14 +81,14 @@ const CreateGroup = (props) => {
.then((data) => dispatchPageUpdate(data, 0))
.then(() => history.push("/groups"))
.catch(() =>
setErrorAlert(`Could not update groups list.`)
setErrorAlert(`Could not update groups list.`),
)
: setErrorAlert(
`Failed to create group. ${
data.status == 409
? "Group already exists."
: ""
}`
}`,
);
})
.catch(() => setErrorAlert(`Failed to create group.`));

2
jsx/src/components/CreateGroup/CreateGroup.test.js
View File

@@ -107,7 +107,7 @@ test("Shows a more specific UI error dialogue when user creation returns an impr
});
let errorDialog = screen.getByText(
"Failed to create group. Group already exists."
"Failed to create group. Group already exists.",
);
expect(errorDialog).toBeVisible();

8
jsx/src/components/EditUser/EditUser.jsx
View File

@@ -96,8 +96,8 @@ const EditUser = (props) => {
.then(() => history.push("/"))
.catch(() =>
setErrorAlert(
`Could not update users list.`
)
`Could not update users list.`,
),
)
: setErrorAlert(`Failed to edit user.`);
})
@@ -129,7 +129,7 @@ const EditUser = (props) => {
editUser(
username,
updatedUsername != "" ? updatedUsername : username,
admin
admin,
)
.then((data) => {
data.status < 300
@@ -137,7 +137,7 @@ const EditUser = (props) => {
.then((data) => dispatchPageChange(data, 0))
.then(() => history.push("/"))
.catch(() =>
setErrorAlert(`Could not update users list.`)
setErrorAlert(`Could not update users list.`),
)
: setErrorAlert(`Failed to edit user.`);
})

6
jsx/src/components/GroupEdit/GroupEdit.jsx
View File

@@ -94,10 +94,10 @@ const GroupEdit = (props) => {
}
let new_users = selected.filter(
(e) => !group_data.users.includes(e)
(e) => !group_data.users.includes(e),
);
let removed_users = group_data.users.filter(
(e) => !selected.includes(e)
(e) => !selected.includes(e),
);
let promiseQueue = [];
@@ -105,7 +105,7 @@ const GroupEdit = (props) => {
promiseQueue.push(addToGroup(new_users, group_data.name));
if (removed_users.length > 0)
promiseQueue.push(
removeFromGroup(removed_users, group_data.name)
removeFromGroup(removed_users, group_data.name),
);
Promise.all(promiseQueue)

2
jsx/src/components/GroupSelect/GroupSelect.jsx
View File

@@ -90,7 +90,7 @@ const GroupSelect = (props) => {
>
{e}
</div>
)
),
)}
</div>
</div>

4
jsx/src/components/Groups/Groups.jsx
View File

@@ -1,4 +1,4 @@
import React, { useEffect, useState } from "react";
import React, { useEffect } from "react";
import { useSelector, useDispatch } from "react-redux";
import PropTypes from "prop-types";
@@ -37,7 +37,7 @@ const Groups = (props) => {
useEffect(() => {
updateGroups(offset, limit).then((data) =>
dispatchPageUpdate(data.items, data._pagination)
dispatchPageUpdate(data.items, data._pagination),
);
}, [offset, limit]);

20
jsx/src/components/ServerDashboard/ServerDashboard.jsx
View File

@@ -38,11 +38,11 @@ const ServerDashboard = (props) => {
adminAsc = (e) => e.sort((a) => (a.admin ? 1 : -1)),
dateDesc = (e) =>
e.sort((a, b) =>
new Date(a.last_activity) - new Date(b.last_activity) > 0 ? -1 : 1
new Date(a.last_activity) - new Date(b.last_activity) > 0 ? -1 : 1,
),
dateAsc = (e) =>
e.sort((a, b) =>
new Date(a.last_activity) - new Date(b.last_activity) > 0 ? 1 : -1
new Date(a.last_activity) - new Date(b.last_activity) > 0 ? 1 : -1,
),
runningAsc = (e) => e.sort((a) => (a.server == null ? -1 : 1)),
runningDesc = (e) => e.sort((a) => (a.server == null ? 1 : -1));
@@ -136,7 +136,7 @@ const ServerDashboard = (props) => {
dispatchPageUpdate(
data.items,
data._pagination,
name_filter
name_filter,
);
})
.catch(() => {
@@ -176,7 +176,7 @@ const ServerDashboard = (props) => {
dispatchPageUpdate(
data.items,
data._pagination,
name_filter
name_filter,
);
})
.catch(() => {
@@ -471,7 +471,7 @@ const ServerDashboard = (props) => {
failedServers.length > 1 ? "servers" : "server"
}. ${
failedServers.length > 1 ? "Are they " : "Is it "
} already running?`
} already running?`,
);
}
return res;
@@ -482,11 +482,11 @@ const ServerDashboard = (props) => {
dispatchPageUpdate(
data.items,
data._pagination,
name_filter
name_filter,
);
})
.catch(() =>
setErrorAlert(`Failed to update users list.`)
setErrorAlert(`Failed to update users list.`),
);
return res;
})
@@ -511,7 +511,7 @@ const ServerDashboard = (props) => {
failedServers.length > 1 ? "servers" : "server"
}. ${
failedServers.length > 1 ? "Are they " : "Is it "
} already stopped?`
} already stopped?`,
);
}
return res;
@@ -522,11 +522,11 @@ const ServerDashboard = (props) => {
dispatchPageUpdate(
data.items,
data._pagination,
name_filter
name_filter,
);
})
.catch(() =>
setErrorAlert(`Failed to update users list.`)
setErrorAlert(`Failed to update users list.`),
);
return res;
})

14
jsx/src/components/ServerDashboard/ServerDashboard.test.js
View File

@@ -369,7 +369,7 @@ test("Shows a UI error dialogue when start all servers fails", async () => {
/>
</Switch>
</HashRouter>
</Provider>
</Provider>,
);
});
@@ -403,7 +403,7 @@ test("Shows a UI error dialogue when stop all servers fails", async () => {
/>
</Switch>
</HashRouter>
</Provider>
</Provider>,
);
});
@@ -437,7 +437,7 @@ test("Shows a UI error dialogue when start user server fails", async () => {
/>
</Switch>
</HashRouter>
</Provider>
</Provider>,
);
});
@@ -471,7 +471,7 @@ test("Shows a UI error dialogue when start user server returns an improper statu
/>
</Switch>
</HashRouter>
</Provider>
</Provider>,
);
});
@@ -505,7 +505,7 @@ test("Shows a UI error dialogue when stop user servers fails", async () => {
/>
</Switch>
</HashRouter>
</Provider>
</Provider>,
);
});
@@ -539,7 +539,7 @@ test("Shows a UI error dialogue when stop user server returns an improper status
/>
</Switch>
</HashRouter>
</Provider>
</Provider>,
);
});
@@ -585,7 +585,7 @@ test("Search for user calls updateUsers with name filter", async () => {
/>
</Switch>
</HashRouter>
</Provider>
</Provider>,
);
});

4
jsx/src/util/withAPI.js
View File

@@ -7,11 +7,11 @@ const withAPI = withProps(() => ({
`/users?include_stopped_servers&offset=${offset}&limit=${limit}&name_filter=${
name_filter || ""
}`,
"GET"
"GET",
).then((data) => data.json()),
updateGroups: (offset, limit) =>
jhapiRequest(`/groups?offset=${offset}&limit=${limit}`, "GET").then(
(data) => data.json()
(data) => data.json(),
),
shutdownHub: () => jhapiRequest("/shutdown", "POST"),
startServer: (name, serverName = "") =>

4
jsx/webpack.config.js
View File

@@ -41,10 +41,10 @@ module.exports = {
const app = devServer.app;
var user_data = JSON.parse(
'[{"kind":"user","name":"foo","admin":true,"groups":[],"server":"/user/foo/","pending":null,"created":"2020-12-07T18:46:27.112695Z","last_activity":"2020-12-07T21:00:33.336354Z","servers":{"":{"name":"","last_activity":"2020-12-07T20:58:02.437408Z","started":"2020-12-07T20:58:01.508266Z","pending":null,"ready":true,"state":{"pid":28085},"url":"/user/foo/","user_options":{},"progress_url":"/hub/api/users/foo/server/progress"}}},{"kind":"user","name":"bar","admin":false,"groups":[],"server":null,"pending":null,"created":"2020-12-07T18:46:27.115528Z","last_activity":"2020-12-07T20:43:51.013613Z","servers":{}}]'
'[{"kind":"user","name":"foo","admin":true,"groups":[],"server":"/user/foo/","pending":null,"created":"2020-12-07T18:46:27.112695Z","last_activity":"2020-12-07T21:00:33.336354Z","servers":{"":{"name":"","last_activity":"2020-12-07T20:58:02.437408Z","started":"2020-12-07T20:58:01.508266Z","pending":null,"ready":true,"state":{"pid":28085},"url":"/user/foo/","user_options":{},"progress_url":"/hub/api/users/foo/server/progress"}}},{"kind":"user","name":"bar","admin":false,"groups":[],"server":null,"pending":null,"created":"2020-12-07T18:46:27.115528Z","last_activity":"2020-12-07T20:43:51.013613Z","servers":{}}]',
);
var group_data = JSON.parse(
'[{"kind":"group","name":"testgroup","users":[]}, {"kind":"group","name":"testgroup2","users":["foo", "bar"]}]'
'[{"kind":"group","name":"testgroup","users":[]}, {"kind":"group","name":"testgroup2","users":["foo", "bar"]}]',
);
// get user_data

6
jsx/yarn.lock
View File

@@ -5046,9 +5046,9 @@ loader-runner@^4.2.0:
integrity sha512-3R/1M+yS3j5ou80Me59j7F9IMs4PXs3VqRrm0TU3AbKPxlmpoY1TNscJV/oGJXo8qCatFGTfDbY6W6ipGOYXfg==
loader-utils@^2.0.0:
version "2.0.2"
resolved "https://registry.yarnpkg.com/loader-utils/-/loader-utils-2.0.2.tgz#d6e3b4fb81870721ae4e0868ab11dd638368c129"
integrity sha512-TM57VeHptv569d/GKh6TAYdzKblwDNiumOdkFnejjD0XwTH87K90w3O7AiJRqdQoXygvi1VQTJTLGhJl7WqA7A==
version "2.0.4"
resolved "https://registry.yarnpkg.com/loader-utils/-/loader-utils-2.0.4.tgz#8b5cb38b5c34a9a018ee1fc0e6a066d1dfcc528c"
integrity sha512-xXqpXoINfFhgua9xiqD8fPFHgkoq1mmmpE92WlDbm9rNRd/EbRb+Gqf908T2DMfuHjjJlksiK2RbHVOdD/MqSw==
dependencies:
big.js "^5.2.2"
emojis-list "^3.0.0"

2
jupyterhub/__init__.py
View File

@@ -1 +1,3 @@
from ._version import __version__, version_info
__all__ = ["__version__", "version_info"]

3
jupyterhub/alembic/versions/19c0846f6344_base_revision_for_0_5.py
View File

@@ -11,9 +11,6 @@ down_revision = None
branch_labels = None
depends_on = None
import sqlalchemy as sa
from alembic import op
def upgrade():
pass

2
jupyterhub/apihandlers/__init__.py
View File

@@ -1,5 +1,5 @@
from . import auth, groups, hub, proxy, services, users
from .base import *
from .base import * # noqa
default_handlers = []
for mod in (auth, hub, proxy, users, groups, services):

1
jupyterhub/apihandlers/hub.py
View File

@@ -5,7 +5,6 @@ import json
import sys
from tornado import web
from tornado.ioloop import IOLoop
from .._version import __version__
from ..scopes import needs_scope

2
jupyterhub/auth.py
View File

@@ -776,8 +776,6 @@ def _deprecated_method(old_name, new_name, version):
return deprecated
import types
# deprecate white/blacklist method names
for _old_name, _new_name, _version in [
("check_whitelist", "check_allowed", "1.2"),

4
jupyterhub/handlers/__init__.py
View File

@@ -1,6 +1,6 @@
from . import base, login, metrics, pages
from .base import *
from .login import *
from .base import * # noqa
from .login import * # noqa
default_handlers = []
for mod in (base, pages, login, metrics):

1
jupyterhub/oauth/provider.py
View File

@@ -13,7 +13,6 @@ from ..scopes import (
_check_scopes_exist,
_resolve_requested_scopes,
access_scopes,
expand_scopes,
identify_scopes,
)
from ..utils import compare_token, hash_token

2
jupyterhub/orm.py
View File

@@ -35,7 +35,6 @@ from sqlalchemy.orm import (
sessionmaker,
)
from sqlalchemy.pool import StaticPool
from sqlalchemy.sql.expression import bindparam
from sqlalchemy.types import LargeBinary, Text, TypeDecorator
from tornado.log import app_log
@@ -996,7 +995,6 @@ def check_db_revision(engine):
).first()[0]
if alembic_revision == head:
app_log.debug("database schema version found: %s", alembic_revision)
pass
else:
raise DatabaseSchemaMismatch(
"Found database schema version {found} != {head}. "

4
jupyterhub/proxy.py
View File

@@ -250,14 +250,12 @@ class Proxy(LoggingConfigurable):
The proxy implementation should also have a way to associate the fact that a
route came from JupyterHub.
"""
pass
async def delete_route(self, routespec):
"""Delete a route with a given routespec if it exists.
**Subclasses must define this method**
"""
pass
async def get_all_routes(self):
"""Fetch and return all the routes associated by JupyterHub from the
@@ -274,7 +272,6 @@ class Proxy(LoggingConfigurable):
'data': the attached data dict for this route (as specified in add_route)
}
"""
pass
async def get_route(self, routespec):
"""Return the route info for a given routespec.
@@ -683,7 +680,6 @@ class ConfigurableHTTPProxy(Proxy):
os.remove(self.pid_file)
except FileNotFoundError:
self.log.debug("PID file %s already removed", self.pid_file)
pass
def _get_ssl_options(self):
"""List of cmd proxy options to use internal SSL"""

1
jupyterhub/services/auth.py
View File

@@ -35,7 +35,6 @@ import string
import time
import uuid
import warnings
from functools import partial
from http import HTTPStatus
from unittest import mock
from urllib.parse import urlencode

7
jupyterhub/singleuser/__init__.py
View File

@@ -5,6 +5,13 @@ Contains default notebook-app subclass and mixins
from .app import SingleUserNotebookApp, main
from .mixins import HubAuthenticatedHandler, make_singleuser_app
__all__ = [
"SingleUserNotebookApp",
"main",
"HubAuthenticatedHandler",
"make_singleuser_app",
]
# backward-compatibility
JupyterHubLoginHandler = SingleUserNotebookApp.login_handler_class
JupyterHubLogoutHandler = SingleUserNotebookApp.logout_handler_class

1
jupyterhub/singleuser/mixins.py
View File

@@ -14,7 +14,6 @@ import logging
import os
import random
import secrets
import ssl
import sys
import warnings
from datetime import timezone

2
jupyterhub/spawner.py
View File

@@ -896,7 +896,6 @@ class Spawner(LoggingConfigurable):
Override in subclasses to restore any extra state that is needed to track
the single-user server for that user. Subclasses should call super().
"""
pass
def get_state(self):
"""Save state of spawner into database.
@@ -1341,7 +1340,6 @@ class Spawner(LoggingConfigurable):
Stopping a server does *not* call this method.
"""
pass
def add_poll_callback(self, callback, *args, **kwargs):
"""Add a callback to fire when the single-user server stops"""

2
jupyterhub/tests/conftest.py
View File

@@ -27,7 +27,6 @@ Fixtures to add functionality or spawning behavior
# Distributed under the terms of the Modified BSD License.
import asyncio
import copy
import inspect
import os
import sys
from functools import partial
@@ -36,7 +35,6 @@ from subprocess import TimeoutExpired
from unittest import mock
from pytest import fixture, raises
from tornado import ioloop
from tornado.httpclient import HTTPError
from tornado.platform.asyncio import AsyncIOMainLoop

3
jupyterhub/tests/mocking.py
View File

@@ -36,7 +36,6 @@ from unittest import mock
from urllib.parse import urlparse
from pamela import PAMError
from tornado.ioloop import IOLoop
from traitlets import Bool, Dict, default
from .. import metrics, orm, roles
@@ -45,7 +44,7 @@ from ..auth import PAMAuthenticator
from ..singleuser import SingleUserNotebookApp
from ..spawner import SimpleLocalProcessSpawner
from ..utils import random_port, utcnow
from .utils import async_requests, public_host, public_url, ssl_setup
from .utils import async_requests, public_url, ssl_setup
def mock_authenticate(username, password, service, encoding):

1
jupyterhub/tests/populate_db.py
View File

@@ -4,7 +4,6 @@ Run with old versions of jupyterhub to test upgrade/downgrade
used in test_db.py
"""
import os
from datetime import datetime
from functools import partial

0
jupyterhub/tests/selenium/__init__.py Normal file
View File

12
jupyterhub/tests/selenium/conftest.py Normal file
View File

@@ -0,0 +1,12 @@
import pytest
from selenium import webdriver
@pytest.fixture()
def browser():
options = webdriver.FirefoxOptions()
options.headless = True
driver = webdriver.Firefox(options=options)
yield driver
driver.close()
driver.quit()

47
jupyterhub/tests/selenium/locators.py Normal file
View File

@@ -0,0 +1,47 @@
from selenium.webdriver.common.by import By
class LoginPageLocators:
"""class for handling the login page locators"""
FORM_LOGIN = (By.XPATH, '//*[@id="login-main"]/form')
SIGN_IN = (By.CLASS_NAME, 'auth-form-header')
ACCOUNT = (By.ID, "username_input")
PASSWORD = (By.ID, "password_input")
LOGIN_BUTTON = (By.ID, "login_submit")
LOGO = (By.ID, "jupyterhub-logo")
LOGO_LINK = (By.XPATH, '//*[@id="jupyterhub-logo"]/a')
LOGO_TITLE = (By.XPATH, '//*[@id="jupyterhub-logo"]/a/img')
ERROR_INVALID_CREDANTIALS = (By.CSS_SELECTOR, "p.login_error")
PAGE_TITLE = 'JupyterHub'
ERROR_MESSAGES_LOGIN = "Invalid username or password"
ERROR_403 = (By.CLASS_NAME, "error")
ERROR_MESSAGES_403 = (
"Action is not authorized with current scopes; requires any of [admin-ui]"
)
class HomePageLocators:
"""class for handling the home page locators"""
LINK_HOME_BAR = (By.CSS_SELECTOR, "div.container-fluid a")
LINK_HOME = (By.CSS_SELECTOR, "a[href*='/hub/home']")
LINK_TOKEN = (By.CSS_SELECTOR, "a[href*='/hub/token']")
BUTTON_LOGOUT = (By.ID, "logout")
BUTTON_START_SERVER = (By.ID, "start")
BUTTON_STOP_SERVER = (By.ID, "stop")
class TokenPageLocators:
"""class for handling the Token page locators"""
BUTTON_API_REQ = (By.XPATH, '//*[@id="request-token-form"]/div[1]/button')
INPUT_TOKEN = (By.ID, "token-note")
LIST_EXP_TOKEN_FIELD = (By.ID, "token-expiration-seconds")
LIST_EXP_TOKEN_OPT = (By.XPATH, '//option')
NEVER_EXP = (By.ID, "Never")
DAY1 = (By.ID, "3600")
PANEL_AREA = (By.ID, 'token-area')
PANEL_TOKEN = (By.CLASS_NAME, 'panel-heading')
RESULT_TOKEN = (By.ID, 'token-result')
TEXT = "Copy this token. You won't be able to see it again, but you can always come back here to get a new one."

237
jupyterhub/tests/selenium/test_browser.py Normal file
View File

@@ -0,0 +1,237 @@
import asyncio
from functools import partial
import pytest
from selenium.common.exceptions import NoSuchElementException
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.ui import WebDriverWait
from tornado.escape import url_escape
from tornado.httputil import url_concat
from jupyterhub.tests.selenium.locators import LoginPageLocators
from jupyterhub.utils import exponential_backoff
from ...utils import url_path_join
from ..utils import public_host, public_url, ujoin
pytestmark = pytest.mark.selenium
async def webdriver_wait(driver, condition, timeout=30):
"""an async wrapper for selenium's wait function,
a condition is something from selenium's expected_conditions"""
return await exponential_backoff(
partial(condition, driver),
timeout=timeout,
fail_message=f"WebDriver condition not met: {condition}",
)
def in_thread(f, *args, **kwargs):
"""Run a function in a background thread
via current event loop's run_in_executor
Returns asyncio.Future
"""
return asyncio.get_event_loop().run_in_executor(None, partial(f, *args, **kwargs))
async def open_url(app, browser, url="login"):
"""initiating open the login page in the browser"""
url = url_path_join(public_host(app), app.hub.base_url, url)
await in_thread(browser.get, url)
return url
def click(browser, by_locator):
"""wait for element to be visible, then click on it"""
WebDriverWait(browser, 10).until(
EC.visibility_of_element_located(by_locator)
).click()
def is_displayed(browser, by_locator):
"""Whether the element is visible or not"""
return (
WebDriverWait(browser, 10)
.until(EC.visibility_of_element_located(by_locator))
.is_displayed()
)
def send_text(browser, by_locator, text):
"""wait for element to be presented, then put the text in it"""
return (
WebDriverWait(browser, 10)
.until(EC.presence_of_element_located(by_locator))
.send_keys(text)
)
def clear(browser, by_locator):
"""wait for element to be presented, then clear the text in it"""
return (
WebDriverWait(browser, 10)
.until(EC.presence_of_element_located(by_locator))
.clear()
)
# LOGIN PAGE
async def test_elements_of_login_page(app, browser):
await open_url(app, browser)
assert is_displayed(browser, LoginPageLocators.LOGO)
logo_text = browser.find_element(*LoginPageLocators.LOGO).get_attribute("innerHTML")
async def login(browser, user, pass_w):
# fill in username field
send_text(browser, LoginPageLocators.ACCOUNT, user)
# fill in password field
send_text(browser, LoginPageLocators.PASSWORD, pass_w)
# click submit button
click(browser, LoginPageLocators.LOGIN_BUTTON)
await webdriver_wait(browser, EC.url_changes(browser.current_url))
async def test_submit_login_form(app, browser):
user = "test_user"
pass_w = "test_user"
await open_url(app, browser, url="login")
redirected_url = ujoin(public_url(app), f"/user/{user}/")
await login(browser, user, pass_w)
# verify url contains username
if f"/user/{user}/" not in browser.current_url:
await webdriver_wait(browser, EC.url_to_be(redirected_url))
else:
pass
assert browser.current_url == redirected_url
@pytest.mark.parametrize(
'url, params, redirected_url, form_action',
[
(
# spawn?param=value
# will encode given parameters for an unauthenticated URL in the next url
# the next parameter will contain the app base URL (replaces BASE_URL in tests)
'spawn',
[('param', 'value')],
'/hub/login?next={{BASE_URL}}hub%2Fspawn%3Fparam%3Dvalue',
'/hub/login?next={{BASE_URL}}hub%2Fspawn%3Fparam%3Dvalue',
),
(
# login?param=fromlogin&next=encoded(/hub/spawn?param=value)
# will drop parameters given to the login page, passing only the next url
'login',
[('param', 'fromlogin'), ('next', '/hub/spawn?param=value')],
'/hub/login?param=fromlogin&next=%2Fhub%2Fspawn%3Fparam%3Dvalue',
'/hub/login?next=%2Fhub%2Fspawn%3Fparam%3Dvalue',
),
(
# login?param=value&anotherparam=anothervalue
# will drop parameters given to the login page, and use an empty next url
'login',
[('param', 'value'), ('anotherparam', 'anothervalue')],
'/hub/login?param=value&anotherparam=anothervalue',
'/hub/login?next=',
),
(
# login
# simplest case, accessing the login URL, gives an empty next url
'login',
[],
'/hub/login',
'/hub/login?next=',
),
],
)
async def test_open_url_login(
app,
browser,
url,
params,
redirected_url,
form_action,
user='test_user',
pass_w='test_user',
):
url = url_path_join(public_host(app), app.hub.base_url, url)
url_new = url_concat(url, params)
await in_thread(browser.get, url_new)
redirected_url = redirected_url.replace('{{BASE_URL}}', url_escape(app.base_url))
form_action = form_action.replace('{{BASE_URL}}', url_escape(app.base_url))
form = browser.find_element(*LoginPageLocators.FORM_LOGIN).get_attribute('action')
# verify title / url
assert browser.title == LoginPageLocators.PAGE_TITLE
assert form.endswith(form_action)
# login in with params
await login(browser, user, pass_w)
# verify next url + params
next_url = browser.current_url
if url_escape(app.base_url) in form_action:
assert next_url.endswith("param=value")
elif "next=%2Fhub" in form_action:
assert next_url.endswith("spawn?param=value")
assert f"user/{user}/" not in next_url
else:
if not next_url.endswith(f"/user/{user}/"):
await webdriver_wait(
browser, EC.url_to_be(ujoin(public_url(app), f"/user/{user}/"))
)
next_url = browser.current_url
assert next_url.endswith(f"/user/{user}/")
@pytest.mark.parametrize(
"user, pass_w",
[
(" ", ""),
("user", ""),
(" ", "password"),
("user", "password"),
],
)
async def test_invalid_credantials(app, browser, user, pass_w):
await open_url(app, browser)
await login(browser, user, pass_w)
await asyncio.sleep(0.1)
"""adding for a catching of the reflected error"""
try:
error = browser.find_element(*LoginPageLocators.ERROR_INVALID_CREDANTIALS)
await webdriver_wait(browser, EC.visibility_of(error))
except NoSuchElementException:
error = None
# verify error message and url still eguals to the login page
assert LoginPageLocators.ERROR_MESSAGES_LOGIN == error.text
assert 'hub/login' in browser.current_url
# HOME PAGE
async def open_home_page(app, browser, user="test_user", pass_w="test_user"):
url = url_path_join(public_host(app), app.hub.base_url, "/login?next=/hub/home")
await in_thread(browser.get, url)
redirected_url = url_path_join(public_host(app), app.base_url, '/hub/home')
await login(browser, user, pass_w)
await in_thread(browser.get, redirected_url)
# TOKEN PAGE
async def open_token_page(app, browser, user="test_user", pass_w="test_user"):
url = url_path_join(public_host(app), app.hub.base_url, "/login?next=/hub/token")
await in_thread(browser.get, url)
redirected_url = url_path_join(public_host(app), app.base_url, '/hub/token')
await login(browser, user, pass_w)
await in_thread(browser.get, redirected_url)

11
jupyterhub/tests/test_api.py
View File

@@ -19,8 +19,15 @@ from ..objects import Server
from ..utils import url_path_join as ujoin
from ..utils import utcnow
from .conftest import new_username
from .mocking import public_host, public_url
from .utils import add_user, api_request, async_requests, auth_header, find_user
from .utils import (
add_user,
api_request,
async_requests,
auth_header,
find_user,
public_host,
public_url,
)
# --------------------
# Authentication tests

1
jupyterhub/tests/test_auth_expiry.py
View File

@@ -7,7 +7,6 @@ authentication can expire in a number of ways:
- doesn't need refresh
- needs refresh and cannot be refreshed without new login
"""
from contextlib import contextmanager
from unittest import mock
from urllib.parse import parse_qs, urlparse

2
jupyterhub/tests/test_eventlog.py
View File

@@ -14,8 +14,6 @@ import jsonschema
import pytest
from traitlets.config import Config
from .mocking import MockHub
# To test new schemas, add them to the `valid_events`
# and `invalid_events` dictionary below.

4
jupyterhub/tests/test_named_servers.py
View File

@@ -11,9 +11,9 @@ from tornado.httputil import url_concat
from .. import orm
from ..utils import url_escape_path, url_path_join
from .mocking import FormSpawner, public_url
from .mocking import FormSpawner
from .test_api import TIMESTAMP, add_user, api_request, fill_user, normalize_user
from .utils import async_requests, get_page
from .utils import async_requests, get_page, public_url
@pytest.fixture

1
jupyterhub/tests/test_orm.py
View File

@@ -7,7 +7,6 @@ from datetime import datetime, timedelta
from unittest import mock
import pytest
from tornado import gen
from .. import crypto, objects, orm, roles
from ..emptyclass import EmptyClass

2
jupyterhub/tests/test_services.py
View File

@@ -6,8 +6,6 @@ from subprocess import Popen
from async_generator import asynccontextmanager
from .. import orm
from ..roles import roles_to_scopes
from ..utils import (
exponential_backoff,
maybe_future,

2
jupyterhub/tests/test_singleuser.py
View File

@@ -1,7 +1,7 @@
"""Tests for jupyterhub.singleuser"""
import os
import sys
from contextlib import contextmanager, nullcontext
from contextlib import nullcontext
from subprocess import CalledProcessError, check_output
from unittest import mock
from urllib.parse import urlencode, urlparse

Some files were not shown because too many files have changed in this diff Show More