Repository: mozilla/jupyter-spark Branch: master Commit: f7814f617204 Files: 20 Total size: 47.6 KB Directory structure: gitextract_apq7qxov/ ├── .coveragerc ├── .eslintrc.json ├── .gitignore ├── .travis.yml ├── CODE_OF_CONDUCT.md ├── LICENSE ├── MANIFEST.in ├── Makefile ├── README.md ├── examples/ │ └── Jupyter Spark example.ipynb ├── package.json ├── pytest.ini ├── setup.cfg ├── setup.py ├── src/ │ └── jupyter_spark/ │ ├── __init__.py │ ├── handlers.py │ ├── spark.py │ └── static/ │ └── extension.js ├── tests/ │ └── test_spark.py └── tox.ini ================================================ FILE CONTENTS ================================================ ================================================ FILE: .coveragerc ================================================ [run] branch = True source = jupyter_spark [paths] source = .tox/*/lib/python*/site-packages/jupyter_spark .tox/pypy*/site-packages/jupyter_spark [report] show_missing = True ================================================ FILE: .eslintrc.json ================================================ { "env": { "browser": true, "jquery": true, "amd": true }, "plugins": [ "amd-imports" ], "extends": "eslint:recommended", "rules": { "indent": [ "error", 4 ], "linebreak-style": [ "error", "unix" ] } } ================================================ FILE: .gitignore ================================================ # Byte-compiled / optimized / DLL files __pycache__/ *.py[cod] *$py.class # C extensions *.so # Distribution / packaging .Python env/ build/ develop-eggs/ dist/ downloads/ eggs/ .eggs/ lib/ lib64/ parts/ sdist/ var/ *.egg-info/ .installed.cfg *.egg # PyInstaller # Usually these files are written by a python script from a template # before PyInstaller builds the exe, so as to inject date/other infos into it. *.manifest *.spec # Installer logs pip-log.txt pip-delete-this-directory.txt # Unit test / coverage reports htmlcov/ .tox/ .coverage .coverage.* .cache nosetests.xml coverage.xml *,cover .hypothesis/ # Translations *.mo *.pot # Django stuff: *.log # Sphinx documentation docs/_build/ # PyBuilder target/ #Ipython Notebook .ipynb_checkpoints node_modules/ ================================================ FILE: .travis.yml ================================================ language: python sudo: false cache: pip python: - '2.7' - '3.4' - '3.5' - '3.6' - pypy install: - pip install tox-travis script: - tox -v after_success: - bash <(curl -s https://codecov.io/bash) jobs: include: - stage: deploy python: '3.5' script: skip deploy: provider: pypi user: jezdez distributions: sdist bdist_wheel password: secure: 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 on: tags: true repo: mozilla/jupyter-spark matrix: include: - env: eslint sudo: false cache: directories: - node_modules # NPM packages install: - nvm install 8 - npm install script: - node ./node_modules/eslint/bin/eslint.js --ext .js src/jupyter_spark/static allow_failures: - env: eslint ================================================ FILE: CODE_OF_CONDUCT.md ================================================ # Community Participation Guidelines This repository is governed by Mozilla's code of conduct and etiquette guidelines. For more details, please read the [Mozilla Community Participation Guidelines](https://www.mozilla.org/about/governance/policies/participation/). ## How to Report For more information on how to report violations of the Community Participation Guidelines, please read our '[How to Report](https://www.mozilla.org/about/governance/policies/participation/reporting/)' page. ================================================ FILE: LICENSE ================================================ Mozilla Public License Version 2.0 ================================== 1. Definitions -------------- 1.1. "Contributor" means each individual or legal entity that creates, contributes to the creation of, or owns Covered Software. 1.2. "Contributor Version" means the combination of the Contributions of others (if any) used by a Contributor and that particular Contributor's Contribution. 1.3. "Contribution" means Covered Software of a particular Contributor. 1.4. "Covered Software" means Source Code Form to which the initial Contributor has attached the notice in Exhibit A, the Executable Form of such Source Code Form, and Modifications of such Source Code Form, in each case including portions thereof. 1.5. "Incompatible With Secondary Licenses" means (a) that the initial Contributor has attached the notice described in Exhibit B to the Covered Software; or (b) that the Covered Software was made available under the terms of version 1.1 or earlier of the License, but not also under the terms of a Secondary License. 1.6. "Executable Form" means any form of the work other than Source Code Form. 1.7. "Larger Work" means a work that combines Covered Software with other material, in a separate file or files, that is not Covered Software. 1.8. "License" means this document. 1.9. "Licensable" means having the right to grant, to the maximum extent possible, whether at the time of the initial grant or subsequently, any and all of the rights conveyed by this License. 1.10. "Modifications" means any of the following: (a) any file in Source Code Form that results from an addition to, deletion from, or modification of the contents of Covered Software; or (b) any new file in Source Code Form that contains any Covered Software. 1.11. "Patent Claims" of a Contributor means any patent claim(s), including without limitation, method, process, and apparatus claims, in any patent Licensable by such Contributor that would be infringed, but for the grant of the License, by the making, using, selling, offering for sale, having made, import, or transfer of either its Contributions or its Contributor Version. 1.12. "Secondary License" means either the GNU General Public License, Version 2.0, the GNU Lesser General Public License, Version 2.1, the GNU Affero General Public License, Version 3.0, or any later versions of those licenses. 1.13. "Source Code Form" means the form of the work preferred for making modifications. 1.14. "You" (or "Your") means an individual or a legal entity exercising rights under this License. For legal entities, "You" includes any entity that controls, is controlled by, or is under common control with You. For purposes of this definition, "control" means (a) the power, direct or indirect, to cause the direction or management of such entity, whether by contract or otherwise, or (b) ownership of more than fifty percent (50%) of the outstanding shares or beneficial ownership of such entity. 2. License Grants and Conditions -------------------------------- 2.1. Grants Each Contributor hereby grants You a world-wide, royalty-free, non-exclusive license: (a) under intellectual property rights (other than patent or trademark) Licensable by such Contributor to use, reproduce, make available, modify, display, perform, distribute, and otherwise exploit its Contributions, either on an unmodified basis, with Modifications, or as part of a Larger Work; and (b) under Patent Claims of such Contributor to make, use, sell, offer for sale, have made, import, and otherwise transfer either its Contributions or its Contributor Version. 2.2. Effective Date The licenses granted in Section 2.1 with respect to any Contribution become effective for each Contribution on the date the Contributor first distributes such Contribution. 2.3. Limitations on Grant Scope The licenses granted in this Section 2 are the only rights granted under this License. No additional rights or licenses will be implied from the distribution or licensing of Covered Software under this License. Notwithstanding Section 2.1(b) above, no patent license is granted by a Contributor: (a) for any code that a Contributor has removed from Covered Software; or (b) for infringements caused by: (i) Your and any other third party's modifications of Covered Software, or (ii) the combination of its Contributions with other software (except as part of its Contributor Version); or (c) under Patent Claims infringed by Covered Software in the absence of its Contributions. This License does not grant any rights in the trademarks, service marks, or logos of any Contributor (except as may be necessary to comply with the notice requirements in Section 3.4). 2.4. Subsequent Licenses No Contributor makes additional grants as a result of Your choice to distribute the Covered Software under a subsequent version of this License (see Section 10.2) or under the terms of a Secondary License (if permitted under the terms of Section 3.3). 2.5. Representation Each Contributor represents that the Contributor believes its Contributions are its original creation(s) or it has sufficient rights to grant the rights to its Contributions conveyed by this License. 2.6. Fair Use This License is not intended to limit any rights You have under applicable copyright doctrines of fair use, fair dealing, or other equivalents. 2.7. Conditions Sections 3.1, 3.2, 3.3, and 3.4 are conditions of the licenses granted in Section 2.1. 3. Responsibilities ------------------- 3.1. Distribution of Source Form All distribution of Covered Software in Source Code Form, including any Modifications that You create or to which You contribute, must be under the terms of this License. You must inform recipients that the Source Code Form of the Covered Software is governed by the terms of this License, and how they can obtain a copy of this License. You may not attempt to alter or restrict the recipients' rights in the Source Code Form. 3.2. Distribution of Executable Form If You distribute Covered Software in Executable Form then: (a) such Covered Software must also be made available in Source Code Form, as described in Section 3.1, and You must inform recipients of the Executable Form how they can obtain a copy of such Source Code Form by reasonable means in a timely manner, at a charge no more than the cost of distribution to the recipient; and (b) You may distribute such Executable Form under the terms of this License, or sublicense it under different terms, provided that the license for the Executable Form does not attempt to limit or alter the recipients' rights in the Source Code Form under this License. 3.3. Distribution of a Larger Work You may create and distribute a Larger Work under terms of Your choice, provided that You also comply with the requirements of this License for the Covered Software. If the Larger Work is a combination of Covered Software with a work governed by one or more Secondary Licenses, and the Covered Software is not Incompatible With Secondary Licenses, this License permits You to additionally distribute such Covered Software under the terms of such Secondary License(s), so that the recipient of the Larger Work may, at their option, further distribute the Covered Software under the terms of either this License or such Secondary License(s). 3.4. Notices You may not remove or alter the substance of any license notices (including copyright notices, patent notices, disclaimers of warranty, or limitations of liability) contained within the Source Code Form of the Covered Software, except that You may alter any license notices to the extent required to remedy known factual inaccuracies. 3.5. Application of Additional Terms You may choose to offer, and to charge a fee for, warranty, support, indemnity or liability obligations to one or more recipients of Covered Software. However, You may do so only on Your own behalf, and not on behalf of any Contributor. You must make it absolutely clear that any such warranty, support, indemnity, or liability obligation is offered by You alone, and You hereby agree to indemnify every Contributor for any liability incurred by such Contributor as a result of warranty, support, indemnity or liability terms You offer. You may include additional disclaimers of warranty and limitations of liability specific to any jurisdiction. 4. Inability to Comply Due to Statute or Regulation --------------------------------------------------- If it is impossible for You to comply with any of the terms of this License with respect to some or all of the Covered Software due to statute, judicial order, or regulation then You must: (a) comply with the terms of this License to the maximum extent possible; and (b) describe the limitations and the code they affect. Such description must be placed in a text file included with all distributions of the Covered Software under this License. Except to the extent prohibited by statute or regulation, such description must be sufficiently detailed for a recipient of ordinary skill to be able to understand it. 5. Termination -------------- 5.1. The rights granted under this License will terminate automatically if You fail to comply with any of its terms. However, if You become compliant, then the rights granted under this License from a particular Contributor are reinstated (a) provisionally, unless and until such Contributor explicitly and finally terminates Your grants, and (b) on an ongoing basis, if such Contributor fails to notify You of the non-compliance by some reasonable means prior to 60 days after You have come back into compliance. Moreover, Your grants from a particular Contributor are reinstated on an ongoing basis if such Contributor notifies You of the non-compliance by some reasonable means, this is the first time You have received notice of non-compliance with this License from such Contributor, and You become compliant prior to 30 days after Your receipt of the notice. 5.2. If You initiate litigation against any entity by asserting a patent infringement claim (excluding declaratory judgment actions, counter-claims, and cross-claims) alleging that a Contributor Version directly or indirectly infringes any patent, then the rights granted to You by any and all Contributors for the Covered Software under Section 2.1 of this License shall terminate. 5.3. In the event of termination under Sections 5.1 or 5.2 above, all end user license agreements (excluding distributors and resellers) which have been validly granted by You or Your distributors under this License prior to termination shall survive termination. ************************************************************************ * * * 6. Disclaimer of Warranty * * ------------------------- * * * * Covered Software is provided under this License on an "as is" * * basis, without warranty of any kind, either expressed, implied, or * * statutory, including, without limitation, warranties that the * * Covered Software is free of defects, merchantable, fit for a * * particular purpose or non-infringing. The entire risk as to the * * quality and performance of the Covered Software is with You. * * Should any Covered Software prove defective in any respect, You * * (not any Contributor) assume the cost of any necessary servicing, * * repair, or correction. This disclaimer of warranty constitutes an * * essential part of this License. No use of any Covered Software is * * authorized under this License except under this disclaimer. * * * ************************************************************************ ************************************************************************ * * * 7. Limitation of Liability * * -------------------------- * * * * Under no circumstances and under no legal theory, whether tort * * (including negligence), contract, or otherwise, shall any * * Contributor, or anyone who distributes Covered Software as * * permitted above, be liable to You for any direct, indirect, * * special, incidental, or consequential damages of any character * * including, without limitation, damages for lost profits, loss of * * goodwill, work stoppage, computer failure or malfunction, or any * * and all other commercial damages or losses, even if such party * * shall have been informed of the possibility of such damages. This * * limitation of liability shall not apply to liability for death or * * personal injury resulting from such party's negligence to the * * extent applicable law prohibits such limitation. Some * * jurisdictions do not allow the exclusion or limitation of * * incidental or consequential damages, so this exclusion and * * limitation may not apply to You. * * * ************************************************************************ 8. Litigation ------------- Any litigation relating to this License may be brought only in the courts of a jurisdiction where the defendant maintains its principal place of business and such litigation shall be governed by laws of that jurisdiction, without reference to its conflict-of-law provisions. Nothing in this Section shall prevent a party's ability to bring cross-claims or counter-claims. 9. Miscellaneous ---------------- This License represents the complete agreement concerning the subject matter hereof. If any provision of this License is held to be unenforceable, such provision shall be reformed only to the extent necessary to make it enforceable. Any law or regulation which provides that the language of a contract shall be construed against the drafter shall not be used to construe this License against a Contributor. 10. Versions of the License --------------------------- 10.1. New Versions Mozilla Foundation is the license steward. Except as provided in Section 10.3, no one other than the license steward has the right to modify or publish new versions of this License. Each version will be given a distinguishing version number. 10.2. Effect of New Versions You may distribute the Covered Software under the terms of the version of the License under which You originally received the Covered Software, or under the terms of any subsequent version published by the license steward. 10.3. Modified Versions If you create software not governed by this License, and you want to create a new license for such software, you may create and use a modified version of this License if you rename the license and remove any references to the name of the license steward (except to note that such modified license differs from this License). 10.4. Distributing Source Code Form that is Incompatible With Secondary Licenses If You choose to distribute Source Code Form that is Incompatible With Secondary Licenses under the terms of this version of the License, the notice described in Exhibit B of this License must be attached. Exhibit A - Source Code Form License Notice ------------------------------------------- This Source Code Form is subject to the terms of the Mozilla Public License, v. 2.0. If a copy of the MPL was not distributed with this file, You can obtain one at http://mozilla.org/MPL/2.0/. If it is not possible or desirable to put the notice in a particular file, then You may include the notice in a location (such as a LICENSE file in a relevant directory) where a recipient would be likely to look for such a notice. You may add additional accurate notices of copyright ownership. Exhibit B - "Incompatible With Secondary Licenses" Notice --------------------------------------------------------- This Source Code Form is "Incompatible With Secondary Licenses", as defined by the Mozilla Public License, v. 2.0. ================================================ FILE: MANIFEST.in ================================================ include README.md recursive-include src *.js recursive-include tests *.py recursive-include notebooks *.ipynb recursive-include screenshots *.png ================================================ FILE: Makefile ================================================ .PHONY: install build uninstall enable clean dev install: jupyter serverextension enable --py jupyter_spark jupyter nbextension install --py jupyter_spark jupyter nbextension enable --py jupyter_spark uninstall: jupyter serverextension disable --py jupyter_spark jupyter nbextension disable --py jupyter_spark jupyter nbextension uninstall --py jupyter_spark pip uninstall -y jupyter-spark clean: uninstall rm -rf dist/ build: clean python setup.py sdist pip install dist/*.tar.gz dev: build install notebook: jupyter notebook ================================================ FILE: README.md ================================================ # jupyter-spark [![No Maintenance Intended](http://unmaintained.tech/badge.svg)](http://unmaintained.tech/) [![Build Status](https://travis-ci.org/mozilla/jupyter-spark.svg?branch=master)](https://travis-ci.org/mozilla/jupyter-spark) [![codecov](https://codecov.io/gh/mozilla/jupyter-spark/branch/master/graph/badge.svg)](https://codecov.io/gh/mozilla/jupyter-spark) **NOTE: This project is currently unmaintained, if anyone would like to take over maintenance please [let us know](https://github.com/mozilla/jupyter-spark/issues/55).** Jupyter Notebook extension for Apache Spark integration. Includes a progress indicator for the current Notebook cell if it invokes a Spark job. Queries the Spark UI service on the backend to get the required Spark job information. ![Alt text](/screenshots/ProgressBar.png?raw=true "Spark progress bar") To view all currently running jobs, click the "show running Spark jobs" button, or press ```Alt+S```. ![Alt text](/screenshots/SparkButton.png?raw=true "show running Spark jobs button") ![Alt text](/screenshots/Dialog.png?raw=true "Spark dialog") A proxied version of the Spark UI can be accessed at http://localhost:8888/spark. ## Installation To install, simply run: ``` pip install jupyter-spark jupyter serverextension enable --py jupyter_spark jupyter nbextension install --py jupyter_spark jupyter nbextension enable --py jupyter_spark jupyter nbextension enable --py widgetsnbextension ``` The last step is needed to enable the `widgetsnbextension` extension that Jupyter-Spark depends on. It may have been enabled before by a different extension. You may want to append ``--user`` to the commands above if you're getting configuration errors upon invoking them. To double-check if the extension was correctly installed run: ``` jupyter nbextension list jupyter serverextension list ``` Pleaes feel free to install [lxml](http://lxml.de/) as well to improve performance of the server side communication to Spark using your favorite package manager, e.g.: ``` pip install lxml ``` For development and testing, clone the project and run from a shell in the project's root directory: ``` pip install -e . jupyter serverextension enable --py jupyter_spark jupyter nbextension install --py jupyter_spark jupyter nbextension enable --py jupyter_spark ``` To uninstall the extension run: ``` jupyter serverextension disable --py jupyter_spark jupyter nbextension disable --py jupyter_spark jupyter nbextension uninstall --py jupyter_spark pip uninstall jupyter-spark ``` ## Configuration To change the URL of the Spark API that the job metadata is fetched from override the `Spark.url` config value, e.g. on the command line: ``` jupyter notebook --Spark.url="http://localhost:4040" ``` ## Example There is a simple `pyspark` example included in `examples` to confirm that your installation is working. ## Changelog ### 0.3.0 (2016-07-04) - Rewrote proxy to use an async Tornado handler and HTTP client to fetch responses from Spark. - Simplified proxy processing to take Amazon EMR proxying into account - Extended test suite to cover proxy handler, too. - Removed requests as a dependency. ### 0.2.0 (2016-06-30) - Refactored to fix a bunch of Python packaging and code quality issues - Added test suite for Python code - Set up continuous integration: https://travis-ci.org/mozilla/jupyter-spark - Set up code coverage reports: https://codecov.io/gh/mozilla/jupyter-spark - Added ability to override Spark API URL via command line option - **IMPORTANT** Requires manual step to enable after running pip install (see installation docs)! To update: 1. Run `pip uninstall jupyter-spark` 2. Delete `spark.js` from your `nbextensions` folder. 3. Delete any references to `jupyter_spark.spark` in `jupyter_notebook_config.json` (in your .jupyter directory) 4. Delete any references to `spark` in `notebook.json` (in .jupyter/nbconfig) 5. Follow installation instructions to reinstall ### 0.1.1 (2016-05-03) - Initial release with a working prototype ================================================ FILE: examples/Jupyter Spark example.ipynb ================================================ { "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "## Example jupyter_spark notebook\n", "\n", "This is an example notebook to demonstrate the `jupyter_spark` notebook plugin.\n", "\n", "It is based on the [approximating pi](https://github.com/apache/spark/blob/master/examples/src/main/python/pi.py) example in the pyspark documentation. This works by sampling random numbers in a square and counting the number that fall inside the unit circle." ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "import sys\n", "from random import random\n", "from operator import add\n", "\n", "from pyspark.sql import SparkSession" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Create a `SparkSession` and give it a name.\n", "\n", "Note: This will start the spark client console -- there is no need to run `spark-shell` directly." ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "scrolled": true }, "outputs": [], "source": [ "spark = SparkSession \\\n", " .builder \\\n", " .appName(\"PythonPi\") \\\n", " .getOrCreate()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "`partitions` is the number of spark workers to partition the work into." ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "partitions = 2" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "`n` is the number of random samples to calculate" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [], "source": [ "n = 100000000" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "This is the sampling function. It generates numbers in the square from (-1, -1) to (1, 1), and returns 1 if it falls inside the unit circle, and 0 otherwise." ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [], "source": [ "def f(_):\n", " x = random() * 2 - 1\n", " y = random() * 2 - 1\n", " return 1 if x ** 2 + y ** 2 <= 1 else 0" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Here's where we farm the work out to Spark." ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [], "source": [ "count = spark.sparkContext \\\n", " .parallelize(range(1, n + 1), partitions) \\\n", " .map(f) \\\n", " .reduce(add)" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Pi is roughly 3.141880\n" ] } ], "source": [ "print(\"Pi is roughly %f\" % (4.0 * count / n))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Shut down the spark server." ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [], "source": [ "spark.stop()" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.6.4" } }, "nbformat": 4, "nbformat_minor": 2 } ================================================ FILE: package.json ================================================ { "devDependencies": { "eslint": "^4.17.0", "eslint-plugin-amd-imports": "^4.0.0" } } ================================================ FILE: pytest.ini ================================================ [pytest] addopts = -v --flake8 --isort --cov-report xml --cov-report=term-missing --cov=jupyter_spark --cov-config .coveragerc norecursedirs = *.egg .eggs dist build docs .tox flake8-ignore = E501 ================================================ FILE: setup.cfg ================================================ [wheel] universal = 1 ================================================ FILE: setup.py ================================================ from setuptools import find_packages, setup setup( name='jupyter-spark', use_scm_version={ 'version_scheme': 'post-release', 'local_scheme': 'dirty-tag' }, setup_requires=['setuptools_scm'], description='Jupyter Notebook extension for Apache Spark integration', author='Mozilla Firefox Data Platform', author_email='fx-data-platform@mozilla.com', packages=find_packages(where='src'), package_dir={'': 'src'}, include_package_data=True, license='MPL2', install_requires=[ 'ipython >= 4', 'jupyter', 'notebook >= 4.2', 'beautifulsoup4', 'widgetsnbextension', ], url='https://github.com/mozilla/jupyter-spark', zip_safe=False, ) ================================================ FILE: src/jupyter_spark/__init__.py ================================================ from pkg_resources import get_distribution, DistributionNotFound try: __version__ = get_distribution(__name__).version except DistributionNotFound: # package is not installed pass def _jupyter_nbextension_paths(): # pragma: no cover return [{ 'section': 'notebook', # the path is relative to the `jupyter_spark` directory 'src': 'static', # directory in the `nbextension/` namespace 'dest': 'jupyter-spark', # _also_ in the `nbextension/` namespace 'require': 'jupyter-spark/extension', }] def _jupyter_server_extension_paths(): # pragma: no cover return [{ 'module': 'jupyter_spark', }] def load_jupyter_server_extension(nbapp): # pragma: no cover from .spark import Spark from .handlers import SparkHandler spark = Spark( # add access to NotebookApp config, too parent=nbapp, base_url=nbapp.web_app.settings['base_url'], ) nbapp.web_app.add_handlers( r'.*', # match any host [(spark.proxy_url + '.*', SparkHandler, {'spark': spark})] ) nbapp.log.info("Jupyter-Spark enabled!") ================================================ FILE: src/jupyter_spark/handlers.py ================================================ import json import tornado.web from notebook.base.handlers import IPythonHandler from tornado import httpclient class SparkHandler(IPythonHandler): def initialize(self, spark): self.spark = spark @tornado.web.asynchronous def get(self): """ Fetch the requested URI from the Spark API, replace the URLs in the response content for HTML responses or return the verbatim response. """ http = httpclient.AsyncHTTPClient() url = self.spark.backend_url(self.request) self.spark.log.debug('Fetching from Spark %s', url) http.fetch(url, self.handle_response) def handle_response(self, response): if response.error: content_type = 'application/json' content = json.dumps({'error': 'SPARK_NOT_RUNNING'}) else: content_type = response.headers['Content-Type'] if 'text/html' in content_type: content = self.spark.replace(response.body) else: # Probably binary response, send it directly. content = response.body self.set_header('Content-Type', content_type) self.write(content) self.finish() ================================================ FILE: src/jupyter_spark/spark.py ================================================ import re from bs4 import BeautifulSoup from notebook.utils import url_path_join from traitlets.config import LoggingConfigurable from traitlets.traitlets import Unicode # try importing lxml and use it as the BeautifulSoup builder if available try: import lxml # noqa except ImportError: BEAUTIFULSOUP_BUILDER = 'html.parser' else: BEAUTIFULSOUP_BUILDER = 'lxml' # pragma: no cover # a regular expression to match paths against the Spark on EMR proxy paths PROXY_PATH_RE = re.compile(r'\/proxy\/application_\d+_\d+\/(.*)') # a tuple of tuples with tag names and their attribute to automatically fix PROXY_ATTRIBUTES = ( (('a', 'link'), 'href'), (('img', 'script'), 'src'), ) class Spark(LoggingConfigurable): """ A config object that is able to replace URLs of the Spark frontend on the fly. """ url = Unicode( 'http://localhost:4040', help='The URL of Spark API', ).tag(config=True) proxy_root = Unicode( '/spark', help='The URL path under which the Spark API will be proxied', ) def __init__(self, *args, **kwargs): self.base_url = kwargs.pop('base_url') super(Spark, self).__init__(*args, **kwargs) self.proxy_url = url_path_join(self.base_url, self.proxy_root) def backend_url(self, request): request_path = request.uri[len(self.proxy_url):] return url_path_join(self.url, request_path) def replace(self, content): """ Replace all the links with our prefixed handler links, e.g.: /proxy/application_1467283586194_0015/static/styles.css' or /static/styles.css with /spark/static/styles.css """ soup = BeautifulSoup(content, BEAUTIFULSOUP_BUILDER) for tags, attribute in PROXY_ATTRIBUTES: for tag in soup.find_all(tags, **{attribute: True}): value = tag[attribute] match = PROXY_PATH_RE.match(value) if match is not None: value = match.groups()[0] tag[attribute] = url_path_join(self.proxy_root, value) return str(soup) ================================================ FILE: src/jupyter_spark/static/extension.js ================================================ var UPDATE_FREQUENCY = 10000; // ms var UPDATE_FREQUENCY_ACTIVE = 500; var PROGRESS_COUNT_TEXT = "Running Spark job "; /* cache is an array of application objects with an added property jobs. application.jobs is the result of the /applications/applicationId/jobs API request. */ var cache = []; var current_update_frequency; var spark_is_running = false; var cell_queue = []; var current_cell; var cell_jobs_counter = 0; var jobs_in_cache = 0; var update = function(api_url) { update_cache(api_url, update_dialog_contents); }; // callbacks follows jQuery callback style, can be either single function or array of functions // callbacks will be passed the cache as a parameter var update_cache = function(api_url, callbacks) { var cbs; if (callbacks) { cbs = $.Callbacks(); cbs.add(callbacks); } $.getJSON(api_url + '/applications').done(function(applications) { var num_applications = cache.length; var num_completed = 0; // Check if Spark is running before processing applications if(!applications.hasOwnProperty('error')){ spark_is_running = true; applications.forEach(function(application, i) { $.getJSON(api_url + '/applications/' + application.id + '/jobs').done(function (jobs) { cache[i] = application; cache[i].jobs = jobs; num_completed++; if (num_completed === num_applications && cbs) { cbs.fire(cache); } // Update progress bars if jobs have been run and there are cells to be updated if (jobs.length > jobs_in_cache && cell_queue.length > 0 ) { $(document).trigger('update.progress.bar'); } }); }); } else { spark_is_running = false; } }); }; var update_dialog_contents = function() { if ($('#dialog_contents').length) { var element = $('
').attr('id', 'dialog_contents'); cache.forEach(function(application){ element.append(create_application_table(application)); }); $('#dialog_contents').replaceWith(element); } }; var create_application_table = function(e) { var application_div = $('
'); application_div.append($('
').text(e.name + ': ' + e.id)); var application_table = $('').addClass('table table-hover'); var header_row = $(''); header_row.append($(''); row.append($('
').text('Job ID')); header_row.append($('').text('Job Name')); header_row.append($('').text('Progress')); application_table.append(header_row); e.jobs.forEach(function(job) { application_table.append(create_table_row(job)); }); application_div.append(application_table); return application_div; }; var create_table_row = function(e) { var row = $('
').text(e.jobId)); row.append($('').text(e.name)); var status_class = get_status_class(e.status); var progress_bar_div = create_progress_bar(status_class, e.numCompletedTasks, e.numTasks); row.append($('').append(progress_bar_div)); return row; }; var get_status_class = function(status) { var status_class; switch(status) { case 'SUCCEEDED': status_class = 'progress-bar-success'; break; case 'RUNNING': status_class = 'progress-bar-info'; break; case 'FAILED': status_class = 'progress-bar-danger'; break; case 'UNKNOWN': status_class = 'progress-bar-warning'; break; } return status_class; } var create_progress_bar = function(status_class, completed, total) { // progress defined in percent var progress = completed / total * 100; var progress_bar_div = $('
') .addClass('progress') .css({'min-width': '100px', 'margin-bottom': 0}); var progress_bar = $('
') .addClass('progress-bar ' + status_class) .attr('role', 'progressbar') .attr('aria-valuenow', progress) .attr('aria-valuemin', 0) .attr('aria-valuemax', 100) .css({'width': progress + '%', 'white-space': 'nowrap', 'overflow': 'visible'}); if (status_class == 'progress-bar-warning') { progress_bar.text('Loading Spark...'); } else { progress_bar.text(completed + ' out of ' + total + ' tasks'); } progress_bar_div.append(progress_bar); return progress_bar_div; }; define([ 'jquery', 'base/js/namespace', 'base/js/dialog', 'base/js/events', 'base/js/utils', 'notebook/js/codecell' ], function ($, Jupyter, dialog, events, utils, codecell) { var CodeCell = codecell.CodeCell; var base_url = utils.get_body_data('baseUrl') || '/'; var api_url = base_url + 'spark/api/v1'; var show_running_jobs = function() { var element = $('
').attr('id', 'dialog_contents'); dialog.modal({ title: "Running Spark Jobs", body: element, buttons: { "Close": {} }, open: update_dialog_contents }); }; var spark_progress_bar = function(event, data) { var cell = data.cell; if (is_spark_cell(cell)) { window.clearInterval(current_update_frequency); current_update_frequency = window.setInterval(update, UPDATE_FREQUENCY_ACTIVE, api_url); cell_queue.push(cell); current_cell = cell_queue[0]; add_progress_bar(current_cell); } }; var add_progress_bar = function(cell) { var progress_bar_div = cell.element.find('.progress-container'); if (progress_bar_div.length < 1) { var input_area = cell.element.find('.input_area'); cell_jobs_counter = 0; if (spark_is_running) { jobs_in_cache = cache[0].jobs.length; } var panel = $('
') .addClass('panel') .addClass('panel-default') .addClass('progress-panel') .css({'margin-bottom': '0'}) .hide(); var jobs_completed_container = $('
') .addClass('progress_counter') .addClass('panel-heading') .text(PROGRESS_COUNT_TEXT + cell_jobs_counter); var progress_bar_container = $('
') .addClass('progress-container'); var progress_bar = create_progress_bar('progress-bar-warning', 1, 5); progress_bar.appendTo(progress_bar_container); jobs_completed_container.appendTo(panel); progress_bar_container.appendTo(panel); panel.appendTo(input_area); } }; var update_progress_bar = function() { var job = cache[0].jobs[0]; var completed = job.numCompletedTasks; var total = job.numTasks; var progress_bar = current_cell.element.find('.progress'); update_progress_count(current_cell, job.jobId); var progress = completed / total * 100; progress_bar.show(); progress_bar.find('.progress-bar') .attr('class', 'progress-bar ' + get_status_class(job.status)) .attr('aria-valuenow', progress) .css('width', progress + '%') .text(completed + ' out of ' + total + ' tasks'); }; var update_progress_count = function(cell, jobId) { var progress_count = cell.element.find('.progress_counter'); var job_name = ""; var canceller = null; if (spark_is_running) { cell_jobs_counter = cache[0].jobs.length - jobs_in_cache; job_name = ": " + cache[0].jobs[0].name canceller = $('Cancel').on( 'click', function () { $.get(base_url + "spark/jobs/job/kill?id=" + jobId)}); } progress_count.text(PROGRESS_COUNT_TEXT + cell_jobs_counter + job_name); progress_count.append(canceller) cell.element.find('.progress-panel').show(); }; var remove_progress_bar = function() { if (current_cell != null) { var progress_panel = current_cell.element.find('.progress-panel'); progress_panel.remove(); start_next_progress_bar(); } }; var start_next_progress_bar = function() { cell_queue.shift(); current_cell = cell_queue[0]; if (current_cell != null) { add_progress_bar(current_cell); } else { window.clearInterval(current_update_frequency); current_update_frequency = window.setInterval(update, UPDATE_FREQUENCY, api_url); } }; var is_spark_cell = function(cell) { // TODO: Find a way to detect if cell is actually running Spark return (cell instanceof CodeCell) }; var load_ipython_extension = function () { events.on('execute.CodeCell', spark_progress_bar); $(document).on('update.progress.bar', update_progress_bar); // Kernel becomes idle after a cell finishes executing events.on('kernel_idle.Kernel', remove_progress_bar); Jupyter.keyboard_manager.command_shortcuts.add_shortcut('Alt-S', show_running_jobs); Jupyter.toolbar.add_buttons_group([{ 'label': 'Show running Spark jobs', 'icon': 'fa-tasks', 'callback': show_running_jobs, 'id': 'show_running_jobs' }]); update(api_url); current_update_frequency = window.setInterval(update, UPDATE_FREQUENCY, api_url); }; return { load_ipython_extension: load_ipython_extension }; }); ================================================ FILE: tests/test_spark.py ================================================ # -*- coding: utf-8 -*- import pytest import six import tornado import tornado.httpclient import tornado.testing import tornado.web from bs4 import BeautifulSoup from jupyter_spark.handlers import SparkHandler from jupyter_spark.spark import BEAUTIFULSOUP_BUILDER, Spark PROXY_PREFIX = "/proxy/application_1234556789012_3456" spark = Spark(base_url='http://localhost:8888') class FakeHandler(tornado.web.RequestHandler): def get(self): self.set_header('Content-Type', self.CONTENT_TYPE) self.write(self.RESPONSE) class FakeReplaceHandler(FakeHandler): handler_root = '/backend/replace' RESPONSE = six.b('') REPLACED = six.b('') CONTENT_TYPE = 'text/html' class FakeVerbatimHandler(FakeHandler): handler_root = '/backend/verbatim' RESPONSE = six.b('Hello, world!') CONTENT_TYPE = 'plain/text' class SparkHandlerTests(tornado.testing.AsyncHTTPTestCase): def get_app(self): port = self.get_http_port() base_url = 'http://localhost:%s' % port self.spark = Spark(base_url=base_url) return tornado.web.Application([ (spark.proxy_root + '.*', SparkHandler, {'spark': self.spark}), (FakeReplaceHandler.handler_root, FakeReplaceHandler), (FakeVerbatimHandler.handler_root, FakeVerbatimHandler), ]) def test_http_fetch_error(self): response = self.fetch(self.spark.proxy_root) self.assertEqual(response.code, 200) self.assertIn(six.b('SPARK_NOT_RUNNING'), response.body) def test_http_fetch_replace_success(self): self.spark.url = self.spark.base_url + FakeReplaceHandler.handler_root response = self.fetch(self.spark.proxy_root) self.assertEqual(response.code, 200) self.assertNotEqual(response.body, FakeReplaceHandler.RESPONSE) self.assertEqual(response.body, FakeReplaceHandler.REPLACED) self.assertEqual(response.headers['Content-Type'], FakeReplaceHandler.CONTENT_TYPE) def test_http_fetch_verbatim_success(self): self.spark.url = self.spark.base_url + FakeVerbatimHandler.handler_root response = self.fetch(self.spark.proxy_root) self.assertEqual(response.code, 200) self.assertEqual(response.body, FakeVerbatimHandler.RESPONSE) self.assertEqual(response.headers['Content-Type'], FakeVerbatimHandler.CONTENT_TYPE) def test_spark_backend_url(self): class FakeRequest(object): # http://localhost:8888/spark/api uri = self.spark.base_url + self.spark.proxy_root + '/api' fake_request = FakeRequest() self.assertEqual(self.spark.backend_url(fake_request), self.spark.url + '/api') @pytest.mark.parametrize('content', [ 'page', '', six.u('Über uns'), # missing href attribute so expected to fail: pytest.mark.xfail('page'), pytest.mark.xfail(''), # fails because the URL path doesn't start with the prefix pytest.mark.xfail('different'), ]) def test_replace_href_tags(content): content = content.format(prefix=PROXY_PREFIX) replaced = spark.replace(content) assert replaced != content soup = BeautifulSoup(replaced, BEAUTIFULSOUP_BUILDER) for tag in soup.find_all(['a', 'link']): assert tag.attrs['href'].startswith(spark.proxy_root) @pytest.mark.parametrize('content', [ '', '