[aehrc#42] Prepare variant-spark for external contribution (aehrc#43)

* Integrated py-lint with spark checks + line-lenght-limit = 100

* Added installation of python dev envirment + the first version of contributing

* Added sudo to python packages installatio

* Working on contributing

* Working on contributing

* Finished first version of CONTRIBUTING.

* Updated README to include python build

* Removed a 'practice' unit test'

.gitignore

@@ -58,3 +58,4 @@ variant-spark_2.11.iml
 
 build
 dist
+_build

.travis.yml

@@ -9,6 +9,9 @@ branches:
   - master
   - /^branch-.*$/
   - /^v\d+\..*$/
+# command to install dependencies
+install:
+  - sudo dev/py-setup.sh
 script: dev/travis-build.sh
 before_deploy: dev/travis-prepare-s3-release.sh
 deploy:

CONTRIBUTING.md

@@ -0,0 +1,40 @@
+Contributing to VariantSpark
+=============================
+
+# Contributing Code Changes
+Please review the preceding section before proposing a code change. This section documents how to do so.
+
+When you contribute code, you affirm that the contribution is your original work and that you license the work to the project under the project’s open source license. Whether or not you state this explicitly, by submitting any copyrighted material via pull request, email, or other means you agree to license the material under the project’s open source license and warrant that you have the legal authority to do so.
+
+## Issue management
+
+Generally, _VariantSpark_ uses _Github Issues_ to track logical issues, including bugs and improvements, and uses _Github_ pull requests to manage the review and merge of specific code changes. That is, _Github Issues_ are used to describe what should be fixed or changed, and high-level approaches, and pull requests describe how to implement that change in the project’s source code. For example, major design decisions are discussed in _Github Issues_
+
+## Pull Request
+
+1. Fork the Github repository at https://github.com/aehrc/VariantSpark if you haven’t already
+2. Clone your fork, create a new branch, push commits to the branch.
+3. Consider whether documentation or tests need to be added or updated as part of the change, and add them as needed.
+4. Run all tests with `./dev/build.sh` to verify that the code still compiles, passes tests, and passes style checks. If style checks fail, review the Code Style Guide below.
+5. Open a pull request against the master branch of aehrc/VariantSpark. (Only in special cases would the PR be opened against other branches.)
+    * The PR title should be of the form `[#XXXX] Title`, where `#XXXX` is the relevant _Github Issue_ number, and Title may be the issue title or a more specific title describing the PR itself.
+    * If the pull request is still a work in progress, and so is not ready to be merged, but needs to be pushed to Github to facilitate review, then add [WIP] after the issue number.
+
+6. Your our pull request will automatically be linked to an issue. There is no need to be the Assignee of the issue to work on it, though you are welcome to comment that you have begun work.
+7. The Travis-CI automatic pull request builder will test your changes
+8. After about 10 minues, Travic-CI will post the results of the test to the pull request, along with a link to the full results on Jenkins.
+9. Watch for the results, and investigate and fix failures promptly
+   * Fixes can simply be pushed to the same branch from which you opened your pull request
+   * Travis-CI will automatically re-test when new commits are pushed
+
+## Closing Your Pull Request / Issue
+
+* If a change is accepted, it will be merged and the pull request will automatically be closed, along with the associated issue if any
+
+## Code Style Guide
+
+Follow the [Apache Spark - Code Style Guide](http://spark.apache.org/contributing.html#code-style-guide)
+
+In particular:
+
+* For Python code follow PEP 8 with one exception: lines can be up to 100 characters in length, not 79.

README.md

@@ -27,12 +27,26 @@ To learn more watch this video from Spark Summit.
 
 ### Building
 
-variant-spark requires java jdk 1.8+ and maven 3+
+_variant-spark_ requires java jdk 1.8+ and maven 3+
 
 In order to build the binaries use:
 
 	mvn clean install
 
+For python _variant-spark_ requires python 2.7 with pip. 
+The other packages required for development are listed in `dev/dev-requirements.txt` and can be installed with:
+
+    pip install -r dev/dev-requirements.txt
+
+or with: 
+
+    ./dev/py-setup.sh
+
+
+The complete built including all check can be run with:
+
+    ./dev/build.sh
+
 ### Running
 
 variant-spark requires an existing spark 2.1+ installation (either a local one or a cluster one).

dev/build.sh

@@ -0,0 +1,25 @@
+#!/bin/bash
+
+set -e
+set -x
+
+FWDIR="$(cd "`dirname $0`"/..; pwd)"
+cd "$FWDIR"
+
+# run code checks
+
+/bin/bash ${FWDIR}/dev/py-lint.sh
+
+# build and package the project
+mvn package -B
+
+# make build info
+env | tee "target/buildinfo" 
+
+# build the python distribution
+
+pushd  ${FWDIR}/python
+python setup.py sdist
+python setup.py bdist_egg
+popd 
+

dev/dev-requirements.txt

@@ -0,0 +1,3 @@
+Sphinx>=1.3.5
+pylint>=1.7.4
+decorator>=4.1.2

dev/py-docs.sh

@@ -0,0 +1,11 @@
+#!/bin/bash
+
+set -e
+set -x
+
+FWDIR="$(cd "`dirname $0`"/..; pwd)"
+cd "$FWDIR"
+
+pushd python/docs
+make clean  html
+popd

dev/py-lint.sh

@@ -0,0 +1,15 @@
+#!/bin/bash
+
+set -e
+set -x
+
+FWDIR="$(cd "`dirname $0`"/..; pwd)"
+cd "$FWDIR"
+
+# check code with pylint
+
+pushd python
+
+export PYTHONPATH=$PYTHONPATH:./deps/hail-py-0.1-src.zip
+pylint variants
+popd

dev/py-setup.sh

@@ -0,0 +1,9 @@
+#!/bin/bash
+
+set -e
+set -x
+
+FWDIR="$(cd "`dirname $0`"/..; pwd)"
+cd "$FWDIR"
+
+pip install -r ${FWDIR}/dev/dev-requirements.txt

dev/travis-build.sh

@@ -8,16 +8,5 @@ cd "$FWDIR"
 
 . ${FWDIR}/dev/travis-set-ver.sh
 
-# build and package the project
-mvn package -B
-
-# make build info
-env | tee "target/buildinfo" 
-
-# build the python distribution
-
-pushd  ${FWDIR}/python
-python setup.py sdist
-python setup.py bdist_egg
-popd 
+/bin/bash ${FWDIR}/dev/build.sh
 

python/docs/Makefile

@@ -0,0 +1,218 @@
+# Makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line.
+SPHINXOPTS    =
+SPHINXBUILD   = sphinx-build
+PAPER         =
+BUILDDIR      = _build
+
+export PYTHONPATH=$(realpath ..):$(realpath ../deps/hail-py-0.1-src.zip):$(realpath ../deps/py4j-0.10.4-src.zip):$(realpath ../deps/pyspark.zip)
+
+# User-friendly check for sphinx-build
+ifeq ($(shell which $(SPHINXBUILD) >/dev/null 2>&1; echo $$?), 1)
+$(error The '$(SPHINXBUILD)' command was not found. Make sure you have Sphinx installed, then set the SPHINXBUILD environment variable to point to the full path of the '$(SPHINXBUILD)' executable. Alternatively you can add the directory with the executable to your PATH. If you don't have Sphinx installed, grab it from http://sphinx-doc.org/)
+endif
+
+# Internal variables.
+PAPEROPT_a4     = -D latex_paper_size=a4
+PAPEROPT_letter = -D latex_paper_size=letter
+ALLSPHINXOPTS   = -d $(BUILDDIR)/doctrees $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) .
+# the i18n builder cannot share the environment and doctrees with the others
+I18NSPHINXOPTS  = $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) .
+
+.PHONY: help
+help:
+	@echo "Please use \`make <target>' where <target> is one of"
+	@echo "  html       to make standalone HTML files"
+	@echo "  dirhtml    to make HTML files named index.html in directories"
+	@echo "  singlehtml to make a single large HTML file"
+	@echo "  pickle     to make pickle files"
+	@echo "  json       to make JSON files"
+	@echo "  htmlhelp   to make HTML files and a HTML help project"
+	@echo "  qthelp     to make HTML files and a qthelp project"
+	@echo "  applehelp  to make an Apple Help Book"
+	@echo "  devhelp    to make HTML files and a Devhelp project"
+	@echo "  epub       to make an epub"
+	@echo "  latex      to make LaTeX files, you can set PAPER=a4 or PAPER=letter"
+	@echo "  latexpdf   to make LaTeX files and run them through pdflatex"
+	@echo "  latexpdfja to make LaTeX files and run them through platex/dvipdfmx"
+	@echo "  text       to make text files"
+	@echo "  man        to make manual pages"
+	@echo "  texinfo    to make Texinfo files"
+	@echo "  info       to make Texinfo files and run them through makeinfo"
+	@echo "  gettext    to make PO message catalogs"
+	@echo "  changes    to make an overview of all changed/added/deprecated items"
+	@echo "  xml        to make Docutils-native XML files"
+	@echo "  pseudoxml  to make pseudoxml-XML files for display purposes"
+	@echo "  linkcheck  to check all external links for integrity"
+	@echo "  doctest    to run all doctests embedded in the documentation (if enabled)"
+	@echo "  coverage   to run coverage check of the documentation (if enabled)"
+
+.PHONY: clean
+clean:
+	rm -rf $(BUILDDIR)/*
+
+.PHONY: html
+html:
+	$(SPHINXBUILD) -b html $(ALLSPHINXOPTS) $(BUILDDIR)/html
+	@echo
+	@echo "Build finished. The HTML pages are in $(BUILDDIR)/html."
+
+.PHONY: dirhtml
+dirhtml:
+	$(SPHINXBUILD) -b dirhtml $(ALLSPHINXOPTS) $(BUILDDIR)/dirhtml
+	@echo
+	@echo "Build finished. The HTML pages are in $(BUILDDIR)/dirhtml."
+
+.PHONY: singlehtml
+singlehtml:
+	$(SPHINXBUILD) -b singlehtml $(ALLSPHINXOPTS) $(BUILDDIR)/singlehtml
+	@echo
+	@echo "Build finished. The HTML page is in $(BUILDDIR)/singlehtml."
+
+.PHONY: pickle
+pickle:
+	$(SPHINXBUILD) -b pickle $(ALLSPHINXOPTS) $(BUILDDIR)/pickle
+	@echo
+	@echo "Build finished; now you can process the pickle files."
+
+.PHONY: json
+json:
+	$(SPHINXBUILD) -b json $(ALLSPHINXOPTS) $(BUILDDIR)/json
+	@echo
+	@echo "Build finished; now you can process the JSON files."
+
+.PHONY: htmlhelp
+htmlhelp:
+	$(SPHINXBUILD) -b htmlhelp $(ALLSPHINXOPTS) $(BUILDDIR)/htmlhelp
+	@echo
+	@echo "Build finished; now you can run HTML Help Workshop with the" \
+	      ".hhp project file in $(BUILDDIR)/htmlhelp."
+
+.PHONY: qthelp
+qthelp:
+	$(SPHINXBUILD) -b qthelp $(ALLSPHINXOPTS) $(BUILDDIR)/qthelp
+	@echo
+	@echo "Build finished; now you can run "qcollectiongenerator" with the" \
+	      ".qhcp project file in $(BUILDDIR)/qthelp, like this:"
+	@echo "# qcollectiongenerator $(BUILDDIR)/qthelp/VariantS.qhcp"
+	@echo "To view the help file:"
+	@echo "# assistant -collectionFile $(BUILDDIR)/qthelp/VariantS.qhc"
+
+.PHONY: applehelp
+applehelp:
+	$(SPHINXBUILD) -b applehelp $(ALLSPHINXOPTS) $(BUILDDIR)/applehelp
+	@echo
+	@echo "Build finished. The help book is in $(BUILDDIR)/applehelp."
+	@echo "N.B. You won't be able to view it unless you put it in" \
+	      "~/Library/Documentation/Help or install it in your application" \
+	      "bundle."
+
+.PHONY: devhelp
+devhelp:
+	$(SPHINXBUILD) -b devhelp $(ALLSPHINXOPTS) $(BUILDDIR)/devhelp
+	@echo
+	@echo "Build finished."
+	@echo "To view the help file:"
+	@echo "# mkdir -p $$HOME/.local/share/devhelp/VariantS"
+	@echo "# ln -s $(BUILDDIR)/devhelp $$HOME/.local/share/devhelp/VariantS"
+	@echo "# devhelp"
+
+.PHONY: epub
+epub:
+	$(SPHINXBUILD) -b epub $(ALLSPHINXOPTS) $(BUILDDIR)/epub
+	@echo
+	@echo "Build finished. The epub file is in $(BUILDDIR)/epub."
+
+.PHONY: latex
+latex:
+	$(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
+	@echo
+	@echo "Build finished; the LaTeX files are in $(BUILDDIR)/latex."
+	@echo "Run \`make' in that directory to run these through (pdf)latex" \
+	      "(use \`make latexpdf' here to do that automatically)."
+
+.PHONY: latexpdf
+latexpdf:
+	$(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
+	@echo "Running LaTeX files through pdflatex..."
+	$(MAKE) -C $(BUILDDIR)/latex all-pdf
+	@echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex."
+
+.PHONY: latexpdfja
+latexpdfja:
+	$(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
+	@echo "Running LaTeX files through platex and dvipdfmx..."
+	$(MAKE) -C $(BUILDDIR)/latex all-pdf-ja
+	@echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex."
+
+.PHONY: text
+text:
+	$(SPHINXBUILD) -b text $(ALLSPHINXOPTS) $(BUILDDIR)/text
+	@echo
+	@echo "Build finished. The text files are in $(BUILDDIR)/text."
+
+.PHONY: man
+man:
+	$(SPHINXBUILD) -b man $(ALLSPHINXOPTS) $(BUILDDIR)/man
+	@echo
+	@echo "Build finished. The manual pages are in $(BUILDDIR)/man."
+
+.PHONY: texinfo
+texinfo:
+	$(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo
+	@echo
+	@echo "Build finished. The Texinfo files are in $(BUILDDIR)/texinfo."
+	@echo "Run \`make' in that directory to run these through makeinfo" \
+	      "(use \`make info' here to do that automatically)."
+
+.PHONY: info
+info:
+	$(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo
+	@echo "Running Texinfo files through makeinfo..."
+	make -C $(BUILDDIR)/texinfo info
+	@echo "makeinfo finished; the Info files are in $(BUILDDIR)/texinfo."
+
+.PHONY: gettext
+gettext:
+	$(SPHINXBUILD) -b gettext $(I18NSPHINXOPTS) $(BUILDDIR)/locale
+	@echo
+	@echo "Build finished. The message catalogs are in $(BUILDDIR)/locale."
+
+.PHONY: changes
+changes:
+	$(SPHINXBUILD) -b changes $(ALLSPHINXOPTS) $(BUILDDIR)/changes
+	@echo
+	@echo "The overview file is in $(BUILDDIR)/changes."
+
+.PHONY: linkcheck
+linkcheck:
+	$(SPHINXBUILD) -b linkcheck $(ALLSPHINXOPTS) $(BUILDDIR)/linkcheck
+	@echo
+	@echo "Link check complete; look for any errors in the above output " \
+	      "or in $(BUILDDIR)/linkcheck/output.txt."
+
+.PHONY: doctest
+doctest:
+	$(SPHINXBUILD) -b doctest $(ALLSPHINXOPTS) $(BUILDDIR)/doctest
+	@echo "Testing of doctests in the sources finished, look at the " \
+	      "results in $(BUILDDIR)/doctest/output.txt."
+
+.PHONY: coverage
+coverage:
+	$(SPHINXBUILD) -b coverage $(ALLSPHINXOPTS) $(BUILDDIR)/coverage
+	@echo "Testing of coverage in the sources finished, look at the " \
+	      "results in $(BUILDDIR)/coverage/python.txt."
+
+.PHONY: xml
+xml:
+	$(SPHINXBUILD) -b xml $(ALLSPHINXOPTS) $(BUILDDIR)/xml
+	@echo
+	@echo "Build finished. The XML files are in $(BUILDDIR)/xml."
+
+.PHONY: pseudoxml
+pseudoxml:
+	$(SPHINXBUILD) -b pseudoxml $(ALLSPHINXOPTS) $(BUILDDIR)/pseudoxml
+	@echo
+	@echo "Build finished. The pseudo-XML files are in $(BUILDDIR)/pseudoxml."