Skip to content

Latest commit

 

History

History
211 lines (159 loc) · 8.91 KB

CONTRIBUTING.md

File metadata and controls

211 lines (159 loc) · 8.91 KB

Contributing to NLTK

Hi! Thanks for your interest in contributing to NLTK. :-) You'll be joining a long list of contributors. In this document we'll try to summarize everything that you need to know to do a good job.

Code and Issues

We use GitHub to host our code repositories and issues. The NLTK organization on GitHub has many repositories, so we can manage better the issues and development. The most important are:

  • nltk/nltk, the main repository with code related to the library;
  • nltk/nltk_data, repository with data related to corpora, taggers and other useful data that are not shipped by default with the library, which can be downloaded by nltk.downloader;
  • nltk/nltk.github.com, NLTK website with information about the library, documentation, link for downloading NLTK Book etc.;
  • nltk/nltk_book, source code for the NLTK Book.

Development priorities

NLTK consists of the functionality that the Python/NLP community is motivated to contribute. Some priority areas for development are listed in the NLTK Wiki.

Git and our Branching model

Git

We use Git as our version control system, so the best way to contribute is to learn how to use it and put your changes on a Git repository. There's a plenty of documentation about Git -- you can start with the Pro Git book.

Setting up a Development Environment

To set up your local development environment for contributing to the main repository nltk/nltk:

  • Fork the nltk/nltk repository on GitHub to your account;
  • Clone your forked repository locally (git clone https://github.com/<your-github-username>/nltk.git);
  • Run cd nltk to get to the root directory of the nltk code base;
  • Install the dependencies (pip install -r pip-req.txt);
  • Download the datasets for running tests (python -m nltk.downloader all);
  • Create a remote link from your local repository to the upstream nltk/nltk on GitHub (git remote add upstream https://github.com/nltk/nltk.git) -- you will need to use this upstream link when updating your local repository with all the latest contributions.

GitHub Pull requests

We use the famous gitflow to manage our branches.

Summary of our git branching model:

  • Go to the develop branch (git checkout develop);
  • Get all the latest work from the upstream nltk/nltk repository (git pull upstream develop);
  • Create a new branch off of develop with a descriptive name (for example: feature/portuguese-sentiment-analysis, hotfix/bug-on-downloader). You can do it by switching to the develop branch (git checkout develop) and then creating a new branch (git checkout -b name-of-the-new-branch);
  • Do many small commits on that branch locally (git add files-changed, git commit -m "Add some change");
  • Run the tests to make sure nothing breaks (tox -e py36 if you are on Python 3.6);
  • Add your name to the AUTHORS.md file as a contributor;
  • Push to your fork on GitHub (with the name as your local branch: git push origin branch-name);
  • Create a pull request using the GitHub Web interface (asking us to pull the changes from your new branch and add to them our develop branch);
  • Wait for comments.

Tips

  • Write helpful commit messages.
  • Anything in the develop branch should be deployable (no failing tests).
  • Never use git add .: it can add unwanted files;
  • Avoid using git commit -a unless you know what you're doing;
  • Check every change with git diff before adding them to the index (stage area) and with git diff --cached before commiting;
  • Make sure you add your name to our list of contributors;
  • If you have push access to the main repository, please do not commit directly to develop: your access should be used only to accept pull requests; if you want to make a new feature, you should use the same process as other developers so you code will be reviewed.
  • See RELEASE-HOWTO.txt to see everything you need before creating a new NLTK release.

Code Guidelines

  • Use PEP8;
  • Write tests for your new features (please see "Tests" topic below);
  • Always remember that commented code is dead code;
  • Name identifiers (variables, classes, functions, module names) with readable names (x is always wrong);
  • When manipulating strings, use Python's new-style formatting ('{} = {}'.format(a, b) instead of '%s = %s' % (a, b));
  • All #TODO comments should be turned into issues (use our GitHub issue system);
  • Run all tests before pushing (just execute tox) so you will know if your changes broke something;

See also our developer's guide.

Tests

You should write tests for every feature you add or bug you solve in the code. Having automated tests for every line of our code lets us make big changes without worries: there will always be tests to verify if the changes introduced bugs or lack of features. If we don't have tests we will be blind and every change will come with some fear of possibly breaking something.

For a better design of your code, we recommend using a technique called test-driven development, where you write your tests before writing the actual code that implements the desired feature.

You can use pytest to run your tests, no matter which type of test it is:

cd nltk/test
pytest util.doctest  # doctest
pytest unit/translate/test_nist.py  # unittest
pytest  # all tests

Continuous Integration

Deprecated: NLTK uses Cloudbees for continuous integration.

NLTK uses Travis for continuous integration.

The .travis.yml file configures the server:

  • matrix: include: section

    • tests against supported Python versions (3.5, 3.6, 3.7, 3.8, 3.9)
      • all python versions run the py-travis tox test environment in the tox.ini file
    • tests against Python 3.6 for third-party tools APIs
  • before_install: section

    • checks the Java and Python version calling the tools/travis/pre-install.sh script
    • changes the permission for tools/travis/coverage-pylint.sh to allow it to be executable
    • changes the permission for tools/travis/third-party.sh to allow it to be executable
  • install section

    • the tools/travis/install.sh installs the pip-req.txt for NLTK and the necessary python packages for CI testing
    • install tox for testing
  • py-travis tox test environment generally

    • the extras = all dependencies in needed to emulate pip install nltk[all], see https://tox.readthedocs.io/en/latest/config.html#confval-extras=MULTI-LINE-LIST

    • for the py-travis-third-party build, it will run tools/travis/third-party.sh to install third-party tools (Stanford NLP tools and CoreNLP and SENNA)

    • calls tools/travis/coverage-pylint.sh shell script that calls pytest with pytest-cov and

    • calls pylint # Currently, disabled because there's lots to clean...

    • before returning a true to state that the build is successful

To test with tox locally

First setup a new virtual environment, see https://docs.python-guide.org/dev/virtualenvs/ Then run tox -e py37.

For example, using pipenv:

git clone https://github.com/nltk/nltk.git
cd nltk
pipenv install -r pip-req.txt
pipenv install tox
tox -e py37

Discussion

We have three mail lists on Google Groups:

  • nltk, for announcements only;
  • nltk-users, for general discussion and user questions;
  • nltk-dev, for people interested in NLTK development.

Please feel free to contact us through the nltk-dev mail list if you have any questions or suggestions. Every contribution is very welcome!

Happy hacking! (;