sourceclassifier icon indicating copy to clipboard operation
sourceclassifier copied to clipboard

Use a Bayesian classifier to determine source code language

h1. SourceClassifier

Source classifier identifies programming language using a Bayesian classifier trained on a corpus generated from the "Computer Language Benchmarks Game":http://shootout.alioth.debian.org/ . It is written in Ruby and availabe as a gem. To train the classifier to identify new languages download the sources from github.

Out of the box SourceClassifier recognises Css, C, Java, Javascript, Perl, Php, Python and Ruby.

h2. Usage

First install the gem using github as a source

$ gem sources -a http://gems.github.com $ sudo gem install chrislo-sourceclassifier

Then, to use

  require 'rubygems'
  require 'sourceclassifier'

  s = SourceClassifier.new

  ruby_text = 

  int main() {
    write(1, "hello world\n", 12);
    return(0);
  }
  EOT

  s.identify(ruby_text) #=> Ruby
  s.identify(c_text) #=> Gcc

h2. Training

Download the sources from github and in the directory run the training rake test

$ rake train

In the ./sources directory are subdirectories for each language you wish to be able to identify. Each subdirectory contains examples of programs written in that language. The name of the directory is significant - it is the value returned by the SourceClassifier.identify() method.

The rake task populate:shootout can be used to build these subdirectories from a checkout of the "computer language shootout sources":http://alioth.debian.org/scm/?group_id=30402 but you are free to train the classifier using any available examples. Edit the Rakefile to point to your checkout of the shootout sources

Run rake populate:css to grab the css files used to train the classifier from csszengarden.com.

To populate the sources directory using all available sources run

$ rake populate:all

h2. Acknowledgments

This library depends heavily on the great "Classifier":http://classifier.rubyforge.org/ gem by Lucas Carlson and David Fayram II.

h2. License

This gem is released under the MIT license (see LICENSE). The training examples retain their original licenses.