boilerpipe-ruby 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: a3ddeb5197a36e243816c8a558826aa25a4127c8
+  data.tar.gz: 3ecf3ded094f75276c5308e48988fd682551c71c
+SHA512:
+  metadata.gz: b3de289e4282a42c4acfa4dd2cc3b7998742c3432789d20404bdd34efc706bde7c205cbf83420b5fe9342e7e4a0cab46beec68a0f62f13c9e7a78f0964011273
+  data.tar.gz: a7617f372ee30014fb614e467d254600b760bdbd7654cbc151b1afd0ff34913ba3198cfa8c7da40a70bf21ab118908ecb5ac90cd493e73b649d7b5c6bd6e0277

data/.gitignore

@@ -0,0 +1,9 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/

data/.rspec

@@ -0,0 +1,2 @@
+--format documentation
+--color

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in boilerpipe-ruby.gemspec
+gemspec

data/README.md

@@ -0,0 +1,36 @@
+# Boilerpipe::Ruby
+
+Welcome to your new gem! In this directory, you'll find the files you need to be able to package up your Ruby library into a gem. Put your Ruby code in the file `lib/boilerpipe/ruby`. To experiment with that code, run `bin/console` for an interactive prompt.
+
+A pure ruby implemenation of the boilerpipe algorithm - in progress ......
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'boilerpipe-ruby'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install boilerpipe-ruby
+
+## Usage
+
+TODO: Write usage instructions here
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+
+To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/boilerpipe-ruby.
+

data/Rakefile

@@ -0,0 +1,6 @@
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+
+RSpec::Core::RakeTask.new(:spec)
+
+task :default => :spec

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "boilerpipe"
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require "irb"
+IRB.start

data/bin/setup

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/boilerpipe-ruby.gemspec

@@ -0,0 +1,24 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'boilerpipe/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "boilerpipe-ruby"
+  spec.version       = Boilerpipe::VERSION
+  spec.authors       = ["Gregory Ostermayr"]
+  spec.email         = ["<gregory.ostermayr@gmail.com>"]
+
+  spec.summary       = %q{A pure ruby implemenation of the boilerpipe algorithm - in progress}
+  spec.description   = %q{A pure ruby implementation of the boilerpipe algorith - in progress}
+  spec.homepage      = "https://github.com/gregors/boilerpipe-ruby"
+
+  spec.files         = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.11"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rspec", "~> 3.0"
+end

data/lib/boilerpipe.rb

@@ -0,0 +1,2 @@
+require 'boilerpipe/version'
+require 'boilerpipe/util/unicode_tokenizer'

data/lib/boilerpipe/util/unicode_tokenizer.rb

@@ -0,0 +1,21 @@
+module Boilerpipe
+  class UnicodeTokenizer
+    INVISIBLE_SEPARATOR = "\u2063"
+    WORD_BOUNDARY = Regexp.new('\b')
+    NOT_WORD_BOUNDARY = Regexp.new("[\u2063]*([\\\"'\\.,\\!\\@\\-\\:\\;\\$\\?\\(\\)/])[\u2063]*")
+
+    # replace word boundaries with 'invisible separator' 
+    # strip invisible separators from non-word boundaries
+    # replace spaces or invisible separators with a single space
+    # trim
+    # split words on single space
+
+    def self.tokenize(text)
+      text.gsub(WORD_BOUNDARY, INVISIBLE_SEPARATOR)
+        .gsub(NOT_WORD_BOUNDARY, '\1')
+        .gsub(/[ \u2063]+/, ' ')
+        .strip
+        .split(/[ ]+/)
+    end
+  end
+end

data/lib/boilerpipe/version.rb

@@ -0,0 +1,3 @@
+module Boilerpipe
+  VERSION = "0.0.1"
+end

metadata

@@ -0,0 +1,96 @@
+--- !ruby/object:Gem::Specification
+name: boilerpipe-ruby
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Gregory Ostermayr
+autorequire:
+bindir: exe
+cert_chain: []
+date: 2016-03-13 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.11'
+  name: bundler
+  prerelease: false
+  type: :development
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.11'
+- !ruby/object:Gem::Dependency
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  name: rake
+  prerelease: false
+  type: :development
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+  name: rspec
+  prerelease: false
+  type: :development
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+description: A pure ruby implementation of the boilerpipe algorith - in progress
+email:
+- "<gregory.ostermayr@gmail.com>"
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- Gemfile
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- boilerpipe-ruby.gemspec
+- lib/boilerpipe.rb
+- lib/boilerpipe/util/unicode_tokenizer.rb
+- lib/boilerpipe/version.rb
+homepage: https://github.com/gregors/boilerpipe-ruby
+licenses: []
+metadata: {}
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project:
+rubygems_version: 2.4.8
+signing_key:
+specification_version: 4
+summary: A pure ruby implemenation of the boilerpipe algorithm - in progress
+test_files: []