woccur 0.0.1

data/.gitignore

@@ -0,0 +1,4 @@
+*.gem
+.bundle
+Gemfile.lock
+pkg/*

data/Gemfile

@@ -0,0 +1,4 @@
+source "http://rubygems.org"
+
+# Specify your gem's dependencies in woccur.gemspec
+gemspec

data/Rakefile

@@ -0,0 +1,2 @@
+require 'bundler'
+Bundler::GemHelper.install_tasks

data/lib/common.yml

@@ -0,0 +1,114 @@
+- a
+- about
+- after
+- again
+- against
+- all
+- an
+- another
+- any
+- and
+- are
+- as
+- at
+- be
+- being
+- been
+- before
+- but
+- by
+- can
+- could
+- did
+- do
+- don't
+- down
+- each 
+- few
+- from
+- for
+- get
+- got
+- great
+- had
+- has
+- have
+- he
+- her
+- here
+- his
+- him
+- himself
+- hers
+- how
+- i
+- if
+- i'm
+- in
+- into
+- is
+- it
+- it's
+- just
+- like
+- made
+- me
+- more
+- most
+- my
+- no
+- not
+- of
+- off
+- on
+- once
+- one
+- only
+- or
+- other
+- our
+- out
+- over
+- own
+- said
+- she
+- should
+- so
+- some
+- such 
+- than
+- that
+- the
+- their
+- them
+- then
+- there
+- these
+- they
+- this
+- those
+- through
+- to
+- too
+- under
+- until
+- up 
+- very
+- was
+- wasn't
+- we
+- were
+- we're
+- what
+- when
+- where
+- which
+- while
+- who
+- why
+- will
+- with
+- would
+- wouldn't
+- you
+- your

data/lib/woccur.rb

@@ -0,0 +1,45 @@
+require 'woccur/version'
+require 'woccur/core_ext'
+require 'yaml'
+
+module Woccur
+  def self.common_words(text = "")
+    words = text.gsub(/[^a-zA-Z\'\s]/, " ").split(" ")
+    freq = Hash.new(0)
+
+    common_words = %w(
+    a about after again against all an another any and are as at
+    be being been before but by
+    can could
+    did do don't down
+    each 
+    few from for
+    get got great
+    had has have he her here his him himself hers how
+    i if i'm in into is it it's
+    just
+    like
+    made me more most my
+    no not
+    of off on once one only or other our out over own
+    said she should so some such 
+    than that the their them then there these they this those through to too
+    under until up 
+    very
+    was wasn't we were we're what when where which while who why will with would wouldn't
+    you your)
+
+    words.each do |word|
+      word = word.downcase  
+      if word == ""
+        next
+      end
+
+      if !common_words.include? word
+        freq[word] = freq[word] +1
+      end
+    end
+
+    freq.sort_by {|k, v| -v}
+  end
+end

data/lib/woccur/core_ext.rb

@@ -0,0 +1,5 @@
+String.class_eval do
+  def common_words
+    Woccur.common_words(self)
+  end
+end

data/lib/woccur/version.rb

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

data/spec/woccur_spec.rb

@@ -0,0 +1,13 @@
+path = File.expand_path(File.dirname(__FILE__) + "/../lib/")
+$LOAD_PATH.unshift(path) unless $LOAD_PATH.include?(path)
+require "woccur"
+
+describe Woccur do
+  it "should ignore common words" do
+    "A is a common word".common_words.select {|x, y| x == "a" }.empty?.should be_true
+  end
+  
+  it "should count words" do
+    "Second has been said for a second time".common_words.select {|x, y| x == "second" }.first.last.should == 2
+  end
+end

data/woccur.gemspec

@@ -0,0 +1,23 @@
+# -*- encoding: utf-8 -*-
+$:.push File.expand_path("../lib", __FILE__)
+require "woccur/version"
+
+Gem::Specification.new do |s|
+  s.name        = "woccur"
+  s.version     = Woccur::VERSION
+  s.platform    = Gem::Platform::RUBY
+  s.authors     = ["Sam Knight"]
+  s.email       = ["sam@samknight.co.uk"]
+  s.homepage    = ""
+  s.summary     = %q{Find the most commons words in a string}
+  s.description = %q{Find the most commons words in a string}
+
+  s.rubyforge_project = "woccur"
+
+  s.files         = `git ls-files`.split("\n")
+  s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
+  s.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
+  s.require_paths = ["lib"]
+  
+  s.add_development_dependency "rspec", "~>2.6"
+end

metadata

@@ -0,0 +1,75 @@
+--- !ruby/object:Gem::Specification 
+name: woccur
+version: !ruby/object:Gem::Version 
+  prerelease: 
+  version: 0.0.1
+platform: ruby
+authors: 
+- Sam Knight
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2011-11-23 00:00:00 +00:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: rspec
+  prerelease: false
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ~>
+      - !ruby/object:Gem::Version 
+        version: "2.6"
+  type: :development
+  version_requirements: *id001
+description: Find the most commons words in a string
+email: 
+- sam@samknight.co.uk
+executables: []
+
+extensions: []
+
+extra_rdoc_files: []
+
+files: 
+- .gitignore
+- Gemfile
+- Rakefile
+- lib/common.yml
+- lib/woccur.rb
+- lib/woccur/core_ext.rb
+- lib/woccur/version.rb
+- spec/woccur_spec.rb
+- woccur.gemspec
+has_rdoc: true
+homepage: ""
+licenses: []
+
+post_install_message: 
+rdoc_options: []
+
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+requirements: []
+
+rubyforge_project: woccur
+rubygems_version: 1.5.0
+signing_key: 
+specification_version: 3
+summary: Find the most commons words in a string
+test_files: 
+- spec/woccur_spec.rb