whatlanguage 1.0.0 → 1.0.4

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: ef04e53215ee669aed4e66e5ec8e66bbcc1f7fa0
+  data.tar.gz: 270302e063e5d85ec875de08ac54100c9db5efb8
+SHA512:
+  metadata.gz: a6be7929232a8b48229cae418de4e4bbb928245f9d4ead0ae38b6286fad8d482e06ec82549781187613799596b3657f99fb442d49348329b3e53ae96130029b0
+  data.tar.gz: 98bea8003cacaf0da3774232f1daf112c11c9b3a826700fd2bb5252e3b9837c012f87f54db17d25c640a45a10e60c5891c8e88b8b0ba7835a6e0389bf2695cce

data/.gitignore

@@ -0,0 +1,17 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in whatlanguage2.gemspec
+gemspec

data/History.txt

@@ -1,3 +1,8 @@
+== 1.0.1 / 2008-08-22
+
+* Public release
+* Removed wordlists from distribution to reduce size
+
 == 1.0.0 / 2007-07-02
 
 * First version with pre-built English, French, and Spanish filters

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2008-2013 Peter Cooper
+
+MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/{README.txt → README.md}

@@ -1,22 +1,21 @@
-whatlanguage
-    by Peter Cooper
-    http://www.petercooper.co.uk/
-    http://www.rubyinside.com/
+# whatlanguage
+
+by Peter Cooper
 
-== DESCRIPTION:
-  
 Text language detection. Quick, fast, memory efficient, and all in pure Ruby. Uses Bloom filters for aforementioned speed and memory benefits.
 
-== FEATURES/PROBLEMS:
+Works with Dutch, English, Farsi, French, German, Italian, Pinyin, Swedish, Portuguese, Russian and Spanish out of the box.
+
+## Important note
   
-* Only does French, English and Spanish out of the box. Very easy to train new languages though.
-* It can be made far more efficient at the comparison stage, but all in good time..! It still beats literal dictionary approaches.
-* No filter selection yet, you get 'em all loaded.
-* Tests are reasonably light.
+This library was first built in 2007 and has received a few minor updates over the years. There are now more efficient and effective algorithms for doing language detection which I am investigating for a WhatLanguage 2.0.
+
+This library has been updated to be distributed and to work on modern Ruby implementations but other than that, has had no improvements.
 
-== SYNOPSIS:
+## Synopsis
+
+Full Example
 
-  Full Example
     require 'whatlanguage'
     
     texts = []
@@ -29,27 +28,40 @@ Text language detection. Quick, fast, memory efficient, and all in pure Ruby. Us
     
     texts.each { |text| puts "#{text[0..18]}... is in #{text.language.to_s.capitalize}" }
 
-  Initialize WhatLanguage with all filters
+Initialize WhatLanguage with all filters
+
     wl = WhatLanguage.new(:all)
 
-  Return language with best score
+Return language with best score
+
     wl.language(text)
 
-  Return hash with scores for all relevant languages
+Return hash with scores for all relevant languages
+
     wl.process_text(text)
 
-  Convenience method on String
+Convenience method on String
+
     "This is a test".language   # => "English"
 
-== REQUIREMENTS:
+## Requirements
+
+None, minor libraries (BloominSimple and BitField) included with this release.
+
+## Installation
 
-* None, minor libraries (BloominSimple and BitField) included with this release.
+    gem install whatlanguage
+
+To test, go into irb, then:
+
+    require 'whatlanguage'
+    "Je suis un homme".language
 
-== LICENSE:
+## License
 
-(The MIT License)
+MIT License
 
-Copyright (c) 2007-2008 Peter Cooper
+Copyright (c) 2007-2013 Peter Cooper
 
 Permission is hereby granted, free of charge, to any person obtaining
 a copy of this software and associated documentation files (the

data/Rakefile

@@ -1,17 +1,6 @@
-# -*- ruby -*-
+require "bundler/gem_tasks"
+require 'rake/testtask'
 
-require 'rubygems'
-require 'hoe'
-require './lib/whatlanguage.rb'
+Rake::TestTask.new
 
-Hoe.new('whatlanguage', WhatLanguage::VERSION) do |p|
-  p.rubyforge_name = 'whatlanguage'
-  p.author = 'Peter Cooper'
-  p.email = 'whatlanguage@peterc.org'
-  p.summary = 'Fast, quick, textual language detection'
-  p.description = p.paragraphs_of('README.txt', 2..5).join("\n\n")
-  p.url = "http://rubyforge.org/projects/whatlanguage/"
-  p.changes = p.paragraphs_of('History.txt', 0..1).join("\n\n")
-end
-
-# vim: syntax=Ruby
+task :default => :test

data/build_filter.rb

@@ -6,4 +6,4 @@
 
 require 'lib/whatlanguage'
 filter = WhatLanguage.filter_from_dictionary(ARGV[0])
-File.open(ARGV[1], 'w') { |f| f.write filter.dump }
+File.open(ARGV[1], 'wb') { |f| f.write filter.dump }

data/build_lang_from_wordlists.rb

@@ -0,0 +1,13 @@
+# Builds all of the word lists in ./wordlists/ into filter files in ./lang/
+
+require 'lib/whatlanguage'
+
+languages_folder = File.join(File.dirname(__FILE__), "lang")
+wordlists_folder = File.join(File.dirname(__FILE__), "wordlists")
+
+Dir.entries(wordlists_folder).grep(/\w/).each do |lang|
+  next if lang == 'generators'
+  puts "Doing #{lang}"
+  filter = WhatLanguage.filter_from_dictionary(File.join(wordlists_folder, lang))
+  File.open(File.join(languages_folder, lang + ".lang"), 'wb') { |f| f.write filter.dump }
+end

data/copyright-en

@@ -0,0 +1,243 @@
+The english word list in `wordlists/english` is compiled from a preexisting word list
+(public domain) in this repository and the word list from SCOWL 7.0. To comply with the
+license of Kevin Atkinson's work, his copyright file is attached below.
+
+------------------------------------------------------------------------
+
+This English word list is comes directly from SCOWL 7.0 (up to level 60,
+using the speller/make-aspell-dict script, http://wordlist.sourceforge.net/) 
+and is thus under the same copyright of SCOWL.  The affix file (only
+included in the aspell6 package) is based on the Ispell one which is
+under the same copyright of Ispell.  Part of SCOWL is also based on
+Ispell thus the Ispell copyright is included with the SCOWL copyright.
+
+The collective work is Copyright 2000-2011 by Kevin Atkinson as well
+as any of the copyrights mentioned below:
+
+  Copyright 2000-2011 by Kevin Atkinson
+
+  Permission to use, copy, modify, distribute and sell these word
+  lists, the associated scripts, the output created from the scripts,
+  and its documentation for any purpose is hereby granted without fee,
+  provided that the above copyright notice appears in all copies and
+  that both that copyright notice and this permission notice appear in
+  supporting documentation. Kevin Atkinson makes no representations
+  about the suitability of this array for any purpose. It is provided
+  "as is" without express or implied warranty.
+
+Alan Beale <biljir@pobox.com> also deserves special credit as he has,
+in addition to providing the 12Dicts package and being a major
+contributor to the ENABLE word list, given me an incredible amount of
+feedback and created a number of special lists (those found in the
+Supplement) in order to help improve the overall quality of SCOWL.
+
+The 10 level includes the 1000 most common English words (according to
+the Moby (TM) Words II [MWords] package), a subset of the 1000 most
+common words on the Internet (again, according to Moby Words II), and
+frequently class 16 from Brian Kelk's "UK English Wordlist
+with Frequency Classification".
+
+The MWords package was explicitly placed in the public domain:
+
+    The Moby lexicon project is complete and has
+    been place into the public domain. Use, sell,
+    rework, excerpt and use in any way on any platform.
+
+    Placing this material on internal or public servers is
+    also encouraged. The compiler is not aware of any
+    export restrictions so freely distribute world-wide.
+
+    You can verify the public domain status by contacting
+
+    Grady Ward
+    3449 Martha Ct.
+    Arcata, CA  95521-4884
+
+    grady@netcom.com
+    grady@northcoast.com
+
+The "UK English Wordlist With Frequency Classification" is also in the
+Public Domain:
+
+  Date: Sat, 08 Jul 2000 20:27:21 +0100
+  From: Brian Kelk <Brian.Kelk@cl.cam.ac.uk>
+
+  > I was wondering what the copyright status of your "UK English
+  > Wordlist With Frequency Classification" word list as it seems to
+  > be lacking any copyright notice.
+
+  There were many many sources in total, but any text marked
+  "copyright" was avoided. Locally-written documentation was one
+  source. An earlier version of the list resided in a filespace called
+  PUBLIC on the University mainframe, because it was considered public
+  domain.
+
+  Date: Tue, 11 Jul 2000 19:31:34 +0100
+
+  > So are you saying your word list is also in the public domain?
+
+  That is the intention.
+
+The 20 level includes frequency classes 7-15 from Brian's word list.
+
+The 35 level includes frequency classes 2-6 and words appearing in at
+least 11 of 12 dictionaries as indicated in the 12Dicts package.  All
+words from the 12Dicts package have had likely inflections added via
+my inflection database.
+
+The 12Dicts package and Supplement is in the Public Domain.
+
+The WordNet database, which was used in the creation of the
+Inflections database, is under the following copyright:
+
+  This software and database is being provided to you, the LICENSEE,
+  by Princeton University under the following license.  By obtaining,
+  using and/or copying this software and database, you agree that you
+  have read, understood, and will comply with these terms and
+  conditions.:
+
+  Permission to use, copy, modify and distribute this software and
+  database and its documentation for any purpose and without fee or
+  royalty is hereby granted, provided that you agree to comply with
+  the following copyright notice and statements, including the
+  disclaimer, and that the same appear on ALL copies of the software,
+  database and documentation, including modifications that you make
+  for internal use or for distribution.
+
+  WordNet 1.6 Copyright 1997 by Princeton University.  All rights
+  reserved.
+
+  THIS SOFTWARE AND DATABASE IS PROVIDED "AS IS" AND PRINCETON
+  UNIVERSITY MAKES NO REPRESENTATIONS OR WARRANTIES, EXPRESS OR
+  IMPLIED.  BY WAY OF EXAMPLE, BUT NOT LIMITATION, PRINCETON
+  UNIVERSITY MAKES NO REPRESENTATIONS OR WARRANTIES OF MERCHANT-
+  ABILITY OR FITNESS FOR ANY PARTICULAR PURPOSE OR THAT THE USE OF THE
+  LICENSED SOFTWARE, DATABASE OR DOCUMENTATION WILL NOT INFRINGE ANY
+  THIRD PARTY PATENTS, COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS.
+
+  The name of Princeton University or Princeton may not be used in
+  advertising or publicity pertaining to distribution of the software
+  and/or database.  Title to copyright in this software, database and
+  any associated documentation shall at all times remain with
+  Princeton University and LICENSEE agrees to preserve same.
+
+The 40 level includes words from Alan's 3esl list found in version 4.0
+of his 12dicts package.  Like his other stuff the 3esl list is also in the
+public domain.
+
+The 50 level includes Brian's frequency class 1, words words appearing
+in at least 5 of 12 of the dictionaries as indicated in the 12Dicts
+package, and uppercase words in at least 4 of the previous 12
+dictionaries.  A decent number of proper names is also included: The
+top 1000 male, female, and Last names from the 1990 Census report; a
+list of names sent to me by Alan Beale; and a few names that I added
+myself.  Finally a small list of abbreviations not commonly found in
+other word lists is included.
+
+The name files form the Census report is a government document which I
+don't think can be copyrighted.
+
+The file special-jargon.50 uses common.lst and word.lst from the
+"Unofficial Jargon File Word Lists" which is derived from "The Jargon
+File".  All of which is in the Public Domain.  This file also contain
+a few extra UNIX terms which are found in the file "unix-terms" in the
+special/ directory.
+
+The 55 level includes words from Alan's 2of4brif list found in version
+4.0 of his 12dicts package.  Like his other stuff the 2of4brif is also
+in the public domain.
+
+The 60 level includes all words appearing in at least 2 of the 12
+dictionaries as indicated by the 12Dicts package.
+
+The 70 level includes Brian's frequency class 0 and the 74,550 common
+dictionary words from the MWords package.  The common dictionary words,
+like those from the 12Dicts package, have had all likely inflections
+added.  The 70 level also included the 5desk list from version 4.0 of
+the 12Dics package which is the public domain.
+
+The 80 level includes the ENABLE word list, all the lists in the
+ENABLE supplement package (except for ABLE), the "UK Advanced Cryptics
+Dictionary" (UKACD), the list of signature words in from YAWL package,
+and the 10,196 places list from the MWords package.
+
+The ENABLE package, mainted by M\Cooper <thegrendel@theriver.com>,
+is in the Public Domain:
+
+  The ENABLE master word list, WORD.LST, is herewith formally released
+  into the Public Domain. Anyone is free to use it or distribute it in
+  any manner they see fit. No fee or registration is required for its
+  use nor are "contributions" solicited (if you feel you absolutely
+  must contribute something for your own peace of mind, the authors of
+  the ENABLE list ask that you make a donation on their behalf to your
+  favorite charity). This word list is our gift to the Scrabble
+  community, as an alternate to "official" word lists. Game designers
+  may feel free to incorporate the WORD.LST into their games. Please
+  mention the source and credit us as originators of the list. Note
+  that if you, as a game designer, use the WORD.LST in your product,
+  you may still copyright and protect your product, but you may *not*
+  legally copyright or in any way restrict redistribution of the
+  WORD.LST portion of your product. This *may* under law restrict your
+  rights to restrict your users' rights, but that is only fair.
+
+UKACD, by J Ross Beresford <ross@bryson.demon.co.uk>, is under the
+following copyright:
+
+  Copyright (c) J Ross Beresford 1993-1999. All Rights Reserved.
+
+  The following restriction is placed on the use of this publication:
+  if The UK Advanced Cryptics Dictionary is used in a software package
+  or redistributed in any form, the copyright notice must be
+  prominently displayed and the text of this document must be included
+  verbatim.
+
+  There are no other restrictions: I would like to see the list
+  distributed as widely as possible.
+
+The 95 level includes the 354,984 single words, 256,772 compound
+words, 4,946 female names and the 3,897 male names, and 21,986 names
+from the MWords package, ABLE.LST from the ENABLE Supplement, and some
+additional words found in my part-of-speech database that were not
+found anywhere else.
+
+Accent information was taken from UKACD.
+
+My VARCON package was used to create the American, British, and
+Canadian word list. 
+
+Since the original word lists used used in the VARCON package came
+from the Ispell distribution they are under the Ispell copyright:
+
+  Copyright 1993, Geoff Kuenning, Granada Hills, CA
+  All rights reserved.
+
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+  1. Redistributions of source code must retain the above copyright
+     notice, this list of conditions and the following disclaimer.
+  2. Redistributions in binary form must reproduce the above copyright
+     notice, this list of conditions and the following disclaimer in the
+     documentation and/or other materials provided with the distribution.
+  3. All modifications to the source code must be clearly marked as
+     such.  Binary redistributions based on modified source code
+     must be clearly marked as modified versions in the documentation
+     and/or other materials provided with the distribution.
+  (clause 4 removed with permission from Geoff Kuenning)
+  5. The name of Geoff Kuenning may not be used to endorse or promote
+     products derived from this software without specific prior
+     written permission.
+
+  THIS SOFTWARE IS PROVIDED BY GEOFF KUENNING AND CONTRIBUTORS ``AS
+  IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+  FOR A PARTICULAR PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL GEOFF
+  KUENNING OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+  INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+  BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+  LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+  CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+  LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+  ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+  POSSIBILITY OF SUCH DAMAGE.

data/lib/whatlanguage.rb

@@ -1,19 +1,18 @@
-require File.join(File.dirname(__FILE__), 'bloominsimple')
+require 'whatlanguage/bloominsimple'
+require 'whatlanguage/bitfield'
 require 'digest/sha1'
 
-class WhatLanguage
-  VERSION = '1.0.0'
-  
+class WhatLanguage  
   HASHER = lambda { |item| Digest::SHA1.digest(item.downcase.strip).unpack("VV") }
   
   BITFIELD_WIDTH = 2_000_000
   
   @@data = {}
   
-  def initialize(options)
+  def initialize(options = {})
     languages_folder = File.join(File.dirname(__FILE__), "..", "lang")
     Dir.entries(languages_folder).grep(/\.lang/).each do |lang|
-      @@data[lang[/\w+/].to_sym] ||= BloominSimple.from_dump(File.read(File.join(languages_folder, lang)), &HASHER)
+      @@data[lang[/\w+/].to_sym] ||= BloominSimple.from_dump(File.new(File.join(languages_folder, lang), 'rb').read, &HASHER)
     end
   end
   

data/lib/{bloominsimple.rb → whatlanguage/bloominsimple.rb}

@@ -36,7 +36,7 @@
 #                 #  =>    nooooooo: false
 #                 #  => newyorkcity: false
 
-require File.join(File.dirname(__FILE__), 'bitfield')
+require 'whatlanguage/bitfield'
 
 class BloominSimple
   attr_accessor :bitfield, :hasher

data/lib/whatlanguage/version.rb

@@ -0,0 +1,3 @@
+class WhatLanguage
+  VERSION = '1.0.4'
+end

data/test/test_whatlanguage.rb

@@ -1,6 +1,7 @@
+# encoding: utf-8
 require "test/unit"
 
-require File.join(File.dirname(__FILE__), "..", "lib", "whatlanguage")
+require 'whatlanguage'
 
 class TestWhatLanguage < Test::Unit::TestCase
   def setup
@@ -10,7 +11,11 @@ class TestWhatLanguage < Test::Unit::TestCase
   def test_string_method
     assert_equal :english, "This is a test".language
   end
-  
+
+  def test_dutch
+    assert_equal :dutch, @wl.language("Als hadden geweest is, is hebben te laat.")
+  end
+
   def test_french
     assert_equal :french, @wl.language("Bonjour, je m'appelle Sandrine. Voila ma chatte.")
   end
@@ -18,6 +23,14 @@ class TestWhatLanguage < Test::Unit::TestCase
   def test_spanish
     assert_equal :spanish, @wl.language("La palabra mezquita se usa en español para referirse a todo tipo de edificios dedicados.")
   end
+
+  def test_swedish
+    assert_equal :swedish, @wl.language("Den spanska räven rev en annan räv alldeles lagom.")
+  end
+
+  def test_russian
+    assert_equal :russian, @wl.language("Все новости в хронологическом порядке")
+  end
   
   def test_nothing
     assert_nil @wl.language("")
@@ -30,4 +43,9 @@ class TestWhatLanguage < Test::Unit::TestCase
   def test_processor
     assert_kind_of Hash, @wl.process_text("this is a test")
   end
-end
+
+  def test_italian
+    assert_equal :italian, @wl.language("Roma, capitale dell'impero romano, è stata per secoli il centro politico e culturale della civiltà occidentale.")
+  end
+
+end

data/whatlanguage.gemspec

@@ -0,0 +1,19 @@
+# -*- encoding: utf-8 -*-
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'whatlanguage/version'
+
+Gem::Specification.new do |gem|
+  gem.name          = "whatlanguage"
+  gem.version       = WhatLanguage::VERSION
+  gem.authors       = ["Peter Cooper"]
+  gem.email         = ["git@peterc.org"]
+  gem.description   = %q{WhatLanguage rapidly detects the language of a sample of text}
+  gem.summary       = %q{Natural language detection for text samples}
+  gem.homepage      = "https://github.com/peterc/whatlanguage"
+
+  gem.files         = `git ls-files`.split($/).reject { |f| f.start_with?("wordlists") }
+  gem.executables   = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
+  gem.test_files    = gem.files.grep(%r{^(test|spec|features)/})
+  gem.require_paths = ["lib"]
+end

metadata

@@ -1,83 +1,72 @@
---- !ruby/object:Gem::Specification 
+--- !ruby/object:Gem::Specification
 name: whatlanguage
-version: !ruby/object:Gem::Version 
-  version: 1.0.0
+version: !ruby/object:Gem::Version
+  version: 1.0.4
 platform: ruby
-authors: 
+authors:
 - Peter Cooper
 autorequire: 
 bindir: bin
 cert_chain: []
-
-date: 2008-08-22 00:00:00 +01:00
-default_executable: 
-dependencies: 
-- !ruby/object:Gem::Dependency 
-  name: hoe
-  type: :development
-  version_requirement: 
-  version_requirements: !ruby/object:Gem::Requirement 
-    requirements: 
-    - - ">="
-      - !ruby/object:Gem::Version 
-        version: 1.7.0
-    version: 
-description: "== FEATURES/PROBLEMS:  * Only does French, English and Spanish out of the box. Very easy to train new languages though. * It can be made far more efficient at the comparison stage, but all in good time..! It still beats literal dictionary approaches. * No filter selection yet, you get 'em all loaded. * Tests are reasonably light.  == SYNOPSIS:  Full Example require 'whatlanguage'  texts = [] texts << %q{Deux autres personnes ont \xC3\xA9t\xC3\xA9 arr\xC3\xAAt\xC3\xA9es durant la nuit} texts << %q{The links between the attempted car bombings in Glasgow and London are becoming clearer} texts << %q{En estado de m\xC3\xA1xima alertaen su nivel de cr\xC3\xADtico} texts << %q{Returns the object in enum with the maximum value.} texts << %q{Propose des donn\xC3\xA9es au sujet de la langue espagnole.} texts << %q{La palabra \"mezquita\" se usa en espa\xC3\xB1ol para referirse a todo tipo de edificios dedicados.}  texts.each { |text| puts \"#{text[0..18]}... is in #{text.language.to_s.capitalize}\" }  Initialize WhatLanguage with all filters wl = WhatLanguage.new(:all)"
-email: whatlanguage@peterc.org
+date: 2013-03-07 00:00:00.000000000 Z
+dependencies: []
+description: WhatLanguage rapidly detects the language of a sample of text
+email:
+- git@peterc.org
 executables: []
-
 extensions: []
-
-extra_rdoc_files: 
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
 - History.txt
+- LICENSE.txt
 - Manifest.txt
-- README.txt
-files: 
-- History.txt
-- Manifest.txt
-- README.txt
+- README.md
 - Rakefile
 - build_filter.rb
+- build_lang_from_wordlists.rb
+- copyright-en
 - example.rb
 - lang/dutch.lang
+- lang/english.lang
 - lang/farsi.lang
+- lang/french.lang
 - lang/german.lang
+- lang/italian.lang
 - lang/pinyin.lang
-- lang/russian.lang
-- lang/english.lang
 - lang/portuguese.lang
-- lang/french.lang
+- lang/russian.lang
 - lang/spanish.lang
-- lib/bitfield.rb
-- lib/bloominsimple.rb
+- lang/swedish.lang
 - lib/whatlanguage.rb
+- lib/whatlanguage/bitfield.rb
+- lib/whatlanguage/bloominsimple.rb
+- lib/whatlanguage/version.rb
 - test/test_whatlanguage.rb
-has_rdoc: true
-homepage: http://rubyforge.org/projects/whatlanguage/
+- whatlanguage.gemspec
+homepage: https://github.com/peterc/whatlanguage
+licenses: []
+metadata: {}
 post_install_message: 
-rdoc_options: 
-- --main
-- README.txt
-require_paths: 
+rdoc_options: []
+require_paths:
 - lib
-required_ruby_version: !ruby/object:Gem::Requirement 
-  requirements: 
-  - - ">="
-    - !ruby/object:Gem::Version 
-      version: "0"
-  version: 
-required_rubygems_version: !ruby/object:Gem::Requirement 
-  requirements: 
-  - - ">="
-    - !ruby/object:Gem::Version 
-      version: "0"
-  version: 
+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: whatlanguage
-rubygems_version: 1.2.0
+rubyforge_project: 
+rubygems_version: 2.0.0
 signing_key: 
-specification_version: 2
-summary: Fast, quick, textual language detection
-test_files: 
+specification_version: 4
+summary: Natural language detection for text samples
+test_files:
 - test/test_whatlanguage.rb