peterc-whatlanguage 1.0.1 → 1.0.2

data/README.txt

@@ -7,9 +7,10 @@ whatlanguage
   
 Text language detection. Quick, fast, memory efficient, and all in pure Ruby. Uses Bloom filters for aforementioned speed and memory benefits.
 
+Works with Dutch, English, Farsi, French, German, Swedish, Portuguese, Russian and Spanish out of the box.
+
 == 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.
@@ -45,6 +46,16 @@ Text language detection. Quick, fast, memory efficient, and all in pure Ruby. Us
 
 * None, minor libraries (BloominSimple and BitField) included with this release.
 
+== INSTALLATION:
+
+  gem sources -a http://gems.github.com
+  sudo gem install peterc-whatlanguage
+
+  To test, go into irb, then:
+
+  require 'whatlanguage'
+  "Je suis un homme".language
+
 == LICENSE:
 
 (The MIT License)

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

@@ -6,7 +6,8 @@ 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"), 'w') { |f| f.write filter.dump }
-end
+  File.open(File.join(languages_folder, lang + ".lang"), 'wb') { |f| f.write filter.dump }
+end

data/lib/whatlanguage.rb

@@ -2,7 +2,7 @@ require File.join(File.dirname(__FILE__), 'bloominsimple')
 require 'digest/sha1'
 
 class WhatLanguage
-  VERSION = '1.0.0'
+  VERSION = '1.0.2'
   
   HASHER = lambda { |item| Digest::SHA1.digest(item.downcase.strip).unpack("VV") }
   
@@ -10,7 +10,7 @@ class WhatLanguage
   
   @@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/test/test_whatlanguage.rb

@@ -18,6 +18,10 @@ 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_nothing
     assert_nil @wl.language("")

data/whatlanguage.gemspec

@@ -1,7 +1,7 @@
 Gem::Specification.new do |s|
   s.name     = "whatlanguage"
-  s.version  = "1.0.1"
-  s.date     = "2008-08-22"
+  s.version  = "1.0.2"
+  s.date     = "2008-08-23"
   s.summary  = "Natural language detection for text samples"
   s.email    = "whatlanguage@peterc.org"
   s.homepage = "http://github.com/peterc/whatlanguage"
@@ -22,6 +22,7 @@ Gem::Specification.new do |s|
 "lang/portuguese.lang",
 "lang/russian.lang",
 "lang/spanish.lang",
+"lang/swedish.lang",
 "lib/bitfield.rb",
 "lib/bloominsimple.rb",
 "lib/whatlanguage.rb",

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: peterc-whatlanguage
 version: !ruby/object:Gem::Version 
-  version: 1.0.1
+  version: 1.0.2
 platform: ruby
 authors: 
 - Peter Cooper
@@ -9,7 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2008-08-22 00:00:00 -07:00
+date: 2008-08-23 00:00:00 -07:00
 default_executable: 
 dependencies: []
 
@@ -37,6 +37,7 @@ files:
 - lang/portuguese.lang
 - lang/russian.lang
 - lang/spanish.lang
+- lang/swedish.lang
 - lib/bitfield.rb
 - lib/bloominsimple.rb
 - lib/whatlanguage.rb