scylla 1.0.7 → 1.0.8

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: cc4efa8f7db7f8d6af1db0fb2ce7c204b6238fd7
+  data.tar.gz: 96723ba86150e5612a1b88ae7ef568bf4080c13a
+SHA512:
+  metadata.gz: e99255de08664a38cc0f155f2d4789f04139dc2277d285aebfa887dcfa4956f9caec90dabfecc1316e6652795f0220c5d5a47decd57f2a4d15da3106c86ad4d1
+  data.tar.gz: b64726df9e01a455e475818e7dd0b9cbe285c056d04a06a7bb576273e8e772444c9c316728c0b0140a400dc2cbfbd7e8cc482065bde720575830ffe8767c3b1f

data/README.rdoc

@@ -26,20 +26,11 @@ Multiple results for other possible languages:
 
 == Training
 
-You can train scylla in new languages by providing sample texts in different languages. The default set is located in the 'source_texts' folder in the gem directory. Add new .txt files to this directory named according to the language i.e. a text file full of Hebrew text should be called 'hebrew.txt'. At least 500 lines of text recommended. Then, in the gem folder, run this:
+Training is done by fetching data from wikipedia. To fetch latest articles (The country name in the language
+in question, eg. "England" for English or "日本" for Japanese), run
 
  rake scylla:train
 
-If you want to store texts in your own folder, you can specify that to the rake task.
-WARNING: specifying a different folder deletes all language support for files located in the default directory if they are not copied over.
-
- rake scylla:train[/Users/hash/mytextdir]
- "Creating language map for /Users/hash/mytextdir/english.txt"
- "Creating language map for /Users/hash/mytextdir/kannada.txt"
- .
- .
- etc
-
 == Contributing to scylla
  
 * Check out the latest master to make sure the feature hasn't been implemented or the bug hasn't been fixed yet

data/test/classifier_test.rb

@@ -1,7 +1,7 @@
 # encoding: utf-8
 require 'helper'
 
-class ClassifierTest < Test::Unit::TestCase
+class ClassifierTest < Minitest::Test
 
   context "#classify" do
     setup do

data/test/generator_test.rb

@@ -1,6 +1,6 @@
 require 'helper'
 
-class GeneratorTest < Test::Unit::TestCase
+class GeneratorTest < Minitest::Test
   context "create_lm ngrams" do
     setup do
       Scylla::Loader.set_dir(File.join("test","fixtures","lms"))

data/test/helper.rb

@@ -1,7 +1,7 @@
 require 'rubygems'
-require 'ruby-debug'
 require 'bundler'
-require 'test/unit'
+require "minitest/autorun"
+# require 'test/unit'
 require 'shoulda'
 require 'scylla'
 require 'sanitize'
@@ -18,5 +18,5 @@ end
 $LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
 $LOAD_PATH.unshift(File.dirname(__FILE__))
 
-class Test::Unit::TestCase
+class Minitest::Test
 end

data/test/language_test.rb

@@ -1,6 +1,6 @@
 require 'helper'
 
-class LanguageTest < Test::Unit::TestCase
+class LanguageTest < Minitest::Test
   context "language detection" do
     setup do
       @sentences = Hash.new

data/test/loader_test.rb

@@ -1,6 +1,6 @@
 require 'helper'
 
-class LoaderTest < Test::Unit::TestCase
+class LoaderTest < Minitest::Test
   context "#languages" do
     setup do
       Scylla::Loader.clear

data/test/scylla_test.rb

@@ -1,6 +1,6 @@
 require 'helper'
 
-class ScyllaTest < Test::Unit::TestCase
+class ScyllaTest < Minitest::Test
   context "String methods" do
     setup do
       Scylla::Loader.set_dir(File.join("test","fixtures","lms"))
@@ -12,8 +12,8 @@ class ScyllaTest < Test::Unit::TestCase
     end
 
     should "load language results for strings" do
-      assert_not_nil @language
-      assert_not_nil @languages
+      assert @language
+      assert @languages
       assert_equal String, @language.class
       assert_equal Array, @languages.class
       assert_equal "english", @language

metadata

@@ -1,8 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: scylla
 version: !ruby/object:Gem::Version
-  version: 1.0.7
-  prerelease: 
+  version: 1.0.8
 platform: ruby
 authors:
 - Ashwin Hegde
@@ -14,35 +13,45 @@ dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: sanitize
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: unicode
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.4.4
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.4.4
 description: Allows for text categorization by guessing the language of a given text
   using n-grams
 email: ahegde@zendesk.com
@@ -53,6 +62,10 @@ extra_rdoc_files:
 - LICENSE.txt
 - README.rdoc
 files:
+- LICENSE.txt
+- README.rdoc
+- bin/scylla
+- lib/scylla.rb
 - lib/scylla/classifier.rb
 - lib/scylla/generator.rb
 - lib/scylla/lms/arabic.lm
@@ -95,9 +108,6 @@ files:
 - lib/scylla/resources.rb
 - lib/scylla/string.rb
 - lib/scylla/tasks.rb
-- lib/scylla.rb
-- README.rdoc
-- LICENSE.txt
 - test/classifier_test.rb
 - test/fixtures/lms/arabic.lm
 - test/fixtures/lms/bulgarian.lm
@@ -157,31 +167,29 @@ files:
 - test/language_test.rb
 - test/loader_test.rb
 - test/scylla_test.rb
-- bin/scylla
 homepage: http://github.com/hashwin/scylla
 licenses:
 - MIT
+metadata: {}
 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: 
-rubygems_version: 1.8.25
+rubygems_version: 2.5.2
 signing_key: 
-specification_version: 3
+specification_version: 4
 summary: Ruby port of Textcat language guesser
 test_files:
 - test/classifier_test.rb