scylla 0.2.0 → 0.3.0

data/README.rdoc

@@ -2,27 +2,43 @@
 
 Scylla is a language categorizing gem that allows you to guess the language of a given text. Scylla is a Ruby port of TextCat (http://www.let.rug.nl/~vannoord/TextCat) and is based on the text categorization algorithm presented in Cavnar, W. B. and J. M. Trenkle, ``N-Gram-Based Text Categorization'' In Proceedings of Third Annual Symposium on Document Analysis and Information Retrieval, Las Vegas, NV, UNLV Publications/Reprographics, pp. 161-175, 11-13 April 1994.
 
-Installation:
+== Installation
 
-gem install scylla
+ gem install scylla
 
-Usage:
+== Usage
 
-require 'scylla'
+ require 'scylla'
 
-"this is english text".language
+ "this is english text".language
  => "english" 
 
-"Este es un texto español".language
-=> "spanish"
+ "Este es un texto español".language
+ => "spanish"
 
 Multiple results for other possible languages:
 
-"isso poderia ser confundido com espanhol, bem".language
-=> "portuguese"
+ "isso poderia ser confundido com espanhol, bem".language
+ => "portuguese"
 
-"isso poderia ser confundido com espanhol, bem".guess
-=> ["portuguese", "spanish"]
+ "isso poderia ser confundido com espanhol, bem".guess
+ => ["portuguese", "spanish"]
+
+== 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:
+
+ 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
  

data/VERSION

@@ -1 +1 @@
-0.2.0
+0.3.0

data/lib/scylla/generator.rb

@@ -6,6 +6,7 @@ module Scylla
     # minsize: The minimum size of the ngrams that you would like to store
     def initialize(dirtext = DEFAULT_SOURCE_DIR, dirlm = DEFAULT_TARGET_DIR, minsize = 0, silent = false)
       @dirtext = dirtext
+      p @dirtext
       @dirlm   = dirlm
       @minsize = minsize
     end

data/lib/scylla/tasks.rb

@@ -10,8 +10,9 @@ module Scylla
     def define_training_task
       namespace :scylla do
         desc "Trains Scylla in new languages"
-        task :train do
-          sg = Scylla::Generator.new
+        task :train, :dir do |t, args|
+          args.with_defaults(:dir => DEFAULT_SOURCE_DIR)
+          sg = Scylla::Generator.new(args[:dir])
           sg.train
         end
       end

data/scylla.gemspec

@@ -5,7 +5,7 @@
 
 Gem::Specification.new do |s|
   s.name = %q{scylla}
-  s.version = "0.2.0"
+  s.version = "0.3.0"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Ashwin Hegde"]

data/test/loader_test.rb

@@ -9,7 +9,7 @@ class LoaderTest < Test::Unit::TestCase
     end
 
     context "when being read" do
-      should_eventually "only load from disk once" do
+      should "only load from disk once" do
        Scylla::Loader.expects(:load_language_maps).once.returns([])
         Scylla::Loader.languages
         Scylla::Loader.languages

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: scylla
 version: !ruby/object:Gem::Version 
-  hash: 23
+  hash: 19
   prerelease: 
   segments: 
   - 0
-  - 2
+  - 3
   - 0
-  version: 0.2.0
+  version: 0.3.0
 platform: ruby
 authors: 
 - Ashwin Hegde