wapiti 0.0.4 → 0.0.5

data/HISTORY.md

@@ -0,0 +1,13 @@
+0.0.5 / 2011-09-06
+==================
+* Added UTF-8 encoding to native result strings for Ruby 1.9
+
+0.0.3 / 2011-09-02
+==================
+* Added support for output scores
+* Improved n-best output
+* Added statistics
+
+0.0.2 / 2011-09-01
+==================
+* Initial release

data/README.md

@@ -14,7 +14,7 @@ Wapiti is written in C and Ruby and requires a compiler with C99
 support (e.g., gcc); on GNU/Linux systems it will be fairly easy to install
 all necessary packages through your distribution; on Mac OS X you can either
 install Xcode or
-(osx-gcc-installer)[https://github.com/kennethreitz/osx-gcc-installer];
+[osx-gcc-installer](https://github.com/kennethreitz/osx-gcc-installer);
 on Windows you may want to install RubyInstaller's
 [DevKit](https://github.com/oneclick/rubyinstaller/wiki/development-kit).
 

data/ext/wapiti/native.c

@@ -991,7 +991,14 @@ static VALUE decode_sequence(VALUE self, mdl_t *model, raw_t *raw) {
 		tokens = rb_ary_new();
 		
 		if (!model->opt->label) {
-			rb_ary_push(tokens, rb_str_new2(raw->lines[t]));
+			VALUE token = rb_str_new2(raw->lines[t]);
+			
+			#ifdef HAVE_RUBY_ENCODING_H
+			int enc = rb_enc_find_index("UTF-8");
+			rb_enc_associate_index(token, enc);
+			#endif
+						
+			rb_ary_push(tokens, token);
 		}
 		
 		for (n = 0; n < N; ++n) {

data/ext/wapiti/native.h

@@ -3,6 +3,10 @@
 
 #include <ruby.h>
 
+#ifdef HAVE_RUBY_ENCODING_H
+#include <ruby/encoding.h>
+#endif
+
 extern VALUE mWapiti;
 extern VALUE mNative;
 

data/lib/wapiti/version.rb

@@ -1,3 +1,3 @@
 module Wapiti
-  VERSION = '0.0.4'.freeze
+  VERSION = '0.0.5'.freeze
 end

data/spec/wapiti/model_spec.rb

@@ -1,3 +1,5 @@
+# -*- encoding: utf-8 -*-
+
 module Wapiti
 	describe 'Model' do
 		
@@ -128,14 +130,14 @@ module Wapiti
 				let(:model) { Model.load(File.expand_path('../../fixtures/ch.mod', __FILE__)) }
 				
 				context 'when passed an array of arrays' do
-					let(:input) { [['Hello NN B-VP', ', , O', 'world NN B-NP', '! ! O']] }
+					let(:input) { [['Héllo NN B-VP', ', , O', 'world NN B-NP', '! ! O']] }
 					
 					it 'returns an array of token-label pairs' do
 						labels = model.label(input)
 						labels[0].map(&:first).should == input[0]
 						labels[0].map(&:last).should == %w{ B-NP O B-NP O }
 					end
-					
+										
 					it 'yields each token/label pair to the supplied block' do
 						labels = model.label(input) do |token, label|
 				      [token.downcase, label.downcase]

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: wapiti
 version: !ruby/object:Gem::Version
-  version: 0.0.4
+  version: 0.0.5
   prerelease: 
 platform: ruby
 authors:
@@ -9,11 +9,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2011-09-03 00:00:00.000000000Z
+date: 2011-09-06 00:00:00.000000000Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
-  requirement: &2156718440 !ruby/object:Gem::Requirement
+  requirement: &2156563060 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -21,10 +21,10 @@ dependencies:
         version: '0.9'
   type: :development
   prerelease: false
-  version_requirements: *2156718440
+  version_requirements: *2156563060
 - !ruby/object:Gem::Dependency
   name: rake-compiler
-  requirement: &2156717640 !ruby/object:Gem::Requirement
+  requirement: &2156559320 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -32,10 +32,10 @@ dependencies:
         version: '0.7'
   type: :development
   prerelease: false
-  version_requirements: *2156717640
+  version_requirements: *2156559320
 - !ruby/object:Gem::Dependency
   name: ZenTest
-  requirement: &2156717060 !ruby/object:Gem::Requirement
+  requirement: &2156553240 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -43,10 +43,10 @@ dependencies:
         version: '4.6'
   type: :development
   prerelease: false
-  version_requirements: *2156717060
+  version_requirements: *2156553240
 - !ruby/object:Gem::Dependency
   name: rspec
-  requirement: &2156685780 !ruby/object:Gem::Requirement
+  requirement: &2156552400 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -54,7 +54,7 @@ dependencies:
         version: '2.6'
   type: :development
   prerelease: false
-  version_requirements: *2156685780
+  version_requirements: *2156552400
 description: This gem provides a Ruby API for Conditional Random Fields (CRF). It
   is implemented as a C exstension and based on the wicked fast "wapiti" package.
 email:
@@ -70,6 +70,7 @@ files:
 - .gitignore
 - .rspec
 - Gemfile
+- HISTORY.md
 - LICENSE
 - README.md
 - Rakefile