mattetti-multibyte 0.0.1

data/spec/multibyte_spec.rb

@@ -0,0 +1,260 @@
+require File.dirname(__FILE__) + '/spec_helper.rb'
+
+describe "Chars" do
+  
+  describe 'dealing with different string formats' do
+  
+    string_format_examples.each do |type, string|
+      describe "a #{type} string" do
+        it "should have the chars method" do
+            string.should respond_to(:chars)
+        end
+      
+        it "should have the to_s method" do
+          string.should respond_to(:to_s)
+        end
+        
+        it "should return an instance of Chars" do
+          string.chars.should be_an_instance_of(Multibyte::Chars)
+        end
+        
+        it "should not be changed when Chars#to_s is used" do
+          string.chars.to_s.should == string
+        end
+      end
+    end
+    
+  end
+    
+    
+  describe 'comparison' do
+    
+    it "should be able to compare normal strings properly" do
+      'a'.should == 'a'
+      'a'.should_not == 'b'
+    end
+  
+    it "should be able to compare chars strings" do
+    "a".chars.should_not == "b".chars
+    "a".chars.should == "A".downcase.chars
+     "a".chars.should == "A".downcase
+    end
+    
+    it "should not support strict comparison" do
+      string_format_examples[:utf8].eql?(string_format_examples[:utf8].chars).should be_false
+    end
+    
+    it "should be compared by their enclosed string" do
+      string_format_examples[:utf8].should == string_format_examples[:utf8].chars
+      other_string = string_format_examples[:utf8].dup
+      other_string.should == string_format_examples[:utf8].chars
+      other_string.chars.should == string_format_examples[:utf8].chars
+    end
+    
+    it "should be sortable based on their enclosed string" do
+      unsorted_strings = ['builder'.chars, 'armor'.chars, 'zebra'.chars]
+      unsorted_strings.sort!
+      ['armor', 'builder', 'zebra'].should == unsorted_strings
+    end
+  
+  end
+  
+  describe 'utf8?' do
+    
+    it "should know that UTF-8 strings are UTF-8" do
+      string_format_examples[:utf8].is_utf8?.should be_true
+    end
+    
+    it "should know that ascii strings are also valid UTF-8" do
+      string_format_examples[:ascii].is_utf8?.should be_true
+    end
+    
+    it "should know that bytestrings not valid utf-8" do
+      string_format_examples[:bytes].is_utf8?.should be_false
+    end
+    
+  end
+  
+  describe 'gsub' do
+    
+    it "should be able to gsub" do
+      'café'.chars.gsub(/f/, 't').should == 'caté'
+      "我的影片".chars.gsub(/片/, 'X').should == "我的影X"
+    end
+    
+    it "should be to gsub even without the kcode setup" do
+      with_kcode('none') do
+        'éda'.chars.gsub(/d/, 'x').should == 'éxa'
+      end
+    end
+    
+  end
+  
+  describe 'split' do
+    
+    before(:each) do
+      @word = "efficient"
+      @chars = ["e", "ffi", "c", "i", "e", "n", "t"]
+    end
+
+    it "should split by chars" do
+      @word.split(//).should == @chars
+      @chars.should == @word.chars.split(//)
+    end
+    
+    it "should return Chars instances" do
+      @word.chars.split(//).first.should be_an_instance_of(Multibyte::Chars)
+    end
+    
+  end
+  
+  describe 'regexp matching' do
+    
+    it "should should use String when kcode not set" do
+      with_kcode('none') do
+        (string_format_examples[:utf8].chars =~ /ffi/).should == 12
+      end
+    end
+    
+    it "should be unicode aware" do
+      with_kcode('UTF8') do
+        (string_format_examples[:utf8].chars =~ /ffi/).should == 9
+      end
+    end
+    
+    it "should return nil if no matches were found" do
+      with_kcode('UTF8') do
+        (''.chars =~ /\d+/).should be_nil
+      end
+    end
+    
+  end
+  
+  describe 'UTF8 pragma' do
+    
+    it "should be on because KCODE is UTF8" do
+      if RUBY_VERSION < '1.9'
+        with_kcode('UTF8') do
+          " ".chars.send(:utf8_pragma?).should be_true
+        end
+      end
+    end
+    
+    it "should be off because KCODE is UTF8" do
+      if RUBY_VERSION < '1.9'
+        with_kcode('none') do
+          " ".chars.send(:utf8_pragma?).should be_false
+        end
+      end
+    end
+    
+    it "should be OFF on Ruby 1.9" do
+      if RUBY_VERSION > '1.9'
+        " ".chars.send(:utf8_pragma?).shoud be_false
+      end
+    end
+    
+  end
+  
+  describe 'handler settings' do
+    
+    before(:each) do
+      @handler = ''.chars.handler
+    end
+    
+    after(:all) do
+      Multibyte::Chars.handler = Multibyte::Handlers::UTF8Handler
+    end
+    
+    it "should process use and set handlers in the proper order" do
+      Multibyte::Chars.handler = :first
+      ''.chars.handler.should == :first
+      
+      Multibyte::Chars.handler = :second
+      ''.chars.handler.should == :second
+      
+      Multibyte::Chars.handler = @handler
+    end
+    
+    it "should raise an error" do
+      lambda{''.chars.handler.split}.should raise_error
+    end
+
+  end
+  
+  describe 'method chaining' do
+    
+    it "should return a chars instance when using downcase" do
+      ''.chars.downcase.should be_an_instance_of(Multibyte::Chars)
+    end
+    
+    it "should return a chars instance when using downcase" do
+      ''.chars.strip.should be_an_instance_of(Multibyte::Chars)
+    end
+    
+    it "should forward the chars instance down the down call path of chaining" do
+      stripped = ''.chars.downcase.strip
+      stripped.should be_an_instance_of(Multibyte::Chars)
+    end
+    
+    it "should output a comparable result than a string result" do
+      "  FOO   ".chars.normalize.downcase.strip.should == 'foo'
+    end
+    
+  end
+  
+  describe 'passthrough_on_kcode' do
+    # The easiest way to check if the passthrough is in place is through #size
+    with_kcode('none') do
+      string_format_examples[:utf8].chars.size.should == 26
+    end
+    
+    with_kcode('UTF8') do
+      string_format_examples[:utf8].chars.size.should == 17
+    end
+  end
+  
+  describe 'desctructiveness' do
+    # Note that we're testing the destructiveness here and not the correct behaviour of the methods
+    
+    before(:each) do
+      @str = 'ac'
+    end
+    
+    it "should be destructive when using Insert on a string" do
+      @str.chars.insert(1, 'b')
+      @str.should == 'abc'
+    end
+    
+    it "should be destructive when using reverse! on a string" do
+      @str.chars.reverse!
+      @str.should == 'ca'
+    end
+    
+  end
+  
+  describe 'resilience' do
+    
+    it "should contain interpretable bytes" do
+      string_format_examples[:bytes].chars.size.should == 5
+    end
+    
+    it "should only yield interpretable bytes when a string is reversed" do
+      reversed = [0xb8, 0x17e, 0x8, 0x2c6, 0xa5].reverse.pack('U*')
+      string_format_examples[:bytes].chars.reverse.to_s.should == reversed
+      string_format_examples[:bytes].chars.reverse!.to_s.should == reversed
+    end
+  end
+  
+  describe 'duck typing' do
+    
+    it "should respond normally to String methods" do
+      'test'.chars.respond_to?(:strip).should be_true
+      'test'.chars.respond_to?(:normalize).should be_true
+      'test'.chars.respond_to?(:normalize!).should be_true
+      'test'.chars.respond_to?(:a_method_that_doesnt_exist).should be_false
+    end
+    
+  end 
+  
+end

data/spec/spec.opts

@@ -0,0 +1,6 @@
+--colour
+--format
+progress
+--loadby
+mtime
+--reverse

data/spec/spec_helper.rb

@@ -0,0 +1,34 @@
+begin
+  require 'spec'
+rescue LoadError
+  require 'rubygems'
+  gem 'rspec'
+  require 'spec'
+end
+
+require File.dirname(__FILE__) + "/../lib/multibyte"
+
+module UnicodeHelper
+  
+  def string_format_examples
+    {
+      :utf8 => "Abcd Блå ffi блa  埋",
+      :ascii => "asci ias c iia s",
+      :bytes => "\270\236\010\210\245"
+    }
+  end
+  
+  def with_kcode(kcode)
+    old_kcode, $KCODE = $KCODE, kcode
+    begin
+      yield
+    ensure
+      $KCODE = old_kcode
+    end
+  end
+  
+end
+
+Spec::Runner.configure do |config|
+  include UnicodeHelper
+end

data/tasks/deployment.rake

@@ -0,0 +1,34 @@
+desc 'Release the website and new gem version'
+task :deploy => [:check_version, :website, :release] do
+  puts "Remember to create SVN tag:"
+  puts "svn copy svn+ssh://#{rubyforge_username}@rubyforge.org/var/svn/#{PATH}/trunk " +
+    "svn+ssh://#{rubyforge_username}@rubyforge.org/var/svn/#{PATH}/tags/REL-#{VERS} "
+  puts "Suggested comment:"
+  puts "Tagging release #{CHANGES}"
+end
+
+desc 'Runs tasks website_generate and install_gem as a local deployment of the gem'
+task :local_deploy => [:website_generate, :install_gem]
+
+task :check_version do
+  unless ENV['VERSION']
+    puts 'Must pass a VERSION=x.y.z release version'
+    exit
+  end
+  unless ENV['VERSION'] == VERS
+    puts "Please update your version.rb to match the release version, currently #{VERS}"
+    exit
+  end
+end
+
+desc 'Install the package as a gem, without generating documentation(ri/rdoc)'
+task :install_gem_no_doc => [:clean, :package] do
+  sh "#{'sudo ' unless Hoe::WINDOZE }gem install pkg/*.gem --no-rdoc --no-ri"
+end
+
+namespace :manifest do
+  desc 'Recreate Manifest.txt to include ALL files'
+  task :refresh do
+    `rake check_manifest | patch -p0 > Manifest.txt`
+  end
+end

data/tasks/environment.rake

@@ -0,0 +1,7 @@
+task :ruby_env do
+  RUBY_APP = if RUBY_PLATFORM =~ /java/
+    "jruby"
+  else
+    "ruby"
+  end unless defined? RUBY_APP
+end

data/tasks/rspec.rake

@@ -0,0 +1,21 @@
+begin
+  require 'spec'
+rescue LoadError
+  require 'rubygems'
+  require 'spec'
+end
+begin
+  require 'spec/rake/spectask'
+rescue LoadError
+  puts <<-EOS
+To use rspec for testing you must install rspec gem:
+    gem install rspec
+EOS
+  exit(0)
+end
+
+desc "Run the specs under spec/models"
+Spec::Rake::SpecTask.new do |t|
+  t.spec_opts = ['--options', "spec/spec.opts"]
+  t.spec_files = FileList['spec/*_spec.rb']
+end

data/tasks/website.rake

@@ -0,0 +1,17 @@
+desc 'Generate website files'
+task :website_generate => :ruby_env do
+  (Dir['website/**/*.txt'] - Dir['website/version*.txt']).each do |txt|
+    sh %{ #{RUBY_APP} script/txt2html #{txt} > #{txt.gsub(/txt$/,'html')} }
+  end
+end
+
+desc 'Upload website files to rubyforge'
+task :website_upload do
+  host = "#{rubyforge_username}@rubyforge.org"
+  remote_dir = "/var/www/gforge-projects/#{PATH}/"
+  local_dir = 'website'
+  sh %{rsync -aCv #{local_dir}/ #{host}:#{remote_dir}}
+end
+
+desc 'Generate and upload website files'
+task :website => [:website_generate, :website_upload, :publish_docs]

data/website/index.txt

@@ -0,0 +1,39 @@
+h1. multibyte
+
+h1. → 'multibyte'
+
+
+h2. What
+
+
+h2. Installing
+
+<pre syntax="ruby">sudo gem install multibyte</pre>
+
+h2. The basics
+
+
+h2. Demonstration of usage
+
+
+
+h2. Forum
+
+"http://groups.google.com/group/multibyte":http://groups.google.com/group/multibyte
+
+TODO - create Google Group - multibyte
+
+h2. How to submit patches
+
+Read the "8 steps for fixing other people's code":http://drnicwilliams.com/2007/06/01/8-steps-for-fixing-other-peoples-code/ and for section "8b: Submit patch to Google Groups":http://drnicwilliams.com/2007/06/01/8-steps-for-fixing-other-peoples-code/#8b-google-groups, use the Google Group above.
+
+The trunk repository is <code>svn://rubyforge.org/var/svn/multibyte/trunk</code> for anonymous access.
+
+h2. License
+
+This code is free to use under the terms of the MIT license. 
+
+h2. Contact
+
+Comments are welcome. Send an email to "FIXME full name":mailto:FIXME email via the "forum":http://groups.google.com/group/multibyte
+

metadata

@@ -0,0 +1,86 @@
+--- !ruby/object:Gem::Specification 
+name: mattetti-multibyte
+version: !ruby/object:Gem::Version 
+  version: 0.0.1
+platform: ruby
+authors: 
+- Matt Aimonetti
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2008-05-28 00:00:00 -07:00
+default_executable: 
+dependencies: []
+
+description: Multibyte support for Ruby
+email: 
+- mattaimonetti@gmail.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: 
+- History.txt
+- License.txt
+- Manifest.txt
+- README.txt
+- website/index.txt
+files: 
+- History.txt
+- License.txt
+- Manifest.txt
+- README.txt
+- Rakefile
+- config/hoe.rb
+- config/requirements.rb
+- lib/multibyte.rb
+- lib/multibyte/chars.rb
+- lib/multibyte/generators/generate_tables.rb
+- lib/multibyte/handlers/passthru_handler.rb
+- lib/multibyte/handlers/utf8_handler.rb
+- lib/multibyte/handlers/utf8_handler_proc.rb
+- lib/multibyte/version.rb
+- lib/unicode.rb
+- log/debug.log
+- script/destroy
+- script/generate
+- script/txt2html
+- setup.rb
+- spec/multibyte_spec.rb
+- spec/spec.opts
+- spec/spec_helper.rb
+- tasks/deployment.rake
+- tasks/environment.rake
+- tasks/rspec.rake
+- tasks/website.rake
+- website/index.txt
+has_rdoc: true
+homepage: http://multibyte.rubyforge.org
+post_install_message: 
+rdoc_options: 
+- --main
+- README.txt
+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: 
+requirements: []
+
+rubyforge_project: multibyte
+rubygems_version: 1.2.0
+signing_key: 
+specification_version: 2
+summary: Multibyte support for Ruby
+test_files: []
+