mattetti-multibyte 0.0.1

data/History.txt

@@ -0,0 +1,4 @@
+== 0.0.1 2008-05-28
+
+* 1 major enhancement:
+  * Initial release

data/License.txt

@@ -0,0 +1,20 @@
+Copyright (c) 2005-2008 David Heinemeier Hansson
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/Manifest.txt

@@ -0,0 +1,28 @@
+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/unicode_tables.dat
+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

data/README.txt

@@ -0,0 +1,19 @@
+Multibyte
+==========
+
+Multibyte is extracted directly from Rails's ActiveSupport and offers Multibyte safety to Ruby. 
+
+Usage
+=====
+
+>> require 'multibyte'
+=> true
+>> "新通訊錄".chars[0..1]
+=> #<Multibyte::Chars:0x127e3d0 @string="新通">
+>> "新通訊錄".chars[0..1].to_s
+=> "新通"
+
+Installation:
+=============
+
+$ sudo gem install mattetti-multibyte --source=http://gems.github.com

data/Rakefile

@@ -0,0 +1,4 @@
+require 'config/requirements'
+require 'config/hoe' # setup Hoe + all gem configuration
+
+Dir['tasks/**/*.rake'].each { |rake| load rake }

data/config/hoe.rb

@@ -0,0 +1,70 @@
+require 'multibyte/version'
+
+AUTHOR = 'FIXME full name'  # can also be an array of Authors
+EMAIL = "FIXME email"
+DESCRIPTION = "description of gem"
+GEM_NAME = 'multibyte' # what ppl will type to install your gem
+RUBYFORGE_PROJECT = 'multibyte' # The unix name for your project
+HOMEPATH = "http://#{RUBYFORGE_PROJECT}.rubyforge.org"
+DOWNLOAD_PATH = "http://rubyforge.org/projects/#{RUBYFORGE_PROJECT}"
+
+@config_file = "~/.rubyforge/user-config.yml"
+@config = nil
+RUBYFORGE_USERNAME = "unknown"
+def rubyforge_username
+  unless @config
+    begin
+      @config = YAML.load(File.read(File.expand_path(@config_file)))
+    rescue
+      puts <<-EOS
+ERROR: No rubyforge config file found: #{@config_file}
+Run 'rubyforge setup' to prepare your env for access to Rubyforge
+ - See http://newgem.rubyforge.org/rubyforge.html for more details
+      EOS
+      exit
+    end
+  end
+  RUBYFORGE_USERNAME.replace @config["username"]
+end
+
+
+REV = nil 
+# UNCOMMENT IF REQUIRED: 
+# REV = `svn info`.each {|line| if line =~ /^Revision:/ then k,v = line.split(': '); break v.chomp; else next; end} rescue nil
+VERS = Multibyte::VERSION::STRING + (REV ? ".#{REV}" : "")
+RDOC_OPTS = ['--quiet', '--title', 'multibyte documentation',
+    "--opname", "index.html",
+    "--line-numbers", 
+    "--main", "README",
+    "--inline-source"]
+
+class Hoe
+  def extra_deps 
+    @extra_deps.reject! { |x| Array(x).first == 'hoe' } 
+    @extra_deps
+  end 
+end
+
+# Generate all the Rake tasks
+# Run 'rake -T' to see list of generated tasks (from gem root directory)
+hoe = Hoe.new(GEM_NAME, VERS) do |p|
+  p.developer(AUTHOR, EMAIL)
+  p.description = DESCRIPTION
+  p.summary = DESCRIPTION
+  p.url = HOMEPATH
+  p.rubyforge_name = RUBYFORGE_PROJECT if RUBYFORGE_PROJECT
+  p.test_globs = ["test/**/test_*.rb"]
+  p.clean_globs |= ['**/.*.sw?', '*.gem', '.config', '**/.DS_Store']  #An array of file patterns to delete on clean.
+  
+  # == Optional
+  p.changes = p.paragraphs_of("History.txt", 0..1).join("\n\n")
+  #p.extra_deps = []     # An array of rubygem dependencies [name, version], e.g. [ ['active_support', '>= 1.3.1'] ]
+  
+  #p.spec_extras = {}    # A hash of extra values to set in the gemspec.
+  
+end
+
+CHANGES = hoe.paragraphs_of('History.txt', 0..1).join("\\n\\n")
+PATH    = (RUBYFORGE_PROJECT == GEM_NAME) ? RUBYFORGE_PROJECT : "#{RUBYFORGE_PROJECT}/#{GEM_NAME}"
+hoe.remote_rdoc_dir = File.join(PATH.gsub(/^#{RUBYFORGE_PROJECT}\/?/,''), 'rdoc')
+hoe.rsync_args = '-av --delete --ignore-errors'

data/config/requirements.rb

@@ -0,0 +1,17 @@
+require 'fileutils'
+include FileUtils
+
+require 'rubygems'
+%w[rake hoe newgem rubigen].each do |req_gem|
+  begin
+    require req_gem
+  rescue LoadError
+    puts "This Rakefile requires the '#{req_gem}' RubyGem."
+    puts "Installation: gem install #{req_gem} -y"
+    exit
+  end
+end
+
+$:.unshift(File.join(File.dirname(__FILE__), %w[.. lib]))
+
+require 'multibyte'

data/lib/multibyte.rb

@@ -0,0 +1,15 @@
+$:.unshift File.dirname(__FILE__)
+$KCODE = 'u'
+
+module Multibyte #:nodoc:
+  DEFAULT_NORMALIZATION_FORM = :kc
+  NORMALIZATIONS_FORMS = [:c, :kc, :d, :kd]
+  UNICODE_VERSION = '5.0.0'
+end
+
+require 'multibyte/chars'
+require 'unicode'
+
+class String #:nodoc:
+  include CoreExtensions::String::Unicode
+end

data/lib/multibyte/chars.rb

@@ -0,0 +1,135 @@
+require 'multibyte/handlers/utf8_handler'
+require 'multibyte/handlers/passthru_handler'
+
+# Encapsulates all the functionality related to the Chars proxy.
+module Multibyte #:nodoc:
+  # Chars enables you to work transparently with multibyte encodings in the Ruby String class without having extensive
+  # knowledge about the encoding. A Chars object accepts a string upon initialization and proxies String methods in an
+  # encoding safe manner. All the normal String methods are also implemented on the proxy.
+  #
+  # String methods are proxied through the Chars object, and can be accessed through the +chars+ method. Methods
+  # which would normally return a String object now return a Chars object so methods can be chained.
+  #
+  #   "The Perfect String  ".chars.downcase.strip.normalize # => "the perfect string"
+  #
+  # Chars objects are perfectly interchangeable with String objects as long as no explicit class checks are made.
+  # If certain methods do explicitly check the class, call +to_s+ before you pass chars objects to them.
+  #
+  #   bad.explicit_checking_method "T".chars.downcase.to_s
+  #
+  # The actual operations on the string are delegated to handlers. Theoretically handlers can be implemented for
+  # any encoding, but the default handler handles UTF-8. This handler is set during initialization, if you want to
+  # use you own handler, you can set it on the Chars class. Look at the UTF8Handler source for an example how to
+  # implement your own handler. If you your own handler to work on anything but UTF-8 you probably also
+  # want to override Chars#handler.
+  #
+  #   Multibyte::Chars.handler = MyHandler
+  #
+  # Note that a few methods are defined on Chars instead of the handler because they are defined on Object or Kernel
+  # and method_missing can't catch them.
+  class Chars
+    
+    attr_reader :string # The contained string
+    alias_method :to_s, :string
+    
+    include Comparable
+    
+    # The magic method to make String and Chars comparable
+    def to_str
+      # Using any other ways of overriding the String itself will lead you all the way from infinite loops to
+      # core dumps. Don't go there.
+      @string
+    end
+    
+    # Make duck-typing with String possible
+    def respond_to?(method)
+      super || @string.respond_to?(method) || handler.respond_to?(method) ||
+        (method.to_s =~ /(.*)!/ && handler.respond_to?($1)) || false
+    end
+    
+    # Create a new Chars instance.
+    def initialize(str)
+      @string = str.respond_to?(:string) ? str.string : str
+    end
+    
+    # Returns -1, 0 or +1 depending on whether the Chars object is to be sorted before, equal or after the
+    # object on the right side of the operation. It accepts any object that implements +to_s+. See String.<=>
+    # for more details.
+    def <=>(other); @string <=> other.to_s; end
+    
+    # Works just like String#split, with the exception that the items in the resulting list are Chars
+    # instances instead of String. This makes chaining methods easier.
+    def split(*args)
+      @string.split(*args).map { |i| i.chars }
+    end
+    
+    # Gsub works exactly the same as gsub on a normal string.
+    def gsub(*a, &b); @string.gsub(*a, &b).chars; end
+    
+    # Like String.=~ only it returns the character offset (in codepoints) instead of the byte offset.
+    def =~(other)
+      handler.translate_offset(@string, @string =~ other)
+    end
+    
+    # Try to forward all undefined methods to the handler, when a method is not defined on the handler, send it to
+    # the contained string. Method_missing is also responsible for making the bang! methods destructive.
+    def method_missing(m, *a, &b)
+      begin
+        # Simulate methods with a ! at the end because we can't touch the enclosed string from the handlers.
+        if m.to_s =~ /^(.*)\!$/ && handler.respond_to?($1)
+          result = handler.send($1, @string, *a, &b)
+          if result == @string
+            result = nil
+          else
+            @string.replace result
+          end
+        elsif handler.respond_to?(m)
+          result = handler.send(m, @string, *a, &b)
+        else
+          result = @string.send(m, *a, &b)
+        end
+      rescue Handlers::EncodingError
+        @string.replace handler.tidy_bytes(@string)
+        retry
+      end
+      
+      if result.kind_of?(String)
+        result.chars
+      else
+        result
+      end
+    end
+    
+    # Set the handler class for the Char objects.
+    def self.handler=(klass)
+      @@handler = klass
+    end
+
+    # Returns the proper handler for the contained string depending on $KCODE and the encoding of the string. This
+    # method is used internally to always redirect messages to the proper classes depending on the context.
+    def handler
+      if utf8_pragma?
+        @@handler
+      else
+        Multibyte::Handlers::PassthruHandler
+      end
+    end
+
+    private
+      
+      # +utf8_pragma+ checks if it can send this string to the handlers. It makes sure @string isn't nil and $KCODE is
+      # set to 'UTF8'.
+      def utf8_pragma?
+        !@string.nil? && ($KCODE == 'UTF8')
+      end
+  end
+end
+
+# When we can load the utf8proc library, override normalization with the faster methods
+begin
+  require 'utf8proc_native'
+  require 'multibyte/handlers/utf8_handler_proc'
+  Multibyte::Chars.handler = Multibyte::Handlers::UTF8HandlerProc
+rescue LoadError
+  Multibyte::Chars.handler = Multibyte::Handlers::UTF8Handler
+end

data/lib/multibyte/generators/generate_tables.rb

@@ -0,0 +1,148 @@
+#!/usr/bin/env ruby
+require 'open-uri'
+require 'tmpdir'
+
+$:.unshift(File.expand_path(File.dirname(__FILE__) + '/../../../lib'))
+require 'multibyte'
+
+module Multibyte::Handlers #:nodoc:
+  class UnicodeDatabase #:nodoc:
+    def self.load
+      [Hash.new(Codepoint.new),[],{},{}]
+    end
+  end
+  
+  class UnicodeTableGenerator #:nodoc:
+    BASE_URI = "http://www.unicode.org/Public/#{Multibyte::UNICODE_VERSION}/ucd/"
+    SOURCES = {
+      :codepoints => BASE_URI + 'UnicodeData.txt',
+      :composition_exclusion => BASE_URI + 'CompositionExclusions.txt',
+      :grapheme_break_property => BASE_URI + 'auxiliary/GraphemeBreakProperty.txt',
+      :cp1252 => 'http://unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1252.TXT'
+    }
+    
+    def initialize
+      @ucd = UnicodeDatabase.new
+      
+      default = Codepoint.new
+      default.combining_class = 0
+      default.uppercase_mapping = 0
+      default.lowercase_mapping = 0
+      @ucd.codepoints = Hash.new(default)
+      
+      @ucd.composition_exclusion = []
+      @ucd.composition_map = {}
+      @ucd.boundary = {}
+      @ucd.cp1252 = {}
+    end
+    
+    def parse_codepoints(line)
+      codepoint = Codepoint.new
+      raise "Could not parse input." unless line =~ /^
+        ([0-9A-F]+);        # code
+        ([^;]+);            # name
+        ([A-Z]+);           # general category
+        ([0-9]+);           # canonical combining class
+        ([A-Z]+);           # bidi class
+        (<([A-Z]*)>)?       # decomposition type
+        ((\ ?[0-9A-F]+)*);  # decompomposition mapping
+        ([0-9]*);           # decimal digit
+        ([0-9]*);           # digit
+        ([^;]*);            # numeric
+        ([YN]*);            # bidi mirrored
+        ([^;]*);            # unicode 1.0 name
+        ([^;]*);            # iso comment
+        ([0-9A-F]*);        # simple uppercase mapping
+        ([0-9A-F]*);        # simple lowercase mapping
+        ([0-9A-F]*)$/ix     # simple titlecase mapping
+      codepoint.code              = $1.hex
+      #codepoint.name              = $2
+      #codepoint.category          = $3
+      codepoint.combining_class   = Integer($4)
+      #codepoint.bidi_class        = $5
+      codepoint.decomp_type       = $7
+      codepoint.decomp_mapping    = ($8=='') ? nil : $8.split.collect { |element| element.hex }
+      #codepoint.bidi_mirrored     = ($13=='Y') ? true : false
+      codepoint.uppercase_mapping = ($16=='') ? 0 : $16.hex
+      codepoint.lowercase_mapping = ($17=='') ? 0 : $17.hex
+      #codepoint.titlecase_mapping = ($18=='') ? nil : $18.hex
+      @ucd.codepoints[codepoint.code] = codepoint
+    end
+
+    def parse_grapheme_break_property(line)
+      if line =~ /^([0-9A-F\.]+)\s*;\s*([\w]+)\s*#/
+        type = $2.downcase.intern
+        @ucd.boundary[type] ||= []
+        if $1.include? '..'
+          parts = $1.split '..'
+          @ucd.boundary[type] << (parts[0].hex..parts[1].hex)
+        else
+          @ucd.boundary[type] << $1.hex
+        end
+      end
+    end
+    
+    def parse_composition_exclusion(line)
+      if line =~ /^([0-9A-F]+)/i
+        @ucd.composition_exclusion << $1.hex
+      end
+    end
+    
+    def parse_cp1252(line)
+      if line =~ /^([0-9A-Fx]+)\s([0-9A-Fx]+)/i
+        @ucd.cp1252[$1.hex] = $2.hex
+      end
+    end
+    
+    def create_composition_map
+      @ucd.codepoints.each do |_, cp|
+        if !cp.nil? and cp.combining_class == 0 and cp.decomp_type.nil? and !cp.decomp_mapping.nil? and cp.decomp_mapping.length == 2 and @ucd[cp.decomp_mapping[0]].combining_class == 0 and !@ucd.composition_exclusion.include?(cp.code)
+          @ucd.composition_map[cp.decomp_mapping[0]] ||= {}
+          @ucd.composition_map[cp.decomp_mapping[0]][cp.decomp_mapping[1]] = cp.code
+        end
+      end
+    end
+
+    def normalize_boundary_map
+      @ucd.boundary.each do |k,v|
+        if [:lf, :cr].include? k
+          @ucd.boundary[k] = v[0]
+        end
+      end
+    end
+  
+    def parse
+      SOURCES.each do |type, url|
+        filename =  File.join(Dir.tmpdir, "#{url.split('/').last}")
+        unless File.exist?(filename)
+          $stderr.puts "Downloading #{url.split('/').last}"
+          File.open(filename, 'wb') do |target|
+            open(url) do |source|
+              source.each_line { |line| target.write line }
+            end
+          end
+        end
+        File.open(filename) do |file|
+          file.each_line { |line| send "parse_#{type}".intern, line }
+        end        
+      end
+      create_composition_map
+      normalize_boundary_map
+    end
+    
+    def dump_to(filename)
+      File.open(filename, 'wb') do |f|
+        f.write Marshal.dump([@ucd.codepoints, @ucd.composition_exclusion, @ucd.composition_map, @ucd.boundary, @ucd.cp1252])
+      end
+    end
+  end
+end
+
+if __FILE__ == $0
+  filename = Multibyte::Handlers::UnicodeDatabase.filename
+  generator = Multibyte::Handlers::UnicodeTableGenerator.new
+  generator.parse
+  print "Writing to: #{filename}"
+  generator.dump_to filename
+  puts " (#{File.size(filename)} bytes)"
+end