activesupport 2.1.2 → 2.2.2

data/lib/active_support/clean_logger.rb

@@ -1,127 +0,0 @@
-require 'logger'
-require 'active_support/core_ext/class/attribute_accessors'
-
-# Extensions to the built in Ruby logger.
-#
-# If you want to use the default log formatter as defined in the Ruby core, then you 
-# will need to set the formatter for the logger as in:
-#
-#   logger.formatter = Formatter.new
-#
-# You can then specify the datetime format, for example:
-#
-#   logger.datetime_format = "%Y-%m-%d"
-#
-# Note: This logger is deprecated in favor of ActiveSupport::BufferedLogger
-class Logger
-  # Set to false to disable the silencer
-  cattr_accessor :silencer
-  self.silencer = true
-  
-  # Silences the logger for the duration of the block.
-  def silence(temporary_level = Logger::ERROR)
-    if silencer
-      begin
-        old_logger_level, self.level = level, temporary_level
-        yield self
-      ensure
-        self.level = old_logger_level
-      end
-    else
-      yield self
-    end
-  end
-  
-  alias :old_datetime_format= :datetime_format=
-  # Logging date-time format (string passed to +strftime+). Ignored if the formatter
-  # does not respond to datetime_format=.
-  def datetime_format=(datetime_format)
-    formatter.datetime_format = datetime_format if formatter.respond_to?(:datetime_format=)
-  end
-  
-  alias :old_datetime_format :datetime_format
-  # Get the logging datetime format. Returns nil if the formatter does not support
-  # datetime formatting.
-  def datetime_format
-    formatter.datetime_format if formatter.respond_to?(:datetime_format)
-  end
-  
-  alias :old_formatter :formatter if method_defined?(:formatter)
-  # Get the current formatter. The default formatter is a SimpleFormatter which only
-  # displays the log message
-  def formatter
-    @formatter ||= SimpleFormatter.new
-  end
-
-  unless const_defined? :Formatter
-    class Formatter
-      Format = "%s, [%s#%d] %5s -- %s: %s\n"
-
-      attr_accessor :datetime_format
-
-      def initialize
-        @datetime_format = nil
-      end
-
-      def call(severity, time, progname, msg)
-        Format % [severity[0..0], format_datetime(time), $$, severity, progname,
-        msg2str(msg)]
-      end
-
-      private
-        def format_datetime(time)
-          if @datetime_format.nil?
-            time.strftime("%Y-%m-%dT%H:%M:%S.") << "%06d " % time.usec
-          else
-            time.strftime(@datetime_format)
-          end
-        end
-
-        def msg2str(msg)
-          case msg
-          when ::String
-            msg
-          when ::Exception
-            "#{ msg.message } (#{ msg.class })\n" <<
-            (msg.backtrace || []).join("\n")
-          else
-            msg.inspect
-          end
-        end
-    end
-  end
-  
-  # Simple formatter which only displays the message.
-  class SimpleFormatter < Logger::Formatter
-    # This method is invoked when a log event occurs
-    def call(severity, timestamp, progname, msg)
-      "#{String === msg ? msg : msg.inspect}\n"
-    end
-  end
-
-  private
-    alias old_format_message format_message
-
-    # Ruby 1.8.3 transposed the msg and progname arguments to format_message.
-    # We can't test RUBY_VERSION because some distributions don't keep Ruby
-    # and its standard library in sync, leading to installations of Ruby 1.8.2
-    # with Logger from 1.8.3 and vice versa.
-    if method_defined?(:formatter=)
-      def format_message(severity, timestamp, progname, msg)
-        formatter.call(severity, timestamp, progname, msg)
-      end
-    else
-      def format_message(severity, timestamp, msg, progname)
-        formatter.call(severity, timestamp, progname, msg)
-      end
-      
-      attr_writer :formatter
-      public :formatter=
-
-      alias old_format_datetime format_datetime
-      def format_datetime(datetime) datetime end
-
-      alias old_msg2str msg2str
-      def msg2str(msg) msg end
-    end
-end

data/lib/active_support/core_ext/string/unicode.rb

@@ -1,66 +0,0 @@
-module ActiveSupport #:nodoc:
-  module CoreExtensions #:nodoc:
-    module String #:nodoc:
-      # Define methods for handling unicode data.
-      module Unicode
-        def self.append_features(base)
-          if '1.8.7 and later'.respond_to?(:chars)
-            base.class_eval { remove_method :chars }
-          end
-          super
-        end
-
-        unless '1.9'.respond_to?(:force_encoding)
-          # +chars+ is a Unicode safe proxy for string methods. It creates and returns an instance of the
-          # ActiveSupport::Multibyte::Chars class which encapsulates the original string. A Unicode safe version of all
-          # the String methods are defined on this proxy class. Undefined methods are forwarded to String, so all of the
-          # string overrides can also be called through the +chars+ proxy.
-          #
-          #   name = 'Claus Müller'
-          #   name.reverse              # => "rell??M sualC"
-          #   name.length               # => 13
-          #
-          #   name.chars.reverse.to_s   # => "rellüM sualC"
-          #   name.chars.length         # => 12
-          #   
-          #
-          # All the methods on the chars proxy which normally return a string will return a Chars object. This allows
-          # method chaining on the result of any of these methods.
-          #
-          #   name.chars.reverse.length # => 12
-          #
-          # The Char object tries to be as interchangeable with String objects as possible: sorting and comparing between
-          # String and Char work like expected. The bang! methods change the internal string representation in the Chars
-          # object. Interoperability problems can be resolved easily with a +to_s+ call.
-          #
-          # For more information about the methods defined on the Chars proxy see ActiveSupport::Multibyte::Chars and
-          # ActiveSupport::Multibyte::Handlers::UTF8Handler.
-          def chars
-            ActiveSupport::Multibyte::Chars.new(self)
-          end
-
-          # Returns true if the string has UTF-8 semantics (a String used for purely byte resources is unlikely to have
-          # them), returns false otherwise.
-          def is_utf8?
-            ActiveSupport::Multibyte::Handlers::UTF8Handler.consumes?(self)
-          end
-        else
-          def chars #:nodoc:
-            self
-          end
-
-          def is_utf8? #:nodoc:
-            case encoding
-              when Encoding::UTF_8
-                valid_encoding?
-              when Encoding::ASCII_8BIT
-                dup.force_encoding('UTF-8').valid_encoding?
-              else
-                false
-            end
-          end
-        end
-      end
-    end
-  end
-end

data/lib/active_support/core_ext/test.rb

@@ -1 +0,0 @@
-require 'active_support/core_ext/test/unit/assertions'

data/lib/active_support/multibyte/generators/generate_tables.rb

@@ -1,149 +0,0 @@
-#!/usr/bin/env ruby
-begin
-  require File.dirname(__FILE__) + '/../../../active_support'
-rescue IOError
-end
-require 'open-uri'
-require 'tmpdir'
-
-module ActiveSupport::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/#{ActiveSupport::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 = ActiveSupport::Multibyte::Handlers::UnicodeDatabase.filename
-  generator = ActiveSupport::Multibyte::Handlers::UnicodeTableGenerator.new
-  generator.parse
-  print "Writing to: #{filename}"
-  generator.dump_to filename
-  puts " (#{File.size(filename)} bytes)"
-end

data/lib/active_support/multibyte/handlers/passthru_handler.rb

@@ -1,9 +0,0 @@
-# Chars uses this handler when $KCODE is not set to 'UTF8'. Because this handler doesn't define any methods all call
-# will be forwarded to String.
-class ActiveSupport::Multibyte::Handlers::PassthruHandler #:nodoc:
-  
-  # Return the original byteoffset
-  def self.translate_offset(string, byte_offset) #:nodoc:
-    byte_offset
-  end
-end

data/lib/active_support/multibyte/handlers/utf8_handler.rb

@@ -1,564 +0,0 @@
-# Contains all the handlers and helper classes
-module ActiveSupport::Multibyte::Handlers #:nodoc:
-  class EncodingError < ArgumentError #:nodoc:
-  end
-  
-  class Codepoint #:nodoc:
-    attr_accessor :code, :combining_class, :decomp_type, :decomp_mapping, :uppercase_mapping, :lowercase_mapping
-  end
-  
-  class UnicodeDatabase #:nodoc:
-    attr_writer :codepoints, :composition_exclusion, :composition_map, :boundary, :cp1252
-    
-    # self-expiring methods that lazily load the Unicode database and then return the value.
-    [:codepoints, :composition_exclusion, :composition_map, :boundary, :cp1252].each do |attr_name|
-      class_eval(<<-EOS, __FILE__, __LINE__)
-        def #{attr_name}
-          load
-          @#{attr_name}
-        end
-      EOS
-    end
-    
-    # Shortcut to ucd.codepoints[]
-    def [](index); codepoints[index]; end
-    
-    # Returns the directory in which the data files are stored
-    def self.dirname
-      File.dirname(__FILE__) + '/../../values/'
-    end
-    
-    # Returns the filename for the data file for this version
-    def self.filename
-      File.expand_path File.join(dirname, "unicode_tables.dat")
-    end
-    
-    # Loads the unicode database and returns all the internal objects of UnicodeDatabase
-    # Once the values have been loaded, define attr_reader methods for the instance variables.
-    def load
-      begin
-        @codepoints, @composition_exclusion, @composition_map, @boundary, @cp1252 = File.open(self.class.filename, 'rb') { |f| Marshal.load f.read }
-      rescue Exception => e
-          raise IOError.new("Couldn't load the unicode tables for UTF8Handler (#{e.message}), handler is unusable")
-      end
-      @codepoints ||= Hash.new(Codepoint.new)
-      @composition_exclusion ||= []
-      @composition_map ||= {}
-      @boundary ||= {}
-      @cp1252 ||= {}
-      
-      # Redefine the === method so we can write shorter rules for grapheme cluster breaks
-      @boundary.each do |k,_|
-        @boundary[k].instance_eval do
-          def ===(other)
-            detect { |i| i === other } ? true : false
-          end
-        end if @boundary[k].kind_of?(Array)
-      end
-
-      # define attr_reader methods for the instance variables
-      class << self
-        attr_reader :codepoints, :composition_exclusion, :composition_map, :boundary, :cp1252
-      end
-    end
-  end
-  
-  # UTF8Handler implements Unicode aware operations for strings, these operations will be used by the Chars
-  # proxy when $KCODE is set to 'UTF8'.
-  class UTF8Handler
-    # Hangul character boundaries and properties
-    HANGUL_SBASE = 0xAC00
-    HANGUL_LBASE = 0x1100
-    HANGUL_VBASE = 0x1161
-    HANGUL_TBASE = 0x11A7
-    HANGUL_LCOUNT = 19
-    HANGUL_VCOUNT = 21
-    HANGUL_TCOUNT = 28
-    HANGUL_NCOUNT = HANGUL_VCOUNT * HANGUL_TCOUNT
-    HANGUL_SCOUNT = 11172
-    HANGUL_SLAST = HANGUL_SBASE + HANGUL_SCOUNT
-    HANGUL_JAMO_FIRST = 0x1100
-    HANGUL_JAMO_LAST = 0x11FF
-    
-    # All the unicode whitespace
-    UNICODE_WHITESPACE = [
-      (0x0009..0x000D).to_a,  # White_Space # Cc   [5] <control-0009>..<control-000D>
-      0x0020,          # White_Space # Zs       SPACE
-      0x0085,          # White_Space # Cc       <control-0085>
-      0x00A0,          # White_Space # Zs       NO-BREAK SPACE
-      0x1680,          # White_Space # Zs       OGHAM SPACE MARK
-      0x180E,          # White_Space # Zs       MONGOLIAN VOWEL SEPARATOR
-      (0x2000..0x200A).to_a, # White_Space # Zs  [11] EN QUAD..HAIR SPACE
-      0x2028,          # White_Space # Zl       LINE SEPARATOR
-      0x2029,          # White_Space # Zp       PARAGRAPH SEPARATOR
-      0x202F,          # White_Space # Zs       NARROW NO-BREAK SPACE
-      0x205F,          # White_Space # Zs       MEDIUM MATHEMATICAL SPACE
-      0x3000,          # White_Space # Zs       IDEOGRAPHIC SPACE
-    ].flatten.freeze
-    
-    # BOM (byte order mark) can also be seen as whitespace, it's a non-rendering character used to distinguish
-    # between little and big endian. This is not an issue in utf-8, so it must be ignored.
-    UNICODE_LEADERS_AND_TRAILERS = UNICODE_WHITESPACE + [65279] # ZERO-WIDTH NO-BREAK SPACE aka BOM
-    
-    # Borrowed from the Kconv library by Shinji KONO - (also as seen on the W3C site)
-     UTF8_PAT = /\A(?:
-                   [\x00-\x7f]                                     |
-                   [\xc2-\xdf] [\x80-\xbf]                         |
-                   \xe0        [\xa0-\xbf] [\x80-\xbf]             |
-                   [\xe1-\xef] [\x80-\xbf] [\x80-\xbf]             |
-                   \xf0        [\x90-\xbf] [\x80-\xbf] [\x80-\xbf] |
-                   [\xf1-\xf3] [\x80-\xbf] [\x80-\xbf] [\x80-\xbf] |
-                   \xf4        [\x80-\x8f] [\x80-\xbf] [\x80-\xbf]
-                  )*\z/xn
-    
-    # Returns a regular expression pattern that matches the passed Unicode codepoints
-    def self.codepoints_to_pattern(array_of_codepoints) #:nodoc:
-      array_of_codepoints.collect{ |e| [e].pack 'U*' }.join('|') 
-    end
-    UNICODE_TRAILERS_PAT = /(#{codepoints_to_pattern(UNICODE_LEADERS_AND_TRAILERS)})+\Z/
-    UNICODE_LEADERS_PAT = /\A(#{codepoints_to_pattern(UNICODE_LEADERS_AND_TRAILERS)})+/
-    
-    class << self
-      
-      # ///
-      # /// BEGIN String method overrides
-      # ///
-      
-      # Inserts the passed string at specified codepoint offsets
-      def insert(str, offset, fragment)
-        str.replace(
-          u_unpack(str).insert(
-            offset,
-            u_unpack(fragment)
-          ).flatten.pack('U*')
-        )
-      end
-      
-      # Returns the position of the passed argument in the string, counting in codepoints
-      def index(str, *args)
-        bidx = str.index(*args)
-        bidx ? (u_unpack(str.slice(0...bidx)).size) : nil
-      end
-      
-      # Works just like the indexed replace method on string, except instead of byte offsets you specify
-      # character offsets.
-      #
-      # Example:
-      #
-      #   s = "Müller"
-      #   s.chars[2] = "e" # Replace character with offset 2
-      #   s # => "Müeler"
-      #
-      #   s = "Müller"
-      #   s.chars[1, 2] = "ö" # Replace 2 characters at character offset 1
-      #   s # => "Möler"
-      def []=(str, *args)
-        replace_by = args.pop
-        # Indexed replace with regular expressions already works
-        return str[*args] = replace_by if args.first.is_a?(Regexp)
-        result = u_unpack(str)
-        if args[0].is_a?(Fixnum)
-          raise IndexError, "index #{args[0]} out of string" if args[0] >= result.length
-          min = args[0]
-          max = args[1].nil? ? min : (min + args[1] - 1)
-          range = Range.new(min, max)
-          replace_by = [replace_by].pack('U') if replace_by.is_a?(Fixnum)
-        elsif args.first.is_a?(Range)
-          raise RangeError, "#{args[0]} out of range" if args[0].min >= result.length
-          range = args[0]
-        else
-          needle = args[0].to_s
-          min = index(str, needle)
-          max = min + length(needle) - 1
-          range = Range.new(min, max)
-        end
-        result[range] = u_unpack(replace_by)
-        str.replace(result.pack('U*'))
-      end
-      
-      # Works just like String#rjust, only integer specifies characters instead of bytes.
-      #
-      # Example:
-      #
-      #   "¾ cup".chars.rjust(8).to_s
-      #   # => "   ¾ cup"
-      #
-      #   "¾ cup".chars.rjust(8, " ").to_s # Use non-breaking whitespace
-      #   # => "   ¾ cup"
-      def rjust(str, integer, padstr=' ')
-        justify(str, integer, :right, padstr)
-      end
-      
-      # Works just like String#ljust, only integer specifies characters instead of bytes.
-      #
-      # Example:
-      #
-      #   "¾ cup".chars.rjust(8).to_s
-      #   # => "¾ cup   "
-      #
-      #   "¾ cup".chars.rjust(8, " ").to_s # Use non-breaking whitespace
-      #   # => "¾ cup   "
-      def ljust(str, integer, padstr=' ')
-        justify(str, integer, :left, padstr)
-      end
-      
-      # Works just like String#center, only integer specifies characters instead of bytes.
-      #
-      # Example:
-      #
-      #   "¾ cup".chars.center(8).to_s
-      #   # => " ¾ cup  "
-      #
-      #   "¾ cup".chars.center(8, " ").to_s # Use non-breaking whitespace
-      #   # => " ¾ cup  "
-      def center(str, integer, padstr=' ')
-        justify(str, integer, :center, padstr)
-      end
-      
-      # Does Unicode-aware rstrip
-      def rstrip(str)
-        str.gsub(UNICODE_TRAILERS_PAT, '')
-      end
-      
-      # Does Unicode-aware lstrip
-      def lstrip(str)
-        str.gsub(UNICODE_LEADERS_PAT, '')
-      end
-      
-      # Removed leading and trailing whitespace
-      def strip(str)
-        str.gsub(UNICODE_LEADERS_PAT, '').gsub(UNICODE_TRAILERS_PAT, '')
-      end
-      
-      # Returns the number of codepoints in the string
-      def size(str)
-        u_unpack(str).size
-      end
-      alias_method :length, :size
-      
-      # Reverses codepoints in the string.
-      def reverse(str)
-        u_unpack(str).reverse.pack('U*')
-      end
-      
-      # Implements Unicode-aware slice with codepoints. Slicing on one point returns the codepoints for that
-      # character.
-      def slice(str, *args)
-        if args.size > 2
-          raise ArgumentError, "wrong number of arguments (#{args.size} for 1)" # Do as if we were native
-        elsif (args.size == 2 && !(args.first.is_a?(Numeric) || args.first.is_a?(Regexp)))
-          raise TypeError, "cannot convert #{args.first.class} into Integer" # Do as if we were native
-        elsif (args.size == 2 && !args[1].is_a?(Numeric))
-          raise TypeError, "cannot convert #{args[1].class} into Integer" # Do as if we were native
-        elsif args[0].kind_of? Range
-          cps = u_unpack(str).slice(*args)
-          cps.nil? ? nil : cps.pack('U*')
-        elsif args[0].kind_of? Regexp
-          str.slice(*args)
-        elsif args.size == 1 && args[0].kind_of?(Numeric)
-          u_unpack(str)[args[0]]
-        else
-          u_unpack(str).slice(*args).pack('U*')
-        end
-      end
-      alias_method :[], :slice
-      
-      # Convert characters in the string to uppercase
-      def upcase(str); to_case :uppercase_mapping, str; end
-      
-      # Convert characters in the string to lowercase
-      def downcase(str); to_case :lowercase_mapping, str; end
-      
-      # Returns a copy of +str+ with the first character converted to uppercase and the remainder to lowercase
-      def capitalize(str)
-        upcase(slice(str, 0..0)) + downcase(slice(str, 1..-1) || '')
-      end
-      
-      # ///
-      # /// Extra String methods for unicode operations
-      # ///
-      
-      # Returns the KC normalization of the string by default. NFKC is considered the best normalization form for
-      # passing strings to databases and validations.
-      #
-      # * <tt>str</tt> - The string to perform normalization on.
-      # * <tt>form</tt> - The form you want to normalize in. Should be one of the following:
-      #   <tt>:c</tt>, <tt>:kc</tt>, <tt>:d</tt>, or <tt>:kd</tt>. Default is
-      #   ActiveSupport::Multibyte::DEFAULT_NORMALIZATION_FORM.
-      def normalize(str, form=ActiveSupport::Multibyte::DEFAULT_NORMALIZATION_FORM)
-        # See http://www.unicode.org/reports/tr15, Table 1
-        codepoints = u_unpack(str)
-        case form
-          when :d
-            reorder_characters(decompose_codepoints(:canonical, codepoints))
-          when :c
-            compose_codepoints reorder_characters(decompose_codepoints(:canonical, codepoints))
-          when :kd
-            reorder_characters(decompose_codepoints(:compatability, codepoints))
-          when :kc
-            compose_codepoints reorder_characters(decompose_codepoints(:compatability, codepoints))
-          else
-            raise ArgumentError, "#{form} is not a valid normalization variant", caller
-        end.pack('U*')
-      end
-      
-      # Perform decomposition on the characters in the string
-      def decompose(str)
-        decompose_codepoints(:canonical, u_unpack(str)).pack('U*')
-      end
-      
-      # Perform composition on the characters in the string
-      def compose(str)
-        compose_codepoints u_unpack(str).pack('U*')
-      end
-      
-      # ///
-      # /// BEGIN Helper methods for unicode operation
-      # ///
-      
-      # Used to translate an offset from bytes to characters, for instance one received from a regular expression match
-      def translate_offset(str, byte_offset)
-        return nil if byte_offset.nil?
-        return 0 if str == ''
-        chunk = str[0..byte_offset]
-        begin
-          begin
-            chunk.unpack('U*').length - 1
-          rescue ArgumentError => e
-            chunk = str[0..(byte_offset+=1)]
-            # Stop retrying at the end of the string
-            raise e unless byte_offset < chunk.length 
-            # We damaged a character, retry
-            retry
-          end
-        # Catch the ArgumentError so we can throw our own
-        rescue ArgumentError 
-          raise EncodingError.new('malformed UTF-8 character')
-        end
-      end
-      
-      # Checks if the string is valid UTF8.
-      def consumes?(str)
-        # Unpack is a little bit faster than regular expressions
-        begin
-          str.unpack('U*')
-          true
-        rescue ArgumentError
-          false
-        end
-      end
-      
-      # Returns the number of grapheme clusters in the string. This method is very likely to be moved or renamed
-      # in future versions.
-      def g_length(str)
-        g_unpack(str).length
-      end
-      
-      # Replaces all the non-utf-8 bytes by their iso-8859-1 or cp1252 equivalent resulting in a valid utf-8 string
-      def tidy_bytes(str)
-        str.split(//u).map do |c|
-          if !UTF8_PAT.match(c)
-            n = c.unpack('C')[0]
-            n < 128 ? n.chr :
-            n < 160 ? [UCD.cp1252[n] || n].pack('U') :
-            n < 192 ? "\xC2" + n.chr : "\xC3" + (n-64).chr
-          else
-            c
-          end
-        end.join
-      end
-      
-      protected
-      
-      # Detect whether the codepoint is in a certain character class. Primarily used by the
-      # grapheme cluster support.
-      def in_char_class?(codepoint, classes)
-        classes.detect { |c| UCD.boundary[c] === codepoint } ? true : false
-      end
-      
-      # Unpack the string at codepoints boundaries
-      def u_unpack(str)
-        begin
-          str.unpack 'U*'
-        rescue ArgumentError
-          raise EncodingError.new('malformed UTF-8 character')
-        end
-      end
-      
-      # Unpack the string at grapheme boundaries instead of codepoint boundaries
-      def g_unpack(str)
-        codepoints = u_unpack(str)
-        unpacked = []
-        pos = 0
-        marker = 0
-        eoc = codepoints.length
-        while(pos < eoc)
-          pos += 1
-          previous = codepoints[pos-1]
-          current = codepoints[pos]
-          if (
-              # CR X LF
-              one = ( previous == UCD.boundary[:cr] and current == UCD.boundary[:lf] ) or
-              # L X (L|V|LV|LVT)
-              two = ( UCD.boundary[:l] === previous and in_char_class?(current, [:l,:v,:lv,:lvt]) ) or
-              # (LV|V) X (V|T)
-              three = ( in_char_class?(previous, [:lv,:v]) and in_char_class?(current, [:v,:t]) ) or
-              # (LVT|T) X (T)
-              four = ( in_char_class?(previous, [:lvt,:t]) and UCD.boundary[:t] === current ) or
-              # X Extend
-              five = (UCD.boundary[:extend] === current)
-            )
-          else
-            unpacked << codepoints[marker..pos-1]
-            marker = pos
-          end
-        end 
-        unpacked
-      end
-      
-      # Reverse operation of g_unpack
-      def g_pack(unpacked)
-        unpacked.flatten
-      end
-      
-      # Justifies a string in a certain way. Valid values for <tt>way</tt> are <tt>:right</tt>, <tt>:left</tt> and
-      # <tt>:center</tt>. Is primarily used as a helper method by <tt>rjust</tt>, <tt>ljust</tt> and <tt>center</tt>.
-      def justify(str, integer, way, padstr=' ')
-        raise ArgumentError, "zero width padding" if padstr.length == 0
-        padsize = integer - size(str)
-        padsize = padsize > 0 ? padsize : 0
-        case way
-        when :right
-          str.dup.insert(0, padding(padsize, padstr))
-        when :left
-          str.dup.insert(-1, padding(padsize, padstr))
-        when :center
-          lpad = padding((padsize / 2.0).floor, padstr)
-          rpad = padding((padsize / 2.0).ceil, padstr)
-          str.dup.insert(0, lpad).insert(-1, rpad)
-        end
-      end
-      
-      # Generates a padding string of a certain size.
-      def padding(padsize, padstr=' ')
-        if padsize != 0
-          slice(padstr * ((padsize / size(padstr)) + 1), 0, padsize)
-        else
-          ''
-        end
-      end
-      
-      # Convert characters to a different case
-      def to_case(way, str)
-        u_unpack(str).map do |codepoint|
-          cp = UCD[codepoint] 
-          unless cp.nil?
-            ncp = cp.send(way)
-            ncp > 0 ? ncp : codepoint
-          else
-            codepoint
-          end
-        end.pack('U*')
-      end
-      
-      # Re-order codepoints so the string becomes canonical
-      def reorder_characters(codepoints)
-        length = codepoints.length- 1
-        pos = 0
-        while pos < length do
-          cp1, cp2 = UCD[codepoints[pos]], UCD[codepoints[pos+1]]
-          if (cp1.combining_class > cp2.combining_class) && (cp2.combining_class > 0)
-            codepoints[pos..pos+1] = cp2.code, cp1.code
-            pos += (pos > 0 ? -1 : 1)
-          else
-            pos += 1
-          end
-        end
-        codepoints
-      end
-      
-      # Decompose composed characters to the decomposed form
-      def decompose_codepoints(type, codepoints)
-        codepoints.inject([]) do |decomposed, cp|
-          # if it's a hangul syllable starter character
-          if HANGUL_SBASE <= cp and cp < HANGUL_SLAST
-            sindex = cp - HANGUL_SBASE
-            ncp = [] # new codepoints
-            ncp << HANGUL_LBASE + sindex / HANGUL_NCOUNT
-            ncp << HANGUL_VBASE + (sindex % HANGUL_NCOUNT) / HANGUL_TCOUNT
-            tindex = sindex % HANGUL_TCOUNT
-            ncp << (HANGUL_TBASE + tindex) unless tindex == 0
-            decomposed.concat ncp
-          # if the codepoint is decomposable in with the current decomposition type
-          elsif (ncp = UCD[cp].decomp_mapping) and (!UCD[cp].decomp_type || type == :compatability)
-            decomposed.concat decompose_codepoints(type, ncp.dup)
-          else
-            decomposed << cp
-          end
-        end
-      end
-      
-      # Compose decomposed characters to the composed form
-      def compose_codepoints(codepoints)
-        pos = 0
-        eoa = codepoints.length - 1
-        starter_pos = 0
-        starter_char = codepoints[0]
-        previous_combining_class = -1
-        while pos < eoa
-          pos += 1
-          lindex = starter_char - HANGUL_LBASE
-          # -- Hangul
-          if 0 <= lindex and lindex < HANGUL_LCOUNT
-            vindex = codepoints[starter_pos+1] - HANGUL_VBASE rescue vindex = -1
-            if 0 <= vindex and vindex < HANGUL_VCOUNT
-              tindex = codepoints[starter_pos+2] - HANGUL_TBASE rescue tindex = -1
-              if 0 <= tindex and tindex < HANGUL_TCOUNT
-                j = starter_pos + 2
-                eoa -= 2
-              else
-                tindex = 0
-                j = starter_pos + 1
-                eoa -= 1
-              end
-              codepoints[starter_pos..j] = (lindex * HANGUL_VCOUNT + vindex) * HANGUL_TCOUNT + tindex + HANGUL_SBASE
-            end
-            starter_pos += 1
-            starter_char = codepoints[starter_pos]
-          # -- Other characters
-          else
-            current_char = codepoints[pos]
-            current = UCD[current_char]
-            if current.combining_class > previous_combining_class
-              if ref = UCD.composition_map[starter_char]
-                composition = ref[current_char]
-              else
-                composition = nil
-              end
-              unless composition.nil?
-                codepoints[starter_pos] = composition
-                starter_char = composition
-                codepoints.delete_at pos
-                eoa -= 1
-                pos -= 1
-                previous_combining_class = -1
-              else
-                previous_combining_class = current.combining_class
-              end
-            else
-              previous_combining_class = current.combining_class
-            end
-            if current.combining_class == 0
-              starter_pos = pos
-              starter_char = codepoints[pos]
-            end
-          end
-        end
-        codepoints
-      end
-      
-      # UniCode Database
-      UCD = UnicodeDatabase.new
-    end
-  end
-end