Ruby 1.8 Unicode Examples

gistfile1.rb

#!/usr/bin/env ruby
# encoding: UTF-8    # 2nd line, says file has Unicode data and names

#####################################################################
# Ruby 1.8 Unicode Demonstration 
#####################################################################

# Enable Unicode Support, or start with: ruby -Ku
$KCODE = "UTF-8"

puts 123 # => 

require 'jcode'
require "iconv"
require 'rubygems'
require 'unicode'
require 'rchardet'


FR = "Résumé"
EN = "Hello world"
CN = "你好世界"
JP = "こんにちは、世界"
AR = "مرحبا العالم"
GR = "Γεια σας κόσμο"
HE = "שלום עולם"
RU = "привет мир"
VN = "Xin chào thế giới"
KO = "안녕하세요 세계"


puts "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Characters"
s = FR
puts s               # => 
puts s.length        # => 
puts s.jsize
puts s.chars.map.inspect   # => 
puts s.upcase

puts "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Regex"
puts s.match(/^\w+/)    # => 
puts s.match(/^\w+/u)   # => 


puts "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ICONV"

def convert_encoding(str, from, to='UTF-8')
  # Iconv::iconv(to, from, *strs)
  Iconv.conv(to, from, str)   

rescue Iconv::InvalidEncoding  =>e
rescue Iconv::InvalidCharacter =>e
rescue Iconv::IllegalSequence =>e
  puts "Could not convert #{str} Error:#{e}"
end

text = FR
latin1 = convert_encoding(text, 'UTF-8', 'LATIN1')
puts "UTF-8: #{text}, Latin-1: #{latin1}" 


puts "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ CharDet"

def to_utf8(text)
  cd = CharDet.detect(text)
  #puts cd.inspect # => {"confidence"=>0.813842214321461, "encoding"=>"ISO-8859-2"} 
  text = cd['confidence'] > 0.6 ? Iconv.conv('UTF-8', cd['encoding'], text) : text
end

s = to_utf8(latin1)
puts "To UTF-8: #{to_utf8(latin1)}"