Understanding encoding through examples in Ruby

gistfile1.rb

# encoding:  UTF-8

utf8_resume = "Résumé"
latin1_resume = utf8_resume.encode("ISO-8859-1")
latin9_resume = utf8_resume.encode("ISO-8859-15")

lower_spanish = "\u00E1 \u00E9 \u00ED \u00F3 \u00FA \u00F1".encode("UTF-8")
puts lower_spanish
upper_spanish = "\u00C1 \u00C9 \u00CD \u00D3 \u00DA \u00D1".encode("UTF-8")
puts upper_spanish

puts 'Display each byte (hex)'
utf8_resume.bytesize.times {|i| printf "%X ", utf8_resume.getbyte(i)}
puts "= #{utf8_resume} encoded as UTF-8"
latin1_resume.bytesize.times {|i| printf "%X ", latin1_resume.getbyte(i)}
puts "= #{latin1_resume.encode('UTF-8')} encoded as ISO-8859-1"
latin9_resume.bytesize.times {|i| printf "%X ", latin9_resume.getbyte(i)}
puts "= #{latin9_resume.encode('UTF-8')} encoded as ISO-8859-15"
puts

puts 'Display each character as a Unicode codepoint (hex)'
utf8_resume.each_codepoint {|c| printf "%X ", c}
puts "= #{utf8_resume} encoded as UTF-8"
latin1_resume.each_codepoint {|c| printf "%X ", c}
puts "= #{utf8_resume} encoded as ISO-8859-1"
latin9_resume.each_codepoint {|c| printf "%X ", c}
puts "= #{utf8_resume} encoded as ISO-8859-15"
puts

utf8_money = "\u{20AC A4 A3 A5}"
latin1_money = "\u{A4 A3 A5}".encode("ISO-8859-1")
latin9_money = "\u{20AC A3 A5}".encode("ISO-8859-15")

puts 'Display each byte (hex)'
utf8_money.bytesize.times {|i| printf "%X ", utf8_money.getbyte(i)}
puts "= #{utf8_money} encoded as UTF-8"
latin1_money.bytesize.times {|i| printf "%X ", latin1_money.getbyte(i)}
puts "= #{latin1_money.encode('UTF-8')} encoded as ISO-8859-1 (20AC is invalid)"
latin9_money.bytesize.times {|i| printf "%X ", latin9_money.getbyte(i)}
puts "= #{latin9_money.encode('UTF-8')} encoded as ISO-8859-15 (A4 is invalid, 20AC gets converted into A4)"
puts

puts 'Display each character as a Unicode codepoint (hex)'
utf8_money.each_codepoint {|c| printf "%X ", c}
puts "= #{utf8_money} encoded as UTF-8"
latin1_money.each_codepoint {|c| printf "%X ", c}
puts "= #{latin1_money.encode('UTF-8')} encoded as ISO-8859-1 (20AC is invalid)"
latin9_money.each_codepoint {|c| printf "%X ", c}
puts "= #{latin9_money.encode('UTF-8')} encoded as ISO-8859-15 (A4 is invalid, 20AC gets converted into A4)"
puts

puts <<EOT
NOTE:
\u00A4 (called currency symbol) in Latin-1 changed to \u20AC in Latin-9
http://en.wikipedia.org/wiki/ISO/IEC_8859-15
EOT