# s is a String assigned a literal value
# representing the word "hello" in the Thai language.
# Ruby string literals are UTF-8 encoded text by default.
s = "สวัสดี"

# This will produce the length of the string in characters.
puts "Len: #{s.length}"

# This loop generates the hex values of all
# the bytes that constitute the characters in s.
s.each_byte do |byte|
  print "#{byte.to_s(16)} "
end
puts

# To count how many characters are in a string, we can use
# the length method. Note that Ruby treats Thai characters
# as single characters, even if they span multiple bytes in UTF-8.
puts "Character count: #{s.length}"

# Ruby's each_char method allows us to iterate over each character
# in the string.
s.each_char.with_index do |char, idx|
  puts "U+#{char.ord.to_s(16).upcase.rjust(4, '0')} '#{char}' starts at #{idx}"
end

puts "\nUsing String#unpack"
# We can achieve a similar iteration by unpacking the string
# into its UTF-8 codepoints.
s.unpack("U*").each_with_index do |codepoint, idx|
  char = [codepoint].pack("U")
  puts "U+#{codepoint.to_s(16).upcase.rjust(4, '0')} '#{char}' starts at #{idx}"
  examine_char(char)
end

def examine_char(char)
  # We can compare a character to a string literal directly.
  if char == 't'
    puts "found tee"
  elsif char == 'ส'
    puts "found so sua"
  end
end