maerzbow · May 28, 2012 10:42
diff --git a/codepoints_vs_bytes.rb b/codepoints_vs_bytes.rb
 german_string = "muß grösser sein"

 # to retrieve the encoding of a String
 puts german_string.encoding.name # >> UTF-8

 # the character count
 puts german_string.size # >> 16

 # the actual bytes of this UTF-8 string
 puts german_string.bytesize # >> 18

 puts german_string.bytes { |byte| print "#{byte} " } # >>  109 117 195 159 32 103 114 195 182 115 115 101 114 32 115 101 105 110
 puts german_string.codepoints { |cp| print "#{cp} " } # >> 109 117 223 32 103 114 246 115 115 101 114 32 115 101 105 110
	german_string = "muß grösser sein"

	# to retrieve the encoding of a String
	puts german_string.encoding.name # >> UTF-8

	# the character count
	puts german_string.size # >> 16

	# the actual bytes of this UTF-8 string
	puts german_string.bytesize # >> 18

	puts german_string.bytes { \|byte\| print "#{byte} " } # >> 109 117 195 159 32 103 114 195 182 115 115 101 114 32 115 101 105 110
	puts german_string.codepoints { \|cp\| print "#{cp} " } # >> 109 117 223 32 103 114 246 115 115 101 114 32 115 101 105 110