UTF-8 codepoints validation rules

gistfile1.txt

	overlong: charset "^(C0)^(C1)"
	invalid-bytes: union overlong charset [#"^(F5)" - #"^(FF)"]
	
	cont-byte: charset [#"^(80)" - #"^(BF)"]
		
	one-byte-codepoint: charset [#"^(00)" - #"^(7F)"]

	two-bytes-codepoint: reduce [
		charset [#"^(C2)" - #"^(DF)"]
		cont-byte
	]
	three-bytes-codepoint: reduce [
		charset [#"^(E0)" - #"^(EF)"]
		charset [#"^(A0)" - #"^(BF)"]
		cont-byte
	]
	four-bytes-codepoint: compose/deep [
		[
			#{F0} (charset [#"^(90)" - #"^(FF)"])
			|  [#{F1} | #{F2}] skip
			| #{F4}	(charset [#"^(00)" - #"^(8F)"])
		]
		(cont-byte)
		(cont-byte)
	]