lex
  # http://www.ietf.org/rfc/rfc3629.txt
  rl UTF8_tail / 0x80..0xBF /
  rl UTF8_1    / 0x00..0x7F /
  rl UTF8_2    / 0xC2..0xDF UTF8_tail /
  rl UTF8_3    / 0xE0 0xA0..0xBF UTF8_tail | 0xE1..0xEC UTF8_tail{2} |
                 0xED 0x80..0x9F UTF8_tail | 0xEE..0xEF UTF8_tail{2} /
  rl UTF8_4    / 0xF0 0x90..0xBF UTF8_tail{2} | 0xF1..0xF3 UTF8_tail{3} |
                 0xF4 0x80..0x8F UTF8_tail{2} /
  token UTF8_char / UTF8_1 | UTF8_2 | UTF8_3 | UTF8_4 /
end

global count: int = 0

def utf8_char
  [UTF8_char] { count = count + 1 }

def utf8_octets
  [utf8_char*]

parse P: utf8_octets[stdin]
print(count, '\n')
##### IN #####
A≢Α.
한국어
日本語
𣎴
###### EXP ######
16