Python implementation of UTF-8 decode algorithm by `decode("Bj\xc3\xb6rn H\xc3\xb6hrmann")` explained at http://bjoern.hoehrmann.de/utf-8/decoder/dfa/. Notes: 1) This is based on the slightly performance enhanced version closer to the end of the article. 2) My C skills are rather limited so it's possible that there are bugs. Simple test strings …

gistfile1.py

UTF8_ACCEPT = 0
UTF8_REJECT = 12
UTF8D = (
    0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
    0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
    0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
    0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,  9,9,9,9,9,9,9,9,9,9,9,9,9,9,9,9,
    7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,  7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,
    8,8,2,2,2,2,2,2,2,2,2,2,2,2,2,2,  2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
    10,3,3,3,3,3,3,3,3,3,3,3,3,4,3,3, 11,6,6,6,5,8,8,8,8,8,8,8,8,8,8,8,
    0,12,24,36,60,96,84,12,12,12,48,72, 12,12,12,12,12,12,12,12,12,12,12,12,
    12, 0,12,12,12,12,12, 0,12, 0,12,12, 12,24,12,12,12,12,12,24,12,24,12,12,
    12,12,12,12,12,12,12,24,12,12,12,12, 12,24,12,12,12,12,12,12,12,24,12,12,
    12,12,12,12,12,12,12,36,12,36,12,12, 12,36,12,12,12,12,12,36,12,36,12,12,
    12,36,12,12,12,12,12,12,12,12,12,12,
)

def decode(string):
    codep = 0
    state = UTF8_ACCEPT
    for char in string:
        byte = ord(char)
        type = UTF8D[byte]
        if state != UTF8_ACCEPT:
            codep = (byte & 0x3f) | (codep << 6)
        else:
            codep = (0xff >> type) & (byte)
        state = UTF8D[256 + state + type]
        if state == UTF8_ACCEPT:
            print codep, unichr(codep)


decode("Bj\xc3\xb6rn H\xc3\xb6hrmann")
decode(u'\u2603'.encode('utf-8'))
decode(u'\U0001F649'.encode('utf-8'))