# Generated by re2py
# re2py $INPUT -o $OUTPUT --input-encoding utf8

# This example supports multiple input encodings: UTF-8 and UTF-32.
# Both lexers are generated from the same rules block, and the use
# blocks add only encoding-specific configurations.


def lex_utf8(yyinput):
    yycursor = 0
    
    yystate = 0
    while True:
        match yystate:
            case 0:
                yych = yyinput[yycursor]
                yycursor += 1
                if yych == 0xE2:
                    yystate = 2
                    continue
                yystate = 1
                continue
            case 1:
                return None
            case 2:
                yymarker = yycursor
                yych = yyinput[yycursor]
                if yych != 0x88:
                    yystate = 1
                    continue
                yycursor += 1
                yych = yyinput[yycursor]
                if yych == 0x80:
                    yycursor += 1
                    yystate = 4
                    continue
                yystate = 3
                continue
            case 3:
                yycursor = yymarker
                yystate = 1
                continue
            case 4:
                yych = yyinput[yycursor]
                if yych != 0x78:
                    yystate = 3
                    continue
                yycursor += 1
                yych = yyinput[yycursor]
                if yych != 0x20:
                    yystate = 3
                    continue
                yycursor += 1
                yych = yyinput[yycursor]
                if yych != 0xE2:
                    yystate = 3
                    continue
                yycursor += 1
                yych = yyinput[yycursor]
                if yych != 0x88:
                    yystate = 3
                    continue
                yycursor += 1
                yych = yyinput[yycursor]
                if yych != 0x83:
                    yystate = 3
                    continue
                yycursor += 1
                yych = yyinput[yycursor]
                if yych != 0x79:
                    yystate = 3
                    continue
                yycursor += 1
                return yycursor
            case _:
                raise "internal lexer error"


def lex_utf32(yyinput):
    yycursor = 0
    
    yystate = 0
    while True:
        match yystate:
            case 0:
                yych = yyinput[yycursor]
                yycursor += 1
                if yych == 0x00002200:
                    yystate = 2
                    continue
                yystate = 1
                continue
            case 1:
                return None
            case 2:
                yymarker = yycursor
                yych = yyinput[yycursor]
                if yych != 0x00000078:
                    yystate = 1
                    continue
                yycursor += 1
                yych = yyinput[yycursor]
                if yych == 0x00000020:
                    yycursor += 1
                    yystate = 4
                    continue
                yystate = 3
                continue
            case 3:
                yycursor = yymarker
                yystate = 1
                continue
            case 4:
                yych = yyinput[yycursor]
                if yych != 0x00002203:
                    yystate = 3
                    continue
                yycursor += 1
                yych = yyinput[yycursor]
                if yych != 0x00000079:
                    yystate = 3
                    continue
                yycursor += 1
                return yycursor
            case _:
                raise "internal lexer error"


s8 = [0xe2, 0x88, 0x80, 0x78, 0x20, 0xe2, 0x88, 0x83, 0x79]
assert lex_utf8(s8) == len(s8)

s32 = [0x2200, 0x78, 0x20, 0x2203, 0x79]
assert lex_utf32(s32) == len(s32)