invalid_sequences = ["\xC0", # always invalid utf8
"\xC2\x4a", # 2-byte multibyte identifier, followed by plain ASCII
"\xC2\xC2", # 2-byte multibyte identifier, followed by another one
invalid_sequences = ["\xC0", # always invalid utf8
"\xC2\x4a", # 2-byte multibyte identifier, followed by plain ASCII
"\xC2\xC2", # 2-byte multibyte identifier, followed by another one