#encoding
utf-8

#name
ASCII
#b
ab
#c
ab
#bc
#cb

#name
Low BMP with last byte missing
#b
a\xC3Z
#c
a\u{FFFD}Z
#bc
#errors fatal
1;m;utf-8:bad bytes;\xC3

#name
Low BMP with last byte missing
#b
a\xC3
#c
a\u{FFFD}
#bc
#errors fatal
1;m;utf-8:bad bytes;\xC3

#name
High BMP with last byte missing
#b
a\xE2\x98Z
#c
a\u{FFFD}Z
#bc
#errors fatal
1;m;utf-8:bad bytes;\xE2\x98

#name
High BMP with last byte missing
#b
a\xE2\x98
#c
a\u{FFFD}
#bc
#errors fatal
1;m;utf-8:bad bytes;\xE2\x98

#name
Astral with last byte missing
#b
a\xF0\x9F\x92Z
#c
a\u{FFFD}Z
#bc
#errors fatal
1;m;utf-8:bad bytes;\xF0\x9F\x92

#name
Astral with last byte missing
#b
a\xF0\x9F\x92
#c
a\u{FFFD}
#bc
#errors fatal
1;m;utf-8:bad bytes;\xF0\x9F\x92

#name
Lone highest continuation
#b
a\xBFZ
#c
a\u{FFFD}Z
#bc
#errors fatal
1;m;utf-8:bad bytes;\xBF

#name
Lone highest continuation
#b
a\xBF
#c
a\u{FFFD}
#bc
#errors fatal
1;m;utf-8:bad bytes;\xBF

#name
Two lone highest continuations
#b
a\xBF\xBFZ
#c
a\u{FFFD}\u{FFFD}Z
#bc
#errors fatal
1;m;utf-8:bad bytes;\xBF
2;m;utf-8:bad bytes;\xBF

#name
Two lone highest continuations
#b
a\xBF\xBF
#c
a\u{FFFD}\u{FFFD}
#bc
#errors fatal
1;m;utf-8:bad bytes;\xBF
2;m;utf-8:bad bytes;\xBF

#name
Low BMP followed by lowest lone continuation
#b
a\xC3\xA4\x80Z
#c
a\u{E4}\u{FFFD}Z
#bc
#errors fatal
3;m;utf-8:bad bytes;\x80

#name
Low BMP followed by lowest lone continuation
#b
a\xC3\xA4\x80
#c
a\u{E4}\u{FFFD}
#bc
#errors fatal
3;m;utf-8:bad bytes;\x80

#name
Low BMP followed by highest lone continuation
#b
a\xC3\xA4\xBFZ
#c
a\u{E4}\u{FFFD}Z
#bc
#errors fatal
3;m;utf-8:bad bytes;\xBF

#name
Low BMP followed by highest lone continuation
#b
a\xC3\xA4\xBF
#c
a\u{E4}\u{FFFD}
#bc
#errors fatal
3;m;utf-8:bad bytes;\xBF

#name
High BMP followed by lowest lone continuation
#b
a\xE2\x98\x83\x80Z
#c
a\u{2603}\u{FFFD}Z
#bc
#errors fatal
4;m;utf-8:bad bytes;\x80

#name
High BMP followed by lowest lone continuation
#b
a\xE2\x98\x83\x80
#c
a\u{2603}\u{FFFD}
#bc
#errors fatal
4;m;utf-8:bad bytes;\x80

#name
High BMP followed by highest lone continuation
#b
a\xE2\x98\x83\xBFZ
#c
a\u{2603}\u{FFFD}Z
#bc
#errors fatal
4;m;utf-8:bad bytes;\xBF

#name
High BMP followed by highest lone continuation
#b
a\xE2\x98\x83\xBF
#c
a\u{2603}\u{FFFD}
#bc
#errors fatal
4;m;utf-8:bad bytes;\xBF

#name
Astral followed by lowest lone continuation
#b
a\xF0\x9F\x92\xA9\x80Z
#c
a\u{1F4A9}\u{FFFD}Z
#bc
#errors fatal
5;m;utf-8:bad bytes;\x80

#name
Astral followed by lowest lone continuation
#b
a\xF0\x9F\x92\xA9\x80
#c
a\u{1F4A9}\u{FFFD}
#bc
#errors fatal
5;m;utf-8:bad bytes;\x80

#name
Astral followed by highest lone continuation
#b
a\xF0\x9F\x92\xA9\xBFZ
#c
a\u{1F4A9}\u{FFFD}Z
#bc
#errors fatal
5;m;utf-8:bad bytes;\xBF

#name
Astral followed by highest lone continuation
#b
a\xF0\x9F\x92\xA9\xBF
#c
a\u{1F4A9}\u{FFFD}
#bc
#errors fatal
5;m;utf-8:bad bytes;\xBF

#name
Lowest single-byte
#b
Z\x00
#c
Z\u{0000}
#bc
#cb

#b
Z\x00Z
#c
Z\u{0000}Z
#bc
#cb

#name
Lowest single-byte as two-byte overlong sequence
#b
a\xC0\x80
#c
a\u{FFFD}\u{FFFD}
#bc
#errors fatal
1;m;utf-8:bad bytes;\xC0
2;m;utf-8:bad bytes;\x80

#b
a\xC0\x80Z
#c
a\u{FFFD}\u{FFFD}Z
#bc
#errors fatal
1;m;utf-8:bad bytes;\xC0
2;m;utf-8:bad bytes;\x80

#name
Lowest single-byte as three-byte overlong sequence
#b
a\xE0\x80\x80
#c
a\u{FFFD}\u{FFFD}\u{FFFD}
#bc
#errors fatal
1;m;utf-8:bad bytes;\xE0
2;m;utf-8:bad bytes;\x80
3;m;utf-8:bad bytes;\x80

#b
a\xE0\x80\x80Z
#c
a\u{FFFD}\u{FFFD}\u{FFFD}Z
#bc
#errors fatal
1;m;utf-8:bad bytes;\xE0
2;m;utf-8:bad bytes;\x80
3;m;utf-8:bad bytes;\x80

#name
Lowest single-byte as four-byte overlong sequence
#b
a\xF0\x80\x80\x80
#c
a\u{FFFD}\u{FFFD}\u{FFFD}\u{FFFD}
#bc
#errors fatal
1;m;utf-8:bad bytes;\xF0
2;m;utf-8:bad bytes;\x80
3;m;utf-8:bad bytes;\x80
4;m;utf-8:bad bytes;\x80

#b
a\xF0\x80\x80\x80Z
#c
a\u{FFFD}\u{FFFD}\u{FFFD}\u{FFFD}Z
#bc
#errors fatal
1;m;utf-8:bad bytes;\xF0
2;m;utf-8:bad bytes;\x80
3;m;utf-8:bad bytes;\x80
4;m;utf-8:bad bytes;\x80

#name
One below lowest single-byte
#b
a\xFF
#c
a\u{FFFD}
#bc
#errors fatal
1;m;utf-8:bad bytes;\xFF

#b
a\xFFZ
#c
a\u{FFFD}Z
#bc
#errors fatal
1;m;utf-8:bad bytes;\xFF

#name
Highest single-byte
#b
a\x7F
#c
a\u{7F}
#bc
#cb

#b
a\x7FZ
#c
a\u{7F}Z
#bc
#cb

#name
Highest single-byte as two-byte overlong sequence
#b
a\xC1\xBF
#c
a\u{FFFD}\u{FFFD}
#bc
#errors fatal
1;m;utf-8:bad bytes;\xC1
2;m;utf-8:bad bytes;\xBF

#b
a\xC1\xBFZ
#c
a\u{FFFD}\u{FFFD}Z
#bc
#errors fatal
1;m;utf-8:bad bytes;\xC1
2;m;utf-8:bad bytes;\xBF

#name
Highest single-byte as three-byte overlong sequence
#b
a\xE0\x81\xBF
#c
a\u{FFFD}\u{FFFD}\u{FFFD}
#bc
#errors fatal
1;m;utf-8:bad bytes;\xE0
2;m;utf-8:bad bytes;\x81
3;m;utf-8:bad bytes;\xBF

#b
a\xE0\x81\xBFZ
#c
a\u{FFFD}\u{FFFD}\u{FFFD}Z
#bc
#errors fatal
1;m;utf-8:bad bytes;\xE0
2;m;utf-8:bad bytes;\x81
3;m;utf-8:bad bytes;\xBF

#name
Highest single-byte as four-byte overlong sequence
#b
a\xF0\x80\x81\xBF
#c
a\u{FFFD}\u{FFFD}\u{FFFD}\u{FFFD}
#bc
#errors fatal
1;m;utf-8:bad bytes;\xF0
2;m;utf-8:bad bytes;\x80
3;m;utf-8:bad bytes;\x81
4;m;utf-8:bad bytes;\xBF

#b
a\xF0\x80\x81\xBFZ
#c
a\u{FFFD}\u{FFFD}\u{FFFD}\u{FFFD}Z
#bc
#errors fatal
1;m;utf-8:bad bytes;\xF0
2;m;utf-8:bad bytes;\x80
3;m;utf-8:bad bytes;\x81
4;m;utf-8:bad bytes;\xBF

#name
One past highest single byte (also lone continuation)
#b
a\x80Z
#c
a\u{FFFD}Z
#bc
#errors fatal
1;m;utf-8:bad bytes;\x80

#b
a\x80
#c
a\u{FFFD}
#bc
#errors fatal
1;m;utf-8:bad bytes;\x80

#name
Two lone continuations
#b
a\x80\x80Z
#c
a\u{FFFD}\u{FFFD}Z
#bc
#errors fatal
1;m;utf-8:bad bytes;\x80
2;m;utf-8:bad bytes;\x80

#b
a\x80\x80
#c
a\u{FFFD}\u{FFFD}
#bc
#errors fatal
1;m;utf-8:bad bytes;\x80
2;m;utf-8:bad bytes;\x80

#name
Three lone continuations
#b
a\x80\x80\x80Z
#c
a\u{FFFD}\u{FFFD}\u{FFFD}Z
#bc
#errors fatal
1;m;utf-8:bad bytes;\x80
2;m;utf-8:bad bytes;\x80
3;m;utf-8:bad bytes;\x80

#b
a\x80\x80\x80
#c
a\u{FFFD}\u{FFFD}\u{FFFD}
#bc
#errors fatal
1;m;utf-8:bad bytes;\x80
2;m;utf-8:bad bytes;\x80
3;m;utf-8:bad bytes;\x80

#name
Four lone continuations
#b
a\x80\x80\x80\x80Z
#c
a\u{FFFD}\u{FFFD}\u{FFFD}\u{FFFD}Z
#bc
#errors fatal
1;m;utf-8:bad bytes;\x80
2;m;utf-8:bad bytes;\x80
3;m;utf-8:bad bytes;\x80
4;m;utf-8:bad bytes;\x80

#b
a\x80\x80\x80\x80
#c
a\u{FFFD}\u{FFFD}\u{FFFD}\u{FFFD}
#bc
#errors fatal
1;m;utf-8:bad bytes;\x80
2;m;utf-8:bad bytes;\x80
3;m;utf-8:bad bytes;\x80
4;m;utf-8:bad bytes;\x80

#name
Lowest two-byte
#b
a\xC2\x80
#c
a\u{0080}
#bc
#cb

#b
a\xC2\x80Z
#c
a\u{0080}Z
#bc
#cb

#name
Lowest two-byte as three-byte overlong sequence
#b
a\xE0\x82\x80
#c
a\u{FFFD}\u{FFFD}\u{FFFD}
#bc
#errors fatal
1;m;utf-8:bad bytes;\xE0
2;m;utf-8:bad bytes;\x82
3;m;utf-8:bad bytes;\x80

#b
a\xE0\x82\x80Z
#c
a\u{FFFD}\u{FFFD}\u{FFFD}Z
#bc
#errors fatal
1;m;utf-8:bad bytes;\xE0
2;m;utf-8:bad bytes;\x82
3;m;utf-8:bad bytes;\x80

#name
Lowest two-byte as four-byte overlong sequence
#b
a\xF0\x80\x82\x80
#c
a\u{FFFD}\u{FFFD}\u{FFFD}\u{FFFD}
#bc
#errors fatal
1;m;utf-8:bad bytes;\xF0
2;m;utf-8:bad bytes;\x80
3;m;utf-8:bad bytes;\x82
4;m;utf-8:bad bytes;\x80

#b
a\xF0\x80\x82\x80Z
#c
a\u{FFFD}\u{FFFD}\u{FFFD}\u{FFFD}Z
#bc
#errors fatal
1;m;utf-8:bad bytes;\xF0
2;m;utf-8:bad bytes;\x80
3;m;utf-8:bad bytes;\x82
4;m;utf-8:bad bytes;\x80

#name
Lead one below lowest two-byte
#b
a\xC1\x80
#c
a\u{FFFD}\u{FFFD}
#bc
#errors fatal
1;m;utf-8:bad bytes;\xC1
2;m;utf-8:bad bytes;\x80

#b
a\xC1\x80Z
#c
a\u{FFFD}\u{FFFD}Z
#bc
#errors fatal
1;m;utf-8:bad bytes;\xC1
2;m;utf-8:bad bytes;\x80

#name
Trail one below lowest two-byte
#b
a\xC2\x7F
#c
a\u{FFFD}\u{007F}
#bc
#errors fatal
1;m;utf-8:bad bytes;\xC2

#b
a\xC2\x7FZ
#c
a\u{FFFD}\u{007F}Z
#bc
#errors fatal
1;m;utf-8:bad bytes;\xC2

#name
Highest two-byte
#b
a\xDF\xBF
#c
a\u{07FF}
#bc
#cb

#b
a\xDF\xBFZ
#c
a\u{07FF}Z
#bc
#cb

#name
Highest two-byte as three-byte overlong sequence
#b
a\xE0\x9F\xBF
#c
a\u{FFFD}\u{FFFD}\u{FFFD}
#bc
#errors fatal
1;m;utf-8:bad bytes;\xE0
2;m;utf-8:bad bytes;\x9F
3;m;utf-8:bad bytes;\xBF

#b
a\xE0\x9F\xBFZ
#c
a\u{FFFD}\u{FFFD}\u{FFFD}Z
#bc
#errors fatal
1;m;utf-8:bad bytes;\xE0
2;m;utf-8:bad bytes;\x9F
3;m;utf-8:bad bytes;\xBF

#name
Highest two-byte as four-byte overlong sequence
#b
a\xF0\x80\x9F\xBF
#c
a\u{FFFD}\u{FFFD}\u{FFFD}\u{FFFD}
#bc
#errors fatal
1;m;utf-8:bad bytes;\xF0
2;m;utf-8:bad bytes;\x80
3;m;utf-8:bad bytes;\x9F
4;m;utf-8:bad bytes;\xBF

#b
a\xF0\x80\x9F\xBFZ
#c
a\u{FFFD}\u{FFFD}\u{FFFD}\u{FFFD}Z
#bc
#errors fatal
1;m;utf-8:bad bytes;\xF0
2;m;utf-8:bad bytes;\x80
3;m;utf-8:bad bytes;\x9F
4;m;utf-8:bad bytes;\xBF

#name
Lowest three-byte
#b
a\xE0\xA0\x80
#c
a\u{0800}
#bc
#cb

#b
a\xE0\xA0\x80Z
#c
a\u{0800}Z
#bc
#cb

#name
Lowest three-byte as four-byte overlong sequence
#b
a\xF0\x80\xA0\x80
#c
a\u{FFFD}\u{FFFD}\u{FFFD}\u{FFFD}
#bc
#errors fatal
1;m;utf-8:bad bytes;\xF0
2;m;utf-8:bad bytes;\x80
3;m;utf-8:bad bytes;\xA0
4;m;utf-8:bad bytes;\x80

#b
a\xF0\x80\xA0\x80Z
#c
a\u{FFFD}\u{FFFD}\u{FFFD}\u{FFFD}Z
#bc
#errors fatal
1;m;utf-8:bad bytes;\xF0
2;m;utf-8:bad bytes;\x80
3;m;utf-8:bad bytes;\xA0
4;m;utf-8:bad bytes;\x80

#name
Highest below surrogates
#b
a\xED\x9F\xBF
#c
a\u{D7FF}
#bc
#cb

#b
a\xED\x9F\xBFZ
#c
a\u{D7FF}Z
#bc
#cb

#name
Highest below surrogates as four-byte overlong sequence
#b
a\xF0\x8D\x9F\xBF
#c
a\u{FFFD}\u{FFFD}\u{FFFD}\u{FFFD}
#bc
#errors fatal
1;m;utf-8:bad bytes;\xF0
2;m;utf-8:bad bytes;\x8D
3;m;utf-8:bad bytes;\x9F
4;m;utf-8:bad bytes;\xBF

#b
a\xF0\x8D\x9F\xBFZ
#c
a\u{FFFD}\u{FFFD}\u{FFFD}\u{FFFD}Z
#bc
#errors fatal
1;m;utf-8:bad bytes;\xF0
2;m;utf-8:bad bytes;\x8D
3;m;utf-8:bad bytes;\x9F
4;m;utf-8:bad bytes;\xBF

#name
First surrogate
#b
a\xED\xA0\x80
#c
a\u{FFFD}\u{FFFD}\u{FFFD}
#bc
#errors fatal
1;m;utf-8:bad bytes;\xED
2;m;utf-8:bad bytes;\xA0
3;m;utf-8:bad bytes;\x80

#b
a\xED\xA0\x80Z
#c
a\u{FFFD}\u{FFFD}\u{FFFD}Z
#bc
#errors fatal
1;m;utf-8:bad bytes;\xED
2;m;utf-8:bad bytes;\xA0
3;m;utf-8:bad bytes;\x80

#name
First surrogate as four-byte overlong sequence
#b
a\xF0\x8D\xA0\x80
#c
a\u{FFFD}\u{FFFD}\u{FFFD}\u{FFFD}
#bc
#errors fatal
1;m;utf-8:bad bytes;\xF0
2;m;utf-8:bad bytes;\x8D
3;m;utf-8:bad bytes;\xA0
4;m;utf-8:bad bytes;\x80

#b
a\xF0\x8D\xA0\x80Z
#c
a\u{FFFD}\u{FFFD}\u{FFFD}\u{FFFD}Z
#bc
#errors fatal
1;m;utf-8:bad bytes;\xF0
2;m;utf-8:bad bytes;\x8D
3;m;utf-8:bad bytes;\xA0
4;m;utf-8:bad bytes;\x80

#name
Last surrogate
#b
a\xED\xBF\xBF
#c
a\u{FFFD}\u{FFFD}\u{FFFD}
#bc
#errors fatal
1;m;utf-8:bad bytes;\xED
2;m;utf-8:bad bytes;\xBF
3;m;utf-8:bad bytes;\xBF

#b
a\xED\xBF\xBFZ
#c
a\u{FFFD}\u{FFFD}\u{FFFD}Z
#bc
#errors fatal
1;m;utf-8:bad bytes;\xED
2;m;utf-8:bad bytes;\xBF
3;m;utf-8:bad bytes;\xBF

#name
Last surrogate as four-byte overlong sequence
#b
a\xF0\x8D\xBF\xBF
#c
a\u{FFFD}\u{FFFD}\u{FFFD}\u{FFFD}
#bc
#errors fatal
1;m;utf-8:bad bytes;\xF0
2;m;utf-8:bad bytes;\x8D
3;m;utf-8:bad bytes;\xBF
4;m;utf-8:bad bytes;\xBF

#b
a\xF0\x8D\xBF\xBFZ
#c
a\u{FFFD}\u{FFFD}\u{FFFD}\u{FFFD}Z
#bc
#errors fatal
1;m;utf-8:bad bytes;\xF0
2;m;utf-8:bad bytes;\x8D
3;m;utf-8:bad bytes;\xBF
4;m;utf-8:bad bytes;\xBF

#name
Lowest above surrogates
#b
a\xEE\x80\x80
#c
a\u{E000}
#bc
#cb

#b
a\xEE\x80\x80Z
#c
a\u{E000}Z
#bc
#cb

#name
Lowest above surrogates as four-byte overlong sequence
#b
a\xF0\x8E\x80\x80
#c
a\u{FFFD}\u{FFFD}\u{FFFD}\u{FFFD}
#bc
#errors fatal
1;m;utf-8:bad bytes;\xF0
2;m;utf-8:bad bytes;\x8E
3;m;utf-8:bad bytes;\x80
4;m;utf-8:bad bytes;\x80

#b
a\xF0\x8E\x80\x80Z
#c
a\u{FFFD}\u{FFFD}\u{FFFD}\u{FFFD}Z
#bc
#errors fatal
1;m;utf-8:bad bytes;\xF0
2;m;utf-8:bad bytes;\x8E
3;m;utf-8:bad bytes;\x80
4;m;utf-8:bad bytes;\x80

#name
Highest three-byte
#b
a\xEF\xBF\xBF
#c
a\u{FFFF}
#bc
#cb

#b
a\xEF\xBF\xBFZ
#c
a\u{FFFF}Z
#bc
#cb

#name
Highest three-byte as four-byte overlong sequence
#b
a\xF0\x8F\xBF\xBF
#c
a\u{FFFD}\u{FFFD}\u{FFFD}\u{FFFD}
#bc
#errors fatal
1;m;utf-8:bad bytes;\xF0
2;m;utf-8:bad bytes;\x8F
3;m;utf-8:bad bytes;\xBF
4;m;utf-8:bad bytes;\xBF

#b
a\xF0\x8F\xBF\xBFZ
#c
a\u{FFFD}\u{FFFD}\u{FFFD}\u{FFFD}Z
#bc
#errors fatal
1;m;utf-8:bad bytes;\xF0
2;m;utf-8:bad bytes;\x8F
3;m;utf-8:bad bytes;\xBF
4;m;utf-8:bad bytes;\xBF

#name
Lowest four-byte
#b
a\xF0\x90\x80\x80
#c
a\u{10000}
#bc
#cb

#b
a\xF0\x90\x80\x80Z
#c
a\u{10000}Z
#bc
#cb

#name
Highest four-byte
#b
a\xF4\x8F\xBF\xBF
#c
a\u{10FFFF}
#bc
#cb

#b
a\xF4\x8F\xBF\xBFZ
#c
a\u{10FFFF}Z
#bc
#cb

#name
One past highest four-byte
#b
a\xF4\x90\x80\x80
#c
a\u{FFFD}\u{FFFD}\u{FFFD}\u{FFFD}
#bc
#errors fatal
1;m;utf-8:bad bytes;\xF4
2;m;utf-8:bad bytes;\x90
3;m;utf-8:bad bytes;\x80
4;m;utf-8:bad bytes;\x80

#b
a\xF4\x90\x80\x80Z
#c
a\u{FFFD}\u{FFFD}\u{FFFD}\u{FFFD}Z
#bc
#errors fatal
1;m;utf-8:bad bytes;\xF4
2;m;utf-8:bad bytes;\x90
3;m;utf-8:bad bytes;\x80
4;m;utf-8:bad bytes;\x80

#name
Highest four-byte with last byte replaced with 0xFF
#b
a\xF4\x8F\xBF\xFF
#c
a\u{FFFD}\u{FFFD}
#bc
#errors fatal
1;m;utf-8:bad bytes;\xF4\x8F\xBF
4;m;utf-8:bad bytes;\xFF

#b
a\xF4\x8F\xBF\xFFZ
#c
a\u{FFFD}\u{FFFD}Z
#bc
#errors fatal
1;m;utf-8:bad bytes;\xF4\x8F\xBF
4;m;utf-8:bad bytes;\xFF