<code>'ä'</code> holds two bytes (<code>0xc3</code> <code>0xa4</code>) representing
a literal <code>a</code>-dieresis, U+00E4, value <code>0xe4</code>.
</p>

<p>
Several backslash escapes allow arbitrary values to be encoded as
ASCII text.  There are four ways to represent the integer value
as a numeric constant: <code>\x</code> followed by exactly two hexadecimal
digits; <code>\u</code> followed by exactly four hexadecimal digits;

Asia/Hovd Asia/Irkutsk Asia/Istanbul Asia/Jakarta Asia/Jayapura Asia/Jerusalem Asia/Kabul Asia/Kamchatka Asia/Karachi Asia/Kashgar Asia/Kathmandu Asia/Katmandu Asia/Khandyga Asia/Kolkata Asia/Krasnoyarsk Asia/Kuala_Lumpur Asia/Kuching Asia/Kuwait Asia/Macao Asia/Macau Asia/Magadan Asia/Makassar Asia/Manila Asia/Muscat Asia/Nicosia Asia/Novokuznetsk Asia/Novosibirsk Asia/Omsk Asia/Oral Asia/Phnom_Penh Asia/Pontianak Asia/Pyongyang Asia/Qatar Asia/Qostanay Asia/Qyzylorda Asia/Rangoon Asia/Riyadh Asia/Saigon...

func hasNUL(s string) bool {
	return strings.Contains(s, "\x00")
}

// isASCII reports whether the input is an ASCII C-style string.
func isASCII(s string) bool {
	for _, c := range s {
		if c >= 0x80 || c == 0x00 {
			return false
		}
	}
	return true
}

// toASCII converts the input to an ASCII C-style string.
// This is a best effort conversion, so invalid characters are dropped.
func toASCII(s string) string {

	if atEOF && len(data) == 0 {
		return 0, nil, nil
	}

	// Fast path 1: ASCII.
	if data[0] < utf8.RuneSelf {
		return 1, data[0:1], nil
	}

	// Fast path 2: Correct UTF-8 decode without error.
	_, width := utf8.DecodeRune(data)
	if width > 1 {
		// It's a valid encoding. Width cannot be one for a correctly encoded
		// non-ASCII rune.
		return width, data[0:width], nil
	}

//	ChangeTime        |    n/a | unlimited |     int89
//	Devmajor/Devminor | uint21 |    uint21 |    uint57
//	------------------+--------+-----------+----------
//	string encoding   |  ASCII |     UTF-8 |    binary
//	sub-second times  |     no |       yes |        no
//	sparse files      |     no |       yes |       yes
//
// The table's upper portion shows the [Header] fields, where each format reports

var makeFieldsInputASCII = func() []byte {
	x := make([]byte, 1<<20)
	// Input is ~10% space, rest ASCII non-space.
	for i := range x {
		if rand.Intn(10) == 0 {
			x[i] = ' '
		} else {
			x[i] = 'x'
		}
	}
	return x
}

var bytesdata = []struct {
	name string
	data []byte
}{
	{"ASCII", makeFieldsInputASCII()},
	{"Mixed", makeFieldsInput()},
}

// given ASCII character in the set. The 128-bits of the lower 16 bytes,
// starting with the least-significant bit of the lowest word to the
// most-significant bit of the highest word, map to the full range of all
// 128 ASCII characters. The 128-bits of the upper 16 bytes will be zeroed,
// ensuring that any non-ASCII character will be reported as not in the set.

<code>'ä'</code> holds two bytes (<code>0xc3</code> <code>0xa4</code>) representing
a literal <code>a</code>-dieresis, U+00E4, value <code>0xe4</code>.
</p>

<p>
Several backslash escapes allow arbitrary values to be encoded as
ASCII text.  There are four ways to represent the integer value
as a numeric constant: <code>\x</code> followed by exactly two hexadecimal
digits; <code>\u</code> followed by exactly four hexadecimal digits;

// or any other common encoding).
func detectUTF8(s string) (valid, require bool) {
	for i := 0; i < len(s); {
		r, size := utf8.DecodeRuneInString(s[i:])
		i += size
		// Officially, ZIP uses CP-437, but many readers use the system's
		// local character encoding. Most encoding are compatible with a large
		// subset of CP-437, which itself is ASCII-like.
		//

			// the parser is more liberal than what USTAR actually permits.
			notASCII := func(r rune) bool { return r >= 0x80 }
			if bytes.IndexFunc(tr.blk[:], notASCII) >= 0 {
				hdr.Format = FormatUnknown // Non-ASCII characters in block.
			}
			nul := func(b []byte) bool { return int(b[len(b)-1]) == 0 }
			if !(nul(v7.size()) && nul(v7.mode()) && nul(v7.uid()) && nul(v7.gid()) &&