{"3>>-4", "negative right shift count"},
	{"3>>(1<<63)", "negative right shift count"},
	{"(1<<63)>>2", "right shift of value with high bit set"},
	{"(1<<62)>>2", ""},
	{`'\x80'`, "illegal UTF-8 encoding for character constant"},
	{"(23*4", "missing closing paren"},
	{")23*4", "unexpected ) evaluating expression"},
	{"18446744073709551616", "value out of range"},
}

func TestBadExpr(t *testing.T) {

	if atEOF {
		return len(data), dropCR(data), nil
	}
	// Request more data.
	return 0, nil, nil
}

// isSpace reports whether the character is a Unicode white space character.
// We avoid dependency on the unicode package, but check validity of the implementation
// in the tests.
func isSpace(r rune) bool {
	if r <= '\u00FF' {

	//
	// By specification, the only other encoding permitted should be CP-437,
	// but historically many ZIP readers interpret Name and Comment as whatever
	// the system's local character encoding happens to be.
	//
	// This flag should only be set if the user intends to encode a non-portable
	// ZIP file for a specific localized region. Otherwise, the Writer

// 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.

// license that can be found in the LICENSE file.

package tar

import (
	"bytes"
	"fmt"
	"strconv"
	"strings"
	"time"
)

// hasNUL reports whether the NUL character exists within s.
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 _, err := io.ReadFull(r, d); err != nil {
		return err
	}
	f.Name = string(d[:filenameLen])
	f.Extra = d[filenameLen : filenameLen+extraLen]
	f.Comment = string(d[filenameLen+extraLen:])

	// Determine the character encoding.
	utf8Valid1, utf8Require1 := detectUTF8(f.Name)
	utf8Valid2, utf8Require2 := detectUTF8(f.Comment)
	switch {
	case !utf8Valid1 || !utf8Valid2:
		// Name and Comment definitely not UTF-8.

		return true
	case '\u2215': // Represents the slash in runtime/debug.setGCPercent. U+2215 '∕' division slash
		return true
	}
	// Digits are OK only after the first character.
	return i > 0 && unicode.IsDigit(ch)
}

func (t *Tokenizer) Text() string {
	switch t.tok {
	case LSH:
		return "<<"
	case RSH:
		return ">>"
	case ARR:
		return "->"
	case ROT:
		return "@>"
	}
	return t.s.TokenText()

// used, by convention, to distinguish byte values from 8-bit unsigned
// integer values.
type byte = uint8

// rune is an alias for int32 and is equivalent to int32 in all ways. It is
// used, by convention, to distinguish character values from integer values.
type rune = int32

// any is an alias for interface{} and is equivalent to interface{} in all ways.
type any = interface{}

)

// A ScanToken represents an input item. It is a simple wrapping of rune, as
// returned by text/scanner.Scanner, plus a couple of extra values.
type ScanToken rune

const (
	// Asm defines some two-character lexemes. We make up
	// a rune/ScanToken value for them - ugly but simple.
	LSH          ScanToken = -1000 - iota // << Left shift.
	RSH                                   // >> Logical right shift.

	// Deprecated: Use TypeReg instead.
	TypeRegA = '\x00'

	// Type '1' to '6' are header-only flags and may not have a data body.
	TypeLink    = '1' // Hard link
	TypeSymlink = '2' // Symbolic link
	TypeChar    = '3' // Character device node
	TypeBlock   = '4' // Block device node
	TypeDir     = '5' // Directory
	TypeFifo    = '6' // FIFO node

	// Type '7' is reserved.
	TypeCont = '7'