Esempio n. 1
0
func unquoteBytes(s []byte) (t []byte, ok bool) {
	if len(s) < 2 || s[0] != '"' || s[len(s)-1] != '"' {
		return
	}
	s = s[1 : len(s)-1]

	// Check for unusual characters. If there are none,
	// then no unquoting is needed, so return a slice of the
	// original bytes.
	r := 0
	for r < len(s) {
		c := s[r]
		if c == '\\' || c == '"' || c < ' ' {
			break
		}
		if c < utf8.RuneSelf {
			r++
			continue
		}
		rune, size := utf8.DecodeRune(s[r:])
		if rune == utf8.RuneError && size == 1 {
			break
		}
		r += size
	}
	if r == len(s) {
		return s, true
	}

	b := make([]byte, len(s)+2*utf8.UTFMax)
	w := copy(b, s[0:r])
	for r < len(s) {
		// Out of room?  Can only happen if s is full of
		// malformed UTF-8 and we're replacing each
		// byte with RuneError.
		if w >= len(b)-2*utf8.UTFMax {
			nb := make([]byte, (len(b)+utf8.UTFMax)*2)
			copy(nb, b[0:w])
			b = nb
		}
		switch c := s[r]; {
		case c == '\\':
			r++
			if r >= len(s) {
				return
			}
			switch s[r] {
			default:
				return
			case '"', '\\', '/', '\'':
				b[w] = s[r]
				r++
				w++
			case 'b':
				b[w] = '\b'
				r++
				w++
			case 'f':
				b[w] = '\f'
				r++
				w++
			case 'n':
				b[w] = '\n'
				r++
				w++
			case 'r':
				b[w] = '\r'
				r++
				w++
			case 't':
				b[w] = '\t'
				r++
				w++
			case 'u':
				r--
				rune := getu4(s[r:])
				if rune < 0 {
					return
				}
				r += 6
				if utf16.IsSurrogate(rune) {
					rune1 := getu4(s[r:])
					if dec := utf16.DecodeRune(rune, rune1); dec != unicode.ReplacementChar {
						// A valid pair; consume.
						r += 6
						w += utf8.EncodeRune(b[w:], dec)
						break
					}
					// Invalid surrogate; fall back to replacement rune.
					rune = unicode.ReplacementChar
				}
				w += utf8.EncodeRune(b[w:], rune)
			}

		// Quote, control characters are invalid.
		case c == '"', c < ' ':
			return

		// ASCII
		case c < utf8.RuneSelf:
			b[w] = c
			r++
			w++

		// Coerce to well-formed UTF-8.
		default:
			rune, size := utf8.DecodeRune(s[r:])
			r += size
			w += utf8.EncodeRune(b[w:], rune)
		}
	}
	return b[0:w], true
}
Esempio n. 2
0
// unquote converts a quoted JSON string literal s into an actual string t.
// The rules are different than for Go, so cannot use strconv.Unquote.
func unquote(s []byte) (t string, ok bool) {
	if len(s) < 2 || s[0] != '"' || s[len(s)-1] != '"' {
		return
	}
	b := make([]byte, len(s)+2*utf8.UTFMax)
	w := 0
	for r := 1; r < len(s)-1; {
		// Out of room?  Can only happen if s is full of
		// malformed UTF-8 and we're replacing each
		// byte with RuneError.
		if w >= len(b)-2*utf8.UTFMax {
			nb := make([]byte, (len(b)+utf8.UTFMax)*2)
			copy(nb, b[0:w])
			b = nb
		}
		switch c := s[r]; {
		case c == '\\':
			r++
			if r >= len(s)-1 {
				return
			}
			switch s[r] {
			default:
				return
			case '"', '\\', '/', '\'':
				b[w] = s[r]
				r++
				w++
			case 'b':
				b[w] = '\b'
				r++
				w++
			case 'f':
				b[w] = '\f'
				r++
				w++
			case 'n':
				b[w] = '\n'
				r++
				w++
			case 'r':
				b[w] = '\r'
				r++
				w++
			case 't':
				b[w] = '\t'
				r++
				w++
			case 'u':
				r--
				rune := getu4(s[r:])
				if rune < 0 {
					return
				}
				r += 6
				if utf16.IsSurrogate(rune) {
					rune1 := getu4(s[r:])
					if dec := utf16.DecodeRune(rune, rune1); dec != unicode.ReplacementChar {
						// A valid pair; consume.
						r += 6
						w += utf8.EncodeRune(dec, b[w:])
						break
					}
					// Invalid surrogate; fall back to replacement rune.
					rune = unicode.ReplacementChar
				}
				w += utf8.EncodeRune(rune, b[w:])
			}

		// Quote, control characters are invalid.
		case c == '"', c < ' ':
			return

		// ASCII
		case c < utf8.RuneSelf:
			b[w] = c
			r++
			w++

		// Coerce to well-formed UTF-8.
		default:
			rune, size := utf8.DecodeRune(s[r:])
			r += size
			w += utf8.EncodeRune(rune, b[w:])
		}
	}
	return string(b[0:w]), true
}