350 lines
6.4 KiB
Go
350 lines
6.4 KiB
Go
package utils
|
|
|
|
import "unicode/utf8"
|
|
|
|
var htmlSafeSet = [utf8.RuneSelf]bool{
|
|
' ': true,
|
|
'!': true,
|
|
'"': false,
|
|
'#': true,
|
|
'$': true,
|
|
'%': true,
|
|
'&': false,
|
|
'\'': true,
|
|
'(': true,
|
|
')': true,
|
|
'*': true,
|
|
'+': true,
|
|
',': true,
|
|
'-': true,
|
|
'.': true,
|
|
'/': true,
|
|
'0': true,
|
|
'1': true,
|
|
'2': true,
|
|
'3': true,
|
|
'4': true,
|
|
'5': true,
|
|
'6': true,
|
|
'7': true,
|
|
'8': true,
|
|
'9': true,
|
|
':': true,
|
|
';': true,
|
|
'<': false,
|
|
'=': true,
|
|
'>': false,
|
|
'?': true,
|
|
'@': true,
|
|
'A': true,
|
|
'B': true,
|
|
'C': true,
|
|
'D': true,
|
|
'E': true,
|
|
'F': true,
|
|
'G': true,
|
|
'H': true,
|
|
'I': true,
|
|
'J': true,
|
|
'K': true,
|
|
'L': true,
|
|
'M': true,
|
|
'N': true,
|
|
'O': true,
|
|
'P': true,
|
|
'Q': true,
|
|
'R': true,
|
|
'S': true,
|
|
'T': true,
|
|
'U': true,
|
|
'V': true,
|
|
'W': true,
|
|
'X': true,
|
|
'Y': true,
|
|
'Z': true,
|
|
'[': true,
|
|
'\\': false,
|
|
']': true,
|
|
'^': true,
|
|
'_': true,
|
|
'`': true,
|
|
'a': true,
|
|
'b': true,
|
|
'c': true,
|
|
'd': true,
|
|
'e': true,
|
|
'f': true,
|
|
'g': true,
|
|
'h': true,
|
|
'i': true,
|
|
'j': true,
|
|
'k': true,
|
|
'l': true,
|
|
'm': true,
|
|
'n': true,
|
|
'o': true,
|
|
'p': true,
|
|
'q': true,
|
|
'r': true,
|
|
's': true,
|
|
't': true,
|
|
'u': true,
|
|
'v': true,
|
|
'w': true,
|
|
'x': true,
|
|
'y': true,
|
|
'z': true,
|
|
'{': true,
|
|
'|': true,
|
|
'}': true,
|
|
'~': true,
|
|
'\u007f': true,
|
|
}
|
|
|
|
var safeSet = [utf8.RuneSelf]bool{
|
|
' ': true,
|
|
'!': true,
|
|
'"': false,
|
|
'#': true,
|
|
'$': true,
|
|
'%': true,
|
|
'&': true,
|
|
'\'': true,
|
|
'(': true,
|
|
')': true,
|
|
'*': true,
|
|
'+': true,
|
|
',': true,
|
|
'-': true,
|
|
'.': true,
|
|
'/': true,
|
|
'0': true,
|
|
'1': true,
|
|
'2': true,
|
|
'3': true,
|
|
'4': true,
|
|
'5': true,
|
|
'6': true,
|
|
'7': true,
|
|
'8': true,
|
|
'9': true,
|
|
':': true,
|
|
';': true,
|
|
'<': true,
|
|
'=': true,
|
|
'>': true,
|
|
'?': true,
|
|
'@': true,
|
|
'A': true,
|
|
'B': true,
|
|
'C': true,
|
|
'D': true,
|
|
'E': true,
|
|
'F': true,
|
|
'G': true,
|
|
'H': true,
|
|
'I': true,
|
|
'J': true,
|
|
'K': true,
|
|
'L': true,
|
|
'M': true,
|
|
'N': true,
|
|
'O': true,
|
|
'P': true,
|
|
'Q': true,
|
|
'R': true,
|
|
'S': true,
|
|
'T': true,
|
|
'U': true,
|
|
'V': true,
|
|
'W': true,
|
|
'X': true,
|
|
'Y': true,
|
|
'Z': true,
|
|
'[': true,
|
|
'\\': false,
|
|
']': true,
|
|
'^': true,
|
|
'_': true,
|
|
'`': true,
|
|
'a': true,
|
|
'b': true,
|
|
'c': true,
|
|
'd': true,
|
|
'e': true,
|
|
'f': true,
|
|
'g': true,
|
|
'h': true,
|
|
'i': true,
|
|
'j': true,
|
|
'k': true,
|
|
'l': true,
|
|
'm': true,
|
|
'n': true,
|
|
'o': true,
|
|
'p': true,
|
|
'q': true,
|
|
'r': true,
|
|
's': true,
|
|
't': true,
|
|
'u': true,
|
|
'v': true,
|
|
'w': true,
|
|
'x': true,
|
|
'y': true,
|
|
'z': true,
|
|
'{': true,
|
|
'|': true,
|
|
'}': true,
|
|
'~': true,
|
|
'\u007f': true,
|
|
}
|
|
|
|
var hex = "0123456789abcdef"
|
|
|
|
func WriteStringSlowPathWithHTMLEscaped(buf *[]byte, i int, s string, valLen int) {
|
|
start := i
|
|
// for the remaining parts, we process them char by char
|
|
for i < valLen {
|
|
if b := s[i]; b < utf8.RuneSelf {
|
|
if htmlSafeSet[b] {
|
|
i++
|
|
continue
|
|
}
|
|
if start < i {
|
|
*buf = append(*buf, s[start:i]...)
|
|
}
|
|
switch b {
|
|
case '\\', '"':
|
|
*buf = append(*buf, '\\', b)
|
|
case '\n':
|
|
*buf = append(*buf, '\\', 'n')
|
|
case '\r':
|
|
*buf = append(*buf, '\\', 'r')
|
|
case '\t':
|
|
*buf = append(*buf, '\\', 't')
|
|
default:
|
|
*buf = append(*buf, `\u00`...)
|
|
*buf = append(*buf, hex[b>>4], hex[b&0xF])
|
|
}
|
|
i++
|
|
start = i
|
|
continue
|
|
}
|
|
c, size := utf8.DecodeRuneInString(s[i:])
|
|
if c == utf8.RuneError && size == 1 {
|
|
if start < i {
|
|
*buf = append(*buf, s[start:i]...)
|
|
}
|
|
*buf = append(*buf, `\ufffd`...)
|
|
i++
|
|
start = i
|
|
continue
|
|
}
|
|
|
|
if c == '\u2028' || c == '\u2029' {
|
|
if start < i {
|
|
*buf = append(*buf, s[start:i]...)
|
|
}
|
|
*buf = append(*buf, `\u202`...)
|
|
*buf = append(*buf, hex[c&0xF])
|
|
i += size
|
|
start = i
|
|
continue
|
|
}
|
|
i += size
|
|
}
|
|
if start < len(s) {
|
|
*buf = append(*buf, s[start:]...)
|
|
}
|
|
*buf = append(*buf, '"')
|
|
}
|
|
|
|
func WriteStringSlowPath(buf *[]byte, i int, s string, valLen int) {
|
|
start := i
|
|
for i < valLen {
|
|
if b := s[i]; b < utf8.RuneSelf {
|
|
if safeSet[b] {
|
|
i++
|
|
continue
|
|
}
|
|
if start < i {
|
|
*buf = append(*buf, s[start:i]...)
|
|
}
|
|
switch b {
|
|
case '\\', '"':
|
|
*buf = append(*buf, '\\', b)
|
|
case '\n':
|
|
*buf = append(*buf, '\\', 'n')
|
|
case '\r':
|
|
*buf = append(*buf, '\\', 'r')
|
|
case '\t':
|
|
*buf = append(*buf, '\\', 't')
|
|
default:
|
|
*buf = append(*buf, `\u00`...)
|
|
*buf = append(*buf, hex[b>>4], hex[b&0xF])
|
|
}
|
|
i++
|
|
start = i
|
|
continue
|
|
}
|
|
i++
|
|
continue
|
|
}
|
|
if start < len(s) {
|
|
*buf = append(*buf, s[start:]...)
|
|
}
|
|
*buf = append(*buf, '"')
|
|
}
|
|
|
|
const (
|
|
t1 = 0x00 // 0000 0000
|
|
tx = 0x80 // 1000 0000
|
|
t2 = 0xC0 // 1100 0000
|
|
t3 = 0xE0 // 1110 0000
|
|
t4 = 0xF0 // 1111 0000
|
|
t5 = 0xF8 // 1111 1000
|
|
|
|
maskx = 0x3F // 0011 1111
|
|
mask2 = 0x1F // 0001 1111
|
|
mask3 = 0x0F // 0000 1111
|
|
mask4 = 0x07 // 0000 0111
|
|
|
|
rune1Max = 1<<7 - 1
|
|
rune2Max = 1<<11 - 1
|
|
rune3Max = 1<<16 - 1
|
|
|
|
surrogateMin = 0xD800
|
|
surrogateMax = 0xDFFF
|
|
|
|
maxRune = '\U0010FFFF' // Maximum valid Unicode code point.
|
|
runeError = '\uFFFD' // the "error" Rune or "Unicode replacement character"
|
|
)
|
|
|
|
func AppendRune(p []byte, r rune) []byte {
|
|
// Negative values are erroneous. Making it unsigned addresses the problem.
|
|
switch i := uint32(r); {
|
|
case i <= rune1Max:
|
|
p = append(p, byte(r))
|
|
return p
|
|
case i <= rune2Max:
|
|
p = append(p, t2|byte(r>>6))
|
|
p = append(p, tx|byte(r)&maskx)
|
|
return p
|
|
case i > maxRune, surrogateMin <= i && i <= surrogateMax:
|
|
r = runeError
|
|
fallthrough
|
|
case i <= rune3Max:
|
|
p = append(p, t3|byte(r>>12))
|
|
p = append(p, tx|byte(r>>6)&maskx)
|
|
p = append(p, tx|byte(r)&maskx)
|
|
return p
|
|
default:
|
|
p = append(p, t4|byte(r>>18))
|
|
p = append(p, tx|byte(r>>12)&maskx)
|
|
p = append(p, tx|byte(r>>6)&maskx)
|
|
p = append(p, tx|byte(r)&maskx)
|
|
return p
|
|
}
|
|
}
|