github.com/qiniu/x@v1.11.9/url/urlescape.go

package url

import (
	"strconv"
)

type Encoding int

const (
	EncodePath Encoding = 1 + iota
	EncodeUserPassword
	EncodeQueryComponent
	EncodeFragment
)

type EscapeError string

func (e EscapeError) Error() string {
	return "invalid URL escape " + strconv.Quote(string(e))
}

func ishex(c byte) bool {
	switch {
	case '0' <= c && c <= '9':
		return true
	case 'a' <= c && c <= 'f':
		return true
	case 'A' <= c && c <= 'F':
		return true
	}
	return false
}

func unhex(c byte) byte {
	switch {
	case '0' <= c && c <= '9':
		return c - '0'
	case 'a' <= c && c <= 'f':
		return c - 'a' + 10
	case 'A' <= c && c <= 'F':
		return c - 'A' + 10
	}
	return 0
}

// Return true if the specified character should be escaped when
// appearing in a URL string, according to RFC 3986.
// When 'all' is true the full range of reserved characters are matched.
func shouldEscape(c byte, mode Encoding) bool {
	// §2.3 Unreserved characters (alphanum)
	if 'A' <= c && c <= 'Z' || 'a' <= c && c <= 'z' || '0' <= c && c <= '9' {
		return false
	}

	switch c {
	case '-', '_', '.', '~': // §2.3 Unreserved characters (mark)
		return false

	case '$', '&', '+', ',', '/', ':', ';', '=', '?', '@': // §2.2 Reserved characters (reserved)
		// Different sections of the URL allow a few of
		// the reserved characters to appear unescaped.
		switch mode {
		case EncodePath: // §3.3
			// The RFC allows : @ & = + $ but saves / ; , for assigning
			// meaning to individual path segments. This package
			// only manipulates the path as a whole, so we allow those
			// last two as well. That leaves only ? to escape.
			return c == '?'

		case EncodeUserPassword: // §3.2.2
			// The RFC allows ; : & = + $ , in userinfo, so we must escape only @ and /.
			// The parsing of userinfo treats : as special so we must escape that too.
			return c == '@' || c == '/' || c == ':'

		case EncodeQueryComponent: // §3.4
			// The RFC reserves (so we must escape) everything.
			return true

		case EncodeFragment: // §4.1
			// The RFC text is silent but the grammar allows
			// everything, so escape nothing.
			return false
		}
	}

	// Everything else must be escaped.
	return true
}

// QueryUnescape does the inverse transformation of QueryEscape, converting
// %AB into the byte 0xAB and '+' into ' ' (space). It returns an error if
// any % is not followed by two hexadecimal digits.
func QueryUnescape(s string) (string, error) {
	return UnescapeEx(s, EncodeQueryComponent)
}

func Unescape(s string) (string, error) {
	return UnescapeEx(s, EncodePath)
}

// UnescapeEx unescapes a string; the mode specifies
// which section of the URL string is being unescaped.
func UnescapeEx(s string, mode Encoding) (string, error) {
	// Count %, check that they're well-formed.
	n := 0
	hasPlus := false
	for i := 0; i < len(s); {
		switch s[i] {
		case '%':
			n++
			if i+2 >= len(s) || !ishex(s[i+1]) || !ishex(s[i+2]) {
				s = s[i:]
				if len(s) > 3 {
					s = s[0:3]
				}
				return "", EscapeError(s)
			}
			i += 3
		case '+':
			hasPlus = mode == EncodeQueryComponent
			i++
		default:
			i++
		}
	}

	if n == 0 && !hasPlus {
		return s, nil
	}

	t := make([]byte, len(s)-2*n)
	j := 0
	for i := 0; i < len(s); {
		switch s[i] {
		case '%':
			t[j] = unhex(s[i+1])<<4 | unhex(s[i+2])
			j++
			i += 3
		case '+':
			if mode == EncodeQueryComponent {
				t[j] = ' '
			} else {
				t[j] = '+'
			}
			j++
			i++
		default:
			t[j] = s[i]
			j++
			i++
		}
	}
	return string(t), nil
}

// QueryEscape escapes the string so it can be safely placed
// inside a URL query.
func QueryEscape(s string) string {
	return EscapeEx(s, EncodeQueryComponent)
}

func Escape(s string) string {
	return EscapeEx(s, EncodePath)
}

func EscapeEx(s string, mode Encoding) string {
	spaceCount, hexCount := 0, 0
	for i := 0; i < len(s); i++ {
		c := s[i]
		if shouldEscape(c, mode) {
			if c == ' ' && mode == EncodeQueryComponent {
				spaceCount++
			} else {
				hexCount++
			}
		}
	}

	if spaceCount == 0 && hexCount == 0 {
		return s
	}

	t := make([]byte, len(s)+2*hexCount)
	j := 0
	for i := 0; i < len(s); i++ {
		switch c := s[i]; {
		case c == ' ' && mode == EncodeQueryComponent:
			t[j] = '+'
			j++
		case shouldEscape(c, mode):
			t[j] = '%'
			t[j+1] = "0123456789ABCDEF"[c>>4]
			t[j+2] = "0123456789ABCDEF"[c&15]
			j += 3
		default:
			t[j] = s[i]
			j++
		}
	}
	return string(t)
}