123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230 |
- package sip
- import (
- "strconv"
- "strings"
- )
- // Copyright 2009 The Go Authors. All rights reserved.
- // This is actually shorten copy of escape/unescape helpers of the net/url package.
- type encoding int
- const (
- EncodeUserPassword encoding = 1 + iota
- EncodeHost
- EncodeZone
- EncodeQueryComponent
- )
- type EscapeError string
- func (e EscapeError) Error() string {
- return "invalid URL escape " + strconv.Quote(string(e))
- }
- type InvalidHostError string
- func (e InvalidHostError) Error() string {
- return "invalid character " + strconv.Quote(string(e)) + " in host name"
- }
- // unescape unescapes a string; the mode specifies
- // which section of the URL string is being unescaped.
- func Unescape(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[:3]
- }
- return "", EscapeError(s)
- }
- // Per https://tools.ietf.org/html/rfc3986#page-21
- // in the host component %-encoding can only be used
- // for non-ASCII bytes.
- // But https://tools.ietf.org/html/rfc6874#section-2
- // introduces %25 being allowed to escape a percent sign
- // in IPv6 scoped-address literals. Yay.
- if mode == EncodeHost && unhex(s[i+1]) < 8 && s[i:i+3] != "%25" {
- return "", EscapeError(s[i : i+3])
- }
- if mode == EncodeZone {
- // RFC 6874 says basically "anything goes" for zone identifiers
- // and that even non-ASCII can be redundantly escaped,
- // but it seems prudent to restrict %-escaped bytes here to those
- // that are valid host name bytes in their unescaped form.
- // That is, you can use escaping in the zone identifier but not
- // to introduce bytes you couldn't just write directly.
- // But Windows puts spaces here! Yay.
- v := unhex(s[i+1])<<4 | unhex(s[i+2])
- if s[i:i+3] != "%25" && v != ' ' && shouldEscape(v, EncodeHost) {
- return "", EscapeError(s[i : i+3])
- }
- }
- i += 3
- case '+':
- hasPlus = mode == EncodeQueryComponent
- i++
- default:
- if (mode == EncodeHost || mode == EncodeZone) && s[i] < 0x80 && shouldEscape(s[i], mode) {
- return "", InvalidHostError(s[i : i+1])
- }
- i++
- }
- }
- if n == 0 && !hasPlus {
- return s, nil
- }
- var t strings.Builder
- t.Grow(len(s) - 2*n)
- for i := 0; i < len(s); i++ {
- switch s[i] {
- case '%':
- t.WriteByte(unhex(s[i+1])<<4 | unhex(s[i+2]))
- i += 2
- case '+':
- t.WriteByte('+')
- default:
- t.WriteByte(s[i])
- }
- }
- return t.String(), nil
- }
- 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.
- //
- // Please be informed that for now shouldEscape does not check all
- // reserved characters correctly. See golang.org/issue/5684.
- 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
- }
- if mode == EncodeHost || mode == EncodeZone {
- // §3.2.2 Host allows
- // sub-delims = "!" / "$" / "&" / "'" / "(" / ")" / "*" / "+" / "," / ";" / "="
- // as part of reg-name.
- // We add : because we include :port as part of host.
- // We add [ ] because we include [ipv6]:port as part of host.
- // We add < > because they're the only characters left that
- // we could possibly allow, and Parse will reject them if we
- // escape them (because hosts can't use %-encoding for
- // ASCII bytes).
- switch c {
- case '!', '$', '&', '\'', '(', ')', '*', '+', ',', ';', '=', ':', '[', ']', '<', '>', '"':
- return false
- }
- }
- switch c {
- case '-', '_', '.', '~': // §2.3 Unreserved characters (mark)
- return false
- case '$', '&', '+', ',', '/', ':', ';', '=', '?', '@': // §2.2 Reserved characters (reserved)
- // Different sections of the URL allow a few of
- // the reserved characters to appear unescaped.
- switch mode {
- case EncodeUserPassword: // §3.2.1
- // The RFC allows ';', ':', '&', '=', '+', '$', and ',' 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 == '?' || c == ':'
- case EncodeQueryComponent: // §3.4
- // The RFC reserves (so we must escape) everything.
- return true
- }
- }
- // Everything else must be escaped.
- return true
- }
- const upperhex = "0123456789ABCDEF"
- func Escape(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
- }
- var buf [64]byte
- var t []byte
- required := len(s) + 2*hexCount
- if required <= len(buf) {
- t = buf[:required]
- } else {
- t = make([]byte, required)
- }
- if hexCount == 0 {
- copy(t, s)
- return string(t)
- }
- j := 0
- for i := 0; i < len(s); i++ {
- switch c := s[i]; {
- case c == ' ' && mode == EncodeQueryComponent:
- t[j] = c
- j++
- case shouldEscape(c, mode):
- t[j] = '%'
- t[j+1] = upperhex[c>>4]
- t[j+2] = upperhex[c&15]
- j += 3
- default:
- t[j] = s[i]
- j++
- }
- }
- return string(t)
- }
|