protocol/triple/common_low_version.go

//go:build !go1.19
// +build !go1.19

/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

package triple

import (
	"net/url"
	"path"
	"strings"
)

func joinProcedure(interfaceName, methodName string) string {
	procedure, _ := joinPath("", interfaceName, methodName)
	return "/" + procedure
}

func joinPath(base string, elem ...string) (result string, err error) {
	u, err := url.Parse(base)
	if err != nil {
		return
	}

	result = joinPathFunc(u, elem...).String()
	return
}

// ---------- For golang version lower than go 1.19 ----------
// The code below is copied from go 1.19. Add Func suffix to tell the difference easily.

const upperhex = "0123456789ABCDEF"

type encoding int

const (
	encodePath encoding = 1 + iota
	encodePathSegment
	encodeHost
	encodeZone
	encodeUserPassword
	encodeQueryComponent
	encodeFragment
)

func isHexFunc(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 unHexFunc(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
}

func shouldEscapeFunc(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 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 three as well. That leaves only ? to escape.
			return c == '?'

		case encodePathSegment: // §3.3
			// The RFC allows : @ & = + $ but saves / ; , for assigning
			// meaning to individual path segments.
			return c == '/' || c == ';' || c == ',' || c == '?'

		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

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

	if mode == encodeFragment {
		// RFC 3986 §2.2 allows not escaping sub-delims. A subset of sub-delims are
		// included in reserved from RFC 2396 §2.2. The remaining sub-delims do not
		// need to be escaped. To minimize potential breakage, we apply two restrictions:
		// (1) we always escape sub-delims outside of the fragment, and (2) we always
		// escape single quote to avoid breaking callers that had previously assumed that
		// single quotes would be escaped. See issue #19917.
		switch c {
		case '!', '(', ')', '*':
			return false
		}
	}

	// Everything else must be escaped.
	return true
}

func joinPathFunc(u *url.URL, elem ...string) *url.URL {
	elem = append([]string{u.EscapedPath()}, elem...)
	var p string
	if !strings.HasPrefix(elem[0], "/") {
		// Return a relative path if u is relative,
		// but ensure that it contains no ../ elements.
		elem[0] = "/" + elem[0]
		p = path.Join(elem...)[1:]
	} else {
		p = path.Join(elem...)
	}
	// path.Join will remove any trailing slashes.
	// Preserve at least one.
	if strings.HasSuffix(elem[len(elem)-1], "/") && !strings.HasSuffix(p, "/") {
		p += "/"
	}
	newURL := *u
	setPathFunc(&newURL, p)
	return &newURL
}

func setPathFunc(u *url.URL, p string) error {
	pathUnescape, err := unescapeFunc(p, encodePath)
	if err != nil {
		return err
	}
	u.Path = pathUnescape
	if pathEscape := escapeFunc(pathUnescape, encodePath); p == pathEscape {
		// Default encoding is fine.
		u.RawPath = ""
	} else {
		u.RawPath = p
	}
	return nil
}

func unescapeFunc(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) || !isHexFunc(s[i+1]) || !isHexFunc(s[i+2]) {
				s = s[i:]
				if len(s) > 3 {
					s = s[:3]
				}
				return "", url.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 && unHexFunc(s[i+1]) < 8 && s[i:i+3] != "%25" {
				return "", url.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 := unHexFunc(s[i+1])<<4 | unHexFunc(s[i+2])
				if s[i:i+3] != "%25" && v != ' ' && shouldEscapeFunc(v, encodeHost) {
					return "", url.EscapeError(s[i : i+3])
				}
			}
			i += 3
		case '+':
			hasPlus = mode == encodeQueryComponent
			i++
		default:
			if (mode == encodeHost || mode == encodeZone) && s[i] < 0x80 && shouldEscapeFunc(s[i], mode) {
				return "", url.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(unHexFunc(s[i+1])<<4 | unHexFunc(s[i+2]))
			i += 2
		case '+':
			if mode == encodeQueryComponent {
				t.WriteByte(' ')
			} else {
				t.WriteByte('+')
			}
		default:
			t.WriteByte(s[i])
		}
	}
	return t.String(), nil
}

func escapeFunc(s string, mode encoding) string {
	spaceCount, hexCount := 0, 0
	for i := 0; i < len(s); i++ {
		c := s[i]
		if shouldEscapeFunc(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)
		for i := 0; i < len(s); i++ {
			if s[i] == ' ' {
				t[i] = '+'
			}
		}
		return string(t)
	}

	j := 0
	for i := 0; i < len(s); i++ {
		switch c := s[i]; {
		case c == ' ' && mode == encodeQueryComponent:
			t[j] = '+'
			j++
		case shouldEscapeFunc(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)
}