blob: c93def0bd77487c8cc74748e6ca5e0b876a6aff8 [file] [log] [blame]
// Copyright 2009 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
// Package url parses URLs and implements query escaping.
package url
// See RFC 3986. This package generally follows RFC 3986, except where
// it deviates for compatibility reasons. When sending changes, first
// search old issues for history on decisions. Unit tests should also
// contain references to issue numbers with details.
import (
"errors"
"fmt"
"sort"
"strconv"
"strings"
)
// Error reports an error and the operation and URL that caused it.
type Error struct {
Op string
URL string
Err error
}
func (e *Error) Unwrap() error { return e.Err }
func (e *Error) Error() string { return fmt.Sprintf("%s %q: %s", e.Op, e.URL, e.Err) }
func (e *Error) Timeout() bool {
t, ok := e.Err.(interface {
Timeout() bool
})
return ok && t.Timeout()
}
func (e *Error) Temporary() bool {
t, ok := e.Err.(interface {
Temporary() bool
})
return ok && t.Temporary()
}
const upperhex = "0123456789ABCDEF"
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
}
type encoding int
const (
encodePath encoding = 1 + iota
encodePathSegment
encodeHost
encodeZone
encodeUserPassword
encodeQueryComponent
encodeFragment
)
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"
}
// 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 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
}
// QueryUnescape does the inverse transformation of QueryEscape,
// converting each 3-byte encoded substring of the form "%AB" into the
// hex-decoded byte 0xAB.
// It returns an error if any % is not followed by two hexadecimal
// digits.
func QueryUnescape(s string) (string, error) {
return unescape(s, encodeQueryComponent)
}
// PathUnescape does the inverse transformation of PathEscape,
// converting each 3-byte encoded substring of the form "%AB" into the
// hex-decoded byte 0xAB. It returns an error if any % is not followed
// by two hexadecimal digits.
//
// PathUnescape is identical to QueryUnescape except that it does not
// unescape '+' to ' ' (space).
func PathUnescape(s string) (string, error) {
return unescape(s, encodePathSegment)
}
// 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 '+':
if mode == encodeQueryComponent {
t.WriteByte(' ')
} else {
t.WriteByte('+')
}
default:
t.WriteByte(s[i])
}
}
return t.String(), nil
}
// QueryEscape escapes the string so it can be safely placed
// inside a URL query.
func QueryEscape(s string) string {
return escape(s, encodeQueryComponent)
}
// PathEscape escapes the string so it can be safely placed inside a URL path segment,
// replacing special characters (including /) with %XX sequences as needed.
func PathEscape(s string) string {
return escape(s, encodePathSegment)
}
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)
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 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)
}
// A URL represents a parsed URL (technically, a URI reference).
//
// The general form represented is:
//
// [scheme:][//[userinfo@]host][/]path[?query][#fragment]
//
// URLs that do not start with a slash after the scheme are interpreted as:
//
// scheme:opaque[?query][#fragment]
//
// Note that the Path field is stored in decoded form: /%47%6f%2f becomes /Go/.
// A consequence is that it is impossible to tell which slashes in the Path were
// slashes in the raw URL and which were %2f. This distinction is rarely important,
// but when it is, the code should use RawPath, an optional field which only gets
// set if the default encoding is different from Path.
//
// URL's String method uses the EscapedPath method to obtain the path. See the
// EscapedPath method for more details.
type URL struct {
Scheme string
Opaque string // encoded opaque data
User *Userinfo // username and password information
Host string // host or host:port
Path string // path (relative paths may omit leading slash)
RawPath string // encoded path hint (see EscapedPath method)
ForceQuery bool // append a query ('?') even if RawQuery is empty
RawQuery string // encoded query values, without '?'
Fragment string // fragment for references, without '#'
RawFragment string // encoded fragment hint (see EscapedFragment method)
}
// User returns a Userinfo containing the provided username
// and no password set.
func User(username string) *Userinfo {
return &Userinfo{username, "", false}
}
// UserPassword returns a Userinfo containing the provided username
// and password.
//
// This functionality should only be used with legacy web sites.
// RFC 2396 warns that interpreting Userinfo this way
// ``is NOT RECOMMENDED, because the passing of authentication
// information in clear text (such as URI) has proven to be a
// security risk in almost every case where it has been used.''
func UserPassword(username, password string) *Userinfo {
return &Userinfo{username, password, true}
}
// The Userinfo type is an immutable encapsulation of username and
// password details for a URL. An existing Userinfo value is guaranteed
// to have a username set (potentially empty, as allowed by RFC 2396),
// and optionally a password.
type Userinfo struct {
username string
password string
passwordSet bool
}
// Username returns the username.
func (u *Userinfo) Username() string {
if u == nil {
return ""
}
return u.username
}
// Password returns the password in case it is set, and whether it is set.
func (u *Userinfo) Password() (string, bool) {
if u == nil {
return "", false
}
return u.password, u.passwordSet
}
// String returns the encoded userinfo information in the standard form
// of "username[:password]".
func (u *Userinfo) String() string {
if u == nil {
return ""
}
s := escape(u.username, encodeUserPassword)
if u.passwordSet {
s += ":" + escape(u.password, encodeUserPassword)
}
return s
}
// Maybe rawurl is of the form scheme:path.
// (Scheme must be [a-zA-Z][a-zA-Z0-9+-.]*)
// If so, return scheme, path; else return "", rawurl.
func getscheme(rawurl string) (scheme, path string, err error) {
for i := 0; i < len(rawurl); i++ {
c := rawurl[i]
switch {
case 'a' <= c && c <= 'z' || 'A' <= c && c <= 'Z':
// do nothing
case '0' <= c && c <= '9' || c == '+' || c == '-' || c == '.':
if i == 0 {
return "", rawurl, nil
}
case c == ':':
if i == 0 {
return "", "", errors.New("missing protocol scheme")
}
return rawurl[:i], rawurl[i+1:], nil
default:
// we have encountered an invalid character,
// so there is no valid scheme
return "", rawurl, nil
}
}
return "", rawurl, nil
}
// split slices s into two substrings separated by the first occurrence of
// sep. If cutc is true then sep is excluded from the second substring.
// If sep does not occur in s then s and the empty string is returned.
func split(s string, sep byte, cutc bool) (string, string) {
i := strings.IndexByte(s, sep)
if i < 0 {
return s, ""
}
if cutc {
return s[:i], s[i+1:]
}
return s[:i], s[i:]
}
// Parse parses rawurl into a URL structure.
//
// The rawurl may be relative (a path, without a host) or absolute
// (starting with a scheme). Trying to parse a hostname and path
// without a scheme is invalid but may not necessarily return an
// error, due to parsing ambiguities.
func Parse(rawurl string) (*URL, error) {
// Cut off #frag
u, frag := split(rawurl, '#', true)
url, err := parse(u, false)
if err != nil {
return nil, &Error{"parse", u, err}
}
if frag == "" {
return url, nil
}
if err = url.setFragment(frag); err != nil {
return nil, &Error{"parse", rawurl, err}
}
return url, nil
}
// ParseRequestURI parses rawurl into a URL structure. It assumes that
// rawurl was received in an HTTP request, so the rawurl is interpreted
// only as an absolute URI or an absolute path.
// The string rawurl is assumed not to have a #fragment suffix.
// (Web browsers strip #fragment before sending the URL to a web server.)
func ParseRequestURI(rawurl string) (*URL, error) {
url, err := parse(rawurl, true)
if err != nil {
return nil, &Error{"parse", rawurl, err}
}
return url, nil
}
// parse parses a URL from a string in one of two contexts. If
// viaRequest is true, the URL is assumed to have arrived via an HTTP request,
// in which case only absolute URLs or path-absolute relative URLs are allowed.
// If viaRequest is false, all forms of relative URLs are allowed.
func parse(rawurl string, viaRequest bool) (*URL, error) {
var rest string
var err error
if stringContainsCTLByte(rawurl) {
return nil, errors.New("net/url: invalid control character in URL")
}
if rawurl == "" && viaRequest {
return nil, errors.New("empty url")
}
url := new(URL)
if rawurl == "*" {
url.Path = "*"
return url, nil
}
// Split off possible leading "http:", "mailto:", etc.
// Cannot contain escaped characters.
if url.Scheme, rest, err = getscheme(rawurl); err != nil {
return nil, err
}
url.Scheme = strings.ToLower(url.Scheme)
if strings.HasSuffix(rest, "?") && strings.Count(rest, "?") == 1 {
url.ForceQuery = true
rest = rest[:len(rest)-1]
} else {
rest, url.RawQuery = split(rest, '?', true)
}
if !strings.HasPrefix(rest, "/") {
if url.Scheme != "" {
// We consider rootless paths per RFC 3986 as opaque.
url.Opaque = rest
return url, nil
}
if viaRequest {
return nil, errors.New("invalid URI for request")
}
// Avoid confusion with malformed schemes, like cache_object:foo/bar.
// See golang.org/issue/16822.
//
// RFC 3986, §3.3:
// In addition, a URI reference (Section 4.1) may be a relative-path reference,
// in which case the first path segment cannot contain a colon (":") character.
colon := strings.Index(rest, ":")
slash := strings.Index(rest, "/")
if colon >= 0 && (slash < 0 || colon < slash) {
// First path segment has colon. Not allowed in relative URL.
return nil, errors.New("first path segment in URL cannot contain colon")
}
}
if (url.Scheme != "" || !viaRequest && !strings.HasPrefix(rest, "///")) && strings.HasPrefix(rest, "//") {
var authority string
authority, rest = split(rest[2:], '/', false)
url.User, url.Host, err = parseAuthority(authority)
if err != nil {
return nil, err
}
}
// Set Path and, optionally, RawPath.
// RawPath is a hint of the encoding of Path. We don't want to set it if
// the default escaping of Path is equivalent, to help make sure that people
// don't rely on it in general.
if err := url.setPath(rest); err != nil {
return nil, err
}
return url, nil
}
func parseAuthority(authority string) (user *Userinfo, host string, err error) {
i := strings.LastIndex(authority, "@")
if i < 0 {
host, err = parseHost(authority)
} else {
host, err = parseHost(authority[i+1:])
}
if err != nil {
return nil, "", err
}
if i < 0 {
return nil, host, nil
}
userinfo := authority[:i]
if !validUserinfo(userinfo) {
return nil, "", errors.New("net/url: invalid userinfo")
}
if !strings.Contains(userinfo, ":") {
if userinfo, err = unescape(userinfo, encodeUserPassword); err != nil {
return nil, "", err
}
user = User(userinfo)
} else {
username, password := split(userinfo, ':', true)
if username, err = unescape(username, encodeUserPassword); err != nil {
return nil, "", err
}
if password, err = unescape(password, encodeUserPassword); err != nil {
return nil, "", err
}
user = UserPassword(username, password)
}
return user, host, nil
}
// parseHost parses host as an authority without user
// information. That is, as host[:port].
func parseHost(host string) (string, error) {
if strings.HasPrefix(host, "[") {
// Parse an IP-Literal in RFC 3986 and RFC 6874.
// E.g., "[fe80::1]", "[fe80::1%25en0]", "[fe80::1]:80".
i := strings.LastIndex(host, "]")
if i < 0 {
return "", errors.New("missing ']' in host")
}
colonPort := host[i+1:]
if !validOptionalPort(colonPort) {
return "", fmt.Errorf("invalid port %q after host", colonPort)
}
// RFC 6874 defines that %25 (%-encoded percent) introduces
// the zone identifier, and the zone identifier can use basically
// any %-encoding it likes. That's different from the host, which
// can only %-encode non-ASCII bytes.
// We do impose some restrictions on the zone, to avoid stupidity
// like newlines.
zone := strings.Index(host[:i], "%25")
if zone >= 0 {
host1, err := unescape(host[:zone], encodeHost)
if err != nil {
return "", err
}
host2, err := unescape(host[zone:i], encodeZone)
if err != nil {
return "", err
}
host3, err := unescape(host[i:], encodeHost)
if err != nil {
return "", err
}
return host1 + host2 + host3, nil
}
} else if i := strings.LastIndex(host, ":"); i != -1 {
colonPort := host[i:]
if !validOptionalPort(colonPort) {
return "", fmt.Errorf("invalid port %q after host", colonPort)
}
}
var err error
if host, err = unescape(host, encodeHost); err != nil {
return "", err
}
return host, nil
}
// setPath sets the Path and RawPath fields of the URL based on the provided
// escaped path p. It maintains the invariant that RawPath is only specified
// when it differs from the default encoding of the path.
// For example:
// - setPath("/foo/bar") will set Path="/foo/bar" and RawPath=""
// - setPath("/foo%2fbar") will set Path="/foo/bar" and RawPath="/foo%2fbar"
// setPath will return an error only if the provided path contains an invalid
// escaping.
func (u *URL) setPath(p string) error {
path, err := unescape(p, encodePath)
if err != nil {
return err
}
u.Path = path
if escp := escape(path, encodePath); p == escp {
// Default encoding is fine.
u.RawPath = ""
} else {
u.RawPath = p
}
return nil
}
// EscapedPath returns the escaped form of u.Path.
// In general there are multiple possible escaped forms of any path.
// EscapedPath returns u.RawPath when it is a valid escaping of u.Path.
// Otherwise EscapedPath ignores u.RawPath and computes an escaped
// form on its own.
// The String and RequestURI methods use EscapedPath to construct
// their results.
// In general, code should call EscapedPath instead of
// reading u.RawPath directly.
func (u *URL) EscapedPath() string {
if u.RawPath != "" && validEncoded(u.RawPath, encodePath) {
p, err := unescape(u.RawPath, encodePath)
if err == nil && p == u.Path {
return u.RawPath
}
}
if u.Path == "*" {
return "*" // don't escape (Issue 11202)
}
return escape(u.Path, encodePath)
}
// validEncoded reports whether s is a valid encoded path or fragment,
// according to mode.
// It must not contain any bytes that require escaping during encoding.
func validEncoded(s string, mode encoding) bool {
for i := 0; i < len(s); i++ {
// RFC 3986, Appendix A.
// pchar = unreserved / pct-encoded / sub-delims / ":" / "@".
// shouldEscape is not quite compliant with the RFC,
// so we check the sub-delims ourselves and let
// shouldEscape handle the others.
switch s[i] {
case '!', '$', '&', '\'', '(', ')', '*', '+', ',', ';', '=', ':', '@':
// ok
case '[', ']':
// ok - not specified in RFC 3986 but left alone by modern browsers
case '%':
// ok - percent encoded, will decode
default:
if shouldEscape(s[i], mode) {
return false
}
}
}
return true
}
// setFragment is like setPath but for Fragment/RawFragment.
func (u *URL) setFragment(f string) error {
frag, err := unescape(f, encodeFragment)
if err != nil {
return err
}
u.Fragment = frag
if escf := escape(frag, encodeFragment); f == escf {
// Default encoding is fine.
u.RawFragment = ""
} else {
u.RawFragment = f
}
return nil
}
// EscapedFragment returns the escaped form of u.Fragment.
// In general there are multiple possible escaped forms of any fragment.
// EscapedFragment returns u.RawFragment when it is a valid escaping of u.Fragment.
// Otherwise EscapedFragment ignores u.RawFragment and computes an escaped
// form on its own.
// The String method uses EscapedFragment to construct its result.
// In general, code should call EscapedFragment instead of
// reading u.RawFragment directly.
func (u *URL) EscapedFragment() string {
if u.RawFragment != "" && validEncoded(u.RawFragment, encodeFragment) {
f, err := unescape(u.RawFragment, encodeFragment)
if err == nil && f == u.Fragment {
return u.RawFragment
}
}
return escape(u.Fragment, encodeFragment)
}
// validOptionalPort reports whether port is either an empty string
// or matches /^:\d*$/
func validOptionalPort(port string) bool {
if port == "" {
return true
}
if port[0] != ':' {
return false
}
for _, b := range port[1:] {
if b < '0' || b > '9' {
return false
}
}
return true
}
// String reassembles the URL into a valid URL string.
// The general form of the result is one of:
//
// scheme:opaque?query#fragment
// scheme://userinfo@host/path?query#fragment
//
// If u.Opaque is non-empty, String uses the first form;
// otherwise it uses the second form.
// Any non-ASCII characters in host are escaped.
// To obtain the path, String uses u.EscapedPath().
//
// In the second form, the following rules apply:
// - if u.Scheme is empty, scheme: is omitted.
// - if u.User is nil, userinfo@ is omitted.
// - if u.Host is empty, host/ is omitted.
// - if u.Scheme and u.Host are empty and u.User is nil,
// the entire scheme://userinfo@host/ is omitted.
// - if u.Host is non-empty and u.Path begins with a /,
// the form host/path does not add its own /.
// - if u.RawQuery is empty, ?query is omitted.
// - if u.Fragment is empty, #fragment is omitted.
func (u *URL) String() string {
var buf strings.Builder
if u.Scheme != "" {
buf.WriteString(u.Scheme)
buf.WriteByte(':')
}
if u.Opaque != "" {
buf.WriteString(u.Opaque)
} else {
if u.Scheme != "" || u.Host != "" || u.User != nil {
if u.Host != "" || u.Path != "" || u.User != nil {
buf.WriteString("//")
}
if ui := u.User; ui != nil {
buf.WriteString(ui.String())
buf.WriteByte('@')
}
if h := u.Host; h != "" {
buf.WriteString(escape(h, encodeHost))
}
}
path := u.EscapedPath()
if path != "" && path[0] != '/' && u.Host != "" {
buf.WriteByte('/')
}
if buf.Len() == 0 {
// RFC 3986 §4.2
// A path segment that contains a colon character (e.g., "this:that")
// cannot be used as the first segment of a relative-path reference, as
// it would be mistaken for a scheme name. Such a segment must be
// preceded by a dot-segment (e.g., "./this:that") to make a relative-
// path reference.
if i := strings.IndexByte(path, ':'); i > -1 && strings.IndexByte(path[:i], '/') == -1 {
buf.WriteString("./")
}
}
buf.WriteString(path)
}
if u.ForceQuery || u.RawQuery != "" {
buf.WriteByte('?')
buf.WriteString(u.RawQuery)
}
if u.Fragment != "" {
buf.WriteByte('#')
buf.WriteString(u.EscapedFragment())
}
return buf.String()
}
// Redacted is like String but replaces any password with "xxxxx".
// Only the password in u.URL is redacted.
func (u *URL) Redacted() string {
if u == nil {
return ""
}
ru := *u
if _, has := ru.User.Password(); has {
ru.User = UserPassword(ru.User.Username(), "xxxxx")
}
return ru.String()
}
// Values maps a string key to a list of values.
// It is typically used for query parameters and form values.
// Unlike in the http.Header map, the keys in a Values map
// are case-sensitive.
type Values map[string][]string
// Get gets the first value associated with the given key.
// If there are no values associated with the key, Get returns
// the empty string. To access multiple values, use the map
// directly.
func (v Values) Get(key string) string {
if v == nil {
return ""
}
vs := v[key]
if len(vs) == 0 {
return ""
}
return vs[0]
}
// Set sets the key to value. It replaces any existing
// values.
func (v Values) Set(key, value string) {
v[key] = []string{value}
}
// Add adds the value to key. It appends to any existing
// values associated with key.
func (v Values) Add(key, value string) {
v[key] = append(v[key], value)
}
// Del deletes the values associated with key.
func (v Values) Del(key string) {
delete(v, key)
}
// ParseQuery parses the URL-encoded query string and returns
// a map listing the values specified for each key.
// ParseQuery always returns a non-nil map containing all the
// valid query parameters found; err describes the first decoding error
// encountered, if any.
//
// Query is expected to be a list of key=value settings separated by
// ampersands or semicolons. A setting without an equals sign is
// interpreted as a key set to an empty value.
func ParseQuery(query string) (Values, error) {
m := make(Values)
err := parseQuery(m, query)
return m, err
}
func parseQuery(m Values, query string) (err error) {
for query != "" {
key := query
if i := strings.IndexAny(key, "&;"); i >= 0 {
key, query = key[:i], key[i+1:]
} else {
query = ""
}
if key == "" {
continue
}
value := ""
if i := strings.Index(key, "="); i >= 0 {
key, value = key[:i], key[i+1:]
}
key, err1 := QueryUnescape(key)
if err1 != nil {
if err == nil {
err = err1
}
continue
}
value, err1 = QueryUnescape(value)
if err1 != nil {
if err == nil {
err = err1
}
continue
}
m[key] = append(m[key], value)
}
return err
}
// Encode encodes the values into ``URL encoded'' form
// ("bar=baz&foo=quux") sorted by key.
func (v Values) Encode() string {
if v == nil {
return ""
}
var buf strings.Builder
keys := make([]string, 0, len(v))
for k := range v {
keys = append(keys, k)
}
sort.Strings(keys)
for _, k := range keys {
vs := v[k]
keyEscaped := QueryEscape(k)
for _, v := range vs {
if buf.Len() > 0 {
buf.WriteByte('&')
}
buf.WriteString(keyEscaped)
buf.WriteByte('=')
buf.WriteString(QueryEscape(v))
}
}
return buf.String()
}
// resolvePath applies special path segments from refs and applies
// them to base, per RFC 3986.
func resolvePath(base, ref string) string {
var full string
if ref == "" {
full = base
} else if ref[0] != '/' {
i := strings.LastIndex(base, "/")
full = base[:i+1] + ref
} else {
full = ref
}
if full == "" {
return ""
}
src := strings.Split(full, "/")
dst := make([]string, 0, len(src))
for _, elem := range src {
switch elem {
case ".":
// drop
case "..":
if len(dst) > 0 {
dst = dst[:len(dst)-1]
}
default:
dst = append(dst, elem)
}
}
if last := src[len(src)-1]; last == "." || last == ".." {
// Add final slash to the joined path.
dst = append(dst, "")
}
return "/" + strings.TrimPrefix(strings.Join(dst, "/"), "/")
}
// IsAbs reports whether the URL is absolute.
// Absolute means that it has a non-empty scheme.
func (u *URL) IsAbs() bool {
return u.Scheme != ""
}
// Parse parses a URL in the context of the receiver. The provided URL
// may be relative or absolute. Parse returns nil, err on parse
// failure, otherwise its return value is the same as ResolveReference.
func (u *URL) Parse(ref string) (*URL, error) {
refurl, err := Parse(ref)
if err != nil {
return nil, err
}
return u.ResolveReference(refurl), nil
}
// ResolveReference resolves a URI reference to an absolute URI from
// an absolute base URI u, per RFC 3986 Section 5.2. The URI reference
// may be relative or absolute. ResolveReference always returns a new
// URL instance, even if the returned URL is identical to either the
// base or reference. If ref is an absolute URL, then ResolveReference
// ignores base and returns a copy of ref.
func (u *URL) ResolveReference(ref *URL) *URL {
url := *ref
if ref.Scheme == "" {
url.Scheme = u.Scheme
}
if ref.Scheme != "" || ref.Host != "" || ref.User != nil {
// The "absoluteURI" or "net_path" cases.
// We can ignore the error from setPath since we know we provided a
// validly-escaped path.
url.setPath(resolvePath(ref.EscapedPath(), ""))
return &url
}
if ref.Opaque != "" {
url.User = nil
url.Host = ""
url.Path = ""
return &url
}
if ref.Path == "" && ref.RawQuery == "" {
url.RawQuery = u.RawQuery
if ref.Fragment == "" {
url.Fragment = u.Fragment
url.RawFragment = u.RawFragment
}
}
// The "abs_path" or "rel_path" cases.
url.Host = u.Host
url.User = u.User
url.setPath(resolvePath(u.EscapedPath(), ref.EscapedPath()))
return &url
}
// Query parses RawQuery and returns the corresponding values.
// It silently discards malformed value pairs.
// To check errors use ParseQuery.
func (u *URL) Query() Values {
v, _ := ParseQuery(u.RawQuery)
return v
}
// RequestURI returns the encoded path?query or opaque?query
// string that would be used in an HTTP request for u.
func (u *URL) RequestURI() string {
result := u.Opaque
if result == "" {
result = u.EscapedPath()
if result == "" {
result = "/"
}
} else {
if strings.HasPrefix(result, "//") {
result = u.Scheme + ":" + result
}
}
if u.ForceQuery || u.RawQuery != "" {
result += "?" + u.RawQuery
}
return result
}
// Hostname returns u.Host, stripping any valid port number if present.
//
// If the result is enclosed in square brackets, as literal IPv6 addresses are,
// the square brackets are removed from the result.
func (u *URL) Hostname() string {
host, _ := splitHostPort(u.Host)
return host
}
// Port returns the port part of u.Host, without the leading colon.
//
// If u.Host doesn't contain a valid numeric port, Port returns an empty string.
func (u *URL) Port() string {
_, port := splitHostPort(u.Host)
return port
}
// splitHostPort separates host and port. If the port is not valid, it returns
// the entire input as host, and it doesn't check the validity of the host.
// Unlike net.SplitHostPort, but per RFC 3986, it requires ports to be numeric.
func splitHostPort(hostport string) (host, port string) {
host = hostport
colon := strings.LastIndexByte(host, ':')
if colon != -1 && validOptionalPort(host[colon:]) {
host, port = host[:colon], host[colon+1:]
}
if strings.HasPrefix(host, "[") && strings.HasSuffix(host, "]") {
host = host[1 : len(host)-1]
}
return
}
// Marshaling interface implementations.
// Would like to implement MarshalText/UnmarshalText but that will change the JSON representation of URLs.
func (u *URL) MarshalBinary() (text []byte, err error) {
return []byte(u.String()), nil
}
func (u *URL) UnmarshalBinary(text []byte) error {
u1, err := Parse(string(text))
if err != nil {
return err
}
*u = *u1
return nil
}
// validUserinfo reports whether s is a valid userinfo string per RFC 3986
// Section 3.2.1:
// userinfo = *( unreserved / pct-encoded / sub-delims / ":" )
// unreserved = ALPHA / DIGIT / "-" / "." / "_" / "~"
// sub-delims = "!" / "$" / "&" / "'" / "(" / ")"
// / "*" / "+" / "," / ";" / "="
//
// It doesn't validate pct-encoded. The caller does that via func unescape.
func validUserinfo(s string) bool {
for _, r := range s {
if 'A' <= r && r <= 'Z' {
continue
}
if 'a' <= r && r <= 'z' {
continue
}
if '0' <= r && r <= '9' {
continue
}
switch r {
case '-', '.', '_', ':', '~', '!', '$', '&', '\'',
'(', ')', '*', '+', ',', ';', '=', '%', '@':
continue
default:
return false
}
}
return true
}
// stringContainsCTLByte reports whether s contains any ASCII control character.
func stringContainsCTLByte(s string) bool {
for i := 0; i < len(s); i++ {
b := s[i]
if b < ' ' || b == 0x7f {
return true
}
}
return false
}