You are viewing a plain text version of this content. The canonical link for it is here.
Posted to notifications@dubbo.apache.org by GitBox <gi...@apache.org> on 2020/09/22 10:14:45 UTC
[GitHub] [dubbo-go] IndiraFinish opened a new pull request #773: 【optimize】replace go/net/ul
IndiraFinish opened a new pull request #773:
URL: https://github.com/apache/dubbo-go/pull/773
根据[#769](https://github.com/apache/dubbo-go/pull/769)的讨论，替换`go/net/url`为`common/net/url`。
```
// Set sets the key to value.
// If value is not "", it will replaces existing values.
func (v Values) Set(key, value string) {
if len(value) == 0 {
return
}
v[key] = []string{value}
}
// Add adds the value to key. If value is not "", it appends to existing
// values associated with key.
func (v Values) Add(key, value string) {
if len(value) == 0 {
return
}
v[key] = append(v[key], value)
}
```
Values的Set方法替换为value 是非空字符串时才能替换old value
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: notifications-unsubscribe@dubbo.apache.org
For additional commands, e-mail: notifications-help@dubbo.apache.org
[GitHub] [dubbo-go] zouyx commented on a change in pull request #773: 【optimize】replace go/net/url
Posted by GitBox <gi...@apache.org>.
zouyx commented on a change in pull request #773:
URL: https://github.com/apache/dubbo-go/pull/773#discussion_r493984885
##########
File path: common/net/url/url.go
##########
@@ -0,0 +1,1161 @@
+/*
+ * 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 url parses URLs and implements query escaping.
+package url
+
+// This package is an extension of the GO SDK
+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 {
Review comment:
Can not extends net/URL？
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: notifications-unsubscribe@dubbo.apache.org
For additional commands, e-mail: notifications-help@dubbo.apache.org
[GitHub] [dubbo-go] IndiraFinish commented on pull request #773: 【optimize】replace go/net/url
Posted by GitBox <gi...@apache.org>.
IndiraFinish commented on pull request #773:
URL: https://github.com/apache/dubbo-go/pull/773#issuecomment-699405758
I'm sorry @watermelo,I didn't bring my computer today
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: notifications-unsubscribe@dubbo.apache.org
For additional commands, e-mail: notifications-help@dubbo.apache.org
[GitHub] [dubbo-go] AlexStocks commented on a change in pull request #773: 【optimize】replace go/net/url
Posted by GitBox <gi...@apache.org>.
AlexStocks commented on a change in pull request #773:
URL: https://github.com/apache/dubbo-go/pull/773#discussion_r492676187
##########
File path: common/url.go
##########
@@ -20,9 +20,9 @@ package common
import (
"encoding/base64"
"fmt"
+ "github.com/apache/dubbo-go/common/net/url"
Review comment:
move this package to the third import block
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: notifications-unsubscribe@dubbo.apache.org
For additional commands, e-mail: notifications-help@dubbo.apache.org
[GitHub] [dubbo-go] IndiraFinish commented on pull request #773: 【optimize】replace go/net/url
Posted by GitBox <gi...@apache.org>.
IndiraFinish commented on pull request #773:
URL: https://github.com/apache/dubbo-go/pull/773#issuecomment-697149861
ok @zouyx
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: notifications-unsubscribe@dubbo.apache.org
For additional commands, e-mail: notifications-help@dubbo.apache.org
[GitHub] [dubbo-go] zouyx commented on a change in pull request #773: 【optimize】replace go/net/url
Posted by GitBox <gi...@apache.org>.
zouyx commented on a change in pull request #773:
URL: https://github.com/apache/dubbo-go/pull/773#discussion_r493984885
##########
File path: common/net/url/url.go
##########
@@ -0,0 +1,1161 @@
+/*
+ * 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 url parses URLs and implements query escaping.
+package url
+
+// This package is an extension of the GO SDK
+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 {
Review comment:
Why do you copy this file?
i think you should just extends net/Values , change or add a method.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: notifications-unsubscribe@dubbo.apache.org
For additional commands, e-mail: notifications-help@dubbo.apache.org
[GitHub] [dubbo-go] IndiraFinish commented on a change in pull request #773: 【optimize】replace go/net/url
Posted by GitBox <gi...@apache.org>.
IndiraFinish commented on a change in pull request #773:
URL: https://github.com/apache/dubbo-go/pull/773#discussion_r495415679
##########
File path: common/net/url/url.go
##########
@@ -0,0 +1,1161 @@
+/*
+ * 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 url parses URLs and implements query escaping.
+package url
+
+// This package is an extension of the GO SDK
+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 {
Review comment:
I agree with you that it was thoughtless here
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: notifications-unsubscribe@dubbo.apache.org
For additional commands, e-mail: notifications-help@dubbo.apache.org
[GitHub] [dubbo-go] zouyx commented on pull request #773: Imp: replace go/net/url
Posted by GitBox <gi...@apache.org>.
zouyx commented on pull request #773:
URL: https://github.com/apache/dubbo-go/pull/773#issuecomment-713530820
what about this feature？
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: notifications-unsubscribe@dubbo.apache.org
For additional commands, e-mail: notifications-help@dubbo.apache.org
[GitHub] [dubbo-go] pantianying commented on a change in pull request #773: 【optimize】replace go/net/url
Posted by GitBox <gi...@apache.org>.
pantianying commented on a change in pull request #773:
URL: https://github.com/apache/dubbo-go/pull/773#discussion_r493350657
##########
File path: common/url_test.go
##########
@@ -41,6 +41,9 @@ func TestNewURLWithOptions(t *testing.T) {
methods := []string{"Methodone,methodtwo"}
params := url.Values{}
params.Set("key", "value")
+ // test value is ""
+ params.Set("group", "")
+ params.Set("vserion", "")
Review comment:
vserion
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: notifications-unsubscribe@dubbo.apache.org
For additional commands, e-mail: notifications-help@dubbo.apache.org
[GitHub] [dubbo-go] AlexStocks commented on pull request #773: Imp: replace go/net/url
Posted by GitBox <gi...@apache.org>.
AlexStocks commented on pull request #773:
URL: https://github.com/apache/dubbo-go/pull/773#issuecomment-714230032
> what about this feature？
@haohongfan own it now.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: notifications-unsubscribe@dubbo.apache.org
For additional commands, e-mail: notifications-help@dubbo.apache.org
[GitHub] [dubbo-go] watermelo commented on pull request #773: 【optimize】replace go/net/url
Posted by GitBox <gi...@apache.org>.
watermelo commented on pull request #773:
URL: https://github.com/apache/dubbo-go/pull/773#issuecomment-699370499
hi @IndiraFinish, pls resolve the conflicts.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: notifications-unsubscribe@dubbo.apache.org
For additional commands, e-mail: notifications-help@dubbo.apache.org
[GitHub] [dubbo-go] fangyincheng closed pull request #773: Imp: replace go/net/url
Posted by GitBox <gi...@apache.org>.
fangyincheng closed pull request #773:
URL: https://github.com/apache/dubbo-go/pull/773
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: notifications-unsubscribe@dubbo.apache.org
For additional commands, e-mail: notifications-help@dubbo.apache.org
[GitHub] [dubbo-go] hxmhlt commented on a change in pull request #773: Imp: replace go/net/url
Posted by GitBox <gi...@apache.org>.
hxmhlt commented on a change in pull request #773:
URL: https://github.com/apache/dubbo-go/pull/773#discussion_r499975191
##########
File path: common/net/url/url.go
##########
@@ -0,0 +1,1161 @@
+/*
+ * 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 url parses URLs and implements query escaping.
+package url
+
+// This package is an extension of the GO SDK
+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 {
Review comment:
+1
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: notifications-unsubscribe@dubbo.apache.org
For additional commands, e-mail: notifications-help@dubbo.apache.org
[GitHub] [dubbo-go] AlexStocks commented on a change in pull request #773: 【optimize】replace go/net/url
Posted by GitBox <gi...@apache.org>.
AlexStocks commented on a change in pull request #773:
URL: https://github.com/apache/dubbo-go/pull/773#discussion_r492676187
##########
File path: common/url.go
##########
@@ -20,9 +20,9 @@ package common
import (
"encoding/base64"
"fmt"
+ "github.com/apache/dubbo-go/common/net/url"
Review comment:
move this package to the third import block
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: notifications-unsubscribe@dubbo.apache.org
For additional commands, e-mail: notifications-help@dubbo.apache.org