1
0
mirror of https://github.com/go-gitea/gitea.git synced 2024-10-31 08:37:35 -04:00
gitea/modules/util/sanitize.go
wxiaoguang c83168104b
Use a more general (and faster) method to sanitize URLs with credentials (#19239)
Use a more general method to sanitize URLs with credentials: Simple and intuitive / Faster /  Remove all credentials in all URLs
2022-03-31 10:25:40 +08:00

76 lines
2.6 KiB
Go

// Copyright 2021 The Gitea Authors. All rights reserved.
// Use of this source code is governed by a MIT-style
// license that can be found in the LICENSE file.
package util
import (
"bytes"
"unicode"
"github.com/yuin/goldmark/util"
)
type sanitizedError struct {
err error
}
func (err sanitizedError) Error() string {
return SanitizeCredentialURLs(err.err.Error())
}
func (err sanitizedError) Unwrap() error {
return err.err
}
// SanitizeErrorCredentialURLs wraps the error and make sure the returned error message doesn't contain sensitive credentials in URLs
func SanitizeErrorCredentialURLs(err error) error {
return sanitizedError{err: err}
}
const userPlaceholder = "sanitized-credential"
var schemeSep = []byte("://")
// SanitizeCredentialURLs remove all credentials in URLs (starting with "scheme://") for the input string: "https://user:pass@domain.com" => "https://sanitized-credential@domain.com"
func SanitizeCredentialURLs(s string) string {
bs := util.StringToReadOnlyBytes(s)
schemeSepPos := bytes.Index(bs, schemeSep)
if schemeSepPos == -1 || bytes.IndexByte(bs[schemeSepPos:], '@') == -1 {
return s // fast return if there is no URL scheme or no userinfo
}
out := make([]byte, 0, len(bs)+len(userPlaceholder))
for schemeSepPos != -1 {
schemeSepPos += 3 // skip the "://"
sepAtPos := -1 // the possible '@' position: "https://foo@[^here]host"
sepEndPos := schemeSepPos // the possible end position: "The https://host[^here] in log for test"
sepLoop:
for ; sepEndPos < len(bs); sepEndPos++ {
c := bs[sepEndPos]
if ('A' <= c && c <= 'Z') || ('a' <= c && c <= 'z') || ('0' <= c && c <= '9') {
continue
}
switch c {
case '@':
sepAtPos = sepEndPos
case '-', '.', '_', '~', '!', '$', '&', '\'', '(', ')', '*', '+', ',', ';', '=', ':', '%':
continue // due to RFC 3986, userinfo can contain - . _ ~ ! $ & ' ( ) * + , ; = : and any percent-encoded chars
default:
break sepLoop // if it is an invalid char for URL (eg: space, '/', and others), stop the loop
}
}
// if there is '@', and the string is like "s://u@h", then hide the "u" part
if sepAtPos != -1 && (schemeSepPos >= 4 && unicode.IsLetter(rune(bs[schemeSepPos-4]))) && sepAtPos-schemeSepPos > 0 && sepEndPos-sepAtPos > 0 {
out = append(out, bs[:schemeSepPos]...)
out = append(out, userPlaceholder...)
out = append(out, bs[sepAtPos:sepEndPos]...)
} else {
out = append(out, bs[:sepEndPos]...)
}
bs = bs[sepEndPos:]
schemeSepPos = bytes.Index(bs, schemeSep)
}
out = append(out, bs...)
return util.BytesToReadOnlyString(out)
}