gin/render/json.go
Amit Mishra ed773a4d38 fix(render): encode non-BMP characters as UTF-16 surrogate pairs in AsciiJSON
AsciiJSON used fmt.Appendf with "\u%04x" to escape all non-ASCII runes.
For code points above U+FFFF the format produces a 5+ digit sequence (e.g.
ὠ0 for U+1F600), which is syntactically valid JSON but wrong: a JSON
\u escape is exactly 4 hex digits, so decoders interpret the 5th digit as
literal text and the recovered string is silently corrupted.

Per RFC 8259 section 7, code points above U+FFFF must be encoded as a
UTF-16 surrogate pair (\uD800-\uDBFF followed by \uDC00-\uDFFF). Use
unicode/utf16.EncodeRune to compute the pair and emit two \uXXXX escapes.

Add TestRenderAsciiJSONNonBMP to verify that emoji and other non-BMP
characters survive an AsciiJSON -> json.Unmarshal round-trip unchanged.

Fixes #4688

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-07-04 02:47:23 +05:30

205 lines
5.4 KiB
Go
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

// Copyright 2014 Manu Martinez-Almeida. All rights reserved.
// Use of this source code is governed by a MIT style
// license that can be found in the LICENSE file.
package render
import (
"bytes"
"fmt"
"html/template"
"net/http"
"unicode"
"unicode/utf16"
"github.com/gin-gonic/gin/codec/json"
"github.com/gin-gonic/gin/internal/bytesconv"
)
// JSON contains the given interface object.
type JSON struct {
Data any
}
// IndentedJSON contains the given interface object.
type IndentedJSON struct {
Data any
}
// SecureJSON contains the given interface object and its prefix.
type SecureJSON struct {
Prefix string
Data any
}
// JsonpJSON contains the given interface object its callback.
type JsonpJSON struct {
Callback string
Data any
}
// AsciiJSON contains the given interface object.
type AsciiJSON struct {
Data any
}
// PureJSON contains the given interface object.
type PureJSON struct {
Data any
}
var (
jsonContentType = []string{"application/json; charset=utf-8"}
jsonpContentType = []string{"application/javascript; charset=utf-8"}
jsonASCIIContentType = []string{"application/json"}
)
// Render (JSON) writes data with custom ContentType.
func (r JSON) Render(w http.ResponseWriter) error {
return WriteJSON(w, r.Data)
}
// WriteContentType (JSON) writes JSON ContentType.
func (r JSON) WriteContentType(w http.ResponseWriter) {
writeContentType(w, jsonContentType)
}
// WriteJSON marshals the given interface object and writes it with custom ContentType.
func WriteJSON(w http.ResponseWriter, obj any) error {
writeContentType(w, jsonContentType)
jsonBytes, err := json.API.Marshal(obj)
if err != nil {
return err
}
_, err = w.Write(jsonBytes)
return err
}
// Render (IndentedJSON) marshals the given interface object and writes it with custom ContentType.
func (r IndentedJSON) Render(w http.ResponseWriter) error {
r.WriteContentType(w)
jsonBytes, err := json.API.MarshalIndent(r.Data, "", " ")
if err != nil {
return err
}
_, err = w.Write(jsonBytes)
return err
}
// WriteContentType (IndentedJSON) writes JSON ContentType.
func (r IndentedJSON) WriteContentType(w http.ResponseWriter) {
writeContentType(w, jsonContentType)
}
// Render (SecureJSON) marshals the given interface object and writes it with custom ContentType.
func (r SecureJSON) Render(w http.ResponseWriter) error {
r.WriteContentType(w)
jsonBytes, err := json.API.Marshal(r.Data)
if err != nil {
return err
}
// if the jsonBytes is array values
if bytes.HasPrefix(jsonBytes, bytesconv.StringToBytes("[")) && bytes.HasSuffix(jsonBytes,
bytesconv.StringToBytes("]")) {
if _, err = w.Write(bytesconv.StringToBytes(r.Prefix)); err != nil {
return err
}
}
_, err = w.Write(jsonBytes)
return err
}
// WriteContentType (SecureJSON) writes JSON ContentType.
func (r SecureJSON) WriteContentType(w http.ResponseWriter) {
writeContentType(w, jsonContentType)
}
// Render (JsonpJSON) marshals the given interface object and writes it and its callback with custom ContentType.
func (r JsonpJSON) Render(w http.ResponseWriter) (err error) {
r.WriteContentType(w)
ret, err := json.API.Marshal(r.Data)
if err != nil {
return err
}
if r.Callback == "" {
_, err = w.Write(ret)
return err
}
callback := template.JSEscapeString(r.Callback)
if _, err = w.Write(bytesconv.StringToBytes(callback)); err != nil {
return err
}
if _, err = w.Write(bytesconv.StringToBytes("(")); err != nil {
return err
}
if _, err = w.Write(ret); err != nil {
return err
}
if _, err = w.Write(bytesconv.StringToBytes(");")); err != nil {
return err
}
return nil
}
// WriteContentType (JsonpJSON) writes Javascript ContentType.
func (r JsonpJSON) WriteContentType(w http.ResponseWriter) {
writeContentType(w, jsonpContentType)
}
// Render (AsciiJSON) marshals the given interface object and writes it with custom ContentType.
func (r AsciiJSON) Render(w http.ResponseWriter) error {
r.WriteContentType(w)
ret, err := json.API.Marshal(r.Data)
if err != nil {
return err
}
var buffer bytes.Buffer
escapeBuf := make([]byte, 0, 13) // Preallocate for worst case: two \uXXXX surrogate pair escapes
for _, r := range bytesconv.BytesToString(ret) {
if r > unicode.MaxASCII {
if r > 0xFFFF {
// Non-BMP character (above U+FFFF): encode as a UTF-16 surrogate pair.
// A JSON \u escape is exactly 4 hex digits, so code points requiring more
// than 4 digits must be split into a high/low surrogate pair per RFC 8259 §7.
high, low := utf16.EncodeRune(r)
escapeBuf = fmt.Appendf(escapeBuf[:0], "\\u%04x\\u%04x", high, low)
} else {
// BMP character (U+0080U+FFFF): a single \uXXXX escape suffices.
escapeBuf = fmt.Appendf(escapeBuf[:0], "\\u%04x", r)
}
buffer.Write(escapeBuf)
} else {
buffer.WriteByte(byte(r))
}
}
_, err = w.Write(buffer.Bytes())
return err
}
// WriteContentType (AsciiJSON) writes JSON ContentType.
func (r AsciiJSON) WriteContentType(w http.ResponseWriter) {
writeContentType(w, jsonASCIIContentType)
}
// Render (PureJSON) writes custom ContentType and encodes the given interface object.
func (r PureJSON) Render(w http.ResponseWriter) error {
r.WriteContentType(w)
encoder := json.API.NewEncoder(w)
encoder.SetEscapeHTML(false)
return encoder.Encode(r.Data)
}
// WriteContentType (PureJSON) writes custom ContentType.
func (r PureJSON) WriteContentType(w http.ResponseWriter) {
writeContentType(w, jsonContentType)
}