gin/render/json.go
okxint 3498e1cdbc fix(render): encode non-BMP characters as UTF-16 surrogate pairs in AsciiJSON
AsciiJSON.Render used fmt.Appendf(buf, "\\u%04x", r) for all non-ASCII
runes. The %04x format is a *minimum* width, not a fixed width, so runes
above U+FFFF (emoji, musical symbols, supplementary CJK, etc.) produce a
5-digit escape like \u1f600. JSON \u escapes are always exactly 4 hex
digits (RFC 8259 §7), so a decoder reads the first 4 digits as a
different character and treats the remaining digit(s) as literal text.
The output is still syntactically valid JSON, which makes the corruption
easy to miss — values silently fail to round-trip.

Fix: detect runes > U+FFFF and split them into a UTF-16 surrogate pair
(\uHHHH\uLLLL) before writing the escape. BMP characters continue to use
the single-escape path unchanged.

Add TestRenderAsciiJSONNonBMP to verify correct surrogate-pair encoding
and full round-trip fidelity for 😀 (U+1F600), 𝄞 (U+1D11E), and 𠀀 (U+20000).

Fixes #4688

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-09-02 12:29:43 +05:30

205 lines
5.3 KiB
Go

// 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"
"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, 12) // 12 bytes for a UTF-16 surrogate pair (\uHHHH\uLLLL)
for _, r := range bytesconv.BytesToString(ret) {
if r > unicode.MaxASCII {
if r > 0xFFFF {
// Non-BMP character: encode as a UTF-16 surrogate pair per RFC 8259 §7.
// \u alone cannot represent code points above U+FFFF (it is always 4 hex digits),
// so we split the rune into a high surrogate and a low surrogate.
r -= 0x10000
high := 0xD800 + (r>>10)&0x3FF
low := 0xDC00 + r&0x3FF
escapeBuf = fmt.Appendf(escapeBuf[:0], "\\u%04x\\u%04x", high, low)
} else {
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)
}