From f788349ddb31421566acd725a139a35244c3cc05 Mon Sep 17 00:00:00 2001
From: jim <398651434@qq.com>
Date: Thu, 16 Apr 2026 12:12:21 +0800
Subject: [PATCH] fix: use StringDecoder to handle UTF-8 chunk boundaries in
 setEncoding

When setEncoding('utf8') is called, each chunk was being converted to
a string individually, which corrupts multi-byte UTF-8 characters that
span chunk boundaries.

This fix:
- Initializes a StringDecoder when setEncoding is called
- Uses StringDecoder.write() in consumePush to properly handle
  incomplete UTF-8 sequences at chunk boundaries
- Resets the decoder in consumeFinish to allow garbage collection

Closes #5002
---
 lib/api/readable.js | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/lib/api/readable.js b/lib/api/readable.js
index 5ebd04ebe83..0c4ec9e5247 100644
--- a/lib/api/readable.js
+++ b/lib/api/readable.js
@@ -1,6 +1,7 @@
 'use strict'
 
 const assert = require('node:assert')
+const { StringDecoder } = require('node:string_decoder')
 const { addAbortListener } = require('node:events')
 const { Readable } = require('node:stream')
 const { RequestAbortedError, NotSupportedError, InvalidArgumentError, AbortError } = require('../core/errors')
@@ -326,6 +327,9 @@ class BodyReadable extends Readable {
   setEncoding (encoding) {
     if (Buffer.isEncoding(encoding)) {
       this._readableState.encoding = encoding
+      if (this[kConsume]) {
+        this[kConsume].decoder = new StringDecoder(encoding)
+      }
     }
     return this
   }
@@ -546,8 +550,14 @@ function consumeEnd (consume, encoding) {
  * @returns {void}
  */
 function consumePush (consume, chunk) {
-  consume.length += chunk.length
-  consume.body.push(chunk)
+  if (consume.decoder) {
+    const string = consume.decoder.write(chunk)
+    consume.length += Buffer.byteLength(string)
+    consume.body.push(string)
+  } else {
+    consume.length += chunk.length
+    consume.body.push(chunk)
+  }
 }
 
 /**