From e2bd2e4bbbc71b36c5a6bf1ee3b35fe5d2300997 Mon Sep 17 00:00:00 2001
From: Yagiz Nizipli <yagiz@nizipli.com>
Date: Sun, 6 Nov 2022 15:27:41 -0500
Subject: [PATCH] util: improve textdecoder decode performance

PR-URL: https://github.com/nodejs/node/pull/45294
Reviewed-By: Anna Henningsen <anna@addaleax.net>
Reviewed-By: Matteo Collina <matteo.collina@gmail.com>
Reviewed-By: James M Snell <jasnell@gmail.com>
Reviewed-By: Minwoo Jung <nodecorelab@gmail.com>
Reviewed-By: Rich Trott <rtrott@gmail.com>
---
 benchmark/util/text-decoder.js | 19 ++++++++++++++++
 lib/internal/encoding.js       |  2 +-
 src/node_i18n.cc               | 40 +++++++++++++++++++++++-----------
 3 files changed, 47 insertions(+), 14 deletions(-)
 create mode 100644 benchmark/util/text-decoder.js

diff --git a/benchmark/util/text-decoder.js b/benchmark/util/text-decoder.js
new file mode 100644
index 00000000000000..ad845f7c92d0c7
--- /dev/null
+++ b/benchmark/util/text-decoder.js
@@ -0,0 +1,19 @@
+'use strict';
+
+const common = require('../common.js');
+
+const bench = common.createBenchmark(main, {
+  encoding: ['utf-8', 'latin1', 'iso-8859-3'],
+  ignoreBOM: [0, 1],
+  len: [256, 1024 * 16, 1024 * 512],
+  n: [1e6]
+});
+
+function main({ encoding, len, n, ignoreBOM }) {
+  const buf = Buffer.allocUnsafe(len);
+  const decoder = new TextDecoder(encoding, { ignoreBOM });
+
+  bench.start();
+  decoder.decode(buf);
+  bench.end(n);
+}
diff --git a/lib/internal/encoding.js b/lib/internal/encoding.js
index 3a3d558361e118..2ab85d9d9acb06 100644
--- a/lib/internal/encoding.js
+++ b/lib/internal/encoding.js
@@ -438,7 +438,7 @@ function makeTextDecoderICU() {
       if (typeof ret === 'number') {
         throw new ERR_ENCODING_INVALID_ENCODED_DATA(this.encoding, ret);
       }
-      return ret.toString('ucs2');
+      return ret;
     }
   }
 
diff --git a/src/node_i18n.cc b/src/node_i18n.cc
index 581d52a7d05738..ed7b72c31f975e 100644
--- a/src/node_i18n.cc
+++ b/src/node_i18n.cc
@@ -50,6 +50,7 @@
 #include "node_buffer.h"
 #include "node_errors.h"
 #include "node_internals.h"
+#include "string_bytes.h"
 #include "util-inl.h"
 #include "v8.h"
 
@@ -96,7 +97,6 @@ using v8::NewStringType;
 using v8::Object;
 using v8::ObjectTemplate;
 using v8::String;
-using v8::Uint8Array;
 using v8::Value;
 
 namespace i18n {
@@ -445,7 +445,6 @@ void ConverterObject::Decode(const FunctionCallbackInfo<Value>& args) {
 
   UErrorCode status = U_ZERO_ERROR;
   MaybeStackBuffer<UChar> result;
-  MaybeLocal<Object> ret;
 
   UBool flush = (flags & CONVERTER_FLAGS_FLUSH) == CONVERTER_FLAGS_FLUSH;
 
@@ -501,19 +500,34 @@ void ConverterObject::Decode(const FunctionCallbackInfo<Value>& args) {
         converter->set_bom_seen(true);
       }
     }
-    ret = ToBufferEndian(env, &result);
-    if (omit_initial_bom && !ret.IsEmpty()) {
+
+    Local<Value> error;
+    UChar* output = result.out();
+    size_t beginning = 0;
+    size_t length = result.length() * sizeof(UChar);
+
+    if (omit_initial_bom) {
       // Perform `ret = ret.slice(2)`.
-      CHECK(ret.ToLocalChecked()->IsUint8Array());
-      Local<Uint8Array> orig_ret = ret.ToLocalChecked().As<Uint8Array>();
-      ret = Buffer::New(env,
-                        orig_ret->Buffer(),
-                        orig_ret->ByteOffset() + 2,
-                        orig_ret->ByteLength() - 2)
-                            .FromMaybe(Local<Uint8Array>());
+      beginning += 2;
+      length -= 2;
     }
-    if (!ret.IsEmpty())
-      args.GetReturnValue().Set(ret.ToLocalChecked());
+
+    char* value = reinterpret_cast<char*>(output) + beginning;
+
+    if (IsBigEndian()) {
+      SwapBytes16(value, length);
+    }
+
+    MaybeLocal<Value> encoded =
+        StringBytes::Encode(env->isolate(), value, length, UCS2, &error);
+
+    Local<Value> ret;
+    if (encoded.ToLocal(&ret)) {
+      args.GetReturnValue().Set(ret);
+    } else {
+      args.GetReturnValue().Set(error);
+    }
+
     return;
   }