[pull] main from nodejs:main

benchmark/fs/readfile-utf8-fastpath.js

@@ -0,0 +1,62 @@
+'use strict';
+
+const common = require('../common.js');
+const fs = require('fs');
+const path = require('path');
+const tmpdir = require('../../test/common/tmpdir');
+
+const bench = common.createBenchmark(main, {
+  size: [64, 1024, 16384, 262144, 4194304],
+  content: ['ascii', 'latin1', 'utf8_mixed'],
+  source: ['path', 'fd'],
+  n: [3e3],
+});
+
+function buildContent(kind, size) {
+  if (kind === 'ascii') {
+    return Buffer.alloc(size, 0x61); // 'a'
+  }
+  if (kind === 'latin1') {
+    // 'é' in UTF-8 is 0xC3 0xA9 (2 bytes per char)
+    const pair = Buffer.from([0xC3, 0xA9]);
+    const buf = Buffer.alloc(size);
+    for (let i = 0; i + 2 <= size; i += 2) pair.copy(buf, i);
+    return buf;
+  }
+  if (kind === 'utf8_mixed') {
+    // mixed ASCII + 3-byte CJK (U+4E2D 中 = E4 B8 AD)
+    const cjk = Buffer.from([0xE4, 0xB8, 0xAD]);
+    const buf = Buffer.alloc(size);
+    let i = 0;
+    while (i + 4 <= size) {
+      buf[i++] = 0x61;
+      cjk.copy(buf, i);
+      i += 3;
+    }
+    return buf;
+  }
+  throw new Error('unknown content: ' + kind);
+}
+
+function main({ n, size, content, source }) {
+  tmpdir.refresh();
+  const file = path.join(tmpdir.path, `bench-${content}-${size}.bin`);
+  fs.writeFileSync(file, buildContent(content, size));
+
+  let arg;
+  let shouldClose = false;
+  if (source === 'fd') {
+    arg = fs.openSync(file, 'r');
+    shouldClose = true;
+  } else {
+    arg = file;
+  }
+
+  bench.start();
+  for (let i = 0; i < n; i++) {
+    fs.readFileSync(arg, 'utf8');
+  }
+  bench.end(n);
+
+  if (shouldClose) fs.closeSync(arg);
+}

benchmark/util/text-decoder.js

@@ -6,26 +6,42 @@ const bench = common.createBenchmark(main, {
   encoding: ['utf-8', 'windows-1252', 'iso-8859-3'],
   ignoreBOM: [0, 1],
   fatal: [0, 1],
+  type: ['SharedArrayBuffer', 'ArrayBuffer', 'Buffer'],
+  content: ['ascii', 'one-byte-string', 'two-byte-string'],
   len: [256, 1024 * 16, 1024 * 128],
   n: [1e3],
-  type: ['SharedArrayBuffer', 'ArrayBuffer', 'Buffer'],
 });
 
-function main({ encoding, len, n, ignoreBOM, type, fatal }) {
+function buildContent(content, len) {
+  let base;
+  switch (content) {
+    case 'ascii': base = 'a'; break;
+    case 'one-byte-string': base = '\xff'; break;
+    case 'two-byte-string': base = 'ğ'; break;
+  }
+  const unitBytes = Buffer.byteLength(base, 'utf8');
+  const copies = Math.max(1, Math.floor(len / unitBytes));
+  return Buffer.from(base.repeat(copies));
+}
+
+function main({ encoding, len, n, ignoreBOM, type, fatal, content }) {
   const decoder = new TextDecoder(encoding, { ignoreBOM, fatal });
+  const seed = buildContent(content, len);
   let buf;
 
   switch (type) {
     case 'SharedArrayBuffer': {
-      buf = new SharedArrayBuffer(len);
+      buf = new SharedArrayBuffer(seed.length);
+      new Uint8Array(buf).set(seed);
       break;
     }
     case 'ArrayBuffer': {
-      buf = new ArrayBuffer(len);
+      buf = new ArrayBuffer(seed.length);
+      new Uint8Array(buf).set(seed);
       break;
     }
     case 'Buffer': {
-      buf = Buffer.allocUnsafe(len);
+      buf = seed;
       break;
     }
   }

src/encoding_binding.cc

@@ -459,14 +459,15 @@ void BindingData::DecodeUTF8(const FunctionCallbackInfo<Value>& args) {
       return node::THROW_ERR_ENCODING_INVALID_ENCODED_DATA(
           env->isolate(), "The encoded data was not valid for encoding utf-8");
     }
-
-    // TODO(chalker): save on utf8 validity recheck in StringBytes::Encode()
   }
 
   if (length == 0) return args.GetReturnValue().SetEmptyString();
 
   Local<Value> ret;
-  if (StringBytes::Encode(env->isolate(), data, length, UTF8).ToLocal(&ret)) {
+  v8::MaybeLocal<Value> encoded =
+      has_fatal ? StringBytes::EncodeValidUtf8(env->isolate(), data, length)
+                : StringBytes::Encode(env->isolate(), data, length, UTF8);
+  if (encoded.ToLocal(&ret)) {
     args.GetReturnValue().Set(ret);
   }
 }

src/string_bytes.cc

@@ -671,6 +671,40 @@ MaybeLocal<Value> StringBytes::Encode(Isolate* isolate,
   }
 }
 
+MaybeLocal<Value> StringBytes::EncodeValidUtf8(Isolate* isolate,
+                                               const char* buf,
+                                               size_t buflen) {
+  CHECK_BUFLEN_IN_RANGE(buflen);
+  if (!buflen) return String::Empty(isolate);
+  buflen = keep_buflen_in_range(buflen);
+
+  // ASCII fast path
+  if (!simdutf::validate_ascii_with_errors(buf, buflen).error) {
+    return ExternOneByteString::NewFromCopy(isolate, buf, buflen);
+  }
+
+  if (buflen >= 32) {
+    size_t u16size = simdutf::utf16_length_from_utf8(buf, buflen);
+    if (u16size > static_cast<size_t>(v8::String::kMaxLength)) {
+      isolate->ThrowException(ERR_STRING_TOO_LONG(isolate));
+      return MaybeLocal<Value>();
+    }
+    return EncodeTwoByteString(
+        isolate, u16size, [buf, buflen, u16size](uint16_t* dst) {
+          size_t written = simdutf::convert_valid_utf8_to_utf16(
+              buf, buflen, reinterpret_cast<char16_t*>(dst));
+          CHECK_EQ(written, u16size);
+        });
+  }
+
+  Local<String> str;
+  if (!String::NewFromUtf8(isolate, buf, v8::NewStringType::kNormal, buflen)
+           .ToLocal(&str)) {
+    isolate->ThrowException(node::ERR_STRING_TOO_LONG(isolate));
+  }
+  return str;
+}
+
 MaybeLocal<Value> StringBytes::Encode(Isolate* isolate,
                                       const uint16_t* buf,
                                       size_t buflen) {

src/string_bytes.h

@@ -83,6 +83,11 @@ class StringBytes {
                                           size_t buflen,
                                           enum encoding encoding);
 
+  // Like Encode(..., UTF8) but does not re-validate. Input must be valid UTF-8.
+  static v8::MaybeLocal<v8::Value> EncodeValidUtf8(v8::Isolate* isolate,
+                                                   const char* buf,
+                                                   size_t buflen);
+
   // Warning: This reverses endianness on BE platforms, even though the
   // signature using uint16_t implies that it should not.
   // However, the brokenness is already public API and can't therefore

src/util-inl.h

@@ -341,22 +341,6 @@ v8::Maybe<void> FromV8Array(v8::Local<v8::Context> context,
   return js_array->Iterate(context, PushItemToVector, &data);
 }
 
-v8::MaybeLocal<v8::Value> ToV8Value(v8::Local<v8::Context> context,
-                                    std::string_view str,
-                                    v8::Isolate* isolate) {
-  if (isolate == nullptr) isolate = v8::Isolate::GetCurrent();
-  if (str.size() >= static_cast<size_t>(v8::String::kMaxLength)) [[unlikely]] {
-    // V8 only has a TODO comment about adding an exception when the maximum
-    // string size is exceeded.
-    ThrowErrStringTooLong(isolate);
-    return v8::MaybeLocal<v8::Value>();
-  }
-
-  return v8::String::NewFromUtf8(
-             isolate, str.data(), v8::NewStringType::kNormal, str.size())
-      .FromMaybe(v8::Local<v8::String>());
-}
-
 v8::MaybeLocal<v8::Value> ToV8Value(v8::Local<v8::Context> context,
                                     std::u16string_view str,
                                     v8::Isolate* isolate) {

src/util.cc

@@ -812,4 +812,15 @@ v8::Maybe<int> GetValidFileMode(Environment* env,
   return v8::Just(mode);
 }
 
+v8::MaybeLocal<v8::Value> ToV8Value(v8::Local<v8::Context> context,
+                                    std::string_view str,
+                                    v8::Isolate* isolate) {
+  if (isolate == nullptr) isolate = v8::Isolate::GetCurrent();
+  if (str.size() >= static_cast<size_t>(v8::String::kMaxLength)) [[unlikely]] {
+    ThrowErrStringTooLong(isolate);
+    return v8::MaybeLocal<v8::Value>();
+  }
+  return StringBytes::Encode(isolate, str.data(), str.size(), UTF8);
+}
+
 }  // namespace node

src/util.h

@@ -701,9 +701,9 @@ inline v8::Maybe<void> FromV8Array(v8::Local<v8::Context> context,
                                    v8::Local<v8::Array> js_array,
                                    std::vector<v8::Global<v8::Value>>* out);
 
-inline v8::MaybeLocal<v8::Value> ToV8Value(v8::Local<v8::Context> context,
-                                           std::string_view str,
-                                           v8::Isolate* isolate = nullptr);
+v8::MaybeLocal<v8::Value> ToV8Value(v8::Local<v8::Context> context,
+                                    std::string_view str,
+                                    v8::Isolate* isolate = nullptr);
 inline v8::MaybeLocal<v8::Value> ToV8Value(v8::Local<v8::Context> context,
                                            std::u16string_view str,
                                            v8::Isolate* isolate = nullptr);

test/parallel/test-fs-readfile-utf8-fast-path.js

@@ -0,0 +1,103 @@
+'use strict';
+
+require('../common');
+const fs = require('node:fs');
+const path = require('node:path');
+const assert = require('node:assert');
+const { describe, it } = require('node:test');
+const tmpdir = require('../common/tmpdir');
+
+tmpdir.refresh();
+
+function writeFile(name, buf) {
+  const p = path.join(tmpdir.path, name);
+  fs.writeFileSync(p, buf);
+  return p;
+}
+
+function expectMatches(filePath, rawBuf) {
+  assert.strictEqual(
+    fs.readFileSync(filePath, 'utf8'),
+    rawBuf.toString('utf8'),
+  );
+}
+
+describe('fs.readFileSync utf8 simdutf dispatch', () => {
+  it('empty file', () => {
+    const p = writeFile('empty.txt', Buffer.alloc(0));
+    assert.strictEqual(fs.readFileSync(p, 'utf8'), '');
+  });
+
+  it('ascii small', () => {
+    const buf = Buffer.from('hello');
+    expectMatches(writeFile('tiny-ascii.txt', buf), buf);
+  });
+
+  it('ascii 20KB', () => {
+    const buf = Buffer.alloc(20 * 1024, 0x41);
+    expectMatches(writeFile('medium-ascii.txt', buf), buf);
+  });
+
+  it('ascii 1MB', () => {
+    const buf = Buffer.alloc(1024 * 1024, 0x61);
+    expectMatches(writeFile('large-ascii.txt', buf), buf);
+  });
+
+  it('fd input', () => {
+    const buf = Buffer.alloc(50 * 1024, 0x62);
+    const p = writeFile('fd-ascii.txt', buf);
+    const fd = fs.openSync(p, 'r');
+    try {
+      assert.strictEqual(fs.readFileSync(fd, 'utf8'), buf.toString('utf8'));
+    } finally {
+      fs.closeSync(fd);
+    }
+  });
+
+  it('multibyte UTF-8', () => {
+    const buf = Buffer.from('中文测试 — café — 🚀'.repeat(500), 'utf8');
+    expectMatches(writeFile('multibyte.txt', buf), buf);
+  });
+
+  it('latin1-fits utf8', () => {
+    const buf = Buffer.from('naïve café résumé — niño Köln '.repeat(500), 'utf8');
+    expectMatches(writeFile('latin1-fits.txt', buf), buf);
+  });
+
+  it('invalid: lone continuation byte', () => {
+    const buf = Buffer.from([0x68, 0x69, 0x80, 0x21]);
+    expectMatches(writeFile('invalid-cont.txt', buf), buf);
+  });
+
+  it('invalid: overlong', () => {
+    const buf = Buffer.from([0x41, 0xC0, 0xAF, 0x42]);
+    expectMatches(writeFile('invalid-overlong.txt', buf), buf);
+  });
+
+  it('invalid: surrogate', () => {
+    const buf = Buffer.from([0x41, 0xED, 0xA0, 0x80, 0x42]);
+    expectMatches(writeFile('invalid-surrogate.txt', buf), buf);
+  });
+
+  it('latin1 boundary U+00FF', () => {
+    const buf = Buffer.from('ÿ'.repeat(2048), 'utf8');
+    expectMatches(writeFile('latin1-boundary.txt', buf), buf);
+  });
+
+  it('above latin1 U+0100', () => {
+    const buf = Buffer.from('ĀāĂ'.repeat(1024), 'utf8');
+    expectMatches(writeFile('above-latin1.txt', buf), buf);
+  });
+
+  it('single codepoint each UTF-8 length', () => {
+    for (const cp of [0x41, 0x00E9, 0x4E2D, 0x1F600]) {
+      const buf = Buffer.from(String.fromCodePoint(cp), 'utf8');
+      expectMatches(writeFile(`single-cp-${cp.toString(16)}.txt`, buf), buf);
+    }
+  });
+
+  it('truncated multibyte at EOF', () => {
+    const buf = Buffer.from([0x41, 0xE4, 0xB8]);
+    expectMatches(writeFile('truncated-multibyte.txt', buf), buf);
+  });
+});