feat(node): buffer isUtf8/isAscii (#23928)

Fixes: https://github.com/denoland/deno/issues/23657

Implements `isUtf8` and `isAscii` as ops.

4 files changed, 144 insertions, 2 deletions

diff --git a/tests/node_compat/config.jsonc b/tests/node_compat/config.jsonc
index af45cc663..56f43b444 100644
--- a/tests/node_compat/config.jsonc
+++ b/tests/node_compat/config.jsonc
@@ -179,7 +179,9 @@
       "test-buffer-includes.js",
       "test-buffer-indexof.js",
       "test-buffer-inheritance.js",
+      "test-buffer-isascii.js",
       "test-buffer-isencoding.js",
+      "test-buffer-isutf8.js",
       "test-buffer-iterator.js",
       "test-buffer-new.js",
       "test-buffer-no-negative-allocation.js",
diff --git a/tests/node_compat/runner/TODO.md b/tests/node_compat/runner/TODO.md
index b812981e5..0bc19a076 100644
--- a/tests/node_compat/runner/TODO.md
+++ b/tests/node_compat/runner/TODO.md
@@ -227,8 +227,6 @@ NOTE: This file should not be manually edited. Please edit `tests/node_compat/co
 - [parallel/test-buffer-constructor-outside-node-modules.js](https://github.com/nodejs/node/tree/v18.12.1/test/parallel/test-buffer-constructor-outside-node-modules.js)
 - [parallel/test-buffer-fill.js](https://github.com/nodejs/node/tree/v18.12.1/test/parallel/test-buffer-fill.js)
 - [parallel/test-buffer-inspect.js](https://github.com/nodejs/node/tree/v18.12.1/test/parallel/test-buffer-inspect.js)
-- [parallel/test-buffer-isascii.js](https://github.com/nodejs/node/tree/v18.12.1/test/parallel/test-buffer-isascii.js)
-- [parallel/test-buffer-isutf8.js](https://github.com/nodejs/node/tree/v18.12.1/test/parallel/test-buffer-isutf8.js)
 - [parallel/test-buffer-pending-deprecation.js](https://github.com/nodejs/node/tree/v18.12.1/test/parallel/test-buffer-pending-deprecation.js)
 - [parallel/test-buffer-pool-untransferable.js](https://github.com/nodejs/node/tree/v18.12.1/test/parallel/test-buffer-pool-untransferable.js)
 - [parallel/test-buffer-prototype-inspect.js](https://github.com/nodejs/node/tree/v18.12.1/test/parallel/test-buffer-prototype-inspect.js)
diff --git a/tests/node_compat/test/parallel/test-buffer-isascii.js b/tests/node_compat/test/parallel/test-buffer-isascii.js
new file mode 100644
index 000000000..59612bb9d
--- /dev/null
+++ b/tests/node_compat/test/parallel/test-buffer-isascii.js
@@ -0,0 +1,49 @@
+// deno-fmt-ignore-file
+// deno-lint-ignore-file
+
+// Copyright Joyent and Node contributors. All rights reserved. MIT license.
+// Taken from Node 18.12.1
+// This file is automatically generated by `tests/node_compat/runner/setup.ts`. Do not modify this file manually.
+
+'use strict';
+
+require('../common');
+const assert = require('assert');
+const { isAscii, Buffer } = require('buffer');
+const { TextEncoder } = require('util');
+
+const encoder = new TextEncoder();
+
+assert.strictEqual(isAscii(encoder.encode('hello')), true);
+assert.strictEqual(isAscii(encoder.encode('ğ')), false);
+assert.strictEqual(isAscii(Buffer.from([])), true);
+
+[
+  undefined,
+  '', 'hello',
+  false, true,
+  0, 1,
+  0n, 1n,
+  Symbol(),
+  () => {},
+  {}, [], null,
+].forEach((input) => {
+  assert.throws(
+    () => { isAscii(input); },
+    {
+      code: 'ERR_INVALID_ARG_TYPE',
+    },
+  );
+});
+
+{
+  // Test with detached array buffers
+  const arrayBuffer = new ArrayBuffer(1024);
+  structuredClone(arrayBuffer, { transfer: [arrayBuffer] });
+  assert.throws(
+    () => { isAscii(arrayBuffer); },
+    {
+      code: 'ERR_INVALID_STATE'
+    }
+  );
+}
diff --git a/tests/node_compat/test/parallel/test-buffer-isutf8.js b/tests/node_compat/test/parallel/test-buffer-isutf8.js
new file mode 100644
index 000000000..02f142db8
--- /dev/null
+++ b/tests/node_compat/test/parallel/test-buffer-isutf8.js
@@ -0,0 +1,93 @@
+// deno-fmt-ignore-file
+// deno-lint-ignore-file
+
+// Copyright Joyent and Node contributors. All rights reserved. MIT license.
+// Taken from Node 18.12.1
+// This file is automatically generated by `tests/node_compat/runner/setup.ts`. Do not modify this file manually.
+
+'use strict';
+
+require('../common');
+const assert = require('assert');
+const { isUtf8, Buffer } = require('buffer');
+const { TextEncoder } = require('util');
+
+const encoder = new TextEncoder();
+
+assert.strictEqual(isUtf8(encoder.encode('hello')), true);
+assert.strictEqual(isUtf8(encoder.encode('ğ')), true);
+assert.strictEqual(isUtf8(Buffer.from([])), true);
+
+// Taken from test/fixtures/wpt/encoding/textdecoder-fatal.any.js
+[
+  [0xFF], // 'invalid code'
+  [0xC0], // 'ends early'
+  [0xE0], // 'ends early 2'
+  [0xC0, 0x00], // 'invalid trail'
+  [0xC0, 0xC0], // 'invalid trail 2'
+  [0xE0, 0x00], // 'invalid trail 3'
+  [0xE0, 0xC0], // 'invalid trail 4'
+  [0xE0, 0x80, 0x00], // 'invalid trail 5'
+  [0xE0, 0x80, 0xC0], // 'invalid trail 6'
+  [0xFC, 0x80, 0x80, 0x80, 0x80, 0x80], // '> 0x10FFFF'
+  [0xFE, 0x80, 0x80, 0x80, 0x80, 0x80], // 'obsolete lead byte'
+
+  // Overlong encodings
+  [0xC0, 0x80], // 'overlong U+0000 - 2 bytes'
+  [0xE0, 0x80, 0x80], // 'overlong U+0000 - 3 bytes'
+  [0xF0, 0x80, 0x80, 0x80], // 'overlong U+0000 - 4 bytes'
+  [0xF8, 0x80, 0x80, 0x80, 0x80], // 'overlong U+0000 - 5 bytes'
+  [0xFC, 0x80, 0x80, 0x80, 0x80, 0x80], // 'overlong U+0000 - 6 bytes'
+
+  [0xC1, 0xBF], // 'overlong U+007F - 2 bytes'
+  [0xE0, 0x81, 0xBF], // 'overlong U+007F - 3 bytes'
+  [0xF0, 0x80, 0x81, 0xBF], // 'overlong U+007F - 4 bytes'
+  [0xF8, 0x80, 0x80, 0x81, 0xBF], // 'overlong U+007F - 5 bytes'
+  [0xFC, 0x80, 0x80, 0x80, 0x81, 0xBF], // 'overlong U+007F - 6 bytes'
+
+  [0xE0, 0x9F, 0xBF], // 'overlong U+07FF - 3 bytes'
+  [0xF0, 0x80, 0x9F, 0xBF], // 'overlong U+07FF - 4 bytes'
+  [0xF8, 0x80, 0x80, 0x9F, 0xBF], // 'overlong U+07FF - 5 bytes'
+  [0xFC, 0x80, 0x80, 0x80, 0x9F, 0xBF], // 'overlong U+07FF - 6 bytes'
+
+  [0xF0, 0x8F, 0xBF, 0xBF], // 'overlong U+FFFF - 4 bytes'
+  [0xF8, 0x80, 0x8F, 0xBF, 0xBF], // 'overlong U+FFFF - 5 bytes'
+  [0xFC, 0x80, 0x80, 0x8F, 0xBF, 0xBF], // 'overlong U+FFFF - 6 bytes'
+
+  [0xF8, 0x84, 0x8F, 0xBF, 0xBF], // 'overlong U+10FFFF - 5 bytes'
+  [0xFC, 0x80, 0x84, 0x8F, 0xBF, 0xBF], // 'overlong U+10FFFF - 6 bytes'
+
+  // UTF-16 surrogates encoded as code points in UTF-8
+  [0xED, 0xA0, 0x80], // 'lead surrogate'
+  [0xED, 0xB0, 0x80], // 'trail surrogate'
+  [0xED, 0xA0, 0x80, 0xED, 0xB0, 0x80], // 'surrogate pair'
+].forEach((input) => {
+  assert.strictEqual(isUtf8(Buffer.from(input)), false);
+});
+
+[
+  null,
+  undefined,
+  'hello',
+  true,
+  false,
+].forEach((input) => {
+  assert.throws(
+    () => { isUtf8(input); },
+    {
+      code: 'ERR_INVALID_ARG_TYPE',
+    },
+  );
+});
+
+{
+  // Test with detached array buffers
+  const arrayBuffer = new ArrayBuffer(1024);
+  structuredClone(arrayBuffer, { transfer: [arrayBuffer] });
+  assert.throws(
+    () => { isUtf8(arrayBuffer); },
+    {
+      code: 'ERR_INVALID_STATE'
+    }
+  );
+}