test: split encoding tests where some cases can be run without ICU

Split the following tests:

- `test-whatwg-encoding-textdecoder-utf16-surrogates.js`
- `test-whatwg-encoding-textdecoder-ignorebom.js`
- `test-whatwg-encoding-textdecoder-streaming.js`

Each into two files: one that can be run without ICU and one that has
to be run with ICU. The latter can be replaced with WPT later.

PR-URL: https://github.com/nodejs/node/pull/25155
Reviewed-By: James M Snell <jasnell@gmail.com>

test/parallel/test-whatwg-encoding-custom-textdecoder-ignorebom.js

@@ -0,0 +1,30 @@
+'use strict';
+
+// From: https://github.com/w3c/web-platform-tests/blob/7f567fa29c/encoding/textdecoder-ignorebom.html
+// This is the part that can be run without ICU
+
+require('../common');
+
+const assert = require('assert');
+
+const cases = [
+  {
+    encoding: 'utf-8',
+    bytes: [0xEF, 0xBB, 0xBF, 0x61, 0x62, 0x63]
+  },
+  {
+    encoding: 'utf-16le',
+    bytes: [0xFF, 0xFE, 0x61, 0x00, 0x62, 0x00, 0x63, 0x00]
+  }
+];
+
+cases.forEach((testCase) => {
+  const BOM = '\uFEFF';
+  let decoder = new TextDecoder(testCase.encoding, { ignoreBOM: true });
+  const bytes = new Uint8Array(testCase.bytes);
+  assert.strictEqual(decoder.decode(bytes), `${BOM}abc`);
+  decoder = new TextDecoder(testCase.encoding, { ignoreBOM: false });
+  assert.strictEqual(decoder.decode(bytes), 'abc');
+  decoder = new TextDecoder(testCase.encoding);
+  assert.strictEqual(decoder.decode(bytes), 'abc');
+});

test/parallel/test-whatwg-encoding-custom-textdecoder-streaming.js

@@ -0,0 +1,38 @@
+'use strict';
+
+// From: https://github.com/w3c/web-platform-tests/blob/fa9436d12c/encoding/textdecoder-streaming.html
+// This is the part that can be run without ICU
+
+require('../common');
+
+const assert = require('assert');
+
+const string =
+  '\x00123ABCabc\x80\xFF\u0100\u1000\uFFFD\uD800\uDC00\uDBFF\uDFFF';
+const octets = {
+  'utf-8': [
+    0x00, 0x31, 0x32, 0x33, 0x41, 0x42, 0x43, 0x61, 0x62, 0x63, 0xc2, 0x80,
+    0xc3, 0xbf, 0xc4, 0x80, 0xe1, 0x80, 0x80, 0xef, 0xbf, 0xbd, 0xf0, 0x90,
+    0x80, 0x80, 0xf4, 0x8f, 0xbf, 0xbf],
+  'utf-16le': [
+    0x00, 0x00, 0x31, 0x00, 0x32, 0x00, 0x33, 0x00, 0x41, 0x00, 0x42, 0x00,
+    0x43, 0x00, 0x61, 0x00, 0x62, 0x00, 0x63, 0x00, 0x80, 0x00, 0xFF, 0x00,
+    0x00, 0x01, 0x00, 0x10, 0xFD, 0xFF, 0x00, 0xD8, 0x00, 0xDC, 0xFF, 0xDB,
+    0xFF, 0xDF]
+};
+
+Object.keys(octets).forEach((encoding) => {
+  for (let len = 1; len <= 5; ++len) {
+    const encoded = octets[encoding];
+    const decoder = new TextDecoder(encoding);
+    let out = '';
+    for (let i = 0; i < encoded.length; i += len) {
+      const sub = [];
+      for (let j = i; j < encoded.length && j < i + len; ++j)
+        sub.push(encoded[j]);
+      out += decoder.decode(new Uint8Array(sub), { stream: true });
+    }
+    out += decoder.decode();
+    assert.strictEqual(out, string);
+  }
+});

test/parallel/test-whatwg-encoding-custom-textdecoder-utf16-surrogates.js

@@ -1,6 +1,7 @@
 'use strict';
 
 // From: https://github.com/w3c/web-platform-tests/blob/39a67e2fff/encoding/textdecoder-utf16-surrogates.html
+// With the twist that we specifically test for Node.js error codes
 
 const common = require('../common');
 
@@ -43,7 +44,7 @@ const bad = [
 ];
 
 bad.forEach((t) => {
-
+  // TODO(joyeecheung): remove this when WPT is ported
   assert.strictEqual(
     new TextDecoder(t.encoding).decode(new Uint8Array(t.input)),
     t.expected);

test/parallel/test-whatwg-encoding-textdecoder-ignorebom.js

@@ -1,34 +1,31 @@
 'use strict';
 
 // From: https://github.com/w3c/web-platform-tests/blob/7f567fa29c/encoding/textdecoder-ignorebom.html
+// TODO(joyeecheung): replace this with WPT
 
 const common = require('../common');
 
+if (!common.hasIntl)
+  common.skip('missing Intl');
+
 const assert = require('assert');
 
 const cases = [
   {
     encoding: 'utf-8',
-    bytes: [0xEF, 0xBB, 0xBF, 0x61, 0x62, 0x63],
-    skipNoIntl: false
+    bytes: [0xEF, 0xBB, 0xBF, 0x61, 0x62, 0x63]
   },
   {
     encoding: 'utf-16le',
-    bytes: [0xFF, 0xFE, 0x61, 0x00, 0x62, 0x00, 0x63, 0x00],
-    skipNoIntl: false
+    bytes: [0xFF, 0xFE, 0x61, 0x00, 0x62, 0x00, 0x63, 0x00]
   },
   {
     encoding: 'utf-16be',
-    bytes: [0xFE, 0xFF, 0x00, 0x61, 0x00, 0x62, 0x00, 0x63],
-    skipNoIntl: true
+    bytes: [0xFE, 0xFF, 0x00, 0x61, 0x00, 0x62, 0x00, 0x63]
   }
 ];
 
 cases.forEach((testCase) => {
-  if (testCase.skipNoIntl && !common.hasIntl) {
-    console.log(`skipping ${testCase.encoding} because missing Intl`);
-    return; // skipping
-  }
   const BOM = '\uFEFF';
   let decoder = new TextDecoder(testCase.encoding, { ignoreBOM: true });
   const bytes = new Uint8Array(testCase.bytes);

test/parallel/test-whatwg-encoding-textdecoder-streaming.js

@@ -1,9 +1,13 @@
 'use strict';
 
 // From: https://github.com/w3c/web-platform-tests/blob/fa9436d12c/encoding/textdecoder-streaming.html
+// TODO(joyeecheung): replace this with WPT
 
 const common = require('../common');
 
+if (!common.hasIntl)
+  common.skip('missing Intl');
+
 const assert = require('assert');
 
 const string =

test/parallel/test-whatwg-encoding-textencoder-utf16-surrogates.js

@@ -1,6 +1,7 @@
 'use strict';
 
 // From: https://github.com/w3c/web-platform-tests/blob/fa9436d12c/encoding/textencoder-utf16-surrogates.html
+// TODO(joyeecheung): replace this with WPT
 
 require('../common');