Switch to lowercase and exodus/bytes

.github/workflows/build.yml

@@ -12,9 +12,14 @@ jobs:
       fail-fast: false
       matrix:
         node-version:
-          - 18
+          # Explicitly test minimum Node.js versions. Keep in sync with package.json.
+          - 20.19.0
           - 20
-          - latest
+          - 22.12.0
+          - 22
+          - 24.0.0
+          - lts/*   # currently 24
+          - latest  # currently 25
     steps:
     - uses: actions/checkout@v4
     - uses: actions/setup-node@v4

README.md

@@ -12,11 +12,11 @@ const sniffedEncoding = htmlEncodingSniffer(htmlBytes);
 
 The passed bytes are given as a `Uint8Array`; the Node.js `Buffer` subclass of `Uint8Array` will also work, as shown above.
 
-The returned value will be a canonical [encoding name](https://encoding.spec.whatwg.org/#names-and-labels) (not a label). You might then combine this with the [whatwg-encoding](https://github.com/jsdom/whatwg-encoding) package to decode the result:
+The returned value will be an [encoding label](https://encoding.spec.whatwg.org/#names-and-labels), and in particular, the label which is a lowercased version of the encoding's name. You might then combine this with the [`@exodus/bytes`](https://github.com/ExodusOSS/bytes/) package to decode the result:
 
 ```js
-const whatwgEncoding = require("whatwg-encoding");
-const htmlString = whatwgEncoding.decode(htmlBytes, sniffedEncoding);
+const { TextDecoder } = require("@exodus/bytes");
+const htmlString = (new TextEncoder(sniffedEncoding)).decode(htmlBytes);
 ```
 
 ## Options

lib/html-encoding-sniffer.js

@@ -1,12 +1,12 @@
 "use strict";
-const whatwgEncoding = require("whatwg-encoding");
+const { getBOMEncoding, normalizeEncoding: labelToName } = require("@exodus/bytes/encoding-lite.js");
 
 // https://html.spec.whatwg.org/#encoding-sniffing-algorithm
 module.exports = (uint8Array, { transportLayerEncodingLabel, defaultEncoding = "windows-1252" } = {}) => {
-  let encoding = whatwgEncoding.getBOMEncoding(uint8Array);
+  let encoding = getBOMEncoding(uint8Array);
 
   if (encoding === null && transportLayerEncodingLabel !== undefined) {
-    encoding = whatwgEncoding.labelToName(transportLayerEncodingLabel);
+    encoding = labelToName(transportLayerEncodingLabel);
   }
 
   if (encoding === null) {
@@ -69,7 +69,7 @@ function prescanMetaCharset(uint8Array) {
                 needPragma = true;
               }
             } else if (attrRes.attr.name === "charset") {
-              charset = whatwgEncoding.labelToName(attrRes.attr.value);
+              charset = labelToName(attrRes.attr.value);
               needPragma = false;
             }
           }
@@ -86,8 +86,8 @@ function prescanMetaCharset(uint8Array) {
           continue;
         }
 
-        if (charset === "UTF-16LE" || charset === "UTF-16BE") {
-          charset = "UTF-8";
+        if (charset === "utf-16le" || charset === "utf-16be") {
+          charset = "utf-8";
         }
         if (charset === "x-user-defined") {
           charset = "windows-1252";
@@ -271,7 +271,7 @@ function extractCharacterEncodingFromMeta(string) {
     const nextIndex = string.indexOf(string[position], position + 1);
 
     if (nextIndex !== -1) {
-      return whatwgEncoding.labelToName(string.substring(position + 1, nextIndex));
+      return labelToName(string.substring(position + 1, nextIndex));
     }
 
     // It is an unmatched quotation mark
@@ -287,7 +287,7 @@ function extractCharacterEncodingFromMeta(string) {
     string.length :
     position + indexOfASCIIWhitespaceOrSemicolon + 1;
 
-  return whatwgEncoding.labelToName(string.substring(position, end));
+  return labelToName(string.substring(position, end));
 }
 
 function isSpaceCharacter(c) {

package.json

@@ -18,13 +18,13 @@
     "lint": "eslint ."
   },
   "dependencies": {
-    "whatwg-encoding": "^3.1.1"
+    "@exodus/bytes": "^1.0.0"
   },
   "devDependencies": {
     "@domenic/eslint-config": "^3.0.0",
     "eslint": "^8.53.0"
   },
   "engines": {
-    "node": ">=18"
+    "node": "^20.19.0 || ^22.12.0 || >=24.0.0"
   }
 }

test/tests.js

@@ -25,7 +25,7 @@ for (const file of fs.readdirSync(path.resolve(__dirname, "fixtures/bom"))) {
     it(`should sniff as ${desiredEncoding}, given overriding options`, () => {
       const sniffedEncoding = htmlEncodingSniffer(buffer, {
         transportLayerEncodingLabel: "windows-1252",
-        defaultEncoding: "UTF-16LE"
+        defaultEncoding: "utf-16le"
       });
 
       assert.strictEqual(sniffedEncoding, desiredEncoding);
@@ -47,7 +47,7 @@ for (const file of fs.readdirSync(path.resolve(__dirname, "fixtures/normal"))) {
     it("should sniff as the transport layer encoding, given that", () => {
       const sniffedEncoding = htmlEncodingSniffer(buffer, {
         transportLayerEncodingLabel: "windows-1251",
-        defaultEncoding: "ISO-8859-16"
+        defaultEncoding: "iso-8859-16"
       });
 
       assert.strictEqual(sniffedEncoding, "windows-1251");
@@ -56,7 +56,7 @@ for (const file of fs.readdirSync(path.resolve(__dirname, "fixtures/normal"))) {
 
     it(`should sniff as ${desiredEncoding}, given only a default encoding`, () => {
       const sniffedEncoding = htmlEncodingSniffer(buffer, {
-        defaultEncoding: "ISO-8859-16"
+        defaultEncoding: "iso-8859-16"
       });
 
       assert.strictEqual(sniffedEncoding, desiredEncoding);
@@ -78,7 +78,7 @@ for (const file of fs.readdirSync(path.resolve(__dirname, "fixtures/no-result"))
     it("should sniff as the transport layer encoding, given that", () => {
       const sniffedEncoding = htmlEncodingSniffer(buffer, {
         transportLayerEncodingLabel: "windows-1251",
-        defaultEncoding: "ISO-8859-16"
+        defaultEncoding: "iso-8859-16"
       });
 
       assert.strictEqual(sniffedEncoding, "windows-1251");
@@ -87,10 +87,10 @@ for (const file of fs.readdirSync(path.resolve(__dirname, "fixtures/no-result"))
 
     it("should sniff as the default encoding, given that", () => {
       const sniffedEncoding = htmlEncodingSniffer(buffer, {
-        defaultEncoding: "ISO-8859-16"
+        defaultEncoding: "iso-8859-16"
       });
 
-      assert.strictEqual(sniffedEncoding, "ISO-8859-16");
+      assert.strictEqual(sniffedEncoding, "iso-8859-16");
     });
   });
 }
@@ -102,13 +102,13 @@ for (const file of fs.readdirSync(path.resolve(__dirname, "fixtures/utf"))) {
     it("should sniff as UTF-8, given no options", () => {
       const sniffedEncoding = htmlEncodingSniffer(buffer);
 
-      assert.strictEqual(sniffedEncoding, "UTF-8");
+      assert.strictEqual(sniffedEncoding, "utf-8");
     });
 
     it("should sniff as the transport layer encoding, given that", () => {
       const sniffedEncoding = htmlEncodingSniffer(buffer, {
         transportLayerEncodingLabel: "windows-1251",
-        defaultEncoding: "ISO-8859-16"
+        defaultEncoding: "iso-8859-16"
       });
 
       assert.strictEqual(sniffedEncoding, "windows-1251");
@@ -117,10 +117,10 @@ for (const file of fs.readdirSync(path.resolve(__dirname, "fixtures/utf"))) {
 
     it("should sniff as UTF-8, given only a default encoding", () => {
       const sniffedEncoding = htmlEncodingSniffer(buffer, {
-        defaultEncoding: "ISO-8859-16"
+        defaultEncoding: "iso-8859-16"
       });
 
-      assert.strictEqual(sniffedEncoding, "UTF-8");
+      assert.strictEqual(sniffedEncoding, "utf-8");
     });
   });
 }