TextDecoder: accept all WHATWG utf-8 encoding labels

Polyfills/TextDecoder/Source/TextDecoder.cpp

@@ -6,6 +6,36 @@
 
 namespace
 {
+    // Normalize an encoding label per the WHATWG Encoding Standard "get an encoding"
+    // algorithm: strip leading/trailing ASCII whitespace and ASCII-lowercase the result.
+    std::string NormalizeEncodingLabel(const std::string& encoding)
+    {
+        const auto isAsciiWhitespace = [](char c) {
+            return c == '\t' || c == '\n' || c == '\f' || c == '\r' || c == ' ';
+        };
+
+        size_t begin = 0;
+        size_t end = encoding.size();
+        while (begin < end && isAsciiWhitespace(encoding[begin]))
+        {
+            ++begin;
+        }
+        while (end > begin && isAsciiWhitespace(encoding[end - 1]))
+        {
+            --end;
+        }
+
+        std::string label = encoding.substr(begin, end - begin);
+        for (auto& c : label)
+        {
+            if (c >= 'A' && c <= 'Z')
+            {
+                c = static_cast<char>(c - 'A' + 'a');
+            }
+        }
+        return label;
+    }
+
     class TextDecoder final : public Napi::ObjectWrap<TextDecoder>
     {
     public:
@@ -33,9 +63,18 @@ namespace
             if (info.Length() > 0 && info[0].IsString())
             {
                 auto encoding = info[0].As<Napi::String>().Utf8Value();
-                if (encoding != "utf-8" && encoding != "UTF-8")
+
+                // Several labels (e.g. "utf8", "unicode-1-1-utf-8") all map to UTF-8 after
+                // normalization; callers such as the glTF/Draco loader pass "utf8".
+                const std::string label = NormalizeEncodingLabel(encoding);
+                if (label != "utf-8" &&
+                    label != "utf8" &&
+                    label != "unicode-1-1-utf-8" &&
+                    label != "unicode11utf8" &&
+                    label != "unicode20utf8" &&
+                    label != "x-unicode20utf8")
                 {
-                    throw Napi::Error::New(Env(), "TextDecoder: unsupported encoding '" + encoding + "', only 'utf-8' is supported");
+                    throw Napi::Error::New(Env(), "TextDecoder: unsupported encoding '" + encoding + "', only UTF-8 is supported");
                 }
             }
         }

Tests/UnitTests/Scripts/tests.ts

@@ -1504,6 +1504,30 @@ describe("TextDecoder", function () {
         const decoder = new TextDecoder("utf-8");
         expect(decoder.decode(new Uint8Array([79, 75]))).to.equal("OK");
     });
+
+    it("should accept the WHATWG 'utf8' label (no hyphen)", function () {
+        const decoder = new TextDecoder("utf8");
+        const result = decoder.decode(new Uint8Array([72, 105])); // "Hi"
+        expect(result).to.equal("Hi");
+    });
+
+    it("should accept utf-8 labels case-insensitively and with surrounding whitespace", function () {
+        for (const label of ["UTF-8", "UTF8", "  utf-8  ", "\tUtf8\n"]) {
+            const decoder = new TextDecoder(label);
+            expect(decoder.decode(new Uint8Array([79, 75]))).to.equal("OK");
+        }
+    });
+
+    it("should accept the other WHATWG utf-8 aliases", function () {
+        for (const label of ["unicode-1-1-utf-8", "unicode11utf8", "unicode20utf8", "x-unicode20utf8"]) {
+            const decoder = new TextDecoder(label);
+            expect(decoder.decode(new Uint8Array([79, 75]))).to.equal("OK");
+        }
+    });
+
+    it("should still throw for a genuinely unsupported encoding", function () {
+        expect(() => new TextDecoder("utf-16")).to.throw();
+    });
 });
 
 describe("TextEncoder", function () {