From 4d2ea5117f0694ba30584fb4eba5c93c53bdf8e7 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Branimir=20Karad=C5=BEi=C4=87?= <bkaradzic@microsoft.com>
Date: Fri, 12 Jun 2026 20:08:17 -0700
Subject: [PATCH] TextDecoder: accept all WHATWG utf-8 encoding labels

The TextDecoder constructor only accepted the exact labels "utf-8"/"UTF-8"
and threw for every other spelling. Per the WHATWG Encoding Standard, an
encoding label is matched after stripping leading/trailing ASCII whitespace
and ASCII-lowercasing, and several labels ("utf8", "unicode-1-1-utf-8",
"unicode11utf8", "unicode20utf8", "x-unicode20utf8") all map to UTF-8.

Consumers such as the Babylon.js glTF/Draco loader construct
`new TextDecoder("utf8")`; the throw aborted decoding mid-load and (in
Babylon Native) left the loader in a state that drove a native out-of-bounds
write, observed as non-deterministic heap corruption on the Draco
validation tests.

Normalize the label per spec and accept all UTF-8 labels. Adds regression
tests for "utf8", case/whitespace variants, the other aliases, and a
still-rejected unsupported encoding.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---
 Polyfills/TextDecoder/Source/TextDecoder.cpp | 34 +++++++++++++++++++-
 Tests/UnitTests/Scripts/tests.ts             | 24 ++++++++++++++
 2 files changed, 57 insertions(+), 1 deletion(-)

diff --git a/Polyfills/TextDecoder/Source/TextDecoder.cpp b/Polyfills/TextDecoder/Source/TextDecoder.cpp
index 10e1d00b..56085432 100644
--- a/Polyfills/TextDecoder/Source/TextDecoder.cpp
+++ b/Polyfills/TextDecoder/Source/TextDecoder.cpp
@@ -33,7 +33,39 @@ namespace
             if (info.Length() > 0 && info[0].IsString())
             {
                 auto encoding = info[0].As<Napi::String>().Utf8Value();
-                if (encoding != "utf-8" && encoding != "UTF-8")
+
+                // Normalize per the WHATWG Encoding Standard "get an encoding" algorithm:
+                // strip leading/trailing ASCII whitespace and lowercase before matching the
+                // label. Several labels (e.g. "utf8", "unicode-1-1-utf-8") all map to UTF-8;
+                // callers such as the glTF/Draco loader pass "utf8".
+                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');
+                    }
+                }
+
+                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");
                 }
diff --git a/Tests/UnitTests/Scripts/tests.ts b/Tests/UnitTests/Scripts/tests.ts
index e0647092..344a41cc 100644
--- a/Tests/UnitTests/Scripts/tests.ts
+++ b/Tests/UnitTests/Scripts/tests.ts
@@ -1490,6 +1490,30 @@ describe("TextDecoder", function () {
         expect(result).to.equal("H\0i");
         expect(result.length).to.equal(3);
     });
+
+    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 () {