fix(duckduckgo): guard out-of-range numeric HTML entities (#96583)

decodeHtmlEntities decoded numeric entities with String.fromCodePoint(parseInt(...)) without a range check, so an out-of-range entity such as � or � threw RangeError and made the whole results page fail to parse. Validate the code point is within 0..0x10FFFF and keep the original entity text otherwise. Add a regression covering decimal and hex out-of-range entities plus a valid astral entity.

extensions/duckduckgo/src/ddg-client.ts

@@ -36,6 +36,10 @@ type DuckDuckGoResult = {
   snippet: string;
 };
 
+function isDecodableCodePoint(cp: number): boolean {
+  return Number.isInteger(cp) && cp >= 0 && cp <= 0x10ffff && (cp < 0xd800 || cp > 0xdfff);
+}
+
 function decodeHtmlEntities(text: string): string {
   return text.replace(
     /&(?:lt|gt|quot|apos|#39|#x27|#x2F|nbsp|ndash|mdash|hellip|amp|#\d+|#x[0-9a-f]+);/gi,
@@ -72,10 +76,12 @@ function decodeHtmlEntities(text: string): string {
         return "&";
       }
       if (normalized.startsWith("&#x")) {
-        return String.fromCodePoint(Number.parseInt(normalized.slice(3, -1), 16));
+        const codePoint = Number.parseInt(normalized.slice(3, -1), 16);
+        return isDecodableCodePoint(codePoint) ? String.fromCodePoint(codePoint) : entity;
       }
       if (normalized.startsWith("&#")) {
-        return String.fromCodePoint(Number.parseInt(normalized.slice(2, -1), 10));
+        const codePoint = Number.parseInt(normalized.slice(2, -1), 10);
+        return isDecodableCodePoint(codePoint) ? String.fromCodePoint(codePoint) : entity;
       }
       return entity;
     },

extensions/duckduckgo/src/ddg-search-provider.test.ts

@@ -205,6 +205,20 @@ describe("duckduckgo web search provider", () => {
     );
   });
 
+  it("leaves out-of-range numeric html entities intact instead of throwing", () => {
+    expect(() => ddgClientTesting.decodeHtmlEntities("Result � end")).not.toThrow();
+    expect(ddgClientTesting.decodeHtmlEntities("Result � end")).toBe(
+      "Result � end",
+    );
+    expect(ddgClientTesting.decodeHtmlEntities("Hex � tail")).toBe("Hex � tail");
+    // Surrogate-range entities would decode to lone UTF-16 surrogates; keep them intact.
+    expect(ddgClientTesting.decodeHtmlEntities("Bad � end")).toBe("Bad � end");
+    expect(ddgClientTesting.decodeHtmlEntities("Bad � end")).toBe("Bad � end");
+    expect(ddgClientTesting.decodeHtmlEntities("Bad � end")).toBe("Bad � end");
+    // A valid supplementary-plane entity still decodes.
+    expect(ddgClientTesting.decodeHtmlEntities("Smile 😀")).toBe("Smile 😀");
+  });
+
   it("does not double-decode escaped entities (decodes & last)", () => {
     // A result whose text literally shows "<" arrives double-encoded as
     // "&amp;lt;". Decoding &amp; first would re-decode it into "<", corrupting