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,

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;

},

);

});

it("leaves out-of-range numeric html entities intact instead of throwing", () => {

expect(() => ddgClientTesting.decodeHtmlEntities("Result &#99999999; end")).not.toThrow();

expect(ddgClientTesting.decodeHtmlEntities("Result &#99999999; end")).toBe(

"Result &#99999999; end",

);

expect(ddgClientTesting.decodeHtmlEntities("Hex &#x110000; tail")).toBe("Hex &#x110000; tail");

// Surrogate-range entities would decode to lone UTF-16 surrogates; keep them intact.

expect(ddgClientTesting.decodeHtmlEntities("Bad &#55296; end")).toBe("Bad &#55296; end");

expect(ddgClientTesting.decodeHtmlEntities("Bad &#xD800; end")).toBe("Bad &#xD800; end");

expect(ddgClientTesting.decodeHtmlEntities("Bad &#xDFFF; end")).toBe("Bad &#xDFFF; end");

// A valid supplementary-plane entity still decodes.

expect(ddgClientTesting.decodeHtmlEntities("Smile &#128512;")).toBe("Smile 😀");

});

it("does not double-decode escaped entities (decodes &amp; last)", () => {

// A result whose text literally shows "&lt;" arrives double-encoded as

// "&amp;lt;". Decoding &amp; first would re-decode it into "<", corrupting