45da0e4a0e
Reject UTF-8 second bytes outside the Encoding Standard's per-lead-byte bounds before consuming the rest of each sequence. This keeps surrogate and out-of-range sequences from collapsing multiple malformed bytes into one replacement character. Also report an odd trailing UTF-16 byte as U+FFFD through the streaming code point path and route UTF-16 to_utf8() through the same logic. This keeps lazy and eager script decoding aligned for bytecode cache source hashes. Cover the malformed UTF-8 and UTF-16 cases in LibTextCodec, TextDecoder, and bytecode-cache source decoding tests.
19 lines
839 B
HTML
19 lines
839 B
HTML
<!DOCTYPE html>
|
|
<script src="../include.js"></script>
|
|
<script>
|
|
test(() => {
|
|
try {
|
|
let decoder = new TextDecoder("utf-8");
|
|
println(`[${decoder.decode(new Uint8Array([0x41, 0x42, 0x43]))}]`); // "ABC"
|
|
println(`[${decoder.decode()}]`);
|
|
|
|
const surrogate = decoder.decode(new Uint8Array([0xed, 0xa0, 0x80])); // U+D800
|
|
println(`[${surrogate.length}, ${surrogate.codePointAt(0).toString(16)}, ${surrogate.codePointAt(1).toString(16)}, ${surrogate.codePointAt(2).toString(16)}]`);
|
|
|
|
const truncatedTail = decoder.decode(new Uint8Array([0xf0, 0x9f, 0x98]));
|
|
println(`[${truncatedTail.length}, ${truncatedTail.codePointAt(0).toString(16)}]`);
|
|
} catch (e) {
|
|
println("ERROR: " + e.name + ": " + e.message);
|
|
}
|
|
});
|
|
</script>
|