1 // META: title=Encoding API: Streaming decode
2 // META: global=window,worker
3 // META: script=resources/encodings.js
4 // META: script=/common/sab.js
6 var string = '\x00123ABCabc\x80\xFF\u0100\u1000\uFFFD\uD800\uDC00\uDBFF\uDFFF';
8 'utf-8': [0x00,0x31,0x32,0x33,0x41,0x42,0x43,0x61,0x62,0x63,0xc2,0x80,
9 0xc3,0xbf,0xc4,0x80,0xe1,0x80,0x80,0xef,0xbf,0xbd,0xf0,0x90,
10 0x80,0x80,0xf4,0x8f,0xbf,0xbf],
11 'utf-16le': [0x00,0x00,0x31,0x00,0x32,0x00,0x33,0x00,0x41,0x00,0x42,0x00,
12 0x43,0x00,0x61,0x00,0x62,0x00,0x63,0x00,0x80,0x00,0xFF,0x00,
13 0x00,0x01,0x00,0x10,0xFD,0xFF,0x00,0xD8,0x00,0xDC,0xFF,0xDB,
15 'utf-16be': [0x00,0x00,0x00,0x31,0x00,0x32,0x00,0x33,0x00,0x41,0x00,0x42,
16 0x00,0x43,0x00,0x61,0x00,0x62,0x00,0x63,0x00,0x80,0x00,0xFF,
17 0x01,0x00,0x10,0x00,0xFF,0xFD,0xD8,0x00,0xDC,0x00,0xDB,0xFF,
21 ["ArrayBuffer", "SharedArrayBuffer"].forEach((arrayBufferOrSharedArrayBuffer) => {
22 Object.keys(octets).forEach(function(encoding) {
23 for (var len = 1; len <= 5; ++len) {
25 var encoded = octets[encoding];
28 var decoder = new TextDecoder(encoding);
29 for (var i = 0; i < encoded.length; i += len) {
31 for (var j = i; j < encoded.length && j < i + len; ++j) {
34 var uintArray = new Uint8Array(createBuffer(arrayBufferOrSharedArrayBuffer, sub.length));
36 out += decoder.decode(uintArray, {stream: true});
38 out += decoder.decode();
39 assert_equals(out, string);
40 }, 'Streaming decode: ' + encoding + ', ' + len + ' byte window (' + arrayBufferOrSharedArrayBuffer + ')');
45 function bytes(byteArray) {
46 const view = new Uint8Array(createBuffer(arrayBufferOrSharedArrayBuffer, byteArray.length));
51 const decoder = new TextDecoder();
53 assert_equals(decoder.decode(bytes([0xC1]), {stream: true}), "\uFFFD");
54 assert_equals(decoder.decode(), "");
56 assert_equals(decoder.decode(bytes([0xF5]), {stream: true}), "\uFFFD");
57 assert_equals(decoder.decode(), "");
59 assert_equals(decoder.decode(bytes([0xE0, 0x41]), {stream: true}), "\uFFFDA");
60 assert_equals(decoder.decode(bytes([0x42])), "B");
62 assert_equals(decoder.decode(bytes([0xE0, 0x80]), {stream: true}), "\uFFFD\uFFFD");
63 assert_equals(decoder.decode(bytes([0x80])), "\uFFFD");
65 assert_equals(decoder.decode(bytes([0xED, 0xA0]), {stream: true}), "\uFFFD\uFFFD");
66 assert_equals(decoder.decode(bytes([0x80])), "\uFFFD");
68 assert_equals(decoder.decode(bytes([0xF0, 0x41]), {stream: true}), "\uFFFDA");
69 assert_equals(decoder.decode(bytes([0x42]), {stream: true}), "B");
70 assert_equals(decoder.decode(bytes([0x43])), "C");
72 assert_equals(decoder.decode(bytes([0xF0, 0x80]), {stream: true}), "\uFFFD\uFFFD");
73 assert_equals(decoder.decode(bytes([0x80]), {stream: true}), "\uFFFD");
74 assert_equals(decoder.decode(bytes([0x80])), "\uFFFD");
76 assert_equals(decoder.decode(bytes([0xF4, 0xA0]), {stream: true}), "\uFFFD\uFFFD");
77 assert_equals(decoder.decode(bytes([0x80]), {stream: true}), "\uFFFD");
78 assert_equals(decoder.decode(bytes([0x80])), "\uFFFD");
80 assert_equals(decoder.decode(bytes([0xF0, 0x90, 0x41]), {stream: true}), "\uFFFDA");
81 assert_equals(decoder.decode(bytes([0x42])), "B");
83 // 4-byte UTF-8 sequences always correspond to non-BMP characters. Here
84 // we make sure that, although the first 3 bytes are enough to emit the
85 // lead surrogate, it only gets emitted when the fourth byte is read.
86 assert_equals(decoder.decode(bytes([0xF0, 0x9F, 0x92]), {stream: true}), "");
87 assert_equals(decoder.decode(bytes([0xA9])), "\u{1F4A9}");
88 }, `Streaming decode: UTF-8 chunk tests (${arrayBufferOrSharedArrayBuffer})`);