1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
|
'use strict';
require('../common');
const assert = require('assert');
const inspect = require('util').inspect;
const StringDecoder = require('string_decoder').StringDecoder;
// Test default encoding
let decoder = new StringDecoder();
assert.strictEqual(decoder.encoding, 'utf8');
// UTF-8
test('utf-8', Buffer.from('$', 'utf-8'), '$');
test('utf-8', Buffer.from('¢', 'utf-8'), '¢');
test('utf-8', Buffer.from('€', 'utf-8'), '€');
test('utf-8', Buffer.from('𤭢', 'utf-8'), '𤭢');
// A mixed ascii and non-ascii string
// Test stolen from deps/v8/test/cctest/test-strings.cc
// U+02E4 -> CB A4
// U+0064 -> 64
// U+12E4 -> E1 8B A4
// U+0030 -> 30
// U+3045 -> E3 81 85
test(
'utf-8',
Buffer.from([0xCB, 0xA4, 0x64, 0xE1, 0x8B, 0xA4, 0x30, 0xE3, 0x81, 0x85]),
'\u02e4\u0064\u12e4\u0030\u3045'
);
// Some invalid input, known to have caused trouble with chunking
// in https://github.com/nodejs/node/pull/7310#issuecomment-226445923
// 00: |00000000 ASCII
// 41: |01000001 ASCII
// B8: 10|111000 continuation
// CC: 110|01100 two-byte head
// E2: 1110|0010 three-byte head
// F0: 11110|000 four-byte head
// F1: 11110|001'another four-byte head
// FB: 111110|11 "five-byte head", not UTF-8
test('utf-8', Buffer.from('C9B5A941', 'hex'), '\u0275\ufffdA');
test('utf-8', Buffer.from('E2', 'hex'), '\ufffd');
test('utf-8', Buffer.from('E241', 'hex'), '\ufffdA');
test('utf-8', Buffer.from('CCCCB8', 'hex'), '\ufffd\u0338');
test('utf-8', Buffer.from('F0B841', 'hex'), '\ufffdA');
test('utf-8', Buffer.from('F1CCB8', 'hex'), '\ufffd\u0338');
test('utf-8', Buffer.from('F0FB00', 'hex'), '\ufffd\ufffd\0');
test('utf-8', Buffer.from('CCE2B8B8', 'hex'), '\ufffd\u2e38');
test('utf-8', Buffer.from('E2B8CCB8', 'hex'), '\ufffd\u0338');
test('utf-8', Buffer.from('E2FBCC01', 'hex'), '\ufffd\ufffd\ufffd\u0001');
test('utf-8', Buffer.from('CCB8CDB9', 'hex'), '\u0338\u0379');
// CESU-8 of U+1D40D
test('utf-8', Buffer.from('EDA0B5EDB08D', 'hex'), '\ufffd\ufffd');
// UCS-2
test('ucs2', Buffer.from('ababc', 'ucs2'), 'ababc');
// UTF-16LE
test('utf16le', Buffer.from('3DD84DDC', 'hex'), '\ud83d\udc4d'); // thumbs up
// Additional UTF-8 tests
decoder = new StringDecoder('utf8');
assert.strictEqual(decoder.write(Buffer.from('E1', 'hex')), '');
assert.strictEqual(decoder.end(), '\ufffd');
decoder = new StringDecoder('utf8');
assert.strictEqual(decoder.write(Buffer.from('E18B', 'hex')), '');
assert.strictEqual(decoder.end(), '\ufffd');
decoder = new StringDecoder('utf8');
assert.strictEqual(decoder.write(Buffer.from('\ufffd')), '\ufffd');
assert.strictEqual(decoder.end(), '');
decoder = new StringDecoder('utf8');
assert.strictEqual(decoder.write(Buffer.from('\ufffd\ufffd\ufffd')),
'\ufffd\ufffd\ufffd');
assert.strictEqual(decoder.end(), '');
decoder = new StringDecoder('utf8');
assert.strictEqual(decoder.write(Buffer.from('EFBFBDE2', 'hex')), '\ufffd');
assert.strictEqual(decoder.end(), '\ufffd');
decoder = new StringDecoder('utf8');
assert.strictEqual(decoder.write(Buffer.from('F1', 'hex')), '');
assert.strictEqual(decoder.write(Buffer.from('41F2', 'hex')), '\ufffdA');
assert.strictEqual(decoder.end(), '\ufffd');
// Additional utf8Text test
decoder = new StringDecoder('utf8');
assert.strictEqual(decoder.text(Buffer.from([0x41]), 2), '');
// Additional UTF-16LE surrogate pair tests
decoder = new StringDecoder('utf16le');
assert.strictEqual(decoder.write(Buffer.from('3DD8', 'hex')), '');
assert.strictEqual(decoder.write(Buffer.from('4D', 'hex')), '');
assert.strictEqual(decoder.write(Buffer.from('DC', 'hex')), '\ud83d\udc4d');
assert.strictEqual(decoder.end(), '');
decoder = new StringDecoder('utf16le');
assert.strictEqual(decoder.write(Buffer.from('3DD8', 'hex')), '');
assert.strictEqual(decoder.end(), '\ud83d');
decoder = new StringDecoder('utf16le');
assert.strictEqual(decoder.write(Buffer.from('3DD8', 'hex')), '');
assert.strictEqual(decoder.write(Buffer.from('4D', 'hex')), '');
assert.strictEqual(decoder.end(), '\ud83d');
assert.throws(() => {
new StringDecoder(1);
}, /^Error: Unknown encoding: 1$/);
assert.throws(() => {
new StringDecoder('test');
}, /^Error: Unknown encoding: test$/);
// test verifies that StringDecoder will correctly decode the given input
// buffer with the given encoding to the expected output. It will attempt all
// possible ways to write() the input buffer, see writeSequences(). The
// singleSequence allows for easy debugging of a specific sequence which is
// useful in case of test failures.
function test(encoding, input, expected, singleSequence) {
let sequences;
if (!singleSequence) {
sequences = writeSequences(input.length);
} else {
sequences = [singleSequence];
}
sequences.forEach((sequence) => {
const decoder = new StringDecoder(encoding);
let output = '';
sequence.forEach((write) => {
output += decoder.write(input.slice(write[0], write[1]));
});
output += decoder.end();
if (output !== expected) {
const message =
'Expected "' + unicodeEscape(expected) + '", ' +
'but got "' + unicodeEscape(output) + '"\n' +
'input: ' + input.toString('hex').match(/.{2}/g) + '\n' +
'Write sequence: ' + JSON.stringify(sequence) + '\n' +
'Full Decoder State: ' + inspect(decoder);
assert.fail(output, expected, message);
}
});
}
// unicodeEscape prints the str contents as unicode escape codes.
function unicodeEscape(str) {
let r = '';
for (let i = 0; i < str.length; i++) {
r += '\\u' + str.charCodeAt(i).toString(16);
}
return r;
}
// writeSequences returns an array of arrays that describes all possible ways a
// buffer of the given length could be split up and passed to sequential write
// calls.
//
// e.G. writeSequences(3) will return: [
// [ [ 0, 3 ] ],
// [ [ 0, 2 ], [ 2, 3 ] ],
// [ [ 0, 1 ], [ 1, 3 ] ],
// [ [ 0, 1 ], [ 1, 2 ], [ 2, 3 ] ]
// ]
function writeSequences(length, start, sequence) {
if (start === undefined) {
start = 0;
sequence = [];
} else if (start === length) {
return [sequence];
}
let sequences = [];
for (let end = length; end > start; end--) {
const subSequence = sequence.concat([[start, end]]);
const subSequences = writeSequences(length, end, subSequence, sequences);
sequences = sequences.concat(subSequences);
}
return sequences;
}
|