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
|
/* Test case for bug 317216
*
* Uses nsIConverterInputStream to decode UTF-16 text with valid surrogate
* pairs and lone surrogate characters
*
* Sample text is: "A" in Mathematical Bold Capitals (U+1D400)
*
* The test uses buffers of 4 different lengths to test end of buffer in mid-
* UTF16 character and mid-surrogate pair
*/
const { NetUtil } = ChromeUtils.importESModule(
"resource://gre/modules/NetUtil.sys.mjs"
);
const test = [
// 0: Valid surrogate pair
[
"%D8%35%DC%20%00%2D%00%2D",
// expected: surrogate pair
"\uD835\uDC20--",
],
// 1: Lone high surrogate
[
"%D8%35%00%2D%00%2D",
// expected: one replacement char
"\uFFFD--",
],
// 2: Lone low surrogate
[
"%DC%20%00%2D%00%2D",
// expected: one replacement char
"\uFFFD--",
],
// 3: Two high surrogates
[
"%D8%35%D8%35%00%2D%00%2D",
// expected: two replacement chars
"\uFFFD\uFFFD--",
],
// 4: Two low surrogates
[
"%DC%20%DC%20%00%2D%00%2D",
// expected: two replacement chars
"\uFFFD\uFFFD--",
],
// 5: Low surrogate followed by high surrogate
[
"%DC%20%D8%35%00%2D%00%2D",
// expected: two replacement chars
"\uFFFD\uFFFD--",
],
// 6: Lone high surrogate followed by valid surrogate pair
[
"%D8%35%D8%35%DC%20%00%2D%00%2D",
// expected: replacement char followed by surrogate pair
"\uFFFD\uD835\uDC20--",
],
// 7: Lone low surrogate followed by valid surrogate pair
[
"%DC%20%D8%35%DC%20%00%2D%00%2D",
// expected: replacement char followed by surrogate pair
"\uFFFD\uD835\uDC20--",
],
// 8: Valid surrogate pair followed by lone high surrogate
[
"%D8%35%DC%20%D8%35%00%2D%00%2D",
// expected: surrogate pair followed by replacement char
"\uD835\uDC20\uFFFD--",
],
// 9: Valid surrogate pair followed by lone low surrogate
[
"%D8%35%DC%20%DC%20%00%2D%00%2D",
// expected: surrogate pair followed by replacement char
"\uD835\uDC20\uFFFD--",
],
// 10: Lone high surrogate at the end of the input
[
"%D8%35%",
// expected: one replacement char
"\uFFFD",
],
// 11: Half code unit at the end of the input
[
"%D8",
// expected: one replacement char
"\uFFFD",
],
];
const ConverterInputStream = Components.Constructor(
"@mozilla.org/intl/converter-input-stream;1",
"nsIConverterInputStream",
"init"
);
function testCase(testText, expectedText, bufferLength, charset) {
var dataURI = "data:text/plain;charset=" + charset + "," + testText;
var channel = NetUtil.newChannel({
uri: dataURI,
loadUsingSystemPrincipal: true,
});
var testInputStream = channel.open();
var testConverter = new ConverterInputStream(
testInputStream,
charset,
bufferLength,
0xfffd
);
if (!(testConverter instanceof Ci.nsIUnicharLineInputStream)) {
throw new Error("not line input stream");
}
var outStr = "";
var more;
do {
// read the line and check for eof
var line = {};
more = testConverter.readLine(line);
outStr += line.value;
} while (more);
// escape the strings before comparing for better readability
Assert.equal(escape(outStr), escape(expectedText));
}
// Add 32 dummy characters to the test text to work around the minimum buffer
// size of an ns*Buffer
const MINIMUM_BUFFER_SIZE = 32;
function padBytes(str) {
var padding = "";
for (var i = 0; i < MINIMUM_BUFFER_SIZE; ++i) {
padding += "%00%2D";
}
return padding + str;
}
function padUnichars(str) {
var padding = "";
for (var i = 0; i < MINIMUM_BUFFER_SIZE; ++i) {
padding += "-";
}
return padding + str;
}
// Byte-swap %-encoded utf-16
function flip(str) {
return str.replace(/(%..)(%..)/g, "$2$1");
}
function run_test() {
for (var i = 0; i < 12; ++i) {
for (
var bufferLength = MINIMUM_BUFFER_SIZE;
bufferLength < MINIMUM_BUFFER_SIZE + 4;
++bufferLength
) {
var testText = padBytes(test[i][0]);
var expectedText = padUnichars(test[i][1]);
testCase(testText, expectedText, bufferLength, "UTF-16BE");
testCase(flip(testText), expectedText, bufferLength, "UTF-16LE");
}
}
}
|
