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
|
// Copyright (C) 2021 The Qt Company Ltd.
// SPDX-License-Identifier: LicenseRef-Qt-Commercial OR GPL-3.0-only
#include <QtCore/QUrl>
#include <QtCore/QFile>
#include <QTest>
#include <QSet>
#include <QByteArray>
#include <algorithm>
class tst_QUrlUts46 : public QObject
{
Q_OBJECT
private Q_SLOTS:
void idnaTestV2_data();
void idnaTestV2();
private:
// All error codes in UTR #46 revision 31 (Unicode 15.1):
// A4_1, A4_2,
// B1, B2, B3, B4, B5, B6,
// C1, C2,
// P4,
// V1, V2, V3, V5, V6,
// X4_2
//
// NOTE: moving this inside idnaTestV2_data() results in ICE with MSVC 2019
static const QSet<QByteArray> fatalErrors;
};
const QSet<QByteArray> tst_QUrlUts46::fatalErrors = {
"A4_2", // Empty ASCII label
};
/**
* Replace \uXXXX escapes in test case fields.
*/
static QString unescapeField(const QString &field)
{
static const QRegularExpression re(R"(\\u([[:xdigit:]]{4}))");
QString result;
qsizetype lastIdx = 0;
for (const auto &match : re.globalMatch(field)) {
// Add stuff before the match
result.append(field.mid(lastIdx, match.capturedStart() - lastIdx));
bool ok = false;
auto c = match.captured(1).toUInt(&ok, 16);
if (!ok) {
qFatal("Failed to parse a Unicode escape: %s", qPrintable(match.captured(1)));
}
result.append(QChar(c));
lastIdx = match.capturedEnd();
}
// Append the unescaped end
result.append(field.mid(lastIdx));
return result;
}
void tst_QUrlUts46::idnaTestV2_data()
{
QTest::addColumn<QString>("source");
QTest::addColumn<QString>("toUnicode");
QTest::addColumn<bool>("toUnicodeOk");
QTest::addColumn<QString>("toAsciiN");
QTest::addColumn<bool>("toAsciiNOk");
QTest::addColumn<QString>("toAsciiT");
QTest::addColumn<bool>("toAsciiTOk");
QFile dataFile(QFINDTESTDATA("testdata/IdnaTestV2.txt"));
qDebug() << "Data file:" << dataFile.fileName();
QVERIFY(dataFile.open(QFile::ReadOnly));
auto isToAsciiOk = [](const QByteArray &s, bool ifEmpty) {
if (s.isEmpty())
return ifEmpty;
Q_ASSERT(s.startsWith('[') && s.endsWith(']'));
const auto errors = s.sliced(1, s.size() - 2).split(',');
// NOTE: empty string is not in fatalErrors and it's ok
return std::all_of(errors.begin(), errors.end(),
[](auto &e) { return !fatalErrors.contains(e.trimmed()); });
};
for (unsigned int lineNo = 1; !dataFile.atEnd(); lineNo++) {
auto line = dataFile.readLine().trimmed();
int commentIdx = line.indexOf('#');
if (commentIdx != -1)
line = line.left(commentIdx).trimmed();
if (line.isEmpty())
continue;
auto fields = line.split(';');
Q_ASSERT(fields.size() == 7);
for (auto &field : fields)
field = unescapeField(field.trimmed()).toUtf8();
const QString &source = fields[0];
QString toUnicode = fields[1].isEmpty() ? source : fields[1];
bool toUnicodeOk = fields[2].isEmpty();
bool toUnicodeOkForAscii = isToAsciiOk(fields[2], true);
QString toAsciiN = fields[3].isEmpty() ? toUnicode : fields[3];
bool toAsciiNOk = isToAsciiOk(fields[4], toUnicodeOkForAscii);
QString toAsciiT = fields[5].isEmpty() ? toAsciiN : fields[5];
bool toAsciiTOk = isToAsciiOk(fields[6], toAsciiNOk);
QTest::addRow("line %u", lineNo) << source << toUnicode << toUnicodeOk << toAsciiN
<< toAsciiNOk << toAsciiT << toAsciiTOk;
}
}
void tst_QUrlUts46::idnaTestV2()
{
QFETCH(QString, source);
QFETCH(QString, toUnicode);
QFETCH(bool, toUnicodeOk);
QFETCH(QString, toAsciiN);
QFETCH(bool, toAsciiNOk);
QFETCH(QString, toAsciiT);
QFETCH(bool, toAsciiTOk);
QString toAceN = QUrl::toAce(source);
if (toUnicodeOk && toAsciiNOk)
QCOMPARE(toAceN, toAsciiN);
else if (toAsciiNOk)
QVERIFY(toAceN.isEmpty() || toAceN == toAsciiN);
else
QCOMPARE(toAceN, QString());
QString toAceT = QUrl::toAce(source, QUrl::AceTransitionalProcessing);
if (toUnicodeOk && toAsciiTOk)
QCOMPARE(toAceT, toAsciiT);
else if (toAsciiTOk)
QVERIFY(toAceT.isEmpty() || toAceT == toAsciiT);
else
QCOMPARE(toAceT, QString());
QString normalized = QUrl::fromAce(toAceN.toUtf8(), QUrl::IgnoreIDNWhitelist);
if (toUnicodeOk && !toAceN.isEmpty())
QCOMPARE(normalized, toUnicode);
else
QCOMPARE(normalized, toAceN);
}
QTEST_APPLESS_MAIN(tst_QUrlUts46)
#include "tst_qurluts46.moc"
|
