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
|
/**
* test_filter.cpp
*
* SPDX-FileCopyrightText: 2004 Zack Rusin <zack@kde.org>
*
* SPDX-License-Identifier: LGPL-2.1-or-later
*/
#include "test_filter.h"
#include "tokenizer_p.h"
#include <QTest>
#include <QVector>
QTEST_GUILESS_MAIN(SonnetFilterTest)
using namespace Sonnet;
struct Hit {
Hit(const QString &w, int s)
: word(w)
, start(s)
{
}
QString word;
int start;
};
void SonnetFilterTest::testLatin()
{
QString buffer(QStringLiteral(" This is a sample thing. Please test me ... He's don't Le'Clerk."));
QList<Hit> hits;
hits.append(Hit(QStringLiteral("This"), 2));
hits.append(Hit(QStringLiteral("is"), 7));
hits.append(Hit(QStringLiteral("a"), 14));
hits.append(Hit(QStringLiteral("sample"), 16));
hits.append(Hit(QStringLiteral("thing"), 23));
hits.append(Hit(QStringLiteral("Please"), 30));
hits.append(Hit(QStringLiteral("test"), 37));
hits.append(Hit(QStringLiteral("me"), 42));
hits.append(Hit(QStringLiteral("He's"), 53));
hits.append(Hit(QStringLiteral("don't"), 58));
hits.append(Hit(QStringLiteral("Le'Clerk"), 64));
WordTokenizer tokenizer;
tokenizer.setBuffer(buffer);
Token w;
int hitNumber = 0;
while (tokenizer.hasNext()) {
w = tokenizer.next();
QCOMPARE(w.toString(), hits[hitNumber].word);
QCOMPARE(w.position(), hits[hitNumber].start);
++hitNumber;
}
QCOMPARE(hitNumber, hits.count());
}
static QVector<ushort> convertToUnicode(const QString &str)
{
QVector<ushort> unicode;
for (int i = 0; i < str.length(); ++i) {
unicode += str[i].unicode();
}
return unicode;
}
void SonnetFilterTest::testIndic()
{
QString buffer;
QList<Hit> hits;
hits.append(Hit(QString::fromUtf8("मराठी"), 0));
hits.append(Hit(QString::fromUtf8("भाषा"), 6));
hits.append(Hit(QString::fromUtf8("महाराष्ट्र"), 11));
hits.append(Hit(QString::fromUtf8("व"), 22));
hits.append(Hit(QString::fromUtf8("गोवा"), 24));
hits.append(Hit(QString::fromUtf8("राज्याची"), 29));
hits.append(Hit(QString::fromUtf8("राजभाषा"), 38));
hits.append(Hit(QString::fromUtf8("असून"), 46));
hits.append(Hit(QString::fromUtf8("सुमारे"), 51));
hits.append(Hit(QString::fromUtf8("९"), 58)); // This is the number 9, so we don't spell-check it
hits.append(Hit(QString::fromUtf8("कोटी"), 60));
hits.append(Hit(QString::fromUtf8("लोकांची"), 65));
hits.append(Hit(QString::fromUtf8("मातृभाषा"), 73));
hits.append(Hit(QString::fromUtf8("आहे"), 82));
hits.append(Hit(QString::fromUtf8("मराठी"), 87));
hits.append(Hit(QString::fromUtf8("भाषा"), 93));
hits.append(Hit(QString::fromUtf8("कमीत"), 98));
hits.append(Hit(QString::fromUtf8("कमी"), 103));
hits.append(Hit(QString::fromUtf8("१०००"), 107)); // just a number
hits.append(Hit(QString::fromUtf8("वर्षापासून"), 112));
hits.append(Hit(QString::fromUtf8("अस्तित्वात"), 123));
hits.append(Hit(QString::fromUtf8("आहे"), 134));
buffer = QString::fromUtf8("मराठी भाषा महाराष्ट्र व गोवा राज्याची राजभाषा असून सुमारे ९ कोटी लोकांची मातृभाषा आहे. मराठी भाषा कमीत कमी १००० वर्षापासून अस्तित्वात आहे.");
WordTokenizer tokenizer;
tokenizer.setBuffer(buffer);
Token w;
int hitNumber = 0;
while (tokenizer.hasNext()) {
w = tokenizer.next();
QVector<ushort> unicode = convertToUnicode(w.toString());
QCOMPARE(w.toString(), hits[hitNumber].word);
QCOMPARE(w.position(), hits[hitNumber].start);
++hitNumber;
}
QCOMPARE(hitNumber, hits.count());
}
void SonnetFilterTest::testSentence()
{
QString buffer(QStringLiteral("This is a sample thing. Please test me ... He's don't Le'Clerk."));
QList<Hit> hits;
hits.append(Hit(QStringLiteral("This is a sample thing. "), 0));
hits.append(Hit(QStringLiteral("Please test me ... "), 28));
hits.append(Hit(QStringLiteral("He's don't Le'Clerk."), 51));
SentenceTokenizer tokenizer;
tokenizer.setBuffer(buffer);
Token w;
int hitNumber = 0;
while (tokenizer.hasNext()) {
w = tokenizer.next();
QCOMPARE(w.toString(), hits[hitNumber].word);
QCOMPARE(w.position(), hits[hitNumber].start);
++hitNumber;
}
QCOMPARE(hitNumber, hits.count());
}
#include "moc_test_filter.cpp"
|
