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
|
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/********************************************************************
* COPYRIGHT:
* Copyright (c) 1997-2010, International Business Machines Corporation and
* others. All Rights Reserved.
********************************************************************/
#include "unicode/utypes.h"
#include "unicode/uchar.h"
#include "unicode/normlzr.h"
#include "unicode/uniset.h"
#include "unicode/usetiter.h"
#include "unicode/schriter.h"
#include "tstnorm.h"
#if !UCONFIG_NO_NORMALIZATION
static UErrorCode status = U_ZERO_ERROR;
// test APIs that are not otherwise used - improve test coverage
void
BasicNormalizerTest::TestNormalizerAPI() {
// instantiate a Normalizer from a CharacterIterator
UnicodeString s=UnicodeString("a\\u0308\\uac00\\U0002f800", "").unescape();
s.append(s); // make s a bit longer and more interesting
StringCharacterIterator iter(s);
Normalizer norm(iter, UNORM_NFC);
if(norm.next()!=0xe4) {
dataerrln("error in Normalizer(CharacterIterator).next()");
}
// test copy constructor
Normalizer copy(norm);
if(copy.next()!=0xac00) {
dataerrln("error in Normalizer(Normalizer(CharacterIterator)).next()");
}
// test clone(), ==, and hashCode()
Normalizer *clone=copy.clone();
if(*clone!=copy) {
errln("error in Normalizer(Normalizer(CharacterIterator)).clone()!=copy");
}
// clone must have the same hashCode()
if(clone->hashCode()!=copy.hashCode()) {
errln("error in Normalizer(Normalizer(CharacterIterator)).clone()->hashCode()!=copy.hashCode()");
}
if(clone->next()!=0x4e3d) {
dataerrln("error in Normalizer(Normalizer(CharacterIterator)).clone()->next()");
}
// position changed, must change hashCode()
if(clone->hashCode()==copy.hashCode()) {
errln("error in Normalizer(Normalizer(CharacterIterator)).clone()->next().hashCode()==copy.hashCode()");
}
delete clone;
clone = nullptr;
// test compose() and decompose()
UnicodeString tel, nfkc, nfkd;
tel = UnicodeString(1, static_cast<UChar32>(0x2121), 10);
tel.insert(1, static_cast<char16_t>(0x301));
UErrorCode errorCode=U_ZERO_ERROR;
Normalizer::compose(tel, true, 0, nfkc, errorCode);
Normalizer::decompose(tel, true, 0, nfkd, errorCode);
if(U_FAILURE(errorCode)) {
dataerrln("error in Normalizer::(de)compose(): %s", u_errorName(errorCode));
} else if(
nfkc!=UnicodeString("TE\\u0139TELTELTELTELTELTELTELTELTEL", "").unescape() ||
nfkd!=UnicodeString("TEL\\u0301TELTELTELTELTELTELTELTELTEL", "").unescape()
) {
errln("error in Normalizer::(de)compose(): wrong result(s)");
}
// test setIndex()
norm.setIndexOnly(3);
if(norm.current()!=0x4e3d) {
dataerrln("error in Normalizer(CharacterIterator).setIndex(3)");
}
// test setText(CharacterIterator) and getText()
UnicodeString out, out2;
errorCode=U_ZERO_ERROR;
copy.setText(iter, errorCode);
if(U_FAILURE(errorCode)) {
errln("error Normalizer::setText() failed: %s", u_errorName(errorCode));
} else {
copy.getText(out);
iter.getText(out2);
if( out!=out2 ||
copy.startIndex()!=iter.startIndex() ||
copy.endIndex()!=iter.endIndex()
) {
errln("error in Normalizer::setText() or Normalizer::getText()");
}
}
// test setText(char16_t *), getUMode() and setMode()
errorCode=U_ZERO_ERROR;
copy.setText(s.getBuffer()+1, s.length()-1, errorCode);
copy.setMode(UNORM_NFD);
if(copy.getUMode()!=UNORM_NFD) {
errln("error in Normalizer::setMode() or Normalizer::getUMode()");
}
if(copy.next()!=0x308 || copy.next()!=0x1100) {
dataerrln("error in Normalizer::setText(char16_t *) or Normalizer::setMode()");
}
// test setText(char16_t *, length=-1)
errorCode=U_ZERO_ERROR;
// NUL-terminate s
s.append(static_cast<char16_t>(0)); // append NUL
s.truncate(s.length()-1); // undo length change
copy.setText(s.getBuffer()+1, -1, errorCode);
if(copy.endIndex()!=s.length()-1) {
errln("error in Normalizer::setText(char16_t *, -1)");
}
// test setOption() and getOption()
copy.setOption(0xaa0000, true);
copy.setOption(0x20000, false);
if(!copy.getOption(0x880000) || copy.getOption(0x20000)) {
errln("error in Normalizer::setOption() or Normalizer::getOption()");
}
// test last()/previous() with an internal buffer overflow
errorCode=U_ZERO_ERROR;
copy.setText(UnicodeString(1000, static_cast<UChar32>(0x308), 1000), errorCode);
if(copy.last()!=0x308) {
errln("error in Normalizer(1000*U+0308).last()");
}
// test UNORM_NONE
norm.setMode(UNORM_NONE);
if(norm.first()!=0x61 || norm.next()!=0x308 || norm.last()!=0x2f800) {
errln("error in Normalizer(UNORM_NONE).first()/next()/last()");
}
Normalizer::normalize(s, UNORM_NONE, 0, out, status);
if(out!=s) {
errln("error in Normalizer::normalize(UNORM_NONE)");
}
// test that the same string can be used as source and destination
s.setTo(static_cast<char16_t>(0xe4));
Normalizer::normalize(s, UNORM_NFD, 0, s, status);
if(s.charAt(1)!=0x308) {
dataerrln("error in Normalizer::normalize(UNORM_NFD, self)");
}
Normalizer::normalize(s, UNORM_NFC, 0, s, status);
if(s.charAt(0)!=0xe4) {
dataerrln("error in Normalizer::normalize(UNORM_NFC, self)");
}
Normalizer::decompose(s, false, 0, s, status);
if(s.charAt(1)!=0x308) {
dataerrln("error in Normalizer::decompose(self)");
}
Normalizer::compose(s, false, 0, s, status);
if(s.charAt(0)!=0xe4) {
dataerrln("error in Normalizer::compose(self)");
}
Normalizer::concatenate(s, s, s, UNORM_NFC, 0, status);
if(s.charAt(1)!=0xe4) {
dataerrln("error in Normalizer::decompose(self)");
}
}
#endif
|
