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
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
|
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
*
* Copyright (C) 2001-2011, International Business Machines
* Corporation and others. All Rights Reserved.
*
*******************************************************************************
* file name: casetrn.cpp
* encoding: UTF-8
* tab size: 8 (not used)
* indentation:4
*
* created on: 2004sep03
* created by: Markus W. Scherer
*
* Implementation class for lower-/upper-/title-casing transliterators.
*/
#include <_foundation_unicode/utypes.h>
#if !UCONFIG_NO_TRANSLITERATION
#include <_foundation_unicode/uchar.h>
#include <_foundation_unicode/ustring.h>
#include <_foundation_unicode/utf.h>
#include <_foundation_unicode/utf16.h>
#include "tolowtrn.h"
#include "ucase.h"
#include "cpputils.h"
/* case context iterator using a Replaceable */
U_CFUNC UChar32 U_CALLCONV
utrans_rep_caseContextIterator(void *context, int8_t dir)
{
U_NAMESPACE_USE
UCaseContext *csc=(UCaseContext *)context;
Replaceable *rep=(Replaceable *)csc->p;
UChar32 c;
if(dir<0) {
/* reset for backward iteration */
csc->index=csc->cpStart;
csc->dir=dir;
} else if(dir>0) {
/* reset for forward iteration */
csc->index=csc->cpLimit;
csc->dir=dir;
} else {
/* continue current iteration direction */
dir=csc->dir;
}
// automatically adjust start and limit if the Replaceable disagrees
// with the original values
if(dir<0) {
if(csc->start<csc->index) {
c=rep->char32At(csc->index-1);
if(c<0) {
csc->start=csc->index;
} else {
csc->index-=U16_LENGTH(c);
return c;
}
}
} else {
// detect, and store in csc->b1, if we hit the limit
if(csc->index<csc->limit) {
c=rep->char32At(csc->index);
if(c<0) {
csc->limit=csc->index;
csc->b1=true;
} else {
csc->index+=U16_LENGTH(c);
return c;
}
} else {
csc->b1=true;
}
}
return U_SENTINEL;
}
U_NAMESPACE_BEGIN
UOBJECT_DEFINE_ABSTRACT_RTTI_IMPLEMENTATION(CaseMapTransliterator)
/**
* Constructs a transliterator.
*/
CaseMapTransliterator::CaseMapTransliterator(const UnicodeString &id, UCaseMapFull *map) :
Transliterator(id, 0),
fMap(map)
{
// TODO test incremental mode with context-sensitive text (e.g. greek sigma)
// TODO need to call setMaximumContextLength()?!
}
/**
* Destructor.
*/
CaseMapTransliterator::~CaseMapTransliterator() {
}
/**
* Copy constructor.
*/
CaseMapTransliterator::CaseMapTransliterator(const CaseMapTransliterator& o) :
Transliterator(o),
fMap(o.fMap)
{
}
/**
* Assignment operator.
*/
/*CaseMapTransliterator& CaseMapTransliterator::operator=(const CaseMapTransliterator& o) {
Transliterator::operator=(o);
fMap = o.fMap;
return *this;
}*/
/**
* Transliterator API.
*/
/*CaseMapTransliterator* CaseMapTransliterator::clone() const {
return new CaseMapTransliterator(*this);
}*/
/**
* Implements {@link Transliterator#handleTransliterate}.
*/
void CaseMapTransliterator::handleTransliterate(Replaceable& text,
UTransPosition& offsets,
UBool isIncremental) const
{
if (offsets.start >= offsets.limit) {
return;
}
UCaseContext csc;
uprv_memset(&csc, 0, sizeof(csc));
csc.p = &text;
csc.start = offsets.contextStart;
csc.limit = offsets.contextLimit;
UnicodeString tmp;
const char16_t *s;
UChar32 c;
int32_t textPos, delta, result;
for(textPos=offsets.start; textPos<offsets.limit;) {
csc.cpStart=textPos;
c=text.char32At(textPos);
csc.cpLimit=textPos+=U16_LENGTH(c);
result=fMap(c, utrans_rep_caseContextIterator, &csc, &s, UCASE_LOC_ROOT);
if(csc.b1 && isIncremental) {
// fMap() tried to look beyond the context limit
// wait for more input
offsets.start=csc.cpStart;
return;
}
if(result>=0) {
// replace the current code point with its full case mapping result
// see UCASE_MAX_STRING_LENGTH
if(result<=UCASE_MAX_STRING_LENGTH) {
// string s[result]
tmp.setTo(false, s, result);
delta=result-U16_LENGTH(c);
} else {
// single code point
tmp.setTo(result);
delta=tmp.length()-U16_LENGTH(c);
}
text.handleReplaceBetween(csc.cpStart, textPos, tmp);
if(delta!=0) {
textPos+=delta;
csc.limit=offsets.contextLimit+=delta;
offsets.limit+=delta;
}
}
}
offsets.start=textPos;
}
U_NAMESPACE_END
#endif /* #if !UCONFIG_NO_TRANSLITERATION */
|
