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
|
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
//
// Copyright (C) 2012 International Business Machines Corporation
// and others. All rights reserved.
//
// file: regeximp.cpp
//
// ICU Regular Expressions,
// miscellaneous implementation functions.
//
#include "unicode/utypes.h"
#if !UCONFIG_NO_REGULAR_EXPRESSIONS
#include "regeximp.h"
#include "unicode/utf16.h"
U_NAMESPACE_BEGIN
CaseFoldingUTextIterator::CaseFoldingUTextIterator(UText &text) :
fUText(text), fFoldChars(NULL), fFoldLength(0) {
}
CaseFoldingUTextIterator::~CaseFoldingUTextIterator() {}
UChar32 CaseFoldingUTextIterator::next() {
UChar32 foldedC;
UChar32 originalC;
if (fFoldChars == NULL) {
// We are not in a string folding of an earlier character.
// Start handling the next char from the input UText.
originalC = UTEXT_NEXT32(&fUText);
if (originalC == U_SENTINEL) {
return originalC;
}
fFoldLength = ucase_toFullFolding(originalC, &fFoldChars, U_FOLD_CASE_DEFAULT);
if (fFoldLength >= UCASE_MAX_STRING_LENGTH || fFoldLength < 0) {
// input code point folds to a single code point, possibly itself.
// See comment in ucase.h for explanation of return values from ucase_toFullFoldings.
if (fFoldLength < 0) {
fFoldLength = ~fFoldLength;
}
foldedC = (UChar32)fFoldLength;
fFoldChars = NULL;
return foldedC;
}
// String foldings fall through here.
fFoldIndex = 0;
}
U16_NEXT(fFoldChars, fFoldIndex, fFoldLength, foldedC);
if (fFoldIndex >= fFoldLength) {
fFoldChars = NULL;
}
return foldedC;
}
UBool CaseFoldingUTextIterator::inExpansion() {
return fFoldChars != NULL;
}
CaseFoldingUCharIterator::CaseFoldingUCharIterator(const UChar *chars, int64_t start, int64_t limit) :
fChars(chars), fIndex(start), fLimit(limit), fFoldChars(NULL), fFoldLength(0) {
}
CaseFoldingUCharIterator::~CaseFoldingUCharIterator() {}
UChar32 CaseFoldingUCharIterator::next() {
UChar32 foldedC;
UChar32 originalC;
if (fFoldChars == NULL) {
// We are not in a string folding of an earlier character.
// Start handling the next char from the input UText.
if (fIndex >= fLimit) {
return U_SENTINEL;
}
U16_NEXT(fChars, fIndex, fLimit, originalC);
fFoldLength = ucase_toFullFolding(originalC, &fFoldChars, U_FOLD_CASE_DEFAULT);
if (fFoldLength >= UCASE_MAX_STRING_LENGTH || fFoldLength < 0) {
// input code point folds to a single code point, possibly itself.
// See comment in ucase.h for explanation of return values from ucase_toFullFoldings.
if (fFoldLength < 0) {
fFoldLength = ~fFoldLength;
}
foldedC = (UChar32)fFoldLength;
fFoldChars = NULL;
return foldedC;
}
// String foldings fall through here.
fFoldIndex = 0;
}
U16_NEXT(fFoldChars, fFoldIndex, fFoldLength, foldedC);
if (fFoldIndex >= fFoldLength) {
fFoldChars = NULL;
}
return foldedC;
}
UBool CaseFoldingUCharIterator::inExpansion() {
return fFoldChars != NULL;
}
int64_t CaseFoldingUCharIterator::getIndex() {
return fIndex;
}
U_NAMESPACE_END
#endif
|
