blob: 5e1a131f11d2be8cedca9c253c7539647efd6467 (
plain)
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
|
/*
**********************************************************************
* Copyright (c) 2001-2012, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
* Date Name Description
* 07/18/01 aliu Creation.
**********************************************************************
*/
#include "unicode/unifilt.h"
#include "unicode/rep.h"
#include "unicode/utf16.h"
U_NAMESPACE_BEGIN
UOBJECT_DEFINE_ABSTRACT_RTTI_IMPLEMENTATION(UnicodeFilter)
/* Define this here due to the lack of another file.
It can't be defined in the header */
UnicodeMatcher::~UnicodeMatcher() {}
UnicodeFilter::~UnicodeFilter() {}
/**
* UnicodeFunctor API.
* Note that UnicodeMatcher is a base class of UnicodeFilter.
*/
UnicodeMatcher* UnicodeFilter::toMatcher() const {
return const_cast<UnicodeFilter *>(this);
}
void UnicodeFilter::setData(const TransliterationRuleData*) {}
/**
* Default implementation of UnicodeMatcher::matches() for Unicode
* filters. Matches a single code point at offset (either one or
* two 16-bit code units).
*/
UMatchDegree UnicodeFilter::matches(const Replaceable& text,
int32_t& offset,
int32_t limit,
UBool incremental) {
UChar32 c;
if (offset < limit &&
contains(c = text.char32At(offset))) {
offset += U16_LENGTH(c);
return U_MATCH;
}
if (offset > limit &&
contains(c = text.char32At(offset))) {
// Backup offset by 1, unless the preceding character is a
// surrogate pair -- then backup by 2 (keep offset pointing at
// the lead surrogate).
--offset;
if (offset >= 0) {
offset -= U16_LENGTH(text.char32At(offset)) - 1;
}
return U_MATCH;
}
if (incremental && offset == limit) {
return U_PARTIAL_MATCH;
}
return U_MISMATCH;
}
U_NAMESPACE_END
//eof
|
