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
|
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************
* Copyright (c) 2001-2007, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
* Date Name Description
* 11/20/2001 aliu Creation.
**********************************************************************
*/
#ifndef UNESCTRN_H
#define UNESCTRN_H
#include "unicode/utypes.h"
#if !UCONFIG_NO_TRANSLITERATION
#include "unicode/translit.h"
U_NAMESPACE_BEGIN
/**
* A transliterator that converts Unicode escape forms to the
* characters they represent. Escape forms have a prefix, a suffix, a
* radix, and minimum and maximum digit counts.
*
* <p>This class is package private. It registers several standard
* variants with the system which are then accessed via their IDs.
*
* @author Alan Liu
*/
class UnescapeTransliterator : public Transliterator {
private:
/**
* The encoded pattern specification. The pattern consists of
* zero or more forms. Each form consists of a prefix, suffix,
* radix, minimum digit count, and maximum digit count. These
* values are stored as a five character header. That is, their
* numeric values are cast to 16-bit characters and stored in the
* string. Following these five characters, the prefix
* characters, then suffix characters are stored. Each form thus
* takes n+5 characters, where n is the total length of the prefix
* and suffix. The end is marked by a header of length one
* consisting of the character END.
*/
char16_t* spec; // owned; may not be nullptr
public:
/**
* Registers standard variants with the system. Called by
* Transliterator during initialization.
*/
static void registerIDs();
/**
* Constructor. Takes the encoded spec array (does not adopt it).
* @param ID the string identifier for this transliterator
* @param spec the encoded spec array
*/
UnescapeTransliterator(const UnicodeString& ID,
const char16_t *spec);
/**
* Copy constructor.
*/
UnescapeTransliterator(const UnescapeTransliterator&);
/**
* Destructor.
*/
virtual ~UnescapeTransliterator();
/**
* Transliterator API.
*/
virtual UnescapeTransliterator* clone() const override;
/**
* ICU "poor man's RTTI", returns a UClassID for the actual class.
*/
virtual UClassID getDynamicClassID() const override;
/**
* ICU "poor man's RTTI", returns a UClassID for this class.
*/
U_I18N_API static UClassID U_EXPORT2 getStaticClassID();
protected:
/**
* Implements {@link Transliterator#handleTransliterate}.
* @param text the buffer holding transliterated and
* untransliterated text
* @param offset the start and limit of the text, the position
* of the cursor, and the start and limit of transliteration.
* @param incremental if true, assume more text may be coming after
* pos.contextLimit. Otherwise, assume the text is complete.
*/
virtual void handleTransliterate(Replaceable& text, UTransPosition& offset,
UBool isIncremental) const override;
};
U_NAMESPACE_END
#endif /* #if !UCONFIG_NO_TRANSLITERATION */
#endif
|
