]>
Commit | Line | Data |
---|---|---|
b75a7d8f A |
1 | /* |
2 | ********************************************************************** | |
374ca955 | 3 | * Copyright (c) 2001-2004, International Business Machines |
b75a7d8f A |
4 | * Corporation and others. All Rights Reserved. |
5 | ********************************************************************** | |
6 | * Date Name Description | |
7 | * 11/20/2001 aliu Creation. | |
8 | ********************************************************************** | |
9 | */ | |
10 | #ifndef ESCTRN_H | |
11 | #define ESCTRN_H | |
12 | ||
13 | #include "unicode/utypes.h" | |
14 | ||
15 | #if !UCONFIG_NO_TRANSLITERATION | |
16 | ||
17 | #include "unicode/translit.h" | |
18 | ||
19 | U_NAMESPACE_BEGIN | |
20 | ||
21 | /** | |
22 | * A transliterator that converts Unicode characters to an escape | |
23 | * form. Examples of escape forms are "U+4E01" and "". | |
24 | * Escape forms have a prefix and suffix, either of which may be | |
25 | * empty, a radix, typically 16 or 10, a minimum digit count, | |
26 | * typically 1, 4, or 8, and a boolean that specifies whether | |
27 | * supplemental characters are handled as 32-bit code points or as two | |
28 | * 16-bit code units. Most escape forms handle 32-bit code points, | |
29 | * but some, such as the Java form, intentionally break them into two | |
30 | * surrogate pairs, for backward compatibility. | |
31 | * | |
32 | * <p>Some escape forms actually have two different patterns, one for | |
33 | * BMP characters (0..FFFF) and one for supplements (>FFFF). To | |
34 | * handle this, a second EscapeTransliterator may be defined that | |
35 | * specifies the pattern to be produced for supplementals. An example | |
36 | * of a form that requires this is the C form, which uses "\\uFFFF" | |
37 | * for BMP characters and "\\U0010FFFF" for supplementals. | |
38 | * | |
39 | * <p>This class is package private. It registers several standard | |
40 | * variants with the system which are then accessed via their IDs. | |
41 | * | |
42 | * @author Alan Liu | |
43 | */ | |
44 | class U_I18N_API EscapeTransliterator : public Transliterator { | |
45 | ||
46 | private: | |
47 | ||
48 | /** | |
49 | * The prefix of the escape form; may be empty, but usually isn't. | |
50 | */ | |
51 | UnicodeString prefix; | |
52 | ||
53 | /** | |
54 | * The prefix of the escape form; often empty. | |
55 | */ | |
56 | UnicodeString suffix; | |
57 | ||
58 | /** | |
59 | * The radix to display the number in. Typically 16 or 10. Must | |
60 | * be in the range 2 to 36. | |
61 | */ | |
62 | int32_t radix; | |
63 | ||
64 | /** | |
65 | * The minimum number of digits. Typically 1, 4, or 8. Values | |
66 | * less than 1 are equivalent to 1. | |
67 | */ | |
68 | int32_t minDigits; | |
69 | ||
70 | /** | |
71 | * If true, supplementals are handled as 32-bit code points. If | |
72 | * false, they are handled as two 16-bit code units. | |
73 | */ | |
74 | UBool grokSupplementals; | |
75 | ||
76 | /** | |
77 | * The form to be used for supplementals. If this is null then | |
78 | * the same form is used for BMP characters and supplementals. If | |
79 | * this is not null and if grokSupplementals is true then the | |
80 | * prefix, suffix, radix, and minDigits of this object are used | |
81 | * for supplementals. This pointer is owned. | |
82 | */ | |
83 | EscapeTransliterator* supplementalHandler; | |
84 | ||
b75a7d8f A |
85 | public: |
86 | ||
87 | /** | |
88 | * Registers standard variants with the system. Called by | |
89 | * Transliterator during initialization. | |
90 | */ | |
91 | static void registerIDs(); | |
92 | ||
93 | /** | |
94 | * Constructs an escape transliterator with the given ID and | |
95 | * parameters. See the class member documentation for details. | |
96 | */ | |
97 | EscapeTransliterator(const UnicodeString& ID, | |
98 | const UnicodeString& prefix, const UnicodeString& suffix, | |
99 | int32_t radix, int32_t minDigits, | |
100 | UBool grokSupplementals, | |
101 | EscapeTransliterator* adoptedSupplementalHandler); | |
102 | ||
103 | /** | |
104 | * Copy constructor. | |
105 | */ | |
106 | EscapeTransliterator(const EscapeTransliterator&); | |
107 | ||
108 | /** | |
109 | * Destructor. | |
110 | */ | |
111 | virtual ~EscapeTransliterator(); | |
112 | ||
113 | /** | |
114 | * Transliterator API. | |
115 | */ | |
116 | virtual Transliterator* clone() const; | |
117 | ||
118 | /** | |
119 | * ICU "poor man's RTTI", returns a UClassID for the actual class. | |
120 | * | |
121 | * @draft ICU 2.2 | |
122 | */ | |
374ca955 | 123 | virtual UClassID getDynamicClassID() const; |
b75a7d8f A |
124 | |
125 | /** | |
126 | * ICU "poor man's RTTI", returns a UClassID for this class. | |
127 | * | |
128 | * @draft ICU 2.2 | |
129 | */ | |
374ca955 | 130 | static UClassID U_EXPORT2 getStaticClassID(); |
b75a7d8f A |
131 | |
132 | protected: | |
133 | ||
134 | /** | |
135 | * Implements {@link Transliterator#handleTransliterate}. | |
136 | */ | |
137 | void handleTransliterate(Replaceable& text, UTransPosition& offset, | |
138 | UBool isIncremental) const; | |
139 | ||
140 | private: | |
141 | ||
142 | /** | |
143 | * Factory methods | |
144 | */ | |
145 | static Transliterator* _createUnicode(const UnicodeString& ID, Token context); | |
146 | static Transliterator* _createJava(const UnicodeString& ID, Token context); | |
147 | static Transliterator* _createC(const UnicodeString& ID, Token context); | |
148 | static Transliterator* _createXML(const UnicodeString& ID, Token context); | |
149 | static Transliterator* _createXML10(const UnicodeString& ID, Token context); | |
150 | static Transliterator* _createPerl(const UnicodeString& ID, Token context); | |
151 | }; | |
152 | ||
153 | U_NAMESPACE_END | |
154 | ||
155 | #endif /* #if !UCONFIG_NO_TRANSLITERATION */ | |
156 | ||
157 | #endif |