|
1 /* |
|
2 ********************************************************************** |
|
3 * Copyright (c) 2001-2007, International Business Machines |
|
4 * Corporation and others. All Rights Reserved. |
|
5 ********************************************************************** |
|
6 * Date Name Description |
|
7 * 11/20/2001 aliu Creation. |
|
8 ********************************************************************** |
|
9 */ |
|
10 #ifndef UNESCTRN_H |
|
11 #define UNESCTRN_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 escape forms to the |
|
23 * characters they represent. Escape forms have a prefix, a suffix, a |
|
24 * radix, and minimum and maximum digit counts. |
|
25 * |
|
26 * <p>This class is package private. It registers several standard |
|
27 * variants with the system which are then accessed via their IDs. |
|
28 * |
|
29 * @author Alan Liu |
|
30 */ |
|
31 class UnescapeTransliterator : public Transliterator { |
|
32 |
|
33 private: |
|
34 |
|
35 /** |
|
36 * The encoded pattern specification. The pattern consists of |
|
37 * zero or more forms. Each form consists of a prefix, suffix, |
|
38 * radix, minimum digit count, and maximum digit count. These |
|
39 * values are stored as a five character header. That is, their |
|
40 * numeric values are cast to 16-bit characters and stored in the |
|
41 * string. Following these five characters, the prefix |
|
42 * characters, then suffix characters are stored. Each form thus |
|
43 * takes n+5 characters, where n is the total length of the prefix |
|
44 * and suffix. The end is marked by a header of length one |
|
45 * consisting of the character END. |
|
46 */ |
|
47 UChar* spec; // owned; may not be NULL |
|
48 |
|
49 public: |
|
50 |
|
51 /** |
|
52 * Registers standard variants with the system. Called by |
|
53 * Transliterator during initialization. |
|
54 */ |
|
55 static void registerIDs(); |
|
56 |
|
57 /** |
|
58 * Constructor. Takes the encoded spec array (does not adopt it). |
|
59 * @param ID the string identifier for this transliterator |
|
60 * @param spec the encoded spec array |
|
61 */ |
|
62 UnescapeTransliterator(const UnicodeString& ID, |
|
63 const UChar *spec); |
|
64 |
|
65 /** |
|
66 * Copy constructor. |
|
67 */ |
|
68 UnescapeTransliterator(const UnescapeTransliterator&); |
|
69 |
|
70 /** |
|
71 * Destructor. |
|
72 */ |
|
73 virtual ~UnescapeTransliterator(); |
|
74 |
|
75 /** |
|
76 * Transliterator API. |
|
77 */ |
|
78 virtual Transliterator* clone() const; |
|
79 |
|
80 /** |
|
81 * ICU "poor man's RTTI", returns a UClassID for the actual class. |
|
82 */ |
|
83 virtual UClassID getDynamicClassID() const; |
|
84 |
|
85 /** |
|
86 * ICU "poor man's RTTI", returns a UClassID for this class. |
|
87 */ |
|
88 U_I18N_API static UClassID U_EXPORT2 getStaticClassID(); |
|
89 |
|
90 protected: |
|
91 |
|
92 /** |
|
93 * Implements {@link Transliterator#handleTransliterate}. |
|
94 * @param text the buffer holding transliterated and |
|
95 * untransliterated text |
|
96 * @param offset the start and limit of the text, the position |
|
97 * of the cursor, and the start and limit of transliteration. |
|
98 * @param incremental if true, assume more text may be coming after |
|
99 * pos.contextLimit. Otherwise, assume the text is complete. |
|
100 */ |
|
101 virtual void handleTransliterate(Replaceable& text, UTransPosition& offset, |
|
102 UBool isIncremental) const; |
|
103 |
|
104 }; |
|
105 |
|
106 U_NAMESPACE_END |
|
107 |
|
108 #endif /* #if !UCONFIG_NO_TRANSLITERATION */ |
|
109 |
|
110 #endif |