1 | // © 2016 and later: Unicode, Inc. and others. |
2 | // License & terms of use: http://www.unicode.org/copyright.html |
3 | /* |
4 | ********************************************************************** |
5 | * Copyright (c) 2001-2007, International Business Machines |
6 | * Corporation and others. All Rights Reserved. |
7 | ********************************************************************** |
8 | * Date Name Description |
9 | * 11/20/2001 aliu Creation. |
10 | ********************************************************************** |
11 | */ |
12 | #ifndef UNESCTRN_H |
13 | #define UNESCTRN_H |
14 | |
15 | #include "unicode/utypes.h" |
16 | |
17 | #if !UCONFIG_NO_TRANSLITERATION |
18 | |
19 | #include "unicode/translit.h" |
20 | |
21 | U_NAMESPACE_BEGIN |
22 | |
23 | /** |
24 | * A transliterator that converts Unicode escape forms to the |
25 | * characters they represent. Escape forms have a prefix, a suffix, a |
26 | * radix, and minimum and maximum digit counts. |
27 | * |
28 | * <p>This class is package private. It registers several standard |
29 | * variants with the system which are then accessed via their IDs. |
30 | * |
31 | * @author Alan Liu |
32 | */ |
33 | class UnescapeTransliterator : public Transliterator { |
34 | |
35 | private: |
36 | |
37 | /** |
38 | * The encoded pattern specification. The pattern consists of |
39 | * zero or more forms. Each form consists of a prefix, suffix, |
40 | * radix, minimum digit count, and maximum digit count. These |
41 | * values are stored as a five character header. That is, their |
42 | * numeric values are cast to 16-bit characters and stored in the |
43 | * string. Following these five characters, the prefix |
44 | * characters, then suffix characters are stored. Each form thus |
45 | * takes n+5 characters, where n is the total length of the prefix |
46 | * and suffix. The end is marked by a header of length one |
47 | * consisting of the character END. |
48 | */ |
49 | UChar* spec; // owned; may not be NULL |
50 | |
51 | public: |
52 | |
53 | /** |
54 | * Registers standard variants with the system. Called by |
55 | * Transliterator during initialization. |
56 | */ |
57 | static void registerIDs(); |
58 | |
59 | /** |
60 | * Constructor. Takes the encoded spec array (does not adopt it). |
61 | * @param ID the string identifier for this transliterator |
62 | * @param spec the encoded spec array |
63 | */ |
64 | UnescapeTransliterator(const UnicodeString& ID, |
65 | const UChar *spec); |
66 | |
67 | /** |
68 | * Copy constructor. |
69 | */ |
70 | UnescapeTransliterator(const UnescapeTransliterator&); |
71 | |
72 | /** |
73 | * Destructor. |
74 | */ |
75 | virtual ~UnescapeTransliterator(); |
76 | |
77 | /** |
78 | * Transliterator API. |
79 | */ |
80 | virtual UnescapeTransliterator* clone() const; |
81 | |
82 | /** |
83 | * ICU "poor man's RTTI", returns a UClassID for the actual class. |
84 | */ |
85 | virtual UClassID getDynamicClassID() const; |
86 | |
87 | /** |
88 | * ICU "poor man's RTTI", returns a UClassID for this class. |
89 | */ |
90 | U_I18N_API static UClassID U_EXPORT2 getStaticClassID(); |
91 | |
92 | protected: |
93 | |
94 | /** |
95 | * Implements {@link Transliterator#handleTransliterate}. |
96 | * @param text the buffer holding transliterated and |
97 | * untransliterated text |
98 | * @param offset the start and limit of the text, the position |
99 | * of the cursor, and the start and limit of transliteration. |
100 | * @param incremental if true, assume more text may be coming after |
101 | * pos.contextLimit. Otherwise, assume the text is complete. |
102 | */ |
103 | virtual void handleTransliterate(Replaceable& text, UTransPosition& offset, |
104 | UBool isIncremental) const; |
105 | |
106 | }; |
107 | |
108 | U_NAMESPACE_END |
109 | |
110 | #endif /* #if !UCONFIG_NO_TRANSLITERATION */ |
111 | |
112 | #endif |
113 | |