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