| 1 | // © 2016 and later: Unicode, Inc. and others. |
| 2 | // License & terms of use: http://www.unicode.org/copyright.html |
| 3 | /* |
| 4 | ********************************************************************** |
| 5 | * Copyright (c) 2002-2011, International Business Machines Corporation |
| 6 | * and others. All Rights Reserved. |
| 7 | ********************************************************************** |
| 8 | * Date Name Description |
| 9 | * 01/21/2002 aliu Creation. |
| 10 | ********************************************************************** |
| 11 | */ |
| 12 | |
| 13 | #ifndef STRREPL_H |
| 14 | #define STRREPL_H |
| 15 | |
| 16 | #include "unicode/utypes.h" |
| 17 | |
| 18 | #if !UCONFIG_NO_TRANSLITERATION |
| 19 | |
| 20 | #include "unicode/unifunct.h" |
| 21 | #include "unicode/unirepl.h" |
| 22 | #include "unicode/unistr.h" |
| 23 | |
| 24 | U_NAMESPACE_BEGIN |
| 25 | |
| 26 | class TransliterationRuleData; |
| 27 | |
| 28 | /** |
| 29 | * A replacer that produces static text as its output. The text may |
| 30 | * contain transliterator stand-in characters that represent nested |
| 31 | * UnicodeReplacer objects, making it possible to encode a tree of |
| 32 | * replacers in a StringReplacer. A StringReplacer that contains such |
| 33 | * stand-ins is called a <em>complex</em> StringReplacer. A complex |
| 34 | * StringReplacer has a slower processing loop than a non-complex one. |
| 35 | * @author Alan Liu |
| 36 | */ |
| 37 | class StringReplacer : public UnicodeFunctor, public UnicodeReplacer { |
| 38 | |
| 39 | private: |
| 40 | |
| 41 | /** |
| 42 | * Output text, possibly containing stand-in characters that |
| 43 | * represent nested UnicodeReplacers. |
| 44 | */ |
| 45 | UnicodeString output; |
| 46 | |
| 47 | /** |
| 48 | * Cursor position. Value is ignored if hasCursor is false. |
| 49 | */ |
| 50 | int32_t cursorPos; |
| 51 | |
| 52 | /** |
| 53 | * True if this object outputs a cursor position. |
| 54 | */ |
| 55 | UBool hasCursor; |
| 56 | |
| 57 | /** |
| 58 | * A complex object contains nested replacers and requires more |
| 59 | * complex processing. StringReplacers are initially assumed to |
| 60 | * be complex. If no nested replacers are seen during processing, |
| 61 | * then isComplex is set to false, and future replacements are |
| 62 | * short circuited for better performance. |
| 63 | */ |
| 64 | UBool isComplex; |
| 65 | |
| 66 | /** |
| 67 | * Object that translates stand-in characters in 'output' to |
| 68 | * UnicodeReplacer objects. |
| 69 | */ |
| 70 | const TransliterationRuleData* data; |
| 71 | |
| 72 | public: |
| 73 | |
| 74 | /** |
| 75 | * Construct a StringReplacer that sets the emits the given output |
| 76 | * text and sets the cursor to the given position. |
| 77 | * @param theOutput text that will replace input text when the |
| 78 | * replace() method is called. May contain stand-in characters |
| 79 | * that represent nested replacers. |
| 80 | * @param theCursorPos cursor position that will be returned by |
| 81 | * the replace() method |
| 82 | * @param theData transliterator context object that translates |
| 83 | * stand-in characters to UnicodeReplacer objects |
| 84 | */ |
| 85 | StringReplacer(const UnicodeString& theOutput, |
| 86 | int32_t theCursorPos, |
| 87 | const TransliterationRuleData* theData); |
| 88 | |
| 89 | /** |
| 90 | * Construct a StringReplacer that sets the emits the given output |
| 91 | * text and does not modify the cursor. |
| 92 | * @param theOutput text that will replace input text when the |
| 93 | * replace() method is called. May contain stand-in characters |
| 94 | * that represent nested replacers. |
| 95 | * @param theData transliterator context object that translates |
| 96 | * stand-in characters to UnicodeReplacer objects |
| 97 | */ |
| 98 | StringReplacer(const UnicodeString& theOutput, |
| 99 | const TransliterationRuleData* theData); |
| 100 | |
| 101 | /** |
| 102 | * Copy constructor. |
| 103 | */ |
| 104 | StringReplacer(const StringReplacer& other); |
| 105 | |
| 106 | /** |
| 107 | * Destructor |
| 108 | */ |
| 109 | virtual ~StringReplacer(); |
| 110 | |
| 111 | /** |
| 112 | * Implement UnicodeFunctor |
| 113 | */ |
| 114 | virtual StringReplacer* clone() const; |
| 115 | |
| 116 | /** |
| 117 | * UnicodeFunctor API. Cast 'this' to a UnicodeReplacer* pointer |
| 118 | * and return the pointer. |
| 119 | */ |
| 120 | virtual UnicodeReplacer* toReplacer() const; |
| 121 | |
| 122 | /** |
| 123 | * UnicodeReplacer API |
| 124 | */ |
| 125 | virtual int32_t replace(Replaceable& text, |
| 126 | int32_t start, |
| 127 | int32_t limit, |
| 128 | int32_t& cursor); |
| 129 | |
| 130 | /** |
| 131 | * UnicodeReplacer API |
| 132 | */ |
| 133 | virtual UnicodeString& toReplacerPattern(UnicodeString& result, |
| 134 | UBool escapeUnprintable) const; |
| 135 | |
| 136 | /** |
| 137 | * Implement UnicodeReplacer |
| 138 | */ |
| 139 | virtual void addReplacementSetTo(UnicodeSet& toUnionTo) const; |
| 140 | |
| 141 | /** |
| 142 | * UnicodeFunctor API |
| 143 | */ |
| 144 | virtual void setData(const TransliterationRuleData*); |
| 145 | |
| 146 | /** |
| 147 | * ICU "poor man's RTTI", returns a UClassID for this class. |
| 148 | */ |
| 149 | static UClassID U_EXPORT2 getStaticClassID(); |
| 150 | |
| 151 | /** |
| 152 | * ICU "poor man's RTTI", returns a UClassID for the actual class. |
| 153 | */ |
| 154 | virtual UClassID getDynamicClassID() const; |
| 155 | }; |
| 156 | |
| 157 | U_NAMESPACE_END |
| 158 | |
| 159 | #endif /* #if !UCONFIG_NO_TRANSLITERATION */ |
| 160 | |
| 161 | #endif |
| 162 | |
| 163 | //eof |
| 164 | |