| 1 | // © 2016 and later: Unicode, Inc. and others. |
| 2 | // License & terms of use: http://www.unicode.org/copyright.html |
| 3 | /* |
| 4 | ********************************************************************** |
| 5 | * Copyright (c) 2001-2011, International Business Machines |
| 6 | * Corporation and others. All Rights Reserved. |
| 7 | ********************************************************************** |
| 8 | * Date Name Description |
| 9 | * 11/19/2001 aliu Creation. |
| 10 | ********************************************************************** |
| 11 | */ |
| 12 | |
| 13 | #include "unicode/utypes.h" |
| 14 | |
| 15 | #if !UCONFIG_NO_TRANSLITERATION |
| 16 | |
| 17 | #include "unicode/utf16.h" |
| 18 | #include "esctrn.h" |
| 19 | #include "util.h" |
| 20 | |
| 21 | U_NAMESPACE_BEGIN |
| 22 | |
| 23 | static const UChar UNIPRE[] = {85,43,0}; // "U+" |
| 24 | static const UChar BS_u[] = {92,117,0}; // "\\u" |
| 25 | static const UChar BS_U[] = {92,85,0}; // "\\U" |
| 26 | static const UChar XMLPRE[] = {38,35,120,0}; // "&#x" |
| 27 | static const UChar XML10PRE[] = {38,35,0}; // "&#" |
| 28 | static const UChar PERLPRE[] = {92,120,123,0}; // "\\x{" |
| 29 | static const UChar SEMI[] = {59,0}; // ";" |
| 30 | static const UChar RBRACE[] = {125,0}; // "}" |
| 31 | |
| 32 | UOBJECT_DEFINE_RTTI_IMPLEMENTATION(EscapeTransliterator) |
| 33 | |
| 34 | /** |
| 35 | * Factory methods |
| 36 | */ |
| 37 | static Transliterator* _createEscUnicode(const UnicodeString& ID, Transliterator::Token /*context*/) { |
| 38 | // Unicode: "U+10FFFF" hex, min=4, max=6 |
| 39 | return new EscapeTransliterator(ID, UnicodeString(TRUE, UNIPRE, 2), UnicodeString(), 16, 4, TRUE, NULL); |
| 40 | } |
| 41 | static Transliterator* _createEscJava(const UnicodeString& ID, Transliterator::Token /*context*/) { |
| 42 | // Java: "\\uFFFF" hex, min=4, max=4 |
| 43 | return new EscapeTransliterator(ID, UnicodeString(TRUE, BS_u, 2), UnicodeString(), 16, 4, FALSE, NULL); |
| 44 | } |
| 45 | static Transliterator* _createEscC(const UnicodeString& ID, Transliterator::Token /*context*/) { |
| 46 | // C: "\\uFFFF" hex, min=4, max=4; \\U0010FFFF hex, min=8, max=8 |
| 47 | return new EscapeTransliterator(ID, UnicodeString(TRUE, BS_u, 2), UnicodeString(), 16, 4, TRUE, |
| 48 | new EscapeTransliterator(UnicodeString(), UnicodeString(TRUE, BS_U, 2), UnicodeString(), 16, 8, TRUE, NULL)); |
| 49 | } |
| 50 | static Transliterator* _createEscXML(const UnicodeString& ID, Transliterator::Token /*context*/) { |
| 51 | // XML: "" hex, min=1, max=6 |
| 52 | return new EscapeTransliterator(ID, UnicodeString(TRUE, XMLPRE, 3), UnicodeString(SEMI[0]), 16, 1, TRUE, NULL); |
| 53 | } |
| 54 | static Transliterator* _createEscXML10(const UnicodeString& ID, Transliterator::Token /*context*/) { |
| 55 | // XML10: "&1114111;" dec, min=1, max=7 (not really "Any-Hex") |
| 56 | return new EscapeTransliterator(ID, UnicodeString(TRUE, XML10PRE, 2), UnicodeString(SEMI[0]), 10, 1, TRUE, NULL); |
| 57 | } |
| 58 | static Transliterator* _createEscPerl(const UnicodeString& ID, Transliterator::Token /*context*/) { |
| 59 | // Perl: "\\x{263A}" hex, min=1, max=6 |
| 60 | return new EscapeTransliterator(ID, UnicodeString(TRUE, PERLPRE, 3), UnicodeString(RBRACE[0]), 16, 1, TRUE, NULL); |
| 61 | } |
| 62 | |
| 63 | /** |
| 64 | * Registers standard variants with the system. Called by |
| 65 | * Transliterator during initialization. |
| 66 | */ |
| 67 | void EscapeTransliterator::registerIDs() { |
| 68 | Token t = integerToken(0); |
| 69 | |
| 70 | Transliterator::_registerFactory(UNICODE_STRING_SIMPLE("Any-Hex/Unicode" ), _createEscUnicode, t); |
| 71 | |
| 72 | Transliterator::_registerFactory(UNICODE_STRING_SIMPLE("Any-Hex/Java" ), _createEscJava, t); |
| 73 | |
| 74 | Transliterator::_registerFactory(UNICODE_STRING_SIMPLE("Any-Hex/C" ), _createEscC, t); |
| 75 | |
| 76 | Transliterator::_registerFactory(UNICODE_STRING_SIMPLE("Any-Hex/XML" ), _createEscXML, t); |
| 77 | |
| 78 | Transliterator::_registerFactory(UNICODE_STRING_SIMPLE("Any-Hex/XML10" ), _createEscXML10, t); |
| 79 | |
| 80 | Transliterator::_registerFactory(UNICODE_STRING_SIMPLE("Any-Hex/Perl" ), _createEscPerl, t); |
| 81 | |
| 82 | Transliterator::_registerFactory(UNICODE_STRING_SIMPLE("Any-Hex" ), _createEscJava, t); |
| 83 | } |
| 84 | |
| 85 | /** |
| 86 | * Constructs an escape transliterator with the given ID and |
| 87 | * parameters. See the class member documentation for details. |
| 88 | */ |
| 89 | EscapeTransliterator::EscapeTransliterator(const UnicodeString& newID, |
| 90 | const UnicodeString& _prefix, const UnicodeString& _suffix, |
| 91 | int32_t _radix, int32_t _minDigits, |
| 92 | UBool _grokSupplementals, |
| 93 | EscapeTransliterator* adoptedSupplementalHandler) : |
| 94 | Transliterator(newID, NULL) |
| 95 | { |
| 96 | this->prefix = _prefix; |
| 97 | this->suffix = _suffix; |
| 98 | this->radix = _radix; |
| 99 | this->minDigits = _minDigits; |
| 100 | this->grokSupplementals = _grokSupplementals; |
| 101 | this->supplementalHandler = adoptedSupplementalHandler; |
| 102 | } |
| 103 | |
| 104 | /** |
| 105 | * Copy constructor. |
| 106 | */ |
| 107 | EscapeTransliterator::EscapeTransliterator(const EscapeTransliterator& o) : |
| 108 | Transliterator(o), |
| 109 | prefix(o.prefix), |
| 110 | suffix(o.suffix), |
| 111 | radix(o.radix), |
| 112 | minDigits(o.minDigits), |
| 113 | grokSupplementals(o.grokSupplementals) { |
| 114 | supplementalHandler = (o.supplementalHandler != 0) ? |
| 115 | new EscapeTransliterator(*o.supplementalHandler) : NULL; |
| 116 | } |
| 117 | |
| 118 | EscapeTransliterator::~EscapeTransliterator() { |
| 119 | delete supplementalHandler; |
| 120 | } |
| 121 | |
| 122 | /** |
| 123 | * Transliterator API. |
| 124 | */ |
| 125 | EscapeTransliterator* EscapeTransliterator::clone() const { |
| 126 | return new EscapeTransliterator(*this); |
| 127 | } |
| 128 | |
| 129 | /** |
| 130 | * Implements {@link Transliterator#handleTransliterate}. |
| 131 | */ |
| 132 | void EscapeTransliterator::handleTransliterate(Replaceable& text, |
| 133 | UTransPosition& pos, |
| 134 | UBool /*isIncremental*/) const |
| 135 | { |
| 136 | /* TODO: Verify that isIncremental can be ignored */ |
| 137 | int32_t start = pos.start; |
| 138 | int32_t limit = pos.limit; |
| 139 | |
| 140 | UnicodeString buf(prefix); |
| 141 | int32_t prefixLen = prefix.length(); |
| 142 | UBool redoPrefix = FALSE; |
| 143 | |
| 144 | while (start < limit) { |
| 145 | int32_t c = grokSupplementals ? text.char32At(start) : text.charAt(start); |
| 146 | int32_t charLen = grokSupplementals ? U16_LENGTH(c) : 1; |
| 147 | |
| 148 | if ((c & 0xFFFF0000) != 0 && supplementalHandler != NULL) { |
| 149 | buf.truncate(0); |
| 150 | buf.append(supplementalHandler->prefix); |
| 151 | ICU_Utility::appendNumber(buf, c, supplementalHandler->radix, |
| 152 | supplementalHandler->minDigits); |
| 153 | buf.append(supplementalHandler->suffix); |
| 154 | redoPrefix = TRUE; |
| 155 | } else { |
| 156 | if (redoPrefix) { |
| 157 | buf.truncate(0); |
| 158 | buf.append(prefix); |
| 159 | redoPrefix = FALSE; |
| 160 | } else { |
| 161 | buf.truncate(prefixLen); |
| 162 | } |
| 163 | ICU_Utility::appendNumber(buf, c, radix, minDigits); |
| 164 | buf.append(suffix); |
| 165 | } |
| 166 | |
| 167 | text.handleReplaceBetween(start, start + charLen, buf); |
| 168 | start += buf.length(); |
| 169 | limit += buf.length() - charLen; |
| 170 | } |
| 171 | |
| 172 | pos.contextLimit += limit - pos.limit; |
| 173 | pos.limit = limit; |
| 174 | pos.start = start; |
| 175 | } |
| 176 | |
| 177 | U_NAMESPACE_END |
| 178 | |
| 179 | #endif /* #if !UCONFIG_NO_TRANSLITERATION */ |
| 180 | |
| 181 | //eof |
| 182 | |