icuSources/i18n/esctrn.cpp

   1 /*
   2 **********************************************************************
   3 *   Copyright (c) 2001-2011, International Business Machines
   4 *   Corporation and others.  All Rights Reserved.
   5 **********************************************************************
   6 *   Date        Name        Description
   7 *   11/19/2001  aliu        Creation.
   8 **********************************************************************
   9 */
  10
  11 #include "unicode/utypes.h"
  12
  13 #if !UCONFIG_NO_TRANSLITERATION
  14
  15 #include "unicode/utf16.h"
  16 #include "esctrn.h"
  17 #include "util.h"
  18
  19 U_NAMESPACE_BEGIN
  20
  21 static const UChar UNIPRE[] = {85,43,0}; // "U+"
  22 static const UChar BS_u[] = {92,117,0}; // "\\u"
  23 static const UChar BS_U[] = {92,85,0}; // "\\U"
  24 static const UChar XMLPRE[] = {38,35,120,0}; // "&#x"
  25 static const UChar XML10PRE[] = {38,35,0}; // "&#"
  26 static const UChar PERLPRE[] = {92,120,123,0}; // "\\x{"
  27 static const UChar SEMI[] = {59,0}; // ";"
  28 static const UChar RBRACE[] = {125,0}; // "}"
  29
  30 UOBJECT_DEFINE_RTTI_IMPLEMENTATION(EscapeTransliterator)
  31
  32 /**
  33  * Factory methods
  34  */
  35 static Transliterator* _createEscUnicode(const UnicodeString& ID, Transliterator::Token /*context*/) {
  36     // Unicode: "U+10FFFF" hex, min=4, max=6
  37     return new EscapeTransliterator(ID, UnicodeString(TRUE, UNIPRE, 2), UnicodeString(), 16, 4, TRUE, NULL);
  38 }
  39 static Transliterator* _createEscJava(const UnicodeString& ID, Transliterator::Token /*context*/) {
  40     // Java: "\\uFFFF" hex, min=4, max=4
  41     return new EscapeTransliterator(ID, UnicodeString(TRUE, BS_u, 2), UnicodeString(), 16, 4, FALSE, NULL);
  42 }
  43 static Transliterator* _createEscC(const UnicodeString& ID, Transliterator::Token /*context*/) {
  44     // C: "\\uFFFF" hex, min=4, max=4; \\U0010FFFF hex, min=8, max=8
  45     return new EscapeTransliterator(ID, UnicodeString(TRUE, BS_u, 2), UnicodeString(), 16, 4, TRUE,
  46              new EscapeTransliterator(UnicodeString(), UnicodeString(TRUE, BS_U, 2), UnicodeString(), 16, 8, TRUE, NULL));
  47 }
  48 static Transliterator* _createEscXML(const UnicodeString& ID, Transliterator::Token /*context*/) {
  49     // XML: "&#x10FFFF;" hex, min=1, max=6
  50     return new EscapeTransliterator(ID, UnicodeString(TRUE, XMLPRE, 3), UnicodeString(SEMI[0]), 16, 1, TRUE, NULL);
  51 }
  52 static Transliterator* _createEscXML10(const UnicodeString& ID, Transliterator::Token /*context*/) {
  53     // XML10: "&1114111;" dec, min=1, max=7 (not really "Any-Hex")
  54     return new EscapeTransliterator(ID, UnicodeString(TRUE, XML10PRE, 2), UnicodeString(SEMI[0]), 10, 1, TRUE, NULL);
  55 }
  56 static Transliterator* _createEscPerl(const UnicodeString& ID, Transliterator::Token /*context*/) {
  57     // Perl: "\\x{263A}" hex, min=1, max=6
  58     return new EscapeTransliterator(ID, UnicodeString(TRUE, PERLPRE, 3), UnicodeString(RBRACE[0]), 16, 1, TRUE, NULL);
  59 }
  60
  61 /**
  62  * Registers standard variants with the system.  Called by
  63  * Transliterator during initialization.
  64  */
  65 void EscapeTransliterator::registerIDs() {
  66     Token t = integerToken(0);
  67
  68     Transliterator::_registerFactory(UNICODE_STRING_SIMPLE("Any-Hex/Unicode"), _createEscUnicode, t);
  69
  70     Transliterator::_registerFactory(UNICODE_STRING_SIMPLE("Any-Hex/Java"), _createEscJava, t);
  71
  72     Transliterator::_registerFactory(UNICODE_STRING_SIMPLE("Any-Hex/C"), _createEscC, t);
  73
  74     Transliterator::_registerFactory(UNICODE_STRING_SIMPLE("Any-Hex/XML"), _createEscXML, t);
  75
  76     Transliterator::_registerFactory(UNICODE_STRING_SIMPLE("Any-Hex/XML10"), _createEscXML10, t);
  77
  78     Transliterator::_registerFactory(UNICODE_STRING_SIMPLE("Any-Hex/Perl"), _createEscPerl, t);
  79
  80     Transliterator::_registerFactory(UNICODE_STRING_SIMPLE("Any-Hex"), _createEscJava, t);
  81 }
  82
  83 /**
  84  * Constructs an escape transliterator with the given ID and
  85  * parameters.  See the class member documentation for details.
  86  */
  87 EscapeTransliterator::EscapeTransliterator(const UnicodeString& newID,
  88                          const UnicodeString& _prefix, const UnicodeString& _suffix,
  89                          int32_t _radix, int32_t _minDigits,
  90                          UBool _grokSupplementals,
  91                          EscapeTransliterator* adoptedSupplementalHandler) :
  92     Transliterator(newID, NULL)
  93 {
  94     this->prefix = _prefix;
  95     this->suffix = _suffix;
  96     this->radix = _radix;
  97     this->minDigits = _minDigits;
  98     this->grokSupplementals = _grokSupplementals;
  99     this->supplementalHandler = adoptedSupplementalHandler;
 100 }
 101
 102 /**
 103  * Copy constructor.
 104  */
 105 EscapeTransliterator::EscapeTransliterator(const EscapeTransliterator& o) :
 106     Transliterator(o),
 107     prefix(o.prefix),
 108     suffix(o.suffix),
 109     radix(o.radix),
 110     minDigits(o.minDigits),
 111     grokSupplementals(o.grokSupplementals) {
 112     supplementalHandler = (o.supplementalHandler != 0) ?
 113         new EscapeTransliterator(*o.supplementalHandler) : NULL;
 114 }
 115
 116 EscapeTransliterator::~EscapeTransliterator() {
 117     delete supplementalHandler;
 118 }
 119
 120 /**
 121  * Transliterator API.
 122  */
 123 Transliterator* EscapeTransliterator::clone() const {
 124     return new EscapeTransliterator(*this);
 125 }
 126
 127 /**
 128  * Implements {@link Transliterator#handleTransliterate}.
 129  */
 130 void EscapeTransliterator::handleTransliterate(Replaceable& text,
 131                                                UTransPosition& pos,
 132                                                UBool /*isIncremental*/) const
 133 {
 134     /* TODO: Verify that isIncremental can be ignored */
 135     int32_t start = pos.start;
 136     int32_t limit = pos.limit;
 137
 138     UnicodeString buf(prefix);
 139     int32_t prefixLen = prefix.length();
 140     UBool redoPrefix = FALSE;
 141
 142     while (start < limit) {
 143         int32_t c = grokSupplementals ? text.char32At(start) : text.charAt(start);
 144         int32_t charLen = grokSupplementals ? U16_LENGTH(c) : 1;
 145
 146         if ((c & 0xFFFF0000) != 0 && supplementalHandler != NULL) {
 147             buf.truncate(0);
 148             buf.append(supplementalHandler->prefix);
 149             ICU_Utility::appendNumber(buf, c, supplementalHandler->radix,
 150                                   supplementalHandler->minDigits);
 151             buf.append(supplementalHandler->suffix);
 152             redoPrefix = TRUE;
 153         } else {
 154             if (redoPrefix) {
 155                 buf.truncate(0);
 156                 buf.append(prefix);
 157                 redoPrefix = FALSE;
 158             } else {
 159                 buf.truncate(prefixLen);
 160             }
 161             ICU_Utility::appendNumber(buf, c, radix, minDigits);
 162             buf.append(suffix);
 163         }
 164
 165         text.handleReplaceBetween(start, start + charLen, buf);
 166         start += buf.length();
 167         limit += buf.length() - charLen;
 168     }
 169
 170     pos.contextLimit += limit - pos.limit;
 171     pos.limit = limit;
 172     pos.start = start;
 173 }
 174
 175 U_NAMESPACE_END
 176
 177 #endif /* #if !UCONFIG_NO_TRANSLITERATION */
 178
 179 //eof