wtf/unicode/wince/UnicodeWince.h

   1 /*
   2  *  Copyright (C) 2006 George Staikos <staikos@kde.org>
   3  *  Copyright (C) 2006 Alexey Proskuryakov <ap@nypop.com>
   4  *  Copyright (C) 2007 Apple Computer, Inc. All rights reserved.
   5  *  Copyright (C) 2007-2009 Torch Mobile, Inc.
   6  *
   7  *  This library is free software; you can redistribute it and/or
   8  *  modify it under the terms of the GNU Library General Public
   9  *  License as published by the Free Software Foundation; either
  10  *  version 2 of the License, or (at your option) any later version.
  11  *
  12  *  This library is distributed in the hope that it will be useful,
  13  *  but WITHOUT ANY WARRANTY; without even the implied warranty of
  14  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  15  *  Library General Public License for more details.
  16  *
  17  *  You should have received a copy of the GNU Library General Public License
  18  *  along with this library; see the file COPYING.LIB.  If not, write to
  19  *  the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
  20  *  Boston, MA 02110-1301, USA.
  21  *
  22  */
  23
  24 #ifndef UNICODE_WINCE_H
  25 #define UNICODE_WINCE_H
  26
  27 #include "ce_unicode.h"
  28
  29 #define TO_MASK(x) (1 << (x))
  30
  31 // some defines from ICU needed one or two places
  32
  33 #define U16_IS_LEAD(c) (((c) & 0xfffffc00) == 0xd800)
  34 #define U16_IS_TRAIL(c) (((c) & 0xfffffc00) == 0xdc00)
  35 #define U16_SURROGATE_OFFSET ((0xd800 << 10UL) + 0xdc00 - 0x10000)
  36 #define U16_GET_SUPPLEMENTARY(lead, trail) \
  37     (((UChar32)(lead) << 10UL) + (UChar32)(trail) - U16_SURROGATE_OFFSET)
  38
  39 #define U16_LEAD(supplementary) (UChar)(((supplementary) >> 10) + 0xd7c0)
  40 #define U16_TRAIL(supplementary) (UChar)(((supplementary) & 0x3ff) | 0xdc00)
  41
  42 #define U_IS_SURROGATE(c) (((c) & 0xfffff800) == 0xd800)
  43 #define U16_IS_SURROGATE(c) U_IS_SURROGATE(c)
  44 #define U16_IS_SURROGATE_LEAD(c) (((c) & 0x400) == 0)
  45
  46 #define U16_NEXT(s, i, length, c) { \
  47     (c)=(s)[(i)++]; \
  48     if (U16_IS_LEAD(c)) { \
  49         uint16_t __c2; \
  50         if ((i) < (length) && U16_IS_TRAIL(__c2 = (s)[(i)])) { \
  51             ++(i); \
  52             (c) = U16_GET_SUPPLEMENTARY((c), __c2); \
  53         } \
  54     } \
  55 }
  56
  57 #define U16_PREV(s, start, i, c) { \
  58     (c)=(s)[--(i)]; \
  59     if (U16_IS_TRAIL(c)) { \
  60         uint16_t __c2; \
  61         if ((i) > (start) && U16_IS_LEAD(__c2 = (s)[(i) - 1])) { \
  62             --(i); \
  63             (c) = U16_GET_SUPPLEMENTARY(__c2, (c)); \
  64         } \
  65     } \
  66 }
  67
  68 #define U16_IS_SINGLE(c) !U_IS_SURROGATE(c)
  69
  70 namespace WTF {
  71
  72     namespace Unicode {
  73
  74         enum Direction {
  75             LeftToRight = UnicodeCE::U_LEFT_TO_RIGHT,
  76             RightToLeft = UnicodeCE::U_RIGHT_TO_LEFT,
  77             EuropeanNumber = UnicodeCE::U_EUROPEAN_NUMBER,
  78             EuropeanNumberSeparator = UnicodeCE::U_EUROPEAN_NUMBER_SEPARATOR,
  79             EuropeanNumberTerminator = UnicodeCE::U_EUROPEAN_NUMBER_TERMINATOR,
  80             ArabicNumber = UnicodeCE::U_ARABIC_NUMBER,
  81             CommonNumberSeparator = UnicodeCE::U_COMMON_NUMBER_SEPARATOR,
  82             BlockSeparator = UnicodeCE::U_BLOCK_SEPARATOR,
  83             SegmentSeparator = UnicodeCE::U_SEGMENT_SEPARATOR,
  84             WhiteSpaceNeutral = UnicodeCE::U_WHITE_SPACE_NEUTRAL,
  85             OtherNeutral = UnicodeCE::U_OTHER_NEUTRAL,
  86             LeftToRightEmbedding = UnicodeCE::U_LEFT_TO_RIGHT_EMBEDDING,
  87             LeftToRightOverride = UnicodeCE::U_LEFT_TO_RIGHT_OVERRIDE,
  88             RightToLeftArabic = UnicodeCE::U_RIGHT_TO_LEFT_ARABIC,
  89             RightToLeftEmbedding = UnicodeCE::U_RIGHT_TO_LEFT_EMBEDDING,
  90             RightToLeftOverride = UnicodeCE::U_RIGHT_TO_LEFT_OVERRIDE,
  91             PopDirectionalFormat = UnicodeCE::U_POP_DIRECTIONAL_FORMAT,
  92             NonSpacingMark = UnicodeCE::U_DIR_NON_SPACING_MARK,
  93             BoundaryNeutral = UnicodeCE::U_BOUNDARY_NEUTRAL
  94         };
  95
  96         enum DecompositionType {
  97           DecompositionNone = UnicodeCE::U_DT_NONE,
  98           DecompositionCanonical = UnicodeCE::U_DT_CANONICAL,
  99           DecompositionCompat = UnicodeCE::U_DT_COMPAT,
 100           DecompositionCircle = UnicodeCE::U_DT_CIRCLE,
 101           DecompositionFinal = UnicodeCE::U_DT_FINAL,
 102           DecompositionFont = UnicodeCE::U_DT_FONT,
 103           DecompositionFraction = UnicodeCE::U_DT_FRACTION,
 104           DecompositionInitial = UnicodeCE::U_DT_INITIAL,
 105           DecompositionIsolated = UnicodeCE::U_DT_ISOLATED,
 106           DecompositionMedial = UnicodeCE::U_DT_MEDIAL,
 107           DecompositionNarrow = UnicodeCE::U_DT_NARROW,
 108           DecompositionNoBreak = UnicodeCE::U_DT_NOBREAK,
 109           DecompositionSmall = UnicodeCE::U_DT_SMALL,
 110           DecompositionSquare = UnicodeCE::U_DT_SQUARE,
 111           DecompositionSub = UnicodeCE::U_DT_SUB,
 112           DecompositionSuper = UnicodeCE::U_DT_SUPER,
 113           DecompositionVertical = UnicodeCE::U_DT_VERTICAL,
 114           DecompositionWide = UnicodeCE::U_DT_WIDE,
 115         };
 116
 117         enum CharCategory {
 118           NoCategory =  0,
 119           Other_NotAssigned = TO_MASK(UnicodeCE::U_GENERAL_OTHER_TYPES),
 120           Letter_Uppercase = TO_MASK(UnicodeCE::U_UPPERCASE_LETTER),
 121           Letter_Lowercase = TO_MASK(UnicodeCE::U_LOWERCASE_LETTER),
 122           Letter_Titlecase = TO_MASK(UnicodeCE::U_TITLECASE_LETTER),
 123           Letter_Modifier = TO_MASK(UnicodeCE::U_MODIFIER_LETTER),
 124           Letter_Other = TO_MASK(UnicodeCE::U_OTHER_LETTER),
 125
 126           Mark_NonSpacing = TO_MASK(UnicodeCE::U_NON_SPACING_MARK),
 127           Mark_Enclosing = TO_MASK(UnicodeCE::U_ENCLOSING_MARK),
 128           Mark_SpacingCombining = TO_MASK(UnicodeCE::U_COMBINING_SPACING_MARK),
 129
 130           Number_DecimalDigit = TO_MASK(UnicodeCE::U_DECIMAL_DIGIT_NUMBER),
 131           Number_Letter = TO_MASK(UnicodeCE::U_LETTER_NUMBER),
 132           Number_Other = TO_MASK(UnicodeCE::U_OTHER_NUMBER),
 133
 134           Separator_Space = TO_MASK(UnicodeCE::U_SPACE_SEPARATOR),
 135           Separator_Line = TO_MASK(UnicodeCE::U_LINE_SEPARATOR),
 136           Separator_Paragraph = TO_MASK(UnicodeCE::U_PARAGRAPH_SEPARATOR),
 137
 138           Other_Control = TO_MASK(UnicodeCE::U_CONTROL_CHAR),
 139           Other_Format = TO_MASK(UnicodeCE::U_FORMAT_CHAR),
 140           Other_PrivateUse = TO_MASK(UnicodeCE::U_PRIVATE_USE_CHAR),
 141           Other_Surrogate = TO_MASK(UnicodeCE::U_SURROGATE),
 142
 143           Punctuation_Dash = TO_MASK(UnicodeCE::U_DASH_PUNCTUATION),
 144           Punctuation_Open = TO_MASK(UnicodeCE::U_START_PUNCTUATION),
 145           Punctuation_Close = TO_MASK(UnicodeCE::U_END_PUNCTUATION),
 146           Punctuation_Connector = TO_MASK(UnicodeCE::U_CONNECTOR_PUNCTUATION),
 147           Punctuation_Other = TO_MASK(UnicodeCE::U_OTHER_PUNCTUATION),
 148
 149           Symbol_Math = TO_MASK(UnicodeCE::U_MATH_SYMBOL),
 150           Symbol_Currency = TO_MASK(UnicodeCE::U_CURRENCY_SYMBOL),
 151           Symbol_Modifier = TO_MASK(UnicodeCE::U_MODIFIER_SYMBOL),
 152           Symbol_Other = TO_MASK(UnicodeCE::U_OTHER_SYMBOL),
 153
 154           Punctuation_InitialQuote = TO_MASK(UnicodeCE::U_INITIAL_PUNCTUATION),
 155           Punctuation_FinalQuote = TO_MASK(UnicodeCE::U_FINAL_PUNCTUATION)
 156         };
 157
 158         CharCategory category(unsigned int);
 159
 160         bool isSpace(wchar_t);
 161         bool isLetter(wchar_t);
 162         bool isPrintableChar(wchar_t);
 163         bool isUpper(wchar_t);
 164         bool isLower(wchar_t);
 165         bool isPunct(wchar_t);
 166         bool isDigit(wchar_t);
 167         inline bool isSeparatorSpace(wchar_t c) { return category(c) == Separator_Space; }
 168         inline bool isHighSurrogate(wchar_t c) { return (c & 0xfc00) == 0xd800; }
 169         inline bool isLowSurrogate(wchar_t c) { return (c & 0xfc00) == 0xdc00; }
 170
 171         wchar_t toLower(wchar_t);
 172         wchar_t toUpper(wchar_t);
 173         wchar_t foldCase(wchar_t);
 174         wchar_t toTitleCase(wchar_t);
 175         int toLower(wchar_t* result, int resultLength, const wchar_t* source, int sourceLength, bool* isError);
 176         int toUpper(wchar_t* result, int resultLength, const wchar_t* source, int sourceLength, bool* isError);
 177         int foldCase(UChar* result, int resultLength, const wchar_t* source, int sourceLength, bool* isError);
 178
 179         int digitValue(wchar_t);
 180
 181         wchar_t mirroredChar(UChar32);
 182         unsigned char combiningClass(UChar32);
 183         DecompositionType decompositionType(UChar32);
 184         Direction direction(UChar32);
 185         inline bool isArabicChar(UChar32)
 186         {
 187             return false; // FIXME: implement!
 188         }
 189
 190         inline bool hasLineBreakingPropertyComplexContext(UChar32)
 191         {
 192             return false; // FIXME: implement!
 193         }
 194
 195         inline int umemcasecmp(const wchar_t* a, const wchar_t* b, int len)
 196         {
 197             for (int i = 0; i < len; ++i) {
 198                 wchar_t c1 = foldCase(a[i]);
 199                 wchar_t c2 = foldCase(b[i]);
 200                 if (c1 != c2)
 201                     return c1 - c2;
 202             }
 203             return 0;
 204         }
 205
 206         inline UChar32 surrogateToUcs4(wchar_t high, wchar_t low)
 207         {
 208             return (UChar32(high) << 10) + low - 0x35fdc00;
 209         }
 210
 211     }   // namespace Unicode
 212
 213 }   // namespace WTF
 214
 215 #endif
 216 // vim: ts=2 sw=2 et