code.vuplus.com Git - vuplus_webkit/blob - Source/JavaScriptCore/wtf/unicode/brew/UnicodeBrew.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  *  Copyright (C) 2010 Company 100, Inc.
   7  *
   8  *  This library is free software; you can redistribute it and/or
   9  *  modify it under the terms of the GNU Library General Public
  10  *  License as published by the Free Software Foundation; either
  11  *  version 2 of the License, or (at your option) any later version.
  12  *
  13  *  This library is distributed in the hope that it will be useful,
  14  *  but WITHOUT ANY WARRANTY; without even the implied warranty of
  15  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  16  *  Library General Public License for more details.
  17  *
  18  *  You should have received a copy of the GNU Library General Public License
  19  *  along with this library; see the file COPYING.LIB.  If not, write to
  20  *  the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
  21  *  Boston, MA 02110-1301, USA.
  22  *
  23  */
  24
  25 #ifndef UnicodeBrew_h
  26 #define UnicodeBrew_h
  27
  28 #include "ScriptCodesFromICU.h"
  29 #include "UnicodeFromICU.h"
  30 #include "UnicodeMacrosFromICU.h"
  31
  32 namespace WTF {
  33 namespace Unicode {
  34
  35 enum Direction {
  36     LeftToRight = ICU::U_LEFT_TO_RIGHT,
  37     RightToLeft = ICU::U_RIGHT_TO_LEFT,
  38     EuropeanNumber = ICU::U_EUROPEAN_NUMBER,
  39     EuropeanNumberSeparator = ICU::U_EUROPEAN_NUMBER_SEPARATOR,
  40     EuropeanNumberTerminator = ICU::U_EUROPEAN_NUMBER_TERMINATOR,
  41     ArabicNumber = ICU::U_ARABIC_NUMBER,
  42     CommonNumberSeparator = ICU::U_COMMON_NUMBER_SEPARATOR,
  43     BlockSeparator = ICU::U_BLOCK_SEPARATOR,
  44     SegmentSeparator = ICU::U_SEGMENT_SEPARATOR,
  45     WhiteSpaceNeutral = ICU::U_WHITE_SPACE_NEUTRAL,
  46     OtherNeutral = ICU::U_OTHER_NEUTRAL,
  47     LeftToRightEmbedding = ICU::U_LEFT_TO_RIGHT_EMBEDDING,
  48     LeftToRightOverride = ICU::U_LEFT_TO_RIGHT_OVERRIDE,
  49     RightToLeftArabic = ICU::U_RIGHT_TO_LEFT_ARABIC,
  50     RightToLeftEmbedding = ICU::U_RIGHT_TO_LEFT_EMBEDDING,
  51     RightToLeftOverride = ICU::U_RIGHT_TO_LEFT_OVERRIDE,
  52     PopDirectionalFormat = ICU::U_POP_DIRECTIONAL_FORMAT,
  53     NonSpacingMark = ICU::U_DIR_NON_SPACING_MARK,
  54     BoundaryNeutral = ICU::U_BOUNDARY_NEUTRAL
  55 };
  56
  57 enum DecompositionType {
  58     DecompositionNone = ICU::U_DT_NONE,
  59     DecompositionCanonical = ICU::U_DT_CANONICAL,
  60     DecompositionCompat = ICU::U_DT_COMPAT,
  61     DecompositionCircle = ICU::U_DT_CIRCLE,
  62     DecompositionFinal = ICU::U_DT_FINAL,
  63     DecompositionFont = ICU::U_DT_FONT,
  64     DecompositionFraction = ICU::U_DT_FRACTION,
  65     DecompositionInitial = ICU::U_DT_INITIAL,
  66     DecompositionIsolated = ICU::U_DT_ISOLATED,
  67     DecompositionMedial = ICU::U_DT_MEDIAL,
  68     DecompositionNarrow = ICU::U_DT_NARROW,
  69     DecompositionNoBreak = ICU::U_DT_NOBREAK,
  70     DecompositionSmall = ICU::U_DT_SMALL,
  71     DecompositionSquare = ICU::U_DT_SQUARE,
  72     DecompositionSub = ICU::U_DT_SUB,
  73     DecompositionSuper = ICU::U_DT_SUPER,
  74     DecompositionVertical = ICU::U_DT_VERTICAL,
  75     DecompositionWide = ICU::U_DT_WIDE,
  76 };
  77
  78 enum CharCategory {
  79     NoCategory =  0,
  80     Other_NotAssigned = TO_MASK(ICU::U_GENERAL_OTHER_TYPES),
  81     Letter_Uppercase = TO_MASK(ICU::U_UPPERCASE_LETTER),
  82     Letter_Lowercase = TO_MASK(ICU::U_LOWERCASE_LETTER),
  83     Letter_Titlecase = TO_MASK(ICU::U_TITLECASE_LETTER),
  84     Letter_Modifier = TO_MASK(ICU::U_MODIFIER_LETTER),
  85     Letter_Other = TO_MASK(ICU::U_OTHER_LETTER),
  86
  87     Mark_NonSpacing = TO_MASK(ICU::U_NON_SPACING_MARK),
  88     Mark_Enclosing = TO_MASK(ICU::U_ENCLOSING_MARK),
  89     Mark_SpacingCombining = TO_MASK(ICU::U_COMBINING_SPACING_MARK),
  90
  91     Number_DecimalDigit = TO_MASK(ICU::U_DECIMAL_DIGIT_NUMBER),
  92     Number_Letter = TO_MASK(ICU::U_LETTER_NUMBER),
  93     Number_Other = TO_MASK(ICU::U_OTHER_NUMBER),
  94
  95     Separator_Space = TO_MASK(ICU::U_SPACE_SEPARATOR),
  96     Separator_Line = TO_MASK(ICU::U_LINE_SEPARATOR),
  97     Separator_Paragraph = TO_MASK(ICU::U_PARAGRAPH_SEPARATOR),
  98
  99     Other_Control = TO_MASK(ICU::U_CONTROL_CHAR),
 100     Other_Format = TO_MASK(ICU::U_FORMAT_CHAR),
 101     Other_PrivateUse = TO_MASK(ICU::U_PRIVATE_USE_CHAR),
 102     Other_Surrogate = TO_MASK(ICU::U_SURROGATE),
 103
 104     Punctuation_Dash = TO_MASK(ICU::U_DASH_PUNCTUATION),
 105     Punctuation_Open = TO_MASK(ICU::U_START_PUNCTUATION),
 106     Punctuation_Close = TO_MASK(ICU::U_END_PUNCTUATION),
 107     Punctuation_Connector = TO_MASK(ICU::U_CONNECTOR_PUNCTUATION),
 108     Punctuation_Other = TO_MASK(ICU::U_OTHER_PUNCTUATION),
 109
 110     Symbol_Math = TO_MASK(ICU::U_MATH_SYMBOL),
 111     Symbol_Currency = TO_MASK(ICU::U_CURRENCY_SYMBOL),
 112     Symbol_Modifier = TO_MASK(ICU::U_MODIFIER_SYMBOL),
 113     Symbol_Other = TO_MASK(ICU::U_OTHER_SYMBOL),
 114
 115     Punctuation_InitialQuote = TO_MASK(ICU::U_INITIAL_PUNCTUATION),
 116     Punctuation_FinalQuote = TO_MASK(ICU::U_FINAL_PUNCTUATION)
 117 };
 118
 119 UChar foldCase(UChar);
 120
 121 int foldCase(UChar* result, int resultLength, const UChar* source, int sourceLength, bool* isError);
 122
 123 int toLower(UChar* result, int resultLength, const UChar* source, int sourceLength, bool* isError);
 124
 125 UChar toUpper(UChar);
 126 UChar toLower(UChar);
 127
 128 bool isUpper(UChar);
 129
 130 int toUpper(UChar* result, int resultLength, const UChar* source, int sourceLength, bool* isError);
 131
 132 UChar toTitleCase(UChar);
 133
 134 inline bool isArabicChar(UChar32 c)
 135 {
 136     return c >= 0x0600 && c <= 0x06FF;
 137 }
 138
 139 bool isAlphanumeric(UChar);
 140
 141 CharCategory category(unsigned int);
 142
 143 inline bool isSeparatorSpace(UChar c)
 144 {
 145     return category(c) == Separator_Space;
 146 }
 147
 148 bool isPrintableChar(UChar);
 149
 150 bool isDigit(UChar);
 151
 152 bool isPunct(UChar);
 153
 154 inline bool hasLineBreakingPropertyComplexContext(UChar32)
 155 {
 156     // FIXME: implement!
 157     return false;
 158 }
 159
 160 inline bool hasLineBreakingPropertyComplexContextOrIdeographic(UChar32 c)
 161 {
 162     // FIXME
 163     return false;
 164 }
 165
 166 UChar mirroredChar(UChar32);
 167
 168 Direction direction(UChar32);
 169
 170 bool isLower(UChar);
 171
 172 int digitValue(UChar);
 173
 174 unsigned char combiningClass(UChar32);
 175
 176 DecompositionType decompositionType(UChar32);
 177
 178 inline int umemcasecmp(const UChar* a, const UChar* b, int len)
 179 {
 180     for (int i = 0; i < len; ++i) {
 181         UChar c1 = foldCase(a[i]);
 182         UChar c2 = foldCase(b[i]);
 183         if (c1 != c2)
 184             return c1 - c2;
 185     }
 186     return 0;
 187 }
 188
 189 bool isSpace(UChar);
 190 bool isLetter(UChar);
 191
 192 } // namespace Unicode
 193 } // namespace WTF
 194
 195 #endif