| OLD | NEW |
| 1 /* | 1 // Copyright 2017 The Chromium Authors. All rights reserved. |
| 2 * Copyright (C) 2006 George Staikos <staikos@kde.org> | 2 // Use of this source code is governed by a BSD-style license that can be |
| 3 * Copyright (C) 2006 Alexey Proskuryakov <ap@nypop.com> | 3 // found in the LICENSE file. |
| 4 * Copyright (C) 2006, 2007, 2008, 2009 Apple Inc. All rights reserved. | |
| 5 * | |
| 6 * This library is free software; you can redistribute it and/or | |
| 7 * modify it under the terms of the GNU Library General Public | |
| 8 * License as published by the Free Software Foundation; either | |
| 9 * version 2 of the License, or (at your option) any later version. | |
| 10 * | |
| 11 * This library is distributed in the hope that it will be useful, | |
| 12 * but WITHOUT ANY WARRANTY; without even the implied warranty of | |
| 13 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU | |
| 14 * Library General Public License for more details. | |
| 15 * | |
| 16 * You should have received a copy of the GNU Library General Public License | |
| 17 * along with this library; see the file COPYING.LIB. If not, write to | |
| 18 * the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, | |
| 19 * Boston, MA 02110-1301, USA. | |
| 20 * | |
| 21 */ | |
| 22 | 4 |
| 23 #ifndef WTF_UnicodeIcu_h | 5 #include "platform/wtf/text/icu/UnicodeIcu.h" |
| 24 #define WTF_UnicodeIcu_h | |
| 25 | 6 |
| 26 #include <unicode/uchar.h> | 7 // The contents of this header was moved to platform/wtf as part of |
| 27 #include <unicode/ustring.h> | 8 // WTF migration project. See the following post for details: |
| 28 | 9 // https://groups.google.com/a/chromium.org/d/msg/blink-dev/tLdAZCTlcAA/bYXVT8gY
CAAJ |
| 29 namespace WTF { | |
| 30 | |
| 31 namespace Unicode { | |
| 32 | |
| 33 enum CharDirection { | |
| 34 LeftToRight = U_LEFT_TO_RIGHT, | |
| 35 RightToLeft = U_RIGHT_TO_LEFT, | |
| 36 EuropeanNumber = U_EUROPEAN_NUMBER, | |
| 37 EuropeanNumberSeparator = U_EUROPEAN_NUMBER_SEPARATOR, | |
| 38 EuropeanNumberTerminator = U_EUROPEAN_NUMBER_TERMINATOR, | |
| 39 ArabicNumber = U_ARABIC_NUMBER, | |
| 40 CommonNumberSeparator = U_COMMON_NUMBER_SEPARATOR, | |
| 41 BlockSeparator = U_BLOCK_SEPARATOR, | |
| 42 SegmentSeparator = U_SEGMENT_SEPARATOR, | |
| 43 WhiteSpaceNeutral = U_WHITE_SPACE_NEUTRAL, | |
| 44 OtherNeutral = U_OTHER_NEUTRAL, | |
| 45 LeftToRightEmbedding = U_LEFT_TO_RIGHT_EMBEDDING, | |
| 46 LeftToRightOverride = U_LEFT_TO_RIGHT_OVERRIDE, | |
| 47 RightToLeftArabic = U_RIGHT_TO_LEFT_ARABIC, | |
| 48 RightToLeftEmbedding = U_RIGHT_TO_LEFT_EMBEDDING, | |
| 49 RightToLeftOverride = U_RIGHT_TO_LEFT_OVERRIDE, | |
| 50 PopDirectionalFormat = U_POP_DIRECTIONAL_FORMAT, | |
| 51 NonSpacingMark = U_DIR_NON_SPACING_MARK, | |
| 52 BoundaryNeutral = U_BOUNDARY_NEUTRAL | |
| 53 }; | |
| 54 | |
| 55 enum CharDecompositionType { | |
| 56 DecompositionNone = U_DT_NONE, | |
| 57 DecompositionCanonical = U_DT_CANONICAL, | |
| 58 DecompositionCompat = U_DT_COMPAT, | |
| 59 DecompositionCircle = U_DT_CIRCLE, | |
| 60 DecompositionFinal = U_DT_FINAL, | |
| 61 DecompositionFont = U_DT_FONT, | |
| 62 DecompositionFraction = U_DT_FRACTION, | |
| 63 DecompositionInitial = U_DT_INITIAL, | |
| 64 DecompositionIsolated = U_DT_ISOLATED, | |
| 65 DecompositionMedial = U_DT_MEDIAL, | |
| 66 DecompositionNarrow = U_DT_NARROW, | |
| 67 DecompositionNoBreak = U_DT_NOBREAK, | |
| 68 DecompositionSmall = U_DT_SMALL, | |
| 69 DecompositionSquare = U_DT_SQUARE, | |
| 70 DecompositionSub = U_DT_SUB, | |
| 71 DecompositionSuper = U_DT_SUPER, | |
| 72 DecompositionVertical = U_DT_VERTICAL, | |
| 73 DecompositionWide = U_DT_WIDE, | |
| 74 }; | |
| 75 | |
| 76 enum CharCategory { | |
| 77 NoCategory = 0, | |
| 78 Other_NotAssigned = U_MASK(U_GENERAL_OTHER_TYPES), | |
| 79 Letter_Uppercase = U_MASK(U_UPPERCASE_LETTER), | |
| 80 Letter_Lowercase = U_MASK(U_LOWERCASE_LETTER), | |
| 81 Letter_Titlecase = U_MASK(U_TITLECASE_LETTER), | |
| 82 Letter_Modifier = U_MASK(U_MODIFIER_LETTER), | |
| 83 Letter_Other = U_MASK(U_OTHER_LETTER), | |
| 84 | |
| 85 Mark_NonSpacing = U_MASK(U_NON_SPACING_MARK), | |
| 86 Mark_Enclosing = U_MASK(U_ENCLOSING_MARK), | |
| 87 Mark_SpacingCombining = U_MASK(U_COMBINING_SPACING_MARK), | |
| 88 | |
| 89 Number_DecimalDigit = U_MASK(U_DECIMAL_DIGIT_NUMBER), | |
| 90 Number_Letter = U_MASK(U_LETTER_NUMBER), | |
| 91 Number_Other = U_MASK(U_OTHER_NUMBER), | |
| 92 | |
| 93 Separator_Space = U_MASK(U_SPACE_SEPARATOR), | |
| 94 Separator_Line = U_MASK(U_LINE_SEPARATOR), | |
| 95 Separator_Paragraph = U_MASK(U_PARAGRAPH_SEPARATOR), | |
| 96 | |
| 97 Other_Control = U_MASK(U_CONTROL_CHAR), | |
| 98 Other_Format = U_MASK(U_FORMAT_CHAR), | |
| 99 Other_PrivateUse = U_MASK(U_PRIVATE_USE_CHAR), | |
| 100 Other_Surrogate = U_MASK(U_SURROGATE), | |
| 101 | |
| 102 Punctuation_Dash = U_MASK(U_DASH_PUNCTUATION), | |
| 103 Punctuation_Open = U_MASK(U_START_PUNCTUATION), | |
| 104 Punctuation_Close = U_MASK(U_END_PUNCTUATION), | |
| 105 Punctuation_Connector = U_MASK(U_CONNECTOR_PUNCTUATION), | |
| 106 Punctuation_Other = U_MASK(U_OTHER_PUNCTUATION), | |
| 107 | |
| 108 Symbol_Math = U_MASK(U_MATH_SYMBOL), | |
| 109 Symbol_Currency = U_MASK(U_CURRENCY_SYMBOL), | |
| 110 Symbol_Modifier = U_MASK(U_MODIFIER_SYMBOL), | |
| 111 Symbol_Other = U_MASK(U_OTHER_SYMBOL), | |
| 112 | |
| 113 Punctuation_InitialQuote = U_MASK(U_INITIAL_PUNCTUATION), | |
| 114 Punctuation_FinalQuote = U_MASK(U_FINAL_PUNCTUATION) | |
| 115 }; | |
| 116 | |
| 117 inline UChar32 foldCase(UChar32 c) { | |
| 118 return u_foldCase(c, U_FOLD_CASE_DEFAULT); | |
| 119 } | |
| 120 | |
| 121 inline int foldCase(UChar* result, | |
| 122 int resultLength, | |
| 123 const UChar* src, | |
| 124 int srcLength, | |
| 125 bool* error) { | |
| 126 UErrorCode status = U_ZERO_ERROR; | |
| 127 int realLength = u_strFoldCase(result, resultLength, src, srcLength, | |
| 128 U_FOLD_CASE_DEFAULT, &status); | |
| 129 *error = !U_SUCCESS(status); | |
| 130 return realLength; | |
| 131 } | |
| 132 | |
| 133 inline int toLower(UChar* result, | |
| 134 int resultLength, | |
| 135 const UChar* src, | |
| 136 int srcLength, | |
| 137 bool* error) { | |
| 138 UErrorCode status = U_ZERO_ERROR; | |
| 139 int realLength = | |
| 140 u_strToLower(result, resultLength, src, srcLength, "", &status); | |
| 141 *error = !!U_FAILURE(status); | |
| 142 return realLength; | |
| 143 } | |
| 144 | |
| 145 inline UChar32 toLower(UChar32 c) { | |
| 146 return u_tolower(c); | |
| 147 } | |
| 148 | |
| 149 inline UChar32 toUpper(UChar32 c) { | |
| 150 return u_toupper(c); | |
| 151 } | |
| 152 | |
| 153 inline int toUpper(UChar* result, | |
| 154 int resultLength, | |
| 155 const UChar* src, | |
| 156 int srcLength, | |
| 157 bool* error) { | |
| 158 UErrorCode status = U_ZERO_ERROR; | |
| 159 int realLength = | |
| 160 u_strToUpper(result, resultLength, src, srcLength, "", &status); | |
| 161 *error = !!U_FAILURE(status); | |
| 162 return realLength; | |
| 163 } | |
| 164 | |
| 165 inline UChar32 toTitleCase(UChar32 c) { | |
| 166 return u_totitle(c); | |
| 167 } | |
| 168 | |
| 169 inline bool isArabicChar(UChar32 c) { | |
| 170 return ublock_getCode(c) == UBLOCK_ARABIC; | |
| 171 } | |
| 172 | |
| 173 inline bool isAlphanumeric(UChar32 c) { | |
| 174 return !!u_isalnum(c); | |
| 175 } | |
| 176 | |
| 177 inline bool isSeparatorSpace(UChar32 c) { | |
| 178 return u_charType(c) == U_SPACE_SEPARATOR; | |
| 179 } | |
| 180 | |
| 181 inline bool isPrintableChar(UChar32 c) { | |
| 182 return !!u_isprint(c); | |
| 183 } | |
| 184 | |
| 185 inline bool isPunct(UChar32 c) { | |
| 186 return !!u_ispunct(c); | |
| 187 } | |
| 188 | |
| 189 inline bool hasLineBreakingPropertyComplexContext(UChar32 c) { | |
| 190 return u_getIntPropertyValue(c, UCHAR_LINE_BREAK) == U_LB_COMPLEX_CONTEXT; | |
| 191 } | |
| 192 | |
| 193 inline UChar32 mirroredChar(UChar32 c) { | |
| 194 return u_charMirror(c); | |
| 195 } | |
| 196 | |
| 197 inline CharCategory category(UChar32 c) { | |
| 198 return static_cast<CharCategory>(U_GET_GC_MASK(c)); | |
| 199 } | |
| 200 | |
| 201 inline CharDirection direction(UChar32 c) { | |
| 202 return static_cast<CharDirection>(u_charDirection(c)); | |
| 203 } | |
| 204 | |
| 205 inline bool isLower(UChar32 c) { | |
| 206 return !!u_islower(c); | |
| 207 } | |
| 208 | |
| 209 inline uint8_t combiningClass(UChar32 c) { | |
| 210 return u_getCombiningClass(c); | |
| 211 } | |
| 212 | |
| 213 inline CharDecompositionType decompositionType(UChar32 c) { | |
| 214 return static_cast<CharDecompositionType>( | |
| 215 u_getIntPropertyValue(c, UCHAR_DECOMPOSITION_TYPE)); | |
| 216 } | |
| 217 | |
| 218 inline int umemcasecmp(const UChar* a, const UChar* b, int len) { | |
| 219 return u_memcasecmp(a, b, len, U_FOLD_CASE_DEFAULT); | |
| 220 } | |
| 221 | |
| 222 } // namespace Unicode | |
| 223 | |
| 224 } // namespace WTF | |
| 225 | |
| 226 #endif // WTF_UnicodeIcu_h | |
| OLD | NEW |