1/* 2 * Copyright (C) Research In Motion Limited 2011. All rights reserved. 3 * 4 * This library is free software; you can redistribute it and/or 5 * modify it under the terms of the GNU Library General Public 6 * License as published by the Free Software Foundation; either 7 * version 2 of the License, or (at your option) any later version. 8 * 9 * This library is distributed in the hope that it will be useful, 10 * but WITHOUT ANY WARRANTY; without even the implied warranty of 11 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU 12 * Library General Public License for more details. 13 * 14 * You should have received a copy of the GNU Library General Public License 15 * along with this library; see the file COPYING.LIB. If not, write to 16 * the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, 17 * Boston, MA 02110-1301, USA. 18 * 19 */ 20 21#ifndef SurrogatePairAwareTextIterator_h 22#define SurrogatePairAwareTextIterator_h 23 24#include "platform/PlatformExport.h" 25#include "wtf/text/WTFString.h" 26#include "wtf/unicode/CharacterNames.h" 27 28namespace blink { 29 30class PLATFORM_EXPORT SurrogatePairAwareTextIterator { 31public: 32 // The passed in UChar pointer starts at 'currentCharacter'. The iterator operatoes on the range [currentCharacter, lastCharacter]. 33 // 'endCharacter' denotes the maximum length of the UChar array, which might exceed 'lastCharacter'. 34 SurrogatePairAwareTextIterator(const UChar*, int currentCharacter, int lastCharacter, int endCharacter); 35 36 inline bool consume(UChar32& character, unsigned& clusterLength) 37 { 38 if (m_currentCharacter >= m_lastCharacter) 39 return false; 40 41 character = *m_characters; 42 clusterLength = 1; 43 44 if (character < HiraganaLetterSmallA) 45 return true; 46 47 return consumeSlowCase(character, clusterLength); 48 } 49 50 void advance(unsigned advanceLength) 51 { 52 m_characters += advanceLength; 53 m_currentCharacter += advanceLength; 54 } 55 56 int currentCharacter() const { return m_currentCharacter; } 57 const UChar* characters() const { return m_characters; } 58 59private: 60 bool consumeSlowCase(UChar32&, unsigned&); 61 UChar32 normalizeVoicingMarks(); 62 63 const UChar* m_characters; 64 int m_currentCharacter; 65 int m_lastCharacter; 66 int m_endCharacter; 67}; 68 69} 70 71#endif 72