From 267c6f2ac71f92999e969232431ba04678e7437e Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Mon, 15 Apr 2024 07:54:39 +0200 Subject: Adding upstream version 4:24.2.0. Signed-off-by: Daniel Baumann --- i18npool/inc/xdictionary.hxx | 94 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 94 insertions(+) create mode 100644 i18npool/inc/xdictionary.hxx (limited to 'i18npool/inc/xdictionary.hxx') diff --git a/i18npool/inc/xdictionary.hxx b/i18npool/inc/xdictionary.hxx new file mode 100644 index 0000000000..f0861408bb --- /dev/null +++ b/i18npool/inc/xdictionary.hxx @@ -0,0 +1,94 @@ +/* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */ +/* + * This file is part of the LibreOffice project. + * + * This Source Code Form is subject to the terms of the Mozilla Public + * License, v. 2.0. If a copy of the MPL was not distributed with this + * file, You can obtain one at http://mozilla.org/MPL/2.0/. + * + * This file incorporates work covered by the following license notice: + * + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed + * with this work for additional information regarding copyright + * ownership. The ASF licenses this file to you under the Apache + * License, Version 2.0 (the "License"); you may not use this file + * except in compliance with the License. You may obtain a copy of + * the License at http://www.apache.org/licenses/LICENSE-2.0 . + */ +#pragma once + +#include +#include + +#include + +namespace i18npool { + +#define CACHE_MAX 32 // max cache structure number +#define DEFAULT_SIZE 256 // for boundary size, to avoid alloc and release memory + +// cache structure. +struct WordBreakCache { + sal_Unicode *contents; // separated segment contents. + sal_Int32* wordboundary; // word boundaries in segments. + sal_Int32 length; // contents length saved here. + sal_Int32 size; // size of wordboundary + + WordBreakCache(); + bool equals(const sal_Unicode *str, css::i18n::Boundary const & boundary) const; // checking cached string +}; + +struct xdictionarydata +{ + const sal_uInt8 * existMark; + const sal_Int16 * index1; + const sal_Int32 * index2; + const sal_Int32 * lenArray; + const sal_Unicode* dataArea; + xdictionarydata() : + existMark( nullptr ), + index1( nullptr ), + index2( nullptr ), + lenArray( nullptr ), + dataArea( nullptr ) + { + } +}; + +class xdictionary +{ +private: + xdictionarydata data; + void initDictionaryData(const char *lang); + + css::i18n::Boundary boundary; + bool japaneseWordBreak; +#ifdef DICT_JA_ZH_IN_DATAFILE + oslFileHandle m_aFileHandle; + sal_uInt64 m_nFileSize; + char* m_pMapping; +#endif + +public: + xdictionary(const char *lang); + ~xdictionary(); + css::i18n::Boundary nextWord( const OUString& rText, sal_Int32 nPos, sal_Int16 wordType); + css::i18n::Boundary previousWord( const OUString& rText, sal_Int32 nPos, sal_Int16 wordType); + css::i18n::Boundary const & getWordBoundary( const OUString& rText, sal_Int32 nPos, sal_Int16 wordType, bool bDirection ); + void setJapaneseWordBreak(); + +private: + WordBreakCache cache[CACHE_MAX]; + OUString segmentCachedString; + css::i18n::Boundary segmentCachedBoundary; + + bool seekSegment(const OUString& rText, sal_Int32 pos, css::i18n::Boundary& boundary); + WordBreakCache& getCache(const sal_Unicode *text, css::i18n::Boundary const & boundary); + bool exists(const sal_uInt32 u) const; + sal_Int32 getLongestMatch(const sal_Unicode *text, sal_Int32 len) const; +}; + +} + +/* vim:set shiftwidth=4 softtabstop=4 expandtab: */ -- cgit v1.2.3