1 /* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
3 * This file is part of the LibreOffice project.
5 * This Source Code Form is subject to the terms of the Mozilla Public
6 * License, v. 2.0. If a copy of the MPL was not distributed with this
7 * file, You can obtain one at http://mozilla.org/MPL/2.0/.
9 * This file incorporates work covered by the following license notice:
11 * Licensed to the Apache Software Foundation (ASF) under one or more
12 * contributor license agreements. See the NOTICE file distributed
13 * with this work for additional information regarding copyright
14 * ownership. The ASF licenses this file to you under the Apache
15 * License, Version 2.0 (the "License"); you may not use this file
16 * except in compliance with the License. You may obtain a copy of
17 * the License at http://www.apache.org/licenses/LICENSE-2.0 .
20 #include <breakiterator_cjk.hxx>
21 #include <localedata.hxx>
22 #include <i18nutil/unicode.hxx>
24 using namespace ::com::sun::star::uno
;
25 using namespace ::com::sun::star::lang
;
27 namespace com
{ namespace sun
{ namespace star
{ namespace i18n
{
29 // ----------------------------------------------------
30 // class BreakIterator_CJK
31 // ----------------------------------------------------;
33 BreakIterator_CJK::BreakIterator_CJK() :
37 cBreakIterator
= "com.sun.star.i18n.BreakIterator_CJK";
41 BreakIterator_CJK::previousWord(const OUString
& text
, sal_Int32 anyPos
,
42 const lang::Locale
& nLocale
, sal_Int16 wordType
) throw(RuntimeException
, std::exception
)
45 result
= dict
->previousWord(text
, anyPos
, wordType
);
46 // #109813# for non-CJK, single character word, fallback to ICU breakiterator.
47 if (result
.endPos
- result
.startPos
!= 1 ||
48 getScriptType(text
, result
.startPos
) == ScriptType::ASIAN
)
50 result
= BreakIterator_Unicode::getWordBoundary(text
, result
.startPos
, nLocale
, wordType
, true);
51 if (result
.endPos
< anyPos
)
54 return BreakIterator_Unicode::previousWord(text
, anyPos
, nLocale
, wordType
);
58 BreakIterator_CJK::nextWord(const OUString
& text
, sal_Int32 anyPos
,
59 const lang::Locale
& nLocale
, sal_Int16 wordType
) throw(RuntimeException
, std::exception
)
62 result
= dict
->nextWord(text
, anyPos
, wordType
);
63 // #109813# for non-CJK, single character word, fallback to ICU breakiterator.
64 if (result
.endPos
- result
.startPos
!= 1 ||
65 getScriptType(text
, result
.startPos
) == ScriptType::ASIAN
)
67 result
= BreakIterator_Unicode::getWordBoundary(text
, result
.startPos
, nLocale
, wordType
, true);
68 if (result
.startPos
> anyPos
)
71 return BreakIterator_Unicode::nextWord(text
, anyPos
, nLocale
, wordType
);
75 BreakIterator_CJK::getWordBoundary( const OUString
& text
, sal_Int32 anyPos
,
76 const lang::Locale
& nLocale
, sal_Int16 wordType
, sal_Bool bDirection
)
77 throw(RuntimeException
, std::exception
)
80 result
= dict
->getWordBoundary(text
, anyPos
, wordType
, bDirection
);
81 // #109813# for non-CJK, single character word, fallback to ICU breakiterator.
82 if (result
.endPos
- result
.startPos
!= 1 ||
83 getScriptType(text
, result
.startPos
) == ScriptType::ASIAN
)
86 return BreakIterator_Unicode::getWordBoundary(text
, anyPos
, nLocale
, wordType
, bDirection
);
89 LineBreakResults SAL_CALL
BreakIterator_CJK::getLineBreak(
90 const OUString
& Text
, sal_Int32 nStartPos
,
91 const lang::Locale
& /*rLocale*/, sal_Int32
/*nMinBreakPos*/,
92 const LineBreakHyphenationOptions
& /*hOptions*/,
93 const LineBreakUserOptions
& bOptions
) throw(RuntimeException
, std::exception
)
97 if (bOptions
.allowPunctuationOutsideMargin
&&
98 hangingCharacters
.indexOf(Text
[nStartPos
]) != -1 &&
99 (Text
.iterateCodePoints( &nStartPos
), nStartPos
== Text
.getLength())) {
101 } else if (bOptions
.applyForbiddenRules
&& 0 < nStartPos
&& nStartPos
< Text
.getLength()) {
102 while (nStartPos
> 0 &&
103 (bOptions
.forbiddenBeginCharacters
.indexOf(Text
[nStartPos
]) != -1 ||
104 bOptions
.forbiddenEndCharacters
.indexOf(Text
[nStartPos
-1]) != -1))
105 Text
.iterateCodePoints( &nStartPos
, -1);
108 lbr
.breakIndex
= nStartPos
;
109 lbr
.breakType
= BreakType::WORDBOUNDARY
;
113 #define LOCALE(language, country) lang::Locale(language, country, OUString())
114 // ----------------------------------------------------
115 // class BreakIterator_zh
116 // ----------------------------------------------------;
117 BreakIterator_zh::BreakIterator_zh()
119 dict
= new xdictionary("zh");
120 hangingCharacters
= LocaleDataImpl().getHangingCharacters(LOCALE("zh", "CN"));
121 cBreakIterator
= "com.sun.star.i18n.BreakIterator_zh";
124 BreakIterator_zh::~BreakIterator_zh()
129 // ----------------------------------------------------
130 // class BreakIterator_zh_TW
131 // ----------------------------------------------------;
132 BreakIterator_zh_TW::BreakIterator_zh_TW()
134 dict
= new xdictionary("zh");
135 hangingCharacters
= LocaleDataImpl().getHangingCharacters(LOCALE("zh", "TW"));
136 cBreakIterator
= "com.sun.star.i18n.BreakIterator_zh_TW";
139 BreakIterator_zh_TW::~BreakIterator_zh_TW()
144 // ----------------------------------------------------
145 // class BreakIterator_ja
146 // ----------------------------------------------------;
147 BreakIterator_ja::BreakIterator_ja()
149 dict
= new xdictionary("ja");
150 dict
->setJapaneseWordBreak();
151 hangingCharacters
= LocaleDataImpl().getHangingCharacters(LOCALE("ja", "JP"));
152 cBreakIterator
= "com.sun.star.i18n.BreakIterator_ja";
155 BreakIterator_ja::~BreakIterator_ja()
160 // ----------------------------------------------------
161 // class BreakIterator_ko
162 // ----------------------------------------------------;
163 BreakIterator_ko::BreakIterator_ko()
165 hangingCharacters
= LocaleDataImpl().getHangingCharacters(LOCALE("ko", "KR"));
166 cBreakIterator
= "com.sun.star.i18n.BreakIterator_ko";
169 BreakIterator_ko::~BreakIterator_ko()
175 /* vim:set shiftwidth=4 softtabstop=4 expandtab: */