374 lines
14 KiB
Text
374 lines
14 KiB
Text
/*************************************************************************
|
|
*
|
|
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
|
|
*
|
|
* Copyright 2000, 2010 Oracle and/or its affiliates.
|
|
*
|
|
* OpenOffice.org - a multi-platform office productivity suite
|
|
*
|
|
* This file is part of OpenOffice.org.
|
|
*
|
|
* OpenOffice.org is free software: you can redistribute it and/or modify
|
|
* it under the terms of the GNU Lesser General Public License version 3
|
|
* only, as published by the Free Software Foundation.
|
|
*
|
|
* OpenOffice.org is distributed in the hope that it will be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
* GNU Lesser General Public License version 3 for more details
|
|
* (a copy is included in the LICENSE file that accompanied this code).
|
|
*
|
|
* You should have received a copy of the GNU Lesser General Public License
|
|
* version 3 along with OpenOffice.org. If not, see
|
|
* <http://www.openoffice.org/license.html>
|
|
* for a copy of the LGPLv3 License.
|
|
*
|
|
************************************************************************/
|
|
#ifndef __com_sun_star_i18n_XBreakIterator_idl__
|
|
#define __com_sun_star_i18n_XBreakIterator_idl__
|
|
|
|
#ifndef __com_sun_star_lang_Locale_idl__
|
|
#include <com/sun/star/lang/Locale.idl>
|
|
#endif
|
|
|
|
#ifndef __com_sun_star_i18n_LineBreakUserOptions_idl__
|
|
#include <com/sun/star/i18n/LineBreakUserOptions.idl>
|
|
#endif
|
|
|
|
#ifndef __com_sun_star_i18n_LineBreakHyphenationOptions_idl__
|
|
#include <com/sun/star/i18n/LineBreakHyphenationOptions.idl>
|
|
#endif
|
|
|
|
#ifndef __com_sun_star_i18n_LineBreakResults_idl__
|
|
#include <com/sun/star/i18n/LineBreakResults.idl>
|
|
#endif
|
|
|
|
#ifndef __com_sun_star_i18n_Boundary_idl__
|
|
#include <com/sun/star/i18n/Boundary.idl>
|
|
#endif
|
|
|
|
//============================================================================
|
|
|
|
module com { module sun { module star { module i18n {
|
|
|
|
//============================================================================
|
|
|
|
/**
|
|
contains the base routines for iteration in Unicode string. Iterates over
|
|
characters, words, sentences and line breaks.
|
|
|
|
<p> Assumption: StartPos is inclusive and EndPos is exclusive. </p>
|
|
*/
|
|
|
|
published interface XBreakIterator: com::sun::star::uno::XInterface
|
|
{
|
|
//------------------------------------------------------------------------
|
|
/** Traverses specified number of characters/cells in Text from
|
|
<em>nStartPos</em> forwards.
|
|
<type>CharacterIteratorMode</type> can be cell based or
|
|
character based. A cell is made of more than one character.
|
|
|
|
@param nCount
|
|
Number of characters to traverse, it should not be less than 0.
|
|
If you want to traverse in the opposite direction use
|
|
<member>XBreakIterator::previousCharacters()</member> instead.
|
|
*/
|
|
long nextCharacters( [in] string aText, [in] long nStartPos,
|
|
[in] ::com::sun::star::lang::Locale aLocale,
|
|
[in] short nCharacterIteratorMode,
|
|
[in] long nCount, [out] long nDone );
|
|
|
|
//------------------------------------------------------------------------
|
|
/** Traverses specified number of characters/cells in Text from
|
|
<em>nStartPos</em> backwards.
|
|
<type>CharacterIteratorMode</type> can be cell based or
|
|
character based. A cell is made of more than one character.
|
|
|
|
@param nCount
|
|
Number of characters to traverse, it should not be less than 0.
|
|
If you want to traverse in the opposite direction use
|
|
<member>XBreakIterator::nextCharacters()</member> instead.
|
|
*/
|
|
long previousCharacters( [in] string aText, [in] long nStartPos,
|
|
[in] ::com::sun::star::lang::Locale aLocale,
|
|
[in] short nCharacterIteratorMode,
|
|
[in] long nCount, [out] long nDone );
|
|
|
|
//------------------------------------------------------------------------
|
|
/** Traverses one word in Text from <em>nStartPos</em> forwards.
|
|
|
|
@param nWordType
|
|
One of <type>WordType</type>, specifies the type of
|
|
travelling.
|
|
|
|
@returns
|
|
The <type>Boundary</type> of the found word. Normally used for
|
|
CTRL-Right.
|
|
*/
|
|
Boundary nextWord( [in] string aText, [in] long nStartPos,
|
|
[in] ::com::sun::star::lang::Locale aLocale,
|
|
[in] short nWordType);
|
|
|
|
//------------------------------------------------------------------------
|
|
/** Traverses one word in Text from <em>nStartPos</em> backwards.
|
|
|
|
@param aLocale
|
|
The locale of the character preceding <em>nStartPos</em>.
|
|
|
|
<p> If the previous character is a space character and
|
|
<em>nWordType</em> indicates spaces should be skipped, and
|
|
if the first non-space character is an Asian character,
|
|
then, since Asian word break needs language specific
|
|
wordbreak dictionaries, the method will return -1 in
|
|
<member>Boundary::endPos</member> and the position after the
|
|
Asian character (i.e. the space character) in
|
|
<member>Boundary::startPos</member>. The caller then has to
|
|
call this method again with a correct <em>aLocale</em>
|
|
referring to the Asian character, which is then the previous
|
|
character of the space character where <em>nStartPos</em>
|
|
points to. </p>
|
|
|
|
<p> <b>Note</b> that the OpenOffice.org 1.0 / StarOffice 6.0
|
|
/ StarSuite 6.0 i18n framework doesn't behave like this and
|
|
mixed Western/CJK text may lead to wrong word iteration.
|
|
This is fixed in later versions. </p>
|
|
|
|
@param nWordType
|
|
One of <type>WordType</type>, specifies the type of
|
|
travelling.
|
|
|
|
@returns
|
|
The <type>Boundary</type> of the found word. Normally used for
|
|
CTRL-Left.
|
|
*/
|
|
Boundary previousWord( [in] string aText, [in] long nStartPos,
|
|
[in] ::com::sun::star::lang::Locale aLocale,
|
|
[in] short nWordType);
|
|
|
|
//------------------------------------------------------------------------
|
|
/** Identifies StartPos and EndPos of current word.
|
|
|
|
<p> If <em>nPos</em> is the boundary of a word, it is StartPos
|
|
of one word and EndPos of previous word. In this situation, the
|
|
outcome of the algorithm can be indeterminate. In this situation
|
|
the <em>bPreferForward</em> flag is used. If bPreferForward ==
|
|
<FALSE/>, <em>nPos</em> is considered to be the end of the word
|
|
and we look backwards for beginning of word, otherwise
|
|
<em>nPos</em> is considered to be the start of the next word and
|
|
we look forwards for the end of the word. </p>
|
|
|
|
@param nWordType
|
|
One of <type>WordType</type>.
|
|
|
|
@returns
|
|
The Boundary of the current word.
|
|
*/
|
|
Boundary getWordBoundary( [in] string aText, [in] long nPos,
|
|
[in] ::com::sun::star::lang::Locale aLocale,
|
|
[in] short nWordType,
|
|
[in] boolean bPreferForward );
|
|
|
|
//------------------------------------------------------------------------
|
|
/** @deprecated
|
|
Get the <type>WordType</type> of the word that starts at
|
|
position <em>nPos</em>.
|
|
|
|
<p> This method is mis-defined, since <type>WordType</type>
|
|
is not an attribute of a word, but a way to break words,
|
|
like excluding or including tail spaces for spellchecker
|
|
or cursor traveling. It returns 0 always.
|
|
</p>
|
|
*/
|
|
short getWordType( [in] string aText, [in] long nPos,
|
|
[in] ::com::sun::star::lang::Locale aLocale);
|
|
|
|
//------------------------------------------------------------------------
|
|
/** If a word starts at position <em>nPos</em>.
|
|
|
|
<p> It is possible that both of this method
|
|
and following method <em>isEndWord</em> all return
|
|
<TRUE/>, since StartPos of a word is inclusive
|
|
while EndPos of a word is exclusive.
|
|
</p>
|
|
|
|
*/
|
|
boolean isBeginWord( [in] string aText, [in] long nPos,
|
|
[in] ::com::sun::star::lang::Locale aLocale,
|
|
[in] short nWordType);
|
|
|
|
//------------------------------------------------------------------------
|
|
/** If a word ends at position <em>nPos</em>.
|
|
*/
|
|
boolean isEndWord( [in] string aText, [in] long nPos,
|
|
[in] ::com::sun::star::lang::Locale aLocale,
|
|
[in] short nWordType);
|
|
|
|
//------------------------------------------------------------------------
|
|
/** Traverses in Text from <em>nStartPos</em> to the start of a
|
|
sentence.
|
|
|
|
@returns
|
|
The position where the sentence starts.
|
|
*/
|
|
long beginOfSentence( [in] string aText, [in] long nStartPos,
|
|
[in] ::com::sun::star::lang::Locale aLocale );
|
|
|
|
//------------------------------------------------------------------------
|
|
/** Traverses in Text from <em>nStartPos</em> to the end of a
|
|
sentence.
|
|
|
|
@returns
|
|
The position where the sentence ends.
|
|
*/
|
|
long endOfSentence( [in] string aText, [in] long nStartPos,
|
|
[in] ::com::sun::star::lang::Locale aLocale );
|
|
|
|
//------------------------------------------------------------------------
|
|
/** Calculate the line break position in the Text from the specified
|
|
<em>nStartPos</em>.
|
|
|
|
@param nMinBreakPos
|
|
Defines a minimum break position for hyphenated line break.
|
|
When the position for hyphenated line break is less than
|
|
<em>nMinBreakPos</em>, break position in
|
|
<type>LineBreakResults</type> is set to -1.
|
|
|
|
@param aHyphOptions
|
|
Defines if the hyphenator is to be used.
|
|
|
|
@param aUserOptions
|
|
Defines how to handle hanging punctuations and forbidden
|
|
characters at the start/end of a line.
|
|
|
|
@returns
|
|
The <type>LineBreakResults</type> contain the break
|
|
position of the line, <type>BreakType</type> and
|
|
<type scope="com::sun::star::linguistic2">XHyphenatedWord</type>
|
|
*/
|
|
LineBreakResults getLineBreak( [in] string aText, [in] long nStartPos,
|
|
[in] ::com::sun::star::lang::Locale aLocale,
|
|
[in] long nMinBreakPos,
|
|
[in] LineBreakHyphenationOptions aHyphOptions,
|
|
[in] LineBreakUserOptions aUserOptions );
|
|
|
|
//------------------------------------------------------------------------
|
|
/** Traverses in Text from <em>nStartPos</em> to the beginning of
|
|
the specified script type.
|
|
|
|
@param nScriptType
|
|
One of <type>ScriptType</type>.
|
|
|
|
@returns
|
|
The position where the script type starts.
|
|
*/
|
|
long beginOfScript( [in] string aText, [in] long nStartPos,
|
|
[in] short nScriptType );
|
|
|
|
//------------------------------------------------------------------------
|
|
/** Traverses in Text from <em>nStartPos</em> to the end of the
|
|
specified script type.
|
|
|
|
@param nScriptType
|
|
One of <type>ScriptType</type>.
|
|
|
|
@returns
|
|
The position where the script type ends.
|
|
*/
|
|
long endOfScript( [in] string aText, [in] long nStartPos,
|
|
[in] short nScriptType );
|
|
|
|
//------------------------------------------------------------------------
|
|
/** Traverses in Text from <em>nStartPos</em> to the next start of
|
|
the specified script type.
|
|
|
|
@param nScriptType
|
|
One of <type>ScriptType</type>.
|
|
|
|
@returns
|
|
The position where the next script type starts.
|
|
*/
|
|
long nextScript( [in] string aText, [in] long nStartPos,
|
|
[in] short nScriptType );
|
|
|
|
//------------------------------------------------------------------------
|
|
/** Traverses in Text from <em>nStartPos</em> to the previous start
|
|
of the specified script type.
|
|
|
|
@param nScriptType
|
|
One of <type>ScriptType</type>.
|
|
|
|
@returns
|
|
The position where the previous script type starts.
|
|
*/
|
|
long previousScript( [in] string aText, [in] long nStartPos,
|
|
[in] short nScriptType );
|
|
|
|
//------------------------------------------------------------------------
|
|
/** Get the script type of the character at position <em>nPos</em>.
|
|
|
|
@returns
|
|
One of <type>ScriptType</type>.
|
|
*/
|
|
short getScriptType( [in] string aText, [in] long nPos);
|
|
|
|
//------------------------------------------------------------------------
|
|
/** Traverses in Text from <em>nStartPos</em> to the beginning of
|
|
the specified character type.
|
|
|
|
@param nCharType
|
|
One of <type>CharType</type>
|
|
|
|
@returns
|
|
The position where the character type starts
|
|
*/
|
|
long beginOfCharBlock( [in] string aText, [in] long nStartPos,
|
|
[in] ::com::sun::star::lang::Locale aLocale,
|
|
[in] short nCharType );
|
|
|
|
//------------------------------------------------------------------------
|
|
/** Traverses in Text from <em>nStartPos</em> to the end of the
|
|
specified character type.
|
|
|
|
@param nCharType
|
|
One of <type>CharType</type>
|
|
|
|
@returns
|
|
The position where the character type ends.
|
|
*/
|
|
long endOfCharBlock( [in] string aText, [in] long nStartPos,
|
|
[in] ::com::sun::star::lang::Locale aLocale,
|
|
[in] short nCharType );
|
|
|
|
//------------------------------------------------------------------------
|
|
/** Traverses in Text from <em>nStartPos</em> to the next start of
|
|
the specified character type.
|
|
|
|
@param nCharType
|
|
One of <type>CharType</type>
|
|
|
|
@returns
|
|
The position where the next character type starts.
|
|
*/
|
|
long nextCharBlock( [in] string aText, [in] long nStartPos,
|
|
[in] ::com::sun::star::lang::Locale aLocale,
|
|
[in] short nCharType );
|
|
|
|
//------------------------------------------------------------------------
|
|
/** Traverses in Text from <em>nStartPos</em> to the previous start
|
|
of the specified character type.
|
|
|
|
@param nCharType
|
|
One of <type>CharType</type>
|
|
|
|
@returns
|
|
The position where the previous character type starts.
|
|
*/
|
|
long previousCharBlock ( [in] string aText, [in] long nStartPos,
|
|
[in] ::com::sun::star::lang::Locale aLocale,
|
|
[in] short nCharType );
|
|
};
|
|
|
|
//============================================================================
|
|
}; }; }; };
|
|
|
|
#endif
|