blob: c04a2cc66c7457b84c904ea1ed22c0674c555c53 [file] [log] [blame]
/**************************************************************
*
* 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
*
* Unless required by applicable law or agreed to in writing,
* software distributed under the License is distributed on an
* "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
* KIND, either express or implied. See the License for the
* specific language governing permissions and limitations
* under the License.
*
*************************************************************/
#ifndef __com_sun_star_linguistic2_XLanguageGuessing_idl__
#define __com_sun_star_linguistic2_XLanguageGuessing_idl__
#ifndef _COM_SUN_STAR_UNO_XINTERFACE_idl_
#include <com/sun/star/uno/XInterface.idl>
#endif
#ifndef _COM_SUN_STAR_LANG_LOCALE_idl_
#include <com/sun/star/lang/Locale.idl>
#endif
#ifndef _COM_SUN_STAR_LANG_ILLEGALARGUMENTEXCEPTION_IDL_
#include <com/sun/star/lang/IllegalArgumentException.idl>
#endif
module com { module sun { module star { module linguistic2 {
/** This interface allows to guess the language of a text
<p> The current set of supported languages is:
<ul>
<li>af : Afrikaans</li>
<li>am : Amharic</li>
<li>ar : Arabic</li>
<li>be : Belarus</li>
<li>br : Breton</li>
<li>bs : Bosnian</li>
<li>ca : Catalan</li>
<li>cs : Czech</li>
<li>cy : Welsh</li>
<li>da : Danish</li>
<li>de : German</li>
<li>drt : Drents</li>
<li>el : Greek</li>
<li>en : English</li>
<li>eo : Esperanto</li>
<li>es : Spanish</li>
<li>et : Estonian</li>
<li>eu : Basque</li>
<li>fa : Persian</li>
<li>fi : Finnish</li>
<li>fr : French</li>
<li>fy : Frisian</li>
<li>ga : Irish Gaelic</li>
<li>gd : Scots Gaelic</li>
<li>gv : Manx Gaelic</li>
<li>he : Hebrew</li>
<li>hi : Hindi</li>
<li>hr : Croatian</li>
<li>hu : Hungarian</li>
<li>hy : Armenian</li>
<li>id : Indonesian</li>
<li>is : Icelandic</li>
<li>it : Italian</li>
<li>ja : Japanese</li>
<li>ka : Georgian</li>
<li>ko : Korean</li>
<li>la : Latin</li>
<li>lb : Luxembourgish (added with OpenOffice 3.3)</li>
<li>lt : Lithuanian</li>
<li>lv : Latvian</li>
<li>mr : Marathi</li>
<li>ms : Malay</li>
<li>ne : Nepali</li>
<li>nl : Dutch</li>
<li>nb : Norwegian (Bokmal)</li>
<li>pl : Polish</li>
<li>pt-PT : Portuguese (Portugal)</li>
<li>qu : Quechua</li>
<li>rm : Romansh</li>
<li>ro : Romanian</li>
<li>ru : Russian</li>
<li>sa : Sanskrit</li>
<li>sco : Scots</li>
<li>sh : Serbian (written with latin characters)</li>
<li>sk-SK : Slovak (written with latin characters)</li>
<li>sl : Slovenian</li>
<li>sq : Albanian</li>
<li>sr : Serbian (written with cyrillic characters) (added with OpenOffice 3.4)</li>
<li>sv : Swedish</li>
<li>sw : Swahili</li>
<li>ta : Tamil</li>
<li>th : Thai</li>
<li>tl : Tagalog</li>
<li>tr : Turkish</li>
<li>uk : Ukrainian</li>
<li>vi : Vietnamese</li>
<li>yi : Yiddish</li>
<li>zh-CN : Chinese (simplified)</li>
<li>zh-TW : Chinese (traditional)</li>
</ul>
</p>
@since OpenOffice 2.2
*/
interface XLanguageGuessing
{
//-------------------------------------------------------------------------
/** determines the single most probable language of a sub-string.
<p>Please note that because statistical analysis is part
of the algorithm the the likelihood to get the correct
result increases with the length of the sub-string.
A word is much less likely guessed correctly compared to
a sentence or even a whole paragraph.</p>
<p>Also note that some languages are that 'close' to each other
that it will be quite unlikely to find a difference in them,
e.g. English (UK), English (IE) and English (AUS) and
most liklely English (US) as well. And thus the result may
be arbitrary.</p>
@returns
the locale for the language identified.
If no language could be identified the locale will be empty.
@param aText
all the text including the part that should checked.
@param nStartPos
specifies the starting index of the sub-string to be checked
The value must met 0 <= nStartPos < (length of text - 1).
@param nLen
specifies the length of the sub-string to be checked.
The value must met 0 <= nLen <= (length of text).
@see <type scope="com::sun::star::lang">Locale</type>
*/
com::sun::star::lang::Locale guessPrimaryLanguage(
[in] string aText,
[in] long nStartPos,
[in] long nLen )
raises( com::sun::star::lang::IllegalArgumentException );
//-------------------------------------------------------------------------
/** allows to explicitly discard some languages from the set of
languages possibly returned.
<p>By default all languages are enabled.</p>
*/
void disableLanguages(
[in] sequence< com::sun::star::lang::Locale > aLanguages )
raises( com::sun::star::lang::IllegalArgumentException );
//-------------------------------------------------------------------------
/** allows to explicitly re-enable some languages that got previously
disabled.
<p>By default all languages are enabled.</p>
*/
void enableLanguages(
[in] sequence< com::sun::star::lang::Locale > aLanguages )
raises( com::sun::star::lang::IllegalArgumentException );
//-------------------------------------------------------------------------
/** returns a list of all supported languages.
<p>This should be the same as the mathematical union of
all enabled and disabled languages.</p>
*/
sequence< com::sun::star::lang::Locale > getAvailableLanguages();
//-------------------------------------------------------------------------
/** returns the list of all enabled languages
*/
sequence< com::sun::star::lang::Locale > getEnabledLanguages();
//-------------------------------------------------------------------------
/** returns the list of all disabled languages
*/
sequence< com::sun::star::lang::Locale > getDisabledLanguages();
};
}; }; }; };
#endif