add new descriptions
This commit is contained in:
jp
parent
f01c2ebc13
commit
a40cbfd518
1 changed files with 219 additions and 103 deletions
|
|
@ -2,9 +2,9 @@
|
|||
*
|
||||
* $RCSfile: XBreakIterator.idl,v $
|
||||
*
|
||||
* $Revision: 1.1 $
|
||||
* $Revision: 1.2 $
|
||||
*
|
||||
* last change: $Author: bustamam $ $Date: 2000-11-19 00:34:22 $
|
||||
* last change: $Author: jp $ $Date: 2001-02-06 09:35:43 $
|
||||
*
|
||||
* The Contents of this file are made available subject to the terms of
|
||||
* either of the following licenses
|
||||
|
|
@ -79,213 +79,326 @@
|
|||
|
||||
//=============================================================================
|
||||
|
||||
// DocMerge: empty anyway
|
||||
//--------------------------------------------------------------------------
|
||||
/** specify the type of character iteration
|
||||
*/
|
||||
constants CharacterIteratorMode
|
||||
{
|
||||
// Iteration mode can be either character or cell based
|
||||
|
||||
// DocMerge: empty anyway
|
||||
/// skip characters
|
||||
const short SKIPCHARACTER = 0;
|
||||
|
||||
// DocMerge: empty anyway
|
||||
/// skip cells
|
||||
const short SKIPCELL = 1;
|
||||
|
||||
// DocMerge: empty anyway
|
||||
/// skip control characters
|
||||
const short SKIPCONTROLCHARACTER = 2;
|
||||
};
|
||||
|
||||
// DocMerge: empty anyway
|
||||
//--------------------------------------------------------------------------
|
||||
/** specify the type of LineBreak
|
||||
*/
|
||||
constants BreakType
|
||||
{
|
||||
// DocMerge: empty anyway
|
||||
/// linebreak is a word break
|
||||
const short WORDBOUNDARY = 1;
|
||||
|
||||
// DocMerge: empty anyway
|
||||
/// linebreak is a result of hyphenation
|
||||
const short HYPHENATION = 2;
|
||||
|
||||
// DocMerge: empty anyway
|
||||
/// linebreak - hanging punctuation recognized
|
||||
const short HANGINGPUNCTUATION = 3;
|
||||
};
|
||||
|
||||
// DocMerge: empty anyway
|
||||
//--------------------------------------------------------------------------
|
||||
/** specify the type scipts
|
||||
*/
|
||||
constants ScriptType
|
||||
{
|
||||
// DocMerge: empty anyway
|
||||
/// latin characters (english, .. )
|
||||
const short LATIN = 1;
|
||||
|
||||
// DocMerge: empty anyway
|
||||
/// asian characters (japanese, .. )
|
||||
const short ASIAN = 2;
|
||||
|
||||
// DocMerge: empty anyway
|
||||
/// complex characters (arabic, ..)
|
||||
const short COMPLEX = 3;
|
||||
|
||||
// DocMerge: empty anyway
|
||||
/// undefined characters (punctuation, .. )
|
||||
const short WEAK = 4;
|
||||
};
|
||||
|
||||
// DocMerge: empty anyway
|
||||
//--------------------------------------------------------------------------
|
||||
/** specify the type of words
|
||||
*/
|
||||
constants WordType
|
||||
{
|
||||
// DocMerge: empty anyway
|
||||
/** any "words" - words in the meaning of same character types,
|
||||
collection auf alphanumeric characters or collection of non
|
||||
alphanumeric characters.
|
||||
*/
|
||||
const short ANY_WORD = 0;
|
||||
|
||||
// DocMerge: empty anyway
|
||||
/** any "words" - words in the meaning of same character types,
|
||||
collection auf alphanumeric characters or collection of non
|
||||
alphanumeric characters except blanks.
|
||||
*/
|
||||
const short ANYWORD_IGNOREWHITESPACES= 1;
|
||||
|
||||
// DocMerge: empty anyway
|
||||
/** "words" - in the meaning of a collection auf alphanumeric characters.
|
||||
*/
|
||||
const short DICTIONARY_WORD = 2;
|
||||
};
|
||||
|
||||
// DocMerge: empty anyway
|
||||
//--------------------------------------------------------------------------
|
||||
/** specify the type character, that starts a charblock
|
||||
*/
|
||||
constants CharType
|
||||
{
|
||||
// DocMerge: empty anyway
|
||||
/// all alpha characters allowed
|
||||
const short ANY_CHAR = 0;
|
||||
|
||||
// DocMerge: empty anyway
|
||||
/// only lower alpha characters allowed
|
||||
const short LOWER_CASE_CHAR = 1;
|
||||
};
|
||||
|
||||
// DocMerge: empty anyway
|
||||
//--------------------------------------------------------------------------
|
||||
/** specify the options for the LineBreak
|
||||
*/
|
||||
struct LineBreakUserOptions
|
||||
{
|
||||
// DocMerge: empty anyway
|
||||
/// these characters are not allowed at the begining of a line
|
||||
string forbiddenBeginCharacters;
|
||||
|
||||
// DocMerge: empty anyway
|
||||
/// these characters are not allowed at the end of a line
|
||||
string forbiddenEndCharacters;
|
||||
|
||||
// DocMerge: empty anyway
|
||||
/// act on the forbidden characters or not
|
||||
boolean applyForbiddenRules;
|
||||
|
||||
// DocMerge: empty anyway
|
||||
/// punctuation characters are allowed at the end of the line
|
||||
boolean allowPunctuationOutsideMargin;
|
||||
|
||||
// DocMerge: empty anyway
|
||||
/// allow Hyphenate English
|
||||
boolean allowHyphenateEnglish;
|
||||
|
||||
};
|
||||
|
||||
// DocMerge: empty anyway
|
||||
//--------------------------------------------------------------------------
|
||||
/** specify the hyphenation options for LineBreak
|
||||
*/
|
||||
struct LineBreakHyphenationOptions
|
||||
{
|
||||
// DocMerge: empty anyway
|
||||
/// reference to the specific hyphenator - can be zero.
|
||||
::com::sun::star::linguistic2::XHyphenator rHyphenator;
|
||||
|
||||
// DocMerge: empty anyway
|
||||
/// start position the hyphenation (?)
|
||||
long hyphenIndex;
|
||||
};
|
||||
|
||||
// DocMerge: empty anyway
|
||||
//--------------------------------------------------------------------------
|
||||
/** specify the result of a LineBreak
|
||||
*/
|
||||
struct LineBreakResults
|
||||
{
|
||||
// DocMerge: empty anyway
|
||||
/// type of line break, see <type>BreakType</type>
|
||||
short breakType;
|
||||
|
||||
// DocMerge: empty anyway
|
||||
/// position of the calculated line break
|
||||
long breakIndex;
|
||||
|
||||
// DocMerge: empty anyway
|
||||
/// return value of the hyphenator
|
||||
::com::sun::star::linguistic2::XHyphenatedWord rHyphenatedWord;
|
||||
};
|
||||
|
||||
// DocMerge: empty anyway
|
||||
//--------------------------------------------------------------------------
|
||||
/** specify the start-/end-position of a word
|
||||
*/
|
||||
struct Boundary
|
||||
{
|
||||
// DocMerge: empty anyway
|
||||
long startPos ; // Inclusive
|
||||
/// start position of a word (dont forget - inclusive)
|
||||
long startPos ;
|
||||
|
||||
// DocMerge: empty anyway
|
||||
long endPos ; // exclusive
|
||||
/// end position of a word (dont forget - exclusive)
|
||||
long endPos;
|
||||
};
|
||||
|
||||
|
||||
// DocMerge: empty anyway
|
||||
//--------------------------------------------------------------------------
|
||||
/** contains the base routines for iterate in Unicode string. Iterates over
|
||||
Characters, Words, Sentences and Linebreaks.
|
||||
<P>It exist also specific breakiterator for asian languages
|
||||
<P>
|
||||
<P>Assumption - StartPos is inclusive and EndPos is exclusive.
|
||||
*/
|
||||
[ uik(779C6834-2510-40b7-8480B56E-D912E71C), ident( "XBreakIterator", 1.0 ) ]
|
||||
interface XBreakIterator: com::sun::star::uno::XInterface
|
||||
{
|
||||
|
||||
|
||||
// Assumption - StartPos is inclusive and EndPos is exclusive.
|
||||
|
||||
// Traverses nCount characters in Text from nStartPos. Iteration mode can be cell based or
|
||||
// character based.A cell is made of more than one character.
|
||||
|
||||
// DocMerge: empty anyway
|
||||
[const] long nextCharacters( [in] string Text, [in] long nStartPos, [in] ::com::sun::star::lang::Locale rLocale,
|
||||
[in] short nCharacterIteratorMode, [in] long nCount, [out] long nDone );
|
||||
|
||||
// DocMerge: empty anyway
|
||||
[const] long previousCharacters( [in] string Text, [in] long nStartPos, [in] ::com::sun::star::lang::Locale nLocale,
|
||||
[in] short nCharacterIteratorMode, [in] long nCount, [out] long nDone );
|
||||
|
||||
/*
|
||||
traverses nCount words forward and returns word boundary both start and end position of the word. To process
|
||||
control +right Use pos = nextWords (text, pos, locale, ANYWORD_IGNOREWHITESPACES, 1, &nDone);pos.startPos should have
|
||||
cursor position.
|
||||
//--------------------------------------------------------------------------
|
||||
/** Traverses specfied number of characters in Text from the
|
||||
StartPos to the right. <type>CharacterIteratorMode</type> can be cell
|
||||
based or character based. A cell is made of more than one character.
|
||||
*/
|
||||
// DocMerge: empty anyway
|
||||
[const] Boundary nextWord( [in] string Text, [in] long nStartPos, [in] ::com::sun::star::lang::Locale nLocale, [in] short WordType);
|
||||
[const] long nextCharacters( [in] string Text, [in] long nStartPos,
|
||||
[in] ::com::sun::star::lang::Locale rLocale,
|
||||
[in] short nCharacterIteratorMode,
|
||||
[in] long nCount, [out] long nDone );
|
||||
|
||||
// DocMerge: empty anyway
|
||||
[const] Boundary previousWord( [in] string Text, [in] long nStartPos, [in] ::com::sun::star::lang::Locale nLocale, [in] short WordType);
|
||||
|
||||
/* identifies StartPos and EndPos of current word. If nPos 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 sitution, bPreferForward flag is used,if bPreferForward == 0, nPos is considered end of word and looks for beginning of word on left
|
||||
otherwise nPos is considered beginning of next word and looks right for end of the word.
|
||||
//--------------------------------------------------------------------------
|
||||
/** Traverses specfied number of characters in Text from the
|
||||
StartPos to the left. <type>CharacterIteratorMode</type> can be cell
|
||||
based or character based. A cell is made of more than one character.
|
||||
*/
|
||||
// DocMerge: empty anyway
|
||||
[const] Boundary getWordBoundary( [in] string Text, [in] long nPos, [in] ::com::sun::star::lang::Locale nLocale, [in] short WordType, [in] boolean bPreferForward);
|
||||
[const] long previousCharacters( [in] string Text, [in] long nStartPos,
|
||||
[in] ::com::sun::star::lang::Locale nLocale,
|
||||
[in] short nCharacterIteratorMode,
|
||||
[in] long nCount, [out] long nDone );
|
||||
|
||||
// DocMerge: empty anyway
|
||||
[const] short getWordType ([in] string Text, [in] long nPos, [in] ::com::sun::star::lang::Locale nLocale);
|
||||
//--------------------------------------------------------------------------
|
||||
/** Traverses one word in Text from the StartPos to the right.
|
||||
The <type>WordType</type> specify the type of travelling.
|
||||
@returns the <type>Boundary</type> of the found word.
|
||||
Normaly used for the CTRL-Right.
|
||||
*/
|
||||
[const] Boundary nextWord( [in] string Text, [in] long nStartPos,
|
||||
[in] ::com::sun::star::lang::Locale nLocale,
|
||||
[in] short WordType);
|
||||
|
||||
// DocMerge: empty anyway
|
||||
[const] boolean isBeginWord ([in] string Text, [in] long nPos, [in] ::com::sun::star::lang::Locale nLocale, [in] short WordType);
|
||||
//--------------------------------------------------------------------------
|
||||
/** Traverses one word in Text from the StartPos to the left.
|
||||
The <type>WordType</type> specify the type of travelling.
|
||||
@returns the <type>Boundary</type> of the found word.
|
||||
Normaly used for the CTRL-Right.
|
||||
*/
|
||||
[const] Boundary previousWord( [in] string Text, [in] long nStartPos,
|
||||
[in] ::com::sun::star::lang::Locale nLocale,
|
||||
[in] short WordType);
|
||||
|
||||
// DocMerge: empty anyway
|
||||
[const] boolean isEndWord ([in] string Text, [in] long nPos, [in] ::com::sun::star::lang::Locale nLocale, [in] short WordType);
|
||||
//--------------------------------------------------------------------------
|
||||
/** identifies StartPos and EndPos of current word. If nPos 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 sitution, bPreferForward flag is used, if bPreferForward == 0,
|
||||
nPos is considered end of word and looks for beginning of word on left
|
||||
otherwise nPos is considered beginning of next word and looks right for
|
||||
end of the word.
|
||||
*/
|
||||
[const] Boundary getWordBoundary( [in] string Text, [in] long nPos,
|
||||
[in] ::com::sun::star::lang::Locale nLocale,
|
||||
[in] short WordType,
|
||||
[in] boolean bPreferForward );
|
||||
|
||||
// DocMerge: empty anyway
|
||||
[const] long beginOfSentence( [in] string Text, [in] long nStartPos, [in] ::com::sun::star::lang::Locale nLocale );
|
||||
//--------------------------------------------------------------------------
|
||||
/** @returns the kind of word that starts at the specified position.
|
||||
*/
|
||||
[const] short getWordType( [in] string Text, [in] long nPos,
|
||||
[in] ::com::sun::star::lang::Locale nLocale);
|
||||
|
||||
// DocMerge: empty anyway
|
||||
[const] long endOfSentence( [in] string Text, [in] long nStartPos, [in] ::com::sun::star::lang::Locale nLocale );
|
||||
//--------------------------------------------------------------------------
|
||||
/** @returns true if at the specified position starts a word
|
||||
*/
|
||||
[const] boolean isBeginWord( [in] string Text, [in] long nPos,
|
||||
[in] ::com::sun::star::lang::Locale nLocale,
|
||||
[in] short WordType);
|
||||
|
||||
//--------------------------------------------------------------------------
|
||||
/** @returns true if at the specified position ends a word
|
||||
*/
|
||||
[const] boolean isEndWord( [in] string Text, [in] long nPos,
|
||||
[in] ::com::sun::star::lang::Locale nLocale,
|
||||
[in] short WordType);
|
||||
|
||||
//--------------------------------------------------------------------------
|
||||
/** Traverses in Text from the StartPos to the start of a sentence.
|
||||
@returns the position where the sentence starts
|
||||
*/
|
||||
[const] long beginOfSentence( [in] string Text, [in] long nStartPos,
|
||||
[in] ::com::sun::star::lang::Locale nLocale );
|
||||
|
||||
//--------------------------------------------------------------------------
|
||||
/** Traverses in Text from the StartPos to the end of a sentence.
|
||||
@returns the position where the sentence ends
|
||||
*/
|
||||
[const] long endOfSentence( [in] string Text, [in] long nStartPos,
|
||||
[in] ::com::sun::star::lang::Locale nLocale );
|
||||
|
||||
|
||||
// DocMerge: empty anyway
|
||||
[const] LineBreakResults getLineBreak( [in] string Text, [in] long nStartPos, [in] ::com::sun::star::lang::Locale nLocale, [in] long nMinBreakPos,
|
||||
[in] LineBreakHyphenationOptions hOptions, [in]LineBreakUserOptions bOptions );
|
||||
//--------------------------------------------------------------------------
|
||||
/** calculate the linebreak position in the Text from the specified StartPos.
|
||||
<type>LineBreakHyphenationOptions</type> defines if the hyphenator is to use.
|
||||
The <type>LineBreakUserOptions</type> defines, how to handle hanging
|
||||
punctuations, the forbidden chraracter at the start/end of a line.
|
||||
|
||||
@returns <type>LineBreakResults</type>, which contains the break position
|
||||
of the word and which kind of break it is.
|
||||
*/
|
||||
[const] LineBreakResults getLineBreak( [in] string Text, [in] long nStartPos,
|
||||
[in] ::com::sun::star::lang::Locale nLocale,
|
||||
[in] long nMinBreakPos,
|
||||
[in] LineBreakHyphenationOptions hOptions,
|
||||
[in] LineBreakUserOptions bOptions );
|
||||
|
||||
|
||||
// DocMerge: empty anyway
|
||||
[const] long beginOfScript( [in] string Text, [in] long nStartPos, [in] short ScriptType );
|
||||
//--------------------------------------------------------------------------
|
||||
/** @returns the position where the specified skipt starts.
|
||||
*/
|
||||
[const] long beginOfScript( [in] string Text, [in] long nStartPos,
|
||||
[in] short ScriptType );
|
||||
|
||||
// DocMerge: empty anyway
|
||||
[const] long endOfScript( [in] string Text, [in] long nStartPos, [in] short ScriptType );
|
||||
//--------------------------------------------------------------------------
|
||||
/** @returns the position where the specified skipt ends.
|
||||
*/
|
||||
[const] long endOfScript( [in] string Text, [in] long nStartPos,
|
||||
[in] short ScriptType );
|
||||
|
||||
// DocMerge: empty anyway
|
||||
[const] long nextScript( [in] string Text, [in] long nStartPos, [in] short ScriptType );
|
||||
//--------------------------------------------------------------------------
|
||||
/** @returns the position where the next specified skipt starts.
|
||||
*/
|
||||
[const] long nextScript( [in] string Text, [in] long nStartPos,
|
||||
[in] short ScriptType );
|
||||
|
||||
// DocMerge: empty anyway
|
||||
[const] long previousScript ( [in] string Text, [in] long nStartPos, [in] short ScriptType );
|
||||
//--------------------------------------------------------------------------
|
||||
/** @returns the position where the previous specified skipt starts.
|
||||
*/
|
||||
[const] long previousScript ( [in] string Text, [in] long nStartPos,
|
||||
[in] short ScriptType );
|
||||
|
||||
// DocMerge: empty anyway
|
||||
//--------------------------------------------------------------------------
|
||||
/** @returns the scipts type of the current position.
|
||||
*/
|
||||
[const] short getScriptType ([in] string Text, [in] long nPos);
|
||||
|
||||
|
||||
// DocMerge: empty anyway
|
||||
[const] long beginOfCharBlock( [in] string Text, [in] long nStartPos,[in] ::com::sun::star::lang::Locale nLocale, [in] short CharType );
|
||||
//--------------------------------------------------------------------------
|
||||
/** Traverses in Text from the StartPos to the begin of the specified character type.
|
||||
@returns the position where the character type starts
|
||||
*/
|
||||
[const] long beginOfCharBlock( [in] string Text, [in] long nStartPos,
|
||||
[in] ::com::sun::star::lang::Locale nLocale,
|
||||
[in] short CharType );
|
||||
|
||||
// DocMerge: empty anyway
|
||||
[const] long endOfCharBlock( [in] string Text, [in] long nStartPos, [in] ::com::sun::star::lang::Locale nLocale, [in] short CharType );
|
||||
//--------------------------------------------------------------------------
|
||||
/** Traverses in Text from the StartPos to the end of the specified character type.
|
||||
@returns the position where the character type ends
|
||||
*/
|
||||
[const] long endOfCharBlock( [in] string Text, [in] long nStartPos,
|
||||
[in] ::com::sun::star::lang::Locale nLocale,
|
||||
[in] short CharType );
|
||||
|
||||
// DocMerge: empty anyway
|
||||
[const] long nextCharBlock( [in] string Text, [in] long nStartPos,[in] ::com::sun::star::lang::Locale nLocale, [in] short CharType );
|
||||
//--------------------------------------------------------------------------
|
||||
/** Traverses in Text from the StartPos to the next start of the specified character type.
|
||||
@returns the position where the next character type starts
|
||||
*/
|
||||
[const] long nextCharBlock( [in] string Text, [in] long nStartPos,
|
||||
[in] ::com::sun::star::lang::Locale nLocale,
|
||||
[in] short CharType );
|
||||
|
||||
// DocMerge: empty anyway
|
||||
[const] long previousCharBlock ( [in] string Text, [in] long nStartPos, [in] ::com::sun::star::lang::Locale nLocale, [in] short CharType );
|
||||
//--------------------------------------------------------------------------
|
||||
/** Traverses in Text from the StartPos to the previous start of the specified character type.
|
||||
@returns the position where the previous character type starts
|
||||
*/
|
||||
[const] long previousCharBlock ( [in] string Text, [in] long nStartPos,
|
||||
[in] ::com::sun::star::lang::Locale nLocale,
|
||||
[in] short CharType );
|
||||
};
|
||||
|
||||
|
||||
|
|
@ -296,6 +409,9 @@ interface XBreakIterator: com::sun::star::uno::XInterface
|
|||
/*=============================================================================
|
||||
|
||||
$Log: not supported by cvs2svn $
|
||||
Revision 1.1 2000/11/19 00:34:22 bustamam
|
||||
move Collation, breakiterator, transliteration to i18n
|
||||
|
||||
Revision 1.2 2000/10/25 13:26:03 tl
|
||||
linguistic => linguistic2
|
||||
|
||||
|
|
|
|||
Loading…
Reference in a new issue