xref: /aoo41x/main/offapi/com/sun/star/i18n/XCharacterClassification.idl (revision cdf0e10c)

/*************************************************************************
 *
 * 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_XCharacterClassification_idl__
#define __com_sun_star_i18n_XCharacterClassification_idl__

#include <com/sun/star/i18n/ParseResult.idl>

#ifndef __com_sun_star_lang_Locale_idl__
#include <com/sun/star/lang/Locale.idl>
#endif
#ifndef __com_sun_star_uno_XInterface_idl__
#include <com/sun/star/uno/XInterface.idl>
#endif

//============================================================================

module com { module sun { module star { module i18n {

//============================================================================

/*

Possible tokens to be parsed with  parse...Token():

UPASCALPHA=[A-Z]
LOASCALPHA=[a-z]
ASCALPHA=1*(UPASCALPHA|LOASCALPHA)
ASCDIGIT=[0-9]
ASC_UNDERSCORE='_'
ASC_SPACE=' '
ASC_HT='\0x9'
ASC_VT='\0xb'
ASC_WS=ASC_SPACE|ASC_HT|ASC_VT
ASC_DBL_QUOTE=\";
ASC_QUOTE=\'
UPASC_IDENTIFIER=UPASCALPHA *(UPASCALPHA|ASCDIGIT|ASC_UNDERSCORE)

ALPHA,DIGIT are the tokens which return true for isAlpha and isDigit
ALNUM=ALPHA|DIGIT
CHAR=anycharacter
WS=isWhiteSpace()
SIGN='+'|'-'
DECSEP=<locale dependent decimal separator>
GRPSEP=<locale dependent thousand separator>
EXPONENT=(E|e)[SIGN]1*ASC_DIGIT

IDENTIFIER=ALPHA *ALNUM
UIDENTIFIER=(ALPHA | ASC_UNDERSCORE) *(ALNUM|ASC_UNDERSCORE)
ALPHA_NAME=ALPHA *(ALNUM|DEFCHARS)
ANY_NAME=1*(ALNUM|DEFCHARS)
SINGLE_QUOTE_NAME=ASC_QUOTE(1*CHAR)ASC_QUOTE
DOUBLE_QUOTE_NAME=ASC_DBL_QUOTE(*CHAR)ASC_DBL_QUOTE
ASC_NUMBER=[SIGN]*(1*ASC_DIGIT  *(GRPSEP 1*ASC_DIGIT))[DECSEP]1*ASC_DIGIT[EXPONENT]
NUMBER=[SIGN]*(1*DIGIT  *(GRPSEP 1*DIGIT))[DECSEP]1*DIGIT[EXPONENT]

*/

//============================================================================

/**
    Character classification (upper, lower, digit, letter, number, ...)
    and generic Unicode enabled parser.
 */

published interface XCharacterClassification : com::sun::star::uno::XInterface
{
    //------------------------------------------------------------------------
    /** Convert lower case alpha to upper case alpha, starting at
        position <em>nPos</em> for <em>nCount</em> code points.
     */
    string   toUpper( [in] string aText, [in] long nPos, [in] long nCount,
                      [in] com::sun::star::lang::Locale aLocale );

    //------------------------------------------------------------------------
    /** Convert upper case alpha to lower case alpha, starting at
        position <em>nPos</em> for <em>nCount</em> code points.
     */
    string   toLower( [in] string aText, [in] long nPos, [in] long nCount,
                      [in] com::sun::star::lang::Locale aLocale );

    //------------------------------------------------------------------------
    /** Convert to title case, starting at
        position <em>nPos</em> for <em>nCount</em> code points.
     */
    string   toTitle( [in] string aText, [in] long nPos, [in] long nCount,
                      [in] com::sun::star::lang::Locale aLocale );

    //------------------------------------------------------------------------
    /// Get <type>UnicodeType</type> of character at position <em>nPos</em>.
    short    getType( [in] string aText, [in] long nPos );

    //------------------------------------------------------------------------
    /** Get <type>DirectionProperty</type> of character at position
        <em>nPos</em>.
     */
    short    getCharacterDirection( [in] string aText, [in] long nPos );

    //------------------------------------------------------------------------
    /// Get <type>UnicodeScript</type> of character at position <em>nPos</em>.
    short    getScript( [in] string aText, [in] long nPos );

    //------------------------------------------------------------------------
    /// Get <type>KCharacterType</type> of character at position <em>nPos</em>.
    long getCharacterType( [in] string aText, [in] long nPos,
                           [in] com::sun::star::lang::Locale aLocale );

    //------------------------------------------------------------------------
    /** Get accumulated <type>KCharacterType</type>s of string starting
        at position <em>nPos</em> of length <em>nCount</em> code points.

        @returns
            A number with appropriate flags set to indicate what type of
            characters the string contains, each flag value being one of
            KCharacterType values.
    */
    long getStringType( [in] string aText, [in] long nPos, [in] long nCount,
                        [in] com::sun::star::lang::Locale aLocale );


    //------------------------------------------------------------------------
    /**
        Parse a string for a token starting at position <em>nPos</em>.

        <p> A name or identifier must match the
        <type>KParseTokens</type> criteria passed in
        <em>nStartCharFlags</em> and <em>nContCharFlags</em> and may
        additionally contain characters of
        <em>aUserDefinedCharactersStart</em> and/or
        <em>aUserDefinedCharactersCont</em>. </p>


        @returns
            A filled <type>ParseResult</type> structure. If no
            unambigous token could be parsed,
            <member>ParseResult::TokenType</member> will be set to
            <b>0</b> (zero), other fields will contain the values parsed
            so far.

            <p> If a token may represent either a numeric value or a
            name according to the passed Start/Cont-Flags/Chars, both
            <const>KParseType::ASC_NUM</const> (or
            <const>KParseType::UNI_NUM</const>) and
            <const>KParseType::IDENTNAME</const> are set in
            <member>ParseResult::TokenType</member>.

        @param  aText
            Text to be parsed.

        @param  nPos
            Position where parsing starts.

        @param  aLocale
            The locale, for example, for decimal and group separator or
            character type determination.

        @param  nStartCharFlags
            A set of <type>KParseTokens</type> constants determining the
            allowed characters a name or identifier may start with.

        @param  aUserDefinedCharactersStart
            A set of additionally allowed characters a name or
            identifier may start with.

        @param  nContCharFlags
            A set of <type>KParseTokens</type> constants determining the
            allowed characters a name or identifier may continue with.

        @param  aUserDefinedCharactersCont
            A set of additionally allowed characters a name or
            identifier may continue with.

        @example:C++
        <listing>
            using namespace ::com::sun::star::i18n;
            // First character of an identifier may be any alphabetic or underscore.
            sal_Int32 nStartFlags = KParseTokens::ANY_ALPHA | KParseTokens::ASC_UNDERSCORE;
            // Continuing characters may be any alphanumeric or underscore or dot.
            sal_Int32 nContFlags = KParseTokens::ANY_ALNUM | KParseTokens::ASC_UNDERSCORE | KParseTokens::ASC_DOT;
            // No further characters assumed to be contained in an identifier
            String aEmptyString;
            // Parse any token.
            ParseResult rRes = xCC->parseAnyToken( aText, nPos, aLocale,
                nStartFlags, aEmptyString, nContFlags, aEmptyString );
            // Get parsed token.
            if ( rRes.TokenType & (KParseType::ASC_NUMBER | KParseType::UNI_NUMBER) )
                fValue = rRes.Value;
            if ( rRes.TokenType & KParseType::IDENTNAME )
                aName = aText.Copy( nPos, rRes.EndPos - nPos );
            else if ( rRes.TokenType & KParseType::SINGLE_QUOTE_NAME )
                aName = rRes.DequotedNameOrString;
            else if ( rRes.TokenType & KParseType::DOUBLE_QUOTE_STRING )
                aString = rRes.DequotedNameOrString;
            else if ( rRes.TokenType & KParseType::BOOLEAN )
                aSymbol = aText.Copy( nPos, rRes.EndPos - nPos );
            else if ( rRes.TokenType & KParseType::ONE_SINGLE_CHAR )
                aSymbol = aText.Copy( nPos, rRes.EndPos - nPos );
        </listing>
     */

    ParseResult parseAnyToken(
                            [in] string aText,
                            [in] long nPos,
                            [in] com::sun::star::lang::Locale aLocale,
                            [in] long nStartCharFlags,
                            [in] string aUserDefinedCharactersStart,
                            [in] long nContCharFlags,
                            [in] string aUserDefinedCharactersCont
                            );

    //------------------------------------------------------------------------
    /**
        Parse a string for a token of type <em>nTokenType</em> starting
        at position <em>nPos</em>.

        <p> Other parameters are the same as in
        <member>parseAnyToken</member>. If the actual token does not
        match the passed <em>nTokenType</em> a
        <member>ParseResult::TokenType</member> set to <b>0</b> (zero)
        is returned. </p>

        @param  nTokenType
            One or more of the <type>KParseType</type> constants.

        @example:C++
        <listing>
            // Determine if a given name is a valid name (not quoted) and contains
            // only allowed characters.
            using namespace ::com::sun::star::i18n;
            // First character of an identifier may be any alphanumeric or underscore.
            sal_Int32 nStartFlags = KParseTokens::ANY_ALNUM | KParseTokens::ASC_UNDERSCORE;
            // No further characters assumed to be contained in an identifier start.
            String aEmptyString;
            // Continuing characters may be any alphanumeric or underscore.
            sal_Int32 nContFlags = nStartFlags;
            // Additionally, continuing characters may contain a blank.
            String aContChars( RTL_CONSTASCII_USTRINGPARAM(" ") );
            // Parse predefined (must be an IDENTNAME) token.
            ParseResult rRes = xCC->parsePredefinedToken( KParseType::IDENTNAME, rName, 0, aLocale,
                nStartFlags, aEmptyString, nContFlags, aContChars );
            // Test if it is an identifier name and if it only is one
            // and no more else is following it.
            bValid = (rRes.TokenType & KParseType::IDENTNAME) && rRes.EndPos == rName.Len();
        </listing>
     */

    ParseResult parsePredefinedToken(
                            [in] long nTokenType,
                            [in] string aText,
                            [in] long nPos,
                            [in] com::sun::star::lang::Locale aLocale,
                            [in] long nStartCharFlags,
                            [in] string aUserDefinedCharactersStart,
                            [in] long nContCharFlags,
                            [in] string aUserDefinedCharactersCont
                            );
};

//=============================================================================
}; }; }; };

#endif