xref: /aoo42x/main/offapi/com/sun/star/i18n/KParseTokens.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_KParseTokens_idl__
#define __com_sun_star_i18n_KParseTokens_idl__

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

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

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

/**
    These constants specify the characters a name or identifier token to
    be parsed can have.

    <p> They are passed to
    <member>XCharacterClassification::parseAnyToken()</member> and
    <member>XCharacterClassification::parsePredefinedToken()</member>.
    They are also set in the <member>ParseResult::StartFlags</member>
    and <member>ParseResult::ContFlags</member>. </p>
 */

published constants KParseTokens
{
    /// ASCII A-Z upper alpha
    const long ASC_UPALPHA          = 0x00000001;

    /// ASCII a-z lower alpha
    const long ASC_LOALPHA          = 0x00000002;

    /// ASCII 0-9 digit
    const long ASC_DIGIT            = 0x00000004;

    /// ASCII '_' underscore
    const long ASC_UNDERSCORE       = 0x00000008;

    /// ASCII '$' dollar
    const long ASC_DOLLAR           = 0x00000010;

    /// ASCII '.' dot/point
    const long ASC_DOT              = 0x00000020;

    /// ASCII ':' colon
    const long ASC_COLON            = 0x00000040;

    /// Special value to allow control characters (0x00 &lt; char &lt; 0x20)
    const long ASC_CONTROL          = 0x00000200;

    /** Special value to allow anything below 128 except control
        characters. <strong>Not</strong> set in
        <type>ParseResult</type>. */
    const long ASC_ANY_BUT_CONTROL  = 0x00000400;

    /** Additional flag set in <member>ParseResult::StartFlags</member>
        or <member>ParseResult::ContFlags</member>. Set if none of the
        above ASC_... (except ASC_ANY_...) single values match an ASCII
        character parsed. */
    const long ASC_OTHER            = 0x00000800;

    /// Unicode (above 127) upper case letter
    const long UNI_UPALPHA          = 0x00001000;

    /// Unicode (above 127) lower case letter
    const long UNI_LOALPHA          = 0x00002000;

    /// Unicode (above 127) decimal digit number
    const long UNI_DIGIT            = 0x00004000;

    /// Unicode (above 127) title case letter
    const long UNI_TITLE_ALPHA      = 0x00008000;

    /// Unicode (above 127) modifier letter
    const long UNI_MODIFIER_LETTER  = 0x00010000;

    /// Unicode (above 127) other letter
    const long UNI_OTHER_LETTER     = 0x00020000;

    /// Unicode (above 127) letter number
    const long UNI_LETTER_NUMBER    = 0x00040000;

    /// Unicode (above 127) other number
    const long UNI_OTHER_NUMBER     = 0x00080000;

    /** If this bit is set in <em>nContCharFlags</em> parameters and a
        string enclosed in double quotes is parsed and two consecutive
        double quotes are encountered, the string is ended. If this bit
        is not set, the two double quotes are parsed as one escaped
        double quote and string parsing continues. The bit is ignored in
        <em>nStartCharFlags</em> parameters.

        <p> Example: <br/>
        "abc""def"  -->  bit not set  =>  abc"def <br/>
        "abc""def"  -->  bit set  =>  abc </p>
      */
    const long TWO_DOUBLE_QUOTES_BREAK_STRING   = 0x10000000;

    /** Additional flag set in <member>ParseResult::StartFlags</member>
        or <member>ParseResult::ContFlags</member>. Set if none of the
        above UNI_... single values match a Unicode character parsed. */
    const long UNI_OTHER            = 0x20000000;

    /** Only valid for <em>nStartCharFlags</em> parameter to
        <method>ChararacterClassification::parseAnyToken</method> and
        <method>ChararacterClassification::parsePredefinedToken</method>,
        ignored on <em>nContCharFlags</em> parameter.
        <strong>Not</strong> set in <type>ParseResult</type>. */
    const long IGNORE_LEADING_WS    = 0x40000000;


    // useful combinations

    /// ASCII a-zA-Z lower or upper alpha
    const long ASC_ALPHA            = ASC_UPALPHA | ASC_LOALPHA;

    /// ASCII a-zA-Z0-9 alphanumeric
    const long ASC_ALNUM            = ASC_ALPHA | ASC_DIGIT;

    /// Unicode (above 127) lower or upper or title case alpha
    const long UNI_ALPHA            = UNI_UPALPHA | UNI_LOALPHA | UNI_TITLE_ALPHA;

    /// Unicode (above 127) alphanumeric
    const long UNI_ALNUM            = UNI_ALPHA | UNI_DIGIT;

    /// Unicode (above 127) alpha or letter
    const long UNI_LETTER           = UNI_ALPHA | UNI_MODIFIER_LETTER |
                                        UNI_OTHER_LETTER;

    /// Unicode (above 127) number
    const long UNI_NUMBER           = UNI_DIGIT | UNI_LETTER_NUMBER |
                                        UNI_OTHER_NUMBER;

    /// any (ASCII or Unicode) alpha
    const long ANY_ALPHA            = ASC_ALPHA | UNI_ALPHA;

    /// any (ASCII or Unicode) digit
    const long ANY_DIGIT            = ASC_DIGIT | UNI_DIGIT;

    /// any (ASCII or Unicode) alphanumeric
    const long ANY_ALNUM            = ASC_ALNUM | UNI_ALNUM;

    /// any (ASCII or Unicode) letter
    const long ANY_LETTER           = ASC_ALPHA | UNI_LETTER;

    /// any (ASCII or Unicode) number
    const long ANY_NUMBER           = ASC_DIGIT | UNI_NUMBER;

    /// any (ASCII or Unicode) letter or number
    const long ANY_LETTER_OR_NUMBER = ANY_LETTER | ANY_NUMBER;
};

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

#endif