offapi/com/sun/star/i18n/KParseTokens.idl

   1 /* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
   2 /*************************************************************************
   3  *
   4  * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
   5  *
   6  * Copyright 2000, 2010 Oracle and/or its affiliates.
   7  *
   8  * OpenOffice.org - a multi-platform office productivity suite
   9  *
  10  * This file is part of OpenOffice.org.
  11  *
  12  * OpenOffice.org is free software: you can redistribute it and/or modify
  13  * it under the terms of the GNU Lesser General Public License version 3
  14  * only, as published by the Free Software Foundation.
  15  *
  16  * OpenOffice.org is distributed in the hope that it will be useful,
  17  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  18  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  19  * GNU Lesser General Public License version 3 for more details
  20  * (a copy is included in the LICENSE file that accompanied this code).
  21  *
  22  * You should have received a copy of the GNU Lesser General Public License
  23  * version 3 along with OpenOffice.org.  If not, see
  24  * <http://www.openoffice.org/license.html>
  25  * for a copy of the LGPLv3 License.
  26  *
  27  ************************************************************************/
  28 #ifndef __com_sun_star_i18n_KParseTokens_idl__
  29 #define __com_sun_star_i18n_KParseTokens_idl__
  30
  31 //============================================================================
  32
  33 module com {  module sun {  module star {  module i18n {
  34
  35 //============================================================================
  36
  37 /**
  38     These constants specify the characters a name or identifier token to
  39     be parsed can have.
  40
  41     <p> They are passed to
  42     <member>XCharacterClassification::parseAnyToken()</member> and
  43     <member>XCharacterClassification::parsePredefinedToken()</member>.
  44     They are also set in the <member>ParseResult::StartFlags</member>
  45     and <member>ParseResult::ContFlags</member>. </p>
  46  */
  47
  48 published constants KParseTokens
  49 {
  50     /// ASCII A-Z upper alpha
  51     const long ASC_UPALPHA          = 0x00000001;
  52
  53     /// ASCII a-z lower alpha
  54     const long ASC_LOALPHA          = 0x00000002;
  55
  56     /// ASCII 0-9 digit
  57     const long ASC_DIGIT            = 0x00000004;
  58
  59     /// ASCII '_' underscore
  60     const long ASC_UNDERSCORE       = 0x00000008;
  61
  62     /// ASCII '$' dollar
  63     const long ASC_DOLLAR           = 0x00000010;
  64
  65     /// ASCII '.' dot/point
  66     const long ASC_DOT              = 0x00000020;
  67
  68     /// ASCII ':' colon
  69     const long ASC_COLON            = 0x00000040;
  70
  71     /// Special value to allow control characters (0x00 &lt; char &lt; 0x20)
  72     const long ASC_CONTROL          = 0x00000200;
  73
  74     /** Special value to allow anything below 128 except control
  75         characters. <strong>Not</strong> set in
  76         <type>ParseResult</type>. */
  77     const long ASC_ANY_BUT_CONTROL  = 0x00000400;
  78
  79     /** Additional flag set in <member>ParseResult::StartFlags</member>
  80         or <member>ParseResult::ContFlags</member>. Set if none of the
  81         above ASC_... (except ASC_ANY_...) single values match an ASCII
  82         character parsed. */
  83     const long ASC_OTHER            = 0x00000800;
  84
  85     /// Unicode (above 127) upper case letter
  86     const long UNI_UPALPHA          = 0x00001000;
  87
  88     /// Unicode (above 127) lower case letter
  89     const long UNI_LOALPHA          = 0x00002000;
  90
  91     /// Unicode (above 127) decimal digit number
  92     const long UNI_DIGIT            = 0x00004000;
  93
  94     /// Unicode (above 127) title case letter
  95     const long UNI_TITLE_ALPHA      = 0x00008000;
  96
  97     /// Unicode (above 127) modifier letter
  98     const long UNI_MODIFIER_LETTER  = 0x00010000;
  99
 100     /// Unicode (above 127) other letter
 101     const long UNI_OTHER_LETTER     = 0x00020000;
 102
 103     /// Unicode (above 127) letter number
 104     const long UNI_LETTER_NUMBER    = 0x00040000;
 105
 106     /// Unicode (above 127) other number
 107     const long UNI_OTHER_NUMBER     = 0x00080000;
 108
 109     /** If this bit is set in <em>nContCharFlags</em> parameters and a
 110         string enclosed in double quotes is parsed and two consecutive
 111         double quotes are encountered, the string is ended. If this bit
 112         is not set, the two double quotes are parsed as one escaped
 113         double quote and string parsing continues. The bit is ignored in
 114         <em>nStartCharFlags</em> parameters.
 115
 116         <p> Example: <br/>
 117         "abc""def"  -->  bit not set  =>  abc"def <br/>
 118         "abc""def"  -->  bit set  =>  abc </p>
 119       */
 120     const long TWO_DOUBLE_QUOTES_BREAK_STRING   = 0x10000000;
 121
 122     /** Additional flag set in <member>ParseResult::StartFlags</member>
 123         or <member>ParseResult::ContFlags</member>. Set if none of the
 124         above UNI_... single values match a Unicode character parsed. */
 125     const long UNI_OTHER            = 0x20000000;
 126
 127     /** Only valid for <em>nStartCharFlags</em> parameter to
 128         <method>ChararacterClassification::parseAnyToken</method> and
 129         <method>ChararacterClassification::parsePredefinedToken</method>,
 130         ignored on <em>nContCharFlags</em> parameter.
 131         <strong>Not</strong> set in <type>ParseResult</type>. */
 132     const long IGNORE_LEADING_WS    = 0x40000000;
 133
 134
 135     // useful combinations
 136
 137     /// ASCII a-zA-Z lower or upper alpha
 138     const long ASC_ALPHA            = ASC_UPALPHA | ASC_LOALPHA;
 139
 140     /// ASCII a-zA-Z0-9 alphanumeric
 141     const long ASC_ALNUM            = ASC_ALPHA | ASC_DIGIT;
 142
 143     /// Unicode (above 127) lower or upper or title case alpha
 144     const long UNI_ALPHA            = UNI_UPALPHA | UNI_LOALPHA | UNI_TITLE_ALPHA;
 145
 146     /// Unicode (above 127) alphanumeric
 147     const long UNI_ALNUM            = UNI_ALPHA | UNI_DIGIT;
 148
 149     /// Unicode (above 127) alpha or letter
 150     const long UNI_LETTER           = UNI_ALPHA | UNI_MODIFIER_LETTER |
 151                                         UNI_OTHER_LETTER;
 152
 153     /// Unicode (above 127) number
 154     const long UNI_NUMBER           = UNI_DIGIT | UNI_LETTER_NUMBER |
 155                                         UNI_OTHER_NUMBER;
 156
 157     /// any (ASCII or Unicode) alpha
 158     const long ANY_ALPHA            = ASC_ALPHA | UNI_ALPHA;
 159
 160     /// any (ASCII or Unicode) digit
 161     const long ANY_DIGIT            = ASC_DIGIT | UNI_DIGIT;
 162
 163     /// any (ASCII or Unicode) alphanumeric
 164     const long ANY_ALNUM            = ASC_ALNUM | UNI_ALNUM;
 165
 166     /// any (ASCII or Unicode) letter
 167     const long ANY_LETTER           = ASC_ALPHA | UNI_LETTER;
 168
 169     /// any (ASCII or Unicode) number
 170     const long ANY_NUMBER           = ASC_DIGIT | UNI_NUMBER;
 171
 172     /// any (ASCII or Unicode) letter or number
 173     const long ANY_LETTER_OR_NUMBER = ANY_LETTER | ANY_NUMBER;
 174 };
 175
 176 //============================================================================
 177 }; }; }; };
 178
 179 #endif
 180
 181 /* vim:set shiftwidth=4 softtabstop=4 expandtab: */