intl/lwbrk/idl/nsISemanticUnitScanner.idl

   1 /* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
   2 /* ***** BEGIN LICENSE BLOCK *****
   3  * Version: MPL 1.1/GPL 2.0/LGPL 2.1
   4  *
   5  * The contents of this file are subject to the Mozilla Public License Version
   6  * 1.1 (the "License"); you may not use this file except in compliance with
   7  * the License. You may obtain a copy of the License at
   8  * http://www.mozilla.org/MPL/
   9  *
  10  * Software distributed under the License is distributed on an "AS IS" basis,
  11  * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
  12  * for the specific language governing rights and limitations under the
  13  * License.
  14  *
  15  * The Original Code is mozilla.org code.
  16  *
  17  * The Initial Developer of the Original Code is
  18  * Netscape Communications Corporation.
  19  * Portions created by the Initial Developer are Copyright (C) 1998
  20  * the Initial Developer. All Rights Reserved.
  21  *
  22  * Contributor(s):
  23  *   Frank Yung-Fong Tang <ftang@netscape.com>
  24  *
  25  * Alternatively, the contents of this file may be used under the terms of
  26  * either of the GNU General Public License Version 2 or later (the "GPL"),
  27  * or the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
  28  * in which case the provisions of the GPL or the LGPL are applicable instead
  29  * of those above. If you wish to allow use of your version of this file only
  30  * under the terms of either the GPL or the LGPL, and not to allow others to
  31  * use your version of this file under the terms of the MPL, indicate your
  32  * decision by deleting the provisions above and replace them with the notice
  33  * and other provisions required by the GPL or the LGPL. If you do not delete
  34  * the provisions above, a recipient may use your version of this file under
  35  * the terms of any one of the MPL, the GPL or the LGPL.
  36  *
  37  * ***** END LICENSE BLOCK ***** */
  38
  39 #include "nsISupports.idl"
  40
  41 %{C++
  42 // {ADF42751-1CEF-4ad2-AA8E-BCB849D8D31F}
  43 #define NS_SEMANTICUNITSCANNER_CID { 0xadf42751, 0x1cef, 0x4ad2, { 0xaa, 0x8e, 0xbc, 0xb8, 0x49, 0xd8, 0xd3, 0x1f}}
  44 #define NS_SEMANTICUNITSCANNER_CONTRACTID "@mozilla.org/intl/semanticunitscanner;1"
  45 %}
  46
  47 /**
  48  * Provides a language independent way to break UNICODE
  49  * text into meaningful semantic units (e.g. words).
  50  */
  51 [scriptable, uuid(9f620be4-e535-11d6-b254-00039310a47a)]
  52 interface nsISemanticUnitScanner : nsISupports {
  53     /**
  54      * start()
  55      *
  56      * Starts up the semantic unit scanner with an optional
  57      * character set, which acts as a hint to optimize the heuristics
  58      * used to determine the language(s) of the processed text.
  59      *
  60      * @param characterSet the character set the text was originally
  61      *                     encoded in (can be NULL)
  62      */
  63     void start(in string characterSet);
  64
  65     /**
  66      * next()
  67      * Get the begin / end offset of the next unit in the current text
  68      *
  69      * @param text the text to be scanned
  70      * @param length the number of characters in the text to be processed
  71      * @param pos the current position
  72      * @param isLastBuffer, the buffer is the last one
  73      * @param begin the begin offset of the next unit
  74      * @param begin the end offset of the next unit
  75      * @return has more unit in the current text
  76      */
  77     boolean next(in wstring text, in long length, in long pos,
  78               in boolean isLastBuffer,
  79               out long begin, out long end );
  80
  81 };