/* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */ /* ***** BEGIN LICENSE BLOCK ***** * Version: MPL 1.1/GPL 2.0/LGPL 2.1 * * The contents of this file are subject to the Mozilla Public License Version * 1.1 (the "License"); you may not use this file except in compliance with * the License. You may obtain a copy of the License at * http://www.mozilla.org/MPL/ * * Software distributed under the License is distributed on an "AS IS" basis, * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License * for the specific language governing rights and limitations under the * License. * * The Original Code is mozilla.org code. * * The Initial Developer of the Original Code is * Netscape Communications Corporation. * Portions created by the Initial Developer are Copyright (C) 1998 * the Initial Developer. All Rights Reserved. * * Contributor(s): * Frank Yung-Fong Tang * * Alternatively, the contents of this file may be used under the terms of * either of the GNU General Public License Version 2 or later (the "GPL"), * or the GNU Lesser General Public License Version 2.1 or later (the "LGPL"), * in which case the provisions of the GPL or the LGPL are applicable instead * of those above. If you wish to allow use of your version of this file only * under the terms of either the GPL or the LGPL, and not to allow others to * use your version of this file under the terms of the MPL, indicate your * decision by deleting the provisions above and replace them with the notice * and other provisions required by the GPL or the LGPL. If you do not delete * the provisions above, a recipient may use your version of this file under * the terms of any one of the MPL, the GPL or the LGPL. * * ***** END LICENSE BLOCK ***** */ #include "nsISupports.idl" %{C++ // {ADF42751-1CEF-4ad2-AA8E-BCB849D8D31F} #define NS_SEMANTICUNITSCANNER_CID { 0xadf42751, 0x1cef, 0x4ad2, { 0xaa, 0x8e, 0xbc, 0xb8, 0x49, 0xd8, 0xd3, 0x1f}} #define NS_SEMANTICUNITSCANNER_CONTRACTID "@mozilla.org/intl/semanticunitscanner;1" %} /** * Provides a language independent way to break UNICODE * text into meaningful semantic units (e.g. words). */ [scriptable, uuid(9f620be4-e535-11d6-b254-00039310a47a)] interface nsISemanticUnitScanner : nsISupports { /** * start() * * Starts up the semantic unit scanner with an optional * character set, which acts as a hint to optimize the heuristics * used to determine the language(s) of the processed text. * * @param characterSet the character set the text was originally * encoded in (can be NULL) */ void start(in string characterSet); /** * next() * Get the begin / end offset of the next unit in the current text * * @param text the text to be scanned * @param length the number of characters in the text to be processed * @param pos the current position * @param isLastBuffer, the buffer is the last one * @param begin the begin offset of the next unit * @param begin the end offset of the next unit * @return has more unit in the current text */ boolean next(in wstring text, in long length, in long pos, in boolean isLastBuffer, out long begin, out long end ); };