intl/lwbrk/src/nsSemanticUnitScanner.cpp

   1 /* -*- Mode: C++; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
   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  *
  24  * Alternatively, the contents of this file may be used under the terms of
  25  * either of the GNU General Public License Version 2 or later (the "GPL"),
  26  * or the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
  27  * in which case the provisions of the GPL or the LGPL are applicable instead
  28  * of those above. If you wish to allow use of your version of this file only
  29  * under the terms of either the GPL or the LGPL, and not to allow others to
  30  * use your version of this file under the terms of the MPL, indicate your
  31  * decision by deleting the provisions above and replace them with the notice
  32  * and other provisions required by the GPL or the LGPL. If you do not delete
  33  * the provisions above, a recipient may use your version of this file under
  34  * the terms of any one of the MPL, the GPL or the LGPL.
  35  *
  36  * ***** END LICENSE BLOCK ***** */
  37
  38 #include "nsSemanticUnitScanner.h"
  39 #include "prmem.h"
  40
  41 NS_IMPL_ISUPPORTS1(nsSemanticUnitScanner, nsISemanticUnitScanner)
  42
  43 nsSemanticUnitScanner::nsSemanticUnitScanner() : nsSampleWordBreaker()
  44 {
  45   /* member initializers and constructor code */
  46 }
  47
  48 nsSemanticUnitScanner::~nsSemanticUnitScanner()
  49 {
  50   /* destructor code */
  51 }
  52
  53
  54 /* void start (in string characterSet); */
  55 NS_IMETHODIMP nsSemanticUnitScanner::Start(const char *characterSet)
  56 {
  57     // do nothing for now.
  58     return NS_OK;
  59 }
  60
  61 /* void next (in wstring text, in long length, in long pos, out boolean hasMoreUnits, out long begin, out long end); */
  62 NS_IMETHODIMP nsSemanticUnitScanner::Next(const PRUnichar *text, PRInt32 length, PRInt32 pos, PRBool isLastBuffer, PRInt32 *begin, PRInt32 *end, PRBool *_retval)
  63 {
  64     // xxx need to bullet proff and check input pointer
  65     //  make sure begin, end and _retval is not nsnull here
  66
  67     // if we reach the end, just return
  68     if (pos >= length) {
  69        *begin = pos;
  70        *end = pos;
  71        *_retval = PR_FALSE;
  72        return NS_OK;
  73     }
  74
  75     PRUint8 char_class = nsSampleWordBreaker::GetClass(text[pos]);
  76
  77     // if we are in chinese mode, return one han letter at a time
  78     // we should not do this if we are in Japanese or Korean mode
  79     if (kWbClassHanLetter == char_class) {
  80        *begin = pos;
  81        *end = pos+1;
  82        *_retval = PR_TRUE;
  83        return NS_OK;
  84     }
  85
  86     PRInt32 next;
  87     // find the next "word"
  88     next = NextWord(text, (PRUint32) length, (PRUint32) pos);
  89
  90     // if we don't have enough text to make decision, return
  91     if (next == NS_WORDBREAKER_NEED_MORE_TEXT) {
  92        *begin = pos;
  93        *end = isLastBuffer ? length : pos;
  94        *_retval = isLastBuffer;
  95        return NS_OK;
  96     }
  97
  98     // if what we got is space or punct, look at the next break
  99     if ((char_class == kWbClassSpace) || (char_class == kWbClassPunct)) {
 100         // if the next "word" is not letters,
 101         // call itself recursively with the new pos
 102         return Next(text, length, next, isLastBuffer, begin, end, _retval);
 103     }
 104
 105     // for the rest, return
 106     *begin = pos;
 107     *end = next;
 108     *_retval = PR_TRUE;
 109     return NS_OK;
 110 }
 111