File indexing completed on 2024-12-22 04:33:43

0001 /* -*- Mode: C; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
0002 /* ***** BEGIN LICENSE BLOCK *****
0003  * Version: MPL 1.1/GPL 2.0/LGPL 2.1
0004  *
0005  * The contents of this file are subject to the Mozilla Public License Version
0006  * 1.1 (the "License"); you may not use this file except in compliance with
0007  * the License. You may obtain a copy of the License at
0008  * http://www.mozilla.org/MPL/
0009  *
0010  * Software distributed under the License is distributed on an "AS IS" basis,
0011  * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
0012  * for the specific language governing rights and limitations under the
0013  * License.
0014  *
0015  * The Original Code is mozilla.org code.
0016  *
0017  * The Initial Developer of the Original Code is
0018  * Netscape Communications Corporation.
0019  * Portions created by the Initial Developer are Copyright (C) 1998
0020  * the Initial Developer. All Rights Reserved.
0021  *
0022  * Contributor(s):
0023  *
0024  * Alternatively, the contents of this file may be used under the terms of
0025  * either the GNU General Public License Version 2 or later (the "GPL"), or
0026  * the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
0027  * in which case the provisions of the GPL or the LGPL are applicable instead
0028  * of those above. If you wish to allow use of your version of this file only
0029  * under the terms of either the GPL or the LGPL, and not to allow others to
0030  * use your version of this file under the terms of the MPL, indicate your
0031  * decision by deleting the provisions above and replace them with the notice
0032  * and other provisions required by the GPL or the LGPL. If you do not delete
0033  * the provisions above, a recipient may use your version of this file under
0034  * the terms of any one of the MPL, the GPL or the LGPL.
0035  *
0036  * ***** END LICENSE BLOCK ***** */
0037 
0038 #pragma GCC visibility push(hidden)
0039 
0040 #include "nsUTF8Prober.h"
0041 
0042 void  nsUTF8Prober::Reset(void)
0043 {
0044   mCodingSM->Reset(); 
0045   mNumOfMBChar = 0;
0046   mState = eDetecting;
0047 }
0048 
0049 nsProbingState nsUTF8Prober::HandleData(const char* aBuf, PRUint32 aLen)
0050 {
0051   nsSMState codingState;
0052 
0053   for (PRUint32 i = 0; i < aLen; i++)
0054   {
0055     codingState = mCodingSM->NextState(aBuf[i]);
0056     if (codingState == eError)
0057     {
0058       mState = eNotMe;
0059       break;
0060     }
0061     if (codingState == eItsMe)
0062     {
0063       mState = eFoundIt;
0064       break;
0065     }
0066     if (codingState == eStart)
0067     {
0068       if (mCodingSM->GetCurrentCharLen() >= 2)
0069         mNumOfMBChar++;
0070     }
0071   }
0072 
0073   if (mState == eDetecting)
0074     if (GetConfidence() > SHORTCUT_THRESHOLD)
0075       mState = eFoundIt;
0076   return mState;
0077 }
0078 
0079 #define ONE_CHAR_PROB   (float)0.50
0080 
0081 float nsUTF8Prober::GetConfidence(void)
0082 {
0083   float unlike = (float)0.99;
0084 
0085   if (mNumOfMBChar < 6)
0086   {
0087     for (PRUint32 i = 0; i < mNumOfMBChar; i++)
0088       unlike *= ONE_CHAR_PROB;
0089     return (float)1.0 - unlike;
0090   }
0091   else
0092     return (float)0.99;
0093 }
0094 
0095 #pragma GCC visibility pop
0096