intl/chardet/src/nsCyrillicDetector.cpp

   1 /* -*- Mode: C; tab-width: 4; 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  *   Pierre Phaneuf <pp@ludusdesign.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 #include "nscore.h"
  39 #include "nsCyrillicProb.h"
  40 #include <stdio.h>
  41
  42 #include "nsCOMPtr.h"
  43 #include "nsISupports.h"
  44 #include "nsICharsetDetector.h"
  45 #include "nsCharDetDll.h"
  46 #include "nsCyrillicDetector.h"
  47
  48 //----------------------------------------------------------------------
  49 // Interface nsISupports [implementation]
  50 NS_IMPL_ISUPPORTS1(nsCyrXPCOMDetector, nsICharsetDetector)
  51 NS_IMPL_ISUPPORTS1(nsCyrXPCOMStringDetector, nsIStringCharsetDetector)
  52
  53 void nsCyrillicDetector::HandleData(const char* aBuf, PRUint32 aLen)
  54 {
  55    PRUint8 cls;
  56    const char* b;
  57    PRUint32 i;
  58    if(mDone)
  59       return;
  60    for(i=0, b=aBuf;i<aLen;i++,b++)
  61    {
  62      for(PRUintn j=0;j<mItems;j++)
  63      {
  64         if( 0x80 & *b)
  65            cls = mCyrillicClass[j][(*b) & 0x7F];
  66         else
  67            cls = 0;
  68         NS_ASSERTION( cls <= 32 , "illegal character class");
  69         mProb[j] += gCyrillicProb[mLastCls[j]][cls];
  70         mLastCls[j] = cls;
  71      }
  72    }
  73    // We now only based on the first block we receive
  74    DataEnd();
  75 }
  76
  77 //---------------------------------------------------------------------
  78 #define THRESHOLD_RATIO 1.5f
  79 void nsCyrillicDetector::DataEnd()
  80 {
  81    PRUint32 max=0;
  82    PRUint8  maxIdx=0;
  83    PRUint8 j;
  84    if(mDone)
  85       return;
  86    for(j=0;j<mItems;j++) {
  87       if(mProb[j] > max)
  88       {
  89            max = mProb[j];
  90            maxIdx= j;
  91       }
  92    }
  93
  94    if( 0 == max ) // if we didn't get any 8 bits data
  95      return;
  96
  97 #ifdef DEBUG
  98    for(j=0;j<mItems;j++)
  99       printf("Charset %s->\t%d\n", mCharsets[j], mProb[j]);
 100 #endif
 101    this->Report(mCharsets[maxIdx]);
 102    mDone = PR_TRUE;
 103 }
 104
 105 //---------------------------------------------------------------------
 106 nsCyrXPCOMDetector:: nsCyrXPCOMDetector(PRUint8 aItems,
 107                       const PRUint8 ** aCyrillicClass,
 108                       const char **aCharsets)
 109              : nsCyrillicDetector(aItems, aCyrillicClass, aCharsets)
 110 {
 111     mObserver = nsnull;
 112 }
 113
 114 //---------------------------------------------------------------------
 115 nsCyrXPCOMDetector::~nsCyrXPCOMDetector()
 116 {
 117 }
 118
 119 //---------------------------------------------------------------------
 120 NS_IMETHODIMP nsCyrXPCOMDetector::Init(
 121   nsICharsetDetectionObserver* aObserver)
 122 {
 123   NS_ASSERTION(mObserver == nsnull , "Init twice");
 124   if(nsnull == aObserver)
 125      return NS_ERROR_ILLEGAL_VALUE;
 126
 127   mObserver = aObserver;
 128   return NS_OK;
 129 }
 130
 131 //----------------------------------------------------------
 132 NS_IMETHODIMP nsCyrXPCOMDetector::DoIt(
 133   const char* aBuf, PRUint32 aLen, PRBool* oDontFeedMe)
 134 {
 135   NS_ASSERTION(mObserver != nsnull , "have not init yet");
 136
 137   if((nsnull == aBuf) || (nsnull == oDontFeedMe))
 138      return NS_ERROR_ILLEGAL_VALUE;
 139
 140   this->HandleData(aBuf, aLen);
 141   *oDontFeedMe = PR_FALSE;
 142   return NS_OK;
 143 }
 144
 145 //----------------------------------------------------------
 146 NS_IMETHODIMP nsCyrXPCOMDetector::Done()
 147 {
 148   NS_ASSERTION(mObserver != nsnull , "have not init yet");
 149   this->DataEnd();
 150   return NS_OK;
 151 }
 152
 153 //----------------------------------------------------------
 154 void nsCyrXPCOMDetector::Report(const char* aCharset)
 155 {
 156   NS_ASSERTION(mObserver != nsnull , "have not init yet");
 157   mObserver->Notify(aCharset, eBestAnswer);
 158 }
 159
 160 //---------------------------------------------------------------------
 161 nsCyrXPCOMStringDetector:: nsCyrXPCOMStringDetector(PRUint8 aItems,
 162                       const PRUint8 ** aCyrillicClass,
 163                       const char **aCharsets)
 164              : nsCyrillicDetector(aItems, aCyrillicClass, aCharsets)
 165 {
 166 }
 167
 168 //---------------------------------------------------------------------
 169 nsCyrXPCOMStringDetector::~nsCyrXPCOMStringDetector()
 170 {
 171 }
 172
 173 //---------------------------------------------------------------------
 174 void nsCyrXPCOMStringDetector::Report(const char *aCharset)
 175 {
 176    mResult = aCharset;
 177 }
 178
 179 //---------------------------------------------------------------------
 180 NS_IMETHODIMP nsCyrXPCOMStringDetector::DoIt(const char* aBuf, PRUint32 aLen,
 181                      const char** oCharset, nsDetectionConfident &oConf)
 182 {
 183    mResult = nsnull;
 184    mDone = PR_FALSE;
 185    this->HandleData(aBuf, aLen);
 186    this->DataEnd();
 187    *oCharset=mResult;
 188    oConf = eBestAnswer;
 189    return NS_OK;
 190 }
 191
 192