extensions/universalchardet/src/base/JpCntx.h

   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 Communicator client 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 the GNU General Public License Version 2 or later (the "GPL"), or
  26  * 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 #ifndef __JPCNTX_H__
  39 #define __JPCNTX_H__
  40
  41 #define NUM_OF_CATEGORY 6
  42
  43 #include "nscore.h"
  44
  45 #define ENOUGH_REL_THRESHOLD  100
  46 #define MAX_REL_THRESHOLD     1000
  47
  48 //hiragana frequency category table
  49 extern char jp2CharContext[83][83];
  50
  51 class JapaneseContextAnalysis
  52 {
  53 public:
  54   JapaneseContextAnalysis() {Reset();}
  55
  56   void HandleData(const char* aBuf, PRUint32 aLen);
  57
  58   void HandleOneChar(const char* aStr, PRUint32 aCharLen)
  59   {
  60     PRInt32 order;
  61
  62     //if we received enough data, stop here
  63     if (mTotalRel > MAX_REL_THRESHOLD)   mDone = PR_TRUE;
  64     if (mDone)       return;
  65
  66     //Only 2-bytes characters are of our interest
  67     order = (aCharLen == 2) ? GetOrder(aStr) : -1;
  68     if (order != -1 && mLastCharOrder != -1)
  69     {
  70       mTotalRel++;
  71       //count this sequence to its category counter
  72       mRelSample[jp2CharContext[mLastCharOrder][order]]++;
  73     }
  74     mLastCharOrder = order;
  75   }
  76
  77   float GetConfidence(PRBool aIsPreferredLanguage);
  78   void      Reset(void);
  79   void      SetOpion(){}
  80   PRBool GotEnoughData() {return mTotalRel > ENOUGH_REL_THRESHOLD;}
  81
  82 protected:
  83   virtual PRInt32 GetOrder(const char* str, PRUint32 *charLen) = 0;
  84   virtual PRInt32 GetOrder(const char* str) = 0;
  85
  86   //category counters, each integer counts sequences in its category
  87   PRUint32 mRelSample[NUM_OF_CATEGORY];
  88
  89   //total sequence received
  90   PRUint32 mTotalRel;
  91
  92   //The order of previous char
  93   PRInt32  mLastCharOrder;
  94
  95   //if last byte in current buffer is not the last byte of a character, we
  96   //need to know how many byte to skip in next buffer.
  97   PRUint32 mNeedToSkipCharNum;
  98
  99   //If this flag is set to PR_TRUE, detection is done and conclusion has been made
 100   PRBool   mDone;
 101 };
 102
 103
 104 class SJISContextAnalysis : public JapaneseContextAnalysis
 105 {
 106   //SJISContextAnalysis(){};
 107 protected:
 108   PRInt32 GetOrder(const char* str, PRUint32 *charLen);
 109
 110   PRInt32 GetOrder(const char* str)
 111   {
 112     //We only interested in Hiragana, so first byte is '\202'
 113     if (*str == '\202' &&
 114           (unsigned char)*(str+1) >= (unsigned char)0x9f &&
 115           (unsigned char)*(str+1) <= (unsigned char)0xf1)
 116       return (unsigned char)*(str+1) - (unsigned char)0x9f;
 117     return -1;
 118   }
 119 };
 120
 121 class EUCJPContextAnalysis : public JapaneseContextAnalysis
 122 {
 123 protected:
 124   PRInt32 GetOrder(const char* str, PRUint32 *charLen);
 125   PRInt32 GetOrder(const char* str)
 126     //We only interested in Hiragana, so first byte is '\244'
 127   {
 128     if (*str == '\244' &&
 129           (unsigned char)*(str+1) >= (unsigned char)0xa1 &&
 130           (unsigned char)*(str+1) <= (unsigned char)0xf3)
 131       return (unsigned char)*(str+1) - (unsigned char)0xa1;
 132     return -1;
 133   }
 134 };
 135
 136 #endif /* __JPCNTX_H__ */
 137