1
/* -*- Mode: C; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
2
/* ***** BEGIN LICENSE BLOCK *****
3
* Version: NPL 1.1/GPL 2.0/LGPL 2.1
5
* The contents of this file are subject to the Netscape Public License
6
* Version 1.1 (the "License"); you may not use this file except in
7
* compliance with the License. You may obtain a copy of the License at
8
* http://www.mozilla.org/NPL/
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
15
* The Original Code is mozilla.org code.
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.
25
* Alternatively, the contents of this file may be used under the terms of
26
* either the GNU General Public License Version 2 or later (the "GPL"), or
27
* 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 NPL, 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 NPL, the GPL or the LGPL.
37
* ***** END LICENSE BLOCK ***** */
39
// for S-JIS encoding, obeserve characteristic:
40
// 1, kana character (or hankaku?) often have hight frequency of appereance
41
// 2, kana character often exist in group
42
// 3, certain combination of kana is never used in japanese language
44
#include "nsSJISProber.h"
46
void nsSJISProber::Reset(void)
50
mContextAnalyser.Reset();
51
mDistributionAnalyser.Reset();
54
nsProbingState nsSJISProber::HandleData(const char* aBuf, PRUint32 aLen)
56
nsSMState codingState;
58
for (PRUint32 i = 0; i < aLen; i++)
60
codingState = mCodingSM->NextState(aBuf[i]);
61
if (codingState == eError)
66
if (codingState == eItsMe)
71
if (codingState == eStart)
73
PRUint32 charLen = mCodingSM->GetCurrentCharLen();
76
mLastChar[1] = aBuf[0];
77
mContextAnalyser.HandleOneChar(mLastChar+2-charLen, charLen);
78
mDistributionAnalyser.HandleOneChar(mLastChar, charLen);
82
mContextAnalyser.HandleOneChar(aBuf+i+1-charLen, charLen);
83
mDistributionAnalyser.HandleOneChar(aBuf+i-1, charLen);
88
mLastChar[0] = aBuf[aLen-1];
90
if (mState == eDetecting)
91
if (mContextAnalyser.GotEnoughData() && GetConfidence() > SHORTCUT_THRESHOLD)
97
float nsSJISProber::GetConfidence(void)
99
float contxtCf = mContextAnalyser.GetConfidence();
100
float distribCf = mDistributionAnalyser.GetConfidence();
102
return (contxtCf > distribCf ? contxtCf : distribCf);