uchardet/src/nsEUCKRProber.h
Jehan 157de1dc65 src: the EUC-KR prober now returns "UHC" as encoding name.
"UHC" is the "Unified Hangul Code" (aka Windows-949 or CP949). It is
apparently "mostly" upward compatible with EUC-KR so returning UHC for
a strict EUC-KR document is usually not to be considered wrong.
Yet I can read that EUC-KR has its own way of representing hangul
syllables not available in precomposed form, and this is not supported
in UHC (since this latter has all possible precomposed syllables), hence
the "mostly" upward-compatibility.
My personal daily experience with Korean documents though is that I
encounter a lot of UHC-encoded files, probably because of predominance
of Microsoft operating systems, which spread this encoding.
So until we get 2 separate detection machines, let's just return EUC-KR
files as being "UHC".
2016-09-19 01:22:45 +02:00

81 lines
3.0 KiB
C++

/* -*- Mode: C; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
/* ***** BEGIN LICENSE BLOCK *****
* Version: MPL 1.1/GPL 2.0/LGPL 2.1
*
* The contents of this file are subject to the Mozilla Public License Version
* 1.1 (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
* http://www.mozilla.org/MPL/
*
* Software distributed under the License is distributed on an "AS IS" basis,
* WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
* for the specific language governing rights and limitations under the
* License.
*
* The Original Code is mozilla.org code.
*
* The Initial Developer of the Original Code is
* Netscape Communications Corporation.
* Portions created by the Initial Developer are Copyright (C) 1998
* the Initial Developer. All Rights Reserved.
*
* Contributor(s):
*
* Alternatively, the contents of this file may be used under the terms of
* either the GNU General Public License Version 2 or later (the "GPL"), or
* the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
* in which case the provisions of the GPL or the LGPL are applicable instead
* of those above. If you wish to allow use of your version of this file only
* under the terms of either the GPL or the LGPL, and not to allow others to
* use your version of this file under the terms of the MPL, indicate your
* decision by deleting the provisions above and replace them with the notice
* and other provisions required by the GPL or the LGPL. If you do not delete
* the provisions above, a recipient may use your version of this file under
* the terms of any one of the MPL, the GPL or the LGPL.
*
* ***** END LICENSE BLOCK ***** */
#ifndef nsEUCKRProber_h__
#define nsEUCKRProber_h__
#include "nsCharSetProber.h"
#include "nsCodingStateMachine.h"
#include "CharDistribution.h"
class nsEUCKRProber: public nsCharSetProber {
public:
nsEUCKRProber(PRBool aIsPreferredLanguage)
:mIsPreferredLanguage(aIsPreferredLanguage)
{mCodingSM = new nsCodingStateMachine(&EUCKRSMModel);
Reset();
}
virtual ~nsEUCKRProber(void){delete mCodingSM;}
nsProbingState HandleData(const char* aBuf, PRUint32 aLen);
/* "Unified Hangul Code", also called "CP949" or "Windows-949" is a
* superset of EUC-KR. Though not fully ok to return UHC here (a
* separate prober would be better), it is acceptable, since many
* Korean documents are actually created with this character set.
*/
const char* GetCharSetName() {return "UHC";}
nsProbingState GetState(void) {return mState;}
void Reset(void);
float GetConfidence(void);
void SetOpion() {}
protected:
void GetDistribution(PRUint32 aCharLen, const char* aStr);
nsCodingStateMachine* mCodingSM;
nsProbingState mState;
//EUCKRContextAnalysis mContextAnalyser;
EUCKRDistributionAnalysis mDistributionAnalyser;
char mLastChar[2];
PRBool mIsPreferredLanguage;
};
#endif /* nsEUCKRProber_h__ */