mirror of
https://gitlab.freedesktop.org/uchardet/uchardet.git
synced 2025-12-08 01:36:41 +08:00
5257fc1abf
Now the UTF-8 prober would not only detect valid UTF-8, but would also
detect the most probable language. Using the data generated 2 commits
away, this works very well.
This is still basic and will require even more improvements. In
particular, now the nsUTF8Prober should return an array of ("UTF-8",
language) couple candidate. And nsMBCSGroupProber should itself forward
these candidates as well as other candidates from other multi-byte
detectors. This way, the public-facing API would get more probable
candidates, in case the algorithm is slightly wrong.
Also the UTF-8 confidence is currently stupidly high as soon as we
consider it to be right. We should likely weigh it with language
detection (in particular, if no language is detected, this should
severely weigh down UTF-8 detection; not to 0, but high enough to be a
fallback in case no other encoding+lang is valid and low enough to give
chances to other good candidate couples.
73 lines
2.7 KiB
C++
73 lines
2.7 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 nsEscCharSetProber_h__
|
|
#define nsEscCharSetProber_h__
|
|
|
|
#include <cstddef>
|
|
|
|
#include "nsCharSetProber.h"
|
|
#include "nsCodingStateMachine.h"
|
|
|
|
#define NUM_OF_ESC_CHARSETS 4
|
|
|
|
class nsEscCharSetProber: public nsCharSetProber {
|
|
public:
|
|
nsEscCharSetProber(PRUint32 aLanguageFilter);
|
|
virtual ~nsEscCharSetProber(void);
|
|
nsProbingState HandleData(const char* aBuf, PRUint32 aLen,
|
|
int** codePointBuffer,
|
|
int* codePointBufferIdx);
|
|
const char* GetCharSetName() {return mDetectedCharset;}
|
|
const char* GetLanguage() {return NULL;}
|
|
nsProbingState GetState(void) {return mState;}
|
|
void Reset(void);
|
|
float GetConfidence(void){return (float)0.99;}
|
|
void SetOpion() {}
|
|
|
|
protected:
|
|
void GetDistribution(PRUint32 aCharLen, const char* aStr);
|
|
|
|
nsCodingStateMachine* mCodingSM[NUM_OF_ESC_CHARSETS] ;
|
|
PRUint32 mActiveSM;
|
|
nsProbingState mState;
|
|
const char * mDetectedCharset;
|
|
};
|
|
|
|
#endif /* nsEscCharSetProber_h__ */
|
|
|