1
/* ***** BEGIN LICENSE BLOCK *****
2
* Version: MPL 1.1/GPL 2.0/LGPL 2.1
4
* The contents of this file are subject to the Mozilla Public License Version
5
* 1.1 (the "License"); you may not use this file except in compliance with
6
* the License. You may obtain a copy of the License at
7
* http://www.mozilla.org/MPL/
9
* Software distributed under the License is distributed on an "AS IS" basis,
10
* WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
11
* for the specific language governing rights and limitations under the
14
* The Original Code is mozilla.org code.
16
* The Initial Developer of the Original Code is
17
* Netscape Communications Corporation.
18
* Portions created by the Initial Developer are Copyright (C) 1998
19
* the Initial Developer. All Rights Reserved.
22
* Kohei TAKETA <k-tak@void.in> (Java port)
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.
36
* ***** END LICENSE BLOCK ***** */
38
package org.mozilla.universalchardet.prober;
40
import org.mozilla.universalchardet.prober.statemachine.CodingStateMachine;
41
import org.mozilla.universalchardet.prober.statemachine.SMModel;
42
import org.mozilla.universalchardet.prober.statemachine.UTF8SMModel;
43
import org.mozilla.universalchardet.Constants;
46
public class UTF8Prober extends CharsetProber
48
////////////////////////////////////////////////////////////////
50
////////////////////////////////////////////////////////////////
51
public static final float ONE_CHAR_PROB = 0.50f;
54
////////////////////////////////////////////////////////////////
56
////////////////////////////////////////////////////////////////
57
private CodingStateMachine codingSM;
58
private ProbingState state;
59
private int numOfMBChar;
61
private static final SMModel smModel = new UTF8SMModel();
64
////////////////////////////////////////////////////////////////
66
////////////////////////////////////////////////////////////////
71
this.codingSM = new CodingStateMachine(smModel);
76
public String getCharSetName()
78
return Constants.CHARSET_UTF_8;
81
public ProbingState handleData(final byte[] buf, int offset, int length)
85
int maxPos = offset + length;
86
for (int i=offset; i<maxPos; ++i) {
87
codingState = this.codingSM.nextState(buf[i]);
88
if (codingState == SMModel.ERROR) {
89
this.state = ProbingState.NOT_ME;
92
if (codingState == SMModel.ITSME) {
93
this.state = ProbingState.FOUND_IT;
96
if (codingState == SMModel.START) {
97
if (this.codingSM.getCurrentCharLen() >= 2) {
103
if (this.state == ProbingState.DETECTING) {
104
if (getConfidence() > SHORTCUT_THRESHOLD) {
105
this.state = ProbingState.FOUND_IT;
112
public ProbingState getState()
119
this.codingSM.reset();
120
this.numOfMBChar = 0;
121
this.state = ProbingState.DETECTING;
124
public float getConfidence()
126
float unlike = 0.99f;
128
if (this.numOfMBChar < 6) {
129
for (int i=0; i<this.numOfMBChar; ++i) {
130
unlike *= ONE_CHAR_PROB;
132
return (1.0f - unlike);
138
public void setOption()