line |
stmt |
bran |
cond |
sub |
pod |
time |
code |
1
|
|
|
|
|
|
|
/* -*- Mode: C; tab-width: 4; 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.org 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
|
|
|
|
|
|
|
#include "nsUTF8Prober.h" |
39
|
|
|
|
|
|
|
|
40
|
8
|
|
|
|
|
|
void nsUTF8Prober::Reset(void) |
41
|
|
|
|
|
|
|
{ |
42
|
8
|
|
|
|
|
|
mCodingSM->Reset(); |
43
|
8
|
|
|
|
|
|
mNumOfMBChar = 0; |
44
|
8
|
|
|
|
|
|
mState = eDetecting; |
45
|
8
|
|
|
|
|
|
} |
46
|
|
|
|
|
|
|
|
47
|
8
|
|
|
|
|
|
nsProbingState nsUTF8Prober::HandleData(const char* aBuf, PRUint32 aLen) |
48
|
|
|
|
|
|
|
{ |
49
|
|
|
|
|
|
|
nsSMState codingState; |
50
|
|
|
|
|
|
|
|
51
|
12
|
100
|
|
|
|
|
for (PRUint32 i = 0; i < aLen; i++) |
52
|
|
|
|
|
|
|
{ |
53
|
10
|
|
|
|
|
|
codingState = mCodingSM->NextState(aBuf[i]); |
54
|
10
|
100
|
|
|
|
|
if (codingState == eError) |
55
|
|
|
|
|
|
|
{ |
56
|
2
|
|
|
|
|
|
mState = eNotMe; |
57
|
2
|
|
|
|
|
|
break; |
58
|
|
|
|
|
|
|
} |
59
|
8
|
50
|
|
|
|
|
if (codingState == eItsMe) |
60
|
|
|
|
|
|
|
{ |
61
|
0
|
|
|
|
|
|
mState = eFoundIt; |
62
|
0
|
|
|
|
|
|
break; |
63
|
|
|
|
|
|
|
} |
64
|
8
|
100
|
|
|
|
|
if (codingState == eStart) |
65
|
|
|
|
|
|
|
{ |
66
|
6
|
100
|
|
|
|
|
if (mCodingSM->GetCurrentCharLen() >= 2) |
67
|
2
|
|
|
|
|
|
mNumOfMBChar++; |
68
|
|
|
|
|
|
|
} |
69
|
|
|
|
|
|
|
} |
70
|
|
|
|
|
|
|
|
71
|
4
|
100
|
|
|
|
|
if (mState == eDetecting) |
72
|
2
|
50
|
|
|
|
|
if (GetConfidence() > SHORTCUT_THRESHOLD) |
73
|
0
|
|
|
|
|
|
mState = eFoundIt; |
74
|
4
|
|
|
|
|
|
return mState; |
75
|
|
|
|
|
|
|
} |
76
|
|
|
|
|
|
|
|
77
|
|
|
|
|
|
|
#define ONE_CHAR_PROB (float)0.50 |
78
|
|
|
|
|
|
|
|
79
|
4
|
|
|
|
|
|
float nsUTF8Prober::GetConfidence(void) |
80
|
|
|
|
|
|
|
{ |
81
|
|
|
|
|
|
|
float unlike = (float)0.99; |
82
|
|
|
|
|
|
|
|
83
|
4
|
50
|
|
|
|
|
if (mNumOfMBChar < 6) |
84
|
|
|
|
|
|
|
{ |
85
|
8
|
100
|
|
|
|
|
for (PRUint32 i = 0; i < mNumOfMBChar; i++) |
86
|
4
|
|
|
|
|
|
unlike *= ONE_CHAR_PROB; |
87
|
4
|
|
|
|
|
|
return (float)1.0 - unlike; |
88
|
|
|
|
|
|
|
} |
89
|
|
|
|
|
|
|
else |
90
|
|
|
|
|
|
|
return (float)0.99; |
91
|
|
|
|
|
|
|
} |
92
|
|
|
|
|
|
|
|