1
/* -*- Mode: C++; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
2
/* ***** BEGIN LICENSE BLOCK *****
3
* Version: MPL 1.1/GPL 2.0/LGPL 2.1
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/
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 Communicator client 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.
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 ***** */
41
#define NUM_OF_CATEGORY 6
45
#define ENOUGH_REL_THRESHOLD 100
46
#define MAX_REL_THRESHOLD 1000
48
//hiragana frequency category table
49
extern const PRUint8 jp2CharContext[83][83];
51
class JapaneseContextAnalysis
54
JapaneseContextAnalysis() {Reset();}
56
void HandleData(const char* aBuf, PRUint32 aLen);
58
void HandleOneChar(const char* aStr, PRUint32 aCharLen)
62
//if we received enough data, stop here
63
if (mTotalRel > MAX_REL_THRESHOLD) mDone = PR_TRUE;
66
//Only 2-bytes characters are of our interest
67
order = (aCharLen == 2) ? GetOrder(aStr) : -1;
68
if (order != -1 && mLastCharOrder != -1)
71
//count this sequence to its category counter
72
mRelSample[(int)jp2CharContext[mLastCharOrder][order]]++; // added (int) to avoid warnings , jens 2009 02 26
74
mLastCharOrder = order;
77
float GetConfidence(PRBool aIsPreferredLanguage);
80
PRBool GotEnoughData() {return mTotalRel > ENOUGH_REL_THRESHOLD;}
83
virtual PRInt32 GetOrder(const char* str, PRUint32 *charLen) = 0;
84
virtual PRInt32 GetOrder(const char* str) = 0;
86
//category counters, each integer counts sequences in its category
87
PRUint32 mRelSample[NUM_OF_CATEGORY];
89
//total sequence received
92
//The order of previous char
93
PRInt32 mLastCharOrder;
95
//if last byte in current buffer is not the last byte of a character, we
96
//need to know how many byte to skip in next buffer.
97
PRUint32 mNeedToSkipCharNum;
99
//If this flag is set to PR_TRUE, detection is done and conclusion has been made
104
class SJISContextAnalysis : public JapaneseContextAnalysis
106
//SJISContextAnalysis(){};
108
PRInt32 GetOrder(const char* str, PRUint32 *charLen);
110
PRInt32 GetOrder(const char* str)
112
//We only interested in Hiragana, so first byte is '\202'
113
if (*str == '\202' &&
114
(unsigned char)*(str+1) >= (unsigned char)0x9f &&
115
(unsigned char)*(str+1) <= (unsigned char)0xf1)
116
return (unsigned char)*(str+1) - (unsigned char)0x9f;
121
class EUCJPContextAnalysis : public JapaneseContextAnalysis
124
PRInt32 GetOrder(const char* str, PRUint32 *charLen);
125
PRInt32 GetOrder(const char* str)
126
//We only interested in Hiragana, so first byte is '\244'
128
if (*str == '\244' &&
129
(unsigned char)*(str+1) >= (unsigned char)0xa1 &&
130
(unsigned char)*(str+1) <= (unsigned char)0xf3)
131
return (unsigned char)*(str+1) - (unsigned char)0xa1;
136
#endif /* __JPCNTX_H__ */