1
/* -*- Mode: C++; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
2
/* ***** BEGIN LICENSE BLOCK *****
3
* Version: NPL 1.1/GPL 2.0/LGPL 2.1
5
* The contents of this file are subject to the Netscape Public License
6
* Version 1.1 (the "License"); you may not use this file except in
7
* compliance with the License. You may obtain a copy of the License at
8
* http://www.mozilla.org/NPL/
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.
25
* Alternatively, the contents of this file may be used under the terms of
26
* either the GNU General Public License Version 2 or later (the "GPL"), or
27
* the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
28
* in which case the provisions of the GPL or the LGPL are applicable instead
29
* of those above. If you wish to allow use of your version of this file only
30
* under the terms of either the GPL or the LGPL, and not to allow others to
31
* use your version of this file under the terms of the NPL, indicate your
32
* decision by deleting the provisions above and replace them with the notice
33
* and other provisions required by the GPL or the LGPL. If you do not delete
34
* the provisions above, a recipient may use your version of this file under
35
* the terms of any one of the NPL, the GPL or the LGPL.
37
* ***** END LICENSE BLOCK ***** */
42
#define NUM_OF_CATEGORY 6
46
#define ENOUGH_REL_THRESHOLD 100
47
#define MAX_REL_THRESHOLD 1000
49
//hiragana frequency category table
50
extern char jp2CharContext[83][83];
52
class JapaneseContextAnalysis
55
JapaneseContextAnalysis() {Reset();};
57
void HandleData(const char* aBuf, PRUint32 aLen);
59
void HandleOneChar(const char* aStr, PRUint32 aCharLen)
63
//if we received enough data, stop here
64
if (mTotalRel > MAX_REL_THRESHOLD) mDone = PR_TRUE;
67
//Only 2-bytes characters are of our interest
68
order = (aCharLen == 2) ? GetOrder(aStr) : -1;
69
if (order != -1 && mLastCharOrder != -1)
72
//count this sequence to its category counter
73
mRelSample[jp2CharContext[mLastCharOrder][order]]++;
75
mLastCharOrder = order;
78
float GetConfidence();
81
PRBool GotEnoughData() {return mTotalRel > ENOUGH_REL_THRESHOLD;};
84
virtual PRInt32 GetOrder(const char* str, PRUint32 *charLen) = 0;
85
virtual PRInt32 GetOrder(const char* str) = 0;
87
//category counters, each interger counts sequence in its category
88
PRUint32 mRelSample[NUM_OF_CATEGORY];
90
//total sequence received
93
//The order of previous char
94
PRInt32 mLastCharOrder;
96
//if last byte in current buffer is not the last byte of a character, we
97
//need to know how many byte to skip in next buffer.
98
PRUint32 mNeedToSkipCharNum;
100
//If this flag is set to PR_TRUE, detection is done and conclusion has been made
105
class SJISContextAnalysis : public JapaneseContextAnalysis
107
//SJISContextAnalysis(){};
109
PRInt32 GetOrder(const char* str, PRUint32 *charLen);
111
PRInt32 GetOrder(const char* str)
113
//We only interested in Hiragana, so first byte is '\202'
114
if (*str == '\202' &&
115
(unsigned char)*(str+1) >= (unsigned char)0x9f &&
116
(unsigned char)*(str+1) <= (unsigned char)0xf1)
117
return (unsigned char)*(str+1) - (unsigned char)0x9f;
122
class EUCJPContextAnalysis : public JapaneseContextAnalysis
125
PRInt32 GetOrder(const char* str, PRUint32 *charLen);
126
PRInt32 GetOrder(const char* str)
127
//We only interested in Hiragana, so first byte is '\244'
129
if (*str == '\244' &&
130
(unsigned char)*(str+1) >= (unsigned char)0xa1 &&
131
(unsigned char)*(str+1) <= (unsigned char)0xf3)
132
return (unsigned char)*(str+1) - (unsigned char)0xa1;
137
#endif /* __JPCNTX_H__ */