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 of the GNU General Public License Version 2 or later (the "GPL"),
26
* or 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
#include "nsGBKConvUtil.h"
41
#include "nsICharRepresentable.h"
42
#define MAX_GBK_LENGTH 24066 /* (0xfe-0x80)*(0xfe-0x3f) */
43
//--------------------------------------------------------------------
45
//--------------------------------------------------------------------
47
static PRBool gInitToGBKTable = PR_FALSE;
48
static const PRUnichar gGBKToUnicodeTable[MAX_GBK_LENGTH] = {
51
static PRUint16 gUnicodeToGBKTable[0xA000-0x4e00];
53
PRBool nsGBKConvUtil::UnicodeToGBKChar(
54
PRUnichar aChar, PRBool aToGL, char*
55
aOutByte1, char* aOutByte2)
57
NS_ASSERTION(gInitToGBKTable, "gGBKToUnicodeTable is not init yet. need to call InitToGBKTable first");
58
PRBool found=PR_FALSE;
59
*aOutByte1 = *aOutByte2 = 0;
60
if(UNICHAR_IN_RANGE(0xd800, aChar, 0xdfff))
62
// surrogate is not in here
65
if(UNICHAR_IN_RANGE(0x4e00, aChar, 0x9FFF))
67
PRUint16 item = gUnicodeToGBKTable[aChar - 0x4e00];
70
*aOutByte1 = item >> 8;
71
*aOutByte2 = item & 0x00FF;
78
for( PRInt32 i = 0; i < MAX_GBK_LENGTH; i++ )
80
if( aChar == gGBKToUnicodeTable[i])
82
*aOutByte1 = (i / 0x00BF + 0x0081) ;
83
*aOutByte2 = (i % 0x00BF + 0x0040) ;
93
// to GL, we only return if it is in the range
94
if(UINT8_IN_RANGE(0xA1, *aOutByte1, 0xFE) &&
95
UINT8_IN_RANGE(0xA1, *aOutByte2, 0xFE))
101
// if it does not fit into 0xa1-0xfe 0xa1-0xfe range that mean
102
// it is not a GB2312 character, we cannot map to GL
110
PRUnichar nsGBKConvUtil::GBKCharToUnicode(char aByte1, char aByte2)
112
NS_ASSERTION(UINT8_IN_RANGE(0x81,aByte1, 0xFE), "first byte out of range");
113
NS_ASSERTION(UINT8_IN_RANGE(0x40,aByte2, 0xFE), "second byte out of range");
115
PRUint8 i1 = (PRUint8)aByte1;
116
PRUint8 i2 = (PRUint8)aByte2;
117
PRUint16 idx = (i1 - 0x0081) * 0x00bf + i2 - 0x0040 ;
119
NS_ASSERTION(idx < MAX_GBK_LENGTH, "ARB");
120
// play it safe- add if statement here ot protect ARB
121
// probably not necessary
122
if(idx < MAX_GBK_LENGTH)
123
return gGBKToUnicodeTable[ idx ];
125
return UCS2_NO_MAPPING;
127
void nsGBKConvUtil::InitToGBKTable()
129
if ( gInitToGBKTable )
134
// zap it to zero first
135
memset(gUnicodeToGBKTable,0, sizeof(gUnicodeToGBKTable));
137
for ( i=0; i<MAX_GBK_LENGTH; i++ )
139
unicode = gGBKToUnicodeTable[i];
140
// to reduce size of gUnicodeToGBKTable, we only do direct unicode to GB
141
// table mapping between unicode 0x4E00 and 0xA000. Others by searching
142
// gGBKToUnicodeTable. There is a trade off between memory usage and speed.
143
if(UNICHAR_IN_RANGE(0x4e00, unicode, 0x9fff))
146
gUnicodeToGBKTable[unicode] = (( i / 0x00BF + 0x0081) << 8) |
147
( i % 0x00BF+ 0x0040);
150
gInitToGBKTable = PR_TRUE;
152
void nsGBKConvUtil::FillInfo(
154
PRUint8 aStart1, PRUint8 aEnd1,
155
PRUint8 aStart2, PRUint8 aEnd2
161
for ( i=aStart1; i<=aEnd1; i++)
163
for( j=aStart2; j<=aEnd2; j++)
165
k = (i - 0x0081)*0x00BF +(j-0x0040);
166
unicode = gGBKToUnicodeTable[k];
167
NS_ASSERTION(unicode != 0xFFFF, "somehow the table still use 0xffff");
168
if (unicode != UCS2_NO_MAPPING)
170
SET_REPRESENTABLE(aInfo, unicode);
175
void nsGBKConvUtil::FillGB2312Info(
179
// The following range is coded by looking at the GB2312 standard
180
// and make sure we do not call FillInfo for undefined code point
182
// row 1 - 1 range (full)
183
FillInfo(aInfo, 0x21|0x80, 0x21|0x80, 0x21|0x80, 0x7E|0x80);
185
FillInfo(aInfo, 0x22|0x80, 0x22|0x80, (0x20+17)|0x80, (0x20+66)|0x80);
186
FillInfo(aInfo, 0x22|0x80, 0x22|0x80, (0x20+69)|0x80, (0x20+78)|0x80);
187
FillInfo(aInfo, 0x22|0x80, 0x22|0x80, (0x20+81)|0x80, (0x20+92)|0x80);
188
// row 3 - 1 range (full)
189
FillInfo(aInfo, 0x23|0x80, 0x23|0x80, 0x21|0x80, 0x7E|0x80);
191
FillInfo(aInfo, 0x24|0x80, 0x24|0x80, (0x20+ 1)|0x80, (0x20+83)|0x80);
193
FillInfo(aInfo, 0x25|0x80, 0x25|0x80, (0x20+ 1)|0x80, (0x20+86)|0x80);
195
FillInfo(aInfo, 0x26|0x80, 0x26|0x80, (0x20+ 1)|0x80, (0x20+24)|0x80);
196
FillInfo(aInfo, 0x26|0x80, 0x26|0x80, (0x20+33)|0x80, (0x20+56)|0x80);
198
FillInfo(aInfo, 0x27|0x80, 0x27|0x80, (0x20+ 1)|0x80, (0x20+33)|0x80);
199
FillInfo(aInfo, 0x27|0x80, 0x27|0x80, (0x20+49)|0x80, (0x20+81)|0x80);
201
FillInfo(aInfo, 0x28|0x80, 0x28|0x80, (0x20+ 1)|0x80, (0x20+26)|0x80);
202
FillInfo(aInfo, 0x28|0x80, 0x28|0x80, (0x20+36)|0x80, (0x20+73)|0x80);
204
FillInfo(aInfo, 0x29|0x80, 0x29|0x80, (0x20+ 4)|0x80, (0x20+79)|0x80);
206
// Frequent used Hanzi
208
FillInfo(aInfo, 0x30|0x80, 0x56|0x80, 0x21|0x80, 0x7E|0x80);
210
FillInfo(aInfo, 0x57|0x80, 0x57|0x80, 0x21|0x80, 0x79|0x80);
212
// Infrequent used Hanzi
214
FillInfo(aInfo, 0x58|0x80, 0x77|0x80, 0x21|0x80, 0x7E|0x80);