|
sl@0
|
1 |
/*
|
|
sl@0
|
2 |
* Copyright (c) 2009 Nokia Corporation and/or its subsidiary(-ies).
|
|
sl@0
|
3 |
* All rights reserved.
|
|
sl@0
|
4 |
* This component and the accompanying materials are made available
|
|
sl@0
|
5 |
* under the terms of "Eclipse Public License v1.0"
|
|
sl@0
|
6 |
* which accompanies this distribution, and is available
|
|
sl@0
|
7 |
* at the URL "http://www.eclipse.org/legal/epl-v10.html".
|
|
sl@0
|
8 |
*
|
|
sl@0
|
9 |
* Initial Contributors:
|
|
sl@0
|
10 |
* Nokia Corporation - initial contribution.
|
|
sl@0
|
11 |
*
|
|
sl@0
|
12 |
* Contributors:
|
|
sl@0
|
13 |
*
|
|
sl@0
|
14 |
* Description: GB18030 converter implementation
|
|
sl@0
|
15 |
*
|
|
sl@0
|
16 |
*/
|
|
sl@0
|
17 |
|
|
sl@0
|
18 |
|
|
sl@0
|
19 |
#include <e32std.h>
|
|
sl@0
|
20 |
#include <charconv.h>
|
|
sl@0
|
21 |
#include <convutils.h>
|
|
sl@0
|
22 |
#include <convdata.h>
|
|
sl@0
|
23 |
#include "gb2312.h"
|
|
sl@0
|
24 |
#include "gbk.h"
|
|
sl@0
|
25 |
#include "gb18030_4byte.h"
|
|
sl@0
|
26 |
#include "gb18030_diff_gbk.h"
|
|
sl@0
|
27 |
#include <ecom/implementationproxy.h>
|
|
sl@0
|
28 |
#include <charactersetconverter.h>
|
|
sl@0
|
29 |
|
|
sl@0
|
30 |
class CGB18030ConverterImpl : public CCharacterSetConverterPluginInterface
|
|
sl@0
|
31 |
{
|
|
sl@0
|
32 |
|
|
sl@0
|
33 |
public:
|
|
sl@0
|
34 |
virtual const TDesC8& ReplacementForUnconvertibleUnicodeCharacters();
|
|
sl@0
|
35 |
|
|
sl@0
|
36 |
virtual TInt ConvertFromUnicode(
|
|
sl@0
|
37 |
CCnvCharacterSetConverter::TEndianness aDefaultEndiannessOfForeignCharacters,
|
|
sl@0
|
38 |
const TDesC8& aReplacementForUnconvertibleUnicodeCharacters,
|
|
sl@0
|
39 |
TDes8& aForeign,
|
|
sl@0
|
40 |
const TDesC16& aUnicode,
|
|
sl@0
|
41 |
CCnvCharacterSetConverter::TArrayOfAscendingIndices& aIndicesOfUnconvertibleCharacters);
|
|
sl@0
|
42 |
|
|
sl@0
|
43 |
virtual TInt ConvertToUnicode(
|
|
sl@0
|
44 |
CCnvCharacterSetConverter::TEndianness aDefaultEndiannessOfForeignCharacters,
|
|
sl@0
|
45 |
TDes16& aUnicode,
|
|
sl@0
|
46 |
const TDesC8& aForeign,
|
|
sl@0
|
47 |
TInt& aState,
|
|
sl@0
|
48 |
TInt& aNumberOfUnconvertibleCharacters,
|
|
sl@0
|
49 |
TInt& aIndexOfFirstByteOfFirstUnconvertibleCharacter);
|
|
sl@0
|
50 |
|
|
sl@0
|
51 |
virtual TBool IsInThisCharacterSetL(
|
|
sl@0
|
52 |
TBool& aSetToTrue,
|
|
sl@0
|
53 |
TInt& aConfidenceLevel,
|
|
sl@0
|
54 |
const TDesC8& aSample);
|
|
sl@0
|
55 |
|
|
sl@0
|
56 |
static CGB18030ConverterImpl* NewL();
|
|
sl@0
|
57 |
virtual ~CGB18030ConverterImpl();
|
|
sl@0
|
58 |
|
|
sl@0
|
59 |
private:
|
|
sl@0
|
60 |
CGB18030ConverterImpl();
|
|
sl@0
|
61 |
TInt ConstructL();
|
|
sl@0
|
62 |
SCnvConversionData * completeGb18030_2byteConversionData; // a merged conversion data including Gb18030-diff-g2312, GB2312, Gb18030-diff-gbk and Gbk
|
|
sl@0
|
63 |
TUint8 * workingMemory;
|
|
sl@0
|
64 |
};
|
|
sl@0
|
65 |
|
|
sl@0
|
66 |
// Implement gb18030 plug-in using cnvutils framework in which gb2312 and gbk conversion data is re-used for memory saving
|
|
sl@0
|
67 |
// 1) foreign->unicode:
|
|
sl@0
|
68 |
// 1.1) 1 byte->unicode bmp: use gb2312 mapping table;
|
|
sl@0
|
69 |
//
|
|
sl@0
|
70 |
// 1.2) 2 byte->unicode bmp: use gb18030-2byte mapping table (gb18030_diff_gb2312ConversionData + gb2312ConversionData + gb18030_diff_gbkConversionData + gbkConversionData);
|
|
sl@0
|
71 |
//
|
|
sl@0
|
72 |
// 1.3) 4 byte->unicode bmp: use gb18030-4byte mapping table;
|
|
sl@0
|
73 |
//
|
|
sl@0
|
74 |
// 1.4) 4 byte->unicode non-bmp: calculate with formula.
|
|
sl@0
|
75 |
//
|
|
sl@0
|
76 |
// 2) unicode->foreign:
|
|
sl@0
|
77 |
// 2.1) firstly check gb18030-2byte mapping table (gb18030_diff_gb2312ConversionData + gb2312ConversionData + gb18030_diff_gbkConversionData + gbkConversionData);
|
|
sl@0
|
78 |
//
|
|
sl@0
|
79 |
// 2.2) if not found in 2.1), check gb18030-4byte mapping table;
|
|
sl@0
|
80 |
//
|
|
sl@0
|
81 |
// 2.3) if not found in 2.2), calculate with formula (gb18030-4byte non BMP);
|
|
sl@0
|
82 |
//
|
|
sl@0
|
83 |
|
|
sl@0
|
84 |
|
|
sl@0
|
85 |
// GB18030-diff-gb2312 defines 1 foreign-to-Unicode range and 2 unicode-to-Foreign range
|
|
sl@0
|
86 |
// GB2312.CTL defines 21 foreign-to-Unicode ranges and 21 Unicode-to-foreign ranges
|
|
sl@0
|
87 |
// GB18030-diff-gbk defines 1 foreign-to-Unicode ranges and 2 Unicode-to-foreign range
|
|
sl@0
|
88 |
// GBK.CTL defines 2 foreign-to-Unicode ranges and 2 Unicode-to-foreign range
|
|
sl@0
|
89 |
const TInt KNumberOfBytesOfWorkingMemory=(1+2+21+21+1+2+2+2)*sizeof(SCnvConversionData::SOneDirectionData::SRange); //totally 1040 bytes
|
|
sl@0
|
90 |
|
|
sl@0
|
91 |
const TDesC8& CGB18030ConverterImpl::ReplacementForUnconvertibleUnicodeCharacters()
|
|
sl@0
|
92 |
{
|
|
sl@0
|
93 |
return CnvGb18030_diff_gbk::ReplacementForUnconvertibleUnicodeCharacters();
|
|
sl@0
|
94 |
}
|
|
sl@0
|
95 |
|
|
sl@0
|
96 |
_LIT(KLitPanicText, "GB18030");
|
|
sl@0
|
97 |
enum TPanic
|
|
sl@0
|
98 |
{
|
|
sl@0
|
99 |
EPanicNothingToConvert1=1,
|
|
sl@0
|
100 |
EPanicNothingToConvert2,
|
|
sl@0
|
101 |
EPanicNothingToConvert3,
|
|
sl@0
|
102 |
EPanicNothingToConvert4,
|
|
sl@0
|
103 |
EPanicNothingToConvert5,
|
|
sl@0
|
104 |
EPanicNothingToConvert6,
|
|
sl@0
|
105 |
EPanicOddNumberOfBytes1,
|
|
sl@0
|
106 |
EPanicOddNumberOfBytes2,
|
|
sl@0
|
107 |
EPanicOddNumberOfBytes3,
|
|
sl@0
|
108 |
EPanicOddNumberOfBytes4,
|
|
sl@0
|
109 |
EPanicOddNumberOfBytes5,
|
|
sl@0
|
110 |
EPanicOddNumberOfBytes6,
|
|
sl@0
|
111 |
EPanicBadHighBit1,
|
|
sl@0
|
112 |
EPanicBadHighBit2,
|
|
sl@0
|
113 |
EPanicBadHighBit3,
|
|
sl@0
|
114 |
EPanicBadHighBit4,
|
|
sl@0
|
115 |
EPanicBadHighBit5,
|
|
sl@0
|
116 |
EPanicBadHighBit6,
|
|
sl@0
|
117 |
EPanicBadHighBit7,
|
|
sl@0
|
118 |
EPanicBadPointers1,
|
|
sl@0
|
119 |
EPanicBadPointers2,
|
|
sl@0
|
120 |
EPanicBadPointers3,
|
|
sl@0
|
121 |
EPanicBadPointers4,
|
|
sl@0
|
122 |
EPanicBadPointers5,
|
|
sl@0
|
123 |
EPanicBadPointers6,
|
|
sl@0
|
124 |
EPanicBadPointers7,
|
|
sl@0
|
125 |
EPanicBadPointers8,
|
|
sl@0
|
126 |
EPanicBadPointers9,
|
|
sl@0
|
127 |
EPanicBadPointers10,
|
|
sl@0
|
128 |
EPanicBadPointers11,
|
|
sl@0
|
129 |
EPanicBadPointers12,
|
|
sl@0
|
130 |
EPanicBadPointers13,
|
|
sl@0
|
131 |
EPanicBadPointers14,
|
|
sl@0
|
132 |
EPanicBadPointers15,
|
|
sl@0
|
133 |
EPanicBadPointers16,
|
|
sl@0
|
134 |
EPanicBadPointers17,
|
|
sl@0
|
135 |
EPanicBadPointers18,
|
|
sl@0
|
136 |
EPanicBadPointers19,
|
|
sl@0
|
137 |
EPanicBadPointers20,
|
|
sl@0
|
138 |
EPanicBadPointers21,
|
|
sl@0
|
139 |
EPanicBadPointers22,
|
|
sl@0
|
140 |
EPanicBadPointers23,
|
|
sl@0
|
141 |
EPanicBadPointers24,
|
|
sl@0
|
142 |
EPanicBadPointers25,
|
|
sl@0
|
143 |
EPanicBadPointers26,
|
|
sl@0
|
144 |
EPanicBadPointers27,
|
|
sl@0
|
145 |
EPanicBadPointers28,
|
|
sl@0
|
146 |
EPanicBadPointers29,
|
|
sl@0
|
147 |
EPanicBadPointers30,
|
|
sl@0
|
148 |
EPanicBadPointers31,
|
|
sl@0
|
149 |
EPanicBadPointers32,
|
|
sl@0
|
150 |
EPanicBadPointers33,
|
|
sl@0
|
151 |
EPanicBadPointers34,
|
|
sl@0
|
152 |
EPanicBadPointers35,
|
|
sl@0
|
153 |
EPanicBadPointers36,
|
|
sl@0
|
154 |
EPanicBadCalculation1,
|
|
sl@0
|
155 |
EPanicBadCalculation2,
|
|
sl@0
|
156 |
EPanicNumberOfBytesIsNotMultipleOfThree1,
|
|
sl@0
|
157 |
EPanicNumberOfBytesIsNotMultipleOfThree2,
|
|
sl@0
|
158 |
EPanicSingleShift2Expected,
|
|
sl@0
|
159 |
EPanicSingleShift3Expected,
|
|
sl@0
|
160 |
EPanicTooManyBytesOfWorkingMemoryUsed1,
|
|
sl@0
|
161 |
EPanicTooManyBytesOfWorkingMemoryUsed2
|
|
sl@0
|
162 |
};
|
|
sl@0
|
163 |
|
|
sl@0
|
164 |
LOCAL_C void Panic(TPanic aPanic)
|
|
sl@0
|
165 |
{
|
|
sl@0
|
166 |
User::Panic(KLitPanicText, aPanic);
|
|
sl@0
|
167 |
}
|
|
sl@0
|
168 |
|
|
sl@0
|
169 |
#define ARRAY_LENGTH(aArray) (sizeof(aArray)/sizeof((aArray)[0]))
|
|
sl@0
|
170 |
|
|
sl@0
|
171 |
LOCAL_C void Step12DummyConvertFromIntermediateBufferInPlace(TInt, TDes8&, TInt& aNumberOfCharactersThatDroppedOut)
|
|
sl@0
|
172 |
{
|
|
sl@0
|
173 |
aNumberOfCharactersThatDroppedOut=0;
|
|
sl@0
|
174 |
}
|
|
sl@0
|
175 |
|
|
sl@0
|
176 |
// Perform the actual conversion (unicode -> gb18030 4byte non-BMP) using formula in this function
|
|
sl@0
|
177 |
LOCAL_C void Step3ConvertFromIntermediateBufferInPlace(TInt aStartPositionInDescriptor, TDes8& aDescriptor, TInt& aNumberOfCharactersThatDroppedOut)
|
|
sl@0
|
178 |
{
|
|
sl@0
|
179 |
aNumberOfCharactersThatDroppedOut = 0; // no drop out, because all GB18030 outside BMP are exactly 4-bytes
|
|
sl@0
|
180 |
|
|
sl@0
|
181 |
const TInt descriptorLength=aDescriptor.Length();
|
|
sl@0
|
182 |
TUint8* pVeryFrom = CONST_CAST(TUint8*, aDescriptor.Ptr());
|
|
sl@0
|
183 |
const TUint8* pEnd = pVeryFrom + descriptorLength;
|
|
sl@0
|
184 |
TUint8* pFrom = pVeryFrom + aStartPositionInDescriptor;
|
|
sl@0
|
185 |
FOREVER
|
|
sl@0
|
186 |
{
|
|
sl@0
|
187 |
if (pFrom + 4 > pEnd)
|
|
sl@0
|
188 |
{
|
|
sl@0
|
189 |
__ASSERT_DEBUG(pFrom==pEnd, Panic(EPanicBadPointers25));
|
|
sl@0
|
190 |
break;
|
|
sl@0
|
191 |
}
|
|
sl@0
|
192 |
TUint characterCode = 0;
|
|
sl@0
|
193 |
for (TInt i=0; i<4; i++)
|
|
sl@0
|
194 |
{
|
|
sl@0
|
195 |
characterCode <<= 8;
|
|
sl@0
|
196 |
characterCode += pFrom[i];
|
|
sl@0
|
197 |
}
|
|
sl@0
|
198 |
|
|
sl@0
|
199 |
// to gb18030
|
|
sl@0
|
200 |
characterCode -= 0x10000;
|
|
sl@0
|
201 |
TUint b4 = characterCode % 10 + 0x30;
|
|
sl@0
|
202 |
characterCode /= 10;
|
|
sl@0
|
203 |
TUint b3 = characterCode % 126 + 0x81;
|
|
sl@0
|
204 |
characterCode /= 126;
|
|
sl@0
|
205 |
TUint b2 = characterCode % 10 + 0x30;
|
|
sl@0
|
206 |
TUint b1 = characterCode / 10 + 0x90;
|
|
sl@0
|
207 |
|
|
sl@0
|
208 |
*pFrom++ = b1;
|
|
sl@0
|
209 |
*pFrom++ = b2;
|
|
sl@0
|
210 |
*pFrom++ = b3;
|
|
sl@0
|
211 |
*pFrom++ = b4;
|
|
sl@0
|
212 |
}
|
|
sl@0
|
213 |
aDescriptor.SetLength(pFrom-pVeryFrom);
|
|
sl@0
|
214 |
}
|
|
sl@0
|
215 |
|
|
sl@0
|
216 |
// gb2312-1byte ->unicode (0x00 - 0x7F)
|
|
sl@0
|
217 |
LOCAL_C TInt Step0NumberOfBytesAbleToConvertToUnicode(const TDesC8& aDescriptor)
|
|
sl@0
|
218 |
{
|
|
sl@0
|
219 |
const TInt descriptorLength=aDescriptor.Length();
|
|
sl@0
|
220 |
const TUint8* pointerToPreviousByte=aDescriptor.Ptr()-1;
|
|
sl@0
|
221 |
const TUint8* const pointerToLastByte=pointerToPreviousByte+aDescriptor.Length();
|
|
sl@0
|
222 |
|
|
sl@0
|
223 |
TInt numOfBytes = 0;
|
|
sl@0
|
224 |
FOREVER
|
|
sl@0
|
225 |
{
|
|
sl@0
|
226 |
if (pointerToPreviousByte>=pointerToLastByte)
|
|
sl@0
|
227 |
{
|
|
sl@0
|
228 |
break;
|
|
sl@0
|
229 |
}
|
|
sl@0
|
230 |
// byte 1
|
|
sl@0
|
231 |
TUint b1 = pointerToPreviousByte[1];
|
|
sl@0
|
232 |
if (b1 <= 0x7F)
|
|
sl@0
|
233 |
{
|
|
sl@0
|
234 |
pointerToPreviousByte++;
|
|
sl@0
|
235 |
numOfBytes++;
|
|
sl@0
|
236 |
}
|
|
sl@0
|
237 |
else
|
|
sl@0
|
238 |
break;
|
|
sl@0
|
239 |
}
|
|
sl@0
|
240 |
return numOfBytes;
|
|
sl@0
|
241 |
}
|
|
sl@0
|
242 |
|
|
sl@0
|
243 |
// gb18030-2byte --> unicode (0x8140 - 0xFE7E, 0x8180 - 0xFEFE)
|
|
sl@0
|
244 |
LOCAL_C TInt Step1NumberOfBytesAbleToConvertToUnicode(const TDesC8& aDescriptor)
|
|
sl@0
|
245 |
{
|
|
sl@0
|
246 |
const TInt descriptorLength=aDescriptor.Length();
|
|
sl@0
|
247 |
const TUint8* pointerToPreviousByte=aDescriptor.Ptr()-1;
|
|
sl@0
|
248 |
const TUint8* const pointerToLastByte=pointerToPreviousByte+aDescriptor.Length();
|
|
sl@0
|
249 |
|
|
sl@0
|
250 |
TInt numOfBytes = 0;
|
|
sl@0
|
251 |
FOREVER
|
|
sl@0
|
252 |
{
|
|
sl@0
|
253 |
if (pointerToPreviousByte>=pointerToLastByte)
|
|
sl@0
|
254 |
{
|
|
sl@0
|
255 |
break;
|
|
sl@0
|
256 |
}
|
|
sl@0
|
257 |
// byte 1
|
|
sl@0
|
258 |
TUint b1 = pointerToPreviousByte[1];
|
|
sl@0
|
259 |
if (b1 <= 0x80 || b1 > 0xFE)
|
|
sl@0
|
260 |
break;
|
|
sl@0
|
261 |
|
|
sl@0
|
262 |
// byte 2
|
|
sl@0
|
263 |
if (pointerToPreviousByte+1 >= pointerToLastByte)
|
|
sl@0
|
264 |
break;
|
|
sl@0
|
265 |
TUint b2 = pointerToPreviousByte[2];
|
|
sl@0
|
266 |
if (b2 >= 0x40 && b2 <= 0xFE && b2 != 0x7F) // all gb18030 2-byte code
|
|
sl@0
|
267 |
{
|
|
sl@0
|
268 |
pointerToPreviousByte = pointerToPreviousByte + 2;
|
|
sl@0
|
269 |
numOfBytes = numOfBytes + 2;
|
|
sl@0
|
270 |
}
|
|
sl@0
|
271 |
else if (b2 < 0x30 || b2 > 0x39)
|
|
sl@0
|
272 |
{
|
|
sl@0
|
273 |
if (numOfBytes <= 0)
|
|
sl@0
|
274 |
return CCnvCharacterSetConverter::EErrorIllFormedInput;
|
|
sl@0
|
275 |
else
|
|
sl@0
|
276 |
break;
|
|
sl@0
|
277 |
}
|
|
sl@0
|
278 |
else
|
|
sl@0
|
279 |
break;
|
|
sl@0
|
280 |
}
|
|
sl@0
|
281 |
return numOfBytes;
|
|
sl@0
|
282 |
}
|
|
sl@0
|
283 |
|
|
sl@0
|
284 |
|
|
sl@0
|
285 |
// gb18030 4-bytes bmp --> unicode (0x81308130 - 0x8439FE39)
|
|
sl@0
|
286 |
LOCAL_C TInt Step2NumberOfBytesAbleToConvertToUnicode(const TDesC8& aDescriptor)
|
|
sl@0
|
287 |
{
|
|
sl@0
|
288 |
const TUint8* pointerToPreviousByte=aDescriptor.Ptr()-1;
|
|
sl@0
|
289 |
const TUint8* const pointerToLastByte=pointerToPreviousByte+aDescriptor.Length();
|
|
sl@0
|
290 |
__ASSERT_DEBUG(pointerToPreviousByte<=pointerToLastByte, Panic(EPanicBadPointers25));
|
|
sl@0
|
291 |
|
|
sl@0
|
292 |
TInt numOfBytes = 0;
|
|
sl@0
|
293 |
FOREVER
|
|
sl@0
|
294 |
{
|
|
sl@0
|
295 |
if (pointerToPreviousByte>=pointerToLastByte)
|
|
sl@0
|
296 |
{
|
|
sl@0
|
297 |
break;
|
|
sl@0
|
298 |
}
|
|
sl@0
|
299 |
|
|
sl@0
|
300 |
// byte 1
|
|
sl@0
|
301 |
TUint b1 = pointerToPreviousByte[1];
|
|
sl@0
|
302 |
if ((b1 < 0x81) || (b1 > 0x84)){
|
|
sl@0
|
303 |
break;
|
|
sl@0
|
304 |
}
|
|
sl@0
|
305 |
|
|
sl@0
|
306 |
// byte 2
|
|
sl@0
|
307 |
if (pointerToPreviousByte+1 >= pointerToLastByte)
|
|
sl@0
|
308 |
break;
|
|
sl@0
|
309 |
TUint b2 = pointerToPreviousByte[2];
|
|
sl@0
|
310 |
if (b2 >= 0x40 && b2 <= 0xFE && b2 != 0x7F) // all gb18030 2-byte code
|
|
sl@0
|
311 |
break;
|
|
sl@0
|
312 |
else if (b2 < 0x30 || b2 > 0x39)
|
|
sl@0
|
313 |
{
|
|
sl@0
|
314 |
if (numOfBytes == 0)
|
|
sl@0
|
315 |
return CCnvCharacterSetConverter::EErrorIllFormedInput;
|
|
sl@0
|
316 |
else
|
|
sl@0
|
317 |
break;
|
|
sl@0
|
318 |
}
|
|
sl@0
|
319 |
|
|
sl@0
|
320 |
|
|
sl@0
|
321 |
// byte 3
|
|
sl@0
|
322 |
if (pointerToPreviousByte+2 >= pointerToLastByte)
|
|
sl@0
|
323 |
break;
|
|
sl@0
|
324 |
TUint b3 = pointerToPreviousByte[3];
|
|
sl@0
|
325 |
if (b3 < 0x81 || b3 > 0xFE)
|
|
sl@0
|
326 |
{
|
|
sl@0
|
327 |
if (numOfBytes == 0)
|
|
sl@0
|
328 |
return CCnvCharacterSetConverter::EErrorIllFormedInput;
|
|
sl@0
|
329 |
else
|
|
sl@0
|
330 |
break;
|
|
sl@0
|
331 |
}
|
|
sl@0
|
332 |
|
|
sl@0
|
333 |
// byte 4
|
|
sl@0
|
334 |
if (pointerToPreviousByte+3 >= pointerToLastByte)
|
|
sl@0
|
335 |
break;
|
|
sl@0
|
336 |
TUint b4 = pointerToPreviousByte[4];
|
|
sl@0
|
337 |
if (b4 < 0x30 || b4 > 0x39)
|
|
sl@0
|
338 |
{
|
|
sl@0
|
339 |
if (numOfBytes == 0)
|
|
sl@0
|
340 |
return CCnvCharacterSetConverter::EErrorIllFormedInput;
|
|
sl@0
|
341 |
else
|
|
sl@0
|
342 |
break;
|
|
sl@0
|
343 |
}
|
|
sl@0
|
344 |
else
|
|
sl@0
|
345 |
{
|
|
sl@0
|
346 |
numOfBytes = numOfBytes + 4;
|
|
sl@0
|
347 |
pointerToPreviousByte = pointerToPreviousByte+4;
|
|
sl@0
|
348 |
}
|
|
sl@0
|
349 |
}
|
|
sl@0
|
350 |
|
|
sl@0
|
351 |
return numOfBytes;
|
|
sl@0
|
352 |
}
|
|
sl@0
|
353 |
|
|
sl@0
|
354 |
// gb18030 4-bytes non-bmp --> unicode (0x90308130~0xE339FE39)
|
|
sl@0
|
355 |
LOCAL_C TInt Step3NumberOfBytesAbleToConvertToUnicode(const TDesC8& aDescriptor)
|
|
sl@0
|
356 |
{
|
|
sl@0
|
357 |
const TUint8* pointerToPreviousByte=aDescriptor.Ptr()-1;
|
|
sl@0
|
358 |
const TUint8* const pointerToLastByte=pointerToPreviousByte+aDescriptor.Length();
|
|
sl@0
|
359 |
__ASSERT_DEBUG(pointerToPreviousByte<=pointerToLastByte, Panic(EPanicBadPointers25));
|
|
sl@0
|
360 |
|
|
sl@0
|
361 |
TInt numOfBytes = 0;
|
|
sl@0
|
362 |
FOREVER
|
|
sl@0
|
363 |
{
|
|
sl@0
|
364 |
if (pointerToPreviousByte>=pointerToLastByte)
|
|
sl@0
|
365 |
{
|
|
sl@0
|
366 |
break;
|
|
sl@0
|
367 |
}
|
|
sl@0
|
368 |
|
|
sl@0
|
369 |
// byte 1
|
|
sl@0
|
370 |
TUint b1 = pointerToPreviousByte[1];
|
|
sl@0
|
371 |
if (b1 < 0x90 || b1 > 0xE3)
|
|
sl@0
|
372 |
break;
|
|
sl@0
|
373 |
|
|
sl@0
|
374 |
// byte 2
|
|
sl@0
|
375 |
if (pointerToPreviousByte+1 >= pointerToLastByte)
|
|
sl@0
|
376 |
break;
|
|
sl@0
|
377 |
TUint b2 = pointerToPreviousByte[2];
|
|
sl@0
|
378 |
if (b2 >= 0x40 && b2 <= 0xFE && b2 != 0x7F)
|
|
sl@0
|
379 |
break;
|
|
sl@0
|
380 |
else if (b2 < 0x30 || b2 > 0x39)
|
|
sl@0
|
381 |
{
|
|
sl@0
|
382 |
if (numOfBytes == 0)
|
|
sl@0
|
383 |
return CCnvCharacterSetConverter::EErrorIllFormedInput;
|
|
sl@0
|
384 |
else
|
|
sl@0
|
385 |
break;
|
|
sl@0
|
386 |
}
|
|
sl@0
|
387 |
|
|
sl@0
|
388 |
// byte 3
|
|
sl@0
|
389 |
if (pointerToPreviousByte+2 >= pointerToLastByte)
|
|
sl@0
|
390 |
break;
|
|
sl@0
|
391 |
TUint b3 = pointerToPreviousByte[3];
|
|
sl@0
|
392 |
if (b3 < 0x81 || b3 > 0xFE)
|
|
sl@0
|
393 |
{
|
|
sl@0
|
394 |
if (numOfBytes == 0)
|
|
sl@0
|
395 |
return CCnvCharacterSetConverter::EErrorIllFormedInput;
|
|
sl@0
|
396 |
else
|
|
sl@0
|
397 |
break;
|
|
sl@0
|
398 |
}
|
|
sl@0
|
399 |
|
|
sl@0
|
400 |
// byte 4
|
|
sl@0
|
401 |
if (pointerToPreviousByte+3 >= pointerToLastByte)
|
|
sl@0
|
402 |
break;
|
|
sl@0
|
403 |
TUint b4 = pointerToPreviousByte[4];
|
|
sl@0
|
404 |
if (b4 < 0x30 || b4 > 0x39)
|
|
sl@0
|
405 |
{
|
|
sl@0
|
406 |
if (numOfBytes == 0)
|
|
sl@0
|
407 |
return CCnvCharacterSetConverter::EErrorIllFormedInput;
|
|
sl@0
|
408 |
else
|
|
sl@0
|
409 |
break;
|
|
sl@0
|
410 |
}
|
|
sl@0
|
411 |
else
|
|
sl@0
|
412 |
{
|
|
sl@0
|
413 |
numOfBytes = numOfBytes + 4;
|
|
sl@0
|
414 |
pointerToPreviousByte = pointerToPreviousByte + 4;
|
|
sl@0
|
415 |
}
|
|
sl@0
|
416 |
}
|
|
sl@0
|
417 |
return numOfBytes;
|
|
sl@0
|
418 |
}
|
|
sl@0
|
419 |
|
|
sl@0
|
420 |
void Step012DummyConvertToIntermediateBufferInPlace(TDes8&)
|
|
sl@0
|
421 |
{
|
|
sl@0
|
422 |
}
|
|
sl@0
|
423 |
|
|
sl@0
|
424 |
// Perform the actual conversion (gb18030 4byte non-BMP -> unicode) using formula in this function
|
|
sl@0
|
425 |
LOCAL_C void Step3ConvertToIntermediateBufferInPlace(TDes8& aDescriptor)
|
|
sl@0
|
426 |
{
|
|
sl@0
|
427 |
const TInt descriptorLength=aDescriptor.Length();
|
|
sl@0
|
428 |
__ASSERT_DEBUG(descriptorLength%4 == 0, Panic(EPanicNothingToConvert5));
|
|
sl@0
|
429 |
TUint8* pointerToTargetByte=CONST_CAST(TUint8*, aDescriptor.Ptr());
|
|
sl@0
|
430 |
const TUint8* pointerToSourceByte=pointerToTargetByte;
|
|
sl@0
|
431 |
const TUint8* const pointerToLastByte=pointerToSourceByte+descriptorLength;
|
|
sl@0
|
432 |
|
|
sl@0
|
433 |
FOREVER
|
|
sl@0
|
434 |
{
|
|
sl@0
|
435 |
if (pointerToLastByte - pointerToSourceByte < 4)
|
|
sl@0
|
436 |
break;
|
|
sl@0
|
437 |
|
|
sl@0
|
438 |
// conversion
|
|
sl@0
|
439 |
TUint8 b1 = pointerToSourceByte[0];
|
|
sl@0
|
440 |
TUint8 b2 = pointerToSourceByte[1];
|
|
sl@0
|
441 |
TUint8 b3 = pointerToSourceByte[2];
|
|
sl@0
|
442 |
TUint8 b4 = pointerToSourceByte[3];
|
|
sl@0
|
443 |
|
|
sl@0
|
444 |
TUint characterCode = 0x10000 + (b1 - 0x90) * 12600 +
|
|
sl@0
|
445 |
(b2 - 0x30) * 1260 +
|
|
sl@0
|
446 |
(b3 - 0x81) * 10 +
|
|
sl@0
|
447 |
(b4 - 0x30);
|
|
sl@0
|
448 |
|
|
sl@0
|
449 |
pointerToTargetByte[0] = ((characterCode >> 24) & 0xFF);
|
|
sl@0
|
450 |
pointerToTargetByte[1] = ((characterCode >> 16) & 0xFF);
|
|
sl@0
|
451 |
pointerToTargetByte[2] = ((characterCode >> 8) & 0xFF);
|
|
sl@0
|
452 |
pointerToTargetByte[3] = (characterCode & 0xFF);
|
|
sl@0
|
453 |
|
|
sl@0
|
454 |
pointerToSourceByte = pointerToSourceByte + 4;
|
|
sl@0
|
455 |
pointerToTargetByte = pointerToTargetByte + 4;
|
|
sl@0
|
456 |
}
|
|
sl@0
|
457 |
|
|
sl@0
|
458 |
aDescriptor.SetLength(descriptorLength);
|
|
sl@0
|
459 |
}
|
|
sl@0
|
460 |
|
|
sl@0
|
461 |
|
|
sl@0
|
462 |
// A dummy "direct" mapping table for non-Bmp chars in step 3
|
|
sl@0
|
463 |
// Use 32-bit Unicode value as intermediate coding
|
|
sl@0
|
464 |
LOCAL_D const SCnvConversionData::SVariableByteData::SRange step3ForeignVariableByteDataRanges[]=
|
|
sl@0
|
465 |
{
|
|
sl@0
|
466 |
{
|
|
sl@0
|
467 |
0x00, // from 0x10000
|
|
sl@0
|
468 |
0x00, // to 0x10FFFF
|
|
sl@0
|
469 |
3, // total 4 bytes
|
|
sl@0
|
470 |
0
|
|
sl@0
|
471 |
},
|
|
sl@0
|
472 |
};
|
|
sl@0
|
473 |
LOCAL_D const SCnvConversionData::SOneDirectionData::SRange step3ForeignToUnicodeDataRanges[]=
|
|
sl@0
|
474 |
{
|
|
sl@0
|
475 |
{
|
|
sl@0
|
476 |
0x10000, // from 0x10000
|
|
sl@0
|
477 |
0x10ffff, // to 0x10FFFF
|
|
sl@0
|
478 |
SCnvConversionData::SOneDirectionData::SRange::EDirect,
|
|
sl@0
|
479 |
0,
|
|
sl@0
|
480 |
0,
|
|
sl@0
|
481 |
{
|
|
sl@0
|
482 |
0 // map from intermediate to unicode with offset = 0
|
|
sl@0
|
483 |
}
|
|
sl@0
|
484 |
},
|
|
sl@0
|
485 |
};
|
|
sl@0
|
486 |
LOCAL_D const SCnvConversionData::SOneDirectionData::SRange step3UnicodeToForeignDataRanges[]=
|
|
sl@0
|
487 |
{
|
|
sl@0
|
488 |
{
|
|
sl@0
|
489 |
0x10000, //from 0x10000
|
|
sl@0
|
490 |
0x10FFFF, //to 0x10FFFF
|
|
sl@0
|
491 |
SCnvConversionData::SOneDirectionData::SRange::EDirect,
|
|
sl@0
|
492 |
4, // output byte count = 4
|
|
sl@0
|
493 |
0,
|
|
sl@0
|
494 |
{
|
|
sl@0
|
495 |
0 // offset = 0
|
|
sl@0
|
496 |
}
|
|
sl@0
|
497 |
},
|
|
sl@0
|
498 |
};
|
|
sl@0
|
499 |
GLDEF_D const SCnvConversionData step3ConversionData=
|
|
sl@0
|
500 |
{
|
|
sl@0
|
501 |
SCnvConversionData::EFixedBigEndian,
|
|
sl@0
|
502 |
{
|
|
sl@0
|
503 |
ARRAY_LENGTH(step3ForeignVariableByteDataRanges),
|
|
sl@0
|
504 |
step3ForeignVariableByteDataRanges
|
|
sl@0
|
505 |
},
|
|
sl@0
|
506 |
{
|
|
sl@0
|
507 |
ARRAY_LENGTH(step3ForeignToUnicodeDataRanges),
|
|
sl@0
|
508 |
step3ForeignToUnicodeDataRanges
|
|
sl@0
|
509 |
},
|
|
sl@0
|
510 |
{
|
|
sl@0
|
511 |
ARRAY_LENGTH(step3UnicodeToForeignDataRanges),
|
|
sl@0
|
512 |
step3UnicodeToForeignDataRanges
|
|
sl@0
|
513 |
},
|
|
sl@0
|
514 |
NULL,
|
|
sl@0
|
515 |
NULL
|
|
sl@0
|
516 |
};
|
|
sl@0
|
517 |
|
|
sl@0
|
518 |
|
|
sl@0
|
519 |
// An internal mapping table to reslove the conflict introduced in symbian GB2312-80 plug-in.
|
|
sl@0
|
520 |
// It will be merged into the gb18030-2byte Conversion Data.
|
|
sl@0
|
521 |
// It includes mapping: (0xA1A4 -> 0x00B7, 0xA1AA -> 0x2014, 0xA844 <- 0x2015, 0x8139A739 <- 0x30FB)
|
|
sl@0
|
522 |
LOCAL_D const SCnvConversionData::SVariableByteData::SRange gb18030_diff_gb2312ForeignVariableByteDataRanges[]=
|
|
sl@0
|
523 |
{
|
|
sl@0
|
524 |
{
|
|
sl@0
|
525 |
0xA1, //from 0xA1A4
|
|
sl@0
|
526 |
0xA1, //to 0xA1AA
|
|
sl@0
|
527 |
1,
|
|
sl@0
|
528 |
0
|
|
sl@0
|
529 |
},
|
|
sl@0
|
530 |
};
|
|
sl@0
|
531 |
LOCAL_D const SCnvConversionData::SOneDirectionData::SRange::UData::SKeyedTable1616::SEntry keyedTable1616_foreignToUnicode_1[]=
|
|
sl@0
|
532 |
{
|
|
sl@0
|
533 |
{
|
|
sl@0
|
534 |
0xA1A4,
|
|
sl@0
|
535 |
0x00B7
|
|
sl@0
|
536 |
},
|
|
sl@0
|
537 |
{
|
|
sl@0
|
538 |
0xA1AA,
|
|
sl@0
|
539 |
0x2014
|
|
sl@0
|
540 |
}
|
|
sl@0
|
541 |
};
|
|
sl@0
|
542 |
LOCAL_D const SCnvConversionData::SOneDirectionData::SRange gb18030_diff_gb2312ForeignToUnicodeDataRanges[]=
|
|
sl@0
|
543 |
{
|
|
sl@0
|
544 |
{
|
|
sl@0
|
545 |
0xA1A4,
|
|
sl@0
|
546 |
0xA1AA,
|
|
sl@0
|
547 |
SCnvConversionData::SOneDirectionData::SRange::EKeyedTable1616,
|
|
sl@0
|
548 |
0,
|
|
sl@0
|
549 |
0,
|
|
sl@0
|
550 |
{
|
|
sl@0
|
551 |
UData_SKeyedTable1616(keyedTable1616_foreignToUnicode_1)
|
|
sl@0
|
552 |
}
|
|
sl@0
|
553 |
},
|
|
sl@0
|
554 |
};
|
|
sl@0
|
555 |
LOCAL_D const SCnvConversionData::SOneDirectionData::SRange::UData::SKeyedTable1616::SEntry keyedTable1616_unicodeToForeign_1[]=
|
|
sl@0
|
556 |
{
|
|
sl@0
|
557 |
{
|
|
sl@0
|
558 |
0x2015,
|
|
sl@0
|
559 |
0xA844
|
|
sl@0
|
560 |
}
|
|
sl@0
|
561 |
};
|
|
sl@0
|
562 |
LOCAL_D const SCnvConversionData::SOneDirectionData::SRange::UData::SKeyedTable3232::SEntry keyedTable3232_unicodeToForeign_1[]=
|
|
sl@0
|
563 |
{
|
|
sl@0
|
564 |
{
|
|
sl@0
|
565 |
0x30FB,
|
|
sl@0
|
566 |
0x8139A739
|
|
sl@0
|
567 |
}
|
|
sl@0
|
568 |
};
|
|
sl@0
|
569 |
|
|
sl@0
|
570 |
LOCAL_D const SCnvConversionData::SOneDirectionData::SRange gb18030_diff_gb2312UnicodeToForeignDataRanges[]=
|
|
sl@0
|
571 |
{
|
|
sl@0
|
572 |
{
|
|
sl@0
|
573 |
0x2015,
|
|
sl@0
|
574 |
0x2015,
|
|
sl@0
|
575 |
SCnvConversionData::SOneDirectionData::SRange::EKeyedTable1616,
|
|
sl@0
|
576 |
2, // output byte count = 2
|
|
sl@0
|
577 |
0,
|
|
sl@0
|
578 |
{
|
|
sl@0
|
579 |
UData_SKeyedTable1616(keyedTable1616_unicodeToForeign_1)
|
|
sl@0
|
580 |
}
|
|
sl@0
|
581 |
},
|
|
sl@0
|
582 |
{
|
|
sl@0
|
583 |
0x30FB,
|
|
sl@0
|
584 |
0x30FB,
|
|
sl@0
|
585 |
SCnvConversionData::SOneDirectionData::SRange::EKeyedTable3232,
|
|
sl@0
|
586 |
4, // output byte count = 4
|
|
sl@0
|
587 |
0,
|
|
sl@0
|
588 |
{
|
|
sl@0
|
589 |
UData_SKeyedTable3232(keyedTable3232_unicodeToForeign_1)
|
|
sl@0
|
590 |
}
|
|
sl@0
|
591 |
},
|
|
sl@0
|
592 |
};
|
|
sl@0
|
593 |
GLDEF_D const SCnvConversionData gb18030_diff_gb2312ConversionData=
|
|
sl@0
|
594 |
{
|
|
sl@0
|
595 |
SCnvConversionData::EFixedBigEndian,
|
|
sl@0
|
596 |
{
|
|
sl@0
|
597 |
ARRAY_LENGTH(gb18030_diff_gb2312ForeignVariableByteDataRanges),
|
|
sl@0
|
598 |
gb18030_diff_gb2312ForeignVariableByteDataRanges
|
|
sl@0
|
599 |
},
|
|
sl@0
|
600 |
{
|
|
sl@0
|
601 |
ARRAY_LENGTH(gb18030_diff_gb2312ForeignToUnicodeDataRanges),
|
|
sl@0
|
602 |
gb18030_diff_gb2312ForeignToUnicodeDataRanges
|
|
sl@0
|
603 |
},
|
|
sl@0
|
604 |
{
|
|
sl@0
|
605 |
ARRAY_LENGTH(gb18030_diff_gb2312UnicodeToForeignDataRanges),
|
|
sl@0
|
606 |
gb18030_diff_gb2312UnicodeToForeignDataRanges
|
|
sl@0
|
607 |
},
|
|
sl@0
|
608 |
NULL,
|
|
sl@0
|
609 |
NULL
|
|
sl@0
|
610 |
};
|
|
sl@0
|
611 |
|
|
sl@0
|
612 |
LOCAL_D const SCnvConversionData::SVariableByteData::SRange foreignVariableByteDataRanges[]=
|
|
sl@0
|
613 |
{
|
|
sl@0
|
614 |
{
|
|
sl@0
|
615 |
0x00,
|
|
sl@0
|
616 |
0x7f,
|
|
sl@0
|
617 |
0,
|
|
sl@0
|
618 |
0
|
|
sl@0
|
619 |
},
|
|
sl@0
|
620 |
{
|
|
sl@0
|
621 |
0x80,
|
|
sl@0
|
622 |
0xff,
|
|
sl@0
|
623 |
1,
|
|
sl@0
|
624 |
0
|
|
sl@0
|
625 |
}
|
|
sl@0
|
626 |
};
|
|
sl@0
|
627 |
|
|
sl@0
|
628 |
LOCAL_C void SetUpCompleteGb18030_2byteConversionData(SCnvConversionData& aCompleteGb18030_2byteConversionData, TUint8* aWorkingMemory)
|
|
sl@0
|
629 |
{
|
|
sl@0
|
630 |
const SCnvConversionData& gb2312ConversionData=CnvGb2312::ConversionData();
|
|
sl@0
|
631 |
const SCnvConversionData& gb18030_diff_gbkConversionData=CnvGb18030_diff_gbk::ConversionData();
|
|
sl@0
|
632 |
const SCnvConversionData& gbkConversionData=CnvGbk::ConversionData();
|
|
sl@0
|
633 |
// create a SCnvConversionData that is the combination of gb18030_diff_gb2312ConversionData, gb2312ConversionData, gb18030_diff_gbkConversionData and gbkConversionData;
|
|
sl@0
|
634 |
aCompleteGb18030_2byteConversionData.iEndiannessOfForeignCharacters=SCnvConversionData::EFixedBigEndian;
|
|
sl@0
|
635 |
aCompleteGb18030_2byteConversionData.iForeignVariableByteData.iNumberOfRanges=ARRAY_LENGTH(foreignVariableByteDataRanges);
|
|
sl@0
|
636 |
aCompleteGb18030_2byteConversionData.iForeignVariableByteData.iRangeArray=foreignVariableByteDataRanges;
|
|
sl@0
|
637 |
TInt numberOfBytesOfWorkingMemoryUsed=0;
|
|
sl@0
|
638 |
|
|
sl@0
|
639 |
// set up the foreign-to-Unicode data
|
|
sl@0
|
640 |
const TInt numberOfForeignToUnicodeDataRanges=gb18030_diff_gb2312ConversionData.iForeignToUnicodeData.iNumberOfRanges + gb2312ConversionData.iForeignToUnicodeData.iNumberOfRanges + gb18030_diff_gbkConversionData.iForeignToUnicodeData.iNumberOfRanges + gbkConversionData.iForeignToUnicodeData.iNumberOfRanges;
|
|
sl@0
|
641 |
aCompleteGb18030_2byteConversionData.iForeignToUnicodeData.iNumberOfRanges=numberOfForeignToUnicodeDataRanges;
|
|
sl@0
|
642 |
SCnvConversionData::SOneDirectionData::SRange* foreignToUnicodeDataRangeArray=REINTERPRET_CAST(SCnvConversionData::SOneDirectionData::SRange*, aWorkingMemory+numberOfBytesOfWorkingMemoryUsed);
|
|
sl@0
|
643 |
numberOfBytesOfWorkingMemoryUsed+=(numberOfForeignToUnicodeDataRanges*sizeof(SCnvConversionData::SOneDirectionData::SRange));
|
|
sl@0
|
644 |
__ASSERT_ALWAYS(numberOfBytesOfWorkingMemoryUsed<=KNumberOfBytesOfWorkingMemory, Panic(EPanicTooManyBytesOfWorkingMemoryUsed1));
|
|
sl@0
|
645 |
aCompleteGb18030_2byteConversionData.iForeignToUnicodeData.iRangeArray=foreignToUnicodeDataRangeArray;
|
|
sl@0
|
646 |
Mem::Copy(foreignToUnicodeDataRangeArray, gb18030_diff_gb2312ConversionData.iForeignToUnicodeData.iRangeArray, gb18030_diff_gb2312ConversionData.iForeignToUnicodeData.iNumberOfRanges*sizeof(SCnvConversionData::SOneDirectionData::SRange));
|
|
sl@0
|
647 |
Mem::Copy(foreignToUnicodeDataRangeArray + gb18030_diff_gb2312ConversionData.iForeignToUnicodeData.iNumberOfRanges, gb2312ConversionData.iForeignToUnicodeData.iRangeArray, gb2312ConversionData.iForeignToUnicodeData.iNumberOfRanges*sizeof(SCnvConversionData::SOneDirectionData::SRange));
|
|
sl@0
|
648 |
Mem::Copy(foreignToUnicodeDataRangeArray + gb18030_diff_gb2312ConversionData.iForeignToUnicodeData.iNumberOfRanges + gb2312ConversionData.iForeignToUnicodeData.iNumberOfRanges, gb18030_diff_gbkConversionData.iForeignToUnicodeData.iRangeArray, gb18030_diff_gbkConversionData.iForeignToUnicodeData.iNumberOfRanges*sizeof(SCnvConversionData::SOneDirectionData::SRange));
|
|
sl@0
|
649 |
Mem::Copy(foreignToUnicodeDataRangeArray + gb18030_diff_gb2312ConversionData.iForeignToUnicodeData.iNumberOfRanges + gb2312ConversionData.iForeignToUnicodeData.iNumberOfRanges + gb18030_diff_gbkConversionData.iForeignToUnicodeData.iNumberOfRanges, gbkConversionData.iForeignToUnicodeData.iRangeArray, gbkConversionData.iForeignToUnicodeData.iNumberOfRanges*sizeof(SCnvConversionData::SOneDirectionData::SRange));
|
|
sl@0
|
650 |
|
|
sl@0
|
651 |
// set up the Unicode-to-foreign data
|
|
sl@0
|
652 |
const TInt numberOfUnicodeToForeignDataRanges=gb18030_diff_gb2312ConversionData.iUnicodeToForeignData.iNumberOfRanges + gb2312ConversionData.iUnicodeToForeignData.iNumberOfRanges + gb18030_diff_gbkConversionData.iUnicodeToForeignData.iNumberOfRanges + gbkConversionData.iUnicodeToForeignData.iNumberOfRanges;
|
|
sl@0
|
653 |
aCompleteGb18030_2byteConversionData.iUnicodeToForeignData.iNumberOfRanges=numberOfUnicodeToForeignDataRanges;
|
|
sl@0
|
654 |
SCnvConversionData::SOneDirectionData::SRange* unicodeToForeignDataRangeArray=REINTERPRET_CAST(SCnvConversionData::SOneDirectionData::SRange*, aWorkingMemory+numberOfBytesOfWorkingMemoryUsed);
|
|
sl@0
|
655 |
numberOfBytesOfWorkingMemoryUsed+=(numberOfUnicodeToForeignDataRanges*sizeof(SCnvConversionData::SOneDirectionData::SRange));
|
|
sl@0
|
656 |
__ASSERT_ALWAYS(numberOfBytesOfWorkingMemoryUsed<=KNumberOfBytesOfWorkingMemory, Panic(EPanicTooManyBytesOfWorkingMemoryUsed2));
|
|
sl@0
|
657 |
aCompleteGb18030_2byteConversionData.iUnicodeToForeignData.iRangeArray=unicodeToForeignDataRangeArray;
|
|
sl@0
|
658 |
Mem::Copy(unicodeToForeignDataRangeArray, gb18030_diff_gb2312ConversionData.iUnicodeToForeignData.iRangeArray, gb18030_diff_gb2312ConversionData.iUnicodeToForeignData.iNumberOfRanges*sizeof(SCnvConversionData::SOneDirectionData::SRange));
|
|
sl@0
|
659 |
Mem::Copy(unicodeToForeignDataRangeArray + gb18030_diff_gb2312ConversionData.iUnicodeToForeignData.iNumberOfRanges, gb2312ConversionData.iUnicodeToForeignData.iRangeArray, gb2312ConversionData.iUnicodeToForeignData.iNumberOfRanges*sizeof(SCnvConversionData::SOneDirectionData::SRange));
|
|
sl@0
|
660 |
Mem::Copy(unicodeToForeignDataRangeArray + gb18030_diff_gb2312ConversionData.iUnicodeToForeignData.iNumberOfRanges + gb2312ConversionData.iUnicodeToForeignData.iNumberOfRanges, gb18030_diff_gbkConversionData.iUnicodeToForeignData.iRangeArray, gb18030_diff_gbkConversionData.iUnicodeToForeignData.iNumberOfRanges*sizeof(SCnvConversionData::SOneDirectionData::SRange));
|
|
sl@0
|
661 |
Mem::Copy(unicodeToForeignDataRangeArray + gb18030_diff_gb2312ConversionData.iUnicodeToForeignData.iNumberOfRanges + gb2312ConversionData.iUnicodeToForeignData.iNumberOfRanges + gb18030_diff_gbkConversionData.iUnicodeToForeignData.iNumberOfRanges, gbkConversionData.iUnicodeToForeignData.iRangeArray, gbkConversionData.iUnicodeToForeignData.iNumberOfRanges*sizeof(SCnvConversionData::SOneDirectionData::SRange));
|
|
sl@0
|
662 |
}
|
|
sl@0
|
663 |
|
|
sl@0
|
664 |
|
|
sl@0
|
665 |
TInt CGB18030ConverterImpl::ConvertFromUnicode(
|
|
sl@0
|
666 |
CCnvCharacterSetConverter::TEndianness aDefaultEndiannessOfForeignCharacters,
|
|
sl@0
|
667 |
const TDesC8& aReplacementForUnconvertibleUnicodeCharacters,
|
|
sl@0
|
668 |
TDes8& aForeign,
|
|
sl@0
|
669 |
const TDesC16& aUnicode,
|
|
sl@0
|
670 |
CCnvCharacterSetConverter::TArrayOfAscendingIndices& aIndicesOfUnconvertibleCharacters)
|
|
sl@0
|
671 |
{
|
|
sl@0
|
672 |
TFixedArray<CnvUtilities::SCharacterSet, 3> characterSets;
|
|
sl@0
|
673 |
|
|
sl@0
|
674 |
// step 1) gb18030-2byte
|
|
sl@0
|
675 |
characterSets[0].iConversionData = completeGb18030_2byteConversionData;
|
|
sl@0
|
676 |
characterSets[0].iConvertFromIntermediateBufferInPlace = Step12DummyConvertFromIntermediateBufferInPlace;
|
|
sl@0
|
677 |
characterSets[0].iEscapeSequence = &KNullDesC8;
|
|
sl@0
|
678 |
|
|
sl@0
|
679 |
// step 2) gb18030-4byte BMP
|
|
sl@0
|
680 |
characterSets[1].iConversionData = &CnvGb18030_4byte::ConversionData();
|
|
sl@0
|
681 |
characterSets[1].iConvertFromIntermediateBufferInPlace = Step12DummyConvertFromIntermediateBufferInPlace;
|
|
sl@0
|
682 |
characterSets[1].iEscapeSequence = &KNullDesC8;
|
|
sl@0
|
683 |
|
|
sl@0
|
684 |
// step 3) gb18030-4byte non-BMP
|
|
sl@0
|
685 |
characterSets[2].iConversionData = &step3ConversionData;
|
|
sl@0
|
686 |
characterSets[2].iConvertFromIntermediateBufferInPlace = Step3ConvertFromIntermediateBufferInPlace;
|
|
sl@0
|
687 |
characterSets[2].iEscapeSequence = &KNullDesC8;
|
|
sl@0
|
688 |
|
|
sl@0
|
689 |
return CnvUtilities::ConvertFromUnicode(aDefaultEndiannessOfForeignCharacters, aReplacementForUnconvertibleUnicodeCharacters, aForeign, aUnicode, aIndicesOfUnconvertibleCharacters, characterSets.Array());
|
|
sl@0
|
690 |
}
|
|
sl@0
|
691 |
|
|
sl@0
|
692 |
|
|
sl@0
|
693 |
TInt CGB18030ConverterImpl::ConvertToUnicode(
|
|
sl@0
|
694 |
CCnvCharacterSetConverter::TEndianness aDefaultEndiannessOfForeignCharacters,
|
|
sl@0
|
695 |
TDes16& aUnicode,
|
|
sl@0
|
696 |
const TDesC8& aForeign,
|
|
sl@0
|
697 |
TInt& /*aState*/,
|
|
sl@0
|
698 |
TInt& aNumberOfUnconvertibleCharacters,
|
|
sl@0
|
699 |
TInt& aIndexOfFirstByteOfFirstUnconvertibleCharacter)
|
|
sl@0
|
700 |
{
|
|
sl@0
|
701 |
TFixedArray<CnvUtilities::SMethod, 4> methods;
|
|
sl@0
|
702 |
// step 0) gb2312-1byte
|
|
sl@0
|
703 |
methods[0].iNumberOfBytesAbleToConvert = Step0NumberOfBytesAbleToConvertToUnicode;
|
|
sl@0
|
704 |
methods[0].iConvertToIntermediateBufferInPlace = Step012DummyConvertToIntermediateBufferInPlace;
|
|
sl@0
|
705 |
methods[0].iConversionData = &CnvGb2312::ConversionData(); //only use one byte part
|
|
sl@0
|
706 |
methods[0].iNumberOfBytesPerCharacter = 1;
|
|
sl@0
|
707 |
methods[0].iNumberOfCoreBytesPerCharacter = 1;
|
|
sl@0
|
708 |
|
|
sl@0
|
709 |
// step 1) gb18030-2byte
|
|
sl@0
|
710 |
methods[1].iNumberOfBytesAbleToConvert = Step1NumberOfBytesAbleToConvertToUnicode;
|
|
sl@0
|
711 |
methods[1].iConvertToIntermediateBufferInPlace = Step012DummyConvertToIntermediateBufferInPlace;
|
|
sl@0
|
712 |
methods[1].iConversionData = completeGb18030_2byteConversionData;
|
|
sl@0
|
713 |
methods[1].iNumberOfBytesPerCharacter = 2;
|
|
sl@0
|
714 |
methods[1].iNumberOfCoreBytesPerCharacter = 2;
|
|
sl@0
|
715 |
|
|
sl@0
|
716 |
// step 2) gb18030 4-byte BMP
|
|
sl@0
|
717 |
methods[2].iNumberOfBytesAbleToConvert = Step2NumberOfBytesAbleToConvertToUnicode;
|
|
sl@0
|
718 |
methods[2].iConvertToIntermediateBufferInPlace = Step012DummyConvertToIntermediateBufferInPlace;
|
|
sl@0
|
719 |
methods[2].iConversionData = &CnvGb18030_4byte::ConversionData();
|
|
sl@0
|
720 |
methods[2].iNumberOfBytesPerCharacter = 4;
|
|
sl@0
|
721 |
methods[2].iNumberOfCoreBytesPerCharacter = 4;
|
|
sl@0
|
722 |
|
|
sl@0
|
723 |
// step 3) gb18030 4-byte non-BMP
|
|
sl@0
|
724 |
methods[3].iNumberOfBytesAbleToConvert = Step3NumberOfBytesAbleToConvertToUnicode;
|
|
sl@0
|
725 |
methods[3].iConvertToIntermediateBufferInPlace = Step3ConvertToIntermediateBufferInPlace;
|
|
sl@0
|
726 |
methods[3].iConversionData = &step3ConversionData;
|
|
sl@0
|
727 |
methods[3].iNumberOfBytesPerCharacter = 4;
|
|
sl@0
|
728 |
methods[3].iNumberOfCoreBytesPerCharacter = 4;
|
|
sl@0
|
729 |
|
|
sl@0
|
730 |
return CnvUtilities::ConvertToUnicodeFromHeterogeneousForeign(aDefaultEndiannessOfForeignCharacters, aUnicode, aForeign, aNumberOfUnconvertibleCharacters, aIndexOfFirstByteOfFirstUnconvertibleCharacter, methods.Array());
|
|
sl@0
|
731 |
}
|
|
sl@0
|
732 |
|
|
sl@0
|
733 |
TBool CGB18030ConverterImpl::IsInThisCharacterSetL(
|
|
sl@0
|
734 |
TBool& aSetToTrue,
|
|
sl@0
|
735 |
TInt& aConfidenceLevel,
|
|
sl@0
|
736 |
const TDesC8& aSample)
|
|
sl@0
|
737 |
{
|
|
sl@0
|
738 |
aSetToTrue = ETrue;
|
|
sl@0
|
739 |
return CnvGb2312::IsCharGBBased(aConfidenceLevel, aSample);
|
|
sl@0
|
740 |
}
|
|
sl@0
|
741 |
|
|
sl@0
|
742 |
CGB18030ConverterImpl* CGB18030ConverterImpl::NewL()
|
|
sl@0
|
743 |
{
|
|
sl@0
|
744 |
CGB18030ConverterImpl* self = new(ELeave) CGB18030ConverterImpl();
|
|
sl@0
|
745 |
CleanupStack::PushL(self);
|
|
sl@0
|
746 |
self->ConstructL();
|
|
sl@0
|
747 |
CleanupStack::Pop(); // self
|
|
sl@0
|
748 |
return self;
|
|
sl@0
|
749 |
}
|
|
sl@0
|
750 |
|
|
sl@0
|
751 |
CGB18030ConverterImpl::~CGB18030ConverterImpl()
|
|
sl@0
|
752 |
{
|
|
sl@0
|
753 |
if (workingMemory)
|
|
sl@0
|
754 |
delete[] workingMemory;
|
|
sl@0
|
755 |
if (completeGb18030_2byteConversionData)
|
|
sl@0
|
756 |
delete completeGb18030_2byteConversionData;
|
|
sl@0
|
757 |
}
|
|
sl@0
|
758 |
|
|
sl@0
|
759 |
CGB18030ConverterImpl::CGB18030ConverterImpl()
|
|
sl@0
|
760 |
{
|
|
sl@0
|
761 |
}
|
|
sl@0
|
762 |
|
|
sl@0
|
763 |
TInt CGB18030ConverterImpl::ConstructL()
|
|
sl@0
|
764 |
{
|
|
sl@0
|
765 |
completeGb18030_2byteConversionData = new (ELeave)SCnvConversionData;
|
|
sl@0
|
766 |
CleanupStack::PushL(completeGb18030_2byteConversionData);
|
|
sl@0
|
767 |
workingMemory = new (ELeave) TUint8[KNumberOfBytesOfWorkingMemory]; //1040 bytes
|
|
sl@0
|
768 |
CleanupStack::Pop(); // completeGb18030_2byteConversionData
|
|
sl@0
|
769 |
SetUpCompleteGb18030_2byteConversionData(*completeGb18030_2byteConversionData, workingMemory);
|
|
sl@0
|
770 |
return 1;
|
|
sl@0
|
771 |
}
|
|
sl@0
|
772 |
|
|
sl@0
|
773 |
const TImplementationProxy ImplementationTable[] =
|
|
sl@0
|
774 |
{
|
|
sl@0
|
775 |
IMPLEMENTATION_PROXY_ENTRY(0x10287038,CGB18030ConverterImpl::NewL)
|
|
sl@0
|
776 |
};
|
|
sl@0
|
777 |
|
|
sl@0
|
778 |
EXPORT_C const TImplementationProxy* ImplementationGroupProxy(TInt& aTableCount)
|
|
sl@0
|
779 |
{
|
|
sl@0
|
780 |
aTableCount = sizeof(ImplementationTable) / sizeof(TImplementationProxy);
|
|
sl@0
|
781 |
|
|
sl@0
|
782 |
return ImplementationTable;
|
|
sl@0
|
783 |
}
|
|
sl@0
|
784 |
|