|
1 /* |
|
2 * Copyright (c) 1997-2008 Nokia Corporation and/or its subsidiary(-ies). |
|
3 * All rights reserved. |
|
4 * This component and the accompanying materials are made available |
|
5 * under the terms of "Eclipse Public License v1.0" |
|
6 * which accompanies this distribution, and is available |
|
7 * at the URL "http://www.eclipse.org/legal/epl-v10.html". |
|
8 * |
|
9 * Initial Contributors: |
|
10 * Nokia Corporation - initial contribution. |
|
11 * |
|
12 * Contributors: |
|
13 * |
|
14 * Description: |
|
15 * |
|
16 */ |
|
17 |
|
18 |
|
19 |
|
20 #if !defined(__CHARCONV_H__) |
|
21 #define __CHARCONV_H__ |
|
22 |
|
23 #if !defined(__E32STD_H__) |
|
24 #include <e32std.h> |
|
25 #endif |
|
26 |
|
27 #if !defined(__E32BASE_H__) |
|
28 #include <e32base.h> |
|
29 #endif |
|
30 |
|
31 /** |
|
32 The maximum length in bytes of the replacement text for unconvertible Unicode |
|
33 characters (=50) (see CCnvCharacterSetConverter::SetReplacementForUnconvertibleUnicodeCharactersL()). |
|
34 @publishedAll |
|
35 @released |
|
36 */ |
|
37 const TInt KMaximumLengthOfReplacementForUnconvertibleUnicodeCharacters=50; |
|
38 |
|
39 /** |
|
40 UTF-7 |
|
41 @publishedAll |
|
42 @released |
|
43 */ |
|
44 const TUint KCharacterSetIdentifierUtf7=0x1000582c; |
|
45 /** |
|
46 UTF-8 |
|
47 @publishedAll |
|
48 @released |
|
49 */ |
|
50 const TUint KCharacterSetIdentifierUtf8=0x1000582d; |
|
51 /** |
|
52 IMAP UTF-7 |
|
53 @publishedAll |
|
54 @released |
|
55 */ |
|
56 const TUint KCharacterSetIdentifierImapUtf7=0x1000582e; |
|
57 /** |
|
58 Java UTF-8 |
|
59 @publishedAll |
|
60 @released |
|
61 */ |
|
62 const TUint KCharacterSetIdentifierJavaConformantUtf8=0x1000582f; |
|
63 /** |
|
64 Code Page 1252 |
|
65 @publishedAll |
|
66 @released |
|
67 */ |
|
68 const TUint KCharacterSetIdentifierCodePage1252=0x100012b6; |
|
69 /** |
|
70 ISO 8859-1 |
|
71 @publishedAll |
|
72 @released |
|
73 */ |
|
74 const TUint KCharacterSetIdentifierIso88591=0x10003b10; |
|
75 /** |
|
76 ISO 8859-2 |
|
77 @publishedAll |
|
78 @released |
|
79 */ |
|
80 const TUint KCharacterSetIdentifierIso88592=0x1000507e; |
|
81 /** |
|
82 ISO 8859-3 |
|
83 @publishedAll |
|
84 @released |
|
85 */ |
|
86 const TUint KCharacterSetIdentifierIso88593=0x10008a28; |
|
87 /** |
|
88 ISO 8859-4 |
|
89 @publishedAll |
|
90 @released |
|
91 */ |
|
92 const TUint KCharacterSetIdentifierIso88594=0x1000507f; |
|
93 /** |
|
94 ISO 8859-5 |
|
95 @publishedAll |
|
96 @released |
|
97 */ |
|
98 const TUint KCharacterSetIdentifierIso88595=0x10005080; |
|
99 /** |
|
100 ISO 8859-6 |
|
101 @publishedAll |
|
102 @released |
|
103 */ |
|
104 const TUint KCharacterSetIdentifierIso88596=0x10008a29; |
|
105 /** |
|
106 ISO 8859-7 |
|
107 @publishedAll |
|
108 @released |
|
109 */ |
|
110 const TUint KCharacterSetIdentifierIso88597=0x10005081; |
|
111 /** |
|
112 ISO 8859-8 |
|
113 @publishedAll |
|
114 @released |
|
115 */ |
|
116 const TUint KCharacterSetIdentifierIso88598=0x10008a2a; |
|
117 /** |
|
118 ISO 8859-9 |
|
119 @publishedAll |
|
120 @released |
|
121 */ |
|
122 const TUint KCharacterSetIdentifierIso88599=0x10005082; |
|
123 /** |
|
124 ISO 8859-10 |
|
125 @publishedAll |
|
126 @released |
|
127 */ |
|
128 const TUint KCharacterSetIdentifierIso885910=0x10008a2b; |
|
129 /** |
|
130 ISO 8859-13 |
|
131 @publishedAll |
|
132 @released |
|
133 */ |
|
134 const TUint KCharacterSetIdentifierIso885913=0x10008a2c; |
|
135 /** |
|
136 ISO 8859-14 |
|
137 @publishedAll |
|
138 @released |
|
139 */ |
|
140 const TUint KCharacterSetIdentifierIso885914=0x10008a2d; |
|
141 /** |
|
142 ISO 8859-15 |
|
143 @publishedAll |
|
144 @released |
|
145 */ |
|
146 const TUint KCharacterSetIdentifierIso885915=0x10008a2e; |
|
147 /** |
|
148 ASCII |
|
149 @publishedAll |
|
150 @released |
|
151 */ |
|
152 const TUint KCharacterSetIdentifierAscii=0x10004cc6; |
|
153 /** |
|
154 SMS 7-bit |
|
155 @publishedAll |
|
156 @released |
|
157 */ |
|
158 const TUint KCharacterSetIdentifierSms7Bit=0x100053ab; |
|
159 /** |
|
160 GB 2312 |
|
161 @publishedAll |
|
162 @released |
|
163 */ |
|
164 const TUint KCharacterSetIdentifierGb2312=0x10000fbe; |
|
165 /** |
|
166 HZ-GB-2312 |
|
167 @publishedAll |
|
168 @released |
|
169 */ |
|
170 const TUint KCharacterSetIdentifierHz=0x10006065; |
|
171 /** |
|
172 GB 12345 |
|
173 @publishedAll |
|
174 @released |
|
175 */ |
|
176 const TUint KCharacterSetIdentifierGb12345=0x1000401a; |
|
177 /** |
|
178 GBK |
|
179 @publishedAll |
|
180 @released |
|
181 */ |
|
182 const TUint KCharacterSetIdentifierGbk=0x10003ecb; |
|
183 /** |
|
184 Big 5 |
|
185 @publishedAll |
|
186 @released |
|
187 */ |
|
188 const TUint KCharacterSetIdentifierBig5=0x10000fbf; |
|
189 /** |
|
190 Shift-JIS |
|
191 @publishedAll |
|
192 @released |
|
193 */ |
|
194 const TUint KCharacterSetIdentifierShiftJis=0x10000fbd; |
|
195 /** |
|
196 ISO-2022-JP |
|
197 @publishedAll |
|
198 @released |
|
199 */ |
|
200 const TUint KCharacterSetIdentifierIso2022Jp=0x100066a0; |
|
201 /** |
|
202 ISO-2022-JP-1 |
|
203 @publishedAll |
|
204 @released |
|
205 */ |
|
206 const TUint KCharacterSetIdentifierIso2022Jp1=0x100066a3; |
|
207 /** |
|
208 JIS Encoding |
|
209 @publishedAll |
|
210 @released |
|
211 */ |
|
212 const TUint KCharacterSetIdentifierJis=0x10006066; |
|
213 /** |
|
214 EUC-JP |
|
215 @publishedAll |
|
216 @released |
|
217 */ |
|
218 const TUint KCharacterSetIdentifierEucJpPacked=0x10006067; |
|
219 |
|
220 /** |
|
221 JP5 |
|
222 @publishedAll |
|
223 @released |
|
224 */ |
|
225 const TUint KCharacterSetIdentifierJ5=0x1020D408; |
|
226 const TUint KCharacterSetIdentifierCP850=0x102825AD; |
|
227 |
|
228 const TUint KCharacterSetIdentifierUnicodeLittle=0x101f3fae; //Little Endian Unicode |
|
229 const TUint KCharacterSetIdentifierUnicodeBig=0x101f4052; // Big Endian Unicode |
|
230 const TUint KCharacterSetIdentifierUcs2=0x101ff492; |
|
231 |
|
232 /** |
|
233 Extended SMS 7-bit (not supported before v9.5) |
|
234 @publishedAll |
|
235 @released |
|
236 */ |
|
237 const TUint KCharacterSetIdentifierExtendedSms7Bit=0x102863FD; |
|
238 |
|
239 /** |
|
240 Turkish |
|
241 @publishedAll |
|
242 @released |
|
243 */ |
|
244 const TUint KCharacterSetIdentifierTurkishSingleSms7Bit=0x102863FE; |
|
245 const TUint KCharacterSetIdentifierTurkishLockingSms7Bit=0x102863FF; |
|
246 const TUint KCharacterSetIdentifierTurkishLockingAndSingleSms7Bit=0x10286400; |
|
247 |
|
248 /** |
|
249 Portuguese |
|
250 @publishedAll |
|
251 @released |
|
252 */ |
|
253 const TUint KCharacterSetIdentifierPortugueseSingleSms7Bit=0x10286407; |
|
254 const TUint KCharacterSetIdentifierPortugueseLockingSms7Bit=0x10286408; |
|
255 const TUint KCharacterSetIdentifierPortugueseLockingAndSingleSms7Bit=0x10286409; |
|
256 |
|
257 /** |
|
258 Spanish |
|
259 @publishedAll |
|
260 @released |
|
261 */ |
|
262 const TUint KCharacterSetIdentifierSpanishSingleSms7Bit=0x1028640A; |
|
263 |
|
264 /** |
|
265 Shift-JIS with Pictograph |
|
266 @publishedAll |
|
267 @released |
|
268 */ |
|
269 const TUint KCharacterSetIdentifierShiftJisDirectmap=0x101F8691; |
|
270 |
|
271 /** |
|
272 EUC-JP with direct mapped pictograph |
|
273 @publishedAll |
|
274 @released |
|
275 */ |
|
276 const TUint KCharacterSetIdentifierEucJpDirectmap=0x101F86A6; |
|
277 // note that other character sets than those listed above may be available at run-time, and also that none of the above are necessarily available at run-time |
|
278 |
|
279 struct SCnvConversionData; |
|
280 class CDeepDestructingArrayOfCharactersSets; |
|
281 class CFileReader; |
|
282 class CStandardNamesAndMibEnums; |
|
283 class RFs; |
|
284 class CCharsetCnvCache; |
|
285 /** |
|
286 Converts text between Unicode and other character sets. |
|
287 |
|
288 The first stage of the conversion is to specify the non-Unicode character |
|
289 set being converted to or from. This is done by calling one of the overloads |
|
290 of PrepareToConvertToOrFromL(). |
|
291 |
|
292 The second stage is to convert the text, using one of the overloads of |
|
293 ConvertFromUnicode() or ConvertToUnicode(). |
|
294 |
|
295 Where possible the first documented overload of PrepareToConvertToOrFromL() |
|
296 should be used because the second overload panics if the specified character |
|
297 set is not available: the first overload simply returns whether the character |
|
298 set is available or not available. However if the conversions are to be |
|
299 performed often, or if the user must select the character set for the |
|
300 conversion from a list, the second overload may be more appropriate. |
|
301 |
|
302 The first overload is less efficient than the second, because it searches |
|
303 through the file system for the selected character set every time it is invoked. |
|
304 The second overload searches through an array of all available character sets. |
|
305 In this method, the file system need only be searched once - when |
|
306 CreateArrayOfCharacterSetsAvailableLC() or |
|
307 CreateArrayOfCharacterSetsAvailableL() is used to create the array. |
|
308 |
|
309 The conversion functions allow users of this class to perform partial |
|
310 conversions on an input descriptor, handling the situation where the input |
|
311 descriptor is truncated mid way through a multi-byte character. This means |
|
312 that you do not have to guess how big to make the output descriptor for a |
|
313 given input descriptor, you can simply do the conversion in a loop using a |
|
314 small output descriptor. The ability to handle truncated descriptors also |
|
315 allows users of the class to convert information received in chunks from an |
|
316 external source. |
|
317 |
|
318 The class also provides a number of utility functions. |
|
319 @publishedAll |
|
320 @released |
|
321 */ |
|
322 class CCnvCharacterSetConverter : public CBase |
|
323 { |
|
324 public: |
|
325 /** Indicates whether a character set is available or unavailable |
|
326 for conversion. Used by the second overload of |
|
327 PrepareToConvertToOrFromL(). */ |
|
328 enum TAvailability |
|
329 { |
|
330 /** The requested character set can be converted. */ |
|
331 EAvailable, |
|
332 /** The requested character set cannot be converted. */ |
|
333 ENotAvailable |
|
334 }; |
|
335 |
|
336 /** Conversion error flags. At this stage there is only one error |
|
337 flag- others may be added in the future. */ |
|
338 enum TError |
|
339 { |
|
340 /** The input descriptor contains a single corrupt character. This |
|
341 might occur when the input descriptor only contains some of the bytes |
|
342 of a single multi-byte character. */ |
|
343 EErrorIllFormedInput=KErrCorrupt |
|
344 }; |
|
345 |
|
346 /** Specifies the default endian-ness of the current character set. |
|
347 Used by SetDefaultEndiannessOfForeignCharacters(). */ |
|
348 enum TEndianness |
|
349 { |
|
350 /** The character set is big-endian. */ |
|
351 ELittleEndian, |
|
352 /** The character set is little-endian. */ |
|
353 EBigEndian |
|
354 }; |
|
355 |
|
356 /** Downgrade for line and paragraph separators */ |
|
357 enum TDowngradeForExoticLineTerminatingCharacters |
|
358 { |
|
359 /** Paragraph/line separators should be downgraded (if necessary) |
|
360 into carriage return and line feed pairs. */ |
|
361 EDowngradeExoticLineTerminatingCharactersToCarriageReturnLineFeed, |
|
362 /** Paragraph/line separators should be downgraded (if necessary) |
|
363 into a line feed only. */ |
|
364 EDowngradeExoticLineTerminatingCharactersToJustLineFeed |
|
365 }; |
|
366 |
|
367 /** Output flag used to indicate whether or not a character in the source |
|
368 descriptor is the first half of a surrogate pair, but is the last |
|
369 character in the descriptor to convert. |
|
370 |
|
371 Note: This enumeration can be used in the DoConvertToUnicode() and |
|
372 DoConvertFromUnicode() functions. These are part of the |
|
373 Character Conversion Plug-in Provider API and are for use by plug-in |
|
374 conversion libraries only. |
|
375 @since 6.0 */ |
|
376 enum |
|
377 { |
|
378 /** Appends the converted text to the output descriptor.*/ |
|
379 EInputConversionFlagAppend =0x00010000, |
|
380 /** By default, when the input descriptor passed to DoConvertFromUnicode() |
|
381 or DoConvertToUnicode() consists of nothing but a truncated sequence, |
|
382 the error-code EErrorIllFormedInput is returned. |
|
383 If this behaviour is undesirable, the input flag |
|
384 EInputConversionFlagAllowTruncatedInputNotEvenPartlyConsumable |
|
385 should be set. */ |
|
386 EInputConversionFlagAllowTruncatedInputNotEvenPartlyConsumable =0x00020000, |
|
387 /** Stops converting when the first unconvertible character is reached. */ |
|
388 EInputConversionFlagStopAtFirstUnconvertibleCharacter =0x00040000, |
|
389 /** Appends the default character set Escape sequence at end of converted text */ |
|
390 EInputConversionFlagMustEndInDefaultCharacterSet =0x00080000, |
|
391 /*defect fix: INC053609; According to RFC1468 we can assume the line starts |
|
392 in ASCII so there is no need to always insert an escape sequence*/ |
|
393 EInputConversionFlagAssumeStartInDefaultCharacterSet =0x00100000 |
|
394 }; |
|
395 enum |
|
396 { |
|
397 /** Indicates whether or not the source descriptor ends in a truncated |
|
398 sequence, e.g. the first half only of a surrogate pair. */ |
|
399 EOutputConversionFlagInputIsTruncated =0x01000000 |
|
400 }; |
|
401 |
|
402 /** Initial value for the state argument in a set of related calls to |
|
403 ConvertToUnicode(). */ |
|
404 enum {KStateDefault=0}; |
|
405 enum |
|
406 { |
|
407 /** The lowest confidence value for a character set accepted by |
|
408 Autodetect*/ |
|
409 ELowestThreshold = 25 |
|
410 }; |
|
411 |
|
412 /** Stores information about a non-Unicode character set. The information |
|
413 is used to locate the conversion information required by |
|
414 ConvertFromUnicode() and ConvertToUnicode(). |
|
415 |
|
416 An array of these structs that contain all available character sets |
|
417 can be generated by CreateArrayOfCharacterSetsAvailableLC() and |
|
418 CreateArrayOfCharacterSetsAvailableL(), and is used by one of the |
|
419 overloads of PrepareToConvertToOrFromL(). */ |
|
420 struct SCharacterSet |
|
421 { |
|
422 /** Gets the character sets UID. |
|
423 |
|
424 @return The UID of the character set. */ |
|
425 inline TUint Identifier() const {return iIdentifier;} |
|
426 |
|
427 /** Tests whether a filename given by the function SCharacterSet::Name() |
|
428 is a real file name (i.e. conversion is provided by a plug in DLL), or |
|
429 just the character set name (i.e. conversion is built into Symbian OS). |
|
430 |
|
431 Note: If the function returns ETrue then the path and filename can be |
|
432 parsed using TParse or TParsePtrC functions to obtain just the filename. |
|
433 |
|
434 @return ETrue if the name is a real filename. EFalse if it is just the |
|
435 character set name. */ |
|
436 inline TBool NameIsFileName() const {return iFlags&EFlagNameIsFileName;} |
|
437 |
|
438 /** Gets the full path and filename of the DLL which implements |
|
439 conversion for the character set. |
|
440 |
|
441 If the character set is one for which conversion is built into Symbian |
|
442 OS rather than implemented by a plug in DLL, the function just returns |
|
443 the name of the character set. The NameIsFileName() function can be |
|
444 used to determine whether or not it is legal to create a TParsePtrC |
|
445 object over the descriptor returned by Name(). |
|
446 |
|
447 Notes: |
|
448 |
|
449 The name returned cannot be treated as an Internet-standard name, it |
|
450 is locale-independent and should be mapped to the locale-dependent name |
|
451 by software at a higher level before being shown to the user. Conversion |
|
452 from Internet-standard names of character sets to the UID identifiers |
|
453 is provided by the member function |
|
454 ConvertStandardNameOfCharacterSetToIdentifierL(). |
|
455 |
|
456 Typically, to find the user-displayable name (as opposed to the |
|
457 internet-standard name) of a character set, you would do something |
|
458 like this: |
|
459 |
|
460 @code |
|
461 const CCnvCharacterSetConverter::SCharacterSet& characterSet=...; |
|
462 const TPtrC userDisplayable(characterSet.NameIsFileName()? TParsePtrC(characterSet.Name()).Name(): |
|
463 characterSet.Name()); |
|
464 @endcode |
|
465 |
|
466 @return Full path and filename of the character set converter plug in |
|
467 DLL, or just the name of the character set. */ |
|
468 inline TPtrC Name() const {return *iName;} |
|
469 private: |
|
470 enum |
|
471 { |
|
472 EFlagNameIsFileName =0x00000001, |
|
473 EFlagFileIsConversionPlugInLibrary =0x00000002 |
|
474 }; |
|
475 private: |
|
476 inline TBool FileIsConversionPlugInLibrary() const {return iFlags&EFlagFileIsConversionPlugInLibrary;} |
|
477 private: |
|
478 TUint iIdentifier; |
|
479 TUint iFlags; |
|
480 HBufC* iName; |
|
481 private: |
|
482 friend class CCnvCharacterSetConverter; |
|
483 friend class CDeepDestructingArrayOfCharactersSets; |
|
484 }; //SCharacterSet |
|
485 |
|
486 |
|
487 /** |
|
488 Holds an ascending array of the indices of the characters in the |
|
489 source Unicode text which could not be converted by |
|
490 CCnvCharacterSetConverter::ConvertFromUnicode() into the foreign |
|
491 character set |
|
492 @publishedAll |
|
493 @released |
|
494 */ |
|
495 class TArrayOfAscendingIndices |
|
496 { |
|
497 public: |
|
498 /** The return value of CCnvCharacterSetConverter::AppendIndex(). */ |
|
499 enum TAppendResult |
|
500 { |
|
501 /** The append failed. */ |
|
502 EAppendFailed, |
|
503 /** The append succeeded. */ |
|
504 EAppendSuccessful |
|
505 }; |
|
506 public: |
|
507 /** C++ constructor. The array is initialised to be of length zero. */ |
|
508 inline TArrayOfAscendingIndices() :iArrayOfIndices(0) {} |
|
509 |
|
510 IMPORT_C TAppendResult AppendIndex(TInt aIndex); |
|
511 |
|
512 /** Deletes a single index from the array. |
|
513 |
|
514 @param aIndexOfIndex The index of the index to delete. Must not be |
|
515 negative and must not be greater than the length of the array, or a |
|
516 panic occurs. */ |
|
517 inline void Remove(TInt aIndexOfIndex) {iArrayOfIndices.Delete(aIndexOfIndex, 1);} |
|
518 |
|
519 /** Deletes all indices from the array. */ |
|
520 inline void RemoveAll() {iArrayOfIndices.SetLength(0);} |
|
521 |
|
522 /** Returns the number of indices in the array. |
|
523 |
|
524 @return The number of indices in the array. */ |
|
525 inline TInt NumberOfIndices() const {return iArrayOfIndices.Length();} |
|
526 |
|
527 /** Gets the value of the specified index. |
|
528 |
|
529 @param aIndexOfIndex Index into the array. |
|
530 @return The value of the index. */ |
|
531 inline TInt operator[](TInt aIndexOfIndex) const {return iArrayOfIndices[aIndexOfIndex];} |
|
532 private: |
|
533 enum {KMaximumNumberOfIndices=25}; |
|
534 private: |
|
535 TBuf16<KMaximumNumberOfIndices> iArrayOfIndices; |
|
536 }; |
|
537 public: |
|
538 IMPORT_C static CCnvCharacterSetConverter* NewL(); |
|
539 IMPORT_C static CCnvCharacterSetConverter* NewLC(); |
|
540 IMPORT_C virtual ~CCnvCharacterSetConverter(); |
|
541 IMPORT_C static CArrayFix<SCharacterSet>* CreateArrayOfCharacterSetsAvailableL(RFs& aFileServerSession); |
|
542 IMPORT_C static CArrayFix<SCharacterSet>* CreateArrayOfCharacterSetsAvailableLC(RFs& aFileServerSession); |
|
543 IMPORT_C TUint ConvertStandardNameOfCharacterSetToIdentifierL(const TDesC8& aStandardNameOfCharacterSet, RFs& aFileServerSession); |
|
544 IMPORT_C HBufC8* ConvertCharacterSetIdentifierToStandardNameL(TUint aCharacterSetIdentifier, RFs& aFileServerSession); |
|
545 IMPORT_C TUint ConvertMibEnumOfCharacterSetToIdentifierL(TInt aMibEnumOfCharacterSet, RFs& aFileServerSession); |
|
546 IMPORT_C TInt ConvertCharacterSetIdentifierToMibEnumL(TUint aCharacterSetIdentifier, RFs& aFileServerSession); |
|
547 IMPORT_C void PrepareToConvertToOrFromL(TUint aCharacterSetIdentifier, const CArrayFix<SCharacterSet>& aArrayOfCharacterSetsAvailable, RFs& aFileServerSession); |
|
548 IMPORT_C TAvailability PrepareToConvertToOrFromL(TUint aCharacterSetIdentifier, RFs& aFileServerSession); |
|
549 // the following attribute-setting functions should be called (if at all) after calling PrepareToConvertToOrFromL and before calling ConvertFromUnicode and/or ConvertToUnicode |
|
550 IMPORT_C void SetDefaultEndiannessOfForeignCharacters(TEndianness aEndianness); |
|
551 IMPORT_C void SetDowngradeForExoticLineTerminatingCharacters(TDowngradeForExoticLineTerminatingCharacters aDowngradeForExoticLineTerminatingCharacters); // by default this attribute is set to EDowngradeExoticLineTerminatingCharactersToCarriageReturnLineFeed |
|
552 IMPORT_C void SetReplacementForUnconvertibleUnicodeCharactersL(const TDesC8& aReplacementForUnconvertibleUnicodeCharacters); // must be a single character preceded by its escape sequence (if any), and must be little-endian if the endianness of the character-set is unspecified, otherwise in the same endianness as the character-set |
|
553 |
|
554 // the conversion functions return either one of the TError values above, or the number of unconverted elements left at the end of the input descriptor |
|
555 IMPORT_C TInt ConvertFromUnicode(TDes8& aForeign, const TDesC16& aUnicode) const; |
|
556 IMPORT_C TInt ConvertFromUnicode(TDes8& aForeign, const TDesC16& aUnicode, TInt& aNumberOfUnconvertibleCharacters) const; |
|
557 IMPORT_C TInt ConvertFromUnicode(TDes8& aForeign, const TDesC16& aUnicode, TInt& aNumberOfUnconvertibleCharacters, TInt& aIndexOfFirstUnconvertibleCharacter) const; |
|
558 IMPORT_C TInt ConvertFromUnicode(TDes8& aForeign, const TDesC16& aUnicode, TArrayOfAscendingIndices& aIndicesOfUnconvertibleCharacters) const; |
|
559 IMPORT_C TInt ConvertToUnicode(TDes16& aUnicode, const TDesC8& aForeign, TInt& aState) const; |
|
560 IMPORT_C TInt ConvertToUnicode(TDes16& aUnicode, const TDesC8& aForeign, TInt& aState, TInt& aNumberOfUnconvertibleCharacters) const; |
|
561 IMPORT_C TInt ConvertToUnicode(TDes16& aUnicode, const TDesC8& aForeign, TInt& aState, TInt& aNumberOfUnconvertibleCharacters, TInt& aIndexOfFirstByteOfFirstUnconvertibleCharacter) const; |
|
562 IMPORT_C static void AutoDetectCharacterSetL(TInt& aConfidenceLevel, TUint& aCharacterSetIdentifier, const CArrayFix<SCharacterSet>& aArrayOfCharacterSetsAvailable, const TDesC8& aSample); |
|
563 IMPORT_C void AutoDetectCharSetL(TInt& aConfidenceLevel, TUint& aCharacterSetIdentifier, const CArrayFix<SCharacterSet>& aArrayOfCharacterSetsAvailable, const TDesC8& aSample); |
|
564 IMPORT_C static void ConvertibleToCharacterSetL(TInt& aConfidenceLevel, const TUint aCharacterSetIdentifier,const CArrayFix<SCharacterSet>& aArrayOfCharacterSetsAvailable, const TDesC8& aSample); |
|
565 IMPORT_C void ConvertibleToCharSetL(TInt& aConfidenceLevel, const TUint aCharacterSetIdentifier,const CArrayFix<SCharacterSet>& aArrayOfCharacterSetsAvailable, const TDesC8& aSample); |
|
566 IMPORT_C void SetMaxCacheSize(TInt aSize); |
|
567 // the following functions are only to be called by conversion plug-in libraries |
|
568 IMPORT_C static TInt DoConvertFromUnicode(const SCnvConversionData& aConversionData, TEndianness aDefaultEndiannessOfForeignCharacters, const TDesC8& aReplacementForUnconvertibleUnicodeCharacters, TDes8& aForeign, const TDesC16& aUnicode, TArrayOfAscendingIndices& aIndicesOfUnconvertibleCharacters); |
|
569 IMPORT_C static TInt DoConvertFromUnicode(const SCnvConversionData& aConversionData, TEndianness aDefaultEndiannessOfForeignCharacters, const TDesC8& aReplacementForUnconvertibleUnicodeCharacters, TDes8& aForeign, const TDesC16& aUnicode, TArrayOfAscendingIndices& aIndicesOfUnconvertibleCharacters, TUint& aOutputConversionFlags, TUint aInputConversionFlags); |
|
570 IMPORT_C static TInt DoConvertToUnicode(const SCnvConversionData& aConversionData, TEndianness aDefaultEndiannessOfForeignCharacters, TDes16& aUnicode, const TDesC8& aForeign, TInt& aNumberOfUnconvertibleCharacters, TInt& aIndexOfFirstByteOfFirstUnconvertibleCharacter); |
|
571 IMPORT_C static TInt DoConvertToUnicode(const SCnvConversionData& aConversionData, TEndianness aDefaultEndiannessOfForeignCharacters, TDes16& aUnicode, const TDesC8& aForeign, TInt& aNumberOfUnconvertibleCharacters, TInt& aIndexOfFirstByteOfFirstUnconvertibleCharacter, TUint& aOutputConversionFlags, TUint aInputConversionFlags); |
|
572 IMPORT_C static const SCnvConversionData& AsciiConversionData(); |
|
573 inline TDowngradeForExoticLineTerminatingCharacters GetDowngradeForExoticLineTerminatingCharacters () |
|
574 { |
|
575 return iDowngradeForExoticLineTerminatingCharacters ; |
|
576 } ; |
|
577 |
|
578 private: |
|
579 enum |
|
580 { |
|
581 EStoredFlagOwnsConversionData =0x00000001, |
|
582 EStoredFlagConversionPlugInLibraryIsLoaded =0x00000002 |
|
583 }; |
|
584 enum TCharacterSetSearch |
|
585 { |
|
586 EStopCharacterSetSearch, |
|
587 EContinueCharacterSetSearch |
|
588 }; |
|
589 enum TConversionPlugInFunctionOrdinals |
|
590 { |
|
591 EReplacementForUnconvertibleUnicodeCharacters=1, |
|
592 EConvertFromUnicode=2, |
|
593 EConvertToUnicode=3, |
|
594 EIsInThisCharacterSet=4 |
|
595 }; |
|
596 |
|
597 private: |
|
598 CCnvCharacterSetConverter(); |
|
599 void ConstructL(); |
|
600 static CArrayFix<SCharacterSet>* DoCreateArrayOfCharacterSetsAvailableLC(RFs& aFileServerSession, TUint aIdentifierOfOnlyCharacterSetOfInterest); |
|
601 static TCharacterSetSearch AppendHardCodedCharacterSetIfRequiredL(CArrayFix<SCharacterSet>& aArrayOfCharacterSets, TUint aIdentifierOfOnlyCharacterSetOfInterest, TUint aIdentifierOfHardCodedCharacterSet, const TDesC& aNameOfHardCodedCharacterSet); |
|
602 void ScanForStandardNamesAndMibEnumsL(RFs& aFileServerSession); |
|
603 void ScanForStandardNamesAndMibEnumsROMOnlyL(RFs& aFileServerSession); |
|
604 TAvailability DoPrepareToConvertToOrFromL(TUint aCharacterSetIdentifier, const CArrayFix<SCharacterSet>* aArrayOfCharacterSetsAvailable, RFs& aFileServerSession); |
|
605 static void DeleteConversionData(const SCnvConversionData* aConversionData); |
|
606 static void DeleteConversionData(TAny* aConversionData); |
|
607 static TEndianness EndiannessOfForeignCharacters(const SCnvConversionData& aConversionData, TEndianness aDefaultEndiannessOfForeignCharacters); |
|
608 |
|
609 private: |
|
610 TUint iStoredFlags; |
|
611 TUint iCharacterSetIdentifierOfLoadedConversionData; // 0 or a UID of the loaded plugin |
|
612 const SCnvConversionData* iConversionData; |
|
613 TEndianness iDefaultEndiannessOfForeignCharacters; |
|
614 TDowngradeForExoticLineTerminatingCharacters iDowngradeForExoticLineTerminatingCharacters; |
|
615 TBuf8<KMaximumLengthOfReplacementForUnconvertibleUnicodeCharacters> iReplacementForUnconvertibleUnicodeCharacters; |
|
616 CStandardNamesAndMibEnums* iStandardNamesAndMibEnums; |
|
617 TBool iFullyConstructed; |
|
618 CCharsetCnvCache* iCharsetCnvCache; |
|
619 }; |
|
620 |
|
621 #endif |
|
622 |