|
1 /* |
|
2 * Copyright (c) 2006-2009 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 * Miscellaneous text related utility methods. |
|
16 * |
|
17 */ |
|
18 |
|
19 |
|
20 |
|
21 // ========== INCLUDE FILES ================================ |
|
22 |
|
23 #include <e32std.h> |
|
24 #include <e32base.h> |
|
25 #include <f32file.h> |
|
26 #include <s32file.h> |
|
27 |
|
28 #include <charconv.h> |
|
29 #include <txtrich.h> |
|
30 |
|
31 #include <cmsvattachment.h> |
|
32 #include <cmsvmimeheaders.h> |
|
33 #include <mmsvattachmentmanager.h> |
|
34 |
|
35 #include "msgtextutils.h" |
|
36 |
|
37 // ========== LOCAL CONSTANTS AND MACROS =================== |
|
38 |
|
39 /* Reddy - Moved ot header |
|
40 // Default charsets |
|
41 const TUint KDefaultCharConvCharset = KCharacterSetIdentifierAscii; |
|
42 const TUint KDefaultMIBCharset = KCharacterSetMIBEnumUsAscii; |
|
43 */ |
|
44 |
|
45 const TInt KMaxSampleLengthForAutoDetection = 512; |
|
46 const TInt KCharsetPluginArrayGranularity = 10; |
|
47 |
|
48 const TUint KCharParagraphSeparator = 0x2029; |
|
49 const TUint KCharLineFeed = 0x0a; |
|
50 const TUint KCharCarriageReturn = 0x0d; |
|
51 const TUint KCharAsciiDot = 0x2e; |
|
52 const TUint KCharAsciiMax = 0x7f; |
|
53 |
|
54 const TInt KMaxFileNameLength = 8; // must be at least 4! |
|
55 const TInt KMaxFileExtensionLenght = 5; // includes dot |
|
56 const TInt KMaxFileTotalLength = 12; |
|
57 |
|
58 _LIT8( KReplaceChar8, "_" ); |
|
59 _LIT16( KReplaceChar16, "_" ); |
|
60 |
|
61 // ========== MEMBER FUNCTIONS ============================= |
|
62 |
|
63 |
|
64 // --------------------------------------------------------- |
|
65 // CMsgTextUtils::NewL |
|
66 // --------------------------------------------------------- |
|
67 // |
|
68 EXPORT_C CMsgTextUtils* CMsgTextUtils::NewL( RFs& aFs ) |
|
69 { |
|
70 CMsgTextUtils* data = new ( ELeave ) CMsgTextUtils( aFs ); |
|
71 CleanupStack::PushL( data ); |
|
72 data->ConstructL(); |
|
73 CleanupStack::Pop(); |
|
74 return data; |
|
75 } |
|
76 |
|
77 |
|
78 // --------------------------------------------------------- |
|
79 // CMsgTextUtils::CMsgTextUtils |
|
80 // |
|
81 // Constructor |
|
82 // --------------------------------------------------------- |
|
83 // |
|
84 CMsgTextUtils::CMsgTextUtils( RFs& aFs ) |
|
85 : iFs( aFs ) |
|
86 { |
|
87 } |
|
88 |
|
89 |
|
90 // --------------------------------------------------------- |
|
91 // CMsgTextUtils::ConstructL |
|
92 // --------------------------------------------------------- |
|
93 // |
|
94 void CMsgTextUtils::ConstructL() |
|
95 { |
|
96 // Nothing to do. Reserved for future use. |
|
97 } |
|
98 |
|
99 // --------------------------------------------------------- |
|
100 // CMsgTextUtils::~CMsgTextUtils |
|
101 // |
|
102 // Destructor. |
|
103 // --------------------------------------------------------- |
|
104 // |
|
105 CMsgTextUtils::~CMsgTextUtils() |
|
106 { |
|
107 delete iCharConv; |
|
108 } |
|
109 |
|
110 // --------------------------------------------------------- |
|
111 // CMsgTextUtils::ConvertToBuffer8LC |
|
112 // |
|
113 // --------------------------------------------------------- |
|
114 // |
|
115 EXPORT_C HBufC8* CMsgTextUtils::ConvertToBuffer8LC( |
|
116 const TDesC& aText, |
|
117 TUint aCharacterSetIdentifier ) |
|
118 { |
|
119 TInt origLength = aText.Length(); |
|
120 TInt maxLength = origLength; |
|
121 HBufC8* resultBuffer = HBufC8::NewLC( maxLength ); |
|
122 if ( !iCharConv ) |
|
123 { |
|
124 iCharConv = CCnvCharacterSetConverter::NewL(); |
|
125 } |
|
126 |
|
127 if ( iCharConv->PrepareToConvertToOrFromL( aCharacterSetIdentifier, iFs ) != |
|
128 CCnvCharacterSetConverter::EAvailable ) |
|
129 { |
|
130 User::Leave( KErrNotSupported ); |
|
131 } |
|
132 |
|
133 iCharConv->SetReplacementForUnconvertibleUnicodeCharactersL( KReplaceChar8 ); |
|
134 |
|
135 TBuf8<40> outputBuffer; |
|
136 TPtrC16 remainderOfUnicode( aText ); |
|
137 |
|
138 FOREVER |
|
139 { |
|
140 const TInt doneAll = iCharConv->ConvertFromUnicode( outputBuffer, remainderOfUnicode ); |
|
141 |
|
142 if ( doneAll == CCnvCharacterSetConverter::EErrorIllFormedInput ) |
|
143 { |
|
144 User::Leave( KErrCorrupt ); |
|
145 } |
|
146 else if ( doneAll < 0 ) |
|
147 { |
|
148 // For future expansion of errors |
|
149 User::Leave( KErrGeneral ); |
|
150 } |
|
151 else |
|
152 { // lint |
|
153 } |
|
154 |
|
155 // Make sure outputBuffer fits into resultBuffer |
|
156 while ( resultBuffer->Length() + outputBuffer.Length() > maxLength ) |
|
157 { |
|
158 // Increase resultBuffer length by origLength |
|
159 maxLength += origLength; |
|
160 resultBuffer = resultBuffer->ReAllocL( maxLength ); |
|
161 CleanupStack::Pop(); // resultBuffer |
|
162 CleanupStack::PushL(resultBuffer); |
|
163 } |
|
164 // Append to result |
|
165 resultBuffer->Des().Append( outputBuffer ); |
|
166 |
|
167 if ( doneAll == 0 ) |
|
168 { |
|
169 return resultBuffer; // All converted |
|
170 } |
|
171 |
|
172 remainderOfUnicode.Set( remainderOfUnicode.Right( doneAll )); |
|
173 } |
|
174 } |
|
175 |
|
176 // --------------------------------------------------------- |
|
177 // CMsgTextUtils::ConvertToBuffer16LC |
|
178 // |
|
179 // --------------------------------------------------------- |
|
180 // |
|
181 EXPORT_C HBufC* CMsgTextUtils::ConvertToBuffer16LC( |
|
182 const TDesC& aText, |
|
183 TUint aCharacterSetIdentifier ) |
|
184 { |
|
185 HBufC8* resultBuffer = ConvertToBuffer8LC( aText, aCharacterSetIdentifier ); |
|
186 |
|
187 HBufC* finalresult = HBufC::NewL( resultBuffer->Length() ); |
|
188 finalresult->Des().Copy( *resultBuffer ); |
|
189 CleanupStack::PopAndDestroy(); // resultbuffer |
|
190 CleanupStack::PushL( finalresult ); |
|
191 |
|
192 return finalresult; |
|
193 } |
|
194 |
|
195 // --------------------------------------------------------- |
|
196 // CMsgTextUtils::ConvertToFileL |
|
197 // |
|
198 // --------------------------------------------------------- |
|
199 // |
|
200 EXPORT_C void CMsgTextUtils::ConvertToFileL( |
|
201 const TDesC& aText, |
|
202 RFile& aFile, |
|
203 TUint aCharacterSetIdentifier ) |
|
204 { |
|
205 // Takes ownership of "aFile". |
|
206 RFileWriteStream writer( aFile ); |
|
207 writer.PushL(); |
|
208 |
|
209 if ( !iCharConv ) |
|
210 { |
|
211 iCharConv = CCnvCharacterSetConverter::NewL(); |
|
212 } |
|
213 |
|
214 if ( iCharConv->PrepareToConvertToOrFromL( aCharacterSetIdentifier, iFs ) |
|
215 != CCnvCharacterSetConverter::EAvailable ) |
|
216 { |
|
217 User::Leave( KErrNotSupported ); |
|
218 } |
|
219 |
|
220 iCharConv->SetReplacementForUnconvertibleUnicodeCharactersL( KReplaceChar8 ); |
|
221 |
|
222 TBuf8<128> outputBuffer; |
|
223 TPtrC16 remainderOfUnicodeText( aText ); |
|
224 FOREVER |
|
225 { |
|
226 TInt doneAll = iCharConv->ConvertFromUnicode( |
|
227 outputBuffer, remainderOfUnicodeText ); |
|
228 if ( doneAll == CCnvCharacterSetConverter::EErrorIllFormedInput ) |
|
229 { |
|
230 User::Leave( KErrCorrupt ); |
|
231 } |
|
232 else if ( doneAll < 0 ) // future-proof against "TError" expanding |
|
233 { |
|
234 User::Leave( KErrGeneral ); |
|
235 } |
|
236 else |
|
237 { // lint |
|
238 } |
|
239 |
|
240 writer.WriteL( outputBuffer ); |
|
241 |
|
242 if ( doneAll == 0 ) |
|
243 { |
|
244 // All of aText has been converted and handled |
|
245 writer.CommitL(); |
|
246 writer.Pop(); |
|
247 writer.Close(); |
|
248 return; |
|
249 } |
|
250 remainderOfUnicodeText.Set( remainderOfUnicodeText.Right( doneAll ) ); |
|
251 } |
|
252 } |
|
253 |
|
254 // --------------------------------------------------------- |
|
255 // CMsgTextUtils::CharconvIdToMibIdL |
|
256 // |
|
257 // --------------------------------------------------------- |
|
258 // |
|
259 EXPORT_C TUint CMsgTextUtils::CharconvIdToMibIdL( TUint aCharconvCharsetId ) |
|
260 { |
|
261 // Switch-case is here for performance optimization |
|
262 TUint charset = 0; |
|
263 switch ( aCharconvCharsetId ) |
|
264 { |
|
265 case 0: |
|
266 // Symbian OS native charset |
|
267 charset = KCharacterSetMIBEnumIso10646Ucs2; |
|
268 break; |
|
269 case KCharacterSetIdentifierAscii: |
|
270 charset = KCharacterSetMIBEnumUsAscii; |
|
271 break; |
|
272 case KCharacterSetIdentifierUtf8: |
|
273 charset = KCharacterSetMIBEnumUtf8; |
|
274 break; |
|
275 case KCharacterSetIdentifierIso88591: |
|
276 charset = KCharacterSetMIBEnumISO_8859_1; |
|
277 break; |
|
278 case KCharacterSetIdentifierIso88592: |
|
279 charset = KCharacterSetMIBEnumISO_8859_2; |
|
280 break; |
|
281 case KCharacterSetIdentifierIso88593: |
|
282 charset = KCharacterSetMIBEnumISO_8859_3; |
|
283 break; |
|
284 case KCharacterSetIdentifierIso88594: |
|
285 charset = KCharacterSetMIBEnumISO_8859_4; |
|
286 break; |
|
287 case KCharacterSetIdentifierIso88595: |
|
288 charset = KCharacterSetMIBEnumISO_8859_5; |
|
289 break; |
|
290 case KCharacterSetIdentifierIso88596: |
|
291 charset = KCharacterSetMIBEnumISO_8859_6; |
|
292 break; |
|
293 case KCharacterSetIdentifierIso88597: |
|
294 charset = KCharacterSetMIBEnumISO_8859_7; |
|
295 break; |
|
296 case KCharacterSetIdentifierIso88598: |
|
297 charset = KCharacterSetMIBEnumISO_8859_8; |
|
298 break; |
|
299 case KCharacterSetIdentifierIso88599: |
|
300 charset = KCharacterSetMIBEnumISO_8859_9; |
|
301 break; |
|
302 case KCharacterSetIdentifierIso885910: |
|
303 charset = KCharacterSetMIBEnumISO_8859_10; |
|
304 break; |
|
305 case KCharacterSetIdentifierIso885913: |
|
306 charset = KCharacterSetMIBEnumISO_8859_13; |
|
307 break; |
|
308 case KCharacterSetIdentifierIso885914: |
|
309 charset = KCharacterSetMIBEnumISO_8859_14; |
|
310 break; |
|
311 case KCharacterSetIdentifierIso885915: |
|
312 charset = KCharacterSetMIBEnumISO_8859_15; |
|
313 break; |
|
314 case KCharacterSetIdentifierUtf7: |
|
315 charset = KCharacterSetMIBEnumUtf7; |
|
316 break; |
|
317 case KCharacterSetIdentifierCodePage1252: |
|
318 charset = KCharacterSetMIBEnumCodePage1252; |
|
319 break; |
|
320 // Chinese charsets |
|
321 case KCharacterSetIdentifierGb2312: |
|
322 charset = KCharacterSetMIBEnumGb2312; |
|
323 break; |
|
324 case KCharacterSetIdentifierHz: |
|
325 charset = KCharacterSetMIBEnumHz; |
|
326 break; |
|
327 case KCharacterSetIdentifierGbk: |
|
328 charset = KCharacterSetMIBEnumGbk; |
|
329 break; |
|
330 case KCharacterSetIdentifierBig5: |
|
331 charset = KCharacterSetMIBEnumBig5; |
|
332 break; |
|
333 // Japanese charsets |
|
334 case KCharacterSetIdentifierShiftJis: |
|
335 charset = KCharacterSetMIBEnumShiftJis; |
|
336 break; |
|
337 case KCharacterSetIdentifierIso2022Jp: |
|
338 charset = KCharacterSetMIBEnumIso2022Jp; |
|
339 break; |
|
340 case KCharacterSetIdentifierJis: |
|
341 charset = KCharacterSetMIBEnumJis; |
|
342 break; |
|
343 case KCharacterSetIdentifierEucJpPacked: |
|
344 charset = KCharacterSetMIBEnumEucJpPacked; |
|
345 break; |
|
346 default: |
|
347 { |
|
348 if ( !iCharConv ) |
|
349 { |
|
350 iCharConv = CCnvCharacterSetConverter::NewL(); |
|
351 } |
|
352 charset = iCharConv->ConvertCharacterSetIdentifierToMibEnumL( |
|
353 aCharconvCharsetId, iFs ); |
|
354 if ( charset == 0 ) |
|
355 { |
|
356 charset = KDefaultMIBCharset; |
|
357 } |
|
358 break; |
|
359 } |
|
360 } |
|
361 return charset; |
|
362 } |
|
363 |
|
364 // --------------------------------------------------------- |
|
365 // CMsgTextUtils::MibIdToCharconvIdL |
|
366 // |
|
367 // --------------------------------------------------------- |
|
368 // |
|
369 EXPORT_C TUint CMsgTextUtils::MibIdToCharconvIdL( TUint aMibId ) |
|
370 { |
|
371 // Switch-case is here for performance optimization |
|
372 TUint charset = 0; |
|
373 switch ( aMibId ) |
|
374 { |
|
375 case KCharacterSetMIBEnumIso10646Ucs2: |
|
376 case KCharacterSetMIBEnumUTF16: |
|
377 //no conversion for Unicode |
|
378 charset = 0; |
|
379 break; |
|
380 case KCharacterSetMIBEnumUTF16BE: |
|
381 charset = KCharacterSetIdentifierUnicodeBig; |
|
382 break; |
|
383 case KCharacterSetMIBEnumUTF16LE: |
|
384 charset = KCharacterSetIdentifierUnicodeLittle; |
|
385 break; |
|
386 case KCharacterSetMIBEnumUsAscii: |
|
387 charset = KCharacterSetIdentifierAscii; |
|
388 break; |
|
389 case KCharacterSetMIBEnumUtf8: |
|
390 charset = KCharacterSetIdentifierUtf8; |
|
391 break; |
|
392 case KCharacterSetMIBEnumISO_8859_1: |
|
393 charset = KCharacterSetIdentifierIso88591; |
|
394 break; |
|
395 case KCharacterSetMIBEnumISO_8859_2: |
|
396 charset = KCharacterSetIdentifierIso88592; |
|
397 break; |
|
398 case KCharacterSetMIBEnumISO_8859_3: |
|
399 charset = KCharacterSetIdentifierIso88593; |
|
400 break; |
|
401 case KCharacterSetMIBEnumISO_8859_4: |
|
402 charset = KCharacterSetIdentifierIso88594; |
|
403 break; |
|
404 case KCharacterSetMIBEnumISO_8859_5: |
|
405 charset = KCharacterSetIdentifierIso88595; |
|
406 break; |
|
407 case KCharacterSetMIBEnumISO_8859_6: |
|
408 charset = KCharacterSetIdentifierIso88596; |
|
409 break; |
|
410 case KCharacterSetMIBEnumISO_8859_7: |
|
411 charset = KCharacterSetIdentifierIso88597; |
|
412 break; |
|
413 case KCharacterSetMIBEnumISO_8859_8: |
|
414 charset = KCharacterSetIdentifierIso88598; |
|
415 break; |
|
416 case KCharacterSetMIBEnumISO_8859_9: |
|
417 charset = KCharacterSetIdentifierIso88599; |
|
418 break; |
|
419 case KCharacterSetMIBEnumISO_8859_10: |
|
420 charset = KCharacterSetIdentifierIso885910; |
|
421 break; |
|
422 case KCharacterSetMIBEnumISO_8859_13: |
|
423 charset = KCharacterSetIdentifierIso885913; |
|
424 break; |
|
425 case KCharacterSetMIBEnumISO_8859_14: |
|
426 charset = KCharacterSetIdentifierIso885914; |
|
427 break; |
|
428 case KCharacterSetMIBEnumISO_8859_15: |
|
429 charset = KCharacterSetIdentifierIso885915; |
|
430 break; |
|
431 case KCharacterSetMIBEnumUtf7: |
|
432 charset = KCharacterSetIdentifierUtf7; |
|
433 break; |
|
434 case KCharacterSetMIBEnumCodePage1252: |
|
435 charset = KCharacterSetIdentifierCodePage1252; |
|
436 break; |
|
437 // Chinese charsets |
|
438 case KCharacterSetMIBEnumGb2312: |
|
439 charset = KCharacterSetIdentifierGb2312; |
|
440 break; |
|
441 case KCharacterSetMIBEnumHz: |
|
442 charset = KCharacterSetIdentifierHz; |
|
443 break; |
|
444 case KCharacterSetMIBEnumGbk: |
|
445 charset = KCharacterSetIdentifierGbk; |
|
446 break; |
|
447 case KCharacterSetMIBEnumBig5: |
|
448 charset = KCharacterSetIdentifierBig5; |
|
449 break; |
|
450 // Japanese charsets |
|
451 case KCharacterSetMIBEnumShiftJis: |
|
452 charset = KCharacterSetIdentifierShiftJis; |
|
453 break; |
|
454 case KCharacterSetMIBEnumIso2022Jp: |
|
455 charset = KCharacterSetIdentifierIso2022Jp; |
|
456 break; |
|
457 case KCharacterSetMIBEnumJis: |
|
458 charset = KCharacterSetIdentifierJis; |
|
459 break; |
|
460 case KCharacterSetMIBEnumEucJpPacked: |
|
461 charset = KCharacterSetIdentifierEucJpPacked; |
|
462 break; |
|
463 default: |
|
464 { |
|
465 if ( !iCharConv ) |
|
466 { |
|
467 iCharConv = CCnvCharacterSetConverter::NewL(); |
|
468 } |
|
469 charset = iCharConv->ConvertMibEnumOfCharacterSetToIdentifierL( aMibId, iFs ); |
|
470 if ( charset == 0 ) |
|
471 { |
|
472 charset = KDefaultCharConvCharset; |
|
473 } |
|
474 break; |
|
475 } |
|
476 } |
|
477 return charset; |
|
478 } |
|
479 |
|
480 // --------------------------------------------------------- |
|
481 // ConvertParagraphSeparatorsLC |
|
482 // --------------------------------------------------------- |
|
483 // |
|
484 EXPORT_C HBufC* CMsgTextUtils::ConvertParagraphSeparatorsLC( const TDesC& aText ) |
|
485 { |
|
486 TInt position; |
|
487 TPtrC ptr; |
|
488 |
|
489 TInt numberOfSeparators = 0; |
|
490 |
|
491 position = 0; |
|
492 ptr.Set( aText.Mid( 0 ) ); |
|
493 while ( position != KErrNotFound && position < aText.Length() ) |
|
494 { |
|
495 ptr.Set( ptr.Mid( position ) ); |
|
496 position = ptr.Locate( TChar( KCharParagraphSeparator ) ); |
|
497 if ( position != KErrNotFound ) |
|
498 { |
|
499 numberOfSeparators++; |
|
500 position++; // point past separator just found |
|
501 } |
|
502 } |
|
503 |
|
504 HBufC* convertedText = HBufC::NewLC( aText.Length() + numberOfSeparators ); |
|
505 ptr.Set( aText.Mid( 0 ) ); |
|
506 TInt start = 0; |
|
507 position = aText.Locate( TChar( KCharParagraphSeparator ) ); |
|
508 while ( position != KErrNotFound && start < aText.Length() ) |
|
509 { |
|
510 ptr.Set( aText.Mid( start ) ); |
|
511 position = ptr.Locate( TChar( KCharParagraphSeparator ) ); |
|
512 if ( position != KErrNotFound ) |
|
513 { |
|
514 convertedText->Des().Append( ptr.Left( position ) ); |
|
515 convertedText->Des().Append( TChar( KCharCarriageReturn ) ); |
|
516 convertedText->Des().Append( TChar( KCharLineFeed ) ); |
|
517 start = start + position + 1; // point past separator |
|
518 } |
|
519 } |
|
520 // append what is left after last separator has been found |
|
521 if ( start < aText.Length() ) |
|
522 { |
|
523 convertedText->Des().Append( aText.Mid( start ) ); |
|
524 } |
|
525 |
|
526 return convertedText; |
|
527 } |
|
528 |
|
529 // --------------------------------------------------------- |
|
530 // CMsgTextUtils::TrimAndRemoveNonAlphaDigit |
|
531 // |
|
532 // NOTE: This is intended for small strings. With long |
|
533 // strings if could be more efficient to to seek replacable |
|
534 // chars than to loop thru every char. |
|
535 // --------------------------------------------------------- |
|
536 // |
|
537 EXPORT_C void CMsgTextUtils::TrimAndRemoveNonAlphaDigit( TDes& aString ) |
|
538 { |
|
539 aString.Trim(); |
|
540 for (TInt i = aString.Length(); --i >= 0 ;) |
|
541 { |
|
542 TChar c = (TChar) aString[i]; |
|
543 // Allow dots i.e. "." because they are allowed in URI and |
|
544 // because filename are created from content-location |
|
545 // so this will result to "filename.txt" instead of "filename_txt" |
|
546 if ( aString[i] > KCharAsciiMax || |
|
547 ( aString[i] != KCharAsciiDot && !c.IsAlphaDigit() ) ) |
|
548 { |
|
549 aString.Replace( i, 1, KReplaceChar16 ); |
|
550 } |
|
551 } |
|
552 } |
|
553 |
|
554 // --------------------------------------------------------- |
|
555 // UTF8Size |
|
556 // --------------------------------------------------------- |
|
557 // |
|
558 EXPORT_C TInt CMsgTextUtils::UTF8Size( TPtrC aText ) |
|
559 { |
|
560 TInt count = 0; |
|
561 TInt sizeInBytes = 0; |
|
562 TUint16 charValue; |
|
563 while ( count < aText.Length() ) |
|
564 { |
|
565 charValue = aText[count]; |
|
566 if ( charValue < 0x80 ) |
|
567 { |
|
568 sizeInBytes += 1; |
|
569 } |
|
570 else if ( charValue < 0x800 ) |
|
571 { |
|
572 sizeInBytes += 2; |
|
573 } |
|
574 else //if ( charValue < 0x10000 ) |
|
575 { |
|
576 sizeInBytes += 3; |
|
577 } |
|
578 count++; |
|
579 } |
|
580 return sizeInBytes; |
|
581 } |
|
582 |
|
583 // --------------------------------------------------------- |
|
584 // ConvertLineBreaksL |
|
585 // --------------------------------------------------------- |
|
586 // |
|
587 EXPORT_C void CMsgTextUtils::ConvertLineBreaksL( CRichText& aText, TInt aMode ) |
|
588 { |
|
589 if ( aMode & ECRLFtoLF ) |
|
590 { |
|
591 DoConvertCRLFL( aText ); |
|
592 } |
|
593 } |
|
594 |
|
595 // --------------------------------------------------------- |
|
596 // DoConvertCRLFL |
|
597 // --------------------------------------------------------- |
|
598 // |
|
599 void CMsgTextUtils::DoConvertCRLFL( CRichText& aText ) |
|
600 { |
|
601 TInt i( 0 ); |
|
602 TInt documentLength( aText.DocumentLength() ); |
|
603 |
|
604 while ( i < documentLength ) |
|
605 { |
|
606 if ( aText.Read( i, 1 ).Locate( KCharCarriageReturn ) != KErrNotFound ) |
|
607 { |
|
608 if ( i < documentLength - 1 && |
|
609 aText.Read( i + 1, 1 ).Locate( KCharLineFeed ) != KErrNotFound ) |
|
610 { |
|
611 // "CR+LF" -> "LF" |
|
612 aText.DeleteL( i, 1 ); |
|
613 documentLength--; |
|
614 } |
|
615 } |
|
616 i++; |
|
617 } |
|
618 } |
|
619 |
|
620 // ----------------------------------------------------------------------------- |
|
621 // RecognizeCharSetL |
|
622 // ----------------------------------------------------------------------------- |
|
623 // |
|
624 EXPORT_C TUint CMsgTextUtils::RecognizeCharSetL( RFs& aFs, RFile& aFile ) |
|
625 { |
|
626 TUint charSet( 0 ); |
|
627 |
|
628 HBufC8* sample = HBufC8::NewLC( KMaxSampleLengthForAutoDetection ); |
|
629 TPtr8 sampleDes = sample->Des(); |
|
630 |
|
631 TInt fileSize( 0 ); |
|
632 User::LeaveIfError( aFile.Size( fileSize ) ); |
|
633 User::LeaveIfError( aFile.Read( 0, sampleDes, fileSize > sampleDes.MaxLength() |
|
634 ? sampleDes.MaxLength() |
|
635 : fileSize ) ); |
|
636 |
|
637 |
|
638 // Check for Byte Order Mark (BOM) |
|
639 // U+FEFF ZERO WIDTH NON-BREAKING SPACE |
|
640 // |
|
641 // (from www.unicode.org FAQ) |
|
642 // - FE FF -> UTF-16, big-endian |
|
643 // - FF FE -> UTF-16, little-endian |
|
644 // |
|
645 if ( !sampleDes.Length() || |
|
646 ( sampleDes.Size() >= 2 && |
|
647 ( ( sampleDes[0] == 0xfe && sampleDes[1] == 0xff ) || |
|
648 ( sampleDes[0] == 0xff && sampleDes[1] == 0xfe ) ) ) ) |
|
649 { |
|
650 // Zero means no conversion |
|
651 charSet = 0; |
|
652 } |
|
653 else |
|
654 { |
|
655 const CArrayFix<CCnvCharacterSetConverter::SCharacterSet>* availableSets = |
|
656 CCnvCharacterSetConverter::CreateArrayOfCharacterSetsAvailableLC( aFs ); |
|
657 |
|
658 CArrayFix<CCnvCharacterSetConverter::SCharacterSet>* toDetectSets = |
|
659 new ( ELeave ) CArrayFixFlat<CCnvCharacterSetConverter::SCharacterSet>( KCharsetPluginArrayGranularity ); |
|
660 CleanupStack::PushL( toDetectSets ); |
|
661 |
|
662 const TInt count( availableSets->Count() ); |
|
663 for ( TInt i( 0 ); i < count; i++ ) |
|
664 { |
|
665 switch ( availableSets->At( i ).Identifier() ) |
|
666 { |
|
667 case KCharacterSetIdentifierSms7Bit: |
|
668 // remove Sms7Bit from charset list |
|
669 break; |
|
670 default: |
|
671 toDetectSets->AppendL( availableSets->At( i ) ); |
|
672 break; |
|
673 } |
|
674 } |
|
675 |
|
676 TUint resultCharset( 0 ); |
|
677 TInt confidence( 0 ); |
|
678 CCnvCharacterSetConverter::AutoDetectCharacterSetL( |
|
679 confidence, resultCharset, *toDetectSets, sampleDes ); |
|
680 charSet = resultCharset; |
|
681 |
|
682 CleanupStack::PopAndDestroy( 2 ); // availableSets, toDetectSets |
|
683 } |
|
684 CleanupStack::PopAndDestroy( sample ); |
|
685 TInt seekPos(0); |
|
686 aFile.Seek( ESeekStart, seekPos ); |
|
687 return charSet; |
|
688 } |
|
689 |
|
690 // --------------------------------------------------------- |
|
691 // GetSafeAttachmentNameLC |
|
692 // --------------------------------------------------------- |
|
693 // |
|
694 EXPORT_C HBufC* CMsgTextUtils::GetSafeAttachmentNameLC( |
|
695 MMsvAttachmentManager& aManager, |
|
696 const TDesC& aFileName, |
|
697 TMsvAttachmentId aAttachmentId, |
|
698 TBool aContentLocation ) |
|
699 { |
|
700 TBuf<KMaxFileNameLength> name; |
|
701 TBuf<KMaxFileExtensionLenght> ext; |
|
702 TBuf<KMaxFileTotalLength> candidate; |
|
703 TParsePtrC parse( aFileName ); |
|
704 |
|
705 ext.Copy( parse.Ext().Left( KMaxFileExtensionLenght ) ); |
|
706 CMsgTextUtils::TrimAndRemoveNonAlphaDigit( ext ); |
|
707 |
|
708 TInt nameLen = Min( KMaxFileNameLength, |
|
709 ( KMaxFileTotalLength - ext.Length() ) ); |
|
710 name.Copy( parse.Name().Left( nameLen ) ); |
|
711 CMsgTextUtils::TrimAndRemoveNonAlphaDigit( name ); |
|
712 |
|
713 candidate.Copy( name ); |
|
714 candidate.Append( ext ); |
|
715 |
|
716 TBool safeFound = EFalse; |
|
717 TInt count = aManager.AttachmentCount(); |
|
718 TInt i = 0; |
|
719 while ( !safeFound && i < count ) |
|
720 { |
|
721 safeFound = ETrue; |
|
722 for ( TInt ii = 0; ii < count && safeFound; ii++ ) |
|
723 { |
|
724 CMsvAttachment* attachment = aManager.GetAttachmentInfoL( ii ); |
|
725 CleanupStack::PushL( attachment ); |
|
726 if ( aContentLocation ) |
|
727 { |
|
728 CMsvMimeHeaders* msvMime = CMsvMimeHeaders::NewLC(); |
|
729 msvMime->RestoreL( *attachment ); |
|
730 if ( attachment->Id() != aAttachmentId && |
|
731 !candidate.CompareF( msvMime->ContentLocation() ) ) |
|
732 { |
|
733 safeFound = EFalse; |
|
734 } |
|
735 CleanupStack::PopAndDestroy( msvMime ); |
|
736 } |
|
737 else |
|
738 { |
|
739 if ( attachment->Id() != aAttachmentId && |
|
740 !candidate.CompareF( attachment->AttachmentName() ) ) |
|
741 { |
|
742 safeFound = EFalse; |
|
743 } |
|
744 } |
|
745 CleanupStack::PopAndDestroy( attachment ); |
|
746 } |
|
747 i++; |
|
748 if ( !safeFound ) |
|
749 { |
|
750 name.Zero(); |
|
751 name.Copy( parse.Name().Left( nameLen - 3 ) ); |
|
752 CMsgTextUtils::TrimAndRemoveNonAlphaDigit( name ); |
|
753 TBuf<3> num; |
|
754 num.NumFixedWidth( i, EDecimal, 3 ); |
|
755 name.Append( num ); |
|
756 candidate.Zero(); |
|
757 candidate.Copy( name ); |
|
758 candidate.Append( ext ); |
|
759 } |
|
760 } |
|
761 |
|
762 // It is guaranteed that we always find a safe candidate: |
|
763 // - either safeFound == ETrue, or |
|
764 // - we've got "count + 1st" candidate while there are |
|
765 // "count" existing attachments. |
|
766 HBufC* safeFileName = candidate.AllocLC(); |
|
767 return safeFileName; |
|
768 } |
|
769 |
|
770 // --------------------------------------------------------- |
|
771 // from: TBool CImRecvConvert::IsIllegalChar(const TUint aChar) |
|
772 // --------------------------------------------------------- |
|
773 // |
|
774 LOCAL_C TBool IsIllegalChar(const TUint aChar) |
|
775 { |
|
776 return ( |
|
777 aChar == '*' || |
|
778 aChar == '\\' || |
|
779 aChar == '<' || |
|
780 aChar == '>' || |
|
781 aChar == ':' || |
|
782 aChar == '.' || |
|
783 aChar == '"' || |
|
784 aChar == '/' || |
|
785 aChar == '|' || |
|
786 aChar == '?' || |
|
787 aChar == CEditableText::EParagraphDelimiter || |
|
788 aChar == CEditableText::ELineBreak || |
|
789 aChar < ' ' ); |
|
790 } |
|
791 |
|
792 // --------------------------------------------------------- |
|
793 // GetFileNameFromBuffer |
|
794 // --------------------------------------------------------- |
|
795 // |
|
796 EXPORT_C void CMsgTextUtils::GetFileNameFromBuffer( |
|
797 TFileName& aFileName, |
|
798 const TDesC& aBuffer, |
|
799 TInt aMaxLength, |
|
800 const TDesC* aExt /*= NULL*/ ) |
|
801 { |
|
802 if ( aExt != NULL ) |
|
803 { |
|
804 aMaxLength -= aExt->Length(); |
|
805 } |
|
806 |
|
807 TInt len = aBuffer.Length(); |
|
808 TInt max = Min( len, aMaxLength ); |
|
809 |
|
810 //__ASSERT_DEBUG( max > 0, Panic( EMsgZeroLength ) ); |
|
811 |
|
812 aFileName.Zero(); |
|
813 |
|
814 TInt cc = 0; |
|
815 TUint ch; |
|
816 TUint ch1 = 0; |
|
817 TBool spaces = EFalse; |
|
818 for ( TInt i = 0; i < len && cc < max; i++ ) |
|
819 { |
|
820 ch = aBuffer[i]; |
|
821 |
|
822 // ignore spaces from beginning of the buffer until first |
|
823 // non-space is encountered. |
|
824 if ( !spaces && ch != ' ' ) |
|
825 { |
|
826 spaces = ETrue; |
|
827 } |
|
828 |
|
829 if ( i > 0 ) |
|
830 { |
|
831 ch1 = aBuffer[i - 1]; |
|
832 } |
|
833 |
|
834 // strip illegal chars away. |
|
835 // checks also if previous and current chars are '.' |
|
836 if ( spaces && ! IsIllegalChar( ch ) ) |
|
837 { |
|
838 if ( !( i > 0 && ch == '.' && ch1 == '.' ) ) |
|
839 { |
|
840 aFileName.Append( ch ); |
|
841 cc++; |
|
842 } |
|
843 } |
|
844 } |
|
845 |
|
846 aFileName.Trim(); |
|
847 |
|
848 // If filename is empty at this point, do not append extension either. |
|
849 // Instead, empty filename is returned so that caller can use whatever |
|
850 // default s/he has for it. |
|
851 if ( aFileName.Length() > 0 && aExt != NULL ) |
|
852 { |
|
853 aFileName.Append( *aExt ); |
|
854 } |
|
855 } |
|
856 |
|
857 // --------------------------------------------------------- |
|
858 // CMsgTextUtils::ConvertToUnicodeL |
|
859 // Converts input 8-bit data buffer (in given foreign charset type) to unicode buffer. |
|
860 // --------------------------------------------------------- |
|
861 EXPORT_C HBufC16* CMsgTextUtils::ConvertToUnicodeL( const TDesC8& aText, TUint aCharacterSetIdentifier ) |
|
862 { |
|
863 TInt origLength = aText.Length(); |
|
864 TInt maxLength = origLength; |
|
865 |
|
866 if ( !iCharConv ) |
|
867 { |
|
868 iCharConv = CCnvCharacterSetConverter::NewL(); |
|
869 } |
|
870 |
|
871 //buffer to hold target data and return to caller |
|
872 HBufC* resultBuffer = HBufC::NewL( maxLength ); |
|
873 _LIT8( KReplaceChar8, "_" ); |
|
874 |
|
875 if ( iCharConv->PrepareToConvertToOrFromL( aCharacterSetIdentifier, iFs ) != |
|
876 CCnvCharacterSetConverter::EAvailable ) |
|
877 { |
|
878 User::Leave( KErrNotSupported ); |
|
879 } |
|
880 |
|
881 //TODO:: need to set endianess if required. |
|
882 //TODO:: below line is not necessary i guess??? |
|
883 //The missing character is simply replaced by the Unicode character which represents unknown characters (0xFFFD) |
|
884 //iCharConv->SetReplacementForUnconvertibleUnicodeCharactersL( KReplaceChar8 ); |
|
885 |
|
886 TBuf16<40> outputBuffer; |
|
887 TPtrC8 remainderOfinputBuf ( aText ); |
|
888 //TODO: KStateDefault header include |
|
889 TInt aState = 0; // KStateDefault; |
|
890 |
|
891 FOREVER |
|
892 { |
|
893 const TInt doneAll = iCharConv->ConvertToUnicode( outputBuffer, remainderOfinputBuf, aState ); |
|
894 |
|
895 if ( doneAll == CCnvCharacterSetConverter::EErrorIllFormedInput ) |
|
896 { |
|
897 User::Leave( KErrCorrupt ); |
|
898 } |
|
899 else if ( doneAll < 0 ) |
|
900 { |
|
901 // For future expansion of errors |
|
902 User::Leave( KErrGeneral ); |
|
903 } |
|
904 else |
|
905 { // lint |
|
906 } |
|
907 |
|
908 // Make sure outputBuffer fits into resultBuffer |
|
909 while ( resultBuffer->Length() + outputBuffer.Length() > maxLength ) |
|
910 { |
|
911 // Increase resultBuffer length by origLength |
|
912 maxLength += origLength; |
|
913 resultBuffer = resultBuffer->ReAllocL( maxLength ); |
|
914 } |
|
915 // Append to result |
|
916 resultBuffer->Des().Append( outputBuffer ); |
|
917 |
|
918 if ( doneAll == 0 ) |
|
919 { |
|
920 /* Testing */ |
|
921 /* start --- |
|
922 resultBuffer = resultBuffer->ReAllocL( maxLength + 20); |
|
923 resultBuffer->Des().Append(_L("Korean Enc:415-5434")); |
|
924 ---- End */ |
|
925 return resultBuffer; // All converted |
|
926 } |
|
927 //TODO:: set the buffer correctly w.r.t length, Remember this is HBUFC16 |
|
928 remainderOfinputBuf.Set( remainderOfinputBuf.Right( doneAll )); |
|
929 } |
|
930 } |
|
931 |
|
932 // --------------------------------------------------------- |
|
933 // CMsgTextUtils::ConvertPtrToDesC16 |
|
934 // Converts input 8-bit data buffer to 16-bit data buffer. |
|
935 // --------------------------------------------------------- |
|
936 EXPORT_C void CMsgTextUtils::ConvertPtrToDesC16( const TDes8& aFromBuff8, TDes16& aToBuff16 ) |
|
937 { |
|
938 TInt i = 0; |
|
939 TInt j = 0; |
|
940 |
|
941 aToBuff16.FillZ( aToBuff16.MaxSize()/2 ); //MaxSize returns in bytes, hence devide by 2 |
|
942 while( j < (aFromBuff8.Length() - 1) ) |
|
943 { |
|
944 aToBuff16[i] = aFromBuff8[j++] & 0xff; // low byte |
|
945 aToBuff16[i++] |= (aFromBuff8[j++] << 8); // high byte |
|
946 } |
|
947 aToBuff16.SetLength(i); |
|
948 } |
|
949 |
|
950 // End of File |