1.1 --- /dev/null Thu Jan 01 00:00:00 1970 +0000
1.2 +++ b/os/textandloc/charconvfw/charconv_fw/inc/charconv.h Fri Jun 15 03:10:57 2012 +0200
1.3 @@ -0,0 +1,755 @@
1.4 +/*
1.5 +* Copyright (c) 1997-2009 Nokia Corporation and/or its subsidiary(-ies).
1.6 +* All rights reserved.
1.7 +* This component and the accompanying materials are made available
1.8 +* under the terms of "Eclipse Public License v1.0"
1.9 +* which accompanies this distribution, and is available
1.10 +* at the URL "http://www.eclipse.org/legal/epl-v10.html".
1.11 +*
1.12 +* Initial Contributors:
1.13 +* Nokia Corporation - initial contribution.
1.14 +*
1.15 +* Contributors:
1.16 +*
1.17 +* Description:
1.18 +*
1.19 +*/
1.20 +
1.21 +
1.22 +#if !defined(__CHARCONV_H__)
1.23 +#define __CHARCONV_H__
1.24 +
1.25 +#if !defined(__E32STD_H__)
1.26 +#include <e32std.h>
1.27 +#endif
1.28 +
1.29 +#if !defined(__E32BASE_H__)
1.30 +#include <e32base.h>
1.31 +#endif
1.32 +
1.33 +/**
1.34 +The maximum length in bytes of the replacement text for unconvertible Unicode
1.35 +characters (=50) (see CCnvCharacterSetConverter::SetReplacementForUnconvertibleUnicodeCharactersL()).
1.36 +@publishedAll
1.37 +@released
1.38 +*/
1.39 +const TInt KMaximumLengthOfReplacementForUnconvertibleUnicodeCharacters=50;
1.40 +
1.41 +/**
1.42 +UTF-7
1.43 +@publishedAll
1.44 +@released
1.45 +*/
1.46 +const TUint KCharacterSetIdentifierUtf7=0x1000582c;
1.47 +/**
1.48 +UTF-8
1.49 +@publishedAll
1.50 +@released
1.51 +*/
1.52 +const TUint KCharacterSetIdentifierUtf8=0x1000582d;
1.53 +/**
1.54 +IMAP UTF-7
1.55 +@publishedAll
1.56 +@released
1.57 +*/
1.58 +const TUint KCharacterSetIdentifierImapUtf7=0x1000582e;
1.59 +/**
1.60 +Java UTF-8
1.61 +@publishedAll
1.62 +@released
1.63 +*/
1.64 +const TUint KCharacterSetIdentifierJavaConformantUtf8=0x1000582f;
1.65 +/**
1.66 +Code Page 1252
1.67 +@publishedAll
1.68 +@released
1.69 +*/
1.70 +const TUint KCharacterSetIdentifierCodePage1252=0x100012b6;
1.71 +/**
1.72 +ISO 8859-1
1.73 +@publishedAll
1.74 +@released
1.75 +*/
1.76 +const TUint KCharacterSetIdentifierIso88591=0x10003b10;
1.77 +/**
1.78 +ISO 8859-2
1.79 +@publishedAll
1.80 +@released
1.81 +*/
1.82 +const TUint KCharacterSetIdentifierIso88592=0x1000507e;
1.83 +/**
1.84 +ISO 8859-3
1.85 +@publishedAll
1.86 +@released
1.87 +*/
1.88 +const TUint KCharacterSetIdentifierIso88593=0x10008a28;
1.89 +/**
1.90 +ISO 8859-4
1.91 +@publishedAll
1.92 +@released
1.93 +*/
1.94 +const TUint KCharacterSetIdentifierIso88594=0x1000507f;
1.95 +/**
1.96 +ISO 8859-5
1.97 +@publishedAll
1.98 +@released
1.99 +*/
1.100 +const TUint KCharacterSetIdentifierIso88595=0x10005080;
1.101 +/**
1.102 +ISO 8859-6
1.103 +@publishedAll
1.104 +@released
1.105 +*/
1.106 +const TUint KCharacterSetIdentifierIso88596=0x10008a29;
1.107 +/**
1.108 +ISO 8859-7
1.109 +@publishedAll
1.110 +@released
1.111 +*/
1.112 +const TUint KCharacterSetIdentifierIso88597=0x10005081;
1.113 +/**
1.114 +ISO 8859-8
1.115 +@publishedAll
1.116 +@released
1.117 +*/
1.118 +const TUint KCharacterSetIdentifierIso88598=0x10008a2a;
1.119 +/**
1.120 +ISO 8859-9
1.121 +@publishedAll
1.122 +@released
1.123 +*/
1.124 +const TUint KCharacterSetIdentifierIso88599=0x10005082;
1.125 +/**
1.126 +ISO 8859-10
1.127 +@publishedAll
1.128 +@released
1.129 +*/
1.130 +const TUint KCharacterSetIdentifierIso885910=0x10008a2b;
1.131 +/**
1.132 +ISO 8859-13
1.133 +@publishedAll
1.134 +@released
1.135 +*/
1.136 +const TUint KCharacterSetIdentifierIso885913=0x10008a2c;
1.137 +/**
1.138 +ISO 8859-14
1.139 +@publishedAll
1.140 +@released
1.141 +*/
1.142 +const TUint KCharacterSetIdentifierIso885914=0x10008a2d;
1.143 +/**
1.144 +ISO 8859-15
1.145 +@publishedAll
1.146 +@released
1.147 +*/
1.148 +const TUint KCharacterSetIdentifierIso885915=0x10008a2e;
1.149 +/**
1.150 +ASCII
1.151 +@publishedAll
1.152 +@released
1.153 +*/
1.154 +const TUint KCharacterSetIdentifierAscii=0x10004cc6;
1.155 +/**
1.156 +SMS 7-bit
1.157 +@publishedAll
1.158 +@released
1.159 +*/
1.160 +const TUint KCharacterSetIdentifierSms7Bit=0x100053ab;
1.161 +/**
1.162 +GB 2312
1.163 +@publishedAll
1.164 +@released
1.165 +*/
1.166 +const TUint KCharacterSetIdentifierGb2312=0x10000fbe;
1.167 +/**
1.168 +HZ-GB-2312
1.169 +@publishedAll
1.170 +@released
1.171 +*/
1.172 +const TUint KCharacterSetIdentifierHz=0x10006065;
1.173 +/**
1.174 +GB 12345
1.175 +@publishedAll
1.176 +@released
1.177 +*/
1.178 +const TUint KCharacterSetIdentifierGb12345=0x1000401a;
1.179 +/**
1.180 +GBK
1.181 +@publishedAll
1.182 +@released
1.183 +*/
1.184 +const TUint KCharacterSetIdentifierGbk=0x10003ecb;
1.185 +/**
1.186 +GB18030
1.187 +@publishedAll
1.188 +@released
1.189 +*/
1.190 +const TUint KCharacterSetIdentifierGb18030=0x10287038;
1.191 +/**
1.192 +Big 5
1.193 +@publishedAll
1.194 +@released
1.195 +*/
1.196 +const TUint KCharacterSetIdentifierBig5=0x10000fbf;
1.197 +/**
1.198 +Shift-JIS
1.199 +@publishedAll
1.200 +@released
1.201 +*/
1.202 +const TUint KCharacterSetIdentifierShiftJis=0x10000fbd;
1.203 +/**
1.204 +ISO-2022-JP
1.205 +@publishedAll
1.206 +@released
1.207 +*/
1.208 +const TUint KCharacterSetIdentifierIso2022Jp=0x100066a0;
1.209 +/**
1.210 +ISO-2022-JP-1
1.211 +@publishedAll
1.212 +@released
1.213 +*/
1.214 +const TUint KCharacterSetIdentifierIso2022Jp1=0x100066a3;
1.215 +/**
1.216 +JIS Encoding
1.217 +@publishedAll
1.218 +@released
1.219 +*/
1.220 +const TUint KCharacterSetIdentifierJis=0x10006066;
1.221 +/**
1.222 +EUC-JP
1.223 +@publishedAll
1.224 +@released
1.225 +*/
1.226 +const TUint KCharacterSetIdentifierEucJpPacked=0x10006067;
1.227 +
1.228 +/**
1.229 +JP5
1.230 +@publishedAll
1.231 +@released
1.232 +*/
1.233 +const TUint KCharacterSetIdentifierJ5=0x1020D408;
1.234 +/**
1.235 +CP850
1.236 +@publishedAll
1.237 +@released
1.238 +*/
1.239 +const TUint KCharacterSetIdentifierCP850=0x102825AD;
1.240 +
1.241 +const TUint KCharacterSetIdentifierUnicodeLittle=0x101f3fae; //Little Endian Unicode
1.242 +const TUint KCharacterSetIdentifierUnicodeBig=0x101f4052; // Big Endian Unicode
1.243 +const TUint KCharacterSetIdentifierUcs2=0x101ff492;
1.244 +
1.245 +
1.246 +/**
1.247 +Extended SMS 7-bit
1.248 +@publishedAll
1.249 +@released
1.250 +*/
1.251 +const TUint KCharacterSetIdentifierExtendedSms7Bit=0x102863FD;
1.252 +
1.253 +/**
1.254 +Turkish
1.255 +@publishedAll
1.256 +@released
1.257 +*/
1.258 +const TUint KCharacterSetIdentifierTurkishSingleSms7Bit=0x102863FE;
1.259 +const TUint KCharacterSetIdentifierTurkishLockingSms7Bit=0x102863FF;
1.260 +const TUint KCharacterSetIdentifierTurkishLockingAndSingleSms7Bit=0x10286400;
1.261 +
1.262 +/**
1.263 +Portuguese
1.264 +@publishedAll
1.265 +@released
1.266 +*/
1.267 +const TUint KCharacterSetIdentifierPortugueseSingleSms7Bit=0x10286407;
1.268 +const TUint KCharacterSetIdentifierPortugueseLockingSms7Bit=0x10286408;
1.269 +const TUint KCharacterSetIdentifierPortugueseLockingAndSingleSms7Bit=0x10286409;
1.270 +
1.271 +/**
1.272 +Spanish
1.273 +@publishedAll
1.274 +@released
1.275 +*/
1.276 +const TUint KCharacterSetIdentifierSpanishSingleSms7Bit=0x1028640A;
1.277 +
1.278 +
1.279 +/**
1.280 +code page 949
1.281 +@publishedAll
1.282 +@released
1.283 +*/
1.284 +const TUint KCharacterSetIdentifierCP949=0x200100FF;
1.285 +
1.286 +/**
1.287 +Shift-JIS with Pictograph
1.288 +@publishedAll
1.289 +@released
1.290 +*/
1.291 +const TUint KCharacterSetIdentifierShiftJisDirectmap=0x101F8691;
1.292 +
1.293 +/**
1.294 +EUC-JP with direct mapped pictograph
1.295 +@publishedAll
1.296 +@released
1.297 +*/
1.298 +const TUint KCharacterSetIdentifierEucJpDirectmap=0x101F86A6;
1.299 +
1.300 +/**
1.301 +EUC-KR
1.302 +@publishedAll
1.303 +@released
1.304 +*/
1.305 +const TUint KCharacterSetIdentifierEUCKR=0x2000E526;
1.306 +
1.307 +/**
1.308 +iscii
1.309 +@publishedAll
1.310 +@released
1.311 +*/
1.312 +const TUint KCharacterSetIdentifierIscii=0x1027508E;
1.313 +
1.314 +/**
1.315 +ISO2022 Korean
1.316 +@publishedAll
1.317 +@released
1.318 +*/
1.319 +const TUint KCharacterSetIdentifierIso2022kr=0x20010101;
1.320 +
1.321 +/**
1.322 +KOI8-R Russian
1.323 +@publishedAll
1.324 +@released
1.325 +*/
1.326 +const TUint KCharacterSetIdentifierKOI8R=0x101F8778;
1.327 +
1.328 +/**
1.329 +KOI8-U Belorusian/Ukrainian Cyrillic
1.330 +@publishedAll
1.331 +@released
1.332 +*/
1.333 +const TUint KCharacterSetIdentifierKOI8U=0x101F8761;
1.334 +
1.335 +/**
1.336 +KSC5601 Korean
1.337 +@publishedAll
1.338 +@released
1.339 +*/
1.340 +const TUint KCharacterSetIdentifierKsc5601=0x200113CD;
1.341 +
1.342 +/**
1.343 +TIS_620 Thai
1.344 +@publishedAll
1.345 +@released
1.346 +*/
1.347 +const TUint KCharacterSetIdentifierTIS_620=0x101F8549;
1.348 +
1.349 +/**
1.350 +Code page 874 Thai
1.351 +@publishedAll
1.352 +@released
1.353 +*/
1.354 +const TUint KCharacterSetIdentifierWin874=0x101F854A;
1.355 +
1.356 +/**
1.357 +Code page 1250 Eastern European
1.358 +@publishedAll
1.359 +@released
1.360 +*/
1.361 +const TUint KCharacterSetIdentifierWin1250=0x100059D6;
1.362 +
1.363 +/**
1.364 +Code page 1251 Cyrillic
1.365 +@publishedAll
1.366 +@released
1.367 +*/
1.368 +const TUint KCharacterSetIdentifierWin1251=0x100059D7;
1.369 +
1.370 +/**
1.371 +Code page 1253 Greek
1.372 +@publishedAll
1.373 +@released
1.374 +*/
1.375 +const TUint KCharacterSetIdentifierWin1253=0x100059D8;
1.376 +
1.377 +/**
1.378 +Code page 1254 Turkish
1.379 +@publishedAll
1.380 +@released
1.381 +*/
1.382 +const TUint KCharacterSetIdentifierWin1254=0x100059D9;
1.383 +
1.384 +/**
1.385 +Code page 1255 Hebrew
1.386 +@publishedAll
1.387 +@released
1.388 +*/
1.389 +const TUint KCharacterSetIdentifierWin1255=0x101F8547;
1.390 +
1.391 +/**
1.392 +Code page 1256 Arabic
1.393 +@publishedAll
1.394 +@released
1.395 +*/
1.396 +const TUint KCharacterSetIdentifierWin1256=0x101F8548;
1.397 +
1.398 +/**
1.399 +Code page 1257 Baltic
1.400 +@publishedAll
1.401 +@released
1.402 +*/
1.403 +const TUint KCharacterSetIdentifierWin1257=0x100059DA;
1.404 +
1.405 +/**
1.406 +Windows-1258
1.407 +@publishedAll
1.408 +@released
1.409 +*/
1.410 +const TUint KCharacterSetIdentifierWin1258=0x102073B8;
1.411 +
1.412 +// 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
1.413 +
1.414 +struct SCnvConversionData;
1.415 +class CDeepDestructingArrayOfCharactersSets;
1.416 +class CFileReader;
1.417 +class CStandardNamesAndMibEnums;
1.418 +class RFs;
1.419 +class CCharsetCnvCache;
1.420 +/**
1.421 +Converts text between Unicode and other character sets.
1.422 +
1.423 +The first stage of the conversion is to specify the non-Unicode character
1.424 +set being converted to or from. This is done by calling one of the overloads
1.425 +of PrepareToConvertToOrFromL().
1.426 +
1.427 +The second stage is to convert the text, using one of the overloads of
1.428 +ConvertFromUnicode() or ConvertToUnicode().
1.429 +
1.430 +Where possible the first documented overload of PrepareToConvertToOrFromL()
1.431 +should be used because the second overload panics if the specified character
1.432 +set is not available: the first overload simply returns whether the character
1.433 +set is available or not available. However if the conversions are to be
1.434 +performed often, or if the user must select the character set for the
1.435 +conversion from a list, the second overload may be more appropriate.
1.436 +
1.437 +The first overload is less efficient than the second, because it searches
1.438 +through the file system for the selected character set every time it is invoked.
1.439 +The second overload searches through an array of all available character sets.
1.440 +In this method, the file system need only be searched once - when
1.441 +CreateArrayOfCharacterSetsAvailableLC() or
1.442 +CreateArrayOfCharacterSetsAvailableL() is used to create the array.
1.443 +
1.444 +The conversion functions allow users of this class to perform partial
1.445 +conversions on an input descriptor, handling the situation where the input
1.446 +descriptor is truncated mid way through a multi-byte character. This means
1.447 +that you do not have to guess how big to make the output descriptor for a
1.448 +given input descriptor, you can simply do the conversion in a loop using a
1.449 +small output descriptor. The ability to handle truncated descriptors also
1.450 +allows users of the class to convert information received in chunks from an
1.451 +external source.
1.452 +
1.453 +The class also provides a number of utility functions.
1.454 +@publishedAll
1.455 +@released
1.456 +*/
1.457 +class CCnvCharacterSetConverter : public CBase
1.458 + {
1.459 +public:
1.460 + /** Indicates whether a character set is available or unavailable
1.461 + for conversion. Used by the second overload of
1.462 + PrepareToConvertToOrFromL(). */
1.463 + enum TAvailability
1.464 + {
1.465 + /** The requested character set can be converted. */
1.466 + EAvailable,
1.467 + /** The requested character set cannot be converted. */
1.468 + ENotAvailable
1.469 + };
1.470 +
1.471 + /** Conversion error flags. At this stage there is only one error
1.472 + flag- others may be added in the future. */
1.473 + enum TError
1.474 + {
1.475 + /** The input descriptor contains a single corrupt character. This
1.476 + might occur when the input descriptor only contains some of the bytes
1.477 + of a single multi-byte character. */
1.478 + EErrorIllFormedInput=KErrCorrupt
1.479 + };
1.480 +
1.481 + /** Specifies the default endian-ness of the current character set.
1.482 + Used by SetDefaultEndiannessOfForeignCharacters(). */
1.483 + enum TEndianness
1.484 + {
1.485 + /** The character set is big-endian. */
1.486 + ELittleEndian,
1.487 + /** The character set is little-endian. */
1.488 + EBigEndian
1.489 + };
1.490 +
1.491 + /** Downgrade for line and paragraph separators */
1.492 + enum TDowngradeForExoticLineTerminatingCharacters
1.493 + {
1.494 + /** Paragraph/line separators should be downgraded (if necessary)
1.495 + into carriage return and line feed pairs. */
1.496 + EDowngradeExoticLineTerminatingCharactersToCarriageReturnLineFeed,
1.497 + /** Paragraph/line separators should be downgraded (if necessary)
1.498 + into a line feed only. */
1.499 + EDowngradeExoticLineTerminatingCharactersToJustLineFeed
1.500 + };
1.501 +
1.502 + /** Output flag used to indicate whether or not a character in the source
1.503 + descriptor is the first half of a surrogate pair, but is the last
1.504 + character in the descriptor to convert.
1.505 +
1.506 + Note: This enumeration can be used in the DoConvertToUnicode() and
1.507 + DoConvertFromUnicode() functions. These are part of the
1.508 + Character Conversion Plug-in Provider API and are for use by plug-in
1.509 + conversion libraries only.
1.510 + @since 6.0 */
1.511 + enum
1.512 + {
1.513 + /** Appends the converted text to the output descriptor.*/
1.514 + EInputConversionFlagAppend =0x00010000,
1.515 + /** By default, when the input descriptor passed to DoConvertFromUnicode()
1.516 + or DoConvertToUnicode() consists of nothing but a truncated sequence,
1.517 + the error-code EErrorIllFormedInput is returned.
1.518 + If this behaviour is undesirable, the input flag
1.519 + EInputConversionFlagAllowTruncatedInputNotEvenPartlyConsumable
1.520 + should be set. */
1.521 + EInputConversionFlagAllowTruncatedInputNotEvenPartlyConsumable =0x00020000,
1.522 + /** Stops converting when the first unconvertible character is reached. */
1.523 + EInputConversionFlagStopAtFirstUnconvertibleCharacter =0x00040000,
1.524 + /** Appends the default character set Escape sequence at end of converted text */
1.525 + EInputConversionFlagMustEndInDefaultCharacterSet =0x00080000,
1.526 + /*defect fix: INC053609; According to RFC1468 we can assume the line starts
1.527 + in ASCII so there is no need to always insert an escape sequence*/
1.528 + EInputConversionFlagAssumeStartInDefaultCharacterSet =0x00100000
1.529 + };
1.530 + enum
1.531 + {
1.532 + /** Indicates whether or not the source descriptor ends in a truncated
1.533 + sequence, e.g. the first half only of a surrogate pair. */
1.534 + EOutputConversionFlagInputIsTruncated =0x01000000
1.535 + };
1.536 +
1.537 + /** Initial value for the state argument in a set of related calls to
1.538 + ConvertToUnicode(). */
1.539 + enum {KStateDefault=0};
1.540 + enum
1.541 + {
1.542 + /** The lowest confidence value for a character set accepted by
1.543 + Autodetect*/
1.544 + ELowestThreshold = 25
1.545 + };
1.546 +
1.547 + /** Stores information about a non-Unicode character set. The information
1.548 + is used to locate the conversion information required by
1.549 + ConvertFromUnicode() and ConvertToUnicode().
1.550 +
1.551 + An array of these structs that contain all available character sets
1.552 + can be generated by CreateArrayOfCharacterSetsAvailableLC() and
1.553 + CreateArrayOfCharacterSetsAvailableL(), and is used by one of the
1.554 + overloads of PrepareToConvertToOrFromL(). */
1.555 + struct SCharacterSet
1.556 + {
1.557 + /** Gets the character sets UID.
1.558 +
1.559 + @return The UID of the character set. */
1.560 + inline TUint Identifier() const {return iIdentifier;}
1.561 +
1.562 + /** Tests whether a filename given by the function SCharacterSet::Name()
1.563 + is a real file name (i.e. conversion is provided by a plug in DLL), or
1.564 + just the character set name (i.e. conversion is built into Symbian OS).
1.565 +
1.566 + Note: If the function returns ETrue then the path and filename can be
1.567 + parsed using TParse or TParsePtrC functions to obtain just the filename.
1.568 +
1.569 + @return ETrue if the name is a real filename. EFalse if it is just the
1.570 + character set name. */
1.571 + inline TBool NameIsFileName() const {return iFlags&EFlagNameIsFileName;}
1.572 +
1.573 + /** Gets the full path and filename of the DLL which implements
1.574 + conversion for the character set.
1.575 +
1.576 + If the character set is one for which conversion is built into Symbian
1.577 + OS rather than implemented by a plug in DLL, the function just returns
1.578 + the name of the character set. The NameIsFileName() function can be
1.579 + used to determine whether or not it is legal to create a TParsePtrC
1.580 + object over the descriptor returned by Name().
1.581 +
1.582 + Notes:
1.583 +
1.584 + The name returned cannot be treated as an Internet-standard name, it
1.585 + is locale-independent and should be mapped to the locale-dependent name
1.586 + by software at a higher level before being shown to the user. Conversion
1.587 + from Internet-standard names of character sets to the UID identifiers
1.588 + is provided by the member function
1.589 + ConvertStandardNameOfCharacterSetToIdentifierL().
1.590 +
1.591 + Typically, to find the user-displayable name (as opposed to the
1.592 + internet-standard name) of a character set, you would do something
1.593 + like this:
1.594 +
1.595 + @code
1.596 + const CCnvCharacterSetConverter::SCharacterSet& characterSet=...;
1.597 + const TPtrC userDisplayable(characterSet.NameIsFileName()? TParsePtrC(characterSet.Name()).Name():
1.598 + characterSet.Name());
1.599 + @endcode
1.600 +
1.601 + @return Full path and filename of the character set converter plug in
1.602 + DLL, or just the name of the character set. */
1.603 + inline TPtrC Name() const {return *iName;}
1.604 + private:
1.605 + enum
1.606 + {
1.607 + EFlagNameIsFileName =0x00000001,
1.608 + EFlagFileIsConversionPlugInLibrary =0x00000002
1.609 + };
1.610 + private:
1.611 + inline TBool FileIsConversionPlugInLibrary() const {return iFlags&EFlagFileIsConversionPlugInLibrary;}
1.612 + private:
1.613 + TUint iIdentifier;
1.614 + TUint iFlags;
1.615 + HBufC* iName;
1.616 + private:
1.617 + friend class CCnvCharacterSetConverter;
1.618 + friend class CDeepDestructingArrayOfCharactersSets;
1.619 + }; //SCharacterSet
1.620 +
1.621 +
1.622 + /**
1.623 + Holds an ascending array of the indices of the characters in the
1.624 + source Unicode text which could not be converted by
1.625 + CCnvCharacterSetConverter::ConvertFromUnicode() into the foreign
1.626 + character set
1.627 + @publishedAll
1.628 + @released
1.629 + */
1.630 + class TArrayOfAscendingIndices
1.631 + {
1.632 + public:
1.633 + /** The return value of CCnvCharacterSetConverter::AppendIndex(). */
1.634 + enum TAppendResult
1.635 + {
1.636 + /** The append failed. */
1.637 + EAppendFailed,
1.638 + /** The append succeeded. */
1.639 + EAppendSuccessful
1.640 + };
1.641 + public:
1.642 + /** C++ constructor. The array is initialised to be of length zero. */
1.643 + inline TArrayOfAscendingIndices() :iArrayOfIndices(0) {}
1.644 +
1.645 + IMPORT_C TAppendResult AppendIndex(TInt aIndex);
1.646 +
1.647 + /** Deletes a single index from the array.
1.648 +
1.649 + @param aIndexOfIndex The index of the index to delete. Must not be
1.650 + negative and must not be greater than the length of the array, or a
1.651 + panic occurs. */
1.652 + inline void Remove(TInt aIndexOfIndex) {iArrayOfIndices.Delete(aIndexOfIndex, 1);}
1.653 +
1.654 + /** Deletes all indices from the array. */
1.655 + inline void RemoveAll() {iArrayOfIndices.SetLength(0);}
1.656 +
1.657 + /** Returns the number of indices in the array.
1.658 +
1.659 + @return The number of indices in the array. */
1.660 + inline TInt NumberOfIndices() const {return iArrayOfIndices.Length();}
1.661 +
1.662 + /** Gets the value of the specified index.
1.663 +
1.664 + @param aIndexOfIndex Index into the array.
1.665 + @return The value of the index. */
1.666 + inline TInt operator[](TInt aIndexOfIndex) const {return iArrayOfIndices[aIndexOfIndex];}
1.667 + private:
1.668 + enum {KMaximumNumberOfIndices=25};
1.669 + private:
1.670 + TBuf16<KMaximumNumberOfIndices> iArrayOfIndices;
1.671 + };
1.672 +public:
1.673 + IMPORT_C static CCnvCharacterSetConverter* NewL();
1.674 + IMPORT_C static CCnvCharacterSetConverter* NewLC();
1.675 + IMPORT_C virtual ~CCnvCharacterSetConverter();
1.676 + IMPORT_C static CArrayFix<SCharacterSet>* CreateArrayOfCharacterSetsAvailableL(RFs& aFileServerSession);
1.677 + IMPORT_C static CArrayFix<SCharacterSet>* CreateArrayOfCharacterSetsAvailableLC(RFs& aFileServerSession);
1.678 + IMPORT_C TUint ConvertStandardNameOfCharacterSetToIdentifierL(const TDesC8& aStandardNameOfCharacterSet, RFs& aFileServerSession);
1.679 + IMPORT_C HBufC8* ConvertCharacterSetIdentifierToStandardNameL(TUint aCharacterSetIdentifier, RFs& aFileServerSession);
1.680 + IMPORT_C TUint ConvertMibEnumOfCharacterSetToIdentifierL(TInt aMibEnumOfCharacterSet, RFs& aFileServerSession);
1.681 + IMPORT_C TInt ConvertCharacterSetIdentifierToMibEnumL(TUint aCharacterSetIdentifier, RFs& aFileServerSession);
1.682 + IMPORT_C void PrepareToConvertToOrFromL(TUint aCharacterSetIdentifier, const CArrayFix<SCharacterSet>& aArrayOfCharacterSetsAvailable, RFs& aFileServerSession);
1.683 + IMPORT_C TAvailability PrepareToConvertToOrFromL(TUint aCharacterSetIdentifier, RFs& aFileServerSession);
1.684 + // the following attribute-setting functions should be called (if at all) after calling PrepareToConvertToOrFromL and before calling ConvertFromUnicode and/or ConvertToUnicode
1.685 + IMPORT_C void SetDefaultEndiannessOfForeignCharacters(TEndianness aEndianness);
1.686 + IMPORT_C void SetDowngradeForExoticLineTerminatingCharacters(TDowngradeForExoticLineTerminatingCharacters aDowngradeForExoticLineTerminatingCharacters); // by default this attribute is set to EDowngradeExoticLineTerminatingCharactersToCarriageReturnLineFeed
1.687 + 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
1.688 +
1.689 + // 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
1.690 + IMPORT_C TInt ConvertFromUnicode(TDes8& aForeign, const TDesC16& aUnicode) const;
1.691 + IMPORT_C TInt ConvertFromUnicode(TDes8& aForeign, const TDesC16& aUnicode, TInt& aNumberOfUnconvertibleCharacters) const;
1.692 + IMPORT_C TInt ConvertFromUnicode(TDes8& aForeign, const TDesC16& aUnicode, TInt& aNumberOfUnconvertibleCharacters, TInt& aIndexOfFirstUnconvertibleCharacter) const;
1.693 + IMPORT_C TInt ConvertFromUnicode(TDes8& aForeign, const TDesC16& aUnicode, TArrayOfAscendingIndices& aIndicesOfUnconvertibleCharacters) const;
1.694 + IMPORT_C TInt ConvertToUnicode(TDes16& aUnicode, const TDesC8& aForeign, TInt& aState) const;
1.695 + IMPORT_C TInt ConvertToUnicode(TDes16& aUnicode, const TDesC8& aForeign, TInt& aState, TInt& aNumberOfUnconvertibleCharacters) const;
1.696 + IMPORT_C TInt ConvertToUnicode(TDes16& aUnicode, const TDesC8& aForeign, TInt& aState, TInt& aNumberOfUnconvertibleCharacters, TInt& aIndexOfFirstByteOfFirstUnconvertibleCharacter) const;
1.697 + IMPORT_C static void AutoDetectCharacterSetL(TInt& aConfidenceLevel, TUint& aCharacterSetIdentifier, const CArrayFix<SCharacterSet>& aArrayOfCharacterSetsAvailable, const TDesC8& aSample);
1.698 + IMPORT_C void AutoDetectCharSetL(TInt& aConfidenceLevel, TUint& aCharacterSetIdentifier, const CArrayFix<SCharacterSet>& aArrayOfCharacterSetsAvailable, const TDesC8& aSample);
1.699 + IMPORT_C static void ConvertibleToCharacterSetL(TInt& aConfidenceLevel, const TUint aCharacterSetIdentifier,const CArrayFix<SCharacterSet>& aArrayOfCharacterSetsAvailable, const TDesC8& aSample);
1.700 + IMPORT_C void ConvertibleToCharSetL(TInt& aConfidenceLevel, const TUint aCharacterSetIdentifier,const CArrayFix<SCharacterSet>& aArrayOfCharacterSetsAvailable, const TDesC8& aSample);
1.701 + IMPORT_C void SetMaxCacheSize(TInt aSize);
1.702 + // the following functions are only to be called by conversion plug-in libraries
1.703 + IMPORT_C static TInt DoConvertFromUnicode(const SCnvConversionData& aConversionData, TEndianness aDefaultEndiannessOfForeignCharacters, const TDesC8& aReplacementForUnconvertibleUnicodeCharacters, TDes8& aForeign, const TDesC16& aUnicode, TArrayOfAscendingIndices& aIndicesOfUnconvertibleCharacters);
1.704 + IMPORT_C static TInt DoConvertFromUnicode(const SCnvConversionData& aConversionData, TEndianness aDefaultEndiannessOfForeignCharacters, const TDesC8& aReplacementForUnconvertibleUnicodeCharacters, TDes8& aForeign, const TDesC16& aUnicode, TArrayOfAscendingIndices& aIndicesOfUnconvertibleCharacters, TUint& aOutputConversionFlags, TUint aInputConversionFlags);
1.705 + IMPORT_C static TInt DoConvertToUnicode(const SCnvConversionData& aConversionData, TEndianness aDefaultEndiannessOfForeignCharacters, TDes16& aUnicode, const TDesC8& aForeign, TInt& aNumberOfUnconvertibleCharacters, TInt& aIndexOfFirstByteOfFirstUnconvertibleCharacter);
1.706 + IMPORT_C static TInt DoConvertToUnicode(const SCnvConversionData& aConversionData, TEndianness aDefaultEndiannessOfForeignCharacters, TDes16& aUnicode, const TDesC8& aForeign, TInt& aNumberOfUnconvertibleCharacters, TInt& aIndexOfFirstByteOfFirstUnconvertibleCharacter, TUint& aOutputConversionFlags, TUint aInputConversionFlags);
1.707 + IMPORT_C static const SCnvConversionData& AsciiConversionData();
1.708 + inline TDowngradeForExoticLineTerminatingCharacters GetDowngradeForExoticLineTerminatingCharacters ()
1.709 + {
1.710 + return iDowngradeForExoticLineTerminatingCharacters ;
1.711 + } ;
1.712 +
1.713 +private:
1.714 + enum
1.715 + {
1.716 + EStoredFlagOwnsConversionData =0x00000001,
1.717 + EStoredFlagConversionPlugInLibraryIsLoaded =0x00000002
1.718 + };
1.719 + enum TCharacterSetSearch
1.720 + {
1.721 + EStopCharacterSetSearch,
1.722 + EContinueCharacterSetSearch
1.723 + };
1.724 + enum TConversionPlugInFunctionOrdinals
1.725 + {
1.726 + EReplacementForUnconvertibleUnicodeCharacters=1,
1.727 + EConvertFromUnicode=2,
1.728 + EConvertToUnicode=3,
1.729 + EIsInThisCharacterSet=4
1.730 + };
1.731 +
1.732 +private:
1.733 + CCnvCharacterSetConverter();
1.734 + void ConstructL();
1.735 + static CArrayFix<SCharacterSet>* DoCreateArrayOfCharacterSetsAvailableLC(RFs& aFileServerSession, TUint aIdentifierOfOnlyCharacterSetOfInterest);
1.736 + static TCharacterSetSearch AppendHardCodedCharacterSetIfRequiredL(CArrayFix<SCharacterSet>& aArrayOfCharacterSets, TUint aIdentifierOfOnlyCharacterSetOfInterest, TUint aIdentifierOfHardCodedCharacterSet, const TDesC& aNameOfHardCodedCharacterSet);
1.737 + void ScanForStandardNamesAndMibEnumsL(RFs& aFileServerSession);
1.738 + void ScanForStandardNamesAndMibEnumsROMOnlyL(RFs& aFileServerSession);
1.739 + TAvailability DoPrepareToConvertToOrFromL(TUint aCharacterSetIdentifier, const CArrayFix<SCharacterSet>* aArrayOfCharacterSetsAvailable, RFs& aFileServerSession);
1.740 + static void DeleteConversionData(const SCnvConversionData* aConversionData);
1.741 + static void DeleteConversionData(TAny* aConversionData);
1.742 + static TEndianness EndiannessOfForeignCharacters(const SCnvConversionData& aConversionData, TEndianness aDefaultEndiannessOfForeignCharacters);
1.743 +
1.744 +private:
1.745 + TUint iStoredFlags;
1.746 + TUint iCharacterSetIdentifierOfLoadedConversionData; // 0 or a UID of the loaded plugin
1.747 + const SCnvConversionData* iConversionData;
1.748 + TEndianness iDefaultEndiannessOfForeignCharacters;
1.749 + TDowngradeForExoticLineTerminatingCharacters iDowngradeForExoticLineTerminatingCharacters;
1.750 + TBuf8<KMaximumLengthOfReplacementForUnconvertibleUnicodeCharacters> iReplacementForUnconvertibleUnicodeCharacters;
1.751 + CStandardNamesAndMibEnums* iStandardNamesAndMibEnums;
1.752 + TBool iTlsDataConstructed;
1.753 + CCharsetCnvCache* iCharsetCnvCache;
1.754 + TBool iIsSystemStandardNamesAndMibEnumsScanned;
1.755 + };
1.756 +
1.757 +#endif
1.758 +