williamr@4
|
1 |
/*
|
williamr@4
|
2 |
* Copyright (c) 1997-2009 Nokia Corporation and/or its subsidiary(-ies).
|
williamr@4
|
3 |
* All rights reserved.
|
williamr@4
|
4 |
* This component and the accompanying materials are made available
|
williamr@4
|
5 |
* under the terms of "Eclipse Public License v1.0"
|
williamr@4
|
6 |
* which accompanies this distribution, and is available
|
williamr@4
|
7 |
* at the URL "http://www.eclipse.org/legal/epl-v10.html".
|
williamr@4
|
8 |
*
|
williamr@4
|
9 |
* Initial Contributors:
|
williamr@4
|
10 |
* Nokia Corporation - initial contribution.
|
williamr@4
|
11 |
*
|
williamr@4
|
12 |
* Contributors:
|
williamr@4
|
13 |
*
|
williamr@4
|
14 |
* Description:
|
williamr@4
|
15 |
*
|
williamr@4
|
16 |
*/
|
williamr@4
|
17 |
|
williamr@2
|
18 |
|
williamr@2
|
19 |
#if !defined(__UTF_H__)
|
williamr@2
|
20 |
#define __UTF_H__
|
williamr@2
|
21 |
|
williamr@2
|
22 |
#if !defined(__E32STD_H__)
|
williamr@2
|
23 |
#include <e32std.h>
|
williamr@2
|
24 |
#endif
|
williamr@2
|
25 |
|
williamr@2
|
26 |
|
williamr@2
|
27 |
class CnvUtfConverter
|
williamr@2
|
28 |
/**
|
williamr@2
|
29 |
Converts text between Unicode (UCS-2) and the two Unicode transformation
|
williamr@2
|
30 |
formats UTF-7 and UTF-8. There are no functions to convert directly between
|
williamr@2
|
31 |
UTF-7 and UTF-8.
|
williamr@2
|
32 |
|
williamr@2
|
33 |
Objects of this class do not need to be created because all the member functions
|
williamr@2
|
34 |
are static. The four functions are passed text in the second argument and
|
williamr@2
|
35 |
output the resulting text in the first argument. Sixteen-bit descriptors are
|
williamr@2
|
36 |
used to hold text encoded in UCS-2 (i.e. normal 16 bit Unicode), and eight-bit
|
williamr@2
|
37 |
descriptors are used to hold text encoded in either of the transformation
|
williamr@2
|
38 |
formats.
|
williamr@2
|
39 |
|
williamr@2
|
40 |
The conversion functions return the number of characters which were not converted
|
williamr@2
|
41 |
because the output descriptor was not long enough to hold all of the converted
|
williamr@2
|
42 |
text. This allows users of this class to perform partial conversions on an
|
williamr@2
|
43 |
input descriptor, handling the case when the input descriptor is truncated
|
williamr@2
|
44 |
mid way through a multi-byte character. The caller does not have to guess
|
williamr@2
|
45 |
how big to make the output descriptor for a given input descriptor- they
|
williamr@2
|
46 |
can simply do the conversion in a loop using a small output descriptor. The
|
williamr@2
|
47 |
ability to handle truncated descriptors is particularly useful if the caller
|
williamr@2
|
48 |
is receiving information in chunks from an external source.
|
williamr@2
|
49 |
@publishedAll
|
williamr@2
|
50 |
@released
|
williamr@2
|
51 |
*/
|
williamr@2
|
52 |
{
|
williamr@2
|
53 |
public:
|
williamr@2
|
54 |
/** Conversion error flags. At this stage there is only one error flag
|
williamr@2
|
55 |
- others may be added in the future. */
|
williamr@2
|
56 |
enum TError
|
williamr@2
|
57 |
{
|
williamr@2
|
58 |
/** The input descriptor contains a single corrupt character. This
|
williamr@2
|
59 |
might occur when the input descriptor only contains some of the bytes
|
williamr@2
|
60 |
of a single multi-byte character. */
|
williamr@2
|
61 |
EErrorIllFormedInput=KErrCorrupt
|
williamr@2
|
62 |
};
|
williamr@2
|
63 |
|
williamr@2
|
64 |
/** Initial value for the state argument in a set of related calls to
|
williamr@2
|
65 |
ConvertToUnicode(). */
|
williamr@2
|
66 |
enum {KStateDefault=0};
|
williamr@2
|
67 |
public:
|
williamr@2
|
68 |
// 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
|
williamr@2
|
69 |
IMPORT_C static TInt ConvertFromUnicodeToUtf7(TDes8& aUtf7, const TDesC16& aUnicode, TBool aEncodeOptionalDirectCharactersInBase64);
|
williamr@2
|
70 |
static TInt ConvertFromUnicodeToUtf7(TDes8& aUtf7, const TDesC16& aUnicode, TBool aIsImapUtf7, TBool aEncodeOptionalDirectCharactersInBase64);
|
williamr@2
|
71 |
IMPORT_C static TInt ConvertFromUnicodeToUtf8(TDes8& aUtf8, const TDesC16& aUnicode);
|
williamr@2
|
72 |
static TInt ConvertFromUnicodeToUtf8(TDes8& aUtf8, const TDesC16& aUnicode, TBool aGenerateJavaConformantUtf8);
|
williamr@2
|
73 |
IMPORT_C static TInt ConvertToUnicodeFromUtf7(TDes16& aUnicode, const TDesC8& aUtf7, TInt& aState);
|
williamr@2
|
74 |
static TInt ConvertToUnicodeFromUtf7(TDes16& aUnicode, const TDesC8& aUtf7, TBool aIsImapUtf7, TInt& aState);
|
williamr@2
|
75 |
IMPORT_C static TInt ConvertToUnicodeFromUtf8(TDes16& aUnicode, const TDesC8& aUtf8);
|
williamr@2
|
76 |
static TInt ConvertToUnicodeFromUtf8(TDes16& aUnicode, const TDesC8& aUtf8, TBool aGenerateJavaConformantUtf8);
|
williamr@2
|
77 |
static TInt ConvertToUnicodeFromUtf8(TDes16& aUnicode, const TDesC8& aUtf8, TBool aGenerateJavaConformantUtf8,
|
williamr@2
|
78 |
TInt& aNumberOfUnconvertibleCharacters, TInt& aIndexOfFirstByteOfFirstUnconvertibleCharacter);
|
williamr@2
|
79 |
|
williamr@2
|
80 |
IMPORT_C static HBufC8* ConvertFromUnicodeToUtf7L(const TDesC16& aUnicode,TBool aEncodeOptionalDirectCharactersInBase64);
|
williamr@2
|
81 |
IMPORT_C static HBufC8* ConvertFromUnicodeToUtf8L(const TDesC16& aUnicode);
|
williamr@2
|
82 |
IMPORT_C static HBufC16* ConvertToUnicodeFromUtf7L(const TDesC8& aUtf7);
|
williamr@2
|
83 |
IMPORT_C static HBufC16* ConvertToUnicodeFromUtf8L(const TDesC8& aUtf8);
|
williamr@2
|
84 |
|
williamr@2
|
85 |
|
williamr@2
|
86 |
};
|
williamr@2
|
87 |
|
williamr@2
|
88 |
#endif
|
williamr@4
|
89 |
|