intl/uconv/public/nsIUnicodeDecoder.h@fc2d59ddac77 (annotated)
intl/uconv/public/nsIUnicodeDecoder.h
Wed, 31 Dec 2014 07:22:50 +0100
- author
- Michael Schloh von Bennewitz <michael@schloh.com>
- date
- Wed, 31 Dec 2014 07:22:50 +0100
- branch
- TOR_BUG_3246
- changeset 4
- fc2d59ddac77
- permissions
- -rw-r--r--
Correct previous dual key logic pending first delivery installment.
| michael@0 | 1 | /* -*- Mode: C++; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */ |
| michael@0 | 2 | /* This Source Code Form is subject to the terms of the Mozilla Public |
| michael@0 | 3 | * License, v. 2.0. If a copy of the MPL was not distributed with this |
| michael@0 | 4 | * file, You can obtain one at http://mozilla.org/MPL/2.0/. */ |
| michael@0 | 5 | |
| michael@0 | 6 | #ifndef nsIUnicodeDecoder_h___ |
| michael@0 | 7 | #define nsIUnicodeDecoder_h___ |
| michael@0 | 8 | |
| michael@0 | 9 | #include "nscore.h" |
| michael@0 | 10 | #include "nsISupports.h" |
| michael@0 | 11 | |
| michael@0 | 12 | // Interface ID for our Unicode Decoder interface |
| michael@0 | 13 | // {25359602-FC70-4d13-A9AB-8086D3827C0D} |
| michael@0 | 14 | //NS_DECLARE_ID(kIUnicodeDecoderIID, |
| michael@0 | 15 | // 0x25359602, 0xfc70, 0x4d13, 0xa9, 0xab, 0x80, 0x86, 0xd3, 0x82, 0x7c, 0xd); |
| michael@0 | 16 | |
| michael@0 | 17 | #define NS_IUNICODEDECODER_IID \ |
| michael@0 | 18 | { 0x25359602, 0xfc70, 0x4d13, \ |
| michael@0 | 19 | { 0xa9, 0xab, 0x80, 0x86, 0xd3, 0x82, 0x7c, 0xd }} |
| michael@0 | 20 | |
| michael@0 | 21 | |
| michael@0 | 22 | #define NS_UNICODEDECODER_CONTRACTID_BASE "@mozilla.org/intl/unicode/decoder;1?charset=" |
| michael@0 | 23 | |
| michael@0 | 24 | /** |
| michael@0 | 25 | * Interface for a Converter from a Charset into Unicode. |
| michael@0 | 26 | * |
| michael@0 | 27 | * @created 23/Nov/1998 |
| michael@0 | 28 | * @author Catalin Rotaru [CATA] |
| michael@0 | 29 | */ |
| michael@0 | 30 | class nsIUnicodeDecoder : public nsISupports |
| michael@0 | 31 | { |
| michael@0 | 32 | public: |
| michael@0 | 33 | NS_DECLARE_STATIC_IID_ACCESSOR(NS_IUNICODEDECODER_IID) |
| michael@0 | 34 | |
| michael@0 | 35 | enum { |
| michael@0 | 36 | kOnError_Recover, // on an error, recover and continue |
| michael@0 | 37 | kOnError_Signal // on an error, stop and signal |
| michael@0 | 38 | }; |
| michael@0 | 39 | |
| michael@0 | 40 | /** |
| michael@0 | 41 | * Converts the data from one Charset to Unicode. |
| michael@0 | 42 | * |
| michael@0 | 43 | * About the byte ordering: |
| michael@0 | 44 | * - For input, if the converter cares (that depends of the charset, for |
| michael@0 | 45 | * example a singlebyte will ignore the byte ordering) it should assume |
| michael@0 | 46 | * network order. If necessary and requested, we can add a method |
| michael@0 | 47 | * SetInputByteOrder() so that the reverse order can be used, too. That |
| michael@0 | 48 | * method would have as default the assumed network order. |
| michael@0 | 49 | * - The output stream is Unicode, having the byte order which is internal |
| michael@0 | 50 | * for the machine on which the converter is running on. |
| michael@0 | 51 | * |
| michael@0 | 52 | * Unless there is not enough output space, this method must consume all the |
| michael@0 | 53 | * available input data! The eventual incomplete final character data will be |
| michael@0 | 54 | * stored internally in the converter and used when the method is called |
| michael@0 | 55 | * again for continuing the conversion. This way, the caller will not have to |
| michael@0 | 56 | * worry about managing incomplete input data by mergeing it with the next |
| michael@0 | 57 | * buffer. |
| michael@0 | 58 | * |
| michael@0 | 59 | * Error conditions: |
| michael@0 | 60 | * If the read value does not belong to this character set, one should |
| michael@0 | 61 | * replace it with the Unicode special 0xFFFD. When an actual input error is |
| michael@0 | 62 | * encountered, like a format error, the converter stop and return error. |
| michael@0 | 63 | * However, we should keep in mind that we need to be lax in decoding. When |
| michael@0 | 64 | * a decoding error is returned to the caller, it is the caller's |
| michael@0 | 65 | * responsibility to advance over the bad byte (unless aSrcLength is -1 in |
| michael@0 | 66 | * which case the caller should call the decoder with 0 offset again) and |
| michael@0 | 67 | * reset the decoder before trying to call the decoder again. |
| michael@0 | 68 | * |
| michael@0 | 69 | * Converter required behavior: |
| michael@0 | 70 | * In this order: when output space is full - return right away. When input |
| michael@0 | 71 | * data is wrong, return input pointer right after the wrong byte. When |
| michael@0 | 72 | * partial input, it will be consumed and cached. All the time input pointer |
| michael@0 | 73 | * will show how much was actually consumed and how much was actually |
| michael@0 | 74 | * written. |
| michael@0 | 75 | * |
| michael@0 | 76 | * @param aSrc [IN] the source data buffer |
| michael@0 | 77 | * @param aSrcLength [IN/OUT] the length of source data buffer; after |
| michael@0 | 78 | * conversion will contain the number of bytes read or |
| michael@0 | 79 | * -1 on error to indicate that the caller should re-push |
| michael@0 | 80 | * the same buffer after resetting the decoder |
| michael@0 | 81 | * @param aDest [OUT] the destination data buffer |
| michael@0 | 82 | * @param aDestLength [IN/OUT] the length of the destination data buffer; |
| michael@0 | 83 | * after conversion will contain the number of Unicode |
| michael@0 | 84 | * characters written |
| michael@0 | 85 | * @return NS_PARTIAL_MORE_INPUT if only a partial conversion was |
| michael@0 | 86 | * done; more input is needed to continue |
| michael@0 | 87 | * NS_PARTIAL_MORE_OUTPUT if only a partial conversion |
| michael@0 | 88 | * was done; more output space is needed to continue |
| michael@0 | 89 | * NS_ERROR_ILLEGAL_INPUT if an illegal input sequence |
| michael@0 | 90 | * was encountered and the behavior was set to "signal"; |
| michael@0 | 91 | * the caller must skip over one byte, reset the decoder |
| michael@0 | 92 | * and retry. |
| michael@0 | 93 | */ |
| michael@0 | 94 | NS_IMETHOD Convert(const char * aSrc, int32_t * aSrcLength, |
| michael@0 | 95 | char16_t * aDest, int32_t * aDestLength) = 0; |
| michael@0 | 96 | |
| michael@0 | 97 | /** |
| michael@0 | 98 | * Returns a quick estimation of the size of the buffer needed to hold the |
| michael@0 | 99 | * converted data. Remember: this estimation is >= with the actual size of |
| michael@0 | 100 | * the buffer needed. It will be computed for the "worst case" |
| michael@0 | 101 | * |
| michael@0 | 102 | * @param aSrc [IN] the source data buffer |
| michael@0 | 103 | * @param aSrcLength [IN] the length of source data buffer |
| michael@0 | 104 | * @param aDestLength [OUT] the needed size of the destination buffer |
| michael@0 | 105 | * @return NS_EXACT_LENGTH if an exact length was computed |
| michael@0 | 106 | * NS_OK is all we have is an approximation |
| michael@0 | 107 | */ |
| michael@0 | 108 | NS_IMETHOD GetMaxLength(const char * aSrc, int32_t aSrcLength, |
| michael@0 | 109 | int32_t * aDestLength) = 0; |
| michael@0 | 110 | |
| michael@0 | 111 | /** |
| michael@0 | 112 | * Resets the charset converter so it may be recycled for a completely |
| michael@0 | 113 | * different and urelated buffer of data. |
| michael@0 | 114 | */ |
| michael@0 | 115 | NS_IMETHOD Reset() = 0; |
| michael@0 | 116 | |
| michael@0 | 117 | /** |
| michael@0 | 118 | * Specify what to do when a character cannot be mapped into unicode |
| michael@0 | 119 | * |
| michael@0 | 120 | * @param aBehavior [IN] the desired behavior |
| michael@0 | 121 | * @see kOnError_Recover |
| michael@0 | 122 | * @see kOnError_Signal |
| michael@0 | 123 | */ |
| michael@0 | 124 | virtual void SetInputErrorBehavior(int32_t aBehavior) = 0; |
| michael@0 | 125 | |
| michael@0 | 126 | /** |
| michael@0 | 127 | * return the UNICODE character for unmapped character |
| michael@0 | 128 | */ |
| michael@0 | 129 | virtual char16_t GetCharacterForUnMapped() = 0; |
| michael@0 | 130 | }; |
| michael@0 | 131 | |
| michael@0 | 132 | NS_DEFINE_STATIC_IID_ACCESSOR(nsIUnicodeDecoder, NS_IUNICODEDECODER_IID) |
| michael@0 | 133 | |
| michael@0 | 134 | #endif /* nsIUnicodeDecoder_h___ */ |
