| 1 | // © 2016 and later: Unicode, Inc. and others. |
| 2 | // License & terms of use: http://www.unicode.org/copyright.html |
| 3 | /* |
| 4 | ********************************************************************** |
| 5 | * Copyright (C) 2000-2004, International Business Machines |
| 6 | * Corporation and others. All Rights Reserved. |
| 7 | ********************************************************************** |
| 8 | * ucnv_cb.h: |
| 9 | * External APIs for the ICU's codeset conversion library |
| 10 | * Helena Shih |
| 11 | * |
| 12 | * Modification History: |
| 13 | * |
| 14 | * Date Name Description |
| 15 | */ |
| 16 | |
| 17 | /** |
| 18 | * \file |
| 19 | * \brief C UConverter functions to aid the writers of callbacks |
| 20 | * |
| 21 | * <h2> Callback API for UConverter </h2> |
| 22 | * |
| 23 | * These functions are provided here for the convenience of the callback |
| 24 | * writer. If you are just looking for callback functions to use, please |
| 25 | * see ucnv_err.h. DO NOT call these functions directly when you are |
| 26 | * working with converters, unless your code has been called as a callback |
| 27 | * via ucnv_setFromUCallback or ucnv_setToUCallback !! |
| 28 | * |
| 29 | * A note about error codes and overflow. Unlike other ICU functions, |
| 30 | * these functions do not expect the error status to be U_ZERO_ERROR. |
| 31 | * Callbacks must be much more careful about their error codes. |
| 32 | * The error codes used here are in/out parameters, which should be passed |
| 33 | * back in the callback's error parameter. |
| 34 | * |
| 35 | * For example, if you call ucnv_cbfromUWriteBytes to write data out |
| 36 | * to the output codepage, it may return U_BUFFER_OVERFLOW_ERROR if |
| 37 | * the data did not fit in the target. But this isn't a failing error, |
| 38 | * in fact, ucnv_cbfromUWriteBytes may be called AGAIN with the error |
| 39 | * status still U_BUFFER_OVERFLOW_ERROR to attempt to write further bytes, |
| 40 | * which will also go into the internal overflow buffers. |
| 41 | * |
| 42 | * Concerning offsets, the 'offset' parameters here are relative to the start |
| 43 | * of SOURCE. For example, Suppose the string "ABCD" was being converted |
| 44 | * from Unicode into a codepage which doesn't have a mapping for 'B'. |
| 45 | * 'A' will be written out correctly, but |
| 46 | * The FromU Callback will be called on an unassigned character for 'B'. |
| 47 | * At this point, this is the state of the world: |
| 48 | * Target: A [..] [points after A] |
| 49 | * Source: A B [C] D [points to C - B has been consumed] |
| 50 | * 0 1 2 3 |
| 51 | * codePoint = "B" [the unassigned codepoint] |
| 52 | * |
| 53 | * Now, suppose a callback wants to write the substitution character '?' to |
| 54 | * the target. It calls ucnv_cbFromUWriteBytes() to write the ?. |
| 55 | * It should pass ZERO as the offset, because the offset as far as the |
| 56 | * callback is concerned is relative to the SOURCE pointer [which points |
| 57 | * before 'C'.] If the callback goes into the args and consumes 'C' also, |
| 58 | * it would call FromUWriteBytes with an offset of 1 (and advance the source |
| 59 | * pointer). |
| 60 | * |
| 61 | */ |
| 62 | |
| 63 | #ifndef UCNV_CB_H |
| 64 | #define UCNV_CB_H |
| 65 | |
| 66 | #include "unicode/utypes.h" |
| 67 | |
| 68 | #if !UCONFIG_NO_CONVERSION |
| 69 | |
| 70 | #include "unicode/ucnv.h" |
| 71 | #include "unicode/ucnv_err.h" |
| 72 | |
| 73 | /** |
| 74 | * ONLY used by FromU callback functions. |
| 75 | * Writes out the specified byte output bytes to the target byte buffer or to converter internal buffers. |
| 76 | * |
| 77 | * @param args callback fromUnicode arguments |
| 78 | * @param source source bytes to write |
| 79 | * @param length length of bytes to write |
| 80 | * @param offsetIndex the relative offset index from callback. |
| 81 | * @param err error status. If <TT>U_BUFFER_OVERFLOW</TT> is returned, then U_BUFFER_OVERFLOW <STRONG>must</STRONG> |
| 82 | * be returned to the user, because it means that not all data could be written into the target buffer, and some is |
| 83 | * in the converter error buffer. |
| 84 | * @see ucnv_cbFromUWriteSub |
| 85 | * @stable ICU 2.0 |
| 86 | */ |
| 87 | U_STABLE void U_EXPORT2 |
| 88 | ucnv_cbFromUWriteBytes (UConverterFromUnicodeArgs *args, |
| 89 | const char* source, |
| 90 | int32_t length, |
| 91 | int32_t offsetIndex, |
| 92 | UErrorCode * err); |
| 93 | |
| 94 | /** |
| 95 | * ONLY used by FromU callback functions. |
| 96 | * This function will write out the correct substitution character sequence |
| 97 | * to the target. |
| 98 | * |
| 99 | * @param args callback fromUnicode arguments |
| 100 | * @param offsetIndex the relative offset index from the current source pointer to be used |
| 101 | * @param err error status. If <TT>U_BUFFER_OVERFLOW</TT> is returned, then U_BUFFER_OVERFLOW <STRONG>must</STRONG> |
| 102 | * be returned to the user, because it means that not all data could be written into the target buffer, and some is |
| 103 | * in the converter error buffer. |
| 104 | * @see ucnv_cbFromUWriteBytes |
| 105 | * @stable ICU 2.0 |
| 106 | */ |
| 107 | U_STABLE void U_EXPORT2 |
| 108 | ucnv_cbFromUWriteSub (UConverterFromUnicodeArgs *args, |
| 109 | int32_t offsetIndex, |
| 110 | UErrorCode * err); |
| 111 | |
| 112 | /** |
| 113 | * ONLY used by fromU callback functions. |
| 114 | * This function will write out the error character(s) to the target UChar buffer. |
| 115 | * |
| 116 | * @param args callback fromUnicode arguments |
| 117 | * @param source pointer to pointer to first UChar to write [on exit: 1 after last UChar processed] |
| 118 | * @param sourceLimit pointer after last UChar to write |
| 119 | * @param offsetIndex the relative offset index from callback which will be set |
| 120 | * @param err error status <TT>U_BUFFER_OVERFLOW</TT> |
| 121 | * @see ucnv_cbToUWriteSub |
| 122 | * @stable ICU 2.0 |
| 123 | */ |
| 124 | U_STABLE void U_EXPORT2 ucnv_cbFromUWriteUChars(UConverterFromUnicodeArgs *args, |
| 125 | const UChar** source, |
| 126 | const UChar* sourceLimit, |
| 127 | int32_t offsetIndex, |
| 128 | UErrorCode * err); |
| 129 | |
| 130 | /** |
| 131 | * ONLY used by ToU callback functions. |
| 132 | * This function will write out the specified characters to the target |
| 133 | * UChar buffer. |
| 134 | * |
| 135 | * @param args callback toUnicode arguments |
| 136 | * @param source source string to write |
| 137 | * @param length the length of source string |
| 138 | * @param offsetIndex the relative offset index which will be written. |
| 139 | * @param err error status <TT>U_BUFFER_OVERFLOW</TT> |
| 140 | * @see ucnv_cbToUWriteSub |
| 141 | * @stable ICU 2.0 |
| 142 | */ |
| 143 | U_STABLE void U_EXPORT2 ucnv_cbToUWriteUChars (UConverterToUnicodeArgs *args, |
| 144 | const UChar* source, |
| 145 | int32_t length, |
| 146 | int32_t offsetIndex, |
| 147 | UErrorCode * err); |
| 148 | |
| 149 | /** |
| 150 | * ONLY used by ToU callback functions. |
| 151 | * This function will write out the Unicode substitution character (U+FFFD). |
| 152 | * |
| 153 | * @param args callback fromUnicode arguments |
| 154 | * @param offsetIndex the relative offset index from callback. |
| 155 | * @param err error status <TT>U_BUFFER_OVERFLOW</TT> |
| 156 | * @see ucnv_cbToUWriteUChars |
| 157 | * @stable ICU 2.0 |
| 158 | */ |
| 159 | U_STABLE void U_EXPORT2 ucnv_cbToUWriteSub (UConverterToUnicodeArgs *args, |
| 160 | int32_t offsetIndex, |
| 161 | UErrorCode * err); |
| 162 | #endif |
| 163 | |
| 164 | #endif |
| 165 | |