Dogcows Code - chaz/yoink/blob - src/moof/ConvertUTF.h

   1
   2 #ifndef _CONVERTUTF_H_
   3 #define _CONVERTUTF_H_
   4
   5 /*
   6  * Copyright 2001-2004 Unicode, Inc.
   7  *
   8  * Disclaimer
   9  *
  10  * This source code is provided as is by Unicode, Inc. No claims are
  11  * made as to fitness for any particular purpose. No warranties of any
  12  * kind are expressed or implied. The recipient agrees to determine
  13  * applicability of information provided. If this file has been
  14  * purchased on magnetic or optical media from Unicode, Inc., the
  15  * sole remedy for any claim will be exchange of defective media
  16  * within 90 days of receipt.
  17  *
  18  * Limitations on Rights to Redistribute This Code
  19  *
  20  * Unicode, Inc. hereby grants the right to freely use the information
  21  * supplied in this file in the creation of products supporting the
  22  * Unicode Standard, and to make copies of this file in any form
  23  * for internal or external distribution as long as this notice
  24  * remains attached.
  25  */
  26
  27 /* ---------------------------------------------------------------------
  28
  29     Conversions between UTF32, UTF-16, and UTF-8.  Header file.
  30
  31     Several funtions are included here, forming a complete set of
  32     conversions between the three formats.  UTF-7 is not included
  33     here, but is handled in a separate source file.
  34
  35     Each of these routines takes pointers to input buffers and output
  36     buffers.  The input buffers are const.
  37
  38     Each routine converts the text between *sourceStart and sourceEnd,
  39     putting the result into the buffer between *targetStart and
  40     targetEnd. Note: the end pointers are *after* the last item: e.g.
  41     *(sourceEnd - 1) is the last item.
  42
  43     The return result indicates whether the conversion was successful,
  44     and if not, whether the problem was in the source or target buffers.
  45     (Only the first encountered problem is indicated.)
  46
  47     After the conversion, *sourceStart and *targetStart are both
  48     updated to point to the end of last text successfully converted in
  49     the respective buffers.
  50
  51     Input parameters:
  52         sourceStart - pointer to a pointer to the source buffer.
  53                 The contents of this are modified on return so that
  54                 it points at the next thing to be converted.
  55         targetStart - similarly, pointer to pointer to the target buffer.
  56         sourceEnd, targetEnd - respectively pointers to the ends of the
  57                 two buffers, for overflow checking only.
  58
  59     These conversion functions take a ConversionFlags argument. When this
  60     flag is set to strict, both irregular sequences and isolated surrogates
  61     will cause an error.  When the flag is set to lenient, both irregular
  62     sequences and isolated surrogates are converted.
  63
  64     Whether the flag is strict or lenient, all illegal sequences will cause
  65     an error return. This includes sequences such as: <F4 90 80 80>, <C0 80>,
  66     or <A0> in UTF-8, and values above 0x10FFFF in UTF-32. Conformant code
  67     must check for illegal sequences.
  68
  69     When the flag is set to lenient, characters over 0x10FFFF are converted
  70     to the replacement character; otherwise (when the flag is set to strict)
  71     they constitute an error.
  72
  73     Output parameters:
  74         The value "sourceIllegal" is returned from some routines if the input
  75         sequence is malformed.  When "sourceIllegal" is returned, the source
  76         value will point to the illegal value that caused the problem. E.g.,
  77         in UTF-8 when a sequence is malformed, it points to the start of the
  78         malformed sequence.
  79
  80     Author: Mark E. Davis, 1994.
  81     Rev History: Rick McGowan, fixes & updates May 2001.
  82                  Fixes & updates, Sept 2001.
  83
  84 ------------------------------------------------------------------------ */
  85
  86 /* ---------------------------------------------------------------------
  87     The following 4 definitions are compiler-specific.
  88     The C standard does not guarantee that wchar_t has at least
  89     16 bits, so wchar_t is no less portable than unsigned short!
  90     All should be unsigned values to avoid sign extension during
  91     bit mask & shift operations.
  92 ------------------------------------------------------------------------ */
  93
  94 #include <stdint.h>
  95 #include <stdbool.h>
  96
  97 typedef uint32_t        UTF32;          /* exactly 32 bits */
  98 typedef uint16_t        UTF16;          /* exactly 16 bits */
  99 typedef uint8_t         UTF8;           /* exactly  8 bits */
 100
 101 /* Some fundamental constants */
 102 #define UNI_REPLACEMENT_CHAR (UTF32)0x0000FFFD
 103 #define UNI_MAX_BMP (UTF32)0x0000FFFF
 104 #define UNI_MAX_UTF16 (UTF32)0x0010FFFF
 105 #define UNI_MAX_UTF32 (UTF32)0x7FFFFFFF
 106 #define UNI_MAX_LEGAL_UTF32 (UTF32)0x0010FFFF
 107
 108 typedef enum {
 109         conversionOK,           /* conversion successful */
 110         sourceExhausted,        /* partial character in source, but hit end */
 111         targetExhausted,        /* insuff. room in target for conversion */
 112         sourceIllegal           /* source sequence is illegal/malformed */
 113 } ConversionResult;
 114
 115 typedef enum {
 116         strictConversion = 0,
 117         lenientConversion
 118 } ConversionFlags;
 119
 120 /* This is for C++ and does no harm in C */
 121 #ifdef __cplusplus
 122 extern "C" {
 123 #endif
 124
 125 ConversionResult ConvertUTF8toUTF16 (
 126                 const UTF8** sourceStart, const UTF8* sourceEnd,
 127                 UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags);
 128
 129 ConversionResult ConvertUTF16toUTF8 (
 130                 const UTF16** sourceStart, const UTF16* sourceEnd,
 131                 UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags);
 132
 133 ConversionResult ConvertUTF8toUTF32 (
 134                 const UTF8** sourceStart, const UTF8* sourceEnd,
 135                 UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags);
 136
 137 ConversionResult ConvertUTF32toUTF8 (
 138                 const UTF32** sourceStart, const UTF32* sourceEnd,
 139                 UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags);
 140
 141 ConversionResult ConvertUTF16toUTF32 (
 142                 const UTF16** sourceStart, const UTF16* sourceEnd,
 143                 UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags);
 144
 145 ConversionResult ConvertUTF32toUTF16 (
 146                 const UTF32** sourceStart, const UTF32* sourceEnd,
 147                 UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags);
 148
 149 bool isLegalUTF8Sequence(const UTF8 *source, const UTF8 *sourceEnd);
 150
 151 #ifdef __cplusplus
 152 }
 153 #endif
 154
 155 /* --------------------------------------------------------------------- */
 156
 157 #endif // _CONVERTUTF_H_
 158