unicode.h

Go to the documentation of this file.
00001 #ifndef TAGLIB_UNICODE_H
00002 #define TAGLIB_UNICODE_H
00003 
00004 /*******************************************************************************
00005  *                                                                             *
00006  * THIS FILE IS INCLUDED IN TAGLIB, BUT IS NOT COPYRIGHTED BY THE TAGLIB       *
00007  * AUTHORS, NOT PART OF THE TAGLIB API AND COULD GO AWAY AT ANY POINT IN TIME. *
00008  * AS SUCH IT SHOULD BE CONSIERED FOR INTERNAL USE ONLY.                       *
00009  *                                                                             *
00010  *******************************************************************************/
00011 
00012 #ifndef DO_NOT_DOCUMENT  // tell Doxygen not to document this header
00013 
00014 /*
00015  * Copyright 2001 Unicode, Inc.
00016  * 
00017  * Disclaimer
00018  * 
00019  * This source code is provided as is by Unicode, Inc. No claims are
00020  * made as to fitness for any particular purpose. No warranties of any
00021  * kind are expressed or implied. The recipient agrees to determine
00022  * applicability of information provided. If this file has been
00023  * purchased on magnetic or optical media from Unicode, Inc., the
00024  * sole remedy for any claim will be exchange of defective media
00025  * within 90 days of receipt.
00026  * 
00027  * Limitations on Rights to Redistribute This Code
00028  * 
00029  * Unicode, Inc. hereby grants the right to freely use the information
00030  * supplied in this file in the creation of products supporting the
00031  * Unicode Standard, and to make copies of this file in any form
00032  * for internal or external distribution as long as this notice
00033  * remains attached.
00034  */
00035 
00036 /*
00037  * This file has been modified by Scott Wheeler <wheeler@kde.org> to remove
00038  * the UTF32 conversion functions and to place the appropriate functions
00039  * in their own C++ namespace.
00040  */
00041 
00042 /* ---------------------------------------------------------------------
00043 
00044     Conversions between UTF32, UTF-16, and UTF-8.  Header file.
00045 
00046     Several functions are included here, forming a complete set of
00047     conversions between the three formats.  UTF-7 is not included
00048     here, but is handled in a separate source file.
00049 
00050     Each of these routines takes pointers to input buffers and output
00051     buffers.  The input buffers are const.
00052 
00053     Each routine converts the text between *sourceStart and sourceEnd,
00054     putting the result into the buffer between *targetStart and
00055     targetEnd. Note: the end pointers are *after* the last item: e.g. 
00056     *(sourceEnd - 1) is the last item.
00057 
00058     The return result indicates whether the conversion was successful,
00059     and if not, whether the problem was in the source or target buffers.
00060     (Only the first encountered problem is indicated.)
00061 
00062     After the conversion, *sourceStart and *targetStart are both
00063     updated to point to the end of last text successfully converted in
00064     the respective buffers.
00065 
00066     Input parameters:
00067     sourceStart - pointer to a pointer to the source buffer.
00068         The contents of this are modified on return so that
00069         it points at the next thing to be converted.
00070     targetStart - similarly, pointer to pointer to the target buffer.
00071     sourceEnd, targetEnd - respectively pointers to the ends of the
00072         two buffers, for overflow checking only.
00073 
00074     These conversion functions take a ConversionFlags argument. When this
00075     flag is set to strict, both irregular sequences and isolated surrogates
00076     will cause an error.  When the flag is set to lenient, both irregular
00077     sequences and isolated surrogates are converted.
00078 
00079     Whether the flag is strict or lenient, all illegal sequences will cause
00080     an error return. This includes sequences such as: <F4 90 80 80>, <C0 80>,
00081     or <A0> in UTF-8, and values above 0x10FFFF in UTF-32. Conformant code
00082     must check for illegal sequences.
00083 
00084     When the flag is set to lenient, characters over 0x10FFFF are converted
00085     to the replacement character; otherwise (when the flag is set to strict)
00086     they constitute an error.
00087 
00088     Output parameters:
00089     The value "sourceIllegal" is returned from some routines if the input
00090     sequence is malformed.  When "sourceIllegal" is returned, the source
00091     value will point to the illegal value that caused the problem. E.g.,
00092     in UTF-8 when a sequence is malformed, it points to the start of the
00093     malformed sequence.  
00094 
00095     Author: Mark E. Davis, 1994.
00096     Rev History: Rick McGowan, fixes & updates May 2001.
00097          Fixes & updates, Sept 2001.
00098 
00099 ------------------------------------------------------------------------ */
00100 
00101 /* ---------------------------------------------------------------------
00102     The following 4 definitions are compiler-specific.
00103     The C standard does not guarantee that wchar_t has at least
00104     16 bits, so wchar_t is no less portable than unsigned short!
00105     All should be unsigned values to avoid sign extension during
00106     bit mask & shift operations.
00107 ------------------------------------------------------------------------ */
00108 
00109 /* Some fundamental constants */
00110 #define UNI_REPLACEMENT_CHAR (UTF32)0x0000FFFD
00111 #define UNI_MAX_BMP (UTF32)0x0000FFFF
00112 #define UNI_MAX_UTF16 (UTF32)0x0010FFFF
00113 #define UNI_MAX_UTF32 (UTF32)0x7FFFFFFF
00114 
00115 namespace Unicode {
00116 
00117 typedef unsigned long   UTF32;  /* at least 32 bits */
00118 typedef unsigned short  UTF16;  /* at least 16 bits */
00119 typedef unsigned char   UTF8;   /* typically 8 bits */
00120 typedef unsigned char   Boolean; /* 0 or 1 */
00121 
00122 typedef enum {
00123     conversionOK = 0,   /* conversion successful */
00124     sourceExhausted = 1,    /* partial character in source, but hit end */
00125     targetExhausted = 2,    /* insuff. room in target for conversion */
00126     sourceIllegal = 3   /* source sequence is illegal/malformed */
00127 } ConversionResult;
00128 
00129 typedef enum {
00130     strictConversion = 0,
00131     lenientConversion
00132 } ConversionFlags;
00133 
00134 ConversionResult ConvertUTF8toUTF16 (
00135         const UTF8** sourceStart, const UTF8* sourceEnd, 
00136         UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags);
00137 
00138 ConversionResult ConvertUTF16toUTF8 (
00139         const UTF16** sourceStart, const UTF16* sourceEnd, 
00140         UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags);
00141         
00142 Boolean isLegalUTF8Sequence(const UTF8 *source, const UTF8 *sourceEnd);
00143 
00144 } // namespace Unicode
00145 
00146 /* --------------------------------------------------------------------- */
00147 
00148 #endif
00149 #endif