mlConvertUTF.h

Go to the documentation of this file.

 
/*
 * Copyright 2001 Unicode, Inc.
 *
 * Disclaimer
 *
 * This source code is provided as is by Unicode, Inc. No claims are
 * made as to fitness for any particular purpose. No warranties of any
 * kind are expressed or implied. The recipient agrees to determine
 * applicability of information provided. If this file has been
 * purchased on magnetic or optical media from Unicode, Inc., the
 * sole remedy for any claim will be exchange of defective media
 * within 90 days of receipt.
 *
 * Limitations on Rights to Redistribute This Code
 *
 * Unicode, Inc. hereby grants the right to freely use the information
 * supplied in this file in the creation of products supporting the
 * Unicode Standard, and to make copies of this file in any form
 * for internal or external distribution as long as this notice
 * remains attached.
 */
 
/* ---------------------------------------------------------------------
 
    Conversions between UTF-32, UTF-16, and UTF-8.  Header file.
 
    Several functions are included here, forming a complete set of
    conversions between the three formats.  UTF-7 is not included
    here, but is handled in a separate source file.
 
    Each of these routines takes pointers to input buffers and output
    buffers. The input buffers are const.
 
    Each routine converts the text between *sourceStart and sourceEnd,
    putting the result into the buffer between *targetStart and
    targetEnd. Note: the end pointers are *after* the last item: e.g.,
    *(sourceEnd - 1) is the last item.
 
    The return result indicates whether the conversion was successful,
    and if not, whether the problem was in the source or target buffers.
    (Only the first encountered problem is indicated.)
 
    After the conversion, *sourceStart and *targetStart are both
    updated to point to the end of last text successfully converted in
    the respective buffers.
 
    General (parameter) errors:
    - If any illegal parameter (that means NULL pointers) is passed,
      then in cases of sourceStart, sourceEnd, or length "sourceIllegal"
      is returned. \n
      In case of NULL targetStart or targetEnd, then "targetExhausted" is
      returned. \n
      None of any parameter passed to those functions will
      be changed in those cases.
    - In cases of caught exceptions, 'sourceIllegal' or 'false' will be
      returned after sending a fatal error message to the ML error handler.
      The state of the target buffers or return pointers is left
      undefined then.
 
    Input parameters:
    sourceStart - pointer to a pointer to the source buffer.
    The contents of this are modified on return so that
    it points at the next thing to be converted.
    targetStart - similarly, pointer to pointer to the target buffer.
    sourceEnd, targetEnd - respectively pointers to the ends of the
    two buffers, for overflow checking only.
 
    These conversion functions take a ConversionFlags argument. If this
    flag is set to strict, both irregular sequences and isolated surrogates
    will cause an error. If the flag is set to lenient, both irregular
    sequences and isolated surrogates are converted.
 
    Whether the flag is strict or lenient, all illegal sequences will cause
    an error return. This includes sequences such as: <F4 90 80 80>, <C0 80>,
    or <A0> in UTF-8, and values above 0x10FFFF in UTF-32. Conform code
    must check for illegal sequences.
 
    If the flag is set to lenient, characters over 0x10FFFF are converted
    to the replacement character; otherwise (if the flag is set to strict)
    they constitute an error.
 
    Output parameters:
    The value 'sourceIllegal' is returned from some routines if the input
    sequence is malformed. If 'sourceIllegal' is returned, the source
    value will point to the illegal value that caused the problem. E.g.,
    in UTF-8 if a sequence is malformed, it points to the start of the
    malformed sequence.
 
    Author: Mark E. Davis, 1994.
    Rev History: Rick McGowan, fixes & updates May 2001.
    Fixes & updates, Sept 2001.
 
------------------------------------------------------------------------ */
 
//--------------------------------------------------------------------
//--------------------------------------------------------------------
 
#ifndef __mlConvertUTF_H
#define __mlConvertUTF_H
 
#include "mlTypeDefs.h"
 
//--------------------------------------------------------------------
//--------------------------------------------------------------------
typedef MLuint32 UTF32;   
typedef MLuint16 UTF16;   
typedef MLuint8  UTF8;    
 
 
//--------------------------------------------------------------------
//--------------------------------------------------------------------
#define UNI_REPLACEMENT_CHAR (static_cast<UTF32>(0x0000FFFD))  
#define UNI_MAX_BMP          (static_cast<UTF32>(0x0000FFFF))
#define UNI_MAX_UTF16        (static_cast<UTF32>(0x0010FFFF))
#define UNI_MAX_UTF32        (static_cast<UTF32>(0x7FFFFFFF))
 
//--------------------------------------------------------------------
//--------------------------------------------------------------------
typedef enum {
  conversionOK,     
  sourceExhausted,  
  targetExhausted,  
  sourceIllegal     
} ConversionResult;
 
//--------------------------------------------------------------------
//--------------------------------------------------------------------
typedef enum {
  strictConversion = 0, 
  lenientConversion     
} ConversionFlags;
 
//--------------------------------------------------------------------
/* This is for C++ and does no harm in C */
//--------------------------------------------------------------------
#ifdef __cplusplus
extern "C" {
#endif
 
//---------------------------------------
//---------------------------------------
 
ConversionResult ConvertUTF32toUTF16 (const UTF32   **sourceStart,
                                      const UTF32    *sourceEnd,
                                      UTF16         **targetStart,
                                      UTF16          *targetEnd,
                                      ConversionFlags flags);
 
ConversionResult ConvertUTF16toUTF32 (const UTF16   **sourceStart,
                                      const UTF16    *sourceEnd,
                                      UTF32         **targetStart,
                                      UTF32          *targetEnd,
                                      ConversionFlags flags);
 
ConversionResult ConvertUTF16toUTF8 ( const UTF16   **sourceStart,
                                      const UTF16    *sourceEnd,
                                      UTF8          **targetStart,
                                      UTF8           *targetEnd,
                                      ConversionFlags flags);
 
ConversionResult ConvertUTF8toUTF16 ( const UTF8    **sourceStart,
                                      const UTF8     *sourceEnd,
                                      UTF16         **targetStart,
                                      UTF16          *targetEnd,
                                      ConversionFlags flags);
 
ConversionResult ConvertUTF32toUTF8  (const UTF32   **sourceStart,
                                      const UTF32    *sourceEnd,
                                      UTF8          **targetStart,
                                      UTF8           *targetEnd,
                                      ConversionFlags flags);
 
ConversionResult ConvertUTF8toUTF32 ( const UTF8    **sourceStart,
                                      const UTF8     *sourceEnd,
                                      UTF32         **targetStart,
                                      UTF32          *targetEnd);
 
 
 
//---------------------------------------
//---------------------------------------
ConversionResult ConvertUTF8toLatin1 (const UTF8     *sourceStart,
                                      char           *targetStart,
                                      char           *targetEnd,
                                      ConversionFlags flags);
 
ConversionResult CalculateNumCharsInUTF8 (const UTF8     *sourceStart,
                                          unsigned int   *length,
                                          ConversionFlags flags);
 
ConversionResult CalculateUTF16BufferSizeForUTF8 (const UTF8     *sourceStart,
                                                  unsigned int   *length,
                                                  ConversionFlags flags);
 
 
 
#ifdef __cplusplus
}
#endif
 
/* --------------------------------------------------------------------- */
 
#endif // __mlConvertUTF_H