PageRenderTime 19ms CodeModel.GetById 13ms app.highlight 3ms RepoModel.GetById 1ms app.codeStats 0ms

C++ Header | 143 lines | 38 code | 16 blank | 89 comment | 0 complexity | 0a972c593f1864b6e8e9dc16ddc7b755 MD5 | raw file
  2 * Copyright 2001-2004 Unicode, Inc.
  3 *
  4 * Disclaimer
  5 *
  6 * This source code is provided as is by Unicode, Inc. No claims are
  7 * made as to fitness for any particular purpose. No warranties of any
  8 * kind are expressed or implied. The recipient agrees to determine
  9 * applicability of information provided. If this file has been
 10 * purchased on magnetic or optical media from Unicode, Inc., the
 11 * sole remedy for any claim will be exchange of defective media
 12 * within 90 days of receipt.
 13 *
 14 * Limitations on Rights to Redistribute This Code
 15 *
 16 * Unicode, Inc. hereby grants the right to freely use the information
 17 * supplied in this file in the creation of products supporting the
 18 * Unicode Standard, and to make copies of this file in any form
 19 * for internal or external distribution as long as this notice
 20 * remains attached.
 21 */
 23/* ---------------------------------------------------------------------
 25Conversions between UTF32, UTF-16, and UTF-8.  Header file.
 27Several funtions are included here, forming a complete set of
 28conversions between the three formats.  UTF-7 is not included
 29here, but is handled in a separate source file.
 31Each of these routines takes pointers to input buffers and output
 32buffers.  The input buffers are const.
 34Each routine converts the text between *sourceStart and sourceEnd,
 35putting the result into the buffer between *targetStart and
 36targetEnd. Note: the end pointers are *after* the last item: e.g.
 37*(sourceEnd - 1) is the last item.
 39The return result indicates whether the conversion was successful,
 40and if not, whether the problem was in the source or target buffers.
 41(Only the first encountered problem is indicated.)
 43After the conversion, *sourceStart and *targetStart are both
 44updated to point to the end of last text successfully converted in
 45the respective buffers.
 47Input parameters:
 48sourceStart - pointer to a pointer to the source buffer.
 49The contents of this are modified on return so that
 50it points at the next thing to be converted.
 51targetStart - similarly, pointer to pointer to the target buffer.
 52sourceEnd, targetEnd - respectively pointers to the ends of the
 53two buffers, for overflow checking only.
 55These conversion functions take a ConversionFlags argument. When this
 56flag is set to strict, both irregular sequences and isolated surrogates
 57will cause an error.  When the flag is set to lenient, both irregular
 58sequences and isolated surrogates are converted.
 60Whether the flag is strict or lenient, all illegal sequences will cause
 61an error return. This includes sequences such as: <F4 90 80 80>, <C0 80>,
 62or <A0> in UTF-8, and values above 0x10FFFF in UTF-32. Conformant code
 63must check for illegal sequences.
 65When the flag is set to lenient, characters over 0x10FFFF are converted
 66to the replacement character; otherwise (when the flag is set to strict)
 67they constitute an error.
 69Output parameters:
 70The value "sourceIllegal" is returned from some routines if the input
 71sequence is malformed.  When "sourceIllegal" is returned, the source
 72value will point to the illegal value that caused the problem. E.g.,
 73in UTF-8 when a sequence is malformed, it points to the start of the
 74malformed sequence.
 76Author: Mark E. Davis, 1994.
 77Rev History: Rick McGowan, fixes & updates May 2001.
 78Fixes & updates, Sept 2001.
 80------------------------------------------------------------------------ */
 82/* ---------------------------------------------------------------------
 83The following 4 definitions are compiler-specific.
 84The C standard does not guarantee that wchar_t has at least
 8516 bits, so wchar_t is no less portable than unsigned short!
 86All should be unsigned values to avoid sign extension during
 87bit mask & shift operations.
 88------------------------------------------------------------------------ */
 90typedef unsigned long	UTF32;	/* at least 32 bits */
 91typedef unsigned short	UTF16;	/* at least 16 bits */
 92typedef unsigned char	UTF8;	/* typically 8 bits */
 93typedef unsigned char	Boolean; /* 0 or 1 */
 95/* Some fundamental constants */
 97#define UNI_MAX_BMP (UTF32)0x0000FFFF
 98#define UNI_MAX_UTF16 (UTF32)0x0010FFFF
 99#define UNI_MAX_UTF32 (UTF32)0x7FFFFFFF
100#define UNI_MAX_LEGAL_UTF32 (UTF32)0x0010FFFF
102typedef enum {
103	conversionOK, 		/* conversion successful */
104	sourceExhausted,	/* partial character in source, but hit end */
105	targetExhausted,	/* insuff. room in target for conversion */
106	sourceIllegal		/* source sequence is illegal/malformed */
107} ConversionResult;
109typedef enum {
110	strictConversion = 0,
111	lenientConversion
112} ConversionFlags;
114/* This is for C++ and does no harm in C */
115#ifdef __cplusplus
116extern "C" {
119ConversionResult ConvertUTF8toUTF16 (const UTF8** sourceStart, const UTF8* sourceEnd,
120                                     UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags);
122ConversionResult ConvertUTF16toUTF8 (const UTF16** sourceStart, const UTF16* sourceEnd,
123                                     UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags);
125ConversionResult ConvertUTF8toUTF32 (const UTF8** sourceStart, const UTF8* sourceEnd,
126                                     UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags);
128ConversionResult ConvertUTF32toUTF8 (const UTF32** sourceStart, const UTF32* sourceEnd,
129                                     UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags);
131ConversionResult ConvertUTF16toUTF32 (const UTF16** sourceStart, const UTF16* sourceEnd,
132                                      UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags);
134ConversionResult ConvertUTF32toUTF16 (const UTF32** sourceStart, const UTF32* sourceEnd,
135                                      UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags);
137Boolean isLegalUTF8Sequence(const UTF8 *source, const UTF8 *sourceEnd);
139#ifdef __cplusplus
143/* --------------------------------------------------------------------- */