一个在UTF32、UTF-16、UTF-8中相互转换的C++程序

首先是最重要的版权信息。

/*
 * Copyright 2001-2004 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.
 */

 

头文件：

 

typedef unsigned int UTF32; /* at least 32 bits */ typedef unsigned short UTF16; /* at least 16 bits */ typedef unsigned char UTF8; /* typically 8 bits */ typedef unsigned char Boolean; /* 0 or 1 */ /* Some fundamental constants */ #define UNI_REPLACEMENT_CHAR (UTF32)0x0000FFFD #define UNI_MAX_BMP (UTF32)0x0000FFFF #define UNI_MAX_UTF16 (UTF32)0x0010FFFF #define UNI_MAX_UTF32 (UTF32)0x7FFFFFFF #define UNI_MAX_LEGAL_UTF32 (UTF32)0x0010FFFF typedef enum { conversionOK, /* conversion successful */ sourceExhausted, /* partial character in source, but hit end */ targetExhausted, /* insuff. room in target for conversion */ sourceIllegal /* source sequence is illegal/malformed */ } ConversionResult; typedef enum { strictConversion = 0, lenientConversion } ConversionFlags; /* This is for C++ and does no harm in C */ #ifdef __cplusplus extern "C" { #endif ConversionResult ConvertUTF8toUTF16 ( const UTF8** sourceStart, const UTF8* sourceEnd, UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags); ConversionResult ConvertUTF16toUTF8 ( const UTF16** sourceStart, const UTF16* sourceEnd, UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags); ConversionResult ConvertUTF8toUTF32 ( const UTF8** sourceStart, const UTF8* sourceEnd, UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags); ConversionResult ConvertUTF32toUTF8 ( const UTF32** sourceStart, const UTF32* sourceEnd, UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags); ConversionResult ConvertUTF16toUTF32 ( const UTF16** sourceStart, const UTF16* sourceEnd, UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags); ConversionResult ConvertUTF32toUTF16 ( const UTF32** sourceStart, const UTF32* sourceEnd, UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags); Boolean isLegalUTF8Sequence(const UTF8 *source, const UTF8 *sourceEnd); #ifdef __cplusplus } #endif

 

实现：

 

#include "ConvertUTF.h" #ifdef CVTUTF_DEBUG #include <stdio.h> #endif static const int halfShift = 10; /* used for shifting by 10 bits */ static const UTF32 halfBase = 0x0010000UL; static const UTF32 halfMask = 0x3FFUL; #define UNI_SUR_HIGH_START (UTF32)0xD800 #define UNI_SUR_HIGH_END (UTF32)0xDBFF #define UNI_SUR_LOW_START (UTF32)0xDC00 #define UNI_SUR_LOW_END (UTF32)0xDFFF #define false 0 #define true 1 /* --------------------------------------------------------------------- */ ConversionResult ConvertUTF32toUTF16 ( const UTF32** sourceStart, const UTF32* sourceEnd, UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags) { ConversionResult result = conversionOK; const UTF32* source = *sourceStart; UTF16* target = *targetStart; while (source < sourceEnd) { UTF32 ch; if (target >= targetEnd) { result = targetExhausted; break; } ch = *source++; if (ch <= UNI_MAX_BMP) { /* Target is a character <= 0xFFFF */ /* UTF-16 surrogate values are illegal in UTF-32; 0xffff or 0xfffe are both reserved values *