战魂小筑

讨论群:309800774 知乎关注:http://zhihu.com/people/sunicdavy 开源项目:https://github.com/davyxu

   :: 首页 :: 新随笔 :: 联系 :: 聚合  :: 管理 ::
  257 随笔 :: 0 文章 :: 506 评论 :: 0 Trackbacks

参考来源:http://blog.csdn.net/flying8127/article/details/1598521

在原来原基础上,将代码整理,并加强安全性. 并按照WindowsAPI设计, 添加输出缓冲长度探测功能

当OutUTFString为NULL时, 可以进行输出的UTF8字符串长度探测

   1:  uint32 UniCharToUTF8(wchar_t UniChar, char *OutUTFString)
   2:      {
   3:   
   4:          uint32 UTF8CharLength = 0;
   5:   
   6:          if (UniChar < 0x80)
   7:          {  
   8:              if ( OutUTFString )
   9:                  OutUTFString[UTF8CharLength++] = (char)UniChar;
  10:              else
  11:                  UTF8CharLength++;
  12:          }
  13:          else if(UniChar < 0x800)
  14:          {
  15:              if ( OutUTFString )
  16:              {
  17:                  OutUTFString[UTF8CharLength++] = 0xc0 | ( UniChar >> 6 );
  18:                  OutUTFString[UTF8CharLength++] = 0x80 | ( UniChar & 0x3f );
  19:              }
  20:              else
  21:              {
  22:                  UTF8CharLength += 2;
  23:              }
  24:          }
  25:          else if(UniChar < 0x10000 )
  26:          {
  27:              if ( OutUTFString )
  28:              {
  29:                  OutUTFString[UTF8CharLength++] = 0xe0 | ( UniChar >> 12 );
  30:                  OutUTFString[UTF8CharLength++] = 0x80 | ( (UniChar >> 6) & 0x3f );
  31:                  OutUTFString[UTF8CharLength++] = 0x80 | ( UniChar & 0x3f );
  32:              }
  33:              else
  34:              {
  35:                  UTF8CharLength += 3;
  36:              }
  37:          }
  38:          else if( UniChar < 0x200000 ) 
  39:          {
  40:              if ( OutUTFString )
  41:              {
  42:                  OutUTFString[UTF8CharLength++] = 0xf0 | ( (int)UniChar >> 18 );
  43:                  OutUTFString[UTF8CharLength++] = 0x80 | ( (UniChar >> 12) & 0x3f );
  44:                  OutUTFString[UTF8CharLength++] = 0x80 | ( (UniChar >> 6) & 0x3f );
  45:                  OutUTFString[UTF8CharLength++] = 0x80 | ( UniChar & 0x3f );
  46:              }
  47:              else
  48:              {
  49:                  UTF8CharLength += 4;
  50:              }
  51:   
  52:          }
  53:   
  54:          return UTF8CharLength;
  55:      }

 

当OutUnicodeString为NULL时, 可以进行输出的Unicode字符串长度探测

 

   1:  uint32 UTF8StrToUnicode( const char* UTF8String, uint32 UTF8StringLength, wchar_t* OutUnicodeString, uint32 UnicodeStringBufferSize )
   2:      {
   3:          uint32 UTF8Index = 0;
   4:          uint32 UniIndex = 0;
   5:   
   6:          while ( UTF8Index < UTF8StringLength )
   7:          {
   8:              unsigned char UTF8Char = UTF8String[UTF8Index];
   9:   
  10:              if ( UnicodeStringBufferSize != 0 && UniIndex >= UnicodeStringBufferSize )
  11:                  break;
  12:   
  13:              if ((UTF8Char & 0x80) == 0) 
  14:              {
  15:                  const uint32 cUTF8CharRequire = 1;
  16:   
  17:                  // UTF8字码不足
  18:                  if ( UTF8Index + cUTF8CharRequire > UTF8StringLength )
  19:                      break;
  20:   
  21:                  if ( OutUnicodeString )
  22:                  {
  23:                      wchar_t& WideChar = OutUnicodeString[UniIndex]; 
  24:   
  25:                      WideChar = UTF8Char;
  26:                  }
  27:   
  28:                  UTF8Index++;
  29:                  
  30:              } 
  31:              else if((UTF8Char & 0xE0) == 0xC0)  ///< 110x-xxxx 10xx-xxxx
  32:              {
  33:                  const uint32 cUTF8CharRequire = 2;
  34:   
  35:                  // UTF8字码不足
  36:                  if ( UTF8Index + cUTF8CharRequire > UTF8StringLength )
  37:                      break;
  38:   
  39:                  if ( OutUnicodeString )
  40:                  {
  41:                      wchar_t& WideChar = OutUnicodeString[UniIndex]; 
  42:                      WideChar  = (UTF8String[UTF8Index + 0] & 0x3F) << 6;
  43:                      WideChar |= (UTF8String[UTF8Index + 1] & 0x3F);
  44:                  }
  45:                  
  46:                  UTF8Index += cUTF8CharRequire;
  47:              }
  48:              else if((UTF8Char & 0xF0) == 0xE0)  ///< 1110-xxxx 10xx-xxxx 10xx-xxxx
  49:              {
  50:                  const uint32 cUTF8CharRequire = 3;
  51:   
  52:                  // UTF8字码不足
  53:                  if ( UTF8Index + cUTF8CharRequire > UTF8StringLength )
  54:                      break;
  55:   
  56:                  if ( OutUnicodeString )
  57:                  {
  58:                      wchar_t& WideChar = OutUnicodeString[UniIndex]; 
  59:   
  60:                      WideChar  = (UTF8String[UTF8Index + 0] & 0x1F) << 12;
  61:                      WideChar |= (UTF8String[UTF8Index + 1] & 0x3F) << 6;
  62:                      WideChar |= (UTF8String[UTF8Index + 2] & 0x3F);
  63:                  }
  64:                  
  65:   
  66:                  UTF8Index += cUTF8CharRequire;
  67:              } 
  68:              else if((UTF8Char & 0xF8) == 0xF0)  ///< 1111-0xxx 10xx-xxxx 10xx-xxxx 10xx-xxxx 
  69:              {
  70:                  const uint32 cUTF8CharRequire = 4;
  71:   
  72:                  // UTF8字码不足
  73:                  if ( UTF8Index + cUTF8CharRequire > UTF8StringLength )
  74:                      break;
  75:   
  76:                  if ( OutUnicodeString )
  77:                  {
  78:                      wchar_t& WideChar = OutUnicodeString[UniIndex]; 
  79:   
  80:                      WideChar  = (UTF8String[UTF8Index + 0] & 0x0F) << 18;
  81:                      WideChar  = (UTF8String[UTF8Index + 1] & 0x3F) << 12;
  82:                      WideChar |= (UTF8String[UTF8Index + 2] & 0x3F) << 6;
  83:                      WideChar |= (UTF8String[UTF8Index + 3] & 0x3F);
  84:                  }
  85:   
  86:                  UTF8Index += cUTF8CharRequire;
  87:              } 
  88:              else ///< 1111-10xx 10xx-xxxx 10xx-xxxx 10xx-xxxx 10xx-xxxx 
  89:              {
  90:                  const uint32 cUTF8CharRequire = 5;
  91:   
  92:                  // UTF8字码不足
  93:                  if ( UTF8Index + cUTF8CharRequire > UTF8StringLength )
  94:                      break;
  95:   
  96:                  if ( OutUnicodeString )
  97:                  {
  98:                      wchar_t& WideChar = OutUnicodeString[UniIndex]; 
  99:   
 100:                      WideChar  = (UTF8String[UTF8Index + 0] & 0x07) << 24;
 101:                      WideChar  = (UTF8String[UTF8Index + 1] & 0x3F) << 18;
 102:                      WideChar  = (UTF8String[UTF8Index + 2] & 0x3F) << 12;
 103:                      WideChar |= (UTF8String[UTF8Index + 3] & 0x3F) << 6;
 104:                      WideChar |= (UTF8String[UTF8Index + 4] & 0x3F);
 105:                  }
 106:   
 107:                  UTF8Index += cUTF8CharRequire;
 108:              }
 109:   
 110:   
 111:              UniIndex++;
 112:          }
 113:   
 114:          return UniIndex;
 115:      }

疗效: 用了此代码啊, 再也不用被iconv折磨了

posted on 2012-02-27 14:21 战魂小筑 阅读(4679) 评论(9)  编辑 收藏 引用 所属分类: 网络 服务器技术C++/ 编程语言

评论

# re: 跨平台Unicode与UTF8互转代码 2012-02-27 21:09 我要去拯救世界
谢谢分享了!  回复  更多评论
  

# re: 跨平台Unicode与UTF8互转代码 2012-02-28 17:30 天下
跨平台使用挺好,
在WIN32下,只要CW2A,CA2W宏全部搞定


  回复  更多评论
  

# re: 跨平台Unicode与UTF8互转代码 2012-03-02 10:08 pillaridge
这个可能有点儿问题,wchar_t在windows下是16位,在*nix下是32位。  回复  更多评论
  

# re: 跨平台Unicode与UTF8互转代码 2012-03-02 10:13 pillaridge
可以借用CLANG源代码 basic下的ConvertUTF.h和ConvertUTF.c  回复  更多评论
  

# re: 跨平台Unicode与UTF8互转代码 2012-03-09 18:04 战魂小筑
@pillaridge
感谢提醒
  回复  更多评论
  

# re: 跨平台Unicode与UTF8互转代码 2012-11-19 14:22 陈成
100: WideChar = (UTF8String[UTF8Index + 0] & 0x07) << 24;
101: WideChar = (UTF8String[UTF8Index + 1] & 0x3F) << 18;
102: WideChar = (UTF8String[UTF8Index + 2] & 0x3F) << 12;
这三行不是只有最后一行才起作用吗?  回复  更多评论
  

# re: 跨平台Unicode与UTF8互转代码 2012-11-20 10:09 战魂小筑
@陈成
这段代码是从其他地方拷贝过来的  回复  更多评论
  

# re: 跨平台Unicode与UTF8互转代码 2013-06-07 17:03 zibbleR
UniCharToUTF8 在转换中文的时候出来的貌似还是乱码,  回复  更多评论
  

# re: 跨平台Unicode与UTF8互转代码 2013-10-15 14:57 zozo
关键是要gb2312-utf8的转换,有木有  回复  更多评论
  


只有注册用户登录后才能发表评论。
网站导航: 博客园   IT新闻   BlogJava   知识库   博问   管理