跨平台utf8转unicode研究实现(4)
2013-08-05 18:54
225 查看
场景:
1.windows下需要unicode来处理非ascii的字符,如中文文件路径.
2.但是做字符串处理时又需要转换成中间的utf8处理,这就涉及到了互转.
3.参考unicode和utf8关系:
http://baike.baidu.com/view/40801.htm
文件:test_utf82unicode.cpp(只做了支持双字节的unicode转码.)
1.windows下需要unicode来处理非ascii的字符,如中文文件路径.
2.但是做字符串处理时又需要转换成中间的utf8处理,这就涉及到了互转.
3.参考unicode和utf8关系:
http://baike.baidu.com/view/40801.htm
文件:test_utf82unicode.cpp(只做了支持双字节的unicode转码.)
#include <stdio.h> #include <assert.h> #include <string.h> #include <stdlib.h> void OneUTF82Unicode(const char* utf_char, char* unicode_char); char* utf82unicode(const char* utf,size_t *unicode_number) { char* utf8 = strdup(utf); size_t utf8_length = strlen(utf8); //这里可以自己考虑实现更精确的大小. //+2是留两个00. char* unicode = (char*)malloc(utf8_length*2+2); memset(unicode,0,utf8_length*2+2); size_t index = 0; size_t start = 0; unsigned char temp; //10000000=0x80 1110=0xE 110=0x6 unsigned char flag = 0; size_t unicode_index = 0; bool is_finded = false; while((temp = utf8[index])) { start = index; temp = temp >> 4 ; if(temp > 0xE) { assert(0); printf("utf8 bigger than 4 byte is not supported.\n"); break; } if(temp == 0xE) { index+=3; is_finded = true; } temp = temp >> 1; if(!is_finded && temp == 0x6) { index+=2; is_finded = true; } temp = temp >> 2; if(!is_finded && temp == 0x00) { index+=1; is_finded = true; } if(index > utf8_length) { break; } flag = utf8[index]; utf8[index] = 0; OneUTF82Unicode(utf8+start,unicode+unicode_index); utf8[index] = flag; unicode_index+=2; is_finded = false; } free(utf8); *unicode_number = unicode_index/2; return unicode; } void OneUTF82Unicode(const char* utf_char, char* unicode_char) { //unicode: 0x192->110010010 ,utf8:0xC692->11000110|10010010 //小端序 int utf_length = strlen(utf_char); //0x3F->00111111 switch(utf_length) { case 1: unicode_char[0] = utf_char[0]; unicode_char[1] = 0; break; case 2: unicode_char[0] = (utf_char[1] & 0x3F) | ((utf_char[0] & 0x3) << 6); unicode_char[1] = (utf_char[0] & 0x3C) >> 2; break; case 3: unicode_char[0] = (utf_char[2] & 0x3F) | ((utf_char[1] & 0x3) << 6); unicode_char[1] = ((utf_char[1] & 0x3C) >> 2) | ((utf_char[0] & 0xF) << 4); break; default: assert(0); printf("utf_char length is bigger than 4 unsupported.\n"); break; } } int main(int argc, char *argv[]) { printf("Hello, world\n"); char utf_char[12] = {0xC3,0xBE}; memset(utf_char+2,0,10); char unicode_char[3] = {0,0,0}; OneUTF82Unicode(utf_char,unicode_char); printf("%x,%x\n",(unsigned char)unicode_char[0],unicode_char[1]); utf_char[0] = 0xE6; utf_char[1] = 0x88; utf_char[2] = 0x91; OneUTF82Unicode(utf_char,unicode_char); printf("%x,%x\n",(unsigned char)unicode_char[0],unicode_char[1]); size_t unicode_number = 0; char utf_str[]={0xC3,0xBE,0xE6,0x88,0x91,0xE4,0xBB,0xAC,0xE7,0x9A,0x84,0xE5,0x9B, 0xBD,0xE5,0xAE,0xB6,0x64,0x61,0xE7,0x9A,0x84,0xE5,0x93,0xA6}; char* unicode = utf82unicode(utf_str,&unicode_number); printf("%d\n",unicode_number); size_t index = 0; for(size_t i=0;i<unicode_number;++i,index+=2) { printf("%x,%x\n",(unsigned char)unicode[index],(unsigned char)unicode[index+1]); } free(unicode); return 0; }
相关文章推荐
- 跨平台utf8转unicode研究实现(3)
- 跨平台utf8转unicode研究实现(2)
- 跨平台utf8转unicode研究实现(2)
- Java实现的utf8,gbk,unicode编码相互转换的代码
- NodeJS研究笔记,利用目录来实现跨平台文件锁
- 跨平台utf8与unicode的互转
- Java实现的utf8,gbk,unicode编码相互转换的代码
- pb字符串实现GB2312与Unicode、UTF8之间的相互转换
- 纯C实现unicode-utf8互转
- Java实现的utf8,gbk,unicode编码相互转换的代码
- 纯C实现unicode-utf8互转
- 纯C实现unicode-utf8互转
- Unicode编码,以及实现方式UTF8的实现方式
- 纯C实现unicode-utf8互转
- 跨平台实现GBK和UTF8之间的转换(通过汉字集合实现)
- 分清“语言/规范”以及“平台/实现”,以及跨平台.NET开发“.NET研究”
- 跨平台Unicode与UTF8互转代码
- java实现unicode的解码
- cocos2d-x 实现跨平台的目录遍历
- 对字符编码与Unicode,ISO 10646,UCS,UTF8,UTF16,GBK,GB2312的理解