参考文章:http://www.qingfengju.com/article.asp?id=245
现在的网站,经常返回下面这样的字符串:
"error":"\u7528\u6237\u4e0d\u5b58\u5728\u6216\u5bc6\u7801\u9519\u8bef"}
其中的\u7528等就是汉字的UTF8编码了,如何将其还原成相应的字符呢?
代码如下:
#include <string>
using std::string;
string Utf8Code2String(char* szCode){ string strRet = ""; for (int i = 0; i < 4; i++) { if (szCode[i] >= '0' && szCode[i] <= '9') continue; if (szCode[i] >= 'A' && szCode[i] <= 'F') continue; if (szCode[i] >= 'a' && szCode[i] <= 'f') continue; return strRet; } char unicode_hex[5] = {0}; memcpy(unicode_hex, szCode, 4); unsigned int iCode = 0; sscanf_s(unicode_hex,"%04x", &iCode); wchar_t wchChar[4] = {0}; wchChar[0] = iCode; char szAnsi[8] = {0}; WideCharToMultiByte(CP_ACP, NULL, wchChar, 1, szAnsi, sizeof(szAnsi), NULL, NULL); strRet = string(szAnsi); return strRet;}string MyUnEscape(char* szUtf8Code){ // {"error":"\u7528\u6237\u4e0d\u5b58\u5728\u6216\u5bc6\u7801\u9519\u8bef"} string strRet = ""; char* szDelimiters = "\\u"; char* pTok = strtok(szUtf8Code, szDelimiters); while(pTok != NULL){ /*OutputDebugString(pTok); OutputDebugString("\r\n");*/ if (strlen(pTok) >= 4) { strRet += Utf8Code2String(pTok); } pTok = strtok(NULL, szDelimiters); } return strRet;}
// 调用例子
MyUnEscape("test \u7528\u6237\u4e0d\u5b58\u5728\u6216\u5bc6\u7801\u9519\u8bef hahah ok");
贴下参考文章的代码:
#include <string.h> #include <iostream>#include <string>using namespace std; #include <atlconv.h> enum{ UNICODE_CALC_SIZE = 1, UNICODE_GET_BYTES = 2}; //将unicode转义字符序列转换为内存中的unicode字符串int unicode_bytes(char* p_unicode_escape_chars,wchar_t *bytes,int flag){ /* char* p_unicode_escape_chars="pp\\u4fddp\\u5b58\\u6210pp\\u529f0a12"; //通过此函数获知转换后需要的字节数 int n_length=unicode_bytes(p_unicode_escape_chars,NULL,UNICODE_CALC_SIZE); //再次调用此函数,取得字节序列 wchar_t *bytes=new wchar_t[n_length+sizeof(wchar_t)]; unicode_bytes(p_unicode_escape_chars,bytes,UNICODE_GET_BYTES); bytes[n_length]=0; //此时的bytes中是转换后的字节序列 delete[] bytes; */ int unicode_count=0; int length=strlen(p_unicode_escape_chars); for (int char_index=0;char_index<length;char_index++) { char unicode_hex[5]; memset(unicode_hex,0,5); char ascii[2]; memset(ascii,0,2); if (*(p_unicode_escape_chars+char_index)=='\\') { char_index++; if (char_index<length) { if (*(p_unicode_escape_chars+char_index)=='u') { if (flag==UNICODE_GET_BYTES) { memcpy(unicode_hex,p_unicode_escape_chars+char_index+1,4); //sscanf不可以使用unsigned short类型 //否则:Run-Time Check Failure #2 - Stack around the variable 'a' was corrupted. unsigned int a=0; sscanf_s(unicode_hex,"%04x",&a); bytes[unicode_count++]=a; } else if(flag==UNICODE_CALC_SIZE) { unicode_count++; } char_index+=4; } } } else { if (flag==UNICODE_GET_BYTES) { memcpy(ascii,p_unicode_escape_chars+char_index,1); unsigned int a=0; sscanf_s(ascii,"%c",&a); bytes[unicode_count++]=a; } else if(flag==UNICODE_CALC_SIZE) { unicode_count++; } } } return unicode_count;} string UnEscape(char* p_unicode_escape_chars){ int nBytes=unicode_bytes(p_unicode_escape_chars,NULL,UNICODE_CALC_SIZE); wchar_t *p_bytes=new wchar_t[nBytes+sizeof(wchar_t)]; unicode_bytes(p_unicode_escape_chars,p_bytes,UNICODE_GET_BYTES); p_bytes[nBytes]=0; USES_CONVERSION; string cs_return=W2A((wchar_t*)p_bytes); delete[] p_bytes; return cs_return;} int _tmain(int argc, _TCHAR* argv[]){ // 发送成功条 // \u53d1\u9001\u6210\u529f1\u6761 char* p_unicode_escape_chars="\\u53d1\\u9001\\u6210\\u529f1\\u6761"; cout<<UnEscape(p_unicode_escape_chars)<<endl; return 0;}