前言

1.C++的string對中文的查找替換之類的基本操作并不友好，如果要對中文進行操作，要把中文轉(zhuǎn)成寬字符（wstring）來解決，因為中文字符長度不確定的，在unicode中每個中文為2個字節(jié)，而字符串中有時還可能有英文數(shù)字字符等，這些只占一個字節(jié)1個字節(jié)，查找的過程很容易返回的不是找到的位置。
2.如果要操作中文字符串，比較好的辦法先把string轉(zhuǎn)成wstring，進行操作查找匹配操作之后，再轉(zhuǎn)回來。
3.這里我定了個類，把它們之間的互相轉(zhuǎn)換都封裝成函數(shù)。

代碼

Chinese.h

#pragma once #include <string> #include <iostream>class Chinese { public:Chinese();~Chinese();//char*轉(zhuǎn)換為wchar_t*wchar_t* MBCSToUnicode(wchar_t * buff, const char * str);//wchar*轉(zhuǎn)換為char*char* unicodeToMBCS(char* buff, const wchar_t* str);//string轉(zhuǎn)wstringstd::wstring strToWstr(std::string &input);std::string wstrToStr(std::wstring &wstr);char* wstrToChar(std::wstring &wstr);char* wstrToChar(const wchar_t* wstr); };

Chinese.cpp

#include "Chinese.h"Chinese::Chinese() {}Chinese::~Chinese() { }wchar_t* Chinese::MBCSToUnicode(wchar_t* buff, const char* str) {wchar_t * wp = buff;char * p = (char *)str;while (*p){if (*p & 0x80){*wp = *(wchar_t *)p;p++;}else {*wp = (wchar_t)*p;}wp++;p++;}*wp = 0x0000;return buff; }char* Chinese::unicodeToMBCS(char* buff, const wchar_t* str) {wchar_t * wp = (wchar_t *)str;char * p = buff, *tmp;while (*wp){tmp = (char *)wp;if (*wp & 0xFF00){*p = *tmp;p++; tmp++;*p = *tmp;p++;}else{*p = *tmp;p++;}wp++;}*p = 0x00;return buff; }std::wstring Chinese::strToWstr(std::string &input) {size_t len = input.size();wchar_t * b = (wchar_t *)malloc((len + 1) * sizeof(wchar_t));MBCSToUnicode(b, input.c_str());std::wstring r(b);free(b);return r; }char* Chinese::wstrToChar(std::wstring &wstr) {char* re = wstrToChar(wstr.c_str());return re; }char* Chinese::wstrToChar(const wchar_t* wstr) {int len = wcslen(wstr);char * buff = (char *)malloc((len * 2 + 1) * sizeof(char));char* re = unicodeToMBCS(buff, wstr);free(buff);return re; }std::string Chinese::wstrToStr(std::wstring &wstr) {size_t len = wstr.size();char * b = (char *)malloc((2 * len + 1) * sizeof(char));unicodeToMBCS(b, wstr.c_str());std::string r(b);free(b);return r; }

main.cpp

#include <iostream> #include <string> #include "Chinese.h"int main() {//輸入層：接收char*輸入，并將其轉(zhuǎn)換為wchar*std::string input = "于老師的k父親王老爺子是蒙古的海軍司令！yes";std::string temp = "王";Chinese ch;std::wstring w_str = ch.strToWstr(input);std::wstring w_tem = ch.strToWstr(temp);int index = w_str.find(w_tem);std::cout << index << std::endl;return 0; }

總結(jié)

以上是生活随笔為你收集整理的C++对中文字符的处理的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。