#include <cstdint> #include <string> #include <iostream> #include <locale> #include <codecvt> using namespace std;wstring utf8_to_wchar(const string& str);int main() {// locale(const char* name)构造函数根据name创建locale对象// auto lkl = locale(); // 输出乱码// auto lkl = locale(NULL); // 编译不过// 下面取自环境变量LANG，我这里LANG=zh_CN.UTF-8；LC_ALL未定义auto lkl = locale("");locale::global(lkl);string str = "测试"; // 可以是GBK等，不是必须是utf-8wstring_convert<codecvt_utf8<wchar_t>> converter;wstring wide_str = converter.from_bytes(str);wstring ws2 = utf8_to_wchar(str);wcout.imbue(lkl); // imbue: fill sb/sth with strong feelings, opinions or values// Well, fuck the one who chose `imbue' 1000 times!! :-)wcout << wide_str << ws2 << endl;// gcc -finput-charset=charset// Set the input character set, used for translation from the character set of the input file// to the source character set used by GCC.// If the locale does not specify (这是啥子语法), or GCC cannot get this information from the locale,// the default is UTF-8.// specify v [Tn, Tf, Tw]// T: transitive (of a verb) that is used with a direct object either expressed or understood// The regulations specify that you may use a dictionary in the examination. 规则中指明考试时可以用词典。wcout << L"一下" << endl;return 0; }wstring utf8_to_wchar(const string& str) {wstring result;for (size_t i = 0; i < str.size();) {const uint8_t c = str[i];if (c <= 0x7F) { // 单字节ASCII字符result += wchar_t(c);++i;} else if ((c & 0xE0) == 0xC0) { // 双字节UTF-8字符++i;if (i >= str.size()) break;const uint8_t c1 = str[i];const wchar_t wc = ((c & 0x1F) << 6) | (c1 & 0x3F);result += wc;++i;} else if ((c & 0xF0) == 0xE0) { // 三字节UTF-8字符if (i + 2 >= str.size()) break;const uint8_t c1 = str[i + 1];const uint8_t c2 = str[i + 2];const wchar_t wc = ((c & 0x0F) << 12) | ((c1 & 0x3F) << 6) | (c2 & 0x3F);result += wc;i += 3;} else // 无效字符，跳过++i;}return result; }
if [ -z "${LANG+x}" ]; then echo "LANG is undefined"; fi if [ -z "${LC_ALL+x}" ]; then echo "LC_ALL is undefined"; fi
wc, water closet, 厕所，名副其实。
#include <locale.h>
char *setlocale(int category, const char *locale);
The setlocale() function is used to set or query the program's current locale.
If locale is not NULL, the program's current locale is modified according to the arguments.
The argument category determines which parts of the program's current locale should be modified.
- LC_ALL All of the locale
- LC_ADDRESS Formatting of addresses and geography-related items (*)
- LC_COLLATE String collation
- LC_CTYPE Character classification
- LC_IDENTIFICATION Metadata describing the locale (*)
- LC_MEASUREMENT Settings related to measurements (metric versus US customary) (*)
- LC_MESSAGES Localizable natural-language messages
- LC_MONETARY Formatting of monetary values
- LC_NAME Formatting of salutations for persons (*)
- LC_NUMERIC Formatting of nonmonetary numeric values
- LC_PAPER Settings related to the standard paper size (*)
- LC_TELEPHONE Formats to be used with telephone services (*)
- LC_TIME Formatting of date and time values