跳转至

Technical Documents

功能函数库

shuhaiwen/technical-documents

功能函数库¶

1 获取lacale集¶

1.1 windows版¶

#include<Windows.h>
#include<string>
using std::wstring;
using std::string;
#ifdef UNICODE
typedef wstring tstring;
#else
typedef string tstring;
#endif // UNICODE


typedef std::vector<tstring> tLocales;
std::vector<tstring> g_locales;

BOOL CALLBACK MyLocaleEnumProc(LPTSTR szLocaleString)
{
    g_locales.push_back(szLocaleString);
    return TRUE;
}

//LCID码转语言和国家全称(English_United States.1252)
tstring& LCID2NLS(LCID lcid, tstring& bstrRetBuf)
{
    TCHAR arcBuf[128];

    memset(arcBuf, 0, sizeof(arcBuf));

    GetLocaleInfo(lcid, LOCALE_SENGLANGUAGE, arcBuf, 127);// English name of language, eg "German"
    bstrRetBuf = arcBuf;
    memset(arcBuf, 0, sizeof(arcBuf));
    //Loading the English name for the country/region
    GetLocaleInfo(lcid, LOCALE_SENGCOUNTRY, arcBuf, 127);// English name of country/region, eg "Germany"
    if (*arcBuf)
    {
        bstrRetBuf += TEXT("_");
        bstrRetBuf += arcBuf;
    }
    //Loading the code page
    memset(arcBuf, 0, sizeof(arcBuf));
    if ((GetLocaleInfo(lcid, LOCALE_IDEFAULTANSICODEPAGE, arcBuf, 127)
        || GetLocaleInfo(lcid, LOCALE_IDEFAULTCODEPAGE, arcBuf, 127))
        && *arcBuf)
    {
        bstrRetBuf += TEXT(".");
        bstrRetBuf += arcBuf;
    }

    return bstrRetBuf;
}

//LCID码转语言和国家缩写（en_US）
tstring& LCID2NLSAbbr(LCID lcid, tstring& bstrRetBuf)
{
    TCHAR arcBuf[128];

    memset(arcBuf, 0, sizeof(arcBuf));

    GetLocaleInfo(lcid, LOCALE_SISO639LANGNAME, arcBuf, 127);// ISO abbreviated language name, eg "en"
    bstrRetBuf = arcBuf;
    memset(arcBuf, 0, sizeof(arcBuf));
    //Loading the English name for the country/region
    GetLocaleInfo(lcid, LOCALE_SISO3166CTRYNAME, arcBuf, 127); // ISO abbreviated country/region name, eg "US"
    if (*arcBuf)
    {
        bstrRetBuf += TEXT("_");
        bstrRetBuf += arcBuf;
    }

    return bstrRetBuf;
}

std::vector<tstring> GetAllLocales(bool isAbbr=true)
{
    EnumSystemLocales(&MyLocaleEnumProc, LCID_INSTALLED);
    std::vector<tstring> vNLS,vNLSAbbr;
    tstring ts;

    for (tLocales::const_iterator i = g_locales.begin(); i != g_locales.end(); i++)
    {
        if (isAbbr) {//en_US
            LCID2NLSAbbr(std::stoul(i->c_str(), nullptr, 16), ts);
            vNLSAbbr.emplace_back(ts);         
        }
        else {//English_United States.1252
            LCID2NLS(std::stoul(i->c_str(), nullptr, 16), ts);
            vNLS.emplace_back(ts);            
        }    
    }
    if (isAbbr) {
        return vNLSAbbr;
    }
    else {
        return vNLS;
    }
}
int main() {
    //获取缩写locale集 en_US
    std::vector<tstring> vstrAbbr= GetAllLocales();
    //获取全称locale集 (English_United States.1252)
    std::vector<tstring> vstr = GetAllLocales(false);
}

1.2 Linux版¶

linux上可以通过调用系统locale -a命令来获取

#include <stdio.h>
#include <iostream>
#include <string>
#include <set>
using namespace std;
int main()
{
  char buf[128] = {0};
  FILE *fp = NULL;
  fp = popen("locale -a", "r");
  set<string> sstr;
  while (!feof(fp))
  {
    fgets(buf, sizeof(buf) - 1, fp);
    sstr.insert(string(buf));
  }
  //fread(buf, 1, 2047, fp);
  pclose(fp);
  for (auto &&str : sstr)
  {
    std::cout << str << std::endl;
  }
}

2 宽字符多字节转换¶

注意：把多字节编码转换成另一多字节编码，需把宽字符编码作为中转编码。

2.1 跨平台¶

代码如下

#include<string>
#include<fstream>
#pragma warning(disable : 4996) 
int main() {
    //utf-8转宽字符
    {
        std::cout << "utf-8转宽字符->" << std::endl;
        setlocale(LC_ALL, "en_US.utf8");
        const char* mbstr = u8"z你好z";
        //获取所需wchar_t空间
        size_t len = mbstowcs(NULL, mbstr, 0);
        wchar_t* wstr = new wchar_t[len + 1];
        wstr[len] = L'\0';
        mbstowcs(wstr, mbstr, 5);
        setlocale(LC_ALL, "");
        std::wcout << L"宽字符：" << wstr << std::endl;
        delete[]wstr;
    }
    //本地环境编码(简体中文系统gbk)转宽字符
    {
        setlocale(LC_ALL, "");
        std::wcout << L"本地环境编码(简体中文系统gbk)转宽字符->" << std::endl;
        const char* mbstr = "z你好z";
        //获取所需wchar_t空间
        size_t len = mbstowcs(NULL, mbstr, 0);
        wchar_t* wstr = new wchar_t[len + 1];
        wstr[len] = L'\0';
        mbstowcs(wstr, mbstr, 5);
        std::wcout << L"宽字符：" << wstr << std::endl;
        delete[]wstr;
    }
    //宽字符转utf-8
    {
        setlocale(LC_ALL, "");
        std::wcout << L"宽字符转utf-8->" << std::endl;
        //设置locale到utf-8环境，这样宽字符才会转出多字节的utf-8编码
        std::string lc= setlocale(LC_ALL, "en_US.utf8");
        const wchar_t* wstr = L"z你好z";
        //获取所需wchar_t空间
        size_t len = wcstombs(NULL, wstr, 0);
        char* mbstr = new char[len + 1];
        mbstr[len] = '\0';
        wcstombs(mbstr, wstr, len);
        //由于控制台直接打印utf-8编码字符比较困难，故写入文件中，打开1.txt文件，查看编码格式utf-8，内容“z你好z”
        std::ofstream fout("1.txt");
        fout << mbstr;
        fout.close();
        delete[]mbstr;
    }
    //宽字符转本地环境编码(简体中文系统gbk)
    {
        setlocale(LC_ALL, "");
        std::wcout << L"宽字符转本地环境编码(简体中文系统gbk)->" << std::endl;
        //设置locale到utf-8环境，这样宽字符才会转出多字节的utf-8编码
        setlocale(LC_ALL, "");
        const wchar_t* wstr = L"z你好z";
        //获取所需wchar_t空间
        size_t len = wcstombs(NULL, wstr, 0);
        char* mbstr = new char[len + 1];
        mbstr[len] = '\0';
        wcstombs(mbstr, wstr, len);
        std::cout << "多字节：";
        std::cout << mbstr << '\n';
        delete[]mbstr;
    }   
}

输出结果

utf-8转宽字符->
宽字符：z你好z
本地环境编码(简体中文系统gbk)转宽字符->
宽字符：z你好z
宽字符转utf-8->
宽字符转本地环境编码(简体中文系统gbk)->
多字节：z你好z

2.2 windows平台¶

#include<Windows.h>
using namespace std;
int main() {
    const char* szU8 = u8"z你好z";
    //原始字符串为utf-8编码
    int wcsLen = ::MultiByteToWideChar(CP_UTF8, NULL, szU8, strlen(szU8), NULL, 0);
    wchar_t* wszString = new wchar_t[wcsLen + 1];
    ::MultiByteToWideChar(CP_UTF8, NULL, szU8, strlen(szU8), wszString, wcsLen);
    wszString[wcsLen] = '\0';
    //转换宽字符到ANSI编码(根据操作系统语言环境决定)
    int ansiLen = ::WideCharToMultiByte(CP_ACP, NULL, wszString, wcslen(wszString), NULL, 0, NULL, NULL);
    char* szAnsi = new char[ansiLen + 1];
    ::WideCharToMultiByte(CP_ACP, NULL, wszString, wcslen(wszString), szAnsi, ansiLen, NULL, NULL);
    szAnsi[ansiLen] = '\0';
    setlocale(LC_CTYPE, "");
    wcout << wszString << endl;
    cout << szAnsi << endl;
}

3 读取文件¶

3.1 按行读取¶

方式一：cpp方法

#include <fstream>
#include <iostream>
#include <string>
using namespace std;
int main()
{
    ifstream rf("1.txt");
    if (rf.is_open())
    {
        string str;
        while (getline(rf,str))
        {
            std::cout << str << std::endl;
        }
    }
}

方式二：c方法

#include "stdlib.h"
#include "stdio.h"

int main(int argc, char *argv[])
{
    FILE *in= fopen("D:/in.java", "r");
    char buf[1024];

    while (fgets(buf, sizeof(buf), in) != NULL)
    {
        printf("%s", buf);
    }

    fclose(in);

    return 0;
}

3.2 全部读取¶

方式一：读取到c风格字符串(char*)中

#include <fstream>
int main()
{
    std::ifstream rf;
    int length;
    rf.open("1.txt");      // open input file
    rf.seekg(0, std::ios::end);    // go to the end
    length = rf.tellg();           // report location (this is the length)
    rf.seekg(0, std::ios::beg);    // go back to the beginning
    buffer = new char[length];    // allocate memory for a buffer of appropriate    dimension
    rf.read(buffer, length);       // read the whole file into the buffer
    rf.close();                    // close file handle
}

方式二：读取到string(streambuf)

#include <string>
#include <fstream>
#include <streambuf>
int main()
{
    std::ifstream rf("1.txt");
    std::string data((std::istreambuf_iterator<char>(rf)),    std::istreambuf_iterator<char>());
}

方式三：读取到string(stringstream)

#include <string>
#include <fstream>
#include <sstream>
int main()
{
    std::ifstream rf("1.txt");
    std::stringstream buffer;
    buffer << rf.rdbuf();
    std::string data(buffer.str());
}

4 获取当前工作目录和当前执行程序目录¶

当前工作目录和当前执行程序目录不是同一个目录。 - 当前工作目录：是指启动可执行程序时所在的目录 - 当前执行程序目录：可执行程序所在目录 - 解释：假设有可执行程序~/test/test.exe,当在~用户目录下执行./test/test.exe时，工作目录是~，而当前可执行程序目录是~/test。

4.1 获取当前工作目录¶

方法一：getcwd
方法二：get_current_dir_name
示例

#include <unistd.h>
int main(int argc, char** argv)
{
   {//方法一
        char *path;
        path = get_current_dir_name();
        return 0;
    }
    {//方法二
        char *path = NULL;
        path = getcwd(NULL,0);
        puts(path);
        free(path);
    }
    return 0;
}

4.2 获取当前执行程序目录¶

通过readlink读取/proc/self/exe,获取程序路径（含程序名）。 - 示例

#include<unistd.h>
int main(int argc, char** argv)
{
    char cur_path[1024]={0};
    if (readlink("/proc/self/exe", cur_path, BUF_SMALL)<0)
    {
    printf("获取可执行程序路径失败\n");
    return -1;
    }
    //截取掉程序名
    string cur_dir= cur_path;
    pos=cur_dir.find_last_of('/');
    cur_dir = cur_dir.substr(0, pos);
    return 0;
}