sqlite中文亂碼問題原因分析及解決
更新時(shí)間:2013年04月19日 15:53:14 作者:
打開數(shù)據(jù)庫,插入,查詢數(shù)據(jù)庫等,如果操作接口輸入?yún)?shù)包含中文字符,會導(dǎo)致操作異常,這是由于sqlite數(shù)據(jù)庫使用的是UTF-8編碼方式
在VC++中通過sqlite3.dll接口對sqlite數(shù)據(jù)庫進(jìn)行操作,包括打開數(shù)據(jù)庫,插入,查詢數(shù)據(jù)庫等,如果操作接口輸入?yún)?shù)包含中文字符,會導(dǎo)致操作異常。例如調(diào)用sqlite3_open打開數(shù)據(jù)庫文件,如果文件路徑出現(xiàn)中文,就會導(dǎo)致打開失敗。sqlite3_exec執(zhí)行sql語句,如果包含中文對應(yīng)字符就會變成亂碼。
這是由于sqlite數(shù)據(jù)庫使用的是UTF-8編碼方式,而傳入的字符串是ASCII編碼或Unicode編碼,導(dǎo)致字符串格式錯(cuò)誤。解決方案是在調(diào)用sqlite接口之前,先將字符串轉(zhuǎn)換成UTF-8編碼,以下提供各種字符串編碼轉(zhuǎn)換函數(shù)。
//UTF-8轉(zhuǎn)Unicode
std::wstring Utf82Unicode(const std::string& utf8string)
{
int widesize = ::MultiByteToWideChar(CP_UTF8, 0, utf8string.c_str(), -1, NULL, 0);
if (widesize == ERROR_NO_UNICODE_TRANSLATION)
{
throw std::exception("Invalid UTF-8 sequence.");
}
if (widesize == 0)
{
throw std::exception("Error in conversion.");
}
std::vector<wchar_t> resultstring(widesize);
int convresult = ::MultiByteToWideChar(CP_UTF8, 0, utf8string.c_str(), -1, &resultstring[0], widesize);
if (convresult != widesize)
{
throw std::exception("La falla!");
}
return std::wstring(&resultstring[0]);
}
//unicode 轉(zhuǎn)為 ascii
string WideByte2Acsi(wstring& wstrcode)
{
int asciisize = ::WideCharToMultiByte(CP_OEMCP, 0, wstrcode.c_str(), -1, NULL, 0, NULL, NULL);
if (asciisize == ERROR_NO_UNICODE_TRANSLATION)
{
throw std::exception("Invalid UTF-8 sequence.");
}
if (asciisize == 0)
{
throw std::exception("Error in conversion.");
}
std::vector<char> resultstring(asciisize);
int convresult =::WideCharToMultiByte(CP_OEMCP, 0, wstrcode.c_str(), -1, &resultstring[0], asciisize, NULL, NULL);
if (convresult != asciisize)
{
throw std::exception("La falla!");
}
return std::string(&resultstring[0]);
}
//utf-8 轉(zhuǎn) ascii
string UTF_82ASCII(string& strUtf8Code)
{
string strRet("");
//先把 utf8 轉(zhuǎn)為 unicode
wstring wstr = Utf82Unicode(strUtf8Code);
//最后把 unicode 轉(zhuǎn)為 ascii
strRet = WideByte2Acsi(wstr);
return strRet;
}
///////////////////////////////////////////////////////////////////////
//ascii 轉(zhuǎn) Unicode
wstring Acsi2WideByte(string& strascii)
{
int widesize = MultiByteToWideChar (CP_ACP, 0, (char*)strascii.c_str(), -1, NULL, 0);
if (widesize == ERROR_NO_UNICODE_TRANSLATION)
{
throw std::exception("Invalid UTF-8 sequence.");
}
if (widesize == 0)
{
throw std::exception("Error in conversion.");
}
std::vector<wchar_t> resultstring(widesize);
int convresult = MultiByteToWideChar (CP_ACP, 0, (char*)strascii.c_str(), -1, &resultstring[0], widesize);
if (convresult != widesize)
{
throw std::exception("La falla!");
}
return std::wstring(&resultstring[0]);
}
//Unicode 轉(zhuǎn) Utf8
std::string Unicode2Utf8(const std::wstring& widestring)
{
int utf8size = ::WideCharToMultiByte(CP_UTF8, 0, widestring.c_str(), -1, NULL, 0, NULL, NULL);
if (utf8size == 0)
{
throw std::exception("Error in conversion.");
}
std::vector<char> resultstring(utf8size);
int convresult = ::WideCharToMultiByte(CP_UTF8, 0, widestring.c_str(), -1, &resultstring[0], utf8size, NULL, NULL);
if (convresult != utf8size)
{
throw std::exception("La falla!");
}
return std::string(&resultstring[0]);
}
//ascii 轉(zhuǎn) Utf8
string ASCII2UTF_8(string& strAsciiCode)
{
string strRet("");
//先把 ascii 轉(zhuǎn)為 unicode
wstring wstr = Acsi2WideByte(strAsciiCode);
//最后把 unicode 轉(zhuǎn)為 utf8
strRet = Unicode2Utf8(wstr);
return strRet;
}
這是由于sqlite數(shù)據(jù)庫使用的是UTF-8編碼方式,而傳入的字符串是ASCII編碼或Unicode編碼,導(dǎo)致字符串格式錯(cuò)誤。解決方案是在調(diào)用sqlite接口之前,先將字符串轉(zhuǎn)換成UTF-8編碼,以下提供各種字符串編碼轉(zhuǎn)換函數(shù)。
復(fù)制代碼 代碼如下:
//UTF-8轉(zhuǎn)Unicode
std::wstring Utf82Unicode(const std::string& utf8string)
{
int widesize = ::MultiByteToWideChar(CP_UTF8, 0, utf8string.c_str(), -1, NULL, 0);
if (widesize == ERROR_NO_UNICODE_TRANSLATION)
{
throw std::exception("Invalid UTF-8 sequence.");
}
if (widesize == 0)
{
throw std::exception("Error in conversion.");
}
std::vector<wchar_t> resultstring(widesize);
int convresult = ::MultiByteToWideChar(CP_UTF8, 0, utf8string.c_str(), -1, &resultstring[0], widesize);
if (convresult != widesize)
{
throw std::exception("La falla!");
}
return std::wstring(&resultstring[0]);
}
//unicode 轉(zhuǎn)為 ascii
string WideByte2Acsi(wstring& wstrcode)
{
int asciisize = ::WideCharToMultiByte(CP_OEMCP, 0, wstrcode.c_str(), -1, NULL, 0, NULL, NULL);
if (asciisize == ERROR_NO_UNICODE_TRANSLATION)
{
throw std::exception("Invalid UTF-8 sequence.");
}
if (asciisize == 0)
{
throw std::exception("Error in conversion.");
}
std::vector<char> resultstring(asciisize);
int convresult =::WideCharToMultiByte(CP_OEMCP, 0, wstrcode.c_str(), -1, &resultstring[0], asciisize, NULL, NULL);
if (convresult != asciisize)
{
throw std::exception("La falla!");
}
return std::string(&resultstring[0]);
}
//utf-8 轉(zhuǎn) ascii
string UTF_82ASCII(string& strUtf8Code)
{
string strRet("");
//先把 utf8 轉(zhuǎn)為 unicode
wstring wstr = Utf82Unicode(strUtf8Code);
//最后把 unicode 轉(zhuǎn)為 ascii
strRet = WideByte2Acsi(wstr);
return strRet;
}
///////////////////////////////////////////////////////////////////////
//ascii 轉(zhuǎn) Unicode
wstring Acsi2WideByte(string& strascii)
{
int widesize = MultiByteToWideChar (CP_ACP, 0, (char*)strascii.c_str(), -1, NULL, 0);
if (widesize == ERROR_NO_UNICODE_TRANSLATION)
{
throw std::exception("Invalid UTF-8 sequence.");
}
if (widesize == 0)
{
throw std::exception("Error in conversion.");
}
std::vector<wchar_t> resultstring(widesize);
int convresult = MultiByteToWideChar (CP_ACP, 0, (char*)strascii.c_str(), -1, &resultstring[0], widesize);
if (convresult != widesize)
{
throw std::exception("La falla!");
}
return std::wstring(&resultstring[0]);
}
//Unicode 轉(zhuǎn) Utf8
std::string Unicode2Utf8(const std::wstring& widestring)
{
int utf8size = ::WideCharToMultiByte(CP_UTF8, 0, widestring.c_str(), -1, NULL, 0, NULL, NULL);
if (utf8size == 0)
{
throw std::exception("Error in conversion.");
}
std::vector<char> resultstring(utf8size);
int convresult = ::WideCharToMultiByte(CP_UTF8, 0, widestring.c_str(), -1, &resultstring[0], utf8size, NULL, NULL);
if (convresult != utf8size)
{
throw std::exception("La falla!");
}
return std::string(&resultstring[0]);
}
//ascii 轉(zhuǎn) Utf8
string ASCII2UTF_8(string& strAsciiCode)
{
string strRet("");
//先把 ascii 轉(zhuǎn)為 unicode
wstring wstr = Acsi2WideByte(strAsciiCode);
//最后把 unicode 轉(zhuǎn)為 utf8
strRet = Unicode2Utf8(wstr);
return strRet;
}
相關(guān)文章
sqlite3自動插入創(chuàng)建時(shí)間和更新時(shí)間的功能實(shí)現(xiàn)
最近在記錄一些簡單的結(jié)構(gòu)化日志信息時(shí),用到了sqlite3數(shù)據(jù)庫(保存的信息比較簡單,用Mysql,SQL Server,Postgres這些數(shù)據(jù)庫有點(diǎn)小題大做),這次使用,希望sqlite3也能提供幾個(gè)基本的功能,自動插入創(chuàng)建時(shí)間和更新時(shí)間,需要的朋友可以參考下2024-06-06
SQLite教程(十四):C語言編程實(shí)例代碼(2)
這篇文章主要介紹了SQLite教程(十四):C語言編程實(shí)例代碼(2),本文講解了高效的批量數(shù)據(jù)插入和數(shù)據(jù)查詢代碼實(shí)例,需要的朋友可以參考下2015-05-05
為SQLite3提供一個(gè)ANSI到UTF8的互轉(zhuǎn)函數(shù)
這篇文章主要為大家分享下ANSI與UTF8的互轉(zhuǎn)函數(shù),需要的朋友可以收藏下2013-12-12
System.Data.SQLite 數(shù)據(jù)庫詳細(xì)介紹
System.Data.SQLite是SQLite的加強(qiáng)版,它可以無需.NET Framework支持,由于它內(nèi)部包含了一個(gè)ADO.NET 2.0引擎,所以.NET開發(fā)人員可以利用System.Data.SQLite方便地開發(fā).NET程序。2011-02-02

