怎样读取文本文档中的unicode编码
在一个文本文档中,其中有几行是unicode码,请问如何用C语言程序查找定位这些行?小菜鸟。。。。
以下是同一文字在不同编码体系下的内码:
程序代码:
#include "stdafx.h"
using namespace System;
using namespace System::Text;
using namespace System::IO;
int main(array<System::String ^> ^args)
{
String^ content = "端面模数AZ1";
Encoding^ unicode = Encoding::Unicode;
array<Byte>^ unicode_array = gcnew array<Byte>(unicode->GetByteCount(content));
Console::Write("Unicode: {0} ", content);
unicode_array = unicode->GetBytes(content);
for (int i = 0; i < unicode_array->Length; ++i)
{
Console::Write("{0:X2} ", unicode_array[i]);
}
Console::WriteLine();
Encoding^ ansi = Encoding::Default;
array<Byte>^ ansi_array = Encoding::Convert(unicode, ansi, unicode_array);
Console::Write(" ANSI: {0} ", ansi->GetString(ansi_array));
for (int i = 0; i < ansi_array->Length; ++i)
{
Console::Write("{0:X2} ", ansi_array[i]);
}
Console::WriteLine();
Encoding^ utf8 = Encoding::UTF8;
array<Byte>^ utf8_array = Encoding::Convert(unicode, utf8, unicode_array);
Console::Write(" UTF8: {0} ", utf8->GetString(utf8_array));
for (int i = 0; i < utf8_array->Length; ++i)
{
Console::Write("{0:X2} ", utf8_array[i]);
}
Console::WriteLine();
return 0;
}
