编码
UnicodeString,AnsiString,WideString 和 UTF8String 等字符串类型使用各自的编码存储在内存中(有关详细信息,请参阅字符串类型)。将一种类型的字符串分配给另一种类型可能会导致转换。类型字符串旨在独立编码 - 你永远不应使用其内部表示。
类 Sysutils.TEncoding
提供方法 GetBytes
用于将 string
转换为 TBytes
(字节数组),GetString
用于将 TBytes
转换为 string
。Sysutils.TEncoding
类还提供了许多预定义的编码作为类属性。
处理编码的一种方法是在应用程序中仅使用 string
类型,并在每次需要使用特定编码时使用 TEncoding
- 通常在 I / O 操作,DLL 调用等中…
placeholderCopyprocedure EncodingExample;
var hello,response:string;
dataout,datain:TBytes;
expectedLength:integer;
stringStream:TStringStream;
stringList:TStringList;
begin
hello := 'Hello World!Привет мир!';
dataout := SysUtils.TEncoding.UTF8.GetBytes(hello); //Conversion to UTF8
datain := SomeIOFunction(dataout); //This function expects input as TBytes in UTF8 and returns output as UTF8 encoded TBytes.
response := SysUtils.TEncoding.UTF8.GetString(datain); //Convertsion from UTF8
//In case you need to send text via pointer and length using specific encoding (used mostly for DLL calls)
dataout := SysUtils.TEncoding.GetEncoding('ISO-8859-2').GetBytes(hello); //Conversion to ISO 8859-2
DLLCall(addr(dataout[0]),length(dataout));
//The same is for cases when you get text via pointer and length
expectedLength := DLLCallToGetDataLength();
setLength(datain,expectedLength);
DLLCall(addr(datain[0]),length(datain));
response := Sysutils.TEncoding.GetEncoding(1250).getString(datain);
//TStringStream and TStringList can use encoding for I/O operations
stringList:TStringList.create;
stringList.text := hello;
stringList.saveToFile('file.txt',SysUtils.TEncoding.Unicode);
stringList.destroy;
stringStream := TStringStream(hello,SysUtils.TEncoding.Unicode);
stringStream.saveToFile('file2.txt');
stringStream.Destroy;
end;