type
TTextFormat=(tfAnsi,tfUnicode,tfUnicodeBigEndian,tfUtf8);
const
TextFormatFlag:array[tfAnsi..tfUtf8] of word=($0000,$FFFE,$FEFF,$EFBB);
function WordLoHiExchange(w:Word):Word;register;
asm
XCHG AL, AH
end;
{ TextFormat返回文本编码类型,sText未经处理的文本 }
procedure ReadTextFile(const FileName: string;
var TextFormat: TTextFormat; var sText:string);
var
w:Word;
b:Byte;
begin
with TFileStream.Create(FileName,fmOpenRead or fmShareDenyNone) do
try
Read(w,2);
w:=WordLoHiExchange(w);//因为是以Word数据类型读取,故高低字节互换
if w = TextFormatFlag[tfUnicode] then
TextFormat:= tfUnicode
else if w = TextFormatFlag[tfUnicodeBigEndian] then
TextFormat:= tfUnicodeBigEndian
else if w = TextFormatFlag[tfUtf8] then
begin
Read(b,1);//这里要注意一下,UFT-8必须要跳过三个字节。
TextFormat:=tfUtf8;
end else
begin
TextFormat:=tfANSI;
Position:=0;
end;
SetLength(sText,Size-Position);
ReadBuffer(sText[1],Size-Position);
finally
Free;
end;
end;