delphi - Delphi 2010:如何模拟Delphi XE TStrings.Encoding属性？

Question

Delphi XE在Encoding类中添加了TStrings属性，该属性存储在调用LoadFromFile()时从BOM表读取的编码。

Delphi 2010没有此属性。
我想效仿它。

我为TStrings创建了以下类帮助器。
该助手可以工作，但是要获得文件的BOM，我发现的唯一解决方案是在FileStream中重新加载相同的文件。我想避免这种情况，因为TStrings.LoadFromFile()已经获得了BOM。

如何告诉助手重新使用已经找到的BOM？

unit TestEncodingName_00;

interface

uses
  Windows, Messages, SysUtils, Variants, Classes, Graphics, Controls, Forms,
  Dialogs, StdCtrls, ExtDlgs;

type
  TForm1 = class(TForm)
  Memo1: TMemo;
  procedure FormCreate(Sender: TObject);
private
{ Private declarations }
public
{ Public declarations }
end;

TMyStrings = class helper for TStrings   // emulate TStrings.Encoding
private
  function GetEncodingName(fPath:string):string;
public
property EncodingName[fPath:string]:string read GetEncodingName;
end;

var
Form1: TForm1;

implementation

{$R *.dfm}

function  TMyStrings.GetEncodingName(fPath:string):string;
var
  fLen : integer;
  fBuffer : TBytes;
  fEncoding : TEncoding;
  fName : string;
  fFs : TFileStream;

begin
   fFs := TFileStream.Create(fPath, fmOpenRead);
 try
    SetLength(fBuffer, 4);
    flen := fFs.Read(fBuffer[0], 4);
    if flen < 4 then
      SetLength(fBuffer, flen);
    fEncoding := nil;
    TEncoding.GetBufferEncoding(fBuffer, fEncoding);
    if fEncoding = TEncoding.Unicode then
    fName := 'Unicode'
  else if fEncoding = TEncoding.UTF8 then
    fName := 'UTF8'
  else fName := 'Default';
  finally
    fFs.Free;
  end;
  result := fName;

end;

procedure TForm1.FormCreate(Sender: TObject);
var
  EncName : string;

begin
(* sample UTF8.txt
Ā ā Ă ă
Ρ Σ Τ Υ
ぁ あ ぃ
*)
  Memo1.Lines.LoadFromFile('Sample UTF8.txt');
  //from here TStrings knows the BOM but I don't know
  // how to refer to it...
  // so I have to create again a stream of the same file to
  // get the BOM. I don't like that.
  EncName :=  Memo1.Lines.EncodingName['Sample UTF8.txt'];
  Memo1.Lines.Add(#13#10'Encoding : ' + EncName);
end;
end. 

Answer 1

首先，是LoadFromStream()发现BOM表编码，而不是LoadFromFile()。 LoadFromFile()只需将文件打开到TFileStream中，然后调用LoadFromStream()。

在Delphi（2009和2010）中，发现的BOM编码不会存储在您可以访问的任何位置。这就是XE通过添加新的Encoding属性解决的问题。在解析之前将文件数据解码为LoadFromStream()时，该编码仅用作UnicodeString内部的局部变量，然后在LoadFromStream()退出时被丢弃。您无能改变这种行为。

因此，唯一的解决方案是手动加载文件，以便您发现其BOM。理想情况下，您将在后代类中覆盖LoadFromStream()，但是不能使TMemo.Lines使用自定义类。 class helper也不能覆盖虚拟方法。

但是，您可以从TStringList派生自定义类以覆盖LoadFromStream()，自己加载文件，然后将Assign()从TStringList到TMemo.Lines。例如：

unit TestEncodingName_00;

interface

uses
  Windows, Messages, SysUtils, Variants, Classes, Graphics, Controls, Forms,
  Dialogs, StdCtrls, ExtDlgs;

type
  TForm1 = class(TForm)
    Memo1: TMemo;
    procedure FormCreate(Sender: TObject);
  private
    { Private declarations }
  public
    { Public declarations }
  end;

  TMyStringList = class(TStringList)
  private
    fEncoding: TEncoding;
  public
    { The single-parameter LoadFromStream(Stream: TStream) simply
    calls LoadFromStream(Stream: TStream; Encoding: TEncoding) with
    the Encoding parameter set to nil, so you only have to override
    that version of LoadFromStream()... }
    procedure LoadFromStream(Stream: TStream; Encoding: TEncoding); override;
    property Encoding: TEncoding read fEncoding;
  end;

var
  Form1: TForm1;

implementation

{$R *.dfm}

procedure TMyStringList.LoadFromStream(Stream: TStream; Encoding: TEncoding);
var
  Size: Integer;
  Buffer: TBytes;
begin
  { this is similar to the implementation that LoadFromStream()
  uses in XE+, but with some differences:

  1. the Encoding property is assigned a bit differently, as XE+
     utilizes a TEncoding.Clone() method when the specified Encoding
     is not a standard RTL encoding (ie, is a custom user class), but
     Clone() does not exist in D2009/2010.

  2. XE+ has a TStrings.DefaultEncoding property, which is passed
     to TEncoding.GetBufferEncoding() as the default to return if no
     BOM is detected, but that property and parameter do not exist in
     D2009/2010.

  3. TStrings.LoadFromStream() does not check if Size is 0 (file is empty)
     before dereferencing the Buffer that is passed to Stream.Read().
     That is a runtime crash waiting to happen! }

  BeginUpdate;
  try
    Size := Stream.Size - Stream.Position;
    SetLength(Buffer, Size);
    if Size > 0 then
      Stream.Read(Buffer[0], Size);
    Size := TEncoding.GetBufferEncoding(Buffer, Encoding);
    fEncoding := Encoding;
    SetTextStr(Encoding.GetString(Buffer, Size, Length(Buffer) - Size));
  finally
    EndUpdate;
  end;
end;

procedure TForm1.FormCreate(Sender: TObject);
var
  EncName : string;
  List: TMyStringList;
begin
  List := TMyStringList.Create;
  try
    List.LoadFromFile('Sample UTF8.txt');
    if List.Encoding = TEncoding.Unicode then
      EncName := 'Unicode'
    else if List.Encoding = TEncoding.UTF8 then
      EncName := 'UTF8'
    else
      EncName := 'Default';

    Memo1.Lines.Assign(List);
    Memo1.Lines.Add;
    Memo1.Lines.Add('Encoding : ' + EncName);
  finally
    List.Free;
  end;
end;

end.