问题来源:http://www.cnblogs.com/del/archive/2011/03/24/1994029.html#2059114

Globe 同学有这样的 XML 文件:
<?xml version="1.0" encoding="gb2312"?> <Root> <friend name="十年"></friend> <friend name="曾經奔放過ヾ "></friend> <friend name="돌아와 나쁜 너 "></friend> </root>

其中包含中文、韩文,并且有些是十六进制、有些是十进制,真实的内容应该是:
<?xml version="1.0" encoding="GB2312"?> <Root> <friend name="十年"/> <friend name="曾經奔放過ヾ "/> <friend name="돌아와 나쁜 너 "/> </root>

下面是把它打开并另存为标准的 UTF-8 格式 XML 的代码(使用了 DelphiXE 最新的正则表达式组件):

unit Unit1;

interface

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

type
  TForm1 = class(TForm)
    Button1: TButton;
    procedure Button1Click(Sender: TObject);
  private
    function MyMatchEvaluator(const Match: TMatch): string;
  public
  end;

var
  Form1: TForm1;

implementation

{$R *.dfm}

procedure TForm1.Button1Click(Sender: TObject);
const
  pattern = '&#x?[0-9A-Fa-f]{1,5};';
var
  List: TStringList;
  reg: TRegEx;
  path,tmpName: string;
begin
  with TOpenDialog.Create(nil) do begin
    Execute;
    path := FileName;
    Free;
  end;
  if path = '' then Exit;

  List := TStringList.Create;
  List.LoadFromFile(path);
  List.Text := StringReplace(List.Text, 'GB2312', 'UTF-8', [rfIgnoreCase]);
  reg := TRegEx.Create(pattern, [roCompiled]);
  List.Text := reg.Replace(List.Text, MyMatchEvaluator);

  tmpName := ExtractFileName(path);
  path := StringReplace(path, tmpName, 'UTF8_' + tmpName, [rfIgnoreCase]);
  Text := path;
  List.SaveToFile(path, TEncoding.UTF8);
  List.Free;
end;

function TForm1.MyMatchEvaluator(const Match: TMatch): string;
begin
  Result := Match.Groups[1].Value;
  if Match.Value[3] = 'x' then Result := '$' + Result;
  Result := WideChar(StrToInt(Result));
end;

end.

posted on 2011-04-01 22:32  万一  阅读(3646)  评论(7编辑  收藏  举报