[yunqa.de] Re: Parsing HTML-Tags detect HTML-Tags wrong
- From: Delphi Inspiration <delphi@xxxxxxxx>
- To: yunqa@xxxxxxxxxxxxx
- Date: Fri, 07 Mar 2008 13:41:20 +0100
Simon Schaeberle wrote:
>I think there is a problem in the parser in combination with widestrings.
No, DIHtmlParser does not have any problems parsing Delphi WideStrings. See
compilable example below for details (same contents as attached *.dpr file).
Ralf
{ DIHtmlParser WideString 2 parsing example.
Character codepages and encodings are confusing to many who want to parse
Unicode HTML. By default, DIHtmlParser handles all input as Latin1
(ISO-8859-1). This applies AnsiStrings and WideStrings as well, since both
string types can potentially store any kind of encoding.
AnsiStrings can, for example, hold Latin1 or UTF-8 encoded text. While
Delphi WideStrings usually contain UTF-16LE, they may also contain UTF-16BE.
It is therefore important to set the TDIHtmlParser.ReadMethods to the correct
encoding ahead of the parsing. In this demo we are parsing UTF-16LE
WideStrings, which is made explicit by the following line of code:
HtmlParser.ReadMethods := Read_UTF_16_LE;
Visit the DIHtmlParser homepage for latest information and updates:
http://www.yunqa.de/delphi/
Copyright (c) 2002-2008 Ralf Junker, The Delphi Inspiration <delphi@xxxxxxxx>
------------------------------------------------------------------------------ }
program DIHtmlParser_WideString_Parsing_2;
{$APPTYPE Console}
{$I DI.inc}
uses
DIUnicode, DIHtmlParser;
function ParseHtml(const AInput: WideString): WideString;
var
HP: TDIHtmlParser;
begin
Result := '';
HP := TDIHtmlParser.Create(nil);
try
HP.ReadMethods := Read_UTF_16_LE;
HP.SetSourceBufferAsStrW(AInput); // Notice the ...W for WideString!
HP.FilterHtmlTags.SetStartEnd(fiShow);
HP.FilterText := fiShow;
while HP.ParseNextPiece do
case HP.PieceType of
ptHtmlTag:
Result := Result + HP.HtmlTag.Code;
ptText:
Result := Result + HP.DataAsStrW;
end;
finally
HP.Free;
end;
end;
const
HTML_DATA: WideString =
'<HEAD>' + #13#10 +
' <!--Head Comment-->' + #13#10 +
'</HEAD>' + #13#10 +
'<BODY>' + #13#10 +
' <!--Body Comment-->' + #13#10 +
'Body Text' + #13#10 +
'</BODY>';
begin
WriteLn('Original HTML:');
WriteLn;
WriteLn(HTML_DATA);
WriteLn;
{ Optionally call these register functions once before the parsing. They are
not actually needed for this example, but are be required for correct
parsing if the HTML contains <PRE>, <TITLE>, <SCRIPT> or <STYLE> elements. }
RegisterHtmlTags;
RegisterHtmlAttribs;
RegisterHtmlDecodingEntities;
WriteLn('Parsed HTML:');
WriteLn;
WriteLn(ParseHtml(HTML_DATA));
WriteLn;
WriteLn('Done - Press ENTER to exit.');
ReadLn;
end.
{ DIHtmlParser WideString 2 parsing example.
Character codepages and encodings are confusing to many who want to parse
Unicode HTML. By default, DIHtmlParser handles all input as Latin1
(ISO-8859-1). This applies AnsiStrings and WideStrings as well, since both
string types can potentially store any kind of encoding.
AnsiStrings can, for example, hold Latin1 or UTF-8 encoded text. While
Delphi WideStrings usually contain UTF-16LE, they may also contain UTF-16BE.
It is therefore important to set the TDIHtmlParser.ReadMethods to the correct
encoding ahead of the parsing. In this demo we are parsing UTF-16LE
WideStrings, which is made explicit by the following line of code:
HtmlParser.ReadMethods := Read_UTF_16_LE;
Visit the DIHtmlParser homepage for latest information and updates:
http://www.yunqa.de/delphi/
Copyright (c) 2002-2008 Ralf Junker, The Delphi Inspiration <delphi@xxxxxxxx>
------------------------------------------------------------------------------ }
program DIHtmlParser_WideString_Parsing_2;
{$APPTYPE Console}
{$I DI.inc}
uses
DIUnicode, DIHtmlParser;
function ParseHtml(const AInput: WideString): WideString;
var
HP: TDIHtmlParser;
begin
Result := '';
HP := TDIHtmlParser.Create(nil);
try
HP.ReadMethods := Read_UTF_16_LE;
HP.SetSourceBufferAsStrW(AInput); // Notice the ...W for WideString!
HP.FilterHtmlTags.SetStartEnd(fiShow);
HP.FilterText := fiShow;
while HP.ParseNextPiece do
case HP.PieceType of
ptHtmlTag:
Result := Result + HP.HtmlTag.Code;
ptText:
Result := Result + HP.DataAsStrW;
end;
finally
HP.Free;
end;
end;
const
HTML_DATA: WideString =
'<HEAD>' + #13#10 +
' <!--Head Comment-->' + #13#10 +
'</HEAD>' + #13#10 +
'<BODY>' + #13#10 +
' <!--Body Comment-->' + #13#10 +
'Body Text' + #13#10 +
'</BODY>';
begin
WriteLn('Original HTML:');
WriteLn;
WriteLn(HTML_DATA);
WriteLn;
{ Optionally call these register functions once before the parsing. They are
not actually needed for this example, but are be required for correct
parsing if the HTML contains <PRE>, <TITLE>, <SCRIPT> or <STYLE> elements. }
RegisterHtmlTags;
RegisterHtmlAttribs;
RegisterHtmlDecodingEntities;
WriteLn('Parsed HTML:');
WriteLn;
WriteLn(ParseHtml(HTML_DATA));
WriteLn;
WriteLn('Done - Press ENTER to exit.');
ReadLn;
end.
Other related posts:
