Update of //cvsroot/htmlparser/htmlparser/src/org/htmlparser
In directory sc8-pr-cvs5.sourceforge.net:/tmp/cvs-serv18017
Modified Files:
Parser.java
Log Message:
Allow passing HTML in the Parser constructor.
So now it allows HTML, a URL or a file name.
Index: Parser.java
===================================================================
RCS file: //cvsroot/htmlparser/htmlparser/src/org/htmlparser/Parser.java,v
retrieving revision 1.114
retrieving revision 1.115
diff -C2 -d -r1.114 -r1.115
*** Parser.java 27 May 2006 18:43:25 -0000 1.114
--- Parser.java 30 May 2006 02:53:56 -0000 1.115
***************
*** 298,302 ****
* it in.
* @see #Parser(URLConnection,ParserFeedback)
! * @param resourceLocn Either the URL or the filename (autodetects).
* A standard HTTP GET is performed to read the content of the URL.
* @param feedback The HTMLParserFeedback object to use when information,
--- 298,306 ----
* it in.
* @see #Parser(URLConnection,ParserFeedback)
! * @param resource Either a URL, a filename or a string of HTML.
! * The string is considered HTML if the first non-whitespace character
! * is a <. The use of a url or file is autodetected by first attempting
! * to open the resource as a URL, if that fails it is assumed to be a file
! * name.
* A standard HTTP GET is performed to read the content of the URL.
* @param feedback The HTMLParserFeedback object to use when information,
***************
*** 305,313 ****
* @throws ParserException If the URL is invalid.
*/
! public Parser (String resourceLocn, ParserFeedback feedback)
throws
ParserException
{
! this (getConnectionManager ().openConnection (resourceLocn), feedback);
}
--- 309,340 ----
* @throws ParserException If the URL is invalid.
*/
! public Parser (String resource, ParserFeedback feedback)
throws
ParserException
{
! int length;
! boolean html;
! char ch;
!
! if (null == resource)
! throw new IllegalArgumentException ("resource cannot be null");
! setFeedback (feedback);
! length = resource.length ();
! html = false;
! for (int i = 0; i < length; i++)
! {
! ch = resource.charAt (i);
! if (!Character.isWhitespace (ch))
! {
! if ('<' == ch)
! html = true;
! break;
! }
! }
! if (html)
! setLexer (new Lexer (new Page (resource)));
! else
! setLexer (new Lexer (getConnectionManager ().openConnection (resource)));
! setNodeFactory (new PrototypicalNodeFactory ());
}
***************
*** 315,325 ****
* Creates a Parser object with the location of the resource (URL or file).
* A DefaultHTMLParserFeedback object is used for feedback.
! * @param resourceLocn Either the URL or the filename (autodetects).
* @throws ParserException If the resourceLocn argument does not resolve
* to a valid page or file.
*/
! public Parser (String resourceLocn) throws ParserException
{
! this (resourceLocn, STDOUT);
}
--- 342,353 ----
* Creates a Parser object with the location of the resource (URL or file).
* A DefaultHTMLParserFeedback object is used for feedback.
! * @param resource Either HTML, a URL or a filename (autodetects).
* @throws ParserException If the resourceLocn argument does not resolve
* to a valid page or file.
+ * @see #Parser(string,ParserFeedback)
*/
! public Parser (String resource) throws ParserException
{
! this (resource, STDOUT);
}
***************
*** 808,821 ****
try
{
- parser = new Parser ();
if (1 < args.length)
filter = new TagNameFilter (args[1]);
else
- { // for a simple dump, use more verbose settings
filter = null;
parser.setFeedback (Parser.STDOUT);
getConnectionManager ().setMonitor (parser);
}
- parser.setURL (args[0]);
System.out.println (parser.parse (filter));
}
--- 836,850 ----
try
{
if (1 < args.length)
filter = new TagNameFilter (args[1]);
else
filter = null;
+ parser = new Parser (args[0]);
+ if (1 < args.length)
+ {
+ // for a simple dump, use more verbose settings
parser.setFeedback (Parser.STDOUT);
getConnectionManager ().setMonitor (parser);
}
System.out.println (parser.parse (filter));
}
|
