Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserapplications
In directory sc8-pr-cvs1.sourceforge.net:/tmp/cvs-serv9575/src/org/htmlparser/parserapplications
Modified Files:
SiteCapturer.java
Log Message:
Fix bug #998195 SiteCatpurer just crashed
After EncodingChangeException try again with the encoding now set correctly.
Index: SiteCapturer.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserapplications/SiteCapturer.java,v
retrieving revision 1.5
retrieving revision 1.6
diff -C2 -d -r1.5 -r1.6
*** SiteCapturer.java 19 Jan 2004 23:14:18 -0000 1.5
--- SiteCapturer.java 29 Jul 2004 01:50:19 -0000 1.6
***************
*** 52,55 ****
--- 52,56 ----
import org.htmlparser.tags.LinkTag;
import org.htmlparser.tags.MetaTag;
+ import org.htmlparser.util.EncodingChangeException;
import org.htmlparser.util.NodeIterator;
import org.htmlparser.util.NodeList;
***************
*** 439,445 ****
// fetch the page and gather the list of nodes
mParser.setURL (url);
! list = new NodeList ();
! for (NodeIterator e = mParser.elements (); e.hasMoreNodes (); )
! list.add (e.nextNode ()); // URL conversion occurs in the tags
// handle robots meta tag according to http://www.robotstxt.org/wc/meta-user.html
--- 440,459 ----
// fetch the page and gather the list of nodes
mParser.setURL (url);
! try
! {
! list = new NodeList ();
! for (NodeIterator e = mParser.elements (); e.hasMoreNodes (); )
! list.add (e.nextNode ()); // URL conversion occurs in the tags
! }
! catch (EncodingChangeException ece)
! {
! // fix bug #998195 SiteCatpurer just crashed
! // try again with the encoding now set correctly
! // hopefully mPages, mImages, mCopied and mFinished won't be corrupted
! mParser.reset ();
! list = new NodeList ();
! for (NodeIterator e = mParser.elements (); e.hasMoreNodes (); )
! list.add (e.nextNode ());
! }
// handle robots meta tag according to http://www.robotstxt.org/wc/meta-user.html
|
