[Htmlparser-cvs] htmlparser/src/org/htmlparser/scanners FormScanner.java,1.47,1.48 LinkScanner.java,
Brought to you by:
derrickoswald
Menu
▾
▴
[Htmlparser-cvs] htmlparser/src/org/htmlparser/scanners FormScanner.java,1.47,1.48 LinkScanner.java,1.56,1.57 TagScanner.java,1.44,1.45 TitleScanner.java,1.32,1.33
|
From: <der...@us...> - 2003-10-27 02:18:38
|
Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners
In directory sc8-pr-cvs1:/tmp/cvs-serv25308/scanners
Modified Files:
FormScanner.java LinkScanner.java TagScanner.java
TitleScanner.java
Log Message:
Some speed improvements; passing tags to evaluate, creating strings without string buffers, etc.
Index: FormScanner.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/FormScanner.java,v
retrieving revision 1.47
retrieving revision 1.48
diff -C2 -d -r1.47 -r1.48
*** FormScanner.java 26 Oct 2003 19:46:19 -0000 1.47
--- FormScanner.java 27 Oct 2003 02:18:04 -0000 1.48
***************
*** 115,126 ****
}
! public boolean evaluate(String s, TagScanner previousOpenScanner)
{
! if (previousOpenScanner instanceof LinkScanner) {
linkScannerAlreadyOpen = true;
StringBuffer msg= new StringBuffer();
! msg.append("<");
! msg.append(s);
! msg.append(">");
msg.append(PREVIOUS_DIRTY_LINK_MESSAGE);
feedback.warning(msg.toString());
--- 115,125 ----
}
! public boolean evaluate(Tag tag, TagScanner previousOpenScanner)
{
! if (previousOpenScanner instanceof LinkScanner)
! {
linkScannerAlreadyOpen = true;
StringBuffer msg= new StringBuffer();
! msg.append(tag.toHtml ());
msg.append(PREVIOUS_DIRTY_LINK_MESSAGE);
feedback.warning(msg.toString());
***************
*** 133,137 ****
else
linkScannerAlreadyOpen = false;
! return super.evaluate(s, previousOpenScanner);
}
--- 132,136 ----
else
linkScannerAlreadyOpen = false;
! return super.evaluate(tag, previousOpenScanner);
}
Index: LinkScanner.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/LinkScanner.java,v
retrieving revision 1.56
retrieving revision 1.57
diff -C2 -d -r1.56 -r1.57
*** LinkScanner.java 26 Oct 2003 19:46:20 -0000 1.56
--- LinkScanner.java 27 Oct 2003 02:18:04 -0000 1.57
***************
*** 89,117 ****
/**
! * Template Method, used to decide if this scanner can handle the Link tag type. If
! * the evaluation returns true, the calling side makes a call to scan().
! * @param s The complete text contents of the Tag.
! * @param previousOpenScanner Indicates any previous scanner which hasnt completed, before the current
! * scan has begun, and hence allows us to write scanners that can work with dirty html
*/
! public boolean evaluate (String s, TagScanner previousOpenScanner)
{
! char ch;
! boolean ret;
!
! // eat up leading blanks
! s = absorbLeadingBlanks (s);
! if (5 > s.length ())
! ret = false;
! else
! {
! ch = s.charAt (0);
! if ((ch=='a' || ch=='A') && Character.isWhitespace (s.charAt (1)))
! ret = -1 != s.toUpperCase().indexOf ("HREF");
! else
! ret = false;
! }
!
! return (ret);
}
--- 89,100 ----
/**
! * Check if we can handle this tag.
! * @param tag The generic tag with the name A.
! * @param previousOpenScanner Indicates any previous scanner which hasn't
! * completed, before the current scan has begun.
*/
! public boolean evaluate (Tag tag, TagScanner previousOpenScanner)
{
! return (null != tag.getAttributeEx ("HREF"));
}
Index: TagScanner.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/TagScanner.java,v
retrieving revision 1.44
retrieving revision 1.45
diff -C2 -d -r1.44 -r1.45
*** TagScanner.java 26 Oct 2003 19:46:21 -0000 1.44
--- TagScanner.java 27 Oct 2003 02:18:04 -0000 1.45
***************
*** 57,61 ****
* <br>
* If you wish to write your own scanner, then you must implement scan().
! * You MAY implement evaluate() as well, if your evaluation logic is not based on a simple text match.
* You MUST implement getID() - which identifies your scanner uniquely in the hashtable of scanners.
*
--- 57,62 ----
* <br>
* If you wish to write your own scanner, then you must implement scan().
! * You MAY implement evaluate() as well, if your evaluation logic is not based
! * on a match of the tag name.
* You MUST implement getID() - which identifies your scanner uniquely in the hashtable of scanners.
*
***************
*** 136,221 ****
}
! /**
! * This method is used to decide if this scanner can handle this tag type. If the
! * evaluation returns true, the calling side makes a call to scan().
! * <strong>This method has to be implemented meaningfully only if a first-word match with
! * the scanner id does not imply a match (or extra processing needs to be done).
! * Default returns true</strong>
! * @param tagContents The complete text contents of the Tag.
! * @param previousOpenScanner Indicates any previous scanner which hasnt completed, before the current
! * scan has begun, and hence allows us to write scanners that can work with dirty html
! */
! public boolean evaluate(String tagContents,TagScanner previousOpenScanner) {
! return true;
! }
!
! /**
! * Pull the text between two matching capitalized 'XML' tags.
! * @deprecated This reads ahead on your iterator and doesn't put them back if it's not an XML tag.
! */
! public static String extractXMLData (Node node, String tagName, NodeIterator iterator)
throws
! ParserException
! {
! try
! {
! String xmlData = "";
!
! boolean xmlTagFound = isXMLTagFound (node, tagName);
! if (xmlTagFound)
! {
! try
! {
! do
! {
! node = iterator.nextNode ();
! if (node!=null)
! {
! if (node instanceof StringNode)
! {
! StringNode stringNode = (StringNode)node;
! if (xmlData.length ()>0)
! xmlData+=" ";
! xmlData += stringNode.getText ();
! }
! else
! if (!(node instanceof Tag && ((Tag)node).isEndTag ()))
! xmlTagFound = false;
! }
! }
! while (node instanceof StringNode);
!
! }
!
! catch (Exception e)
! {
! throw new ParserException ("TagScanner.extractXMLData() : error while trying to find xml tag",e);
! }
! }
! // check end tag matches start tag
! if (xmlTagFound)
! {
! if (node!=null)
! {
! if (node instanceof Tag && ((Tag)node).isEndTag ())
! {
! Tag endTag = (Tag)node;
! if (!endTag.getTagName ().equals (tagName))
! xmlTagFound = false;
! }
!
! }
!
! }
! if (xmlTagFound)
! return xmlData;
! else
! return null;
! }
! catch (Exception e)
! {
! throw new ParserException ("TagScanner.extractXMLData() : Error occurred while trying to extract xml tag",e);
! }
! }
public String getFilter() {
--- 137,224 ----
}
! /**
! * This method is used to decide if this scanner can handle this tag type. If the
! * evaluation returns true, the calling side makes a call to scan().
! * <strong>This method has to be implemented meaningfully only if a first-word match with
! * the scanner id does not imply a match (or extra processing needs to be done).
! * Default returns true</strong>
! * @param tag The tag with a name that matches a value from {@link #getID}.
! * @param previousOpenScanner Indicates any previous scanner which hasn't
! * completed, before the current scan has begun, and hence allows us to
! * write scanners that can work with dirty html.
! */
! public boolean evaluate (Tag tag, TagScanner previousOpenScanner)
! {
! return (true);
! }
!
! /**
! * Pull the text between two matching capitalized 'XML' tags.
! * @deprecated This reads ahead on your iterator and doesn't put them back if it's not an XML tag.
! */
! public static String extractXMLData (Node node, String tagName, NodeIterator iterator)
throws
! ParserException
! {
! try
! {
! String xmlData = "";
!
! boolean xmlTagFound = isXMLTagFound (node, tagName);
! if (xmlTagFound)
! {
! try
! {
! do
! {
! node = iterator.nextNode ();
! if (node!=null)
! {
! if (node instanceof StringNode)
! {
! StringNode stringNode = (StringNode)node;
! if (xmlData.length ()>0)
! xmlData+=" ";
! xmlData += stringNode.getText ();
! }
! else
! if (!(node instanceof Tag && ((Tag)node).isEndTag ()))
! xmlTagFound = false;
! }
! }
! while (node instanceof StringNode);
!
! }
!
! catch (Exception e)
! {
! throw new ParserException ("TagScanner.extractXMLData() : error while trying to find xml tag",e);
! }
! }
! // check end tag matches start tag
! if (xmlTagFound)
! {
! if (node!=null)
! {
! if (node instanceof Tag && ((Tag)node).isEndTag ())
! {
! Tag endTag = (Tag)node;
! if (!endTag.getTagName ().equals (tagName))
! xmlTagFound = false;
! }
!
! }
!
! }
! if (xmlTagFound)
! return xmlData;
! else
! return null;
! }
! catch (Exception e)
! {
! throw new ParserException ("TagScanner.extractXMLData() : Error occurred while trying to extract xml tag",e);
! }
! }
public String getFilter() {
Index: TitleScanner.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/TitleScanner.java,v
retrieving revision 1.32
retrieving revision 1.33
diff -C2 -d -r1.32 -r1.33
*** TitleScanner.java 26 Oct 2003 19:46:21 -0000 1.32
--- TitleScanner.java 27 Oct 2003 02:18:04 -0000 1.33
***************
*** 53,60 ****
}
! public boolean evaluate(String tagNameBeingChecked, TagScanner previousOpenScanner) {
! absorbLeadingBlanks(tagNameBeingChecked);
! return (tagNameBeingChecked.toUpperCase ().startsWith (MATCH_NAME[0]) && ((null == previousOpenScanner)
! || !previousOpenScanner.getID ()[0].equals ("TITLE")));
}
--- 53,59 ----
}
! public boolean evaluate(Tag tag, TagScanner previousOpenScanner)
! {
! return ((null == previousOpenScanner) || !previousOpenScanner.getID ()[0].equals ("TITLE"));
}
|
