[Htmlparser-cvs] htmlparser/src/org/htmlparser/scanners CompositeTagScanner.java,1.75,1.76 FormScann
Brought to you by:
derrickoswald
Menu
▾
▴
[Htmlparser-cvs] htmlparser/src/org/htmlparser/scanners CompositeTagScanner.java,1.75,1.76 FormScanner.java,1.50,1.51 ScriptScanner.java,1.45,1.46 TagScanner.java,1.45,1.46
|
From: <der...@us...> - 2003-10-28 12:55:11
|
Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners
In directory sc8-pr-cvs1:/tmp/cvs-serv5437/scanners
Modified Files:
CompositeTagScanner.java FormScanner.java ScriptScanner.java
TagScanner.java
Log Message:
Remove TagScanner cruft.
Index: CompositeTagScanner.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/CompositeTagScanner.java,v
retrieving revision 1.75
retrieving revision 1.76
diff -C2 -d -r1.75 -r1.76
*** CompositeTagScanner.java 28 Oct 2003 10:31:02 -0000 1.75
--- CompositeTagScanner.java 28 Oct 2003 12:54:21 -0000 1.76
***************
*** 238,242 ****
scanner = parser.getScanner (name);
if ((null != scanner) && scanner.evaluate (next, this))
! node = scanner.createScannedNode (next, lexer.getPage ().getUrl (), lexer);
}
}
--- 238,242 ----
scanner = parser.getScanner (name);
if ((null != scanner) && scanner.evaluate (next, this))
! node = scanner.scan (next, lexer.getPage ().getUrl (), lexer);
}
}
***************
*** 252,255 ****
--- 252,256 ----
composite = (CompositeTag)createTag (lexer.getPage (), tag.elementBegin (), endTag.elementEnd (), tag.getAttributesEx (), tag, endTag, nodeList);
+ composite.setThisScanner (this);
for (int i = 0; i < composite.getChildCount (); i++)
composite.childAt (i).setParent (composite);
Index: FormScanner.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/FormScanner.java,v
retrieving revision 1.50
retrieving revision 1.51
diff -C2 -d -r1.50 -r1.51
*** FormScanner.java 28 Oct 2003 10:31:02 -0000 1.50
--- FormScanner.java 28 Oct 2003 12:54:21 -0000 1.51
***************
*** 45,50 ****
{
private static final String [] MATCH_ID = { "FORM" };
- public static final String PREVIOUS_DIRTY_LINK_MESSAGE="Encountered a form tag after an open link tag.\nThere should have been an end tag for the link before the form tag began.\nCorrecting this..";
- private boolean linkScannerAlreadyOpen=false;
private static final String [] formTagEnders = {"FORM","HTML","BODY"};
--- 45,48 ----
***************
*** 110,133 ****
{
return MATCH_ID;
- }
-
- 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());
- // This is dirty HTML. Assume the current tag is
- // not a new link tag - but an end tag. This is actually a really wild bug -
- // Internet Explorer actually parses such tags.
- // So - we shall then proceed to fool the scanner into sending an endtag of type </A>
- // For this - set the dirty flag to true and return
- }
- else
- linkScannerAlreadyOpen = false;
- return super.evaluate(tag, previousOpenScanner);
}
--- 108,111 ----
Index: ScriptScanner.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/ScriptScanner.java,v
retrieving revision 1.45
retrieving revision 1.46
diff -C2 -d -r1.45 -r1.46
*** ScriptScanner.java 28 Oct 2003 03:04:18 -0000 1.45
--- ScriptScanner.java 28 Oct 2003 12:54:21 -0000 1.46
***************
*** 169,172 ****
--- 169,173 ----
//TODO: use the factory:
ret = createTag (lexer.getPage (), tag.elementBegin(), end.elementEnd(), tag.getAttributesEx (), tag, end, new NodeList (last));
+ ret.setThisScanner (this);
}
finally
Index: TagScanner.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/TagScanner.java,v
retrieving revision 1.45
retrieving revision 1.46
diff -C2 -d -r1.45 -r1.46
*** TagScanner.java 27 Oct 2003 02:18:04 -0000 1.45
--- TagScanner.java 28 Oct 2003 12:54:21 -0000 1.46
***************
*** 70,138 ****
Serializable
{
! /**
! * A filter which is used to associate this tag. The filter contains a string
! * that is used to match which tags are to be allowed to pass through. This can
! * be useful when one wishes to dynamically filter out all tags except one type
! * which may be programmed later than the parser. Is also useful for command line
! * implementations of the parser.
! */
! protected String filter;
!
! /**
! * HTMLParserFeedback object automatically initialized
! */
! protected ParserFeedback feedback;
! /**
! * Default Constructor, automatically registers the scanner into a static array of
! * scanners inside Tag
! */
! public TagScanner()
! {
! this.filter="";
! }
! /**
! * This constructor automatically registers the scanner, and sets the filter for this
! * tag.
! * @param filter The filter which will allow this tag to pass through.
! */
! public TagScanner(String filter)
! {
! this.filter=filter;
! }
! /**
! * Insert the method's description here.
! * Creation date: (6/4/2001 11:44:09 AM)
! * @return java.lang.String
! * @param c char
*/
! public String absorb(String s,char c) {
! int index = s.indexOf(c);
! if (index!=-1) s=s.substring(index+1,s.length());
! return s;
}
/**
! * Remove whitespace from the front of the given string.
! * @param s The string to trim.
! * @return Either the same string or a string with whitespace chopped off.
*/
! public static String absorbLeadingBlanks (String s)
{
! int length;
! int i;
! String ret;
!
! i = 0;
! length = s.length ();
! while (i < length && Character.isWhitespace (s.charAt (i)))
! i++;
! if (0 == i)
! ret = s;
! else if (length == i)
! ret = "";
! else
! ret = s.substring (i);
!
! return (ret);
}
--- 70,99 ----
Serializable
{
! /**
! * A filter which is used to associate this tag. The filter contains a string
! * that is used to match which tags are to be allowed to pass through. This can
! * be useful when one wishes to dynamically filter out all tags except one type
! * which may be programmed later than the parser. Is also useful for command line
! * implementations of the parser.
*/
! protected String filter;
!
! /**
! * Default Constructor, automatically registers the scanner into a static array of
! * scanners inside Tag
! */
! public TagScanner ()
! {
! this ("");
}
/**
! * This constructor automatically registers the scanner, and sets the filter for this
! * tag.
! * @param filter The filter which will allow this tag to pass through.
*/
! public TagScanner (String filter)
{
! this.filter=filter;
}
***************
*** 153,356 ****
}
! /**
! * 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() {
return filter;
}
- public static boolean isXMLTagFound(Node node, String tagName) {
- boolean xmlTagFound=false;
- if (node instanceof Tag) {
- Tag tag = (Tag)node;
- if (tag.getText().toUpperCase().indexOf(tagName)==0) {
- xmlTagFound=true;
- }
- }
- return xmlTagFound;
- }
-
- public final Tag createScannedNode(Tag tag,String url,Lexer lexer) throws ParserException {
- Tag thisTag = scan(tag,url,lexer);
- thisTag.setThisScanner(this);
- thisTag.setAttributesEx(tag.getAttributesEx());
- return thisTag;
- }
-
- /**
- * Override this method to create your own tag type
- * @param tagData
- * @param tag
- * @param url
- * @return Tag
- * @throws ParserException
- */
- protected abstract Tag createTag(Page page, int start, int end, Vector attributes, Tag tag, String url) throws ParserException;
-
/**
* Scan the tag and extract the information related to this type. The url of the
* initiating scan has to be provided in case relative links are found. The initial
* url is then prepended to it to give an absolute link.
! * The NodeReader is provided in order to do a lookahead operation. We assume that
* the identification has already been performed using the evaluate() method.
! * @param tag HTML Tag to be scanned for identification
! * @param url The initiating url of the scan (Where the html page lies)
! * @param reader The reader object responsible for reading the html page
*/
! public Tag scan(Tag tag,String url,Lexer lexer) throws ParserException
! {
! return (createTag(lexer.getPage (), tag.elementBegin(), tag.elementEnd(), tag.getAttributesEx (), tag, url));
! }
!
! public String removeChars(String s,String occur) {
! StringBuffer newString = new StringBuffer();
! int index;
! do {
! index = s.indexOf(occur);
! if (index!=-1) {
! newString.append(s.substring(0,index));
! s=s.substring(index+occur.length());
! }
! }
! while (index!=-1);
! newString.append(s);
! return newString.toString();
! }
!
! public abstract String [] getID();
!
! public final void setFeedback(ParserFeedback feedback) {
! this.feedback = feedback;
! }
!
! public static Map adjustScanners(Parser parser)
{
! Map ret;
!
! ret = parser.getScanners();
! // Remove all existing scanners
! parser.flushScanners();
return (ret);
}
- public static void restoreScanners(Parser parser, Hashtable tempScanners)
- {
- // Flush the scanners
- parser.setScanners(tempScanners);
- }
-
/**
! * Insert an EndTag in the currentLine, just before the occurence of the provided tag
*/
! public String insertEndTagBeforeNode(AbstractNode node, String currentLine) {
! String newLine = currentLine.substring(0,node.elementBegin());
! newLine += "</A>";
! newLine += currentLine.substring(node.elementBegin(),currentLine.length());
! return newLine;
! }
!
! // protected Tag getReplacedEndTag(Tag tag, NodeReader reader, String currentLine) {
! // // Replace tag - it was a <A> tag - replace with </a>
! // String newLine = replaceFaultyTagWithEndTag(tag, currentLine);
! // reader.changeLine(newLine);
! // return new EndTag(
! // new TagData(
! // tag.elementBegin(),
! // tag.elementBegin()+3,
! // tag.getTagName(),
! // currentLine
! // )
! // );
! // }
!
! public String replaceFaultyTagWithEndTag(Tag tag, String currentLine) {
! String newLine = currentLine.substring(0,tag.elementBegin());
! newLine+="</"+tag.getTagName()+">";
! newLine+=currentLine.substring(tag.elementEnd()+1,currentLine.length());
!
! return newLine;
! }
!
! // protected Tag getInsertedEndTag(Tag tag, String currentLine) {
! // // Insert end tag
! // String newLine = insertEndTagBeforeNode(tag, currentLine);
! // reader.changeLine(newLine);
! // return new EndTag(
! // new TagData(
! // tag.elementBegin(),
! // tag.elementBegin()+3,
! // tag.getTagName(),
! // currentLine
! // )
! // );
! // }
!
}
--- 114,154 ----
}
! public String getFilter()
{
return filter;
}
/**
* Scan the tag and extract the information related to this type. The url of the
* initiating scan has to be provided in case relative links are found. The initial
* url is then prepended to it to give an absolute link.
! * The Lexer is provided in order to do a lookahead operation. We assume that
* the identification has already been performed using the evaluate() method.
! * @param tag HTML Tag to be scanned for identification.
! * @param url The initiating url of the scan (Where the html page lies).
! * @param lexer Provides html page access.
! * @return The resultant tag (may be unchanged).
*/
! public Tag scan (Tag tag, String url, Lexer lexer) throws ParserException
{
! Tag ret;
!
! ret = createTag(lexer.getPage (), tag.elementBegin(), tag.elementEnd(), tag.getAttributesEx (), tag, url);
! ret.setThisScanner(this);
return (ret);
}
/**
! * Create a tag.
! * Override this method to create your own tag type.
! * @param tagData
! * @param tag
! * @param url
! * @return Tag
! * @throws ParserException
*/
! protected abstract Tag createTag(Page page, int start, int end, Vector attributes, Tag tag, String url) throws ParserException;
+ public abstract String [] getID();
}
|
