[Htmlparser-cvs] htmlparser/src/org/htmlparser/lexer/nodes Attribute.java,1.8,1.9 TagNode.java,1.12,
Brought to you by:
derrickoswald
Menu
▾
▴
[Htmlparser-cvs] htmlparser/src/org/htmlparser/lexer/nodes Attribute.java,1.8,1.9 TagNode.java,1.12,1.13
|
From: <der...@us...> - 2003-10-02 23:49:03
|
Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexer/nodes
In directory sc8-pr-cvs1:/tmp/cvs-serv28867/lexer/nodes
Modified Files:
Attribute.java TagNode.java
Log Message:
Moved SpecialHashTable to util.
Fixed some attribute bugs and some test cases.
Index: Attribute.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexer/nodes/Attribute.java,v
retrieving revision 1.8
retrieving revision 1.9
diff -C2 -d -r1.8 -r1.9
*** Attribute.java 22 Sep 2003 02:39:59 -0000 1.8
--- Attribute.java 2 Oct 2003 23:48:53 -0000 1.9
***************
*** 148,156 ****
{
if (null == mName)
! if (0 <= mNameStart)
mName = mPage.getText (mNameStart, mNameEnd);
return (mName);
}
/**
* Get the value of the attribute.
--- 148,166 ----
{
if (null == mName)
! if ((null != mPage) && (0 <= mNameStart))
mName = mPage.getText (mNameStart, mNameEnd);
return (mName);
}
+ /**
+ * Predicate to determine if this attribute is whitespace.
+ * @return <code>true</code> if this attribute is whitespace,
+ * <code>false</code> if it is a real attribute.
+ */
+ public boolean isWhitespace ()
+ {
+ return (null == getName ());
+ }
+
/**
* Get the value of the attribute.
Index: TagNode.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexer/nodes/TagNode.java,v
retrieving revision 1.12
retrieving revision 1.13
diff -C2 -d -r1.12 -r1.13
*** TagNode.java 28 Sep 2003 15:33:57 -0000 1.12
--- TagNode.java 2 Oct 2003 23:48:53 -0000 1.13
***************
*** 32,68 ****
import java.util.Hashtable;
import java.util.Vector;
- import org.htmlparser.lexer.Cursor;
import org.htmlparser.lexer.Page;
- import org.htmlparser.parserHelper.SpecialHashtable;
import org.htmlparser.util.NodeList;
import org.htmlparser.util.ParserException;
import org.htmlparser.util.Translate;
/**
! * TagNode represents a generic tag. This class allows users to register specific
! * tag scanners, which can identify links, or image references. This tag asks the
! * scanners to run over the text, and identify. It can be used to dynamically
! * configure a parser.
! * @author Kaarle Kaila 23.10.2001
*/
! public class TagNode extends AbstractNode
{
! public static final String TYPE = "TAG";
! /**
! * Constant used as value for the value of the tag name
! * in parseParameters (Kaarle Kaila 3.8.2001)
! */
! public final static String TAGNAME = "$<TAGNAME>$";
! public final static String EMPTYTAG = "$<EMPTYTAG>$";
! public final static String NULLVALUE = "$<NULL>$";
! public final static String NOTHING = "$<NOTHING>$";
! private final static String EMPTY_STRING="";
!
! private boolean emptyXmlTag = false;
/**
* The tag attributes.
! * Objects of type Attribute.
*/
protected Vector mAttributes;
--- 32,57 ----
import java.util.Hashtable;
import java.util.Vector;
+ import org.htmlparser.lexer.Cursor;
+ import org.htmlparser.lexer.Lexer;
import org.htmlparser.lexer.Page;
import org.htmlparser.util.NodeList;
import org.htmlparser.util.ParserException;
+ import org.htmlparser.util.SpecialHashtable;
import org.htmlparser.util.Translate;
/**
! * TagNode represents a generic tag.
! *
*/
! public class TagNode
! extends
! AbstractNode
{
! private boolean emptyXmlTag;
/**
* The tag attributes.
! * Objects of type {@link Attribute}.
*/
protected Vector mAttributes;
***************
*** 108,111 ****
--- 97,108 ----
/**
+ * Create an empty tag.
+ */
+ public TagNode ()
+ {
+ this (null, -1, -1, new Vector ());
+ }
+
+ /**
* Create a tag with the location and attributes provided
* @param page The page this tag was read from.
***************
*** 119,131 ****
super (page, start, end);
mAttributes = attributes;
! }
!
! /**
! * Create an empty tag.
! */
! public TagNode ()
! {
! super (null, -1, -1);
! mAttributes = new Vector ();
}
--- 116,120 ----
super (page, start, end);
mAttributes = attributes;
! emptyXmlTag = false;
}
***************
*** 138,165 ****
public String getAttribute (String name)
{
- Vector attributes;
- int size;
Attribute attribute;
- String string;
String ret;
ret = null;
! attributes = getAttributesEx ();
! if (name.equalsIgnoreCase (TAGNAME))
! ret = ((Attribute)attributes.elementAt (0)).getName ();
else
{
! size = attributes.size ();
! for (int i = 1; i < size; i++)
! {
! attribute = (Attribute)attributes.elementAt (i);
! string = attribute.getName ();
! if ((null != string) && name.equalsIgnoreCase (string))
! {
! ret = attribute.getValue ();
! i = size; // exit fast
! }
! }
}
--- 127,142 ----
public String getAttribute (String name)
{
Attribute attribute;
String ret;
ret = null;
! if (name.equalsIgnoreCase (SpecialHashtable.TAGNAME))
! ret = ((Attribute)getAttributesEx ().elementAt (0)).getName ();
else
{
! attribute = getAttributeEx (name);
! if (null != attribute)
! ret = attribute.getValue ();
}
***************
*** 243,246 ****
--- 220,255 ----
/**
+ * Returns the attribute with the given name.
+ * @param name Name of attribute, case insensitive.
+ * @return The attribute or null if it does
+ * not exist.
+ */
+ public Attribute getAttributeEx (String name)
+ {
+ Vector attributes;
+ int size;
+ Attribute attribute;
+ String string;
+ Attribute ret;
+
+ ret = null;
+
+ attributes = getAttributesEx ();
+ size = attributes.size ();
+ for (int i = 0; i < size; i++)
+ {
+ attribute = (Attribute)attributes.elementAt (i);
+ string = attribute.getName ();
+ if ((null != string) && name.equalsIgnoreCase (string))
+ {
+ ret = attribute;
+ i = size; // exit fast
+ }
+ }
+
+ return (ret);
+ }
+
+ /**
* Set an attribute.
* This replaces an attribute of the same name.
***************
*** 252,255 ****
--- 261,265 ----
boolean replaced;
Vector attributes;
+ int length;
String name;
Attribute test;
***************
*** 258,262 ****
replaced = false;
attributes = getAttributesEx ();
! if (0 < attributes.size ())
{
name = attribute.getName ();
--- 268,273 ----
replaced = false;
attributes = getAttributesEx ();
! length = attributes.size ();
! if (0 < length)
{
name = attribute.getName ();
***************
*** 274,278 ****
--- 285,294 ----
}
if (!replaced)
+ {
+ // add whitespace between attributes
+ if (!((Attribute)attributes.elementAt (length - 1)).isWhitespace ())
+ attributes.addElement (new Attribute ((String)null, " ", (char)0));
attributes.addElement (attribute);
+ }
}
***************
*** 296,300 ****
public Vector getAttributesEx ()
{
! return mAttributes;
}
--- 312,316 ----
public Vector getAttributesEx ()
{
! return (mAttributes);
}
***************
*** 317,326 ****
// special handling for the node name
attribute = (Attribute)attributes.elementAt (0);
! ret.put (TAGNAME, attribute.getName ().toUpperCase ());
// the rest
for (int i = 1; i < attributes.size (); i++)
{
attribute = (Attribute)attributes.elementAt (i);
! if (null != attribute.getName ())
{
if (0 != attribute.getQuote ())
--- 333,342 ----
// special handling for the node name
attribute = (Attribute)attributes.elementAt (0);
! ret.put (SpecialHashtable.TAGNAME, attribute.getName ().toUpperCase ());
// the rest
for (int i = 1; i < attributes.size (); i++)
{
attribute = (Attribute)attributes.elementAt (i);
! if (!attribute.isWhitespace ())
{
if (0 != attribute.getQuote ())
***************
*** 330,337 ****
value = attribute.getValue ();
if ((null != value) && value.equals (""))
! value = NOTHING;
}
if (null == value)
! value = NULLVALUE;
ret.put (attribute.getName ().toUpperCase (), value);
}
--- 346,353 ----
value = attribute.getValue ();
if ((null != value) && value.equals (""))
! value = SpecialHashtable.NOTHING;
}
if (null == value)
! value = SpecialHashtable.NULLVALUE;
ret.put (attribute.getName ().toUpperCase (), value);
}
***************
*** 339,343 ****
}
else
! ret.put (TAGNAME, "");
return (ret);
--- 355,359 ----
}
else
! ret.put (SpecialHashtable.TAGNAME, "");
return (ret);
***************
*** 348,356 ****
* <p>
* <em>
! * Note: This value is converted to uppercase.
! * To get at the original case version of the tag name use:
! * <pre>
! * getAttribute (TagNode.TAGNAME);
! * </pre>
* </em>
* @return The tag name.
--- 364,371 ----
* <p>
* <em>
! * Note: This value is converted to uppercase and does not
! * begin with "/" if it is an end tag.
! * To get at the original text of the tag name use
! * {@link #getRawTagName getRawTagName()}.
* </em>
* @return The tag name.
***************
*** 358,366 ****
public String getTagName ()
{
String ret;
! ret = getAttribute (TAGNAME).toUpperCase ();
! if (ret.startsWith ("/")) // end tag
! ret = ret.substring (1);
return (ret);
--- 373,411 ----
public String getTagName ()
{
+ Vector attributes;
String ret;
! ret = null;
!
! attributes = getAttributesEx ();
! if (0 != attributes.size ())
! {
! ret = getRawTagName ();
! if (null != ret)
! {
! ret = ret.toUpperCase ();
! if (ret.startsWith ("/"))
! ret = ret.substring (1);
! }
! }
!
! return (ret);
! }
!
! /**
! * Return the name of this tag.
! * @return The tag name or null if this tag contains nothing or only
! * whitespace.
! */
! public String getRawTagName ()
! {
! Vector attributes;
! String ret;
!
! ret = null;
!
! attributes = getAttributesEx ();
! if (0 != attributes.size ())
! ret = ((Attribute)attributes.elementAt (0)).getName ();
return (ret);
***************
*** 401,405 ****
public String getText ()
{
! return (mPage.getText (elementBegin () + 1, elementEnd () - 1));
}
--- 446,456 ----
public String getText ()
{
! String ret;
!
! //ret = mPage.getText (elementBegin () + 1, elementEnd () - 1);
! ret = toHtml ();
! ret = ret.substring (1, ret.length () - 1);
!
! return (ret);
}
***************
*** 433,438 ****
else
quote = (char)0;
! attribute = new Attribute (key, value, quote);
! att.addElement (attribute);
}
this.mAttributes = att;
--- 484,500 ----
else
quote = (char)0;
! if (key.equals (SpecialHashtable.TAGNAME))
! {
! attribute = new Attribute (value, null, quote);
! att.insertElementAt (attribute, 0);
! }
! else
! {
! // add whitespace between attributes
! attribute = new Attribute ((String)null, " ", (char)0);
! att.addElement (attribute);
! attribute = new Attribute (key, value, quote);
! att.addElement (attribute);
! }
}
this.mAttributes = att;
***************
*** 489,500 ****
public void setText (String text)
{
! mPage = new Page (text);
! nodeBegin = 0;
! nodeEnd = text.length ();
}
public String toPlainTextString ()
{
! return (EMPTY_STRING);
}
--- 551,580 ----
public void setText (String text)
{
! Lexer lexer;
! TagNode output;
!
! lexer = new Lexer (text);
! try
! {
! output = (TagNode)lexer.nextNode ();
! mPage = output.getPage ();
! nodeBegin = output.elementBegin ();
! nodeEnd = output.elementEnd ();
! mAttributes = output.getAttributesEx ();
! }
! catch (ParserException pe)
! {
! throw new IllegalArgumentException (pe.getMessage ());
! }
}
+ /**
+ * Get the plain text from this node.
+ * @return An empty string (tag contents do not display in a browser).
+ * If you want this tags HTML equivalent, use {@link #toHtml toHtml()}.
+ */
public String toPlainTextString ()
{
! return ("");
}
***************
*** 584,592 ****
}
- public String getType ()
- {
- return TYPE;
- }
-
/**
* Is this an empty xml tag of the form<br>
--- 664,667 ----
***************
*** 604,610 ****
}
public boolean isEndTag ()
{
! return ('/' == getAttribute (TAGNAME).toUpperCase ().charAt (0));
}
}
--- 679,693 ----
}
+ /**
+ * Predicate to determine if this tag is an end tag (i.e. </HTML>).
+ * @return <code>true</code> if this tag is an end tag.
+ */
public boolean isEndTag ()
{
! String raw;
!
! raw = getRawTagName ();
!
! return ((null == raw) ? false : ('/' == raw.charAt (0)));
}
}
|
