/* HTMLDocument.java --
Copyright (C) 2005 Free Software Foundation, Inc.
This file is part of GNU Classpath.
GNU Classpath is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2, or (at your option)
any later version.
GNU Classpath is distributed in the hope that it will be useful, but
WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
General Public License for more details.
You should have received a copy of the GNU General Public License
along with GNU Classpath; see the file COPYING. If not, write to the
Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
02110-1301 USA.
Linking this library statically or dynamically with other modules is
making a combined work based on this library. Thus, the terms and
conditions of the GNU General Public License cover the whole
combination.
As a special exception, the copyright holders of this library give you
permission to link this library with independent modules to produce an
executable, regardless of the license terms of these independent
modules, and to copy and distribute the resulting executable under
terms of your choice, provided that you also meet, for each linked
independent module, the terms and conditions of the license of that
module. An independent module is a module which is not derived from
or based on this library. If you modify this library, you may extend
this exception to your version of the library, but you are not
obligated to do so. If you do not wish to do so, delete this
exception statement from your version. */
package javax.swing.text.html;
import gnu.classpath.NotImplementedException;
import java.io.IOException;
import java.io.StringReader;
import java.net.MalformedURLException;
import java.net.URL;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.Stack;
import java.util.Vector;
import javax.swing.ButtonGroup;
import javax.swing.DefaultButtonModel;
import javax.swing.JEditorPane;
import javax.swing.ListSelectionModel;
import javax.swing.event.DocumentEvent;
import javax.swing.event.UndoableEditEvent;
import javax.swing.text.AbstractDocument;
import javax.swing.text.AttributeSet;
import javax.swing.text.BadLocationException;
import javax.swing.text.DefaultStyledDocument;
import javax.swing.text.Element;
import javax.swing.text.ElementIterator;
import javax.swing.text.GapContent;
import javax.swing.text.MutableAttributeSet;
import javax.swing.text.PlainDocument;
import javax.swing.text.SimpleAttributeSet;
import javax.swing.text.StyleConstants;
import javax.swing.text.html.HTML.Tag;
/**
* Represents the HTML document that is constructed by defining the text and
* other components (images, buttons, etc) in HTML language. This class can
* becomes the default document for {@link JEditorPane} after setting its
* content type to "text/html". HTML document also serves as an intermediate
* data structure when it is needed to parse HTML and then obtain the content of
* the certain types of tags. This class also has methods for modifying the HTML
* content.
*
* @author Audrius Meskauskas (AudriusA@Bioinformatics.org)
* @author Anthony Balkissoon (abalkiss@redhat.com)
* @author Lillian Angel (langel@redhat.com)
*/
public class HTMLDocument extends DefaultStyledDocument
{
/** A key for document properies. The value for the key is
* a Vector of Strings of comments not found in the body.
*/
public static final String AdditionalComments = "AdditionalComments";
URL baseURL = null;
boolean preservesUnknownTags = true;
int tokenThreshold = Integer.MAX_VALUE;
HTMLEditorKit.Parser parser;
/**
* Indicates whether this document is inside a frame or not.
*/
private boolean frameDocument;
/**
* Package private to avoid accessor methods.
*/
String baseTarget;
/**
* Constructs an HTML document using the default buffer size and a default
* StyleSheet.
*/
public HTMLDocument()
{
this(new GapContent(BUFFER_SIZE_DEFAULT), new StyleSheet());
}
/**
* Constructs an HTML document with the default content storage
* implementation and the specified style/attribute storage mechanism.
*
* @param styles - the style sheet
*/
public HTMLDocument(StyleSheet styles)
{
this(new GapContent(BUFFER_SIZE_DEFAULT), styles);
}
/**
* Constructs an HTML document with the given content storage implementation
* and the given style/attribute storage mechanism.
*
* @param c - the document's content
* @param styles - the style sheet
*/
public HTMLDocument(AbstractDocument.Content c, StyleSheet styles)
{
super(c, styles);
}
/**
* Gets the style sheet with the document display rules (CSS) that were specified
* in the HTML document.
*
* @return - the style sheet
*/
public StyleSheet getStyleSheet()
{
return (StyleSheet) getAttributeContext();
}
/**
* This method creates a root element for the new document.
*
* @return the new default root
*/
protected AbstractElement createDefaultRoot()
{
AbstractDocument.AttributeContext ctx = getAttributeContext();
// Create html element.
AttributeSet atts = ctx.getEmptySet();
atts = ctx.addAttribute(atts, StyleConstants.NameAttribute, HTML.Tag.HTML);
BranchElement html = (BranchElement) createBranchElement(null, atts);
// Create body element.
atts = ctx.getEmptySet();
atts = ctx.addAttribute(atts, StyleConstants.NameAttribute, HTML.Tag.BODY);
BranchElement body = (BranchElement) createBranchElement(html, atts);
html.replace(0, 0, new Element[] { body });
// Create p element.
atts = ctx.getEmptySet();
atts = ctx.addAttribute(atts, StyleConstants.NameAttribute, HTML.Tag.P);
BranchElement p = (BranchElement) createBranchElement(body, atts);
body.replace(0, 0, new Element[] { p });
// Create an empty leaf element.
atts = ctx.getEmptySet();
atts = ctx.addAttribute(atts, StyleConstants.NameAttribute,
HTML.Tag.CONTENT);
Element leaf = createLeafElement(p, atts, 0, 1);
p.replace(0, 0, new Element[]{ leaf });
return html;
}
/**
* This method returns an HTMLDocument.RunElement object attached to
* parent representing a run of text from p0 to p1. The run has
* attributes described by a.
*
* @param parent - the parent element
* @param a - the attributes for the element
* @param p0 - the beginning of the range >= 0
* @param p1 - the end of the range >= p0
*
* @return the new element
*/
protected Element createLeafElement(Element parent, AttributeSet a, int p0,
int p1)
{
return new RunElement(parent, a, p0, p1);
}
/**
* This method returns an HTMLDocument.BlockElement object representing the
* attribute set a and attached to parent.
*
* @param parent - the parent element
* @param a - the attributes for the element
*
* @return the new element
*/
protected Element createBranchElement(Element parent, AttributeSet a)
{
return new BlockElement(parent, a);
}
/**
* Returns the parser used by this HTMLDocument to insert HTML.
*
* @return the parser used by this HTMLDocument to insert HTML.
*/
public HTMLEditorKit.Parser getParser()
{
return parser;
}
/**
* Sets the parser used by this HTMLDocument to insert HTML.
*
* @param p the parser to use
*/
public void setParser (HTMLEditorKit.Parser p)
{
parser = p;
}
/**
* Sets the number of tokens to buffer before trying to display the
* Document.
*
* @param n the number of tokens to buffer
*/
public void setTokenThreshold (int n)
{
tokenThreshold = n;
}
/**
* Returns the number of tokens that are buffered before the document
* is rendered.
*
* @return the number of tokens buffered
*/
public int getTokenThreshold ()
{
return tokenThreshold;
}
/**
* Returns the location against which to resolve relative URLs.
* This is the document's URL if the document was loaded from a URL.
* If a base
tag is found, it will be used.
* @return the base URL
*/
public URL getBase()
{
return baseURL;
}
/**
* Sets the location against which to resolve relative URLs.
* @param u the new base URL
*/
public void setBase(URL u)
{
baseURL = u;
getStyleSheet().setBase(u);
}
/**
* Returns whether or not the parser preserves unknown HTML tags.
* @return true if the parser preserves unknown tags
*/
public boolean getPreservesUnknownTags()
{
return preservesUnknownTags;
}
/**
* Sets the behaviour of the parser when it encounters unknown HTML tags.
* @param preservesTags true if the parser should preserve unknown tags.
*/
public void setPreservesUnknownTags(boolean preservesTags)
{
preservesUnknownTags = preservesTags;
}
/**
* An iterator to iterate through LeafElements in the document.
*/
class LeafIterator extends Iterator
{
HTML.Tag tag;
HTMLDocument doc;
ElementIterator it;
public LeafIterator (HTML.Tag t, HTMLDocument d)
{
doc = d;
tag = t;
it = new ElementIterator(doc);
}
/**
* Return the attributes for the tag associated with this iteartor
* @return the AttributeSet
*/
public AttributeSet getAttributes()
{
if (it.current() != null)
return it.current().getAttributes();
return null;
}
/**
* Get the end of the range for the current occurrence of the tag
* being defined and having the same attributes.
* @return the end of the range
*/
public int getEndOffset()
{
if (it.current() != null)
return it.current().getEndOffset();
return -1;
}
/**
* Get the start of the range for the current occurrence of the tag
* being defined and having the same attributes.
* @return the start of the range (-1 if it can't be found).
*/
public int getStartOffset()
{
if (it.current() != null)
return it.current().getStartOffset();
return -1;
}
/**
* Advance the iterator to the next LeafElement .
*/
public void next()
{
it.next();
while (it.current()!= null && !it.current().isLeaf())
it.next();
}
/**
* Indicates whether or not the iterator currently represents an occurrence
* of the tag.
* @return true if the iterator currently represents an occurrence of the
* tag.
*/
public boolean isValid()
{
return it.current() != null;
}
/**
* Type of tag for this iterator.
*/
public Tag getTag()
{
return tag;
}
}
public void processHTMLFrameHyperlinkEvent(HTMLFrameHyperlinkEvent event)
{
String target = event.getTarget();
Element el = event.getSourceElement();
URL url = event.getURL();
if (target.equals("_self"))
{
updateFrame(el, url);
}
else if (target.equals("_parent"))
{
updateFrameSet(el.getParentElement(), url);
}
else
{
Element targetFrame = findFrame(target);
if (targetFrame != null)
updateFrame(targetFrame, url);
}
}
/**
* Finds the named frame inside this document.
*
* @param target the name to look for
*
* @return the frame if there is a matching frame, null
* otherwise
*/
private Element findFrame(String target)
{
ElementIterator i = new ElementIterator(this);
Element next = null;
while ((next = i.next()) != null)
{
AttributeSet atts = next.getAttributes();
if (atts.getAttribute(StyleConstants.NameAttribute) == HTML.Tag.FRAME)
{
String name = (String) atts.getAttribute(HTML.Attribute.NAME);
if (name != null && name.equals(target))
break;
}
}
return next;
}
/**
* Updates the frame that is represented by the specified element to
* refer to the specified URL.
*
* @param el the element
* @param url the new url
*/
private void updateFrame(Element el, URL url)
{
try
{
writeLock();
DefaultDocumentEvent ev =
new DefaultDocumentEvent(el.getStartOffset(), 1,
DocumentEvent.EventType.CHANGE);
AttributeSet elAtts = el.getAttributes();
AttributeSet copy = elAtts.copyAttributes();
MutableAttributeSet matts = (MutableAttributeSet) elAtts;
ev.addEdit(new AttributeUndoableEdit(el, copy, false));
matts.removeAttribute(HTML.Attribute.SRC);
matts.addAttribute(HTML.Attribute.SRC, url.toString());
ev.end();
fireChangedUpdate(ev);
fireUndoableEditUpdate(new UndoableEditEvent(this, ev));
}
finally
{
writeUnlock();
}
}
/**
* Updates the frameset that is represented by the specified element
* to create a frame that refers to the specified URL.
*
* @param el the element
* @param url the url
*/
private void updateFrameSet(Element el, URL url)
{
int start = el.getStartOffset();
int end = el.getEndOffset();
StringBuilder html = new StringBuilder();
html.append("');
if (getParser() == null)
setParser(new HTMLEditorKit().getParser());
try
{
setOuterHTML(el, html.toString());
}
catch (BadLocationException ex)
{
ex.printStackTrace();
}
catch (IOException ex)
{
ex.printStackTrace();
}
}
/**
* Gets an iterator for the given HTML.Tag.
* @param t the requested HTML.Tag
* @return the Iterator
*/
public HTMLDocument.Iterator getIterator (HTML.Tag t)
{
return new HTMLDocument.LeafIterator(t, this);
}
/**
* An iterator over a particular type of tag.
*/
public abstract static class Iterator
{
/**
* Return the attribute set for this tag.
* @return the AttributeSet
(null if none found).
*/
public abstract AttributeSet getAttributes();
/**
* Get the end of the range for the current occurrence of the tag
* being defined and having the same attributes.
* @return the end of the range
*/
public abstract int getEndOffset();
/**
* Get the start of the range for the current occurrence of the tag
* being defined and having the same attributes.
* @return the start of the range (-1 if it can't be found).
*/
public abstract int getStartOffset();
/**
* Move the iterator forward.
*/
public abstract void next();
/**
* Indicates whether or not the iterator currently represents an occurrence
* of the tag.
* @return true if the iterator currently represents an occurrence of the
* tag.
*/
public abstract boolean isValid();
/**
* Type of tag this iterator represents.
* @return the tag.
*/
public abstract HTML.Tag getTag();
}
public class BlockElement extends AbstractDocument.BranchElement
{
public BlockElement (Element parent, AttributeSet a)
{
super(parent, a);
}
/**
* Gets the resolving parent. Since HTML attributes are not
* inherited at the model level, this returns null.
*/
public AttributeSet getResolveParent()
{
return null;
}
/**
* Gets the name of the element.
*
* @return the name of the element if it exists, null otherwise.
*/
public String getName()
{
Object tag = getAttribute(StyleConstants.NameAttribute);
String name = null;
if (tag != null)
name = tag.toString();
if (name == null)
name = super.getName();
return name;
}
}
/**
* RunElement represents a section of text that has a set of
* HTML character level attributes assigned to it.
*/
public class RunElement extends AbstractDocument.LeafElement
{
/**
* Constructs an element that has no children. It represents content
* within the document.
*
* @param parent - parent of this
* @param a - elements attributes
* @param start - the start offset >= 0
* @param end - the end offset
*/
public RunElement(Element parent, AttributeSet a, int start, int end)
{
super(parent, a, start, end);
}
/**
* Gets the name of the element.
*
* @return the name of the element if it exists, null otherwise.
*/
public String getName()
{
Object tag = getAttribute(StyleConstants.NameAttribute);
String name = null;
if (tag != null)
name = tag.toString();
if (name == null)
name = super.getName();
return name;
}
/**
* Gets the resolving parent. HTML attributes do not inherit at the
* model level, so this method returns null.
*
* @return null
*/
public AttributeSet getResolveParent()
{
return null;
}
}
/**
* A reader to load an HTMLDocument with HTML structure.
*
* @author Anthony Balkissoon abalkiss at redhat dot com
*/
public class HTMLReader extends HTMLEditorKit.ParserCallback
{
/**
* The maximum token threshold. We don't grow it larger than this.
*/
private static final int MAX_THRESHOLD = 10000;
/**
* The threshold growth factor.
*/
private static final int GROW_THRESHOLD = 5;
/**
* Holds the current character attribute set *
*/
protected MutableAttributeSet charAttr = new SimpleAttributeSet();
protected Vector parseBuffer = new Vector();
/**
* The parse stack. It holds the current element tree path.
*/
private Stack parseStack = new Stack();
/**
* A stack for character attribute sets *
*/
Stack charAttrStack = new Stack();
/** A mapping between HTML.Tag objects and the actions that handle them **/
HashMap tagToAction;
/** Tells us whether we've received the '