org.enhydra.xml.io.HTMLFormatter Maven / Gradle / Ivy
The newest version!
/*
* Enhydra Java Application Server Project
*
* The contents of this file are subject to the Enhydra Public License
* Version 1.1 (the "License"); you may not use this file except in
* compliance with the License. You may obtain a copy of the License on
* the Enhydra web site ( http://www.enhydra.org/ ).
*
* Software distributed under the License is distributed on an "AS IS"
* basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See
* the License for the specific terms governing rights and limitations
* under the License.
*
* The Initial Developer of the Enhydra Application Server is Lutris
* Technologies, Inc. The Enhydra Application Server and portions created
* by Lutris Technologies, Inc. are Copyright Lutris Technologies, Inc.
* All Rights Reserved.
*
* Contributor(s):
*
* $Id: HTMLFormatter.java,v 1.7 2005/01/26 08:29:24 jkjome Exp $
*/
package org.enhydra.xml.io;
import java.io.IOException;
import org.enhydra.xml.dom.DOMAccess;
import org.w3c.dom.Attr;
import org.w3c.dom.CDATASection;
import org.w3c.dom.Document;
import org.w3c.dom.DocumentFragment;
import org.w3c.dom.DocumentType;
import org.w3c.dom.Element;
import org.w3c.dom.Node;
import org.w3c.dom.ProcessingInstruction;
import org.w3c.dom.Text;
/*
* FIXME:
* - Need to check for optional attributes.
* - Give control over newline in OutputOptions or maybe use a PrintWriter???
* - Need option to include HTML 4.0 entity references.
* - script and style child special handling.
* - Need to output HTML header.
*/
/**
* Formatter for outputting a HTML DOM as a HTML text document.
*/
final class HTMLFormatter extends BaseDOMFormatter implements Formatter {
/**
* Default XML encoding.
*/
private static final String DEFAULT_XML_ENCODING = "ISO-8859-1";
/**
* Table use to optimized checking for characters that should be
* represented as entity references.
*/
private static final boolean[] fEntityQuickCheck
= new boolean[MAX_ENTITY_QUICK_CHECK_CHAR+1];
/**
* Should SPAN ID attributes be dropped?
*/
private final boolean fDropSpanIds;
/**
* Flag that indicates the ID attribute should be dropped for the current
* element.
*/
private boolean fDropThisId;
/**
* Flag that indicates wether to use all named entites for all HTML 4.0 character
* entities or not.
*/
private boolean fUseHTML4Entities;
/**
* Nesting count for elements that don't have their content formatted.
* This is done for script and style elements. The contents of these
* elements are outputted as-is. Its not legal for them to nest, but a
* count is used to keep code from being confused by a broken DOM.
*/
private int fNoFormatNestCount;
/**
* Indicates then a text has just been handled
*/
private boolean fHandleText = false;
/**
* Indicates the next Sibling is a Text node
*/
private boolean fNextSiblingText = false;
/**
* Static constructor.
*/
static {
for (char ch = 0; ch <= MAX_ENTITY_QUICK_CHECK_CHAR; ch++) {
fEntityQuickCheck[ch] = (HTMLEntities.charToEntity(ch) != null);
}
}
/**
* Constructor.
*/
public HTMLFormatter(Node node,
OutputOptions outputOptions,
boolean forPreFormatting) {
super(node, outputOptions, forPreFormatting, DEFAULT_XML_ENCODING, fEntityQuickCheck);
fDropSpanIds = fOptions.getDropHtmlSpanIds();
fUseHTML4Entities = fOptions.getUseHTML4Entities();
}
/**
* Get the default OutputOptions for a document formatter with this
* formatter. The encoding will not be set, which signals to use the
* default encoding.
*/
static OutputOptions getDefaultOutputOptions() {
return new OutputOptions(); // Nothing special
}
/**
* @see BaseDOMFormatter#getCharacterEntity
*/
protected final String getCharacterEntity(char textChar) {
if (fUseHTML4Entities) {
return HTMLEntities.charToEntity4(textChar);
} else {
return HTMLEntities.charToEntity(textChar);
}
}
/**
* Determine if an attribute's value should be printer. Those that don't
* normally have values only get them if one was explictly supplied.
*/
private boolean printableAttrValue(Attr attr) {
return (!(HTMLElements.isBooleanAttr(attr.getName())));
}
/**
* Output the DOCTYPE declaration, if the information is available.
*/
private void outputDocType(Document document) throws IOException {
//FIXME: Don't currently have a way of getting doctype from the parser
//to here, the only way is via the outputOptions override.
if ((fPublicId != null) || (fSystemId != null)) {
fOut.write("');
writeln();
}
}
/**
* Handler called for Document nodes.
* @see org.enhydra.xml.dom.DOMTraversal.Handler#handleDocument
*/
public void handleDocument(Document document) throws IOException {
if (!fOptions.getOmitDocType()) {
outputDocType(document);
}
fTraverser.processChildren(document);
}
/**
* Handler called for Document nodes; should never be called.
* @see org.enhydra.xml.dom.DOMTraversal.Handler#handleDocumentType
*/
public void handleDocumentType(DocumentType documentType) throws IOException {
throw new XMLIOError("Unexpected call to handleDocumentType");
}
/**
* Handler called for DocumentFragment nodes; just process children.
* @see org.enhydra.xml.dom.DOMTraversal.Handler#handleDocumentFragment
*/
public void handleDocumentFragment(DocumentFragment documentFragment) {
fTraverser.processChildren(documentFragment);
}
/**
* Handler called for Attr nodes.
* @see org.enhydra.xml.dom.DOMTraversal.Handler#handleAttr
*/
public void handleAttr(Attr attr) throws IOException {
String name = attr.getName();
if (!(fDropThisId && name.equals("id"))) {
fOut.write(' ');
fOut.write(name);
if (printableAttrValue(attr)) {
writeAttributeValue(attr);
}
}
}
/**
* Write an element open tag. The hasChildren option is ignored.
*/
protected final void writeOpenTag(Element element,
String tagName,
boolean hasChildren) throws IOException {
String formattedTag = null;
if (fPrettyPrinting) {
if (fNextSiblingText) {
fOut.write('\n');
}
fNextSiblingText = (element.getNextSibling() instanceof Text);
} // end of if ()
if (fUsePreFormattedElements && (element instanceof PreFormattedText)) {
formattedTag = ((PreFormattedText)element).getPreFormattedText();
}
if (formattedTag != null) {
fOut.write(formattedTag);
fPreFormattedElementCount++;
} else {
if (fPrettyPrinting && !(element.getPreviousSibling() instanceof Text)) {
printIndent();
} // end of if ()
fDropThisId = fDropSpanIds && tagName.equals("SPAN");
fOut.write('<');
fOut.write(tagName);
fTraverser.processAttributes(element);
fOut.write('>');
fDynamicFormattedElementCount++;
if (fPrettyPrinting && !(element.getFirstChild() instanceof Text)) {
fOut.write('\n');
} // end of if ()
}
}
/**
* Write an element close tag.
*/
private void writeCloseTag(String tagName) throws IOException {
// Output end tag when legal.
if (fHandleText) {
fHandleText = false;
} else {
printIndent();
} // end of else
if (HTMLElements.hasCloseTag(tagName)) {
fOut.write("');
}
if (fPrettyPrinting && !fNextSiblingText) {
fOut.write('\n');
} // end of if ()
}
/**
* Handler called for Element nodes.
*
* This optionally corrects problem cases for browsers:
*
* - ID attributes are dropped from SPAN tags. This cause Internet
* Explorer 4.0 to get confused on keep-alive connections.
*
* @see org.enhydra.xml.dom.DOMTraversal.Handler#handleElement
*/
public void handleElement(Element element) throws IOException {
String tagName = element.getTagName();
// Start Barracuda Kludge ======
// check the element to see if it contains a
// attribute "visdom".
// (org.enhydra.barracuda.core.comp.BComponent.VISIBILITY_MARKER)
// This controls DOM visibility. If this value exists and does not
// match to true, don't print this particular node.
// Note: This should be made generic, but for now...
Attr attr = DOMAccess.accessAttribute(fDocument, element, null, "visdom");
if (attr != null && !(Boolean.valueOf(attr.getValue()).booleanValue())) return;
// End Barracuda Kludge ======
// HTML version doesn't care if it has childrne.
writeOpenTag(element, tagName, false);
// Output childern and close
boolean isScriptStyle = HTMLElements.isScriptStyle(element);
if (isScriptStyle) {
fNoFormatNestCount++;
}
fTraverser.processChildren(element);
if (isScriptStyle) {
fNoFormatNestCount--;
}
writeCloseTag(tagName);
}
/**
* Handler called for ProcessingInstruction nodes.
* @see org.enhydra.xml.dom.DOMTraversal.Handler#handleProcessingInstruction
*/
public void handleProcessingInstruction(ProcessingInstruction pi) throws IOException {
throw new XMLIOError("Unexpected call to handleProcessingInstruction");
}
/**
* Handler called for CDATASection nodes.
* Non-standard extension: outputs data as-is.
* @see org.enhydra.xml.dom.DOMTraversal.Handler#handleCDATASection
*/
public void handleCDATASection(CDATASection cdata) throws IOException {
fOut.write(cdata.getData());
}
/**
* Handler called for Text nodes.
* @see org.enhydra.xml.dom.DOMTraversal.Handler#handleText
*/
public final void handleText(Text text) throws IOException {
fHandleText = true;
if (fNoFormatNestCount > 0) {
fOut.write(text.getData());
} else {
super.handleText(text);
}
}
}
© 2015 - 2025 Weber Informatics LLC | Privacy Policy