| Methods Summary |
|---|
| public org.w3c.dom.DOMImplementation | getDOMImplementation()
return dom;
|
| public boolean | isIgnoringComments()Reflects whether this DocumentBuilder is configured to ignore comments.
return ignoreComments;
|
| public boolean | isIgnoringElementContentWhitespace()Reflects whether this DocumentBuilder is configured to ignore element
content whitespace.
return ignoreElementContentWhitespace;
|
| public boolean | isNamespaceAware()
return namespaceAware;
|
| public boolean | isValidating()
return false;
|
| public org.w3c.dom.Document | newDocument()
return dom.createDocument(null, null, null);
|
| public org.w3c.dom.Document | parse(org.xml.sax.InputSource source)
if (source == null) {
throw new IllegalArgumentException();
}
Document document = newDocument();
try {
XmlPullParser parser = new KXmlParser();
parser.setFeature(XmlPullParser.FEATURE_PROCESS_NAMESPACES,
namespaceAware);
if (source.getByteStream() != null) {
parser.setInput(source.getByteStream(), source.getEncoding());
} else if (source.getCharacterStream() != null) {
parser.setInput(source.getCharacterStream());
} else {
// TODO Accept other sources as well?
throw new SAXParseException(
"InputSource needs either stream or reader", null);
}
if(parser.nextToken() == XmlPullParser.END_DOCUMENT) {
throw new SAXParseException(
"Unexpected end of document", null);
}
parse(parser, document, document, XmlPullParser.END_DOCUMENT);
parser.require(XmlPullParser.END_DOCUMENT, null, null);
} catch (XmlPullParserException ex) {
if(ex.getDetail() instanceof IOException) {
throw (IOException)ex.getDetail();
}
if(ex.getDetail() instanceof RuntimeException) {
throw (RuntimeException)ex.getDetail();
}
LocatorImpl locator = new LocatorImpl();
locator.setPublicId(source.getPublicId());
locator.setSystemId(source.getSystemId());
locator.setLineNumber(ex.getLineNumber());
locator.setColumnNumber(ex.getColumnNumber());
SAXParseException newEx = new SAXParseException(ex.getMessage(),
locator);
if (errorHandler != null) {
errorHandler.error(newEx);
}
throw newEx;
}
return document;
|
| private void | parse(org.xmlpull.v1.XmlPullParser parser, org.w3c.dom.Document document, org.w3c.dom.Node node, int endToken)Implements the whole parsing of the XML document. The XML pull parser is
actually more of a tokenizer, and we are doing a classical recursive
descent parsing (the method invokes itself for XML elements). Our
approach to parsing does accept some illegal documents (more than one
root element, for example). The assumption is that the DOM implementation
throws the proper exceptions in these cases.
int token = parser.getEventType();
/*
* The main parsing loop. The precondition is that we are already on the
* token to be processed. This holds for each iteration of the loop, so
* the inner statements have to ensure that (in particular the recursive
* call).
*/
while (token != endToken && token != XmlPullParser.END_DOCUMENT) {
if (token == XmlPullParser.PROCESSING_INSTRUCTION) {
/*
* Found a processing instructions. We need to split the token
* text at the first whitespace character.
*/
String text = parser.getText();
int dot = text.indexOf(' ");
String target = (dot != -1 ? text.substring(0, dot) : text);
String data = (dot != -1 ? text.substring(dot + 1) : "");
node.appendChild(document.createProcessingInstruction(target,
data));
} else if (token == XmlPullParser.DOCDECL) {
/*
* Found a document type declaration. Unfortunately KXML doesn't
* have the necessary details. Do we parse it ourselves, or do
* we silently ignore it, since it isn't mandatory in DOM 2
* anyway?
*/
StringTokenizer tokenizer = new StringTokenizer(parser.getText());
if (tokenizer.hasMoreTokens()) {
String name = tokenizer.nextToken();
String pubid = null;
String sysid = null;
if (tokenizer.hasMoreTokens()) {
String text = tokenizer.nextToken();
if ("SYSTEM".equals(text)) {
if (tokenizer.hasMoreTokens()) {
sysid = tokenizer.nextToken();
}
} else if ("PUBLIC".equals(text)) {
if (tokenizer.hasMoreTokens()) {
pubid = tokenizer.nextToken();
}
if (tokenizer.hasMoreTokens()) {
sysid = tokenizer.nextToken();
}
}
}
if (pubid != null && pubid.length() >= 2 && pubid.startsWith("\"") && pubid.endsWith("\"")) {
pubid = pubid.substring(1, pubid.length() - 1);
}
if (sysid != null && sysid.length() >= 2 && sysid.startsWith("\"") && sysid.endsWith("\"")) {
sysid = sysid.substring(1, sysid.length() - 1);
}
document.appendChild(dom.createDocumentType(name, pubid, sysid));
}
} else if (token == XmlPullParser.COMMENT) {
/*
* Found a comment. We simply take the token text, but we only
* create a node if the client wants to see comments at all.
*/
if (!ignoreComments) {
node.appendChild(document.createComment(parser.getText()));
}
} else if (token == XmlPullParser.IGNORABLE_WHITESPACE) {
/*
* Found some ignorable whitespace. We simply take the token
* text, but we only create a node if the client wants to see
* whitespace at all.
*/
if (!ignoreElementContentWhitespace) {
node.appendChild(document.createTextNode(parser.getText()));
}
} else if (token == XmlPullParser.TEXT) {
/*
* Found a piece of text. That's the easiest case. We simply
* take it and create a corresponding node.
*/
node.appendChild(document.createTextNode(parser.getText()));
} else if (token == XmlPullParser.CDSECT) {
/*
* Found a CDATA section. That's also trivial. We simply
* take it and create a corresponding node.
*/
node.appendChild(document.createCDATASection(parser.getText()));
} else if (token == XmlPullParser.ENTITY_REF) {
/*
* Found an entity reference. If an entity resolver is
* installed, we replace it by text (if possible). Otherwise we
* add an entity reference node.
*/
String entity = parser.getName();
if (entityResolver != null) {
// TODO Implement this...
}
String replacement = resolveStandardEntity(entity);
if (replacement != null) {
node.appendChild(document.createTextNode(replacement));
} else {
node.appendChild(document.createEntityReference(entity));
}
} else if (token == XmlPullParser.START_TAG) {
/*
* Found an element start tag. We create an element node with
* the proper info and attributes. We then invoke parse()
* recursively to handle the next level of nesting. When we
* return from this call, we check that we are on the proper
* element end tag. The whole handling differs somewhat
* depending on whether the parser is namespace-aware or not.
*/
if (namespaceAware) {
// Collect info for element node
String namespace = parser.getNamespace();
String name = parser.getName();
String prefix = parser.getPrefix();
if ("".equals(namespace)) {
namespace = null;
}
// Create element node and wire it correctly
Element element = document.createElementNS(namespace, name);
element.setPrefix(prefix);
node.appendChild(element);
for (int i = 0; i < parser.getAttributeCount(); i++) {
// Collect info for a single attribute node
String attrNamespace = parser.getAttributeNamespace(i);
String attrPrefix = parser.getAttributePrefix(i);
String attrName = parser.getAttributeName(i);
String attrValue = parser.getAttributeValue(i);
if ("".equals(attrNamespace)) {
attrNamespace = null;
}
// Create attribute node and wire it correctly
Attr attr = document.createAttributeNS(attrNamespace, attrName);
attr.setPrefix(attrPrefix);
attr.setValue(attrValue);
element.setAttributeNodeNS(attr);
}
// Recursive descent
token = parser.nextToken();
parse(parser, document, element, XmlPullParser.END_TAG);
// Expect the element's end tag here
parser.require(XmlPullParser.END_TAG, namespace, name);
} else {
// Collect info for element node
String name = parser.getName();
// Create element node and wire it correctly
Element element = document.createElement(name);
node.appendChild(element);
for (int i = 0; i < parser.getAttributeCount(); i++) {
// Collect info for a single attribute node
String attrName = parser.getAttributeName(i);
String attrValue = parser.getAttributeValue(i);
// Create attribute node and wire it correctly
Attr attr = document.createAttribute(attrName);
attr.setValue(attrValue);
element.setAttributeNode(attr);
}
// Recursive descent
token = parser.nextToken();
parse(parser, document, element, XmlPullParser.END_TAG);
// Expect the element's end tag here
parser.require(XmlPullParser.END_TAG, "", name);
}
}
token = parser.nextToken();
}
|
| private java.lang.String | resolveStandardEntity(java.lang.String entity)Resolves one of the five standard XML entities.
if ("lt".equals(entity)) {
return "<";
} else if ("gt".equals(entity)) {
return ">";
} else if ("amp".equals(entity)) {
return "&";
} else if ("apos".equals(entity)) {
return "'";
} else if ("quot".equals(entity)) {
return "\"";
} else {
return null;
}
|
| public void | setEntityResolver(org.xml.sax.EntityResolver resolver)
entityResolver = resolver;
|
| public void | setErrorHandler(org.xml.sax.ErrorHandler handler)
errorHandler = handler;
|
| public void | setIgnoreComments(boolean value)Controls whether this DocumentBuilder ignores comments.
ignoreComments = value;
|
| public void | setIgnoreElementContentWhitespace(boolean value)Controls whether this DocumentBuilder ignores element content whitespace.
ignoreElementContentWhitespace = value;
|
| public void | setNamespaceAware(boolean value)Controls whether this DocumentBuilder is namespace-aware.
namespaceAware = value;
|
