Java/XML/XPath
Содержание
Create an XML document and search by XPath
<source lang="java">
import javax.xml.parsers.DocumentBuilderFactory; import javax.xml.xpath.XPath; import javax.xml.xpath.XPathConstants; import javax.xml.xpath.XPathFactory; import org.w3c.dom.Document; import org.w3c.dom.Element; public class MainClass {
public static void main(String[] args) throws Exception {
DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
Document retval = dbf.newDocumentBuilder().newDocument();
Element parent = retval.createElement("parent");
retval.appendChild(parent);
Element child1 = retval.createElement("child");
child1.setTextContent("child.text");
parent.appendChild(child1);
Element child2 = retval.createElement("child");
child2.setTextContent("child.text.2");
parent.appendChild(child2);
XPathFactory factory = XPathFactory.newInstance();
XPath xPath = factory.newXPath();
System.out.println(xPath.evaluate("//child/text()", retval, XPathConstants.NODE).getClass());
}
}
</source>
Deep print of node list
<source lang="java">
import java.io.OutputStream; import java.io.PrintStream; import javax.xml.transform.Transformer; import javax.xml.transform.dom.DOMSource; import javax.xml.transform.stream.StreamResult; import org.w3c.dom.Document; import org.w3c.dom.NamedNodeMap; import org.w3c.dom.Node; import org.w3c.dom.NodeList; import com.sun.org.apache.xpath.internal.XPathAPI; public class MainClass {
public static void print(Node node, OutputStream os) {
PrintStream ps = new PrintStream(os);
switch (node.getNodeType()) {
case Node.ELEMENT_NODE:
ps.print("<" + node.getNodeName());
NamedNodeMap map = node.getAttributes();
for (int i = 0; i < map.getLength(); i++) {
ps.print(" " + map.item(i).getNodeName() + "=\""
+ map.item(i).getNodeValue() + "\"");
}
ps.println(">");
return;
case Node.ATTRIBUTE_NODE:
ps.println(node.getNodeName() + "=\"" + node.getNodeValue() + "\"");
return;
case Node.TEXT_NODE:
ps.println(node.getNodeValue());
return;
case Node.CDATA_SECTION_NODE:
ps.println(node.getNodeValue());
return;
case Node.PROCESSING_INSTRUCTION_NODE:
ps.println(node.getNodeValue());
return;
case Node.DOCUMENT_NODE:
case Node.DOCUMENT_FRAGMENT_NODE:
ps.println(node.getNodeName() + "=" + node.getNodeValue());
return;
}
}
static void evalXPath(Document doc, Transformer serializer, String absolute,
String relative) throws Exception {
NodeList list = XPathAPI.selectNodeList(doc, absolute, doc);
Node node = null;
//
for (int i = 0; (node = list.item(i)) != null; i++) {
NodeList innerList = XPathAPI.selectNodeList(node, relative, doc);
Node innerNode = null;
for (int j = 0; (innerNode = innerList.item(j)) != null; j++) {
serializer.transform(new DOMSource(node), new StreamResult(System.out));
}
}
}
}
</source>
Get the String data associated with the XPath selection supplied
<source lang="java">
/*
Milyn - Copyright (C) 2006 This library is free software; you can redistribute it and/or modify it under the terms of the GNU Lesser General Public License (version 2.1) as published by the Free Software Foundation. This library 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 Lesser General Public License for more details: http://www.gnu.org/licenses/lgpl.txt */
import org.w3c.dom.Attr; import org.w3c.dom.DOMException; import org.w3c.dom.Document; import org.w3c.dom.Node; import org.w3c.dom.NodeList; import org.xml.sax.EntityResolver; import org.xml.sax.ErrorHandler; import org.xml.sax.InputSource; import org.xml.sax.SAXException; import org.xml.sax.SAXParseException;
import javax.xml.XMLConstants; import javax.xml.parsers.DocumentBuilder; import javax.xml.parsers.DocumentBuilderFactory; import javax.xml.parsers.FactoryConfigurationError; import javax.xml.parsers.ParserConfigurationException; import javax.xml.transform.OutputKeys; import javax.xml.transform.Transformer; import javax.xml.transform.TransformerFactory; import javax.xml.transform.dom.DOMSource; import javax.xml.transform.stream.StreamResult; import javax.xml.transform.stream.StreamSource; import javax.xml.validation.Schema; import javax.xml.validation.SchemaFactory; import javax.xml.xpath.XPath; import javax.xml.xpath.XPathConstants; import javax.xml.xpath.XPathExpressionException; import javax.xml.xpath.XPathFactory; import java.io.IOException; import java.io.InputStream; import java.io.InputStreamReader; import java.io.Reader; import java.io.StringReader; import java.io.StringWriter; import java.io.Writer; /**
* XMl utility methods. * * @author Tom Fennelly */
public class XmlUtil {
/**
* Document validation types.
*/
public static enum VALIDATION_TYPE {
/**
* No validation.
*/
NONE,
/**
* DTD based validation.
*/
DTD,
/**
* XSD based validation.
*/
XSD,
}
private static String ELEMENT_NAME_FUNC = "/name()";
private static XPathFactory xPathFactory = XPathFactory.newInstance();
/**
* Get the String data associated with the XPath selection supplied.
*
* @param node The node to be searched.
* @param xpath The XPath String to be used in the selection.
* @return The string data located at the specified location in the
* document, or an empty string for an empty resultset query.
*/
public static String getString(Node node, String xpath) {
NodeList nodeList = getNodeList(node, xpath);
if (nodeList == null || nodeList.getLength() == 0) {
return "";
}
if (xpath.endsWith(ELEMENT_NAME_FUNC)) {
if (nodeList.getLength() > 0) {
return nodeList.item(0).getNodeName();
} else {
return "";
}
} else {
return serialize(nodeList);
}
}
/**
* Serialise the supplied W3C DOM subtree.
* <p/>
* The output is unformatted.
*
* @param nodeList The DOM subtree as a NodeList.
* @return The subtree in serailised form.
* @throws DOMException Unable to serialise the DOM.
*/
public static String serialize(NodeList nodeList) throws DOMException {
return serialize(nodeList, false);
}
/**
* Serialise the supplied W3C DOM subtree.
*
* @param node The DOM node to be serialized.
* @param format Format the output.
* @return The subtree in serailised form.
* @throws DOMException Unable to serialise the DOM.
*/
public static String serialize(final Node node, boolean format) throws DOMException {
StringWriter writer = new StringWriter();
serialize(node, format, writer);
return writer.toString();
}
/**
* Serialise the supplied W3C DOM subtree.
*
* @param node The DOM node to be serialized.
* @param format Format the output.
* @param writer The target writer for serialization.
* @throws DOMException Unable to serialise the DOM.
*/
public static void serialize(final Node node, boolean format, Writer writer) throws DOMException {
if(node.getNodeType() == Node.DOCUMENT_NODE) {
serialize(node.getChildNodes(), format, writer);
} else {
serialize(new NodeList() {
public Node item(int index) {
return node;
}
public int getLength() {
return 1;
}
}, format, writer);
}
}
/**
* Serialise the supplied W3C DOM subtree.
*
* @param nodeList The DOM subtree as a NodeList.
* @param format Format the output.
* @return The subtree in serailised form.
* @throws DOMException Unable to serialise the DOM.
*/
public static String serialize(NodeList nodeList, boolean format) throws DOMException {
StringWriter writer = new StringWriter();
serialize(nodeList, format, writer);
return writer.toString();
}
/**
* Serialise the supplied W3C DOM subtree.
*
* @param nodeList The DOM subtree as a NodeList.
* @param format Format the output.
* @param writer The target writer for serialization.
* @throws DOMException Unable to serialise the DOM.
*/
public static void serialize(NodeList nodeList, boolean format, Writer writer) throws DOMException {
if (nodeList == null) {
throw new IllegalArgumentException(
"null "subtree" NodeIterator arg in method call.");
}
try {
TransformerFactory factory = TransformerFactory.newInstance();
Transformer transformer;
if(format) {
try {
factory.setAttribute("indent-number", new Integer(4));
} catch(Exception e) {
// Ignore... Xalan may throw on this!!
// We handle Xalan indentation below (yeuckkk) ...
}
}
transformer = factory.newTransformer();
transformer.setOutputProperty(OutputKeys.OMIT_XML_DECLARATION, "yes");
if(format) {
transformer.setOutputProperty(OutputKeys.INDENT, "yes");
transformer.setOutputProperty("{http://xml.apache.org/xalan}indent-amount", "4");
}
int listLength = nodeList.getLength();
// Iterate through the Node List.
for (int i = 0; i < listLength; i++) {
Node node = nodeList.item(i);
if (isTextNode(node)) {
writer.write(node.getNodeValue());
} else if (node.getNodeType() == Node.ATTRIBUTE_NODE) {
writer.write(((Attr) node).getValue());
} else if (node.getNodeType() == Node.ELEMENT_NODE) {
transformer.transform(new DOMSource(node), new StreamResult(writer));
}
}
} catch (Exception e) {
DOMException domExcep = new DOMException(
DOMException.INVALID_ACCESS_ERR,
"Unable to serailise DOM subtree.");
domExcep.initCause(e);
throw domExcep;
}
}
/**
* Is the supplied W3C DOM Node a text node.
*
* @param node The node to be tested.
* @return True if the node is a text node, otherwise false.
*/
public static boolean isTextNode(Node node) {
short nodeType;
if (node == null) {
return false;
}
nodeType = node.getNodeType();
return nodeType == Node.CDATA_SECTION_NODE
|| nodeType == Node.TEXT_NODE;
}
/**
* Get the W3C NodeList instance associated with the XPath selection
* supplied.
*
* @param node The document node to be searched.
* @param xpath The XPath String to be used in the selection.
* @return The W3C NodeList instance at the specified location in the
* document, or null.
*/
public static NodeList getNodeList(Node node, String xpath) {
if (node == null) {
throw new IllegalArgumentException(
"null "document" arg in method call.");
} else if (xpath == null) {
throw new IllegalArgumentException(
"null "xpath" arg in method call.");
}
try {
XPath xpathEvaluater = xPathFactory.newXPath();
if (xpath.endsWith(ELEMENT_NAME_FUNC)) {
return (NodeList) xpathEvaluater.evaluate(xpath.substring(0,
xpath.length() - ELEMENT_NAME_FUNC.length()), node,
XPathConstants.NODESET);
} else {
return (NodeList) xpathEvaluater.evaluate(xpath, node,
XPathConstants.NODESET);
}
} catch (XPathExpressionException e) {
throw new IllegalArgumentException("bad "xpath" expression ["
+ xpath + "].");
}
}
}
</source>
Parse with XPath
<source lang="java">
import javax.xml.xpath.XPath; import javax.xml.xpath.XPathConstants; import javax.xml.xpath.XPathFactory; import org.w3c.dom.NodeList; import org.xml.sax.InputSource; public class Main {
public static void main(String[] args) throws Exception {
XPath xpath = XPathFactory.newInstance().newXPath();
String xpathExpression = "/howto/topic/@name";
InputSource inputSource = new InputSource("howto.xml");
NodeList nodes = (NodeList) xpath
.evaluate(xpathExpression, inputSource, XPathConstants.NODESET);
int j = nodes.getLength();
for (int i = 0; i < j; i++) {
System.out.println(nodes.item(i).getTextContent());
}
}
}
</source>
Shallow print of node list
<source lang="java">
import java.io.OutputStream; import java.io.PrintStream; import javax.xml.transform.Transformer; import javax.xml.transform.dom.DOMSource; import javax.xml.transform.stream.StreamResult; import org.w3c.dom.Document; import org.w3c.dom.NamedNodeMap; import org.w3c.dom.Node; import org.w3c.dom.NodeList; import com.sun.org.apache.xpath.internal.XPathAPI; public class MainClass {
public static void print(Node node, OutputStream os) {
PrintStream ps = new PrintStream(os);
switch (node.getNodeType()) {
case Node.ELEMENT_NODE:
ps.print("<" + node.getNodeName());
NamedNodeMap map = node.getAttributes();
for (int i = 0; i < map.getLength(); i++) {
ps.print(" " + map.item(i).getNodeName() + "=\""
+ map.item(i).getNodeValue() + "\"");
}
ps.println(">");
return;
case Node.ATTRIBUTE_NODE:
ps.println(node.getNodeName() + "=\"" + node.getNodeValue() + "\"");
return;
case Node.TEXT_NODE:
ps.println(node.getNodeValue());
return;
case Node.CDATA_SECTION_NODE:
ps.println(node.getNodeValue());
return;
case Node.PROCESSING_INSTRUCTION_NODE:
ps.println(node.getNodeValue());
return;
case Node.DOCUMENT_NODE:
case Node.DOCUMENT_FRAGMENT_NODE:
ps.println(node.getNodeName() + "=" + node.getNodeValue());
return;
}
}
static void evalXPath(Document doc, Transformer serializer, String absolute,
String relative) throws Exception {
NodeList list = XPathAPI.selectNodeList(doc, absolute, doc);
Node node = null;
//
for (int i = 0; (node = list.item(i)) != null; i++) {
NodeList innerList = XPathAPI.selectNodeList(node, relative, doc);
Node innerNode = null;
for (int j = 0; (innerNode = innerList.item(j)) != null; j++) {
print(innerNode, System.out);
}
}
}
}
</source>
Use XPath to select node
<source lang="java">
import java.io.File; import org.jdom.Attribute; import org.jdom.Document; import org.jdom.Element; import org.jdom.input.SAXBuilder; import org.jdom.xpath.XPath; public class MainClass {
public static void main(String[] args) throws Exception {
SAXBuilder builder = new SAXBuilder();
Document doc = builder.build(new File("tds.xml"));
Attribute attr = (Attribute) XPath.selectSingleNode(doc, "/schedule/@name");
System.out.println(attr.getValue());
Element el = new Element("parent").addContent(new Element("child").setAttribute("name", "value"));
System.out.println(XPath.selectSingleNode(new Attribute("foo", "bar"), "position()"));
XPath path = XPath.newInstance("/schedule/@name");
System.out.println(path.valueOf(doc));
}
}
</source>
XML and XPath utilities
<source lang="java">
// Copyright (c) 2003-2009, Jodd Team (jodd.org). All Rights Reserved.
import org.w3c.dom.NamedNodeMap; import org.w3c.dom.Node; import org.w3c.dom.NodeList; import org.w3c.dom.Element; import java.util.ArrayList; import java.util.HashMap; import java.util.List; import java.util.Map; /**
* Some XML and XPath utilities. */
public class XmlUtil {
// ---------------------------------------------------------------- attributes
/**
* Returns a map of all node"s attributes. All non-attribute nodes are ignored.
*/
public static Map<String, String> getAllAttributes(Node node) {
HashMap<String, String> attrs = new HashMap<String, String>();
NamedNodeMap nmm = node.getAttributes();
for (int j = 0; j < nmm.getLength(); j++) {
Node attribute = nmm.item(j);
if (attribute.getNodeType() != Node.ATTRIBUTE_NODE) {
continue;
}
attrs.put(attribute.getNodeName(), attribute.getNodeValue());
}
return attrs;
}
/**
* Returns attribute value of a node or null if attribute name not found.
* Specified attribute is searched on every call.
* Consider {@link #getAllAttributes(org.w3c.dom.Node)} for better performances.
*/
public static String getAttributeValue(Node node, String attrName) {
NamedNodeMap nmm = node.getAttributes();
for (int j = 0; j < nmm.getLength(); j++) {
Node attribute = nmm.item(j);
if (attribute.getNodeType() != Node.ATTRIBUTE_NODE) {
continue;
}
String nodeName = attribute.getNodeName();
if (nodeName.equals(attrName)) {
return attribute.getNodeValue();
}
}
return null;
}
/**
* Get element"s attribute value or null if attribute not found or empty.
*/
public static String getAttributeValue(Element element, String name) {
String value = element.getAttribute(name);
if (value.length() == 0) {
value = null;
}
return value;
}
// ---------------------------------------------------------------- nodelist
/**
* Filters node list by keeping nodes of specified type.
*/
public static List filterNodeList(NodeList nodeList, short keepNodeType) {
return filterNodeList(nodeList, keepNodeType, null);
}
/**
* Filters node list by keeping nodes of specified type and node name.
*/
public static List<Node> filterNodeList(NodeList nodeList, short keepNodeType, String nodeName) {
List<Node> nodes = new ArrayList<Node>();
for (int k = 0; k < nodeList.getLength(); k++) {
Node node = nodeList.item(k);
if (node.getNodeType() != keepNodeType) {
continue;
}
if (nodeName != null && (node.getNodeName().equals(nodeName) == false)) {
continue;
}
nodes.add(node);
}
return nodes;
}
/**
* Filter node list for all Element nodes.
*/
public static List filterNodeListElements(NodeList nodeList) {
return filterNodeListElements(nodeList, null);
}
/**
* Filter node list for Element nodes of specified name.
*/
public static List<Node> filterNodeListElements(NodeList nodeList, String nodeName) {
List<Node> nodes = new ArrayList<Node>();
for (int k = 0; k < nodeList.getLength(); k++) {
Node node = nodeList.item(k);
if (node.getNodeType() != Node.ELEMENT_NODE) {
continue;
}
if (nodeName != null && (node.getNodeName().equals(nodeName) == false)) {
continue;
}
nodes.add(node);
}
return nodes;
}
/**
* Returns a list of all child Elements,
*/
public static List getChildElements(Node node) {
return getChildElements(node, null);
}
/**
* Returns a list of child Elements of specified name.
*/
public static List getChildElements(Node node, String nodeName) {
NodeList childs = node.getChildNodes();
return filterNodeListElements(childs, nodeName);
}
// ---------------------------------------------------------------- node
/** * Returns value of first available child text node ornullif not found. */ public static String getFirstChildTextNodeValue(Node node) { NodeList children = node.getChildNodes(); int len = children.getLength(); for (int i = 0; i < len; i++) { Node n = children.item(i); if (n.getNodeType() == Node.TEXT_NODE) { return n.getNodeValue(); } } return null; } /** * Returns value of single child text node ornull. */ public static String getChildTextNodeValue(Node node) { if (node.getChildNodes().getLength() != 1) { return null; } Node item0 = node.getChildNodes().item(0); if (item0.getNodeType() != Node.TEXT_NODE) { return null; } return item0.getNodeValue(); }
}
</source>
