XPath parser in Java

• 1.概览
• 2.解决要点
• 3.代码实现
• 4.测试代码实现
• 5.测试结果
• 6.总结

1.概览

本主题旨在不依赖第三方软件情况下如何使用Java实现XPath的解析。

2.解决要点

1)如何把XML文件/XML字符流转换为DOM模型下的Node/Element.
 
2)XML文件/XML字符流编码格式的指定。

3)提供XML的Namespace Resolver.

4)调用XPath的相关API并依赖用户指定的experssion进行解析，并返回结果。

3.代码实现

package com.chris.xpath;

import java.io.BufferedReader;
import java.io.IOException;
import java.io.PrintStream;
import java.io.StringReader;

import javax.xml.namespace.NamespaceContext;
import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.ParserConfigurationException;
import javax.xml.xpath.XPath;
import javax.xml.xpath.XPathConstants;
import javax.xml.xpath.XPathExpression;
import javax.xml.xpath.XPathExpressionException;
import javax.xml.xpath.XPathFactory;

import org.w3c.dom.Node;
import org.xml.sax.InputSource;
import org.xml.sax.SAXException;
import org.xml.sax.SAXParseException;
/**
 * <code>XPathUtil</code>.
 * @author chris.wang
 */
public class XPathUtil
{
	private PrintStream error = System.err;

	/**
	 * Populate XPath-expression.
	 * @param query
	 * @param xmlDocument
	 * @param defaultNamespaceContext
	 * @return value of element or attribute.
	 */
	public String evaluateXPath( String query, Node xmlDocument,
											NamespaceContext defaultNamespaceContext )
	{
		String result = null;

		XPathFactory factory = XPathFactory.newInstance();

		XPath xpath = factory.newXPath();

		xpath.setNamespaceContext(defaultNamespaceContext);

		XPathExpression expr = null;

		try
		{
			expr = xpath.compile(query);
		}
		catch ( XPathExpressionException xpee )
		{
			Throwable x = xpee;

			if ( null != xpee.getCause() )
			{
				x = xpee.getCause();

				if ( "javax.xml.transform.TransformerException".equals(x.getClass()
						.getName()) )
				{
					error
							.println("Error compiling xpath expression ["
									+ query
									+ "].  Could all the required namespaces be resolved from the previous response?");
				}
				else
				{
					error.println("Error compiling xpath expression [" + query
							+ "].  Is the expression well-formed in XML Spy?");
				}
			}

			x.printStackTrace(error);

			return null;
		}

		try
		{
			result = (String) expr.evaluate(xmlDocument, XPathConstants.STRING);
		}
		catch ( XPathExpressionException e )
		{
			e.printStackTrace(error);
		}

		return result;
	}

	/**
	 * Convert xmlString into Node.
	 * @param xmlString
	 * @param encodingHint encoding type.
	 * @return Node
	 */
	public Node loadXMLResource( String xmlString, String encodingHint )
	{
		Node document = null;

		if ( 0xFEFF == xmlString.charAt(0) )
		{
			xmlString = xmlString.substring(1);
		}

		InputSource source = new InputSource(new BufferedReader(new StringReader(
				xmlString)));

		if ( null != encodingHint )
		{
			source.setEncoding(encodingHint);
		}

		// parse the XML purely as well-formed XML and get a DOM tree
		// represenation.
		try
		{
			document = loadDocument(source);
		}
		catch ( SAXParseException spe )
		{
			// Error generated by the parser
			if ( null != spe.getSystemId() )
			{
				error.println("\n** XML Parsing error **, line "
						+ spe.getLineNumber() + " character " + spe.getColumnNumber()
						+ ", uri=" + spe.getSystemId());
				error.println("   " + spe.getMessage() + "\n"); // NOPMD
			}
			else
			{
				error.println("\n** XML Parsing error ** : " + spe.getMessage()
						+ "\n");
			}

			// Use the contained exception, if any
			Exception x = spe;

			if ( null != spe.getException() )
			{
				x = spe.getException();
			}

			x.printStackTrace(error);
		}
		catch ( SAXException se )
		{
			document = null;

			error
					.println("Error parsing the XML resource - is the XML valid and well-formed?");

			// Use the contained exception, if any
			Exception x = se;

			if ( null != se.getException() )
			{
				x = se.getException();
			}

			x.printStackTrace(error);
		}
		catch ( IOException ioe )
		{
			document = null;

			error
					.println("Error loading the XML resource - can the xmlString be read?");

			ioe.printStackTrace(error);
		}

		return document;
	}

	/**
	 * Load document from InputSource( i.e. XML file or other stream ).
	 * @param source
	 * @return Node of DOM.
	 * @throws SAXException
	 * @throws IOException
	 */
	public Node loadDocument( InputSource source ) throws SAXException,
			IOException
	{
		Node document = null;

		// Get a parser capable of parsing XML into a DOM tree
		DocumentBuilder parser = null;

		// Create the dom factory
		DocumentBuilderFactory domFactory = DocumentBuilderFactory.newInstance();

		domFactory.setNamespaceAware(true);
		domFactory.setValidating(false); // only for DocType (dtd) validation

		try
		{
			parser = domFactory.newDocumentBuilder();
		}
		catch ( ParserConfigurationException pce )
		{
			pce.printStackTrace(error);
		}

		// parse the XML purely as well-formed XML and get a DOM tree
		// represenation.
		parser.reset();

		document = parser.parse(source);

		return document;
	}

}

4.测试代码的实现

package com.chris.xpath;

import java.util.Iterator;
import java.util.Map;

import javax.xml.XMLConstants;
import javax.xml.namespace.NamespaceContext;

import org.w3c.dom.Node;

public class XPathUtilDriver
{

	private static NamespaceContext defaultNamespaceContext;
	static
	{
		defaultNamespaceContext = new NamespaceContext()
		{

			private Map<String, String> m_prefixMap = null; // NOPMD

			public String getNamespaceURI( String prefix )
			{
				if ( null == prefix )
				{
					throw new NullPointerException("Null prefix"); // NOPMD
				}
				else
				{
					if ( "xml".equals(prefix) )
					{
						return XMLConstants.XML_NS_URI;
					}

					if ( null != m_prefixMap )
					{
						for ( String key : m_prefixMap.keySet() )
						{
							if ( key.equals(prefix) )
							{
								return m_prefixMap.get(key);
							}
						}
					}
				}

				return XMLConstants.NULL_NS_URI;
			}

			// This method isn't necessary for XPath processing.
			public String getPrefix( String uri )
			{
				throw new UnsupportedOperationException();
			}

			// This method isn't necessary for XPath processing either.
			public Iterator getPrefixes( String uri )
			{
				throw new UnsupportedOperationException();
			}

		};
	}

	public static void main( String[] args )
	{
		String xmlString = "<?xml version=\"1.0\" encoding=\"utf-8\"?>"
				+ "<books><book><name>JUnit in Action</name>" + "</book>"
				+ "</books>";
		XPathUtil util = new XPathUtil();
		Node node = util.loadXMLResource(xmlString, "utf-8");
		String value = util.evaluateXPath("//books/book[1]/name/text()", node,
														defaultNamespaceContext);
		System.out.println("execute result" + value);
	}
}

5.测试结果

execute result:JUnit in Action

6.总结

1)如果要是namespace产生效果一定要加上domFactory.setNamespaceAware(true), 不然解析后的Node可能不能用.
2)XML可能涉及到不同的编码，所以编码问题也是一个注意点。
3)第三方开发软件如JDOM,DOM4j对XPath都有很好的支持，个人觉得使用也是很方便，如果你的项目中刚好用的这个组件，那一些解析的操作就可以省了。