multitextextractor.java

JAVA与XML处理一个重要方法是SAX,该包提供了11个常用程序,下载后可以根据具体情况对改进.这11个程序都已调试过.包括对XML的各种处理.建议先下载这个.

import org.xml.sax.*;
import java.util.List;

public class MultiTextExtractor implements ContentHandler
{
	private List documents;
	private StringBuffer currentDocument;
	
	public MultiTextExtractor(List documents)
	{
		if(documents==null)
		{
			throw new NullPointerException(
				"Documents list must be non-null");
		}
		this.documents=documents;
	}
	public void startDocument()
	{
		currentDocument=new StringBuffer();
	}
	public void endDocument()
	{
		String text=currentDocument.toString();
	}
	public void characters(char[] text, int start, int length)
	{
		currentDocument.append(text, start, length);
	}	
	public void setDocumentLocator(Locator locator){}
	public void startPrefixMapping(String prefix, String uri) {}
	public void endPrefixMapping(String prefix) {}
	public void startElement(String namespaceURI, String localName,
	   String qualifiedName, Attributes atts) {}
	public void endElement(String namespaceURI, String localName, 
	   String qualifiedName)  {}
	public void ignorableWhitespace(char[] text, int start, 
	   int length) throws SAXException {}
	public void processingInstruction(String target, String data) {}
	public void skippedEntity(String name) {}
}