StateOfBiocatalogue.java

/**
 * test if the web services listed in http://www.biocatalogue.org/ are
 * valid for wsimport
 * Author : Pierre Lindenbaum PhD
 * http://plindenbaum.blogspot.com
 */
import java.io.File;
import java.io.IOException;
import java.io.InputStream;
import java.io.PrintWriter;
import java.util.Arrays;

import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.xpath.XPath;
import javax.xml.xpath.XPathConstants;
import javax.xml.xpath.XPathExpression;
import javax.xml.xpath.XPathFactory;
//see http://code.google.com/p/lindenb/source/browse/trunk/src/java/org/lindenb/xml/NamespaceContextImpl.java
import org.lindenb.xml.NamespaceContextImpl;
import org.w3c.dom.Attr;
import org.w3c.dom.Document;
import org.w3c.dom.NodeList;


public class StateOfBiocatalogue
	{
	private File generated;
	private DocumentBuilder builder;
	private XPathExpression servicesExpr;
	private XPathExpression titleExpr;
	private XPathExpression wsdlExpr;
	StateOfBiocatalogue() throws Exception
		{
		DocumentBuilderFactory factory=DocumentBuilderFactory.newInstance();
		factory.setCoalescing(true);
		factory.setExpandEntityReferences(true);
		factory.setValidating(false);
		factory.setIgnoringComments(true);
		factory.setNamespaceAware(true);
		factory.setIgnoringElementContentWhitespace(true);
		this.builder=factory.newDocumentBuilder();
		
		XPathFactory xpathFactory=XPathFactory.newInstance();
	    XPath xpath=xpathFactory.newXPath();
	    NamespaceContextImpl nsContext=new NamespaceContextImpl();
	    nsContext.setPrefixURI("rest", "http://www.biocatalogue.org/2009/xml/rest");
	    nsContext.setPrefixURI("xlink", "http://www.w3.org/1999/xlink");
	    nsContext.setPrefixURI("dc", "http://purl.org/dc/elements/1.1/");
	    xpath.setNamespaceContext(nsContext);
	    this.servicesExpr= xpath.compile("/rest:services/rest:results/rest:service/@xlink:href");
	    this.titleExpr= xpath.compile("/rest:service/dc:title");
	    this.wsdlExpr= xpath.compile("/rest:service/rest:variants/rest:soapService/rest:wsdlLocation");
		}
	private int cleanup(File generated)
		{
		int count=0;
		if(!generated.exists()) return 0;
		if(generated.isDirectory())
			{
			for(File f2: generated.listFiles())
				{
				count+=cleanup(f2);
				}
			generated.delete();
			}
		else if(generated.isFile())
			{
			if(generated.getName().endsWith(".class")) ++count;
			generated.delete();
			}
		return count;
		}
	
	private Document parseXML(String url) throws Exception
		{
		System.err.println(url);
		int n_try=0;
		Document dom= null;
		while(n_try<10)
			{
			try
				{
				dom=this.builder.parse(url);
				break;
				}
			catch(Exception err)
				{
				Thread.sleep(30000);//wait 30 secs
				System.err.println("Trying again.... "+url);
				n_try++;
				continue;
				}
			}
		if(dom==null) throw new IOException("Cannot read "+url);
		return dom;
		}
	
	private void lookup(PrintWriter out,String url) throws Exception
		{
		File generated=new File(System.getProperty("java.io.tmpdir","/tmp/"),"generated");
		String javaHome= System.getProperty("java.home");
		
		Document dom=null;
		try
			{
			dom=parseXML(url+".xml");
			}
		catch(Exception err)
			{
			out.print(url);
			out.print("\t");
			out.print("[error]");
			out.print("\tNO:CONNECTION_FAILED");
			out.println();
			return;
			}
		NodeList wsdls=(NodeList)this.wsdlExpr.evaluate(dom, XPathConstants.NODESET);
		if(wsdls.getLength()==0)
			{
			out.print(url);
			out.print("\t");
			out.print(this.titleExpr.evaluate(dom,XPathConstants.STRING));
			out.print("\tNO-WSDL");
			out.println();
			return;
			}
		for(int i=0;i< wsdls.getLength();++i)
			{
			out.print(url);
			out.print("\t");
			out.print(this.titleExpr.evaluate(dom,XPathConstants.STRING));
			out.print("\tYES");
			out.print("\t");
			String wsdlURI=wsdls.item(i).getTextContent();
			out.print(wsdlURI);
			
			generated.mkdir();
			String cmdarray[]={javaHome+"/bin/wsimport",
					//"-httpproxy:host:port",
					"-d",generated.toString(),wsdlURI
					};
			
			StringBuilder message=new StringBuilder();
			Process proc=Runtime.getRuntime().exec(cmdarray);
			System.err.println("run : "+Arrays.toString(cmdarray));
			InputStream in=proc.getInputStream();
			int c;
			while(in!=null && (c=in.read())!=-1)
				{
				message.append((char)c);
				}
			int rez=proc.waitFor();
			if(in!=null) in.close();
			int nClass=cleanup(generated);
			if(rez==0 && nClass==0) rez=-1; 
			out.print("\t"+(rez==0?"SUCCESS":"FAILURE"));
			if(rez!=0)
				{
				out.print("\t");
				for(String s:message.toString().replace("\r", "\n").replace('\t', ' ').split("[\n]"))
					{
					s=s.trim();
					if(!s.startsWith("[ERROR]")) continue;
					out.print(s);
					break;
					}
				}
			else
				{
				out.print("\t"+(nClass)+" classes");
				}
			out.println();
			}
		out.flush();
		}
	
	private void run(PrintWriter out) throws Exception
		{
		int service_page=0;
		while(true)
			{
			service_page++;
			Document dom=parseXML("http://www.biocatalogue.org/services.xml?page="+service_page);
			
			NodeList serviceList=(NodeList)this.servicesExpr.evaluate(dom, XPathConstants.NODESET);
			for(int i=0;i< serviceList.getLength();++i)
				{
				lookup(out,Attr.class.cast(serviceList.item(i)).getValue());
				}
			if(serviceList.getLength()==0) break;
			}
		System.err.println("\nDone\n");
		}
	
	public static void main(String[] args)
		{
		try {
			PrintWriter out=new PrintWriter(new File("biocatalog.xls"));
			new StateOfBiocatalogue().run(out);
			out.flush();
			out.close();
			} 
		catch (Exception e)
			{
			e.printStackTrace();
			}
		}
	}