Menu
▾
▴
[Archive-access-cvs] SF.net SVN: archive-access:[2960] trunk/archive-access/projects/nutchwax/ archive
|
From: <bi...@us...> - 2010-02-22 05:17:29
|
Revision: 2960
http://archive-access.svn.sourceforge.net/archive-access/?rev=2960&view=rev
Author: binzino
Date: 2010-02-22 05:17:20 +0000 (Mon, 22 Feb 2010)
Log Message:
-----------
Initial revision of OpenSearch master/slave system. Work-in-progress.
Added Paths:
-----------
trunk/archive-access/projects/nutchwax/archive/lib/jdom.LICENSE
trunk/archive-access/projects/nutchwax/archive/lib/jdom.jar
trunk/archive-access/projects/nutchwax/archive/src/java/org/archive/nutchwax/OpenSearchMaster.java
trunk/archive-access/projects/nutchwax/archive/src/java/org/archive/nutchwax/OpenSearchMasterServlet.java
trunk/archive-access/projects/nutchwax/archive/src/java/org/archive/nutchwax/OpenSearchSlave.java
Added: trunk/archive-access/projects/nutchwax/archive/lib/jdom.LICENSE
===================================================================
--- trunk/archive-access/projects/nutchwax/archive/lib/jdom.LICENSE (rev 0)
+++ trunk/archive-access/projects/nutchwax/archive/lib/jdom.LICENSE 2010-02-22 05:17:20 UTC (rev 2960)
@@ -0,0 +1,56 @@
+/*--
+
+ $Id: LICENSE.txt,v 1.11 2004/02/06 09:32:57 jhunter Exp $
+
+ Copyright (C) 2000-2004 Jason Hunter & Brett McLaughlin.
+ All rights reserved.
+
+ Redistribution and use in source and binary forms, with or without
+ modification, are permitted provided that the following conditions
+ are met:
+
+ 1. Redistributions of source code must retain the above copyright
+ notice, this list of conditions, and the following disclaimer.
+
+ 2. Redistributions in binary form must reproduce the above copyright
+ notice, this list of conditions, and the disclaimer that follows
+ these conditions in the documentation and/or other materials
+ provided with the distribution.
+
+ 3. The name "JDOM" must not be used to endorse or promote products
+ derived from this software without prior written permission. For
+ written permission, please contact <request_AT_jdom_DOT_org>.
+
+ 4. Products derived from this software may not be called "JDOM", nor
+ may "JDOM" appear in their name, without prior written permission
+ from the JDOM Project Management <request_AT_jdom_DOT_org>.
+
+ In addition, we request (but do not require) that you include in the
+ end-user documentation provided with the redistribution and/or in the
+ software itself an acknowledgement equivalent to the following:
+ "This product includes software developed by the
+ JDOM Project (http://www.jdom.org/)."
+ Alternatively, the acknowledgment may be graphical using the logos
+ available at http://www.jdom.org/images/logos.
+
+ THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
+ WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
+ OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ DISCLAIMED. IN NO EVENT SHALL THE JDOM AUTHORS OR THE PROJECT
+ CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
+ USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+ OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
+ OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ SUCH DAMAGE.
+
+ This software consists of voluntary contributions made by many
+ individuals on behalf of the JDOM Project and was originally
+ created by Jason Hunter <jhunter_AT_jdom_DOT_org> and
+ Brett McLaughlin <brett_AT_jdom_DOT_org>. For more information
+ on the JDOM Project, please see <http://www.jdom.org/>.
+
+ */
+
Added: trunk/archive-access/projects/nutchwax/archive/lib/jdom.jar
===================================================================
(Binary files differ)
Property changes on: trunk/archive-access/projects/nutchwax/archive/lib/jdom.jar
___________________________________________________________________
Added: svn:mime-type
+ application/octet-stream
Added: trunk/archive-access/projects/nutchwax/archive/src/java/org/archive/nutchwax/OpenSearchMaster.java
===================================================================
--- trunk/archive-access/projects/nutchwax/archive/src/java/org/archive/nutchwax/OpenSearchMaster.java (rev 0)
+++ trunk/archive-access/projects/nutchwax/archive/src/java/org/archive/nutchwax/OpenSearchMaster.java 2010-02-22 05:17:20 UTC (rev 2960)
@@ -0,0 +1,364 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.archive.nutchwax;
+
+import java.io.IOException;
+import java.io.BufferedReader;
+import java.io.InputStreamReader;
+import java.io.FileInputStream;
+import java.util.Comparator;
+import java.util.Collections;
+import java.util.List;
+import java.util.ArrayList;
+import java.util.LinkedList;
+
+import org.jdom.Document;
+import org.jdom.Element;
+import org.jdom.Namespace;
+import org.jdom.output.XMLOutputter;
+
+
+/**
+ *
+ */
+public class OpenSearchMaster
+{
+ List<OpenSearchSlave> slaves = new ArrayList<OpenSearchSlave>( );
+ long timeout = 30 * 1000;
+
+ public OpenSearchMaster( String slavesFile, long timeout )
+ throws IOException
+ {
+ this( slavesFile );
+ this.timeout = timeout;
+ }
+
+ public OpenSearchMaster( String slavesFile )
+ throws IOException
+ {
+ BufferedReader r = null;
+ try
+ {
+ r = new BufferedReader( new InputStreamReader( new FileInputStream( slavesFile ), "utf-8" ) );
+
+ String line;
+ while ( (line = r.readLine()) != null )
+ {
+ line = line.trim();
+ if ( line.length() == 0 || line.charAt( 0 ) == '#' )
+ {
+ // Ignore it.
+ continue ;
+ }
+
+ OpenSearchSlave slave = new OpenSearchSlave( line );
+
+ this.slaves.add( slave );
+ }
+ }
+ finally
+ {
+ try { if ( r != null ) r.close(); } catch ( IOException ioe ) { }
+ }
+
+ }
+
+ public Document query( String query, int startIndex, int numResults, int hitsPerSite )
+ {
+ long startTime = System.currentTimeMillis( );
+
+ List<SlaveQueryThread> slaveThreads = new ArrayList<SlaveQueryThread>( this.slaves.size() );
+
+ for ( OpenSearchSlave slave : this.slaves )
+ {
+ SlaveQueryThread sqt = new SlaveQueryThread( slave, query, 0, (startIndex+numResults), hitsPerSite );
+
+ sqt.start( );
+
+ slaveThreads.add( sqt );
+ }
+
+ waitForThreads( slaveThreads, this.timeout, startTime );
+
+ LinkedList<Element> items = new LinkedList<Element>( );
+ long totalResults = 0;
+
+ for ( SlaveQueryThread sqt : slaveThreads )
+ {
+ if ( sqt.throwable != null )
+ {
+ // TODO: Handle problems with slaves
+ continue ;
+ }
+
+ // Dump all the results ("item" elements) into a single list.
+ Element channel = sqt.response.getRootElement( ).getChild( "channel" );
+ items.addAll( (List<Element>) channel.getChildren( "item" ) );
+ channel.removeChildren( "item" );
+
+ try
+ {
+ totalResults += Integer.parseInt( channel.getChild( "totalResults", Namespace.getNamespace( "http://a9.com/-/spec/opensearchrss/1.0/" ) ).getTextTrim( ) );
+ }
+ catch ( Exception e )
+ {
+ // TODO: Log error getting total.
+ }
+
+ }
+
+ if ( items.size( ) > 0 && hitsPerSite > 0 )
+ {
+ Collections.sort( items, new ElementSiteThenScoreComparator( ) );
+
+ LinkedList<Element> collapsed = new LinkedList<Element>( );
+
+ collapsed.add( items.removeFirst( ) );
+
+ int count = 1;
+ for ( Element item : items )
+ {
+ String lastSite = collapsed.getLast( ).getChild( "site", Namespace.getNamespace( "http://www.nutch.org/opensearchrss/1.0/" ) ).getTextTrim( );
+
+ if ( lastSite.length( ) == 0 ||
+ !lastSite.equals( item.getChild( "site", Namespace.getNamespace( "http://www.nutch.org/opensearchrss/1.0/" ) ).getTextTrim( ) ) )
+ {
+ collapsed.add( item );
+ count = 1;
+ }
+ else if ( count < hitsPerSite )
+ {
+ collapsed.add( item );
+ count++;
+ }
+ else
+ {
+ // TODO: Log collapse of item.
+ }
+ }
+
+ // Replace the list of items with the collapsed list.
+ items = collapsed;
+ }
+
+ Collections.sort( items, new ElementScoreComparator( ) );
+
+ // Build the final results OpenSearch XML document.
+ Element channel = new Element( "channel" );
+ channel.addContent( new Element( "title" ) );
+ channel.addContent( new Element( "description" ) );
+ channel.addContent( new Element( "link" ) );
+
+ Element eTotalResults = new Element( "totalResults", Namespace.getNamespace( "http://a9.com/-/spec/opensearchrss/1.0/" ) );
+ Element eStartIndex = new Element( "startIndex", Namespace.getNamespace( "http://a9.com/-/spec/opensearchrss/1.0/" ) );
+ Element eItemsPerPage = new Element( "itemsPerPage", Namespace.getNamespace( "http://a9.com/-/spec/opensearchrss/1.0/" ) );
+
+ eTotalResults.setText( Long.toString( totalResults ) );
+ eStartIndex. setText( Long.toString( startIndex ) );
+ eItemsPerPage.setText( Long.toString( numResults ) );
+
+ channel.addContent( eTotalResults );
+ channel.addContent( eStartIndex );
+ channel.addContent( eItemsPerPage );
+
+ // Get a sub-list of only the items we want: [startIndex,(startIndex+numResults)]
+ List<Element> subList = items.subList( Math.min( startIndex, items.size( ) ),
+ Math.min( (startIndex+numResults), items.size( ) ) );
+ channel.addContent( subList );
+
+ Element rss = new Element( "rss" );
+ rss.addContent( channel );
+
+ return new Document( rss );
+ }
+
+
+ /**
+ * Convenience method to wait for a collection of threads to complete,
+ * or until a timeout after a startTime expires.
+ */
+ private void waitForThreads( List<SlaveQueryThread> threads, long timeout, long startTime )
+ {
+ for ( Thread t : threads )
+ {
+ long timeRemaining = timeout - (System.currentTimeMillis( ) - startTime);
+
+ // If we are out of time, don't wait for any more threads.
+ if ( timeRemaining <= 0 )
+ {
+ break;
+ }
+
+ // Otherwise, wait for the next unfinished thread to finish.
+ try
+ {
+ t.join( timeRemaining );
+ }
+ catch ( InterruptedException ie )
+ {
+ break;
+ }
+ }
+ }
+
+
+ public static void main( String args[] )
+ throws Exception
+ {
+ String usage = "OpenSearchMaster [OPTIONS] SLAVES.txt query"
+ + "\n\t-h <n> Hits per site"
+ + "\n\t-n <n> Number of results"
+ + "\n\t-s <n> Start index"
+ + "\n";
+
+ if ( args.length < 2 )
+ {
+ System.err.println( usage );
+ System.exit( 1 );
+ }
+
+ String slavesFile = args[args.length - 2];
+ String query = args[args.length - 1];
+
+ int startIndex = 0;
+ int hitsPerSite = 0;
+ int numHits = 10;
+ for ( int i = 0 ; i < args.length - 2 ; i++ )
+ {
+ try
+ {
+ if ( "-h".equals( args[i] ) )
+ {
+ i++;
+ hitsPerSite = Integer.parseInt( args[i] );
+ }
+ if ( "-n".equals( args[i] ) )
+ {
+ i++;
+ numHits = Integer.parseInt( args[i] );
+ }
+ if ( "-s".equals( args[i] ) )
+ {
+ i++;
+ startIndex = Integer.parseInt( args[i] );
+ }
+ }
+ catch ( NumberFormatException nfe )
+ {
+ System.err.println( "Error: not a numeric value: " + args[i] );
+ System.err.println( usage );
+ System.exit( 1 );
+ }
+ }
+
+ OpenSearchMaster master = new OpenSearchMaster( slavesFile );
+
+ Document doc = master.query( query, startIndex, numHits, hitsPerSite );
+
+ (new XMLOutputter()).output( doc, System.out );
+ }
+
+}
+
+
+class SlaveQueryThread extends Thread
+{
+ OpenSearchSlave slave;
+
+ String query;
+ int startIndex;
+ int numResults;
+ int hitsPerSite;
+
+ Document response;
+ Throwable throwable;
+
+
+ SlaveQueryThread( OpenSearchSlave slave, String query, int startIndex, int numResults, int hitsPerSite )
+ {
+ this.slave = slave;
+ this.query = query;
+ this.startIndex = startIndex;
+ this.numResults = numResults;
+ this.hitsPerSite = hitsPerSite;
+ }
+
+ public void run( )
+ {
+ try
+ {
+ this.response = this.slave.query( this.query, this.startIndex, this.numResults, this.hitsPerSite );
+ }
+ catch ( Throwable t )
+ {
+ this.throwable = t;
+ }
+ }
+}
+
+
+class ElementScoreComparator implements Comparator<Element>
+{
+ public int compare( Element e1, Element e2 )
+ {
+ if ( e1 == e2 ) return 0;
+ if ( e1 == null ) return 1;
+ if ( e2 == null ) return -1;
+
+ Element score1 = e1.getChild( "score" );
+ Element score2 = e2.getChild( "score" );
+
+ if ( score1 == score2 ) return 0;
+ if ( score1 == null ) return 1;
+ if ( score2 == null ) return -1;
+
+ String text1 = score1.getText().trim();
+ String text2 = score2.getText().trim();
+
+ float value1 = 0.0f;
+ float value2 = 0.0f;
+
+ try { value1 = Float.parseFloat( text1 ); } catch ( NumberFormatException nfe ) { }
+ try { value2 = Float.parseFloat( text2 ); } catch ( NumberFormatException nfe ) { }
+
+ if ( value1 == value2 ) return 0;
+
+ return value1 > value2 ? -1 : 1;
+ }
+}
+
+class ElementSiteThenScoreComparator extends ElementScoreComparator
+{
+ public int compare( Element e1, Element e2 )
+ {
+ if ( e1 == e2 ) return 0;
+ if ( e1 == null ) return 1;
+ if ( e2 == null ) return -1;
+
+ String site1 = e1.getChild( "site", Namespace.getNamespace( "http://www.nutch.org/opensearchrss/1.0/" ) ).getTextTrim();
+ String site2 = e2.getChild( "site", Namespace.getNamespace( "http://www.nutch.org/opensearchrss/1.0/" ) ).getTextTrim();
+
+ if ( site1.equals( site2 ) )
+ {
+ // Sites are equal, then compare scores.
+ return super.compare( e1, e2 );
+ }
+
+ return site1.compareTo( site2 );
+ }
+}
\ No newline at end of file
Added: trunk/archive-access/projects/nutchwax/archive/src/java/org/archive/nutchwax/OpenSearchMasterServlet.java
===================================================================
--- trunk/archive-access/projects/nutchwax/archive/src/java/org/archive/nutchwax/OpenSearchMasterServlet.java (rev 0)
+++ trunk/archive-access/projects/nutchwax/archive/src/java/org/archive/nutchwax/OpenSearchMasterServlet.java 2010-02-22 05:17:20 UTC (rev 2960)
@@ -0,0 +1,52 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.archive.nutchwax;
+
+import java.io.IOException;
+import java.io.BufferedReader;
+import java.io.InputStreamReader;
+import java.io.FileInputStream;
+import java.util.List;
+import java.util.ArrayList;
+import javax.servlet.ServletException;
+import javax.servlet.ServletConfig;
+import javax.servlet.http.HttpServlet;
+import javax.servlet.http.HttpServletRequest;
+import javax.servlet.http.HttpServletResponse;
+
+
+/**
+ *
+ */
+public class OpenSearchMasterServlet extends HttpServlet
+{
+
+ public void init( ServletConfig config )
+ throws ServletException
+ {
+
+
+ }
+
+ public void doGet( HttpServletRequest request, HttpServletResponse response )
+ throws ServletException, IOException
+ {
+
+ }
+
+}
Added: trunk/archive-access/projects/nutchwax/archive/src/java/org/archive/nutchwax/OpenSearchSlave.java
===================================================================
--- trunk/archive-access/projects/nutchwax/archive/src/java/org/archive/nutchwax/OpenSearchSlave.java (rev 0)
+++ trunk/archive-access/projects/nutchwax/archive/src/java/org/archive/nutchwax/OpenSearchSlave.java 2010-02-22 05:17:20 UTC (rev 2960)
@@ -0,0 +1,209 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.archive.nutchwax;
+
+import java.io.IOException;
+import java.io.InputStream;
+import java.io.UnsupportedEncodingException;
+import java.net.HttpURLConnection;
+import java.net.MalformedURLException;
+import java.net.URL;
+import java.net.URLConnection;
+import java.net.URLEncoder;
+import java.util.List;
+
+import org.jdom.Document;
+import org.jdom.Element;
+import org.jdom.Namespace;
+import org.jdom.input.SAXBuilder;
+import org.jdom.output.XMLOutputter;
+
+/**
+ *
+ */
+public class OpenSearchSlave
+{
+ private String urlTemplate;
+
+ public OpenSearchSlave( String urlTemplate )
+ {
+ this.urlTemplate = urlTemplate;
+ }
+
+ public Document query( String query, int startIndex, int requestedNumResults, int hitsPerSite )
+ throws Exception
+ {
+ URL url = buildRequestUrl( query, startIndex, requestedNumResults, hitsPerSite );
+
+ InputStream is = null;
+ try
+ {
+ is = getInputStream( url );
+
+ Document doc = (new SAXBuilder()).build( is );
+
+ doc = validate( doc );
+
+ return doc;
+ }
+ finally
+ {
+ // Ensure the InputStream is closed, which should trigger the
+ // underlying HTTP connection to be cleaned-up.
+ try { if ( is != null ) is.close( ); } catch ( IOException ioe ) { } // Not much we can do
+ }
+ }
+
+ private Document validate( Document doc )
+ throws Exception
+ {
+ if ( doc.getRootElement( ) == null ) throw new Exception( "Invalid OpenSearch response: missing /rss" );
+ Element root = doc.getRootElement( );
+
+ if ( ! "rss".equals( root.getName( ) ) ) throw new Exception( "Invalid OpenSearch response: missing /rss" );
+ Element channel = root.getChild( "channel" );
+
+ if ( channel == null ) throw new Exception( "Invalid OpenSearch response: missing /rss/channel" );
+
+ for ( Element item : (List<Element>) channel.getChildren( "item" ) )
+ {
+ Element site = item.getChild( "site", Namespace.getNamespace( "http://www.nutch.org/opensearchrss/1.0/" ) );
+ if ( site == null )
+ {
+ item.addContent( new Element( "site", Namespace.getNamespace( "http://www.nutch.org/opensearchrss/1.0/" ) ) );
+ }
+
+ Element score = item.getChild( "score", Namespace.getNamespace( "http://www.nutch.org/opensearchrss/1.0/" ) );
+ if ( score == null )
+ {
+ score = new Element( "score", Namespace.getNamespace( "http://www.nutch.org/opensearchrss/1.0/" ) );
+ score.setText( "" );
+
+ item.addContent( score );
+ }
+ }
+
+ return doc;
+ }
+
+ /**
+ *
+ */
+ public URL buildRequestUrl( String query, int startIndex, int requestedNumResults, int hitsPerSite )
+ throws MalformedURLException, UnsupportedEncodingException
+ {
+ String url = this.urlTemplate;
+
+ // Note about replaceAll: In the Java regex library, the replacement string has a few
+ // special characters: \ and $. Forunately, since we URL-encode the replacement string,
+ // any occurance of \ or $ is converted to %xy form. So we don't have to worry about it. :)
+ url = url.replaceAll( "[{]searchTerms[}]", URLEncoder.encode( query, "utf-8" ) );
+ url = url.replaceAll( "[{]count[}]" , String.valueOf( requestedNumResults ) );
+ url = url.replaceAll( "[{]startIndex[}]" , String.valueOf( startIndex ) );
+ url = url.replaceAll( "[{]hitsPerSite[}]", String.valueOf( hitsPerSite ) );
+
+ // We don't know about any optional parameters, so we remove them (per the OpenSearch spec.)
+ url = url.replaceAll( "[{][^}]+[?][}]", "" );
+
+ return new URL( url );
+ }
+
+
+ public InputStream getInputStream( URL url )
+ throws IOException
+ {
+ URLConnection connection = url.openConnection( );
+ connection.setDoOutput( false );
+ connection.setRequestProperty( "User-Agent", "Mozilla/4.0 (compatible; NutchWAX OpenSearchMaster)" );
+ connection.connect( );
+
+ if ( connection instanceof HttpURLConnection )
+ {
+ HttpURLConnection hc = (HttpURLConnection) connection;
+
+ switch ( hc.getResponseCode( ) )
+ {
+ case 200:
+ // All good.
+ break;
+ default:
+ // Problems! Bail out.
+ throw new IOException( "HTTP error from " + url + ": " + hc.getResponseMessage( ) );
+ }
+ }
+
+ InputStream is = connection.getInputStream( );
+
+ return is;
+ }
+
+ public String toString()
+ {
+ return this.urlTemplate;
+ }
+
+ public static void main( String args[] )
+ throws Exception
+ {
+ String usage = "OpenSearchSlave [OPTIONS] urlTemplate query"
+ + "\n\t-h <n> Hits per site"
+ + "\n\t-n <n> Number of results"
+ + "\n";
+
+ if ( args.length < 2 )
+ {
+ System.err.println( usage );
+ System.exit( 1 );
+ }
+
+ String urlTemplate = args[args.length - 2];
+ String query = args[args.length - 1];
+
+ int hitsPerSite = 0;
+ int numHits = 10;
+ for ( int i = 0 ; i < args.length - 2 ; i++ )
+ {
+ try
+ {
+ if ( "-h".equals( args[i] ) )
+ {
+ i++;
+ hitsPerSite = Integer.parseInt( args[i] );
+ }
+ if ( "-n".equals( args[i] ) )
+ {
+ i++;
+ numHits = Integer.parseInt( args[i] );
+ }
+ }
+ catch ( NumberFormatException nfe )
+ {
+ System.err.println( "Error: not a numeric value: " + args[i] );
+ System.err.println( usage );
+ System.exit( 1 );
+ }
+ }
+
+ OpenSearchSlave osl = new OpenSearchSlave( urlTemplate );
+
+ Document doc = osl.query( query, 0, numHits, hitsPerSite );
+
+ (new XMLOutputter()).output( doc, System.out );
+ }
+
+}
\ No newline at end of file
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
