updated pom and added command line parameters

defindexer/pom.xml

@@ -7,6 +7,24 @@
 	<version>0.0.1-SNAPSHOT</version>
 	<name>defindexer Maven Webapp</name>
 	<url>http://maven.apache.org</url>
+
+	<build>
+		<plugins>
+			<plugin>
+				<groupId>org.apache.maven.plugins</groupId>
+				<artifactId>maven-jar-plugin</artifactId>
+				<configuration>
+					<archive>
+						<manifest>
+							<addClasspath>true</addClasspath>
+							<mainClass>info.kwarc.lmh.DefIndexer.DefIndexer</mainClass>
+						</manifest>
+					</archive>
+				</configuration>
+			</plugin>
+		</plugins>
+	</build>
+
 	<dependencies>
 		<dependency>
 			<groupId>junit</groupId>
@@ -19,20 +37,21 @@
 			<artifactId>solr-solrj</artifactId>
 			<version>4.6.0</version>
 		</dependency>
-
+		<dependency>
+			<groupId>args4j</groupId>
+			<artifactId>args4j</artifactId>
+			<version>2.0.26</version>
+		</dependency>
 		<dependency>
 			<groupId>commons-logging</groupId>
 			<artifactId>commons-logging</artifactId>
 			<version>1.1.3</version>
 		</dependency>
-		
+
 		<dependency>
 			<groupId>info.kwarc.mmt</groupId>
 			<artifactId>service-wrapper</artifactId>
 			<version>0.0.1-SNAPSHOT</version>
 		</dependency>
 	</dependencies>
-	<build>
-		<finalName>defindexer</finalName>
-	</build>
 </project>

defindexer/src/main/java/info/kwarc/lmh/DefIndexer/DefIndexer.java

@@ -2,39 +2,103 @@ package info.kwarc.lmh.DefIndexer;
 
 import info.kwarc.mmt.MMT;
 
+import java.io.ByteArrayInputStream;
 import java.io.IOException;
+import java.io.InputStream;
+import java.io.Reader;
+import java.io.StringReader;
 import java.util.regex.Matcher;
 import java.util.regex.Pattern;
 
-import org.apache.solr.client.solrj.SolrServer;
 import org.apache.solr.client.solrj.SolrServerException;
-import org.apache.solr.client.solrj.impl.HttpSolrServer;
-import org.apache.solr.common.SolrInputDocument;
+import org.apache.solr.client.solrj.impl.ConcurrentUpdateSolrServer;
+import org.apache.solr.client.solrj.request.AbstractUpdateRequest;
+import org.apache.solr.client.solrj.request.ContentStreamUpdateRequest;
+import org.apache.solr.common.util.ContentStream;
+import org.kohsuke.args4j.CmdLineException;
+import org.kohsuke.args4j.CmdLineParser;
+import org.kohsuke.args4j.Option;
 
 public class DefIndexer {
+    @Option(name="--solr",usage="URL of the SOLR server")
+	String solrUrl = "http://localhost:8983/solr";
+    
+    @Option(name="--mmt",usage="URL of the MMT server")
+	String mmtUrl = "http://localhost:8080";
 
+    @Option(name="--stomp", usage="Connect to STOMP server to serve e.g. authoring environments")
+    String stompUrl = "http://localhost:61613";
+    
 	public DefIndexer() {
 	}
 
+
 	final static Pattern uri  = Pattern.compile("http://mathhub.info/([\\w-]+)/([\\w-]+)/([\\w-\\./]+)\\?([\\w-.]+)(\\?([\\w-.]+))?");
 	
-	public static void main(String[] args) {
-		String urlString = "http://mathhub.info:8983/solr";
-		SolrServer solr = new HttpSolrServer(urlString);
+	class StringContentStream implements ContentStream {
+		String content;
+		
+		public StringContentStream(String content) {
+			this.content = content;
+		}
+		
+		public String getName() {
+			return "noname";
+		}
+
+		public String getSourceInfo() {
+			return "mmt";
+		}
+
+		public String getContentType() {
+			return "application/xml";
+		}
+
+		public Long getSize() {
+			return new Long(content.length());
+		}
+
+		public InputStream getStream() throws IOException {
+			return new ByteArrayInputStream(content.getBytes());
+		}
+
+		public Reader getReader() throws IOException {
+			return new StringReader(content);
+		}
+		
+	}
 
+	public void run(String[] args) {
+        CmdLineParser parser = new CmdLineParser(this);
+
+        try {
+            parser.parseArgument(args);
+        } catch( CmdLineException e ) {
+            System.err.println(e.getMessage());
+            System.err.println("java DefIndexer [options...] arguments...");
+            parser.printUsage(System.err);
+            System.err.println();
+
+            System.err.println("  Example: java DefIndexer --solr http://mathhub.info:8983/solr --mmt http://mathhub.info:8080 ");
+            return;
+        }
+        
+		//SolrServer solr = new HttpSolrServer(solrUrl);
+		ConcurrentUpdateSolrServer solr = new ConcurrentUpdateSolrServer(solrUrl, 10, 5);
 		try {
 			solr.deleteByQuery( "*:*" );
+			solr.commit();
 		} catch (SolrServerException e1) {
 			e1.printStackTrace();
 		} catch (IOException e1) {
 			e1.printStackTrace();
 		}
-		MMT mmt = new MMT("http://mathhub.info:8080");
+		
+		MMT mmt = new MMT(mmtUrl);
 
 		for (String theoryURI : mmt.getTheories()) {
 			String content = mmt.getPresentation(theoryURI);
 			for (String concept : mmt.getTheoryConcepts(theoryURI)) {
-				SolrInputDocument doc = new SolrInputDocument();
 				Matcher m = uri.matcher(concept);
 				if (!m.matches()) {
 					continue;
@@ -46,37 +110,34 @@ public class DefIndexer {
 				String omdoc = m.group(3);
 				String theory = m.group(4);
 				String symb = m.group(6);
-
-				doc.addField( "id", concept, 1.0f );
-				doc.addField( "repository", repo, 1.0f );
-				doc.addField( "repository_name", repo_name, 1.0f );
-				doc.addField( "repository_group", repo_group, 1.0f );
-				
-				doc.addField( "omdoc", omdoc, 1.0f );
-				doc.addField( "theory", theory, 1.0f );
-				doc.addField( "symbol", symb, 1.0f );
-				doc.addField( "content", content, 1.0f );
 				
 				try {
-					solr.add(doc);
-				} catch (SolrServerException e) {
+					ContentStreamUpdateRequest up = new ContentStreamUpdateRequest("/update/extract");
+					up.addContentStream(new StringContentStream(content));
+					up.setParam( "literal.id", concept);
+					up.setParam( "literal.repository", repo);
+					up.setParam( "literal.repository_name", repo_name);
+					up.setParam( "literal.repository_group", repo_group);
+					
+					up.setParam( "literal.omdoc", omdoc);
+					up.setParam( "literal.theory", theory);
+					up.setParam( "literal.symbol", symb);
+					up.setParam( "literal.description", content);
+					//up.setParam( "literal.content", content);
+					
+					up.setAction(AbstractUpdateRequest.ACTION.COMMIT, true, true);
+					solr.request(up);
+				} catch (IOException e2) {
 					// TODO Auto-generated catch block
-					e.printStackTrace();
-				} catch (IOException e) {
+					e2.printStackTrace();
+				} catch (SolrServerException e) {
 					// TODO Auto-generated catch block
 					e.printStackTrace();
-				}		
+				}
 			}
 		}
-		
-		try {
-			solr.commit();
-		} catch (SolrServerException e) {
-			// TODO Auto-generated catch block
-			e.printStackTrace();
-		} catch (IOException e) {
-			e.printStackTrace();
-		}
-
+	}
+	public static void main(String[] args) {
+		new DefIndexer().run(args);
 	}
 }