Merge pull request awslabs#18 from iansrobinson/master

Update rdf4j version

neptune-export/pom.xml

@@ -74,9 +74,36 @@
         <dependency>
             <groupId>org.eclipse.rdf4j</groupId>
             <artifactId>rdf4j-runtime</artifactId>
-            <version>2.2</version>
+            <version>[2.4.0,)</version>
         </dependency>
 
+        <dependency>
+            <groupId>org.eclipse.rdf4j</groupId>
+            <artifactId>rdf4j-rio-turtle</artifactId>
+            <version>2.4.3</version>
+        </dependency>
+
+        <dependency>
+            <groupId>org.slf4j</groupId>
+            <artifactId>slf4j-api</artifactId>
+            <version>1.8.0-beta2</version>
+        </dependency>
+
+        <dependency>
+            <groupId>org.slf4j</groupId>
+            <artifactId>jcl-over-slf4j</artifactId>
+            <version>1.8.0-beta2</version>
+        </dependency>
+
+        <dependency>
+            <groupId>org.slf4j</groupId>
+            <artifactId>slf4j-simple</artifactId>
+            <version>1.8.0-beta2</version>
+        </dependency>
+
+
+
+
     </dependencies>
 
     <build>

neptune-export/src/main/java/com/amazonaws/services/neptune/NeptuneExportCli.java

@@ -39,6 +39,11 @@
         }))
 public class NeptuneExportCli {
 
+    static {
+        System.setProperty("org.apache.commons.logging.Log",
+                "org.apache.commons.logging.impl.NoOpLog");
+    }
+
     public static void main(String[] args) {
         com.github.rvesse.airline.Cli<Runnable> cli = new com.github.rvesse.airline.Cli<>(NeptuneExportCli.class);
 

neptune-export/src/main/java/com/amazonaws/services/neptune/rdf/NeptuneSparqlClient.java

@@ -12,13 +12,19 @@
 
 package com.amazonaws.services.neptune.rdf;
 
+import com.amazonaws.services.neptune.rdf.io.EnhancedTurtleWriter;
 import org.eclipse.rdf4j.query.GraphQuery;
 import org.eclipse.rdf4j.query.GraphQueryResult;
 import org.eclipse.rdf4j.repository.RepositoryConnection;
 import org.eclipse.rdf4j.repository.base.AbstractRepository;
 import org.eclipse.rdf4j.repository.sparql.SPARQLRepository;
+import org.eclipse.rdf4j.rio.WriterConfig;
 import org.joda.time.DateTime;
 
+import java.io.FileWriter;
+import java.io.IOException;
+import java.io.Writer;
+import java.nio.file.Path;
 import java.util.Collection;
 import java.util.List;
 import java.util.Random;
@@ -42,11 +48,17 @@ private NeptuneSparqlClient(List<SPARQLRepository> repositories) {
         this.repositories = repositories;
     }
 
-    public GraphQueryResult executeQuery(String sparql) {
-        try (RepositoryConnection connection = chooseRepository().getConnection()) {
-            GraphQuery query = connection.prepareGraphQuery(sparql);
-            return query.evaluate();
+    public void executeQuery(String sparql, Path file) throws IOException {
+        Prefixes prefixes = new Prefixes();
+
+        try (RepositoryConnection connection = chooseRepository().getConnection();
+             Writer fileWriter = new FileWriter(file.toFile())) {
+
+            EnhancedTurtleWriter writer = new EnhancedTurtleWriter(fileWriter, prefixes);
+            connection.prepareGraphQuery(sparql).evaluate(writer);
         }
+
+        prefixes.addTo(file);
     }
 
     private SPARQLRepository chooseRepository() {

neptune-export/src/main/java/com/amazonaws/services/neptune/rdf/Prefixes.java

@@ -15,6 +15,7 @@
 import org.apache.commons.io.FileUtils;
 import org.apache.commons.io.IOUtils;
 import org.apache.commons.io.LineIterator;
+import org.eclipse.rdf4j.rio.RDFWriter;
 
 import java.io.BufferedWriter;
 import java.io.File;
@@ -55,6 +56,21 @@ public String formatIRI(String s) {
         }
     }
 
+    public void parse(String s, RDFWriter writer) {
+
+        int i = s.indexOf("#");
+
+        if (i > 0 && i < (s.length() - 1)) {
+            String uri = s.substring(0, i + 1);
+
+            if (!prefixes.containsKey(uri)) {
+                String prefix = "s" + (prefixes.size() - offset);
+                prefixes.put(uri, prefix);
+                writer.handleNamespace(prefix, uri);
+            }
+        }
+    }
+
     public void addTo(Path filePath) throws IOException {
         File source = filePath.toFile();
         LineIterator lineIterator = FileUtils.lineIterator(source);

neptune-export/src/main/java/com/amazonaws/services/neptune/rdf/io/EnhancedTurtleWriter.java

@@ -0,0 +1,51 @@
+/*
+Copyright 2019 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+Licensed under the Apache License, Version 2.0 (the "License").
+You may not use this file except in compliance with the License.
+A copy of the License is located at
+    http://www.apache.org/licenses/LICENSE-2.0
+or in the "license" file accompanying this file. This file 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 com.amazonaws.services.neptune.rdf.io;
+
+import com.amazonaws.services.neptune.io.Status;
+import com.amazonaws.services.neptune.rdf.Prefixes;
+import org.eclipse.rdf4j.model.Statement;
+import org.eclipse.rdf4j.rio.RDFHandlerException;
+import org.eclipse.rdf4j.rio.turtle.TurtleWriter;
+
+import java.io.IOException;
+import java.io.Writer;
+
+public class EnhancedTurtleWriter extends TurtleWriter {
+
+    private final Prefixes prefixes;
+    private final Status status = new Status();
+
+    public EnhancedTurtleWriter(Writer writer, Prefixes prefixes) {
+        super(writer);
+        this.prefixes = prefixes;
+    }
+
+    @Override
+    public void handleStatement(Statement statement) throws RDFHandlerException {
+
+        prefixes.parse(statement.getSubject().stringValue(), this);
+        prefixes.parse(statement.getPredicate().toString(), this);
+        prefixes.parse(statement.getObject().stringValue(), this);
+
+        super.handleStatement(statement);
+
+        status.update();
+    }
+
+    @Override
+    protected void writeNamespace(String prefix, String name)
+            throws IOException {
+        // Do nothing
+    }
+}

neptune-export/src/main/java/com/amazonaws/services/neptune/rdf/io/ExportRdfGraphJob.java

@@ -13,11 +13,8 @@
 package com.amazonaws.services.neptune.rdf.io;
 
 import com.amazonaws.services.neptune.io.Directories;
-import com.amazonaws.services.neptune.io.Status;
 import com.amazonaws.services.neptune.rdf.NeptuneSparqlClient;
 import com.amazonaws.services.neptune.rdf.Prefixes;
-import com.amazonaws.services.neptune.rdf.StatementHandler;
-import org.eclipse.rdf4j.query.GraphQueryResult;
 
 public class ExportRdfGraphJob {
 
@@ -37,22 +34,6 @@ public void execute() throws Exception {
         java.nio.file.Path filePath = directories.createFilePath(
                 directories.statementsDirectory(), "statements", 0, () -> "ttl");
 
-        try (StatementsPrinter printer = new StatementsPrinter(filePath)) {
-
-            Status status = new Status();
-            StatementHandler handler = StatementHandler.create(prefixes);
-
-            GraphQueryResult result = client.executeQuery("CONSTRUCT { ?s ?p ?o } WHERE { ?s ?p ?o }");
-
-            while (result.hasNext()) {
-
-                handler = handler.handle(result.next());
-                handler.printTo(printer);
-
-                status.update();
-            }
-        }
-
-        prefixes.addTo(filePath);
+        client.executeQuery("CONSTRUCT { ?s ?p ?o } WHERE { ?s ?p ?o }", filePath);
     }
 }