#4513 - Support full text search in knowledge bases running on Blazegraph

inception/inception-dependencies/pom.xml

@@ -140,6 +140,13 @@
         <type>pom</type>
         <scope>import</scope>
       </dependency>
+      <dependency>
+        <groupId>org.testcontainers</groupId>
+        <artifactId>testcontainers-bom</artifactId>
+        <version>${testcontainers.version}</version>
+        <type>pom</type>
+        <scope>import</scope>
+      </dependency>
       <dependency>
         <groupId>org.assertj</groupId>
         <artifactId>assertj-core</artifactId>

inception/inception-kb/pom.xml

@@ -336,6 +336,16 @@
       <artifactId>spring-core</artifactId>
       <scope>test</scope>
     </dependency>
+    <dependency>
+      <groupId>org.testcontainers</groupId>
+      <artifactId>testcontainers</artifactId>
+      <scope>test</scope>
+    </dependency>
+    <dependency>
+      <groupId>org.testcontainers</groupId>
+      <artifactId>junit-jupiter</artifactId>
+      <scope>test</scope>
+    </dependency>
   </dependencies>
   <build>
     <pluginManagement>

inception/inception-kb/src/main/java/de/tudarmstadt/ukp/inception/kb/IriConstants.java

@@ -47,6 +47,7 @@ public class IriConstants
     public static final String PREFIX_LUCENE_SEARCH = "http://www.openrdf.org/contrib/lucenesail#";
     public static final String PREFIX_MWAPI = "https://www.mediawiki.org/ontology#API/";
     public static final String PREFIX_STARDOG = "tag:stardog:api:search:";
+    public static final String PREFIX_BLAZEGRAPH = "http://www.bigdata.com/rdf/search#";
 
     public static final String UKP_WIKIDATA_SPARQL_ENDPOINT = "http://knowledgebase.ukp.informatik.tu-darmstadt.de:8890/sparql";
     public static final Set<String> IMPLICIT_NAMESPACES = Set.of(RDF.NAMESPACE, RDFS.NAMESPACE,
@@ -87,6 +88,7 @@ public class IriConstants
     public static final IRI FTS_VIRTUOSO;
     public static final IRI FTS_WIKIDATA;
     public static final IRI FTS_STARDOG;
+    public static final IRI FTS_BLAZEGRAPH;
     public static final IRI FTS_NONE;
 
     public static final List<IRI> CLASS_IRIS;
@@ -116,6 +118,7 @@ public class IriConstants
         FTS_LUCENE = vf.createIRI(PREFIX_LUCENE_SEARCH, "matches");
         FTS_WIKIDATA = vf.createIRI(PREFIX_MWAPI, "search");
         FTS_STARDOG = vf.createIRI(PREFIX_STARDOG, "textMatch");
+        FTS_BLAZEGRAPH = vf.createIRI(PREFIX_BLAZEGRAPH, "search");
         FTS_NONE = vf.createIRI("FTS:NONE");
 
         CLASS_IRIS = asList(RDFS.CLASS, OWL.CLASS, WIKIDATA_CLASS, SKOS.CONCEPT);

inception/inception-kb/src/main/java/de/tudarmstadt/ukp/inception/kb/querybuilder/BlazegraphFtsQuery.java

@@ -0,0 +1,90 @@
+/*
+ * Licensed to the Technische Universität Darmstadt under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The Technische Universität Darmstadt 
+ * 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.
+ *  
+ * 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 de.tudarmstadt.ukp.inception.kb.querybuilder;
+
+import static org.eclipse.rdf4j.sparqlbuilder.core.SparqlBuilder.prefix;
+import static org.eclipse.rdf4j.sparqlbuilder.rdf.Rdf.iri;
+import static org.eclipse.rdf4j.sparqlbuilder.rdf.Rdf.literalOf;
+
+import org.eclipse.rdf4j.sparqlbuilder.core.Prefix;
+import org.eclipse.rdf4j.sparqlbuilder.core.Variable;
+import org.eclipse.rdf4j.sparqlbuilder.graphpattern.GraphPattern;
+import org.eclipse.rdf4j.sparqlbuilder.rdf.Iri;
+
+import de.tudarmstadt.ukp.inception.kb.IriConstants;
+
+public class BlazegraphFtsQuery
+    implements GraphPattern
+{
+    public static final Prefix PREFIX_BLAZEGRAPH_SEARCH = prefix("bds",
+            iri(IriConstants.FTS_BLAZEGRAPH));
+    public static final Iri BLAZEGRAPH_SEARCH = PREFIX_BLAZEGRAPH_SEARCH.iri("search");
+    public static final Iri BLAZEGRAPH_RELEVANCE = PREFIX_BLAZEGRAPH_SEARCH.iri("relevance");
+    public static final Iri BLAZEGRAPH_MAX_RANK = PREFIX_BLAZEGRAPH_SEARCH.iri("maxRank");
+
+    private final Variable subject;
+    private final Variable score;
+    private final Variable matchTerm;
+    private final Variable matchTermProperty;
+    private final String query;
+    private int limit = 0;
+
+    public BlazegraphFtsQuery(Variable aSubject, Variable aScore, Variable aMatchTerm,
+            Variable aMatchTermProperty, String aQuery)
+    {
+        subject = aSubject;
+        score = aScore;
+        matchTerm = aMatchTerm;
+        matchTermProperty = aMatchTermProperty;
+        query = aQuery;
+    }
+
+    public BlazegraphFtsQuery withLimit(int aLimit)
+    {
+        limit = aLimit;
+        return this;
+    }
+
+    @Override
+    public String getQueryString()
+    {
+        var sb = new StringBuilder();
+        sb.append("SERVICE ");
+        sb.append(BLAZEGRAPH_SEARCH.getQueryString());
+        sb.append(" { \n");
+
+        var pattern = matchTerm //
+                .has(BLAZEGRAPH_SEARCH, literalOf(query)) //
+                .andHas(BLAZEGRAPH_RELEVANCE, score);
+
+        if (limit > 0) {
+            pattern = pattern.andHas(BLAZEGRAPH_MAX_RANK, literalOf(2 * limit));
+        }
+
+        sb.append(pattern.getQueryString());
+        sb.append(" } ");
+        sb.append(subject.has(matchTermProperty, matchTerm).getQueryString());
+        return sb.toString();
+    }
+
+    @Override
+    public boolean isEmpty()
+    {
+        return false;
+    }
+}