feat: loadTokenizer uses default tokenizer when none provided

Author: Anton Hosgood

oak-lucene/src/main/java/org/apache/jackrabbit/oak/plugins/index/lucene/NodeStateAnalyzerFactory.java

@@ -58,8 +58,6 @@
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 
-import static java.util.Objects.requireNonNull;
-
 /**
  * Constructs a Lucene Analyzer from nodes (based on NodeState content).
  *
@@ -141,9 +139,13 @@ private CharFilterFactory[] loadCharFilterFactories(NodeState charFiltersState)
     }
 
     private TokenizerFactory loadTokenizer(NodeState state) {
-        String clazz = requireNonNull(state.getString(FulltextIndexConstants.ANL_NAME));
+        String name = state.getString(FulltextIndexConstants.ANL_NAME);
+        if (name == null) {
+            log.warn("No tokenizer name specified in analyzer configuration. Using default 'standard' tokenizer.");
+            name = "standard";
+        }
         Map<String, String> args = convertNodeState(state);
-        TokenizerFactory tf = TokenizerFactory.forName(clazz, args);
+        TokenizerFactory tf = TokenizerFactory.forName(name, args);
         init(tf, state);
         return tf;
     }

oak-lucene/src/test/java/org/apache/jackrabbit/oak/plugins/index/lucene/NodeStateAnalyzerFactoryTest.java

@@ -38,6 +38,7 @@
 import org.apache.lucene.analysis.core.StopFilterFactory;
 import org.apache.lucene.analysis.core.WhitespaceTokenizerFactory;
 import org.apache.lucene.analysis.path.PathHierarchyTokenizerFactory;
+import org.apache.lucene.analysis.standard.StandardTokenizerFactory;
 import org.apache.lucene.analysis.util.CharArraySet;
 import org.apache.lucene.analysis.util.ClasspathResourceLoader;
 import org.apache.lucene.analysis.util.StopwordAnalyzerBase;
@@ -191,6 +192,18 @@ public void nodeStateAsMap() throws Exception{
         assertNull(result.get(":hiddenProp"));
     }
 
+    @Test
+    public void missingTokenizerName() throws Exception{
+        NodeBuilder nb = EMPTY_NODE.builder();
+        nb.child(ANL_TOKENIZER);
+
+        TokenizerChain analyzer = (TokenizerChain) factory.createInstance(nb.getNodeState());
+        assertNotNull(analyzer);
+        assertNotNull(analyzer.getTokenizer());
+
+        assertEquals(StandardTokenizerFactory.class.getName(), analyzer.getTokenizer().getClassArg());
+    }
+
     private static NodeBuilder createFileNode(NodeBuilder nb, String nodeName, byte[] content){
         return nb.child(nodeName).child(JCR_CONTENT).setProperty(JCR_DATA, content);
     }