From 43af96bb0f086ede0b8dbc417fd92e52ea1760cc Mon Sep 17 00:00:00 2001
From: Jeremy Long <jeremy.long@gmail.com>
Date: Fri, 29 Dec 2017 05:58:44 -0500
Subject: [PATCH] enhanced filter to support empty tokens

---
 .../data/lucene/AlphaNumericFilter.java       |  4 +++-
 .../data/lucene/AlphaNumericFilterTest.java   | 19 +++++++++++++++++++
 2 files changed, 22 insertions(+), 1 deletion(-)

diff --git a/dependency-check-core/src/main/java/org/owasp/dependencycheck/data/lucene/AlphaNumericFilter.java b/dependency-check-core/src/main/java/org/owasp/dependencycheck/data/lucene/AlphaNumericFilter.java
index 761aaa3de..f23ee8eab 100644
--- a/dependency-check-core/src/main/java/org/owasp/dependencycheck/data/lucene/AlphaNumericFilter.java
+++ b/dependency-check-core/src/main/java/org/owasp/dependencycheck/data/lucene/AlphaNumericFilter.java
@@ -72,7 +72,9 @@ public final class AlphaNumericFilter extends AbstractTokenizingFilter {
             skipCounter = 0;
             while (input.incrementToken()) {
                 final String text = new String(termAtt.buffer(), 0, termAtt.length());
-
+                if (text.isEmpty()) {
+                    return true;
+                }
                 parts = text.split("[^a-zA-Z0-9]");
                 if (parts.length == 0) {
                     skipCounter += posIncrAttribute.getPositionIncrement();
diff --git a/dependency-check-core/src/test/java/org/owasp/dependencycheck/data/lucene/AlphaNumericFilterTest.java b/dependency-check-core/src/test/java/org/owasp/dependencycheck/data/lucene/AlphaNumericFilterTest.java
index 3e279805d..32e980a6f 100644
--- a/dependency-check-core/src/test/java/org/owasp/dependencycheck/data/lucene/AlphaNumericFilterTest.java
+++ b/dependency-check-core/src/test/java/org/owasp/dependencycheck/data/lucene/AlphaNumericFilterTest.java
@@ -18,9 +18,11 @@ package org.owasp.dependencycheck.data.lucene;
 import java.io.IOException;
 import org.apache.lucene.analysis.Analyzer;
 import org.apache.lucene.analysis.BaseTokenStreamTestCase;
+import static org.apache.lucene.analysis.BaseTokenStreamTestCase.checkOneTerm;
 import static org.apache.lucene.analysis.BaseTokenStreamTestCase.checkRandomData;
 import org.apache.lucene.analysis.MockTokenizer;
 import org.apache.lucene.analysis.Tokenizer;
+import org.apache.lucene.analysis.core.KeywordTokenizer;
 import static org.apache.lucene.util.LuceneTestCase.RANDOM_MULTIPLIER;
 import static org.apache.lucene.util.LuceneTestCase.random;
 import org.junit.Test;
@@ -82,4 +84,21 @@ public class AlphaNumericFilterTest extends BaseTokenStreamTestCase {
             fail("Failed test random strings: " + ex.getMessage());
         }
     }
+    
+        /**
+     * copied from
+     * http://svn.apache.org/repos/asf/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/en/TestEnglishMinimalStemFilter.java
+     *
+     * @throws IOException
+     */
+    public void testEmptyTerm() throws IOException {
+        Analyzer a = new Analyzer() {
+            @Override
+            protected Analyzer.TokenStreamComponents createComponents(String fieldName) {
+                Tokenizer tokenizer = new KeywordTokenizer();
+                return new Analyzer.TokenStreamComponents(tokenizer, new AlphaNumericFilter(tokenizer));
+            }
+        };
+        checkOneTerm(a, "", "");
+    }
 }