Respect ignoreCase flag in CommonGramsFilterFactory

apache · Dec 12, 2022 · e603350 · e603350
1 parent c0c4804
commit e603350
Show file tree

Hide file tree

Showing 2 changed files with 19 additions and 3 deletions.
diff --git a/src/Lucene.Net.Analysis.Common/Analysis/CommonGrams/CommonGramsFilterFactory.cs b/src/Lucene.Net.Analysis.Common/Analysis/CommonGrams/CommonGramsFilterFactory.cs
@@ -36,7 +36,7 @@ namespace Lucene.Net.Analysis.CommonGrams
     /// </summary>
     public class CommonGramsFilterFactory : TokenFilterFactory, IResourceLoaderAware
     {
-        // TODO: shared base class for Stop/Keep/CommonGrams? 
+        // TODO: shared base class for Stop/Keep/CommonGrams?
         private CharArraySet commonWords;
         private readonly string commonWordFiles;
         private readonly string format;
@@ -71,7 +71,7 @@ public virtual void Inform(IResourceLoader loader)
             }
             else
             {
-                commonWords = StopAnalyzer.ENGLISH_STOP_WORDS_SET;
+                commonWords = new CharArraySet(m_luceneMatchVersion,StopAnalyzer.ENGLISH_STOP_WORDS_SET, ignoreCase);
             }
         }
 

diff --git a/src/Lucene.Net.Tests.Analysis.Common/Analysis/Commongrams/TestCommonGramsFilterFactory.cs b/src/Lucene.Net.Tests.Analysis.Common/Analysis/Commongrams/TestCommonGramsFilterFactory.cs
@@ -28,7 +28,7 @@ namespace Lucene.Net.Analysis.CommonGrams
     /// Tests pretty much copied from StopFilterFactoryTest We use the test files
     /// used by the StopFilterFactoryTest TODO: consider creating separate test files
     /// so this won't break if stop filter test files change
-    /// 
+    ///
     /// </summary>
     public class TestCommonGramsFilterFactory : BaseTokenStreamFactoryTestCase
     {
@@ -79,6 +79,22 @@ public virtual void TestDefaults()
             AssertTokenStreamContents(stream, new string[] { "testing", "testing_the", "the", "the_factory", "factory" });
         }
 
+        [Test]
+        public void TestIgnoreCase()
+        {
+            IResourceLoader loader = new ClasspathResourceLoader(typeof(TestAnalyzers));
+            CommonGramsFilterFactory factory =
+                (CommonGramsFilterFactory)
+                TokenFilterFactory("CommonGrams", TEST_VERSION_CURRENT, loader, "ignoreCase", "true");
+            CharArraySet words = factory.CommonWords;
+            assertTrue("words is null and it shouldn't be", words != null);
+            assertTrue(words.contains("the"));
+            assertTrue(words.contains("The"));
+            Tokenizer tokenizer = new MockTokenizer(new StringReader("testing The factory"),MockTokenizer.WHITESPACE, false);
+            TokenStream stream = factory.Create(tokenizer);
+            AssertTokenStreamContents(
+                stream, new String[] {"testing", "testing_The", "The", "The_factory", "factory"});
+        }
         /// <summary>
         /// Test that bogus arguments result in exception </summary>
         [Test]