Skip to content

Apache Lucene open-source search software

Fix and simplify the test (#11734).

Dawid Weiss8bdfa90ea9b9
diff --git a/lucene/analysis/opennlp/src/test/org/apache/lucene/analysis/opennlp/TestOpenNLPLemmatizerFilterFactory.java b/lucene/analysis/opennlp/src/test/org/apache/lucene/analysis/opennlp/TestOpenNLPLemmatizerFilterFactory.java
index 681ec91eb22..20e42d38991 100644
--- a/lucene/analysis/opennlp/src/test/org/apache/lucene/analysis/opennlp/TestOpenNLPLemmatizerFilterFactory.java
+++ b/lucene/analysis/opennlp/src/test/org/apache/lucene/analysis/opennlp/TestOpenNLPLemmatizerFilterFactory.java
@@ -20,8 +20,6 @@ package org.apache.lucene.analysis.opennlp;
import java.io.IOException;
import java.io.InputStream;
import java.nio.charset.StandardCharsets;
-import java.util.Arrays;
-import java.util.stream.Collectors;
import org.apache.lucene.analysis.custom.CustomAnalyzer;
import org.apache.lucene.analysis.miscellaneous.KeywordRepeatFilterFactory;
import org.apache.lucene.analysis.miscellaneous.RemoveDuplicatesTokenFilterFactory;
@@ -332,11 +330,8 @@ public class TestOpenNLPLemmatizerFilterFactory extends BaseTokenStreamTestCase
earlyExitOutput = loader.openResource("data/early-exit-bug-output.txt");
String earlyExitOutputText =
new String(earlyExitOutput.readAllBytes(), StandardCharsets.UTF_8);
- String[] earlyExitOutputTexts =
- Arrays.stream(earlyExitOutputText.split("\\s"))
- .filter(text -> text != "")
- .collect(Collectors.joining(" "))
- .split(" ");
+ String[] earlyExitOutputTexts = earlyExitOutputText.split("[\\s\\r\\n]+");
+
CustomAnalyzer analyzer =
CustomAnalyzer.builder(new ClasspathResourceLoader(getClass()))
.withTokenizer(