From 2183756f1c8253002bb697bdb8e026e86c4b3db5 Mon Sep 17 00:00:00 2001
From: Alan Woodward <romseygeek@apache.org>
Date: Wed, 9 Feb 2022 14:37:44 +0000
Subject: [PATCH] LUCENE-10413: Make default Ukrainian stopword set available
 (#665)

This commit adds a new getDefaultStopwords() static method to
UkrainianMorfologikAnalyzer, which makes it possible to create an
analyzer with the default stop word set but a custom stem exclusion
set.
---
 lucene/CHANGES.txt                                    |  2 ++
 .../analysis/uk/UkrainianMorfologikAnalyzer.java      | 11 ++++-------
 .../lucene/analysis/uk/TestUkrainianAnalyzer.java     |  8 ++++++++
 3 files changed, 14 insertions(+), 7 deletions(-)

diff --git a/lucene/CHANGES.txt b/lucene/CHANGES.txt
index 6f380a4965b..73909964b22 100644
--- a/lucene/CHANGES.txt
+++ b/lucene/CHANGES.txt
@@ -267,6 +267,8 @@ Other
   and discover classes to check from module system. The test now checks all analyzer modules,
   so it may discover new bugs outside of analysis:common module.  (Uwe Schindler, Robert Muir)
 
+* LUCENE-10413: Make Ukrainian default stop words list available as a public getter. (Alan Woodward)
+
 ======================= Lucene 9.0.0 =======================
 
 New Features
diff --git a/lucene/analysis/morfologik/src/java/org/apache/lucene/analysis/uk/UkrainianMorfologikAnalyzer.java b/lucene/analysis/morfologik/src/java/org/apache/lucene/analysis/uk/UkrainianMorfologikAnalyzer.java
index eb29448ca7d..558239a95d9 100644
--- a/lucene/analysis/morfologik/src/java/org/apache/lucene/analysis/uk/UkrainianMorfologikAnalyzer.java
+++ b/lucene/analysis/morfologik/src/java/org/apache/lucene/analysis/uk/UkrainianMorfologikAnalyzer.java
@@ -113,14 +113,11 @@ public final class UkrainianMorfologikAnalyzer extends StopwordAnalyzerBase {
     return defaultResources;
   }
 
-  private static class DefaultResources {
-    final CharArraySet stopSet;
-    final Dictionary dictionary;
+  private record DefaultResources(CharArraySet stopSet, Dictionary dictionary) {}
 
-    private DefaultResources(CharArraySet stopSet, Dictionary dictionary) {
-      this.stopSet = stopSet;
-      this.dictionary = dictionary;
-    }
+  /** Returns the default stopword set for this analyzer */
+  public static CharArraySet getDefaultStopwords() {
+    return CharArraySet.unmodifiableSet(getDefaultResources().stopSet);
   }
 
   /** Builds an analyzer with the default stop words. */
diff --git a/lucene/analysis/morfologik/src/test/org/apache/lucene/analysis/uk/TestUkrainianAnalyzer.java b/lucene/analysis/morfologik/src/test/org/apache/lucene/analysis/uk/TestUkrainianAnalyzer.java
index e04f62639db..f984ff8c18c 100644
--- a/lucene/analysis/morfologik/src/test/org/apache/lucene/analysis/uk/TestUkrainianAnalyzer.java
+++ b/lucene/analysis/morfologik/src/test/org/apache/lucene/analysis/uk/TestUkrainianAnalyzer.java
@@ -18,6 +18,7 @@ package org.apache.lucene.analysis.uk;
 
 import java.io.IOException;
 import org.apache.lucene.analysis.Analyzer;
+import org.apache.lucene.analysis.CharArraySet;
 import org.apache.lucene.tests.analysis.BaseTokenStreamTestCase;
 
 /** Test case for UkrainianAnalyzer. */
@@ -99,4 +100,11 @@ public class TestUkrainianAnalyzer extends BaseTokenStreamTestCase {
     checkRandomData(random(), analyzer, 200 * RANDOM_MULTIPLIER);
     analyzer.close();
   }
+
+  public void testDefaultStopWords() {
+    CharArraySet stopwords = UkrainianMorfologikAnalyzer.getDefaultStopwords();
+    assertTrue(stopwords.contains("аби"));
+    stopwords.remove("аби");
+    assertTrue(UkrainianMorfologikAnalyzer.getDefaultStopwords().contains("аби"));
+  }
 }