From af3942eeddf958879ee041f4996b0fb7e218f3f4 Mon Sep 17 00:00:00 2001
From: Damien <damien-git@users.noreply.github.com>
Date: Thu, 7 Nov 2024 10:50:31 -0500
Subject: [PATCH 1/2] Fixed TitleNormalizer for Chinese characters

---
 src/main/java/org/vufind/util/TitleNormalizer.java | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/src/main/java/org/vufind/util/TitleNormalizer.java b/src/main/java/org/vufind/util/TitleNormalizer.java
index 7324516..503c226 100644
--- a/src/main/java/org/vufind/util/TitleNormalizer.java
+++ b/src/main/java/org/vufind/util/TitleNormalizer.java
@@ -5,14 +5,16 @@
 import org.solrmarc.index.extractor.formatter.FieldFormatter;
 import org.solrmarc.tools.DataUtil;
 
-public class TitleNormalizer implements Normalizer
+public class TitleNormalizer extends ICUCollatorNormalizer
 {
     @Override
     public byte[] normalize(String s)
     {
         EnumSet<FieldFormatter.eCleanVal> cleanValue = DataUtil.getCleanValForParam("titleSortLower");
         String normalizedTitle = DataUtil.cleanByVal(s, cleanValue);
-        byte[] bytes = normalizedTitle == null ? null : normalizedTitle.getBytes();
-        return bytes;
+        if (normalizedTitle == null) {
+            return null;
+        }
+        return collator.getCollationKey(normalizedTitle).toByteArray();
     }
 }

From 6eccf32726237a92817f03dbd9fcee040f0d7d76 Mon Sep 17 00:00:00 2001
From: Damien <damien-git@users.noreply.github.com>
Date: Thu, 7 Nov 2024 14:56:07 -0500
Subject: [PATCH 2/2] Added TitleNormalizerTest

---
 .../browse/tests/TitleNormalizerTest.java     | 121 ++++++++++++++++++
 1 file changed, 121 insertions(+)
 create mode 100644 tests/org/vufind/solr/browse/tests/TitleNormalizerTest.java

diff --git a/tests/org/vufind/solr/browse/tests/TitleNormalizerTest.java b/tests/org/vufind/solr/browse/tests/TitleNormalizerTest.java
new file mode 100644
index 0000000..74df73d
--- /dev/null
+++ b/tests/org/vufind/solr/browse/tests/TitleNormalizerTest.java
@@ -0,0 +1,121 @@
+package org.vufind.solr.browse.tests;
+
+import static org.junit.Assert.assertArrayEquals;
+import static org.junit.Assert.assertEquals;
+
+import java.util.ArrayList;
+import java.util.Comparator;
+import java.util.Collections;
+import java.util.List;
+
+import org.junit.Before;
+import org.junit.Test;
+import org.junit.runner.RunWith;
+import org.junit.runners.JUnit4;
+
+import org.vufind.util.TitleNormalizer;
+
+public class TitleNormalizerTest
+{
+    private TitleNormalizer titleNormalizer;
+
+    @Before
+    public void setUp()
+    {
+        titleNormalizer = new TitleNormalizer();
+    }
+
+
+    @Test
+    public void sortsSimpleStrings()
+    {
+        assertEquals(listOf("apple", "banana", "cherry", "orange"),
+                     sort(listOf("banana", "orange", "apple", "cherry")));
+    }
+
+
+    @Test
+    public void sortsDiacriticStrings()
+    {
+        assertEquals(listOf("AAA", "Äardvark", "Apple", "Banana", "grapefruit", "Orange"),
+                     sort(listOf("grapefruit", "Apple", "Orange", "AAA", "Äardvark", "Banana")));
+    }
+
+
+    @Test
+    public void handlesHyphensQuotesAndWhitespace()
+    {
+        assertEquals(listOf("AAA", "Äardvark", "Apple", "Banana", "grapefruit",
+                            "\"Hyphenated-words and double quotes\"",
+                            "   inappropriate leading space",
+                            "Orange"),
+                     sort(listOf("Orange",
+                                 "\"Hyphenated-words and double quotes\"",
+                                 "Banana", "grapefruit",
+                                 "   inappropriate leading space",
+                                 "Äardvark", "Apple", "AAA")));
+
+    }
+
+
+    @Test
+    public void sortsUnicodeCharacters()
+    {
+        assertEquals(listOf("apple", "바나나", "チェリー", "橙子"),
+                     sort(listOf("바나나", "橙子", "apple", "チェリー")));
+    }
+
+
+    @Test
+    public void ignoresPunctuationMixedWithSpaces()
+    {
+        assertArrayEquals(titleNormalizer.normalize("wharton, edith"), titleNormalizer.normalize("wharton edith"));
+        assertArrayEquals(titleNormalizer.normalize("st. john"), titleNormalizer.normalize("st john"));
+    }
+
+
+    //
+    // Helpers
+    //
+
+    private List<String> listOf(String ... args)
+    {
+        List<String> result = new ArrayList<String> ();
+        for (String s : args) {
+            result.add(s);
+        }
+
+        return result;
+    }
+
+
+    // http://stackoverflow.com/questions/5108091/java-comparator-for-byte-array-lexicographic
+    private int compareByteArrays(byte[] left, byte[] right)
+    {
+        for (int i = 0, j = 0; i < left.length && j < right.length; i++, j++) {
+            int a = (left[i] & 0xff);
+            int b = (right[j] & 0xff);
+            if (a != b) {
+                return a - b;
+            }
+        }
+        return left.length - right.length;
+    }
+
+
+    private List<String> sort(List<String> list)
+    {
+        List<String> result = new ArrayList<String> ();
+        result.addAll(list);
+
+        Collections.sort(result, new Comparator<String> () {
+            public int compare(String s1, String s2) {
+                return compareByteArrays(titleNormalizer.normalize(s1),
+                                         titleNormalizer.normalize(s2));
+            }
+        });
+
+        return result;
+    }
+
+}