From 5cf142f972db9a658d768ba3eac42c29916545aa Mon Sep 17 00:00:00 2001
From: Robert Muir <rmuir@apache.org>
Date: Tue, 13 Jul 2021 23:11:18 -0400
Subject: [PATCH] LUCENE-5595: re-enable TestICUNormalizer2CharFilter random
 test, splitting by mode (#211)

Re-enable the randomized testing here, but with a separate test for each
mode rather than all in one method. It gives better testing and also easier-to-debug
testing.
---
 .../icu/TestICUNormalizer2CharFilter.java     | 69 +++++++++++++++++--
 1 file changed, 64 insertions(+), 5 deletions(-)

diff --git a/lucene/analysis/icu/src/test/org/apache/lucene/analysis/icu/TestICUNormalizer2CharFilter.java b/lucene/analysis/icu/src/test/org/apache/lucene/analysis/icu/TestICUNormalizer2CharFilter.java
index 79b1dfe68f6..9026701b70e 100644
--- a/lucene/analysis/icu/src/test/org/apache/lucene/analysis/icu/TestICUNormalizer2CharFilter.java
+++ b/lucene/analysis/icu/src/test/org/apache/lucene/analysis/icu/TestICUNormalizer2CharFilter.java
@@ -321,9 +321,47 @@ public class TestICUNormalizer2CharFilter extends BaseTokenStreamTestCase {
         16);
   }
 
-  @AwaitsFix(bugUrl = "https://issues.apache.org/jira/browse/LUCENE-5595")
-  public void testRandomStrings() throws IOException {
-    // nfkc_cf
+  public void testRandomStringsNFC() throws IOException {
+    Analyzer a =
+        new Analyzer() {
+          @Override
+          protected TokenStreamComponents createComponents(String fieldName) {
+            return new TokenStreamComponents(new MockTokenizer(MockTokenizer.WHITESPACE, false));
+          }
+
+          @Override
+          protected Reader initReader(String fieldName, Reader reader) {
+            return new ICUNormalizer2CharFilter(
+                reader, Normalizer2.getInstance(null, "nfc", Normalizer2.Mode.COMPOSE));
+          }
+        };
+    checkRandomData(random(), a, 200 * RANDOM_MULTIPLIER);
+    // huge strings
+    checkRandomData(random(), a, 25 * RANDOM_MULTIPLIER, 8192);
+    a.close();
+  }
+
+  public void testRandomStringsNFKC() throws IOException {
+    Analyzer a =
+        new Analyzer() {
+          @Override
+          protected TokenStreamComponents createComponents(String fieldName) {
+            return new TokenStreamComponents(new MockTokenizer(MockTokenizer.WHITESPACE, false));
+          }
+
+          @Override
+          protected Reader initReader(String fieldName, Reader reader) {
+            return new ICUNormalizer2CharFilter(
+                reader, Normalizer2.getInstance(null, "nfkc", Normalizer2.Mode.COMPOSE));
+          }
+        };
+    checkRandomData(random(), a, 200 * RANDOM_MULTIPLIER);
+    // huge strings
+    checkRandomData(random(), a, 25 * RANDOM_MULTIPLIER, 8192);
+    a.close();
+  }
+
+  public void testRandomStringsNFKC_CF() throws IOException {
     Analyzer a =
         new Analyzer() {
           @Override
@@ -341,9 +379,30 @@ public class TestICUNormalizer2CharFilter extends BaseTokenStreamTestCase {
     // huge strings
     checkRandomData(random(), a, 25 * RANDOM_MULTIPLIER, 8192);
     a.close();
+  }
 
-    // nfkd
-    a =
+  public void testRandomStringsNFD() throws IOException {
+    Analyzer a =
+        new Analyzer() {
+          @Override
+          protected TokenStreamComponents createComponents(String fieldName) {
+            return new TokenStreamComponents(new MockTokenizer(MockTokenizer.WHITESPACE, false));
+          }
+
+          @Override
+          protected Reader initReader(String fieldName, Reader reader) {
+            return new ICUNormalizer2CharFilter(
+                reader, Normalizer2.getInstance(null, "nfc", Normalizer2.Mode.DECOMPOSE));
+          }
+        };
+    checkRandomData(random(), a, 200 * RANDOM_MULTIPLIER);
+    // huge strings
+    checkRandomData(random(), a, 25 * RANDOM_MULTIPLIER, 8192);
+    a.close();
+  }
+
+  public void testRandomStringsNFKD() throws IOException {
+    Analyzer a =
         new Analyzer() {
           @Override
           protected TokenStreamComponents createComponents(String fieldName) {