CLDR-18869 Use latest (Aug 5) version of ICU4J, update tests/code (unicode-org#4932)

Author: pedberg-icu

tools/cldr-code/src/main/java/org/unicode/cldr/util/Quoter.java

@@ -13,7 +13,7 @@ public abstract class Quoter {
     private static boolean DEBUG = false;
 
     protected boolean quoting = false;
-    protected StringBuffer output = new StringBuffer();
+    protected StringBuilder output = new StringBuilder();
 
     public void setQuoting(boolean value) {
         quoting = value;
@@ -50,7 +50,7 @@ public String toString() {
 
     /** Implements standard ICU rule quoting */
     public static class RuleQuoter extends Quoter {
-        private StringBuffer quoteBuffer = new StringBuffer();
+        private StringBuilder quoteBuffer = new StringBuilder();
 
         @Override
         public void setQuoting(boolean value) {

tools/cldr-code/src/test/java/org/unicode/cldr/unittest/LanguageTest.java

@@ -159,6 +159,10 @@ public void TestScriptsWithoutLanguage() {
         Set<String> needTransfer = new LinkedHashSet<>();
         Set<String> unicodeScripts = getUnicodeScripts();
         for (String script : unicodeScripts) {
+            if (script.equals("Chis")) {
+                logKnownIssue("ICU-23038", "ICU4J UScript still supports CHISOI");
+                continue;
+            }
             String likely = likelyMap.get("und_" + script);
             if (likely == null) {
                 final String data = script2likely.get(script);

tools/cldr-code/src/test/java/org/unicode/cldr/unittest/LikelySubtagsTest.java

@@ -310,13 +310,17 @@ public void TestForMissingScriptMetadata() {
             int ch = current.charAt(0);
             int script = UScript.getScript(ch);
             String shortName = UScript.getShortName(script);
-            Info i = ScriptMetadata.getInfo(shortName);
-            if (i == null) {
-                errln("Script Metadata is missing: " + shortName);
-                continue;
-            }
-            if (i.likelyLanguage.equals("und") && !exceptions.contains(shortName)) {
-                errln("Script has no likely language: " + shortName);
+            if (shortName.equals("Chis")) {
+                logKnownIssue("ICU-23038", "ICU4J UScript still supports CHISOI");
+            } else {
+                Info i = ScriptMetadata.getInfo(shortName);
+                if (i == null) {
+                    errln("Script Metadata is missing: " + shortName);
+                    continue;
+                }
+                if (i.likelyLanguage.equals("und") && !exceptions.contains(shortName)) {
+                    errln("Script has no likely language: " + shortName);
+                }
             }
             toRemove.applyIntPropertyValue(UProperty.SCRIPT, script);
             current.removeAll(toRemove);

tools/cldr-code/src/test/java/org/unicode/cldr/unittest/TestDataTest.java

@@ -96,6 +96,12 @@ private void checkPersonNameTests(Path filePath) {
             return;
         }
         String localeId = name.substring(0, name.length() - 4);
+        if (localeId.equals("km")) {
+            logKnownIssue(
+                    "CLDR-18870",
+                    "With ICU4J 2025-08-05, testData/personNameTest/km.txt needs updating");
+            return;
+        }
         final PersonNameData pnd = new PersonNameData();
         pnd.pnf = new PersonNameFormatter(FACTORY.make(localeId, true));
         pnd.localeId = localeId;

tools/cldr-code/src/test/java/org/unicode/cldr/unittest/TestScriptMetadata.java

@@ -113,16 +113,13 @@ public void TestScripts() {
         for (int i = UScript.COMMON; i < UScript.CODE_LIMIT; ++i) {
             String longName = UScript.getName(i);
             String shortName = UScript.getShortName(i);
+            if (shortName.equals("Chis")) {
+                logKnownIssue("ICU-23038", "ICU4J UScript still supports CHISOI");
+                continue;
+            }
             Info info = ScriptMetadata.getInfo(i);
             if (info != null) {
                 map.put(info.idUsage, longName + "\t(" + shortName + ")\t" + info);
-            } else if (shortName.equals("Chis")) {
-                // pass:
-                // UTC #184 moved Chisoi from Unicode 17 to Unicode 18
-                // but as of 20250728 CLDR still depends on a version of ICU that
-                // includes UScript.CHISOI.
-                // Its numeric value will be reused for a different script.
-                // TODO: Remove this hack after CLDR has been updated to ICU 78 final.
             } else {
                 // There are many script codes that are not "real"; there are no
                 // Unicode characters for them.
@@ -172,15 +169,6 @@ public void TestShowLanguages() {
         Set<String> bads = new TreeSet<>();
         UnicodeSet temp = new UnicodeSet();
         for (String s : getScriptsToShow(sc, english)) {
-            if (s.equals("Chis")) {
-                // pass:
-                // UTC #184 moved Chisoi from Unicode 17 to Unicode 18
-                // but as of 20250728 CLDR still depends on a version of ICU that
-                // includes UScript.CHISOI.
-                // Its numeric value will be reused for a different script.
-                // TODO: Remove this hack after CLDR has been updated to ICU 78 final.
-                continue;
-            }
             if (ScriptMetadata.getInfo(s) == null) {
                 // There are many script codes that are not "real"; there are no
                 // Unicode characters for them.

tools/cldr-code/src/test/java/org/unicode/cldr/unittest/TestSupplementalInfo.java

@@ -2118,6 +2118,10 @@ public void TestNumberingSystemDigitCompleteness() {
         List<Integer> unicodeDigits = new ArrayList<>();
         for (int cp = UCharacter.MIN_CODE_POINT; cp <= UCharacter.MAX_CODE_POINT; cp++) {
             if (UCharacter.getType(cp) == UCharacterEnums.ECharacterCategory.DECIMAL_DIGIT_NUMBER) {
+                if (UScript.getShortName(UScript.getScript(cp)).equals("Chis")) {
+                    logKnownIssue("ICU-23038", "ICU4J UCharacter still supports CHISOI");
+                    continue;
+                }
                 unicodeDigits.add(cp);
             }
         }

tools/pom.xml

@@ -25,7 +25,7 @@
 			release candidate and changes to a version like nn.1-SNAPSHOT, we should just use
 			that so we are always getting the latest version pushed (and should not have CLDR
 			compatibility issues at that point). -->
-		<icu4j.version>78.0.1-20250521.091503-4</icu4j.version> <!-- before ICU rc, specific dated version -->
+		<icu4j.version>78.0.1-20250805.181531-5</icu4j.version> <!-- before ICU rc, specific dated version -->
 		<!--<icu4j.version>78.1-SNAPSHOT</icu4j.version>--> <!-- after ICU rc, latest published version -->
 		<junit.jupiter.version>5.8.2</junit.jupiter.version>
 		<maven-surefire-plugin-version>3.3.1</maven-surefire-plugin-version>