8307547: Support variant collations

Reviewed-by: srl, jlu, alanb

src/java.base/share/classes/java/text/Collator.java

@@ -41,7 +41,6 @@ package java.text;
 import java.lang.ref.SoftReference;
 import java.text.spi.CollatorProvider;
 import java.util.Locale;
-import java.util.ResourceBundle;
 import java.util.concurrent.ConcurrentHashMap;
 import java.util.concurrent.ConcurrentMap;
 import sun.util.locale.provider.LocaleProviderAdapter;
@@ -71,7 +70,6 @@ import sun.util.locale.provider.LocaleServiceProviderPool;
  * <p>
  * The following example shows how to compare two strings using
  * the {@code Collator} for the default locale.
- * <blockquote>
  * {@snippet lang=java :
  * // Compare two strings in the default locale
  * Collator myCollator = Collator.getInstance();
@@ -81,7 +79,6 @@ import sun.util.locale.provider.LocaleServiceProviderPool;
  *     System.out.println("abc is greater than or equal to ABC");
  * }
  * }
- * </blockquote>
  *
  * <p>
  * You can set a {@code Collator}'s <em>strength</em> property
@@ -94,7 +91,6 @@ import sun.util.locale.provider.LocaleServiceProviderPool;
  * "e" and "E" are tertiary differences and "e" and "e" are identical.
  * The following shows how both case and accents could be ignored for
  * US English.
- * <blockquote>
  * {@snippet lang=java :
  * // Get the Collator for US English and set its strength to PRIMARY
  * Collator usCollator = Collator.getInstance(Locale.US);
@@ -103,7 +99,6 @@ import sun.util.locale.provider.LocaleServiceProviderPool;
  *     System.out.println("Strings are equivalent");
  * }
  * }
- * </blockquote>
  * <p>
  * For comparing {@code String}s exactly once, the {@code compare}
  * method provides the best performance. When sorting a list of
@@ -114,7 +109,7 @@ import sun.util.locale.provider.LocaleServiceProviderPool;
  * against other {@code CollationKey}s. A {@code CollationKey} is
  * created by a {@code Collator} object for a given {@code String}.
  * <br>
- * <strong>Note:</strong> {@code CollationKey}s from different
+ * @apiNote {@code CollationKey}s from different
  * {@code Collator}s can not be compared. See the class description
  * for {@link CollationKey}
  * for an example using {@code CollationKey}s.
@@ -222,7 +217,7 @@ public abstract class Collator
 
     /**
      * Gets the Collator for the current default locale.
-     * The default locale is determined by java.util.Locale.getDefault.
+     * The default locale is determined by {@link Locale#getDefault()}.
      * @return the Collator for the default locale.(for example, en_US)
      * @see java.util.Locale#getDefault
      */
@@ -232,6 +227,19 @@ public abstract class Collator
 
     /**
      * Gets the Collator for the desired locale.
+     * @apiNote Implementations of {@code Collator} class may produce
+     * different instances based on the "{@code co}"
+     * <a href="https://www.unicode.org/reports/tr35/#UnicodeCollationIdentifier">
+     * Unicode collation identifier</a> in the {@code desiredLocale}.
+     * For example:
+     * {@snippet lang = java:
+     * Collator.getInstance(Locale.forLanguageTag("sv-u-co-trad"));
+     * }
+     * may return a {@code Collator} instance with the Swedish traditional sorting, which
+     * gives 'v' and 'w' the same sorting order, while the {@code Collator} instance
+     * for the Swedish locale without "co" identifier distinguishes 'v' and 'w'.
+     * @spec https://www.unicode.org/reports/tr35/ Unicode Locale Data Markup Language
+     *     (LDML)
      * @param desiredLocale the desired locale.
      * @return the Collator for the desired locale.
      * @see java.util.Locale

src/java.base/share/classes/sun/util/locale/provider/LocaleResources.java

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2012, 2022, Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 2012, 2023, Oracle and/or its affiliates. All rights reserved.
  * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
  *
  * This code is free software; you can redistribute it and/or modify it
@@ -86,7 +86,7 @@ public class LocaleResources {
     // cache key prefixes
     private static final String BREAK_ITERATOR_INFO = "BII.";
     private static final String CALENDAR_DATA = "CALD.";
-    private static final String COLLATION_DATA_CACHEKEY = "COLD";
+    private static final String COLLATION_DATA = "COLD.";
     private static final String DECIMAL_FORMAT_SYMBOLS_DATA_CACHEKEY = "DFSD";
     private static final String CURRENCY_NAMES = "CN.";
     private static final String LOCALE_NAMES = "LN.";
@@ -186,17 +186,25 @@ public class LocaleResources {
 
     public String getCollationData() {
         String key = "Rule";
+        String cacheKey = COLLATION_DATA;
         String coldata = "";
 
+        try {
+            var type = locale.getUnicodeLocaleType("co");
+            if (type != null && !type.isEmpty() && !type.equalsIgnoreCase("standard")) {
+                key += "." + type;
+                cacheKey += type;
+            }
+        } catch (IllegalArgumentException ignore) {}
+
         removeEmptyReferences();
-        ResourceReference data = cache.get(COLLATION_DATA_CACHEKEY);
+        ResourceReference data = cache.get(cacheKey);
         if (data == null || ((coldata = (String) data.get()) == null)) {
             ResourceBundle rb = localeData.getCollationData(locale);
             if (rb.containsKey(key)) {
                 coldata = rb.getString(key);
             }
-            cache.put(COLLATION_DATA_CACHEKEY,
+            cache.put(cacheKey, new ResourceReference(cacheKey, coldata, referenceQueue));
-                      new ResourceReference(COLLATION_DATA_CACHEKEY, coldata, referenceQueue));
         }
 
         return coldata;

src/jdk.localedata/share/classes/sun/text/resources/ext/CollationData_sv.java

@@ -54,6 +54,16 @@ public class CollationData_sv extends ListResourceBundle {
                 "< o\u030b , O\u030b ; \u00f8 , \u00d8 " +   // o-double-acute < o-stroke
                 "& Y, u\u0308 , U\u0308" + // u-double-acute
                 "; u\u030b, U\u030b "
+            },
+            {"Rule.trad",
+                "& Z < a\u030a , A\u030a" +  // a-ring, aa ligaure
+                "< a\u0308 , A\u0308 < a\u030b, A\u030b " +  // a-umlaut, a-double-acute
+                "< \u00e6 , \u00c6 " +                   //  ae ligature
+                "< o\u0308 , O\u0308 " +   // o-umlaut
+                "< o\u030b , O\u030b ; \u00f8 , \u00d8 " +   // o-double-acute < o-stroke
+                "& V ; w , W" +
+                "& Y, u\u0308 , U\u0308" + // u-double-acute
+                "; u\u030b, U\u030b "
             }
         };
     }

test/jdk/sun/text/resources/Collator/SwedishTest.java

@@ -23,23 +23,50 @@
 
 /*
  * @test
- * @bug 8306927
+ * @bug 8306927 8307547
  * @modules jdk.localedata
  * @summary Tests Swedish collation involving 'v' and 'w'.
+ * @run junit SwedishTest
  */
 
 import java.text.Collator;
 import java.util.Arrays;
 import java.util.Locale;
+import java.util.stream.Stream;
+
+import org.junit.jupiter.api.Test;
+import org.junit.jupiter.params.ParameterizedTest;
+import org.junit.jupiter.params.provider.Arguments;
+import org.junit.jupiter.params.provider.MethodSource;
+import static org.junit.jupiter.api.Assertions.assertArrayEquals;
 
 public class SwedishTest {
     private static final String[] src = {"wb", "va", "vc"};
-    private static final String[] expected = {"va", "vc", "wb"};
+    private static final String[] standard = {"va", "vc", "wb"};
+    private static final String[] traditional = {"va", "wb", "vc"};
 
-    public static void main (String[] args) {
+    @ParameterizedTest
-        Arrays.sort(src, Collator.getInstance(Locale.of("sv")));
+    @MethodSource("swedishData")
-        if (!Arrays.equals(src, expected)) {
+    public void testSwedishCollation(Locale l, String[] expected) {
-            throw new RuntimeException("Swedish collation failed");
+        Arrays.sort(src, Collator.getInstance(l));
+        assertArrayEquals(expected, src);
     }
+
+    private static Stream<Arguments> swedishData() {
+        return Stream.of(
+            Arguments.of(Locale.forLanguageTag("sv"), standard),
+            Arguments.of(Locale.forLanguageTag("sv-u-co-standard"), standard),
+            Arguments.of(Locale.forLanguageTag("sv-u-co-STANDARD"), standard),
+            Arguments.of(Locale.forLanguageTag("sv-u-co-traditio"), standard),
+            Arguments.of(Locale.forLanguageTag("sv-u-co-TRADITIO"), standard),
+            Arguments.of(Locale.forLanguageTag("sv-u-co-traditional"), standard),
+            Arguments.of(Locale.forLanguageTag("sv-u-co-TRADITIONAL"), standard),
+            // the new standard used to be called "reformed"
+            Arguments.of(Locale.forLanguageTag("sv-u-co-reformed"), standard),
+            Arguments.of(Locale.forLanguageTag("sv-u-co-REFORMED"), standard),
+
+            Arguments.of(Locale.forLanguageTag("sv-u-co-trad"), traditional),
+            Arguments.of(Locale.forLanguageTag("sv-u-co-TRAD"), traditional)
+        );
     }
 }