8319993: Update Unicode Data Files to 16.0.0

8319992: Update ICU4J to Version 76.1

Reviewed-by: jlu, joehw, iris

src/java.base/share/classes/java/lang/CharacterData00.java.template

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2003, 2023, Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 2003, 2024, 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
@@ -382,6 +382,8 @@ class CharacterData00 extends CharacterData {
             case 0xA7B3: mapChar = 0xAB53; break;
             case 0xA7C5: mapChar = 0x0282; break;
             case 0xA7C6: mapChar = 0x1D8E; break;
+            case 0xA7CB: mapChar = 0x0264; break;
+            case 0xA7DC: mapChar = 0x019B; break;
               // default mapChar is already set, so no
               // need to redo it here.
               // default       : mapChar = ch;
@@ -403,13 +405,15 @@ class CharacterData00 extends CharacterData {
           if ((val & $$maskCaseOffset) == $$maskCaseOffset) {
             switch(ch) {
             case 0x017F: mapChar = 0x0053; break;
+            case 0x019B: mapChar = 0xA7DC; break;
             case 0x023F: mapChar = 0x2C7E; break;
             case 0x0240: mapChar = 0x2C7F; break;
             case 0x0250: mapChar = 0x2C6F; break;
             case 0x0251: mapChar = 0x2C6D; break;
             case 0x0252: mapChar = 0x2C70; break;
             case 0x025C: mapChar = 0xA7AB; break;
             case 0x0261: mapChar = 0xA7AC; break;
+            case 0x0264: mapChar = 0xA7CB; break;
             case 0x0265: mapChar = 0xA78D; break;
             case 0x0266: mapChar = 0xA7AA; break;
             case 0x026A: mapChar = 0xA7AE; break;
@@ -857,13 +861,15 @@ class CharacterData00 extends CharacterData {
             else {
                 switch(ch) {
                     case 0x017F: mapChar = 0x0053; break;
+                    case 0x019B: mapChar = 0xA7DC; break;
                     case 0x023F: mapChar = 0x2C7E; break;
                     case 0x0240: mapChar = 0x2C7F; break;
                     case 0x0250: mapChar = 0x2C6F; break;
                     case 0x0251: mapChar = 0x2C6D; break;
                     case 0x0252: mapChar = 0x2C70; break;
                     case 0x025C: mapChar = 0xA7AB; break;
                     case 0x0261: mapChar = 0xA7AC; break;
+                    case 0x0264: mapChar = 0xA7CB; break;
                     case 0x0265: mapChar = 0xA78D; break;
                     case 0x0266: mapChar = 0xA7AA; break;
                     case 0x026A: mapChar = 0xA7AE; break;

src/java.base/share/classes/jdk/internal/icu/impl/UCharacterProperty.java

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2005, 2020, Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 2005, 2024, 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
@@ -40,6 +40,7 @@
 import jdk.internal.icu.lang.UCharacter.NumericType;
 import jdk.internal.icu.text.UTF16;
 import jdk.internal.icu.text.UnicodeSet;
+import jdk.internal.icu.util.CodePointTrie;
 import jdk.internal.icu.util.VersionInfo;
 
 /**
@@ -136,10 +137,8 @@ public int getAdditional(int codepoint, int column) {
      */
     public VersionInfo getAge(int codepoint)
     {
-        int version = getAdditional(codepoint, 0) >> AGE_SHIFT_;
-        return VersionInfo.getInstance(
-                           (version >> FIRST_NIBBLE_SHIFT_) & LAST_NIBBLE_MASK_,
-                           version & LAST_NIBBLE_MASK_, 0, 0);
+        int version = getAdditional(codepoint, 0) >>> AGE_SHIFT_;
+        return VersionInfo.getInstance(version >> 2, version & 3, 0, 0);
     }
 
     // int-value and enumerated properties --------------------------------- ***
@@ -150,7 +149,11 @@ public int getType(int c) {
 
     /*
      * Map some of the Grapheme Cluster Break values to Hangul Syllable Types.
-     * Hangul_Syllable_Type is fully redundant with a subset of Grapheme_Cluster_Break.
+     * Hangul_Syllable_Type used to be fully redundant with a subset of Grapheme_Cluster_Break.
+     *
+     * Starting with Unicode 16, this is no longer true for HST=V vs. GCB=V in some cases:
+     * Some Kirat Rai vowels are given GCB=V for proper grapheme clustering, but
+     * they are of course not related to Hangul syllables.
      */
     private static final int /* UHangulSyllableType */ gcbToHst[]={
         HangulSyllableType.NOT_APPLICABLE,   /* U_GCB_OTHER */
@@ -310,11 +313,16 @@ public int digit(int c) {
      * 0
      */
      int m_maxJTGValue_;
+    /** maximum values for other code values */
+    int m_maxValuesOther_;
+
     /**
      * Script_Extensions data
      */
     public char[] m_scriptExtensions_;
 
+    CodePointTrie m_blockTrie_;
+
     // private variables -------------------------------------------------
 
     /**
@@ -534,12 +542,13 @@ private UCharacterProperty() throws IOException
         int additionalVectorsOffset = bytes.getInt();
         m_additionalColumnsCount_ = bytes.getInt();
         int scriptExtensionsOffset = bytes.getInt();
-        int reservedOffset7 = bytes.getInt();
-        /* reservedOffset8 = */ bytes.getInt();
+        int blockTrieOffset = bytes.getInt();
+        int reservedOffset8 = bytes.getInt();
         /* dataTopOffset = */ bytes.getInt();
         m_maxBlockScriptValue_ = bytes.getInt();
         m_maxJTGValue_ = bytes.getInt();
-        ICUBinary.skipBytes(bytes, (16 - 12) << 2);
+        m_maxValuesOther_ = bytes.getInt();
+        ICUBinary.skipBytes(bytes, (16 - 13) << 2);
 
         // read the main properties trie
         m_trie_ = Trie2_16.createFromSerialized(bytes);
@@ -574,19 +583,29 @@ private UCharacterProperty() throws IOException
         }
 
         // Script_Extensions
-        int numChars = (reservedOffset7 - scriptExtensionsOffset) * 2;
+        int numChars = (blockTrieOffset - scriptExtensionsOffset) * 2;
         if(numChars > 0) {
             m_scriptExtensions_ = new char[numChars];
             for(int i = 0; i < numChars; ++i) {
                 m_scriptExtensions_[i] = bytes.getChar();
             }
         }
+
+        // Read the blockTrie.
+        int partLength = (reservedOffset8 - blockTrieOffset) * 4;
+        int triePosition = bytes.position();
+        m_blockTrie_ = CodePointTrie.fromBinary(null, CodePointTrie.ValueWidth.BITS_16, bytes);
+        trieLength = bytes.position() - triePosition;
+        if (trieLength > partLength) {
+            throw new IOException("uprops.icu: not enough bytes for blockTrie");
+        }
+        ICUBinary.skipBytes(bytes, partLength - trieLength);  // skip padding after trie bytes
     }
 
     private static final class IsAcceptable implements ICUBinary.Authenticate {
         // @Override when we switch to Java 6
         public boolean isDataVersionAcceptable(byte version[]) {
-            return version[0] == 7;
+            return version[0] == 9;
         }
     }
 

src/java.base/share/classes/jdk/internal/icu/util/VersionInfo.java

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2005, 2022, Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 2005, 2024, 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
@@ -36,7 +36,7 @@
 
 package jdk.internal.icu.util;
 
-import java.util.HashMap;
+import java.util.concurrent.ConcurrentHashMap;
 
 /**
  * Class to store version numbers of the form major.minor.milli.micro.
@@ -48,13 +48,13 @@ public final class VersionInfo
     // public data members -------------------------------------------------
 
     /**
-     * Data version string for ICU's internal data.
-     * Used for appending to data path (e.g. icudt43b)
+     * Data version string for ICU's data file.
+     * Not used when loading from resources packaged in the .jar.
      * @internal
      * @deprecated This API is ICU internal only.
      */
     @Deprecated
-    public static final String ICU_DATA_VERSION_PATH = "74b";
+    public static final String ICU_DATA_VERSION_PATH = "76b";
 
     // public methods ------------------------------------------------------
 
@@ -171,7 +171,7 @@ public int compareTo(VersionInfo other)
     /**
      * Map of singletons
      */
-    private static final HashMap<Integer, Object> MAP_ = new HashMap<>();
+    private static final ConcurrentHashMap<Integer, Object> MAP_ = new ConcurrentHashMap<>();
     /**
      * Error statement string
      */

src/java.base/share/classes/jdk/internal/util/regex/Grapheme.java

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016, 2023, Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 2016, 2024, 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
@@ -35,9 +35,9 @@ public final class Grapheme {
      * <p>
      * See Unicode Standard Annex #29 Unicode Text Segmentation for the specification
      * for the extended grapheme cluster boundary rules. The following implementation
-     * is based on the annex for Unicode version 15.1.
+     * is based on the annex for Unicode version 16.0.
      *
-     * @spec http://www.unicode.org/reports/tr29/tr29-43.html
+     * @spec http://www.unicode.org/reports/tr29/tr29-45.html
      * @param src the {@code CharSequence} to be scanned
      * @param off offset to start looking for the next boundary in the src
      * @param limit limit offset in the src (exclusive)
@@ -267,7 +267,10 @@ static int getType(int cp) {
             if (cp >= 0xA960 && cp <= 0xA97C)
                 return L;
             //  hangul jamo_extended B
-            if (cp >= 0xD7B0 && cp <= 0xD7C6)
+            //  Kirat Rai vowel sign
+            if (cp >= 0xD7B0 && cp <= 0xD7C6 ||
+                cp == 0x16D63 ||
+                cp >= 0x16D67 && cp <= 0x16D6A)
                 return V;
             if (cp >= 0xD7CB && cp <= 0xD7FB)
                 return T;
@@ -277,6 +280,7 @@ static int getType(int cp) {
                 case 0x0D4E:
                 case 0x111C2:
                 case 0x111C3:
+                case 0x113D1:
                 case 0x1193F:
                 case 0x11941:
                 case 0x11A3A:

src/java.base/share/data/unicodedata/Blocks.txt

@@ -1,7 +1,8 @@
-# Blocks-15.1.0.txt
-# Date: 2023-07-28, 15:47:20 GMT
-# Copyright (c) 2023 Unicode, Inc.
-# For terms of use, see https://www.unicode.org/terms_of_use.html
+# Blocks-16.0.0.txt
+# Date: 2024-02-02
+# Copyright (c) 2024 Unicode, Inc.
+# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
+# For terms of use and license, see https://www.unicode.org/terms_of_use.html
 #
 # Unicode Character Database
 # For documentation, see https://www.unicode.org/reports/tr44/
@@ -217,6 +218,7 @@ FFF0..FFFF; Specials
 10500..1052F; Elbasan
 10530..1056F; Caucasian Albanian
 10570..105BF; Vithkuqi
+105C0..105FF; Todhri
 10600..1077F; Linear A
 10780..107BF; Latin Extended-F
 10800..1083F; Cypriot Syllabary
@@ -239,6 +241,7 @@ FFF0..FFFF; Specials
 10C00..10C4F; Old Turkic
 10C80..10CFF; Old Hungarian
 10D00..10D3F; Hanifi Rohingya
+10D40..10D8F; Garay
 10E60..10E7F; Rumi Numeral Symbols
 10E80..10EBF; Yezidi
 10EC0..10EFF; Arabic Extended-C
@@ -258,12 +261,14 @@ FFF0..FFFF; Specials
 11280..112AF; Multani
 112B0..112FF; Khudawadi
 11300..1137F; Grantha
+11380..113FF; Tulu-Tigalari
 11400..1147F; Newa
 11480..114DF; Tirhuta
 11580..115FF; Siddham
 11600..1165F; Modi
 11660..1167F; Mongolian Supplement
 11680..116CF; Takri
+116D0..116FF; Myanmar Extended-C
 11700..1174F; Ahom
 11800..1184F; Dogra
 118A0..118FF; Warang Citi
@@ -274,6 +279,7 @@ FFF0..FFFF; Specials
 11AB0..11ABF; Unified Canadian Aboriginal Syllabics Extended-A
 11AC0..11AFF; Pau Cin Hau
 11B00..11B5F; Devanagari Extended-A
+11BC0..11BFF; Sunuwar
 11C00..11C6F; Bhaiksuki
 11C70..11CBF; Marchen
 11D00..11D5F; Masaram Gondi
@@ -288,12 +294,15 @@ FFF0..FFFF; Specials
 12F90..12FFF; Cypro-Minoan
 13000..1342F; Egyptian Hieroglyphs
 13430..1345F; Egyptian Hieroglyph Format Controls
+13460..143FF; Egyptian Hieroglyphs Extended-A
 14400..1467F; Anatolian Hieroglyphs
+16100..1613F; Gurung Khema
 16800..16A3F; Bamum Supplement
 16A40..16A6F; Mro
 16A70..16ACF; Tangsa
 16AD0..16AFF; Bassa Vah
 16B00..16B8F; Pahawh Hmong
+16D40..16D7F; Kirat Rai
 16E40..16E9F; Medefaidrin
 16F00..16F9F; Miao
 16FE0..16FFF; Ideographic Symbols and Punctuation
@@ -308,6 +317,7 @@ FFF0..FFFF; Specials
 1B170..1B2FF; Nushu
 1BC00..1BC9F; Duployan
 1BCA0..1BCAF; Shorthand Format Controls
+1CC00..1CEBF; Symbols for Legacy Computing Supplement
 1CF00..1CFCF; Znamenny Musical Notation
 1D000..1D0FF; Byzantine Musical Symbols
 1D100..1D1FF; Musical Symbols
@@ -325,6 +335,7 @@ FFF0..FFFF; Specials
 1E290..1E2BF; Toto
 1E2C0..1E2FF; Wancho
 1E4D0..1E4FF; Nag Mundari
+1E5D0..1E5FF; Ol Onal
 1E7E0..1E7FF; Ethiopic Extended-B
 1E800..1E8DF; Mende Kikakui
 1E900..1E95F; Adlam