8346944: Update Unicode Data Files to 17.0.0

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

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 1996, 2023, Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 1996, 2025, 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
@@ -661,7 +661,7 @@ private int nextContractChar(int ch)
 
         // (the Normalizer is cloned here so that the seeking we do in the next loop
         // won't affect our real position in the text)
-        NormalizerBase tempText = (NormalizerBase)text.clone();
+        NormalizerBase tempText = text.clone();
 
         // extract the next maxLength characters in the string (we have to do this using the
         // Normalizer to ensure that our offsets correspond to those the rest of the
@@ -732,7 +732,7 @@ private int prevContractChar(int ch)
         pair = list.lastElement();
         int maxLength = pair.entryName.length();
 
-        NormalizerBase tempText = (NormalizerBase)text.clone();
+        NormalizerBase tempText = text.clone();
 
         tempText.next();
         key.setLength(0);

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

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2005, 2020, Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 2005, 2025, 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
@@ -47,7 +47,7 @@
  * @author ram
  */
 
-public class CharacterIteratorWrapper extends UCharacterIterator {
+public class CharacterIteratorWrapper extends UCharacterIterator implements Cloneable {
 
     private CharacterIterator iterator;
 
@@ -135,7 +135,7 @@ public int getText(char[] fillIn, int offset){
      * Creates a clone of this iterator.  Clones the underlying character iterator.
      * @see UCharacterIterator#clone()
      */
-    public Object clone(){
+    public CharacterIteratorWrapper clone(){
         try {
             CharacterIteratorWrapper result = (CharacterIteratorWrapper) super.clone();
             result.iterator = (CharacterIterator)this.iterator.clone();

src/java.base/share/classes/jdk/internal/icu/impl/Norm2AllModes.java

@@ -269,8 +269,8 @@ private static final class Norm2AllModesSingleton {
         private Norm2AllModesSingleton(String name) {
             try {
                 @SuppressWarnings("deprecation")
-                String DATA_FILE_NAME = "/jdk/internal/icu/impl/data/icudt" +
-                    VersionInfo.ICU_DATA_VERSION_PATH + "/" + name + ".nrm";
+                String DATA_FILE_NAME = "/jdk/internal/icu/impl/data/icudata/" +
+                    name + ".nrm";
                 NormalizerImpl impl=new NormalizerImpl().load(DATA_FILE_NAME);
                 allModes=new Norm2AllModes(impl);
             } catch (RuntimeException e) {

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

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2005, 2020, Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 2005, 2025, 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
@@ -51,7 +51,7 @@
  *
  * What are first, last, and getBeginIndex doing here?!?!?!
  */
-public class ReplaceableUCharacterIterator extends UCharacterIterator {
+public class ReplaceableUCharacterIterator extends UCharacterIterator implements Cloneable {
 
     // public constructor ------------------------------------------------------
 
@@ -86,9 +86,9 @@ public ReplaceableUCharacterIterator(StringBuffer buf){
      * <code>Replaceable</code>object
      * @return copy of this iterator
      */
-    public Object clone(){
+    public ReplaceableUCharacterIterator clone(){
         try {
-          return super.clone();
+          return (ReplaceableUCharacterIterator) super.clone();
         } catch (CloneNotSupportedException e) {
             return null; // never invoked
         }

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

@@ -201,9 +201,7 @@ public final int getPairedBracket(int c) {
     // data format constants ----------------------------------------------- ***
     @SuppressWarnings("deprecation")
     private static final String DATA_FILE_NAME =
-            "/jdk/internal/icu/impl/data/icudt" +
-            VersionInfo.ICU_DATA_VERSION_PATH +
-            "/ubidi.icu";
+            "/jdk/internal/icu/impl/data/icudata/ubidi.icu";
 
     /* format "BiDi" */
     private static final int FMT=0x42694469;

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

@@ -330,9 +330,7 @@ public int digit(int c) {
      */
     @SuppressWarnings("deprecation")
     private static final String DATA_FILE_NAME_ =
-            "/jdk/internal/icu/impl/data/icudt" +
-            VersionInfo.ICU_DATA_VERSION_PATH +
-            "/uprops.icu";
+            "/jdk/internal/icu/impl/data/icudata/uprops.icu";
 
     /**
      * Shift value for lead surrogate to form a supplementary character.

src/java.base/share/classes/jdk/internal/icu/text/NormalizerBase.java

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2005, 2022, Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 2005, 2025, 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
@@ -420,10 +420,10 @@ public NormalizerBase(CharacterIterator iter, Mode mode) {
      * iterator's {@code clone} method does so.
      * @stable ICU 2.8
      */
-    public Object clone() {
+    public NormalizerBase clone() {
         try {
             NormalizerBase copy = (NormalizerBase) super.clone();
-            copy.text = (UCharacterIterator) text.clone();
+            copy.text = text.clone();
             copy.mode = mode;
             copy.options = options;
             copy.norm2 = norm2;

src/java.base/share/classes/jdk/internal/icu/text/UCharacterIterator.java

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2003, 2022, Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 2003, 2025, 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
@@ -310,8 +310,8 @@ public int moveCodePointIndex(int delta){
      * @return copy of this iterator
      * @stable ICU 2.4
      */
-    public Object clone() throws CloneNotSupportedException{
-        return super.clone();
+    public UCharacterIterator clone() throws CloneNotSupportedException{
+        return (UCharacterIterator) super.clone();
     }
 
 }

src/java.base/share/classes/jdk/internal/icu/text/UnicodeSet.java

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2005, 2022, Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 2005, 2025, 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
@@ -293,7 +293,7 @@
  * @author Alan Liu
  * @stable ICU 2.0
  */
-public class UnicodeSet {
+public class UnicodeSet implements Cloneable {
 
     private static final int LOW = 0x000000; // LOW <= all valid values. ZERO for codepoints
     private static final int HIGH = 0x110000; // HIGH > all valid values. 10000 for code units.
@@ -385,6 +385,18 @@ public UnicodeSet(String pattern) {
         applyPattern(pattern, null);
     }
 
+    /**
+     * Return a new set that is equivalent to this one.
+     * @stable ICU 2.0
+     */
+    @Override
+    public UnicodeSet clone() {
+        if (isFrozen()) {
+            return this;
+        }
+        return new UnicodeSet(this);
+    }
+
     /**
      * Make this object represent the same set as <code>other</code>.
      * @param other a <code>UnicodeSet</code> whose value will be

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

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2005, 2024, Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 2005, 2025, 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
@@ -54,7 +54,7 @@ public final class VersionInfo
      * @deprecated This API is ICU internal only.
      */
     @Deprecated
-    public static final String ICU_DATA_VERSION_PATH = "76b";
+    public static final String ICU_DATA_VERSION_PATH = "78b";
 
     // public methods ------------------------------------------------------
 

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

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016, 2024, Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 2016, 2025, 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 16.0.
+     * is based on the annex for Unicode version 17.0.
      *
-     * @spec http://www.unicode.org/reports/tr29/tr29-45.html
+     * @spec http://www.unicode.org/reports/tr29/tr29-47.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)
@@ -283,7 +283,6 @@ static int getType(int cp) {
                 case 0x113D1:
                 case 0x1193F:
                 case 0x11941:
-                case 0x11A3A:
                 case 0x11A84:
                 case 0x11A85:
                 case 0x11A86:

src/java.base/share/classes/jdk/internal/util/regex/IndicConjunctBreak.java.template

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2023, Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 2023, 2025, 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
@@ -49,8 +49,9 @@ final class IndicConjunctBreak {
     }
 
     static boolean isConsonant(int cp) {
-        // fast check - Devanagari to Malayalam
-        if (cp < 0x0900 || cp > 0x0D7F) {
+        // fast check - return false for code points below
+        // the Devanagari range (lowest among Indic scripts)
+        if (cp < 0x0900) {
             return false;
         }
 

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

@@ -1,6 +1,6 @@
-# Blocks-16.0.0.txt
-# Date: 2024-02-02
-# Copyright (c) 2024 Unicode, Inc.
+# Blocks-17.0.0.txt
+# Date: 2025-08-01
+# © 2025 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
 #
@@ -228,6 +228,7 @@ FFF0..FFFF; Specials
 108E0..108FF; Hatran
 10900..1091F; Phoenician
 10920..1093F; Lydian
+10940..1095F; Sidetic
 10980..1099F; Meroitic Hieroglyphs
 109A0..109FF; Meroitic Cursive
 10A00..10A5F; Kharoshthi
@@ -279,11 +280,13 @@ FFF0..FFFF; Specials
 11AB0..11ABF; Unified Canadian Aboriginal Syllabics Extended-A
 11AC0..11AFF; Pau Cin Hau
 11B00..11B5F; Devanagari Extended-A
+11B60..11B7F; Sharada Supplement
 11BC0..11BFF; Sunuwar
 11C00..11C6F; Bhaiksuki
 11C70..11CBF; Marchen
 11D00..11D5F; Masaram Gondi
 11D60..11DAF; Gunjala Gondi
+11DB0..11DEF; Tolong Siki
 11EE0..11EFF; Makasar
 11F00..11F5F; Kawi
 11FB0..11FBF; Lisu Supplement
@@ -304,12 +307,14 @@ FFF0..FFFF; Specials
 16B00..16B8F; Pahawh Hmong
 16D40..16D7F; Kirat Rai
 16E40..16E9F; Medefaidrin
+16EA0..16EDF; Beria Erfe
 16F00..16F9F; Miao
 16FE0..16FFF; Ideographic Symbols and Punctuation
 17000..187FF; Tangut
 18800..18AFF; Tangut Components
 18B00..18CFF; Khitan Small Script
 18D00..18D7F; Tangut Supplement
+18D80..18DFF; Tangut Components Supplement
 1AFF0..1AFFF; Kana Extended-B
 1B000..1B0FF; Kana Supplement
 1B100..1B12F; Kana Extended-A
@@ -318,6 +323,7 @@ FFF0..FFFF; Specials
 1BC00..1BC9F; Duployan
 1BCA0..1BCAF; Shorthand Format Controls
 1CC00..1CEBF; Symbols for Legacy Computing Supplement
+1CEC0..1CEFF; Miscellaneous Symbols Supplement
 1CF00..1CFCF; Znamenny Musical Notation
 1D000..1D0FF; Byzantine Musical Symbols
 1D100..1D1FF; Musical Symbols
@@ -336,6 +342,7 @@ FFF0..FFFF; Specials
 1E2C0..1E2FF; Wancho
 1E4D0..1E4FF; Nag Mundari
 1E5D0..1E5FF; Ol Onal
+1E6C0..1E6FF; Tai Yo
 1E7E0..1E7FF; Ethiopic Extended-B
 1E800..1E8DF; Mende Kikakui
 1E900..1E95F; Adlam
@@ -367,6 +374,7 @@ FFF0..FFFF; Specials
 2F800..2FA1F; CJK Compatibility Ideographs Supplement
 30000..3134F; CJK Unified Ideographs Extension G
 31350..323AF; CJK Unified Ideographs Extension H
+323B0..3347F; CJK Unified Ideographs Extension J
 E0000..E007F; Tags
 E0100..E01EF; Variation Selectors Supplement
 F0000..FFFFF; Supplementary Private Use Area-A

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

@@ -1,6 +1,6 @@
-# CaseFolding-16.0.0.txt
-# Date: 2024-04-30, 21:48:11 GMT
-# © 2024 Unicode®, Inc.
+# CaseFolding-17.0.0.txt
+# Date: 2025-07-30, 23:54:36 GMT
+# © 2025 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
 #
@@ -18,15 +18,15 @@
 # The data supports both implementations that require simple case foldings
 # (where string lengths don't change), and implementations that allow full case folding
 # (where string lengths may grow). Note that where they can be supported, the
-# full case foldings are superior: for example, they allow "MASSE" and "Maße" to match.
+# full case foldings are superior: for example, they allow "FUSS" and "Fuß" to match.
 #
 # All code points not listed in this file map to themselves.
 #
 # NOTE: case folding does not preserve normalization formats!
 #
 # For information on case folding, including how to have case folding
-# preserve normalization formats, see Section 3.13 Default Case Algorithms in
-# The Unicode Standard.
+# preserve normalization formats, see the
+# "Conformance" / "Default Case Algorithms" section of the core specification.
 #
 # ================================================================================
 # Format
@@ -1243,7 +1243,10 @@ A7C7; C; A7C8; # LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY
 A7C9; C; A7CA; # LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY
 A7CB; C; 0264; # LATIN CAPITAL LETTER RAMS HORN
 A7CC; C; A7CD; # LATIN CAPITAL LETTER S WITH DIAGONAL STROKE
+A7CE; C; A7CF; # LATIN CAPITAL LETTER PHARYNGEAL VOICED FRICATIVE
 A7D0; C; A7D1; # LATIN CAPITAL LETTER CLOSED INSULAR G
+A7D2; C; A7D3; # LATIN CAPITAL LETTER DOUBLE THORN
+A7D4; C; A7D5; # LATIN CAPITAL LETTER DOUBLE WYNN
 A7D6; C; A7D7; # LATIN CAPITAL LETTER MIDDLE SCOTS S
 A7D8; C; A7D9; # LATIN CAPITAL LETTER SIGMOID S
 A7DA; C; A7DB; # LATIN CAPITAL LETTER LAMBDA
@@ -1616,6 +1619,31 @@ FF3A; C; FF5A; # FULLWIDTH LATIN CAPITAL LETTER Z
 16E5D; C; 16E7D; # MEDEFAIDRIN CAPITAL LETTER O
 16E5E; C; 16E7E; # MEDEFAIDRIN CAPITAL LETTER AI
 16E5F; C; 16E7F; # MEDEFAIDRIN CAPITAL LETTER Y
+16EA0; C; 16EBB; # BERIA ERFE CAPITAL LETTER ARKAB
+16EA1; C; 16EBC; # BERIA ERFE CAPITAL LETTER BASIGNA
+16EA2; C; 16EBD; # BERIA ERFE CAPITAL LETTER DARBAI
+16EA3; C; 16EBE; # BERIA ERFE CAPITAL LETTER EH
+16EA4; C; 16EBF; # BERIA ERFE CAPITAL LETTER FITKO
+16EA5; C; 16EC0; # BERIA ERFE CAPITAL LETTER GOWAY
+16EA6; C; 16EC1; # BERIA ERFE CAPITAL LETTER HIRDEABO
+16EA7; C; 16EC2; # BERIA ERFE CAPITAL LETTER I
+16EA8; C; 16EC3; # BERIA ERFE CAPITAL LETTER DJAI
+16EA9; C; 16EC4; # BERIA ERFE CAPITAL LETTER KOBO
+16EAA; C; 16EC5; # BERIA ERFE CAPITAL LETTER LAKKO
+16EAB; C; 16EC6; # BERIA ERFE CAPITAL LETTER MERI
+16EAC; C; 16EC7; # BERIA ERFE CAPITAL LETTER NINI
+16EAD; C; 16EC8; # BERIA ERFE CAPITAL LETTER GNA
+16EAE; C; 16EC9; # BERIA ERFE CAPITAL LETTER NGAY
+16EAF; C; 16ECA; # BERIA ERFE CAPITAL LETTER OI
+16EB0; C; 16ECB; # BERIA ERFE CAPITAL LETTER PI
+16EB1; C; 16ECC; # BERIA ERFE CAPITAL LETTER ERIGO
+16EB2; C; 16ECD; # BERIA ERFE CAPITAL LETTER ERIGO TAMURA
+16EB3; C; 16ECE; # BERIA ERFE CAPITAL LETTER SERI
+16EB4; C; 16ECF; # BERIA ERFE CAPITAL LETTER SHEP
+16EB5; C; 16ED0; # BERIA ERFE CAPITAL LETTER TATASOUE
+16EB6; C; 16ED1; # BERIA ERFE CAPITAL LETTER UI
+16EB7; C; 16ED2; # BERIA ERFE CAPITAL LETTER WASSE
+16EB8; C; 16ED3; # BERIA ERFE CAPITAL LETTER AY
 1E900; C; 1E922; # ADLAM CAPITAL LETTER ALIF
 1E901; C; 1E923; # ADLAM CAPITAL LETTER DAALI
 1E902; C; 1E924; # ADLAM CAPITAL LETTER LAAM
@@ -1651,4 +1679,4 @@ FF3A; C; FF5A; # FULLWIDTH LATIN CAPITAL LETTER Z
 1E920; C; 1E942; # ADLAM CAPITAL LETTER KPO
 1E921; C; 1E943; # ADLAM CAPITAL LETTER SHA
 #
-# EOF
+# EOF