8284842: Update Unicode Data Files to Version 15.0.0

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

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2009, 2020, Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 2009, 2022, 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
@@ -25,7 +25,7 @@
 
 /*
  *******************************************************************************
- *   Copyright (C) 2009-2014, International Business Machines
+ *   Copyright (C) 2009-2015, International Business Machines
  *   Corporation and others.  All Rights Reserved.
  *******************************************************************************
  */
@@ -556,8 +556,8 @@ public String getDecomposition(int c) {
     public static final int MIN_YES_YES_WITH_CC=0xfe02;
     public static final int JAMO_VT=0xfe00;
     public static final int MIN_NORMAL_MAYBE_YES=0xfc00;
-    public static final int JAMO_L=2;  // offset=1 hasCompBoundaryAfter=FALSE
-    public static final int INERT=1;  // offset=0 hasCompBoundaryAfter=TRUE
+    public static final int JAMO_L=2;  // offset=1 hasCompBoundaryAfter=false
+    public static final int INERT=1;  // offset=0 hasCompBoundaryAfter=true
 
     // norm16 bit 0 is comp-boundary-after.
     public static final int HAS_COMP_BOUNDARY_AFTER=1;

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

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2005, 2020, Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 2005, 2022, 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
@@ -24,7 +24,7 @@
  */
 /*
  *******************************************************************************
- * Copyright (C) 1996-2011, International Business Machines Corporation and    *
+ * Copyright (C) 1996-2015, International Business Machines Corporation and    *
  * others. All Rights Reserved.                                                *
  *******************************************************************************
  */
@@ -246,8 +246,8 @@ public static boolean isUnprintable(int c) {
      * Escape unprintable characters using <backslash>uxxxx notation
      * for U+0000 to U+FFFF and <backslash>Uxxxxxxxx for U+10000 and
      * above.  If the character is printable ASCII, then do nothing
-     * and return FALSE.  Otherwise, append the escaped notation and
-     * return TRUE.
+     * and return false.  Otherwise, append the escaped notation and
+     * return true.
      */
     public static <T extends Appendable> boolean escapeUnprintable(T result, int c) {
         try {

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

@@ -117,7 +117,7 @@ static void setTrailingWSStart(BidiBase bidiBase)
            are already set to paragraph level.
            Setting trailingWSStart to pBidi->length will avoid changing the
            level of B chars from 0 to paraLevel in getLevels when
-           orderParagraphsLTR==TRUE
+           orderParagraphsLTR==true
         */
         if (dirProps[start - 1] == BidiBase.B) {
             bidiBase.trailingWSStart = start;   /* currently == bidiBase.length */

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

@@ -54,7 +54,7 @@ public final class VersionInfo
      * @deprecated This API is ICU internal only.
      */
     @Deprecated
-    public static final String ICU_DATA_VERSION_PATH = "70b";
+    public static final String ICU_DATA_VERSION_PATH = "72b";
 
     // public methods ------------------------------------------------------
 

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

@@ -35,8 +35,8 @@ 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 14.0.
-     * (http://www.unicode.org/reports/tr29/tr29-38.html)
+     * is based on the annex for Unicode version 15.0.
+     * (http://www.unicode.org/reports/tr29/tr29-40.html)
      *
      * @param src the {@code CharSequence} to be scanned
      * @param off offset to start looking for the next boundary in the src
@@ -277,6 +277,7 @@ static int getType(int cp) {
                 case 0x11A88:
                 case 0x11A89:
                 case 0x11D46:
+                case 0x11F02:
                     return PREPEND;
             }
         }

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

@@ -1,10 +1,10 @@
-# Blocks-14.0.0.txt
-# Date: 2021-01-22, 23:29:00 GMT [KW]
-# Copyright (c) 2021 Unicode, Inc.
-# For terms of use, see http://www.unicode.org/terms_of_use.html
+# Blocks-15.0.0.txt
+# Date: 2022-01-28, 20:58:00 GMT [KW]
+# Copyright (c) 2022 Unicode, Inc.
+# For terms of use, see https://www.unicode.org/terms_of_use.html
 #
 # Unicode Character Database
-# For documentation, see http://www.unicode.org/reports/tr44/
+# For documentation, see https://www.unicode.org/reports/tr44/
 #
 # Format:
 # Start Code..End Code; Block Name
@@ -15,7 +15,7 @@
 #         and underbars are ignored.
 #         For example, "Latin Extended-A" and "latin extended a" are equivalent.
 #         For more information on the comparison of property values,
-#            see UAX #44: http://www.unicode.org/reports/tr44/
+#            see UAX #44: https://www.unicode.org/reports/tr44/
 #
 #  All block ranges start with a value where (cp MOD 16) = 0,
 #  and end with a value where (cp MOD 16) = 15. In other words,
@@ -241,6 +241,7 @@ FFF0..FFFF; Specials
 10D00..10D3F; Hanifi Rohingya
 10E60..10E7F; Rumi Numeral Symbols
 10E80..10EBF; Yezidi
+10EC0..10EFF; Arabic Extended-C
 10F00..10F2F; Old Sogdian
 10F30..10F6F; Sogdian
 10F70..10FAF; Old Uyghur
@@ -272,19 +273,21 @@ FFF0..FFFF; Specials
 11A50..11AAF; Soyombo
 11AB0..11ABF; Unified Canadian Aboriginal Syllabics Extended-A
 11AC0..11AFF; Pau Cin Hau
+11B00..11B5F; Devanagari Extended-A
 11C00..11C6F; Bhaiksuki
 11C70..11CBF; Marchen
 11D00..11D5F; Masaram Gondi
 11D60..11DAF; Gunjala Gondi
 11EE0..11EFF; Makasar
+11F00..11F5F; Kawi
 11FB0..11FBF; Lisu Supplement
 11FC0..11FFF; Tamil Supplement
 12000..123FF; Cuneiform
 12400..1247F; Cuneiform Numbers and Punctuation
 12480..1254F; Early Dynastic Cuneiform
 12F90..12FFF; Cypro-Minoan
 13000..1342F; Egyptian Hieroglyphs
-13430..1343F; Egyptian Hieroglyph Format Controls
+13430..1345F; Egyptian Hieroglyph Format Controls
 14400..1467F; Anatolian Hieroglyphs
 16800..16A3F; Bamum Supplement
 16A40..16A6F; Mro
@@ -309,16 +312,19 @@ FFF0..FFFF; Specials
 1D000..1D0FF; Byzantine Musical Symbols
 1D100..1D1FF; Musical Symbols
 1D200..1D24F; Ancient Greek Musical Notation
+1D2C0..1D2DF; Kaktovik Numerals
 1D2E0..1D2FF; Mayan Numerals
 1D300..1D35F; Tai Xuan Jing Symbols
 1D360..1D37F; Counting Rod Numerals
 1D400..1D7FF; Mathematical Alphanumeric Symbols
 1D800..1DAAF; Sutton SignWriting
 1DF00..1DFFF; Latin Extended-G
 1E000..1E02F; Glagolitic Supplement
+1E030..1E08F; Cyrillic Extended-D
 1E100..1E14F; Nyiakeng Puachue Hmong
 1E290..1E2BF; Toto
 1E2C0..1E2FF; Wancho
+1E4D0..1E4FF; Nag Mundari
 1E7E0..1E7FF; Ethiopic Extended-B
 1E800..1E8DF; Mende Kikakui
 1E900..1E95F; Adlam
@@ -348,6 +354,7 @@ FFF0..FFFF; Specials
 2CEB0..2EBEF; CJK Unified Ideographs Extension F
 2F800..2FA1F; CJK Compatibility Ideographs Supplement
 30000..3134F; CJK Unified Ideographs Extension G
+31350..323AF; CJK Unified Ideographs Extension H
 E0000..E007F; Tags
 E0100..E01EF; Variation Selectors Supplement
 F0000..FFFFF; Supplementary Private Use Area-A