8291660: Grapheme support in BreakIterator

make/jdk/src/classes/build/tools/generatebreakiteratordata/GenerateBreakIteratorData.java

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2003, 2020, Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 2003, 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
@@ -94,25 +94,20 @@ private static void generateFiles() throws Exception {
         rules = (ResourceBundle) Class.forName(
             localizedBundleName("sun.text.resources", "BreakIteratorRules")).getDeclaredConstructor().newInstance();
 
-        if (info.containsKey("CharacterData")) {
-            generateDataFile(info.getString("CharacterData"),
-                             rules.getString("CharacterBreakRules"),
-                             classNames[0]);
-        }
         if (info.containsKey("WordData")) {
             generateDataFile(info.getString("WordData"),
                              rules.getString("WordBreakRules"),
-                             classNames[1]);
+                             classNames[0]);
         }
         if (info.containsKey("LineData")) {
             generateDataFile(info.getString("LineData"),
                              rules.getString("LineBreakRules"),
-                             classNames[2]);
+                             classNames[1]);
         }
         if (info.containsKey("SentenceData")) {
             generateDataFile(info.getString("SentenceData"),
                              rules.getString("SentenceBreakRules"),
-                             classNames[3]);
+                             classNames[2]);
         }
     }
 

make/modules/java.base/gensrc/GensrcEmojiData.gmk

@@ -24,12 +24,12 @@
 #
 
 #
-# Rules to create $(SUPPORT_OUTPUTDIR)/gensrc/java.base/java/util/regex/EmojiData.java
+# Rules to create $(SUPPORT_OUTPUTDIR)/gensrc/java.base/jdk/internal/util/regex/EmojiData.java
 #
 
-GENSRC_EMOJIDATA := $(SUPPORT_OUTPUTDIR)/gensrc/java.base/java/util/regex/EmojiData.java
+GENSRC_EMOJIDATA := $(SUPPORT_OUTPUTDIR)/gensrc/java.base/jdk/internal/util/regex/EmojiData.java
 
-EMOJIDATATEMP = $(MODULE_SRC)/share/classes/java/util/regex/EmojiData.java.template
+EMOJIDATATEMP = $(MODULE_SRC)/share/classes/jdk/internal/util/regex/EmojiData.java.template
 UNICODEDATA = $(MODULE_SRC)/share/data/unicodedata
 
 $(GENSRC_EMOJIDATA): $(BUILD_TOOLS_JDK) $(EMOJIDATATEMP) $(UNICODEDATA)/emoji/emoji-data.txt

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

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 1996, 2021, Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 1996, 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
@@ -99,6 +99,12 @@
  * and a diacritical mark. What users consider to be a character can
  * differ between languages.
  *
+ * @implSpec The default implementation of the character boundary analysis
+ * conforms to the Unicode Consortium's Extended Grapheme Cluster breaks.
+ * For more detail, refer to
+ * <a href="https://www.unicode.org/reports/tr29/#Grapheme_Cluster_Boundaries">
+ * Grapheme Cluster Boundaries</a> section in the Unicode Standard Annex #29.
+ *
  * <p>
  * The {@code BreakIterator} instances returned by the factory methods
  * of this class are intended for use with natural languages only, not for

src/java.base/share/classes/java/util/regex/Pattern.java

@@ -44,6 +44,7 @@
 import java.util.stream.StreamSupport;
 
 import jdk.internal.util.ArraysSupport;
+import jdk.internal.util.regex.Grapheme;
 
 /**
  * A compiled representation of a regular expression.

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

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2019, Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 2019, 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
@@ -23,7 +23,7 @@
  * questions.
  */
 
-package java.util.regex;
+package jdk.internal.util.regex;
 
 /**
  * Holds data contained in the Unicode Technical Standard #51: Unicode

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

@@ -23,11 +23,11 @@
  * questions.
  */
 
-package java.util.regex;
+package jdk.internal.util.regex;
 
 import java.util.Objects;
 
-final class Grapheme {
+public final class Grapheme {
 
     /**
      * Look for the next extended grapheme cluster boundary in a CharSequence.
@@ -43,7 +43,7 @@ final class Grapheme {
      * @param limit limit offset in the src (exclusive)
      * @return the next grapheme boundary
      */
-    static int nextBoundary(CharSequence src, int off, int limit) {
+    public static int nextBoundary(CharSequence src, int off, int limit) {
         Objects.checkFromToIndex(off, limit, src.length());
 
         int ch0 = Character.codePointAt(src, off);

src/java.base/share/classes/sun/text/resources/BreakIteratorInfo.java

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2003, 2005, Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 2003, 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
@@ -50,15 +50,13 @@ protected final Object[][] getContents() {
             // built-in type of BreakIterator
             {"BreakIteratorClasses",
                 new String[] {
-                    "RuleBasedBreakIterator",  // character-break iterator class
                     "RuleBasedBreakIterator",  // word-break iterator class
                     "RuleBasedBreakIterator",  // line-break iterator class
                     "RuleBasedBreakIterator"   // sentence-break iterator class
                 }
             },
 
             // Rules filename for each break-iterator
-            {"CharacterData", "CharacterBreakIteratorData"},
             {"WordData",      "WordBreakIteratorData"},
             {"LineData",      "LineBreakIteratorData"},
             {"SentenceData",  "SentenceBreakIteratorData"},

src/java.base/share/classes/sun/text/resources/BreakIteratorRules.java

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 1999, 2021, Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 1999, 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
@@ -67,53 +67,6 @@
 public class BreakIteratorRules extends ListResourceBundle {
     protected final Object[][] getContents() {
         return new Object[][] {
-            // rules describing how to break between logical characters
-            { "CharacterBreakRules",
-
-              // ignore non-spacing marks and enclosing marks (since we never
-              // put a break before ignore characters, this keeps combining
-              // accents with the base characters they modify)
-              "<enclosing>=[:Mn::Me:];"
-
-              // other category definitions
-              + "<choseong>=[\u1100-\u115f];"
-              + "<jungseong>=[\u1160-\u11a7];"
-              + "<jongseong>=[\u11a8-\u11ff];"
-              + "<surr-hi>=[\ud800-\udbff];"
-              + "<surr-lo>=[\udc00-\udfff];"
-
-              // break after every character, except as follows:
-              + ".;"
-
-              // keep base and combining characters togethers
-              + "<base>=[^<enclosing>^[:Cc::Cf::Zl::Zp:]];"
-              + "<base><enclosing><enclosing>*;"
-
-              // keep CRLF sequences together
-              + "\r\n;"
-
-              // keep surrogate pairs together
-              + "<surr-hi><surr-lo>;"
-
-              // keep Hangul syllables spelled out using conjoining jamo together
-              + "<choseong>*<jungseong>*<jongseong>*;"
-
-              // various additions for Hindi support
-              + "<nukta>=[\u093c];"
-              + "<danda>=[\u0964\u0965];"
-              + "<virama>=[\u094d];"
-              + "<devVowelSign>=[\u093e-\u094c\u0962\u0963];"
-              + "<devConsonant>=[\u0915-\u0939];"
-              + "<devNuktaConsonant>=[\u0958-\u095f];"
-              + "<devCharEnd>=[\u0902\u0903\u0951-\u0954];"
-              + "<devCAMN>=(<devConsonant>{<nukta>});"
-              + "<devConsonant1>=(<devNuktaConsonant>|<devCAMN>);"
-              + "<zwj>=[\u200d];"
-              + "<devConjunct>=({<devConsonant1><virama>{<zwj>}}<devConsonant1>);"
-              + "<devConjunct>{<devVowelSign>}{<devCharEnd>};"
-              + "<danda><nukta>;"
-            },
-
             // default rules for finding word boundaries
             { "WordBreakRules",
               // ignore non-spacing marks, enclosing marks, and format characters,