8305681: Allow additional characters for GB18030-2022 (Level 2) support

naotoj · Justin Lu · naotoj · commit 3d9e8d05e053 · 2023-05-10T17:15:52.000Z
Co-authored-by: Justin Lu &lt;jlu@openjdk.org&gt;
Reviewed-by: lancea, iris, rriggs
Backport-of: b08cddec8625424b1292051088513a60606ef1e9
diff --git a/jdk/make/data/characterdata/CharacterData02.java.template b/jdk/make/data/characterdata/CharacterData02.java.template
@@ -103,11 +103,21 @@ class CharacterData02 extends CharacterData {
     }
 
     boolean isJavaIdentifierStart(int ch) {
+        // isJavaIdentifierStart strictly conforms to code points assigned
+        // in Unicode 6.2.
+        if(Character.UnicodeBlock.of(ch) ==
+            Character.UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E)
+            return false;
         int props = getProperties(ch);
         return ((props & $$maskIdentifierInfo) >= $$lowJavaStart);
     }
 
     boolean isJavaIdentifierPart(int ch) {
+        // isJavaIdentifierPart strictly conforms to code points assigned
+        // in Unicode 6.2.
+        if(Character.UnicodeBlock.of(ch) ==
+            Character.UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E)
+            return false;
         int props = getProperties(ch);
         return ((props & $$nonzeroJavaPart) != 0);
     }
diff --git a/jdk/make/data/unicodedata/UnicodeData.txt b/jdk/make/data/unicodedata/UnicodeData.txt
@@ -23550,6 +23550,8 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;;
 2B734;<CJK Ideograph Extension C, Last>;Lo;0;L;;;;;N;;;;;
 2B740;<CJK Ideograph Extension D, First>;Lo;0;L;;;;;N;;;;;
 2B81D;<CJK Ideograph Extension D, Last>;Lo;0;L;;;;;N;;;;;
+2B820;<CJK Ideograph Extension E, First>;Lo;0;L;;;;;N;;;;;
+2CEA1;<CJK Ideograph Extension E, Last>;Lo;0;L;;;;;N;;;;;
 2F800;CJK COMPATIBILITY IDEOGRAPH-2F800;Lo;0;L;4E3D;;;;N;;;;;
 2F801;CJK COMPATIBILITY IDEOGRAPH-2F801;Lo;0;L;4E38;;;;N;;;;;
 2F802;CJK COMPATIBILITY IDEOGRAPH-2F802;Lo;0;L;4E41;;;;N;;;;;
diff --git a/jdk/src/share/classes/java/lang/Character.java b/jdk/src/share/classes/java/lang/Character.java
@@ -58,8 +58,10 @@
  * block from version 10.0 of the Unicode Standard. Second, the Java SE 8 Platform
  * allows an implementation of class {@code Character} to use the code points
  * in the range of {@code U+9FCD} to {@code U+9FEF} from version 11.0 of the
- * Unicode Standard, in order for the class to allow the "Implementation
- * Level 1" of the Chinese GB18030-2022 standard. Third, the Java SE 8 Platform
+ * Unicode Standard and in the {@code CJK Unified Ideographs Extension E} block
+ * from version 8.0 of the Unicode Standard, in order for the class to allow the
+ * "Implementation Level 2" of the Chinese GB18030-2022 standard.
+ * Third, the Java SE 8 Platform
  * allows an implementation of class {@code Character} to use the Japanese Era
  * code point, {@code U+32FF}, from the Unicode Standard version 12.1.
  * Consequently, the
@@ -2575,7 +2577,18 @@ private UnicodeBlock(String idName, String... aliases) {
                              "ARABIC MATHEMATICAL ALPHABETIC SYMBOLS",
                              "ARABICMATHEMATICALALPHABETICSYMBOLS");
 
-        private static final int[] blockStarts = {
+        /**
+         * Constant for the "CJK Unified Ideographs Extension E" Unicode
+         * character block.
+         * @apiNote This field is defined in Java SE 8 Maintenance Release 5.
+         * @since 1.8
+         */
+        public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E =
+                new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E",
+                        "CJK UNIFIED IDEOGRAPHS EXTENSION E",
+                        "CJKUNIFIEDIDEOGRAPHSEXTENSIONE");
+
+        private static final int blockStarts[] = {
             0x0000,   // 0000..007F; Basic Latin
             0x0080,   // 0080..00FF; Latin-1 Supplement
             0x0100,   // 0100..017F; Latin Extended-A
@@ -2823,7 +2836,8 @@ private UnicodeBlock(String idName, String... aliases) {
             0x2A6E0,  //               unassigned
             0x2A700,  // 2A700..2B73F; CJK Unified Ideographs Extension C
             0x2B740,  // 2B740..2B81F; CJK Unified Ideographs Extension D
-            0x2B820,  //               unassigned
+            0x2B820,  // 2B820..2CEAF; CJK Unified Ideographs Extension E
+            0x2CEB0,  //               unassigned
             0x2F800,  // 2F800..2FA1F; CJK Compatibility Ideographs Supplement
             0x2FA20,  //               unassigned
             0xE0000,  // E0000..E007F; Tags
@@ -3082,6 +3096,7 @@ private UnicodeBlock(String idName, String... aliases) {
             null,
             CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C,
             CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D,
+            CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E,
             null,
             CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT,
             null,
diff --git a/jdk/test/java/lang/Character/CheckScript.java b/jdk/test/java/lang/Character/CheckScript.java
@@ -1,6 +1,6 @@
 
 /*
- * Copyright (c) 2010, 2012, Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 2010, 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
@@ -24,7 +24,7 @@
 
 /**
  * @test
- * @bug 6945564 6959267 7033561 7070436 7198195
+ * @bug 6945564 6959267 7033561 7070436 7198195 8305681
  * @summary  Check that the j.l.Character.UnicodeScript
  */
 
diff --git a/jdk/test/java/lang/Character/Scripts.txt b/jdk/test/java/lang/Character/Scripts.txt
@@ -1439,9 +1439,10 @@ FA70..FAD9    ; Han # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILI
 20000..2A6D6  ; Han # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6
 2A700..2B734  ; Han # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734
 2B740..2B81D  ; Han # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
+2B820..2CEA1  ; Han # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
 2F800..2FA1D  ; Han # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
 
-# Total code points: 75998
+# Total code points: 81760
 
 # ================================================
 
diff --git a/jdk/test/java/lang/Character/TestIsJavaIdentifierMethods.java b/jdk/test/java/lang/Character/TestIsJavaIdentifierMethods.java
@@ -25,19 +25,26 @@
  * @test
  * @summary Test behavior of isJavaIdentifierXX, testIsJavaLetter, and
  *  testIsJavaLetterOrDigit methods for all code points.
- * @bug 8218915
+ * @bug 8218915 8301400 8305681
  */
 
 public class TestIsJavaIdentifierMethods {
     // Unassigned code points not present in Unicode 6.2 (which Java SE 8
     // is based upon), including: various currency symbol sign code points
-    // (Nordic Mark ... Bitcoin), Japanese Era Square character code point,
-    // and 35 CJK Unified Ideograph code points from GB18030-2022
+    // (Nordic Mark ... Bitcoin), the Japanese Era Square character code point, and
+    // code points for GB1030-2022 level 1 and 2 implementation including
+    // (35 code points from CJK Unified Ideographs and all of CJK Unified Ideographs
+    // Extension E).
     private static final int CS_SIGNS_CODEPOINT_START = 0x20BB;
     private static final int CS_SIGNS_CODEPOINT_END = 0x20BF;
     private static final int JAPANESE_ERA_CODEPOINT = 0x32FF;
-    private static final int GB18030_2022_CODEPOINT_START = 0x9FCD;
-    private static final int GB18030_2022_CODEPOINT_END = 0x9FEF;
+    // GB18030_2022 Code Points
+    private static final int CJK_GB18030_LEVEL1_START = 0x9FCD;
+    private static final int CJK_GB18030_LEVEL1_END = 0x9FEF;
+    // Extension E code points are greater than U+FFFF,
+    // and thus only the int methods need to be tested
+    private static final int CJK_EXTENSION_E_START = 0x2B820;
+    private static final int CJK_EXTENSION_E_END = 0x2CEAF;
 
     public static void main(String[] args) {
         testIsJavaIdentifierPart_int();
@@ -77,7 +84,8 @@ public static void testIsJavaIdentifierPart_int() {
             // value of variable "expected" is considered false.
             if (cp != JAPANESE_ERA_CODEPOINT &&
                     !(cp >= CS_SIGNS_CODEPOINT_START && cp <= CS_SIGNS_CODEPOINT_END) &&
-                    !(cp >= GB18030_2022_CODEPOINT_START && cp <= GB18030_2022_CODEPOINT_END)) {
+                    !(cp >= CJK_GB18030_LEVEL1_START && cp <= CJK_GB18030_LEVEL1_END) &&
+                    !(cp >= CJK_EXTENSION_E_START && cp <= CJK_EXTENSION_E_END)) {
                 byte type = (byte) Character.getType(cp);
                 expected = Character.isLetter(cp)
                         || type == Character.CURRENCY_SYMBOL
@@ -125,7 +133,7 @@ public static void testIsJavaIdentifierPart_char() {
             // value of variable "expected" is considered false.
             if (i != JAPANESE_ERA_CODEPOINT &&
                     !(i >= CS_SIGNS_CODEPOINT_START && i <= CS_SIGNS_CODEPOINT_END) &&
-                    !(i >= GB18030_2022_CODEPOINT_START && i <= GB18030_2022_CODEPOINT_END)) {
+                    !(i >= CJK_GB18030_LEVEL1_START && i <= CJK_GB18030_LEVEL1_END)) {
                 byte type = (byte) Character.getType(ch);
                 expected = Character.isLetter(ch)
                         || type == Character.CURRENCY_SYMBOL
@@ -168,7 +176,8 @@ public static void testIsJavaIdentifierStart_int() {
             // value of variable "expected" is considered false.
             if (cp != JAPANESE_ERA_CODEPOINT &&
                     !(cp >= CS_SIGNS_CODEPOINT_START && cp <= CS_SIGNS_CODEPOINT_END) &&
-                    !(cp >= GB18030_2022_CODEPOINT_START && cp <= GB18030_2022_CODEPOINT_END)) {
+                    !(cp >= CJK_GB18030_LEVEL1_START && cp <= CJK_GB18030_LEVEL1_END) &&
+                    !(cp >= CJK_EXTENSION_E_START && cp <= CJK_EXTENSION_E_END)) {
                 byte type = (byte) Character.getType(cp);
                 expected = Character.isLetter(cp)
                         || type == Character.LETTER_NUMBER
@@ -208,7 +217,7 @@ public static void testIsJavaIdentifierStart_char() {
             // value of variable "expected" is considered false.
             if (i != JAPANESE_ERA_CODEPOINT &&
                     !(i >= CS_SIGNS_CODEPOINT_START && i <= CS_SIGNS_CODEPOINT_END) &&
-                    !(i >= GB18030_2022_CODEPOINT_START && i <= GB18030_2022_CODEPOINT_END)) {
+                    !(i >= CJK_GB18030_LEVEL1_START && i <= CJK_GB18030_LEVEL1_END)) {
                 byte type = (byte) Character.getType(ch);
                 expected = Character.isLetter(ch)
                         || type == Character.LETTER_NUMBER
@@ -248,7 +257,7 @@ public static void testIsJavaLetter() {
             // value of variable "expected" is considered false.
             if (i != JAPANESE_ERA_CODEPOINT &&
                     !(i >= CS_SIGNS_CODEPOINT_START && i <= CS_SIGNS_CODEPOINT_END) &&
-                    !(i >= GB18030_2022_CODEPOINT_START && i <= GB18030_2022_CODEPOINT_END)) {
+                    !(i >= CJK_GB18030_LEVEL1_START && i <= CJK_GB18030_LEVEL1_END)) {
                 byte type = (byte) Character.getType(ch);
                 expected = Character.isLetter(ch)
                         || type == Character.LETTER_NUMBER
@@ -292,7 +301,7 @@ public static void testIsJavaLetterOrDigit() {
             // value of variable "expected" is considered false.
             if (i != JAPANESE_ERA_CODEPOINT &&
                     !(i >= CS_SIGNS_CODEPOINT_START && i <= CS_SIGNS_CODEPOINT_END) &&
-                    !(i >= GB18030_2022_CODEPOINT_START && i <= GB18030_2022_CODEPOINT_END)) {
+                    !(i >= CJK_GB18030_LEVEL1_START && i <= CJK_GB18030_LEVEL1_END)) {
                 byte type = (byte) Character.getType(ch);
                 expected = Character.isLetter(ch)
                         || type == Character.CURRENCY_SYMBOL
