Mercurial Mercurial > jdk-sandbox / changeset
summary | shortlog | changelog | graph | tags | bookmarks | branches | files | changeset | raw | help
Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
8143282: \p{Cn} unassigned code points should be included in \p{C}
authorsherman
Fri, 20 May 2016 12:47:41 -0700
changeset 38450 516990ff3a4c
parent 38449 f9026e7a6321
child 38451 a98523f5cbff
8143282: \p{Cn} unassigned code points should be included in \p{C} Summary: to add unassigned cp support into \p{C} Reviewed-by: martin
jdk/src/java.base/share/classes/java/util/regex/CharPredicates.java file | annotate | diff | comparison | revisions
jdk/test/java/util/regex/RegExTest.java file | annotate | diff | comparison | revisions 
--- a/jdk/src/java.base/share/classes/java/util/regex/CharPredicates.java	Fri May 20 20:27:28 2016 +0200
+++ b/jdk/src/java.base/share/classes/java/util/regex/CharPredicates.java	Fri May 20 12:47:41 2016 -0700
@@ -302,7 +302,8 @@
         defCategory("C", ((1<<Character.CONTROL)     |
                           (1<<Character.FORMAT)      |
                           (1<<Character.PRIVATE_USE) |
-                          (1<<Character.SURROGATE))); // Other
+                          (1<<Character.SURROGATE)   |
+                          (1<<Character.UNASSIGNED))); // Other
         defCategory("P", ((1<<Character.DASH_PUNCTUATION)      |
                           (1<<Character.START_PUNCTUATION)     |
                           (1<<Character.END_PUNCTUATION)       |
--- a/jdk/test/java/util/regex/RegExTest.java	Fri May 20 20:27:28 2016 +0200
+++ b/jdk/test/java/util/regex/RegExTest.java	Fri May 20 12:47:41 2016 -0700
@@ -34,7 +34,7 @@
  * 7067045 7014640 7189363 8007395 8013252 8013254 8012646 8023647 6559590
  * 8027645 8035076 8039124 8035975 8074678 6854417 8143854 8147531 7071819
  * 8151481 4867170 7080302 6728861 6995635 6736245 4916384
- * 6328855 6192895 6345469 6988218 6693451 7006761 8140212
+ * 6328855 6192895 6345469 6988218 6693451 7006761 8140212 8143282
  *
  * @library /lib/testlibrary
  * @build jdk.testlibrary.*
@@ -4345,12 +4345,13 @@
         Matcher definedP = Pattern.compile("\\p{IsAssigned}").matcher("");
         Matcher nonCCPP = Pattern.compile("\\p{IsNoncharacterCodePoint}").matcher("");
         Matcher joinCrtl = Pattern.compile("\\p{IsJoinControl}").matcher("");
-
         // javaMethod
         Matcher lowerJ  = Pattern.compile("\\p{javaLowerCase}").matcher("");
         Matcher upperJ  = Pattern.compile("\\p{javaUpperCase}").matcher("");
         Matcher alphaJ  = Pattern.compile("\\p{javaAlphabetic}").matcher("");
         Matcher ideogJ  = Pattern.compile("\\p{javaIdeographic}").matcher("");
+        // GC/C
+        Matcher gcC  = Pattern.compile("\\p{C}").matcher("");
 
         for (int cp = 1; cp < 0x30000; cp++) {
             String str = new String(Character.toChars(cp));
@@ -4416,8 +4417,14 @@
                 Character.isIdeographic(cp) != ideogJ.reset(str).matches() ||
                 (Character.UNASSIGNED == type) == definedP.reset(str).matches() ||
                 POSIX_Unicode.isNoncharacterCodePoint(cp) != nonCCPP.reset(str).matches() ||
-                POSIX_Unicode.isJoinControl(cp) != joinCrtl.reset(str).matches())
+                POSIX_Unicode.isJoinControl(cp) != joinCrtl.reset(str).matches() ||
+                // gc_C
+                (Character.CONTROL == type || Character.FORMAT == type ||
+                 Character.PRIVATE_USE == type || Character.SURROGATE == type ||
+                 Character.UNASSIGNED == type)
+                != gcC.reset(str).matches()) {
                 failCount++;
+            }
         }
 
         // bounds/word align
jdk-sandbox