duerst	2016-07-22 17:13:38 +0900 (Fri, 22 Jul 2016)

  New Revision: 55728

  https://svn.ruby-lang.org/cgi-bin/viewvc.cgi?view=revision&revision=55728

  Log:
    * string.c (String#dump): Change escaping of non-ASCII characters in
      UTF-8 to use upper-case four-digit hexadecimal escapes without braces
      where possible [Feature #12419].
    * test/ruby/test_string.rb (test_dump): Add tests for above.

  Modified files:
    trunk/ChangeLog
    trunk/string.c
    trunk/test/ruby/test_string.rb
Index: string.c
===================================================================
--- string.c	(revision 55727)
+++ string.c	(revision 55728)
@@ -5656,12 +5656,16 @@ rb_str_dump(VALUE str) https://github.com/ruby/ruby/blob/trunk/string.c#L5656
 		len++;
 	    }
 	    else {
-		if (u8 && c > 0x7F) {	/* \u{NN} */
+		if (u8 && c > 0x7F) {	/* \u notation */
 		    int n = rb_enc_precise_mbclen(p-1, pend, enc);
 		    if (MBCLEN_CHARFOUND_P(n)) {
 			unsigned int cc = rb_enc_mbc_to_codepoint(p-1, pend, enc);
-			while (cc >>= 4) len++;
-			len += 5;
+			if (cc <= 0xFFFF)
+			    len += 6;  /* \uXXXX */
+			else if (cc <= 0xFFFFF)
+			    len += 9;  /* \u{XXXXX} */
+			else
+			    len += 10; /* \u{XXXXXX} */
 			p += MBCLEN_CHARFOUND_LEN(n)-1;
 			break;
 		    }
@@ -5734,7 +5738,10 @@ rb_str_dump(VALUE str) https://github.com/ruby/ruby/blob/trunk/string.c#L5738
 		if (MBCLEN_CHARFOUND_P(n)) {
 		    int cc = rb_enc_mbc_to_codepoint(p-1, pend, enc);
 		    p += n;
-		    snprintf(q, qend-q, "u{%x}", cc);
+		    if (cc <= 0xFFFF)
+			snprintf(q, qend-q, "u%04X", cc);    /* \uXXXX */
+		    else
+			snprintf(q, qend-q, "u{%X}", cc);  /* \u{XXXXX} or \u{XXXXXX} */
 		    q += strlen(q);
 		    continue;
 		}
Index: test/ruby/test_string.rb
===================================================================
--- test/ruby/test_string.rb	(revision 55727)
+++ test/ruby/test_string.rb	(revision 55728)
@@ -614,6 +614,18 @@ CODE https://github.com/ruby/ruby/blob/trunk/test/ruby/test_string.rb#L614
   def test_dump
     a= S("Test") << 1 << 2 << 3 << 9 << 13 << 10
     assert_equal(S('"Test\\x01\\x02\\x03\\t\\r\\n"'), a.dump)
+    b= S("\u{7F}")
+    assert_equal(S('"\\x7F"'), b.dump)
+    b= S("\u{AB}")
+    assert_equal(S('"\\u00AB"'), b.dump)
+    b= S("\u{ABC}")
+    assert_equal(S('"\\u0ABC"'), b.dump)
+    b= S("\uABCD")
+    assert_equal(S('"\\uABCD"'), b.dump)
+    b= S("\u{ABCDE}")
+    assert_equal(S('"\\u{ABCDE}"'), b.dump)
+    b= S("\u{10ABCD}")
+    assert_equal(S('"\\u{10ABCD}"'), b.dump)
   end
 
   def test_dup
Index: ChangeLog
===================================================================
--- ChangeLog	(revision 55727)
+++ ChangeLog	(revision 55728)
@@ -1,3 +1,11 @@ https://github.com/ruby/ruby/blob/trunk/ChangeLog#L1
+Fri Jul 22 17:13:37 2016  Martin Duerst  <duerst@i...>
+
+	* string.c (String#dump): Change escaping of non-ASCII characters in
+	  UTF-8 to use upper-case four-digit hexadecimal escapes without braces
+	  where possible [Feature #12419].
+
+	* test/ruby/test_string.rb (test_dump): Add tests for above.
+
 Fri Jul 22 10:35:35 2016  Kouhei Sutou  <kou@c...>
 
 	* lib/rexml/attribute.rb (REXML::Attribute#to_string): Fix wrong

--
ML: ruby-changes@q...
Info: http://www.atdot.net/~ko1/quickml/