nobu	2015-07-22 23:44:20 +0900 (Wed, 22 Jul 2015)

  New Revision: 51344

  http://svn.ruby-lang.org/cgi-bin/viewvc.cgi?view=revision&revision=51344

  Log:
    string.c: fix coderange of reverse
    
    * string.c (rb_str_reverse): reversed string is not a substring,
      and should not set coderange of the original string.
      [ruby-dev:49189] [Bug #11387]

  Modified files:
    trunk/ChangeLog
    trunk/string.c
    trunk/test/ruby/test_m17n.rb
Index: ChangeLog
===================================================================
--- ChangeLog	(revision 51343)
+++ ChangeLog	(revision 51344)
@@ -1,3 +1,9 @@ https://github.com/ruby/ruby/blob/trunk/ChangeLog#L1
+Wed Jul 22 23:44:17 2015  Nobuyoshi Nakada  <nobu@r...>
+
+	* string.c (rb_str_reverse): reversed string is not a substring,
+	  and should not set coderange of the original string.
+	  [ruby-dev:49189] [Bug #11387]
+
 Wed Jul 22 20:17:51 2015  Koichi Sasada  <ko1@a...>
 
 	* vm_core.h: modify layout of rb_iseq_constant_body.
Index: string.c
===================================================================
--- string.c	(revision 51343)
+++ string.c	(revision 51344)
@@ -4802,13 +4802,14 @@ rb_str_reverse(VALUE str) https://github.com/ruby/ruby/blob/trunk/string.c#L4802
     rb_encoding *enc;
     VALUE rev;
     char *s, *e, *p;
-    int single = 1;
+    int cr;
 
     if (RSTRING_LEN(str) <= 1) return rb_str_dup(str);
     enc = STR_ENC_GET(str);
     rev = rb_str_new_with_class(str, 0, RSTRING_LEN(str));
     s = RSTRING_PTR(str); e = RSTRING_END(str);
     p = RSTRING_END(rev);
+    cr = ENC_CODERANGE(str);
 
     if (RSTRING_LEN(str) > 1) {
 	if (single_byte_optimizable(str)) {
@@ -4816,21 +4817,22 @@ rb_str_reverse(VALUE str) https://github.com/ruby/ruby/blob/trunk/string.c#L4817
 		*--p = *s++;
 	    }
 	}
-	else if (ENC_CODERANGE(str) == ENC_CODERANGE_VALID) {
+	else if (cr == ENC_CODERANGE_VALID) {
 	    while (s < e) {
 		int clen = rb_enc_fast_mbclen(s, e, enc);
 
-		if (clen > 1 || (*s & 0x80)) single = 0;
 		p -= clen;
 		memcpy(p, s, clen);
 		s += clen;
 	    }
 	}
 	else {
+	    cr = rb_enc_asciicompat(enc) ?
+		ENC_CODERANGE_7BIT : ENC_CODERANGE_VALID;
 	    while (s < e) {
 		int clen = rb_enc_mbclen(s, e, enc);
 
-		if (clen > 1 || (*s & 0x80)) single = 0;
+		if (clen > 1 || (*s & 0x80)) cr = ENC_CODERANGE_UNKNOWN;
 		p -= clen;
 		memcpy(p, s, clen);
 		s += clen;
@@ -4839,15 +4841,8 @@ rb_str_reverse(VALUE str) https://github.com/ruby/ruby/blob/trunk/string.c#L4841
     }
     STR_SET_LEN(rev, RSTRING_LEN(str));
     OBJ_INFECT(rev, str);
-    if (ENC_CODERANGE(str) == ENC_CODERANGE_UNKNOWN) {
-	if (single) {
-	    ENC_CODERANGE_SET(str, ENC_CODERANGE_7BIT);
-	}
-	else {
-	    ENC_CODERANGE_SET(str, ENC_CODERANGE_VALID);
-	}
-    }
-    rb_enc_cr_str_copy_for_substr(rev, str);
+    str_enc_copy(rev, str);
+    ENC_CODERANGE_SET(rev, cr);
 
     return rev;
 }
Index: test/ruby/test_m17n.rb
===================================================================
--- test/ruby/test_m17n.rb	(revision 51343)
+++ test/ruby/test_m17n.rb	(revision 51344)
@@ -1142,7 +1142,12 @@ class TestM17N < Test::Unit::TestCase https://github.com/ruby/ruby/blob/trunk/test/ruby/test_m17n.rb#L1142
   end
 
   def test_reverse
-    assert_equal(u("\xf0jihgfedcba"), u("abcdefghij\xf0").reverse)
+    bug11387 = '[ruby-dev:49189] [Bug #11387]'
+    s1 = u("abcdefghij\xf0")
+    s2 = s1.reverse
+    assert_not_predicate(s1, :valid_encoding?, bug11387)
+    assert_equal(u("\xf0jihgfedcba"), s2)
+    assert_not_predicate(s2, :valid_encoding?, bug11387)
   end
 
   def test_reverse_bang

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