transcode.c: scrub in the given encoding

* transcode.c (str_transcode0): scrub in the given encoding when
  the source encoding is given, not in the encoding of the
  receiver.  [ruby-core:75732] [Bug #12431]

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@55181 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

5 files changed, 17 insertions, 3 deletions

diff --git a/ChangeLog b/ChangeLog
index 7de6ec6891..6fe7d64c60 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,9 @@
+Fri May 27 17:09:44 2016  Nobuyoshi Nakada  <nobu@ruby-lang.org>
+
+	* transcode.c (str_transcode0): scrub in the given encoding when
+	  the source encoding is given, not in the encoding of the
+	  receiver.  [ruby-core:75732] [Bug #12431]
+
 Fri May 27 15:07:32 2016  Nobuyoshi Nakada  <nobu@ruby-lang.org>
 
 	* include/ruby/ruby.h (rb_scan_args): remove nul padding which
diff --git a/internal.h b/internal.h
index 0f16fcc94b..38c7986734 100644
--- a/internal.h
+++ b/internal.h
@@ -1356,6 +1356,7 @@ VALUE rb_str_locktmp_ensure(VALUE str, VALUE (*func)(VALUE), VALUE arg);
 VALUE rb_external_str_with_enc(VALUE str, rb_encoding *eenc);
 VALUE rb_str_cat_conv_enc_opts(VALUE newstr, long ofs, const char *ptr, long len,
 			       rb_encoding *from, int ecflags, VALUE ecopts);
+VALUE rb_enc_str_scrub(rb_encoding *enc, VALUE str, VALUE repl);
 #endif
 #define STR_NOEMBED      FL_USER1
 #define STR_SHARED       FL_USER2 /* = ELTS_SHARED */
diff --git a/string.c b/string.c
index 049b088a0d..80b668d52d 100644
--- a/string.c
+++ b/string.c
@@ -8927,8 +8927,13 @@ str_compat_and_valid(VALUE str, rb_encoding *enc)
 VALUE
 rb_str_scrub(VALUE str, VALUE repl)
 {
+    return rb_enc_str_scrub(STR_ENC_GET(str), str, repl);
+}
+
+VALUE
+rb_enc_str_scrub(rb_encoding *enc, VALUE str, VALUE repl)
+{
     int cr = ENC_CODERANGE(str);
-    rb_encoding *enc;
     int encidx;
     VALUE buf = Qnil;
     const char *rep;
@@ -8938,7 +8943,6 @@ rb_str_scrub(VALUE str, VALUE repl)
     if (ENC_CODERANGE_CLEAN_P(cr))
 	return Qnil;
 
-    enc = STR_ENC_GET(str);
     if (!NIL_P(repl)) {
 	repl = str_compat_and_valid(repl, enc);
 	tainted = OBJ_TAINTED_RAW(repl);
diff --git a/test/ruby/test_transcode.rb b/test/ruby/test_transcode.rb
index 33e7467102..2f97d098fd 100644
--- a/test/ruby/test_transcode.rb
+++ b/test/ruby/test_transcode.rb
@@ -1213,6 +1213,9 @@ class TestTranscode < Test::Unit::TestCase
   def test_invalid_replace_string
     assert_equal("a<x>A", "a\x80A".encode("us-ascii", "euc-jp", :invalid=>:replace, :replace=>"<x>"))
     assert_equal("a<x>A", "a\x80A".encode("us-ascii", "euc-jis-2004", :invalid=>:replace, :replace=>"<x>"))
+    s = "abcd\u{c1}"
+    r = s.b.encode("UTF-8", "UTF-8", invalid: :replace, replace: "\u{fffd}")
+    assert_equal(s, r)
   end
 
   def test_undef_replace
diff --git a/transcode.c b/transcode.c
index 0514adaf7e..8aa9cf3352 100644
--- a/transcode.c
+++ b/transcode.c
@@ -2700,7 +2700,7 @@ str_transcode0(int argc, VALUE *argv, VALUE *self, int ecflags, VALUE ecopts)
 		if (!NIL_P(ecopts)) {
 		    rep = rb_hash_aref(ecopts, sym_replace);
 		}
-		dest = rb_str_scrub(str, rep);
+		dest = rb_enc_str_scrub(senc, str, rep);
 		if (NIL_P(dest)) dest = str;
 		*self = dest;
 		return dencidx;