string.c: respect the actual encoding

* string.c (rb_enc_str_coderange): respect the actual encoding of
  if a BOM presents, and scan for the actual code range.
  [ruby-core:91662] [Bug #15635]

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@67167 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

2 files changed, 10 insertions, 2 deletions

diff --git a/string.c b/string.c
index 88686db76d..449fb558db 100644
--- a/string.c
+++ b/string.c
@@ -655,12 +655,13 @@ rb_enc_str_coderange(VALUE str)
     if (cr == ENC_CODERANGE_UNKNOWN) {
 	int encidx = ENCODING_GET(str);
 	rb_encoding *enc = rb_enc_from_index(encidx);
-	if (rb_enc_mbminlen(enc) > 1 && rb_enc_dummy_p(enc)) {
+	if (rb_enc_mbminlen(enc) > 1 && rb_enc_dummy_p(enc) &&
+            rb_enc_mbminlen(enc = get_actual_encoding(encidx, str)) == 1) {
 	    cr = ENC_CODERANGE_BROKEN;
 	}
 	else {
 	    cr = coderange_scan(RSTRING_PTR(str), RSTRING_LEN(str),
-				get_actual_encoding(encidx, str));
+                                enc);
 	}
         ENC_CODERANGE_SET(str, cr);
     }
diff --git a/test/ruby/test_m17n.rb b/test/ruby/test_m17n.rb
index c1184c551f..75daf61376 100644
--- a/test/ruby/test_m17n.rb
+++ b/test/ruby/test_m17n.rb
@@ -269,6 +269,13 @@ class TestM17N < Test::Unit::TestCase
     assert_empty(encs, bug10598)
   end
 
+  def test_utf_without_bom_valid
+    encs = [Encoding::UTF_16, Encoding::UTF_32].find_all {|enc|
+      !(+"abcd").encode!(enc).force_encoding(enc).valid_encoding?
+    }
+    assert_empty(encs)
+  end
+
   def test_object_utf16_32_inspect
     EnvUtil.suppress_warning do
       begin