* parse.y (parser_str_new): encoding of UTF-8 literal string in

	  US-ASCII script is UTF-8. [ruby-dev:33406]



git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@15285 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

3 files changed, 7 insertions, 1 deletions

diff --git a/ChangeLog b/ChangeLog
index b0930a631a..1e09121d7b 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,8 @@
+Mon Jan 28 11:24:49 2008  NAKAMURA Usaku  <usa@ruby-lang.org>
+
+	* parse.y (parser_str_new): encoding of UTF-8 literal string in
+	  US-ASCII script is UTF-8. [ruby-dev:33406]
+
 Mon Jan 28 10:25:59 2008  NAKAMURA Usaku  <usa@ruby-lang.org>
 
 	* test/ruby/test_m17n.rb (test_magic_comment): add test.
diff --git a/parse.y b/parse.y
index 19b8ba658c..721e88cab2 100644
--- a/parse.y
+++ b/parse.y
@@ -4848,7 +4848,7 @@ parser_str_new(const char *p, long n, rb_encoding *enc, int func, rb_encoding *e
 	if (rb_enc_str_coderange(str) == ENC_CODERANGE_7BIT) {
 	    rb_enc_associate(str, rb_usascii_encoding());
 	}
-	else if (enc0 == rb_usascii_encoding()) {
+	else if (enc0 == rb_usascii_encoding() && enc != rb_utf8_encoding()) {
 	    rb_enc_associate(str, rb_ascii8bit_encoding());
 	}
     }
diff --git a/test/ruby/test_m17n.rb b/test/ruby/test_m17n.rb
index c503cdbea3..3423a1d58a 100644
--- a/test/ruby/test_m17n.rb
+++ b/test/ruby/test_m17n.rb
@@ -153,6 +153,7 @@ class TestM17N < Test::Unit::TestCase
 
   def test_utf8_literal
     assert_equal(Encoding::UTF_8, "\u3042".encoding, "[ruby-dev:33406] \"\\u3042\".encoding")
+    assert_raise(SyntaxError) { eval(a('\u3052\x80')) }
   end
 
   def test_string_mixed_unicode