* string.c (rb_str_init): now accepts new option parameter `encoding'.

  [Feature #11785]


git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@52976 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

4 files changed, 56 insertions, 5 deletions

diff --git a/ChangeLog b/ChangeLog
index 64de792d03..132374aef1 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,8 @@
+Wed Dec  9 01:46:35 2015  NAKAMURA Usaku  <usa@ruby-lang.org>
+
+	* string.c (rb_str_init): now accepts new option parameter `encoding'.
+	  [Feature #11785]
+
 Wed Dec  9 00:52:37 2015  Nobuyoshi Nakada  <nobu@ruby-lang.org>
 
 	* file.c (rb_stat_wr, rb_stat_ww): call get_stat only once and
diff --git a/NEWS b/NEWS
index 80bd3cd683..5dd370ad39 100644
--- a/NEWS
+++ b/NEWS
@@ -132,6 +132,8 @@ with all sufficient information, see the ChangeLog file.
   * String#+@ and String#-@ are added to get mutable/frozen strings.
     [Feature #11782]
 
+  * String.new now accepts new option parameter `encoding'.
+
 * Struct
   * Struct#dig [Feature #11688]
 
diff --git a/string.c b/string.c
index d34359f328..c39e34c1a3 100644
--- a/string.c
+++ b/string.c
@@ -1324,17 +1324,34 @@ rb_str_resurrect(VALUE str)
 /*
  *  call-seq:
  *     String.new(str="")   -> new_str
+ *     String.new(str="", encoding: enc) -> new_str
  *
  *  Returns a new string object containing a copy of <i>str</i>.
+ *  The optional <i>enc</i> argument specifies the encoding of the new string.
+ *  If not specified, the encoding of <i>str</i> (or ASCII-8BIT, if <i>str</i>
+ *  is not specified) is used.
  */
 
 static VALUE
 rb_str_init(int argc, VALUE *argv, VALUE str)
 {
-    VALUE orig;
+    static ID keyword_ids[1];
+    VALUE orig, opt, enc;
+    int n;
+
+    if (!keyword_ids[0])
+	keyword_ids[0] = rb_intern("encoding");
 
-    if (argc > 0 && rb_scan_args(argc, argv, "01", &orig) == 1)
+    n = rb_scan_args(argc, argv, "01:", &orig, &opt);
+    if (argc > 0 && n == 1)
 	rb_str_replace(str, orig);
+    if (!NIL_P(opt)) {
+	rb_get_kwargs(opt, keyword_ids, 0, 1, &enc);
+	if (enc != Qundef && !NIL_P(enc)) {
+	    rb_enc_associate(str, rb_to_encoding(enc));
+	    ENC_CODERANGE_CLEAR(str);
+	}
+    }
     return str;
 }
 
diff --git a/test/ruby/test_string.rb b/test/ruby/test_string.rb
index 824c0e6b1c..eed7c69a02 100644
--- a/test/ruby/test_string.rb
+++ b/test/ruby/test_string.rb
@@ -11,12 +11,39 @@ class TestString < Test::Unit::TestCase
     super
   end
 
-  def S(str)
-    @cls.new(str)
+  def S(*args)
+    @cls.new(*args)
   end
 
   def test_s_new
-    assert_equal("RUBY", S("RUBY"))
+    assert_equal("", S())
+    assert_equal(Encoding::ASCII_8BIT, S().encoding)
+
+    assert_equal("", S(""))
+    assert_equal(__ENCODING__, S("").encoding)
+
+    src = "RUBY"
+    assert_equal(src, S(src))
+    assert_equal(__ENCODING__, S(src).encoding)
+
+    src.force_encoding("euc-jp")
+    assert_equal(src, S(src))
+    assert_equal(Encoding::EUC_JP, S(src).encoding)
+
+
+    assert_equal("", S(encoding: "euc-jp"))
+    assert_equal(Encoding::EUC_JP, S(encoding: "euc-jp").encoding)
+
+    assert_equal("", S("", encoding: "euc-jp"))
+    assert_equal(Encoding::EUC_JP, S("", encoding: "euc-jp").encoding)
+
+    src = "RUBY"
+    assert_equal(src, S(src, encoding: "euc-jp"))
+    assert_equal(Encoding::EUC_JP, S(src, encoding: "euc-jp").encoding)
+
+    src.force_encoding("euc-jp")
+    assert_equal(src, S(src, encoding: "utf-8"))
+    assert_equal(Encoding::UTF_8, S(src, encoding: "utf-8").encoding)
   end
 
   def test_AREF # '[]'