* include/ruby/ruby.h: add RSTRING_FSTR flag

* internal.h: add rb_fstring() prototype
* parse.y (str_suffix_gen): deduplicate frozen string literals
* string.c (rb_fstring): deduplicate frozen string literals
* string.c (rb_str_free): delete fstrings from frozen_strings table when
  they are GC'd
* string.c (Init_String): initialize frozen_strings table
* test/ruby/test_string.rb: test frozen strings are deduplicated

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@42843 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

ChangeLog

@@ -1,3 +1,20 @@
+Thu Sep  5 13:49:00 2013  Charlie Somerville  <charliesome@ruby-lang.org>
+
+	* include/ruby/ruby.h: add RSTRING_FSTR flag
+
+	* internal.h: add rb_fstring() prototype
+
+	* parse.y (str_suffix_gen): deduplicate frozen string literals
+
+	* string.c (rb_fstring): deduplicate frozen string literals
+
+	* string.c (rb_str_free): delete fstrings from frozen_strings table when
+	  they are GC'd
+
+	* string.c (Init_String): initialize frozen_strings table
+
+	* test/ruby/test_string.rb: test frozen strings are deduplicated
+
 Thu Sep  5 12:48:00 2013  Kenta Murata  <mrkn@cookpad.com>
 
 	* configure.in (with_gmp): set with_gmp no if it is empty.

include/ruby/ruby.h

@@ -905,6 +905,7 @@ struct RString {
     } as;
 };
 #define RSTRING_NOEMBED FL_USER1
+#define RSTRING_FSTR FL_USER17
 #define RSTRING_EMBED_LEN_MASK (FL_USER2|FL_USER3|FL_USER4|FL_USER5|FL_USER6)
 #define RSTRING_EMBED_LEN_SHIFT (FL_USHIFT+2)
 #define RSTRING_EMBED_LEN(str) \

internal.h

@@ -600,6 +600,7 @@ size_t rb_strftime(char *s, size_t maxsize, const char *format, rb_encoding *enc
 #endif
 
 /* string.c */
+VALUE rb_fstring(VALUE);
 int rb_str_buf_cat_escaped_char(VALUE result, unsigned int c, int unicode_p);
 int rb_str_symname_p(VALUE);
 VALUE rb_str_quote_unprintable(VALUE);

parse.y

@@ -8561,7 +8561,7 @@ str_suffix_gen(struct parser_params *parser, NODE *node, long opt)
 #endif
 #if STR_OPTION_FROZEN
 	if (opt & STR_OPTION_FROZEN) {
-	    OBJ_FREEZE(node->nd_lit);
+	    node->nd_lit = rb_fstring(node->nd_lit);
 	    nd_set_type(node, NODE_LIT);
 	}
 #endif

string.c

@@ -131,6 +131,26 @@ VALUE rb_cSymbol;
 
 #define STR_ENC_GET(str) rb_enc_from_index(ENCODING_GET(str))
 
+static st_table* frozen_strings;
+
+static const struct st_hash_type fstring_hash_type = {
+    rb_str_cmp,
+    rb_str_hash
+};
+
+VALUE
+rb_fstring(VALUE str)
+{
+    VALUE fstr;
+    if (!st_lookup(frozen_strings, (st_data_t)str, (st_data_t*)&fstr)) {
+	fstr = rb_str_dup(str);
+	OBJ_FREEZE(fstr);
+	RBASIC(fstr)->flags |= RSTRING_FSTR;
+	st_insert(frozen_strings, fstr, fstr);
+    }
+    return fstr;
+}
+
 static inline int
 single_byte_optimizable(VALUE str)
 {
@@ -838,6 +858,9 @@ rb_free_tmp_buffer(volatile VALUE *store)
 void
 rb_str_free(VALUE str)
 {
+    if (FL_TEST(str, RSTRING_FSTR)) {
+	st_delete(frozen_strings, (st_data_t*)&str, NULL);
+    }
     if (!STR_EMBED_P(str) && !STR_SHARED_P(str)) {
 	xfree(RSTRING(str)->as.heap.ptr);
     }
@@ -8672,6 +8695,8 @@ Init_String(void)
 #undef rb_intern
 #define rb_intern(str) rb_intern_const(str)
 
+    frozen_strings = st_init_table(&fstring_hash_type);
+
     rb_cString  = rb_define_class("String", rb_cObject);
     rb_include_module(rb_cString, rb_mComparable);
     rb_define_alloc_func(rb_cString, empty_str_alloc);

test/ruby/test_string.rb

@@ -2243,6 +2243,12 @@ class TestString < Test::Unit::TestCase
       })
     end
   end
+
+  def test_frozen_strings_are_deduplicated
+    a = "hello"f
+    b = "hello"f
+    assert_equal a.object_id, b.object_id
+  end
 end
 
 class TestString2 < TestString