nobu	2016-02-17 20:24:09 +0900 (Wed, 17 Feb 2016)

  New Revision: 53855

  https://svn.ruby-lang.org/cgi-bin/viewvc.cgi?view=revision&revision=53855

  Log:
    string.c: fix rb_str_init
    
    * string.c (rb_str_init): fix segfault and memory leak, consider
      wide char encoding terminator.

  Modified files:
    trunk/ChangeLog
    trunk/string.c
    trunk/test/ruby/test_string.rb
Index: test/ruby/test_string.rb
===================================================================
--- test/ruby/test_string.rb	(revision 53854)
+++ test/ruby/test_string.rb	(revision 53855)
@@ -70,6 +70,24 @@ class TestString < Test::Unit::TestCase https://github.com/ruby/ruby/blob/trunk/test/ruby/test_string.rb#L70
     assert_raise(RuntimeError){ str.__send__(:initialize, 'abc', capacity: 1000, encoding: 'euc-jp') }
   end
 
+  def test_initialize_nonstring
+    assert_raise(TypeError) {
+      S(1)
+    }
+    assert_raise(TypeError) {
+      S(1, capacity: 1000)
+    }
+  end
+
+  def test_initialize_memory_leak
+    assert_no_memory_leak([], <<-PREP, <<-CODE, rss: true)
+code = proc {('x'*100000).__send__(:initialize, '')}
+1_000.times(&code)
+PREP
+100_000.times(&code)
+CODE
+  end
+
   def test_AREF # '[]'
     assert_equal("A",  S("AooBar")[0])
     assert_equal("B",  S("FooBaB")[-1])
Index: string.c
===================================================================
--- string.c	(revision 53854)
+++ string.c	(revision 53855)
@@ -163,6 +163,7 @@ static VALUE str_new_shared(VALUE klass, https://github.com/ruby/ruby/blob/trunk/string.c#L163
 static VALUE str_new_frozen(VALUE klass, VALUE orig);
 static VALUE str_new_static(VALUE klass, const char *ptr, long len, int encindex);
 static void str_make_independent_expand(VALUE str, long len, long expand, const int termlen);
+static inline void str_modifiable(VALUE str);
 
 static inline void
 str_make_independent(VALUE str)
@@ -1367,8 +1368,9 @@ static VALUE https://github.com/ruby/ruby/blob/trunk/string.c#L1368
 rb_str_init(int argc, VALUE *argv, VALUE str)
 {
     static ID keyword_ids[2];
-    VALUE orig, opt, enc, vcapa;
+    VALUE orig, opt, venc, vcapa;
     VALUE kwargs[2];
+    rb_encoding *enc = 0;
     int n;
 
     if (!keyword_ids[0]) {
@@ -1379,45 +1381,53 @@ rb_str_init(int argc, VALUE *argv, VALUE https://github.com/ruby/ruby/blob/trunk/string.c#L1381
     n = rb_scan_args(argc, argv, "01:", &orig, &opt);
     if (!NIL_P(opt)) {
 	rb_get_kwargs(opt, keyword_ids, 0, 2, kwargs);
-	enc = kwargs[0];
+	venc = kwargs[0];
 	vcapa = kwargs[1];
+	if (venc != Qundef && !NIL_P(venc)) {
+	    enc = rb_to_encoding(venc);
+	}
 	if (vcapa != Qundef && !NIL_P(vcapa)) {
 	    long capa = NUM2LONG(vcapa);
-	    str_discard(str);
+	    long len = 0;
+	    int termlen = enc ? rb_enc_mbminlen(enc) : 1;
+
 	    if (capa < STR_BUF_MIN_SIZE) {
 		capa = STR_BUF_MIN_SIZE;
 	    }
 	    if (n == 1) {
-		long len = RSTRING_LEN(orig);
+		StringValue(orig);
+		len = RSTRING_LEN(orig);
 		if (capa < len) {
 		    capa = len;
 		}
-		RSTRING(str)->as.heap.ptr = ALLOC_N(char, capa+1);
-		memcpy(RSTRING(str)->as.heap.ptr, RSTRING_PTR(orig), RSTRING_LEN(orig));
-		RSTRING(str)->as.heap.len = len;
-		rb_enc_cr_str_exact_copy(str, orig);
+		if (orig == str) n = 0;
 	    }
-	    else {
-		RSTRING(str)->as.heap.ptr = ALLOC_N(char, capa+1);
-		RSTRING(str)->as.heap.ptr[0] = '\0';
+	    str_modifiable(str);
+	    if (STR_EMBED_P(str)) { /* make noembed always */
+		RSTRING(str)->as.heap.ptr = ALLOC_N(char, capa+termlen);
+	    }
+	    else if (STR_HEAP_SIZE(str) != capa+termlen) {
+		REALLOC_N(RSTRING(str)->as.heap.ptr, char, capa+termlen);
+	    }
+	    RSTRING(str)->as.heap.len = len;
+	    TERM_FILL(&RSTRING(str)->as.heap.ptr[len], termlen);
+	    if (n == 1) {
+		memcpy(RSTRING(str)->as.heap.ptr, RSTRING_PTR(orig), len);
+		rb_enc_cr_str_exact_copy(str, orig);
 	    }
 	    FL_SET(str, STR_NOEMBED);
 	    RSTRING(str)->as.heap.aux.capa = capa;
 	}
 	else if (n == 1) {
-	    StringValue(orig);
-	    str_discard(str);
-	    str_replace(str, orig);
+	    rb_str_replace(str, orig);
 	}
-	if (enc != Qundef && !NIL_P(enc)) {
-	    rb_enc_associate(str, rb_to_encoding(enc));
+	if (enc) {
+	    rb_enc_associate(str, enc);
 	    ENC_CODERANGE_CLEAR(str);
 	}
     }
     else if (n == 1) {
-	StringValue(orig);
-	str_discard(str);
-	str_replace(str, orig);
+	rb_str_replace(str, orig);
     }
     return str;
 }
Index: ChangeLog
===================================================================
--- ChangeLog	(revision 53854)
+++ ChangeLog	(revision 53855)
@@ -1,3 +1,13 @@ https://github.com/ruby/ruby/blob/trunk/ChangeLog#L1
+Wed Feb 17 20:23:38 2016  Nobuyoshi Nakada  <nobu@r...>
+
+	* string.c (rb_str_init): fix segfault and memory leak, consider
+	  wide char encoding terminator.
+
+Wed Feb 17 19:55:24 2016  Nobuyoshi Nakada  <nobu@r...>
+
+	* string.c (rb_str_init): fix segfault and memory leak, consider
+	  wide char encoding terminator.
+
 Wed Feb 17 12:14:59 2016  NARUSE, Yui  <naruse@r...>
 
 	* string.c (rb_str_init): introduce String.new(capacity: size)

--
ML: ruby-changes@q...
Info: http://www.atdot.net/~ko1/quickml/