* string.c (str_byte_substr): don't set coderange if it's not known.

[Bug #7954] [ruby-dev:47108]

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@39495 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

ChangeLog

@@ -1,3 +1,8 @@
+Mon Feb 25 21:03:34 2013  NARUSE, Yui  <naruse@ruby-lang.org>
+
+	* string.c (str_byte_substr): don't set coderange if it's not known.
+	  [Bug #7954] [ruby-dev:47108]
+
 Mon Feb 25 16:47:02 2013  Nobuyoshi Nakada  <nobu@ruby-lang.org>
 
 	* common.mk (realclean-local): miniprelude.c is made by srcs, so it

string.c

@@ -4124,10 +4124,29 @@ str_byte_substr(VALUE str, long beg, long len)
     }
     else {
 	str2 = rb_str_new5(str, p, len);
-	rb_enc_cr_str_copy_for_substr(str2, str);
-	OBJ_INFECT(str2, str);
     }
 
+    str_enc_copy(str2, str);
+
+    if (RSTRING_LEN(str2) == 0) {
+	if (!rb_enc_asciicompat(STR_ENC_GET(str)))
+	    ENC_CODERANGE_SET(str2, ENC_CODERANGE_VALID);
+	else
+	    ENC_CODERANGE_SET(str2, ENC_CODERANGE_7BIT);
+    }
+    else {
+	switch (ENC_CODERANGE(str)) {
+	  case ENC_CODERANGE_7BIT:
+	    ENC_CODERANGE_SET(str2, ENC_CODERANGE_7BIT);
+	    break;
+	  default:
+	    ENC_CODERANGE_SET(str2, ENC_CODERANGE_UNKNOWN);
+	    break;
+	}
+    }
+
+    OBJ_INFECT(str2, str);
+
     return str2;
 }
 

test/ruby/test_string.rb

@@ -2181,6 +2181,10 @@ class TestString < Test::Unit::TestCase
     assert_equal(u("\x81\x82"), "\u3042".byteslice(1..2))
 
     assert_equal(u("\x82")+("\u3042"*9), ("\u3042"*10).byteslice(2, 28))
+
+    bug7954 = '[ruby-dev:47108]'
+    assert_equal(false, "\u3042".byteslice(0, 2).valid_encoding?)
+    assert_equal(false, ("\u3042"*10).byteslice(0, 20).valid_encoding?)
   end
 end