x509name: add OpenSSL::X509::Name#to_utf8

The existing #to_s does not interact well with distinguished names
containing multi-byte UTF-8 characters since the OpenSSL function
X509_NAME_print_ex() escapes bytes with MSB set by default.

Unfortunately we can't fix it without breaking backwards compatibility.
It takes options as a bit field that is directly passed to
X509_NAME_print_ex(). Let's add a new method instead.

Fixes: https://github.com/ruby/openssl/issues/26

2 files changed, 53 insertions, 0 deletions

diff --git a/ext/openssl/ossl_x509name.c b/ext/openssl/ossl_x509name.c
index f0bbda41..86dbab18 100644
--- a/ext/openssl/ossl_x509name.c
+++ b/ext/openssl/ossl_x509name.c
@@ -305,6 +305,21 @@ ossl_x509name_to_s(int argc, VALUE *argv, VALUE self)
 }
 
 /*
+ * call-seq;
+ *    name.to_utf8 -> string
+ *
+ * Returns an UTF-8 representation of the distinguished name, as specified
+ * in {RFC 2253}[https://www.ietf.org/rfc/rfc2253.txt].
+ */
+static VALUE
+ossl_x509name_to_utf8(VALUE self)
+{
+    VALUE str = x509name_print(self, XN_FLAG_RFC2253 & ~ASN1_STRFLGS_ESC_MSB);
+    rb_enc_associate_index(str, rb_utf8_encindex());
+    return str;
+}
+
+/*
  * call-seq:
  *    name.to_a => [[name, data, type], ...]
  *
@@ -498,6 +513,7 @@ Init_ossl_x509name(void)
     rb_define_method(cX509Name, "initialize_copy", ossl_x509name_initialize_copy, 1);
     rb_define_method(cX509Name, "add_entry", ossl_x509name_add_entry, -1);
     rb_define_method(cX509Name, "to_s", ossl_x509name_to_s, -1);
+    rb_define_method(cX509Name, "to_utf8", ossl_x509name_to_utf8, 0);
     rb_define_method(cX509Name, "to_a", ossl_x509name_to_a, 0);
     rb_define_method(cX509Name, "cmp", ossl_x509name_cmp, 1);
     rb_define_alias(cX509Name, "<=>", "cmp");
diff --git a/test/test_x509name.rb b/test/test_x509name.rb
index c9864063..ce370415 100644
--- a/test/test_x509name.rb
+++ b/test/test_x509name.rb
@@ -356,6 +356,43 @@ class OpenSSL::TestX509Name < OpenSSL::TestCase
     assert_equal("CN=unya,OU=b+OU=a,O=ruby-lang", dn.dup.to_s(OpenSSL::X509::Name::RFC2253))
   end
 
+  def test_to_s
+    dn = [
+      ["DC", "org"],
+      ["DC", "ruby-lang"],
+      ["CN", "フー, バー"],
+    ]
+    name = OpenSSL::X509::Name.new
+    dn.each { |x| name.add_entry(*x) }
+
+    assert_equal "/DC=org/DC=ruby-lang/" \
+      "CN=\\xE3\\x83\\x95\\xE3\\x83\\xBC, \\xE3\\x83\\x90\\xE3\\x83\\xBC",
+      name.to_s
+    # OpenSSL escapes characters with MSB by default
+    assert_equal \
+      "CN=\\E3\\83\\95\\E3\\83\\BC\\, \\E3\\83\\90\\E3\\83\\BC," \
+      "DC=ruby-lang,DC=org",
+      name.to_s(OpenSSL::X509::Name::RFC2253)
+    assert_equal "DC = org, DC = ruby-lang, " \
+      "CN = \"\\E3\\83\\95\\E3\\83\\BC, \\E3\\83\\90\\E3\\83\\BC\"",
+      name.to_s(OpenSSL::X509::Name::ONELINE)
+  end
+
+  def test_to_utf8
+    dn = [
+      ["DC", "org"],
+      ["DC", "ruby-lang"],
+      ["CN", "フー, バー"],
+    ]
+    name = OpenSSL::X509::Name.new
+    dn.each { |x| name.add_entry(*x) }
+
+    str = name.to_utf8
+    expected = "CN=フー\\, バー,DC=ruby-lang,DC=org".force_encoding("UTF-8")
+    assert_equal expected, str
+    assert_equal Encoding.find("UTF-8"), str.encoding
+  end
+
   def test_equals2
     n1 = OpenSSL::X509::Name.parse 'CN=a'
     n2 = OpenSSL::X509::Name.parse 'CN=a'