From dd5118f8524c425894d4716b787837ad7380bb0d Mon Sep 17 00:00:00 2001
From: "NARUSE, Yui" <naruse@airemix.jp>
Date: Sun, 13 Jan 2019 08:58:00 +0900
Subject: [PATCH] URI.parse should set empty string in host instead of nil

---
 lib/uri/rfc3986_parser.rb | 3 +--
 test/uri/test_generic.rb  | 9 ++++++++-
 test/uri/test_ldap.rb     | 6 +++---
 3 files changed, 12 insertions(+), 6 deletions(-)

diff --git a/lib/uri/rfc3986_parser.rb b/lib/uri/rfc3986_parser.rb
index 3e07de4805..68661d1185 100644
--- a/lib/uri/rfc3986_parser.rb
+++ b/lib/uri/rfc3986_parser.rb
@@ -2,8 +2,7 @@
 module URI
   class RFC3986_Parser # :nodoc:
     # URI defined in RFC3986
-    # this regexp is modified not to host is not empty string
-    RFC3986_URI = /\A(?<URI>(?<scheme>[A-Za-z][+\-.0-9A-Za-z]*):(?<hier-part>\/\/(?<authority>(?:(?<userinfo>(?:%\h\h|[!$&-.0-;=A-Z_a-z~])*)@)?(?<host>(?<IP-literal>\[(?:(?<IPv6address>(?:\h{1,4}:){6}(?<ls32>\h{1,4}:\h{1,4}|(?<IPv4address>(?<dec-octet>[1-9]\d|1\d{2}|2[0-4]\d|25[0-5]|\d)\.\g<dec-octet>\.\g<dec-octet>\.\g<dec-octet>))|::(?:\h{1,4}:){5}\g<ls32>|\h{1,4}?::(?:\h{1,4}:){4}\g<ls32>|(?:(?:\h{1,4}:)?\h{1,4})?::(?:\h{1,4}:){3}\g<ls32>|(?:(?:\h{1,4}:){,2}\h{1,4})?::(?:\h{1,4}:){2}\g<ls32>|(?:(?:\h{1,4}:){,3}\h{1,4})?::\h{1,4}:\g<ls32>|(?:(?:\h{1,4}:){,4}\h{1,4})?::\g<ls32>|(?:(?:\h{1,4}:){,5}\h{1,4})?::\h{1,4}|(?:(?:\h{1,4}:){,6}\h{1,4})?::)|(?<IPvFuture>v\h+\.[!$&-.0-;=A-Z_a-z~]+))\])|\g<IPv4address>|(?<reg-name>(?:%\h\h|[!$&-.0-9;=A-Z_a-z~])+))?(?::(?<port>\d*))?)(?<path-abempty>(?:\/(?<segment>(?:%\h\h|[!$&-.0-;=@-Z_a-z~])*))*)|(?<path-absolute>\/(?:(?<segment-nz>(?:%\h\h|[!$&-.0-;=@-Z_a-z~])+)(?:\/\g<segment>)*)?)|(?<path-rootless>\g<segment-nz>(?:\/\g<segment>)*)|(?<path-empty>))(?:\?(?<query>[^#]*))?(?:\#(?<fragment>(?:%\h\h|[!$&-.0-;=@-Z_a-z~\/?])*))?)\z/
+    RFC3986_URI = /\A(?<URI>(?<scheme>[A-Za-z][+\-.0-9A-Za-z]*):(?<hier-part>\/\/(?<authority>(?:(?<userinfo>(?:%\h\h|[!$&-.0-;=A-Z_a-z~])*)@)?(?<host>(?<IP-literal>\[(?:(?<IPv6address>(?:\h{1,4}:){6}(?<ls32>\h{1,4}:\h{1,4}|(?<IPv4address>(?<dec-octet>[1-9]\d|1\d{2}|2[0-4]\d|25[0-5]|\d)\.\g<dec-octet>\.\g<dec-octet>\.\g<dec-octet>))|::(?:\h{1,4}:){5}\g<ls32>|\h{1,4}?::(?:\h{1,4}:){4}\g<ls32>|(?:(?:\h{1,4}:)?\h{1,4})?::(?:\h{1,4}:){3}\g<ls32>|(?:(?:\h{1,4}:){,2}\h{1,4})?::(?:\h{1,4}:){2}\g<ls32>|(?:(?:\h{1,4}:){,3}\h{1,4})?::\h{1,4}:\g<ls32>|(?:(?:\h{1,4}:){,4}\h{1,4})?::\g<ls32>|(?:(?:\h{1,4}:){,5}\h{1,4})?::\h{1,4}|(?:(?:\h{1,4}:){,6}\h{1,4})?::)|(?<IPvFuture>v\h+\.[!$&-.0-;=A-Z_a-z~]+))\])|\g<IPv4address>|(?<reg-name>(?:%\h\h|[!$&-.0-9;=A-Z_a-z~])*))(?::(?<port>\d*))?)(?<path-abempty>(?:\/(?<segment>(?:%\h\h|[!$&-.0-;=@-Z_a-z~])*))*)|(?<path-absolute>\/(?:(?<segment-nz>(?:%\h\h|[!$&-.0-;=@-Z_a-z~])+)(?:\/\g<segment>)*)?)|(?<path-rootless>\g<segment-nz>(?:\/\g<segment>)*)|(?<path-empty>))(?:\?(?<query>[^#]*))?(?:\#(?<fragment>(?:%\h\h|[!$&-.0-;=@-Z_a-z~\/?])*))?)\z/
     RFC3986_relative_ref = /\A(?<relative-ref>(?<relative-part>\/\/(?<authority>(?:(?<userinfo>(?:%\h\h|[!$&-.0-;=A-Z_a-z~])*)@)?(?<host>(?<IP-literal>\[(?<IPv6address>(?:\h{1,4}:){6}(?<ls32>\h{1,4}:\h{1,4}|(?<IPv4address>(?<dec-octet>[1-9]\d|1\d{2}|2[0-4]\d|25[0-5]|\d)\.\g<dec-octet>\.\g<dec-octet>\.\g<dec-octet>))|::(?:\h{1,4}:){5}\g<ls32>|\h{1,4}?::(?:\h{1,4}:){4}\g<ls32>|(?:(?:\h{1,4}:){,1}\h{1,4})?::(?:\h{1,4}:){3}\g<ls32>|(?:(?:\h{1,4}:){,2}\h{1,4})?::(?:\h{1,4}:){2}\g<ls32>|(?:(?:\h{1,4}:){,3}\h{1,4})?::\h{1,4}:\g<ls32>|(?:(?:\h{1,4}:){,4}\h{1,4})?::\g<ls32>|(?:(?:\h{1,4}:){,5}\h{1,4})?::\h{1,4}|(?:(?:\h{1,4}:){,6}\h{1,4})?::)|(?<IPvFuture>v\h+\.[!$&-.0-;=A-Z_a-z~]+)\])|\g<IPv4address>|(?<reg-name>(?:%\h\h|[!$&-.0-9;=A-Z_a-z~])+))?(?::(?<port>\d*))?)(?<path-abempty>(?:\/(?<segment>(?:%\h\h|[!$&-.0-;=@-Z_a-z~])*))*)|(?<path-absolute>\/(?:(?<segment-nz>(?:%\h\h|[!$&-.0-;=@-Z_a-z~])+)(?:\/\g<segment>)*)?)|(?<path-noscheme>(?<segment-nz-nc>(?:%\h\h|[!$&-.0-9;=@-Z_a-z~])+)(?:\/\g<segment>)*)|(?<path-empty>))(?:\?(?<query>[^#]*))?(?:\#(?<fragment>(?:%\h\h|[!$&-.0-;=@-Z_a-z~\/?])*))?)\z/
     attr_reader :regexp
 
diff --git a/test/uri/test_generic.rb b/test/uri/test_generic.rb
index fdb405e396..3897c3d6ee 100644
--- a/test/uri/test_generic.rb
+++ b/test/uri/test_generic.rb
@@ -24,7 +24,8 @@ class URI::TestGeneric < Test::Unit::TestCase
 
     assert_equal "file:///foo", URI("file:///foo").to_s
     assert_equal "postgres:///foo", URI("postgres:///foo").to_s
-    assert_equal "http:/foo", URI("http:///foo").to_s
+    assert_equal "http:///foo", URI("http:///foo").to_s
+    assert_equal "http:/foo", URI("http:/foo").to_s
   end
 
   def test_parse
@@ -157,6 +158,12 @@ class URI::TestGeneric < Test::Unit::TestCase
     assert_equal(nil, url.user)
     assert_equal(nil, url.password)
     assert_equal(nil, url.userinfo)
+
+    # sec-156615
+    url = URI.parse('http:////example.com')
+    # must be empty string to identify as path-abempty, not path-absolute
+    assert_equal('', url.host)
+    assert_equal('http:////example.com', url.to_s)
   end
 
   def test_parse_scheme_with_symbols
diff --git a/test/uri/test_ldap.rb b/test/uri/test_ldap.rb
index 64845e487a..2625b24103 100644
--- a/test/uri/test_ldap.rb
+++ b/test/uri/test_ldap.rb
@@ -39,7 +39,7 @@ class TestLDAP < Test::Unit::TestCase
     # from RFC2255, section 6.
     {
       'ldap:///o=University%20of%20Michigan,c=US' =>
-      ['ldap', nil, URI::LDAP::DEFAULT_PORT,
+      ['ldap', '', URI::LDAP::DEFAULT_PORT,
 	'o=University%20of%20Michigan,c=US',
 	nil, nil, nil, nil],
 
@@ -74,12 +74,12 @@ class TestLDAP < Test::Unit::TestCase
 	nil, '(int=%5c00%5c00%5c00%5c04)', nil, nil],
 
       'ldap:///??sub??bindname=cn=Manager%2co=Foo' =>
-      ['ldap', nil, URI::LDAP::DEFAULT_PORT,
+      ['ldap', '', URI::LDAP::DEFAULT_PORT,
 	'',
 	nil, 'sub', nil, 'bindname=cn=Manager%2co=Foo'],
 
       'ldap:///??sub??!bindname=cn=Manager%2co=Foo' =>
-      ['ldap', nil, URI::LDAP::DEFAULT_PORT,
+      ['ldap', '', URI::LDAP::DEFAULT_PORT,
 	'',
 	nil, 'sub', nil, '!bindname=cn=Manager%2co=Foo'],
     }.each do |url2, ary|