Skip to content

Commit

Permalink
URI.parse should set empty string in host instead of nil
Browse files Browse the repository at this point in the history 
ruby/ruby@dd5118f
  • Loading branch information
@nurse @hsbt
nurse authored and hsbt committed Oct 13, 2022
1 parent 6bc8f66 commit 81263c9
Show file tree
Hide file tree
Showing 3 changed files with 12 additions and 6 deletions.
3 changes: 1 addition & 2 deletions lib/uri/rfc3986_parser.rb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -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

Expand Down
9 changes: 8 additions & 1 deletion test/uri/test_generic.rb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,8 @@ def test_to_s

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
Expand Down Expand Up @@ -157,6 +158,12 @@ def test_parse
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
Expand Down
6 changes: 3 additions & 3 deletions test/uri/test_ldap.rb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -39,7 +39,7 @@ def test_parse
# 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],

Expand Down Expand Up @@ -74,12 +74,12 @@ def test_parse
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|
Expand Down

0 comments on commit 81263c9

Please sign in to comment.