From cff9d743242f7c50e8e5cf350a8c3e60bb00f1dc Mon Sep 17 00:00:00 2001 From: Hiroshi SHIBATA Date: Fri, 24 Mar 2023 18:53:18 +0900 Subject: [PATCH 1/5] Fix splitting relative URI --- lib/uri/rfc3986_parser.rb | 2 +- test/uri/test_parser.rb | 7 +++++++ 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/lib/uri/rfc3986_parser.rb b/lib/uri/rfc3986_parser.rb index 49a594c..75fd5b1 100644 --- a/lib/uri/rfc3986_parser.rb +++ b/lib/uri/rfc3986_parser.rb @@ -4,7 +4,7 @@ module URI # URI defined in RFC3986 # this regexp is modified not to host is not empty string RFC3986_URI = /\A(?(?[A-Za-z][+\-.0-9A-Za-z]*):(?\/\/(?(?:(?(?:%\h\h|[!$&-.0-;=A-Z_a-z~])*)@)?(?(?\[(?:(?(?:\h{1,4}:){6}(?\h{1,4}:\h{1,4}|(?(?[1-9]\d|1\d{2}|2[0-4]\d|25[0-5]|\d)\.\g\.\g\.\g))|::(?:\h{1,4}:){5}\g|\h{1,4}?::(?:\h{1,4}:){4}\g|(?:(?:\h{1,4}:)?\h{1,4})?::(?:\h{1,4}:){3}\g|(?:(?:\h{1,4}:){,2}\h{1,4})?::(?:\h{1,4}:){2}\g|(?:(?:\h{1,4}:){,3}\h{1,4})?::\h{1,4}:\g|(?:(?:\h{1,4}:){,4}\h{1,4})?::\g|(?:(?:\h{1,4}:){,5}\h{1,4})?::\h{1,4}|(?:(?:\h{1,4}:){,6}\h{1,4})?::)|(?v\h+\.[!$&-.0-;=A-Z_a-z~]+))\])|\g|(?(?:%\h\h|[!$&-.0-9;=A-Z_a-z~])+))?(?::(?\d*))?)(?(?:\/(?(?:%\h\h|[!$&-.0-;=@-Z_a-z~])*))*)|(?\/(?:(?(?:%\h\h|[!$&-.0-;=@-Z_a-z~])+)(?:\/\g)*)?)|(?\g(?:\/\g)*)|(?))(?:\?(?[^#]*))?(?:\#(?(?:%\h\h|[!$&-.0-;=@-Z_a-z~\/?])*))?)\z/ - RFC3986_relative_ref = /\A(?(?\/\/(?(?:(?(?:%\h\h|[!$&-.0-;=A-Z_a-z~])*)@)?(?(?\[(?(?:\h{1,4}:){6}(?\h{1,4}:\h{1,4}|(?(?[1-9]\d|1\d{2}|2[0-4]\d|25[0-5]|\d)\.\g\.\g\.\g))|::(?:\h{1,4}:){5}\g|\h{1,4}?::(?:\h{1,4}:){4}\g|(?:(?:\h{1,4}:){,1}\h{1,4})?::(?:\h{1,4}:){3}\g|(?:(?:\h{1,4}:){,2}\h{1,4})?::(?:\h{1,4}:){2}\g|(?:(?:\h{1,4}:){,3}\h{1,4})?::\h{1,4}:\g|(?:(?:\h{1,4}:){,4}\h{1,4})?::\g|(?:(?:\h{1,4}:){,5}\h{1,4})?::\h{1,4}|(?:(?:\h{1,4}:){,6}\h{1,4})?::)|(?v\h+\.[!$&-.0-;=A-Z_a-z~]+)\])|\g|(?(?:%\h\h|[!$&-.0-9;=A-Z_a-z~])+))?(?::(?\d*))?)(?(?:\/(?(?:%\h\h|[!$&-.0-;=@-Z_a-z~])*))*)|(?\/(?:(?(?:%\h\h|[!$&-.0-;=@-Z_a-z~])+)(?:\/\g)*)?)|(?(?(?:%\h\h|[!$&-.0-9;=@-Z_a-z~])+)(?:\/\g)*)|(?))(?:\?(?[^#]*))?(?:\#(?(?:%\h\h|[!$&-.0-;=@-Z_a-z~\/?])*))?)\z/ + RFC3986_relative_ref = /\A(?(?\/\/(?(?:(?(?:%\h\h|[!$&-.0-;=A-Z_a-z~])*)@)?(?(?\[(?:(?(?:\h{1,4}:){6}(?\h{1,4}:\h{1,4}|(?(?[1-9]\d|1\d{2}|2[0-4]\d|25[0-5]|\d)\.\g\.\g\.\g))|::(?:\h{1,4}:){5}\g|\h{1,4}?::(?:\h{1,4}:){4}\g|(?:(?:\h{1,4}:){,1}\h{1,4})?::(?:\h{1,4}:){3}\g|(?:(?:\h{1,4}:){,2}\h{1,4})?::(?:\h{1,4}:){2}\g|(?:(?:\h{1,4}:){,3}\h{1,4})?::\h{1,4}:\g|(?:(?:\h{1,4}:){,4}\h{1,4})?::\g|(?:(?:\h{1,4}:){,5}\h{1,4})?::\h{1,4}|(?:(?:\h{1,4}:){,6}\h{1,4})?::)|(?v\h+\.[!$&-.0-;=A-Z_a-z~]+))\])|\g|(?(?:%\h\h|[!$&-.0-9;=A-Z_a-z~])+))?(?::(?\d*))?)(?(?:\/(?(?:%\h\h|[!$&-.0-;=@-Z_a-z~])*))*)|(?\/(?:(?(?:%\h\h|[!$&-.0-;=@-Z_a-z~])+)(?:\/\g)*)?)|(?(?(?:%\h\h|[!$&-.0-9;=@-Z_a-z~])+)(?:\/\g)*)|(?))(?:\?(?[^#]*))?(?:\#(?(?:%\h\h|[!$&-.0-;=@-Z_a-z~\/?])*))?)\z/ attr_reader :regexp def initialize diff --git a/test/uri/test_parser.rb b/test/uri/test_parser.rb index b13a26c..37e7107 100644 --- a/test/uri/test_parser.rb +++ b/test/uri/test_parser.rb @@ -58,4 +58,11 @@ class URI::TestParser < Test::Unit::TestCase assert_equal("\u3042", p1.unescape('%e3%81%82'.force_encoding(Encoding::US_ASCII))) assert_equal("\xe3\x83\x90\xe3\x83\x90", p1.unescape("\xe3\x83\x90%e3%83%90")) end + + def test_split + assert_equal(["http", nil, "example.com", nil, nil, "", nil, nil, nil], URI.split("http://example.com")) + assert_equal(["http", nil, "[0::0]", nil, nil, "", nil, nil, nil], URI.split("http://[0::0]")) + assert_equal([nil, nil, "example.com", nil, nil, "", nil, nil, nil], URI.split("//example.com")) + assert_equal([nil, nil, "[0::0]", nil, nil, "", nil, nil, nil], URI.split("//[0::0]")) + end end -- 2.33.0