Allow empty path components in a URI [Bug #8352]

* generic.rb (URI::Generic#merge, URI::Generic#route_to): Fix a bug
  where a sequence of slashes in the path part gets collapsed to a
  single slash.  According to the relevant RFCs and WHATWG URL
  Standard, empty path components are simply valid and there is no
  special treatment defined for them, so we just keep them as they
  are.

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@61218 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

3 files changed, 13 insertions, 3 deletions

diff --git a/NEWS b/NEWS
index 12949c496c..b458b549a3 100644
--- a/NEWS
+++ b/NEWS
@@ -353,6 +353,10 @@ with all sufficient information, see the ChangeLog file or Redmine
 
     * StringScanner#size, StringScanner#captures, StringScanner#values_at  [Feature #836]
 
+* URI
+
+  * Relative path operations no longer collapse consecutive slashes to a single slash. [Bug #8352]
+
 * WEBrick
 
   * Add Server Name Indication (SNI) support [Feature #13729]
diff --git a/lib/uri/generic.rb b/lib/uri/generic.rb
index dc4f9c4c30..629323e80e 100644
--- a/lib/uri/generic.rb
+++ b/lib/uri/generic.rb
@@ -979,7 +979,7 @@ module URI
     # returns an Array of the path split on '/'
     #
     def split_path(path)
-      path.split(%r{/+}, -1)
+      path.split(%r{/}, -1)
     end
     private :split_path
 
@@ -1154,8 +1154,8 @@ module URI
         return dst.dup
       end
 
-      src_path = src.scan(%r{(?:\A|[^/]+)/})
-      dst_path = dst.scan(%r{(?:\A|[^/]+)/?})
+      src_path = src.scan(%r{[^/]*/})
+      dst_path = dst.scan(%r{[^/]*/?})
 
       # discard same parts
       while !dst_path.empty? && dst_path.first == src_path.first
diff --git a/test/uri/test_generic.rb b/test/uri/test_generic.rb
index b77717f949..7e428aa849 100644
--- a/test/uri/test_generic.rb
+++ b/test/uri/test_generic.rb
@@ -208,6 +208,9 @@ class URI::TestGeneric < Test::Unit::TestCase
     assert(nil != u.merge!("../baz"))
     assert_equal('http://foo/baz', u.to_s)
 
+    url = URI.parse('http://a/b//c') + 'd//e'
+    assert_equal('http://a/b//d//e', url.to_s)
+
     u0 = URI.parse('mailto:foo@example.com')
     u1 = URI.parse('mailto:foo@example.com#bar')
     assert_equal(uri_to_ary(u0 + '#bar'), uri_to_ary(u1), "[ruby-dev:23628]")
@@ -265,6 +268,9 @@ class URI::TestGeneric < Test::Unit::TestCase
     url = URI.parse('http://hoge/b').route_to('http://hoge/b:c')
     assert_equal('./b:c', url.to_s)
 
+    url = URI.parse('http://hoge/b//c').route_to('http://hoge/b/c')
+    assert_equal('../c', url.to_s)
+
     url = URI.parse('file:///a/b/').route_to('file:///a/b/')
     assert_equal('', url.to_s)
     url = URI.parse('file:///a/b/').route_to('file:///a/b')