mechanize 0.6.0 → 0.6.1

data/CHANGELOG

@@ -1,5 +1,23 @@
 = Mechanize CHANGELOG
 
+== 0.6.1
+
+* Added a method to Form called "submit".  Now forms can be submitted by
+  calling a method on the form.
+* Added a click method to links
+* Added an REXML pluggable parser for backwards compatability.  To use it,
+  just do this:
+   agent.pluggable_parser.html = WWW::Mechanize::REXMLPage
+* Fixed a bug with referrers by adding a page attribute to forms and links.
+* Fixed a bug where domain names were case sensitive.
+  http://tenderlovemaking.com/2006/09/04/road-to-ruby-mechanize-060/#comment-53
+* Fixed a bug with URI escaped links.
+  http://rubyforge.org/pipermail/mechanize-users/2006-September/000002.html
+* Fixed a bug when options in select lists don't have a value. Thanks Dan Higham
+  [#5837] Code in lib/mechanize/form_elements.rb is incorrect.
+* Fixed a bug with loading text in to links.
+  http://rubyforge.org/pipermail/mechanize-users/2006-September/000000.html
+
 == 0.6.0
 
 * Changed main parser to use hpricot

data/NOTES

@@ -1,5 +1,19 @@
 = Mechanize Release Notes
 
+== 0.6.1 (Chuck)
+
+Mechanize version 0.6.1 (Chuck) is done, and is ready for you to use.  This
+post "my trip to europe" release includes many bug fixes and a handful of
+new features.
+
+New features include, a submit method on forms, a click method on links, and an
+REXML pluggable parser.  Now you can submit a form just by calling a method on
+the form, rather than passing the form to the submit method on the mech object.
+The click method on links lets you click the link by calling a method on the
+link rather than passing the link to the click method on the mech object.
+Lastly, the REXML pluggable parser lets you use your pre-0.6.0 code with
+0.6.1.  See the CHANGELOG for more details.
+
 == 0.6.0 (Rufus)
 
 WWW::Mechanize 0.6.0 aka Rufus is ready!  This hpricot flavored pie has

data/lib/mechanize.rb

@@ -129,8 +129,9 @@ class Mechanize
   end
 
   # Fetches the URL passed in and returns a page.
-  def get(url)
-    cur_page = current_page || Page.new( nil, {'content-type'=>'text/html'})
+  def get(url, referer=nil)
+    cur_page = referer || current_page ||
+                    Page.new( nil, {'content-type'=>'text/html'})
 
     # fetch the page
     abs_uri = to_absolute_uri(url, cur_page)
@@ -152,7 +153,13 @@ class Mechanize
     uri = to_absolute_uri(
       link.attributes['href'] || link.attributes['src'] || link.href
     )
-    get(uri)
+    referer =
+      begin
+        link.page
+      rescue
+        nil
+      end
+    get(uri, referer)
   end
 
   # Equivalent to the browser back button.  Returns the most recent page
@@ -233,7 +240,10 @@ class Mechanize
   private
 
   def to_absolute_uri(url, cur_page=current_page())
-    url =  URI.parse(URI.escape(url.to_s.strip)) unless url.is_a? URI
+    url =  URI.parse(
+           URI.escape(
+           URI.unescape(url.to_s.strip)
+                     )) unless url.is_a? URI
 
     # construct an absolute uri
     if url.relative?
@@ -245,7 +255,8 @@ class Mechanize
   end
 
   def post_form(url, form)
-    cur_page = current_page || Page.new(nil, {'content-type'=>'text/html'})
+    cur_page = form.page || current_page ||
+                    Page.new( nil, {'content-type'=>'text/html'})
 
     request_data = form.request_data
 
@@ -380,6 +391,8 @@ class Mechanize
           response.code
         )
 
+        page.mech = self if page.respond_to? :mech=
+
         log.info("status: #{ page.code }") if log
 
         if page.respond_to? :watch_for_set

data/lib/mechanize/cookie.rb

@@ -7,8 +7,7 @@ module WWW
   # This class is used to represent an HTTP Cookie.
     class Cookie < WEBrick::Cookie
       def self.parse(uri, str)
-        cookies = []
-        str.gsub(/(,([^;,]*=)|,$)/) { "\r\n#{$2}" }.split(/\r\n/).each { |c|
+        return str.split(/,(?=[^;,]*=)|,$/).collect { |c|
           cookie_elem = c.split(/;/)
           first_elem = cookie_elem.shift
           first_elem.strip!
@@ -40,9 +39,7 @@ module WWW
           cookie.domain  ||= uri.host
           # Move this in to the cookie jar
           yield cookie if block_given?
-          cookies << cookie
         }
-        return cookies
       end
     
       def to_s
@@ -61,12 +58,13 @@ module WWW
     
       # Add a cookie to the Jar.
       def add(uri, cookie)
-        return unless uri.host =~ /#{cookie.domain}$/
-        unless @jar.has_key?(cookie.domain)
-          @jar[cookie.domain] = Hash.new
+        return unless uri.host =~ /#{cookie.domain}$/i
+        normal_domain = cookie.domain.downcase
+        unless @jar.has_key?(normal_domain)
+          @jar[normal_domain] = Hash.new
         end
     
-        @jar[cookie.domain][cookie.name] = cookie
+        @jar[normal_domain][cookie.name] = cookie
         cleanup()
         cookie
       end
@@ -77,7 +75,7 @@ module WWW
         cookies = []
         url.path = '/' if url.path.empty?
         @jar.each_key do |domain|
-          if url.host =~ /#{domain}$/
+          if url.host =~ /#{domain}$/i
             @jar[domain].each_key do |name|
               if url.path =~ /^#{@jar[domain][name].path}/
                 if @jar[domain][name].expires.nil?

data/lib/mechanize/form.rb

@@ -212,10 +212,12 @@ module WWW
     #  puts form['name']
     class Form < GlobalForm
       attr_reader :node
+      attr_reader :page
     
-      def initialize(node)
-        @node = node
-        super(@node, @node)
+      def initialize(node, mech=nil, page=nil)
+        super(node, node)
+        @page = page
+        @mech = mech
       end
 
       # Fetch the first field whose name is equal to field_name
@@ -268,6 +270,11 @@ module WWW
         end
         super
       end
+
+      # Submit this form with the button passed in
+      def submit(button=nil)
+        @mech.submit(self, button)
+      end
     end
   end
 end

data/lib/mechanize/form_elements.rb

@@ -213,6 +213,7 @@ module WWW
     alias :selected? :selected
 
     def initialize(node, select_list)
+      node.attributes ||= {}
       @text     = node.all_text
       @value    = node.attributes['value']
       @selected = node.attributes.has_key?('selected') ? true : false

data/lib/mechanize/hpricot.rb

@@ -6,6 +6,9 @@ class Hpricot::Elem
       if child.respond_to? :content
         text << child.content
       end
+      if child.respond_to? :all_text
+        text << child.all_text
+      end
     end
     text
   end

data/lib/mechanize/list.rb

@@ -54,12 +54,16 @@ module WWW
       alias :and :with
 
       def method_missing(meth_sym, *args)
-        return first.send(meth_sym) if args.empty?
-        arg = args.first
-        if arg.class == Regexp
-          WWW::Mechanize::List.new(find_all { |e| e.send(meth_sym) =~ arg })
+        if length > 0
+          return first.send(meth_sym) if args.empty?
+          arg = args.first
+          if arg.class == Regexp
+            WWW::Mechanize::List.new(find_all { |e| e.send(meth_sym) =~ arg })
+          else
+            WWW::Mechanize::List.new(find_all { |e| e.send(meth_sym) == arg })
+          end
         else
-          WWW::Mechanize::List.new(find_all { |e| e.send(meth_sym) == arg })
+          ''
         end
       end
     end

data/lib/mechanize/mech_version.rb

@@ -1,5 +1,5 @@
 module WWW
   class Mechanize
-    Version = '0.6.0'
+    Version = '0.6.1'
   end
 end

data/lib/mechanize/page.rb

@@ -17,16 +17,23 @@ module WWW
     class Page < File
       attr_reader :root, :title, :watch_for_set
       attr_reader :frames, :iframes, :links, :forms, :meta, :watches
+      attr_accessor :mech
 
-      def initialize(uri=nil, response=nil, body=nil, code=nil)
+      def initialize(uri=nil, response=nil, body=nil, code=nil, mech=nil)
         super(uri, response, body, code)
         @watch_for_set = {}
+        @mech          = mech
 
         yield self if block_given?
 
         raise Mechanize::ContentTypeError.new(response['content-type']) unless
             content_type() =~ /^text\/html/ 
-        parse_html if body && response
+
+        # construct parser and feed with HTML
+        if body && response
+          @root = Hpricot.parse(body)
+          parse_html
+        end
       end
     
       # Get the response header
@@ -62,9 +69,6 @@ module WWW
       private
     
       def parse_html
-        # construct parser and feed with HTML
-        @root = Hpricot.parse(@body)
-    
         @forms    = WWW::Mechanize::List.new
         @links    = WWW::Mechanize::List.new
         @meta     = WWW::Mechanize::List.new
@@ -79,14 +83,14 @@ module WWW
 
         # Find all the form tags
         (@root/'form').each do |html_form|
-          form = Form.new(html_form)
+          form = Form.new(html_form, @mech, self)
           form.action ||= @uri
           @forms << form
         end
 
         # Find all the 'a' tags
         (@root/'a').each do |node|
-          @links << Link.new(node)
+          @links << Link.new(node, @mech, self)
         end
 
         # Find all 'meta' tags
@@ -99,19 +103,19 @@ module WWW
           if equiv != nil && equiv.downcase == 'refresh'
             if content != nil && content =~ /^\d+\s*;\s*url\s*=\s*(\S+)/i
               node.attributes['href'] = $1
-              @meta << Meta.new(node)
+              @meta << Meta.new(node, @mech, self)
             end
           end
         end
 
         # Find all 'frame' tags
         (@root/'frame').each do |node|
-          @frames << Frame.new(node)
+          @frames << Frame.new(node, @mech, self)
         end
 
         # Find all 'iframe' tags
         (@root/'iframe').each do |node|
-          @iframes << Frame.new(node)
+          @iframes << Frame.new(node, @mech, self)
         end
 
         # Find all watch tags

data/lib/mechanize/page_elements.rb

@@ -13,13 +13,16 @@ module WWW
       attr_reader :href
       attr_reader :text
       attr_reader :attributes
+      attr_reader :page
       alias :to_s :text
     
-      def initialize(node)
+      def initialize(node, mech, page)
         node.attributes ||= {}
         @node = node
         @href = node.attributes['href'] 
         @text = node.all_text
+        @page = page
+        @mech = mech
         @attributes = node.attributes
 
         # If there is no text, try to find an image and use it's alt text
@@ -36,6 +39,11 @@ module WWW
       def uri
         URI.parse(@href)
       end
+
+      # Click on this link
+      def click
+        @mech.click self
+      end
     end
     
     # This class encapsulates a Meta tag.  Mechanize treats meta tags just
@@ -53,7 +61,8 @@ module WWW
       alias :src :href
       alias :name :text
 
-      def initialize(node)
+      def initialize(node, mech, referer)
+        super(node, mech, referer)
         node.attributes ||= {}
         @node = node
         @text = node.attributes['name']

data/lib/mechanize/parsers/rexml_page.rb

@@ -0,0 +1,37 @@
+require 'web/htmltools/xmltree'
+require 'mechanize/rexml'
+
+class WWW::Mechanize::REXMLPage < WWW::Mechanize::Page
+  def initialize(uri=nil, response=nil, body=nil, code=nil, mech=nil)
+    super(uri, response, body, code)
+    @watch_for_set = {}
+    @mech          = mech
+    
+    yield self if block_given?
+    
+    raise Mechanize::ContentTypeError.new(response['content-type']) unless
+        content_type() =~ /^text\/html/ 
+    
+    # construct parser and feed with HTML
+    parser = HTMLTree::XMLParser.new
+    begin
+      parser.feed(@body)
+    rescue => ex
+      if ex.message =~ /attempted adding second root element to document/ and
+        # Put the whole document inside a single root element, which I
+        # simply name <root>, just to make the parser happy. It's no
+        #longer valid HTML, but without a single root element, it's not
+        # valid HTML as well.
+
+        # TODO: leave a possible doctype definition outside this element.
+        parser = HTMLTree::XMLParser.new
+        parser.feed("<root>" + @body + "</root>")
+      else
+        raise
+      end
+    end
+
+    @root = parser.document
+    parse_html if body && response
+  end
+end

data/lib/mechanize/rexml.rb

@@ -0,0 +1,236 @@
+#
+# Copyright (c) 2005 by Michael Neumann (mneumann@ntecs.de).
+# Released under the same terms of license as Ruby.
+#
+
+require 'rexml/rexml'
+
+class REXML::Text
+  def collect_text_recursively
+    value()
+  end
+end
+
+class REXML::Comment
+  def collect_text_recursively
+    []
+  end
+end
+
+module REXML::Node
+
+# Aliasing functions to get rid of warnings.  Remove when support for 1.8.2
+# is dropped.
+if RUBY_VERSION > "1.8.2"
+  alias :old_each_recursive       :each_recursive
+  alias :old_find_first_recursive :find_first_recursive
+  alias :old_index_in_parent      :index_in_parent
+end
+
+  def search(arg)
+    list = WWW::Mechanize::List.new
+    each_recursive { |n|
+      list << n if n.name.downcase == arg
+    }
+    list
+  end
+
+  alias :/ :search
+
+  # Visit all subnodes of +self+ recursively
+
+  def each_recursive(&block) # :yields: node
+    self.elements.each {|node|
+      block.call(node)
+      node.each_recursive(&block) 
+    }
+  end
+
+  # Find (and return) first subnode (recursively) for which the block evaluates
+  # to true. Returns +nil+ if none was found.
+
+  def find_first_recursive(&block) # :yields: node
+    each_recursive {|node|
+      return node if block.call(node)
+    }
+    return nil
+  end
+
+  # Find all subnodes (recursively) for which the block evaluates to true. 
+
+  def find_all_recursive(&block) # :yields: node
+    arr = []
+    each_recursive {|node|
+      arr << node if block.call(node)
+    }
+    arr
+  end
+
+  # Returns the index that +self+ has in its parent's elements array, so that
+  # the following equation holds true:
+  #
+  #   node == node.parent.elements[node.index_in_parent]
+
+  def index_in_parent
+    parent.index(self)+1
+  end
+
+  # Recursivly collects all text strings starting into an array.
+  #
+  # E.g. the method would return [["abc"], "def"] for this node:
+  # 
+  #   <i><b>abc</b>def</i>
+  
+  def collect_text_recursively
+    map {|n| n.collect_text_recursively}
+  end
+
+  # Returns all text of all subnodes (recursivly), merged into one string.
+  # This is equivalent to:
+  #
+  #   collect_text_recursively.flatten.join("")
+
+  def all_text
+    collect_text_recursively.flatten.join("")
+  end
+
+  alias :text :all_text
+
+end
+
+#
+# Starting with +root_node+, we recursively look for a node with the given
+# +tag+, the given +attributes+ (a Hash) and whoose text equals or matches the
+# +text+ string or regular expression. 
+#
+# To find the following node:
+#
+#   <td class='abc'>text</td>
+#
+# We use:
+#
+#   find_node(root, 'td', {'class' => 'abc'}, "text")
+#
+# Returns +nil+ if no matching node was found. 
+
+def find_node(root_node, tag, attributes, text=nil)
+  root_node.find_first_recursive {|node|
+    node.name == tag and
+    attributes.all? {|attr, val| node.attributes[attr] == val} and
+    (text ? text === node.text : true)
+  }
+end
+
+#
+# Extract specific columns (specified by the position of it's corrensponding
+# header column) from a table. 
+#
+# Given the following table:
+#
+#   <table>
+#     <tr>
+#       <td>A</td>
+#       <td>B</td>
+#       <td>C</td>
+#     </tr>
+#     <tr>
+#       <td>A.1</td>
+#       <td>B.1</td>
+#       <td>C.1</td>
+#     </tr>
+#     <tr>
+#       <td>A.2</td>
+#       <td>B.2</td>
+#       <td>C.2</td>
+#     </tr>
+#   </table>
+#
+# To extract the first (A) and last (C) column:
+#
+#   extract_from_table(root_node, ["A", "C"])  
+#
+# And you get this as result:
+#
+#   [ 
+#     ["A.1", "C.1"],
+#     ["A.2", "C.2"]
+#   ]
+#
+
+def extract_from_table(root_node, headers, header_tags = %w(td th))
+
+  # extract and collect all header nodes
+
+  header_nodes = headers.collect { |header| 
+    root_node.find_first_recursive {|node| 
+      header_tags.include?(node.name.downcase) and header === node.all_text
+    }
+  }
+
+  raise "some headers not found" if header_nodes.compact.size < headers.size
+
+  # assert that all headers have the same parent 'header_row', which is the row
+  # in which the header_nodes are contained. 'table' is the surrounding table tag.
+
+  header_row = header_nodes.first.parent
+  table = header_row.parent 
+
+  raise "different parents" unless header_nodes.all? {|n| n.parent == header_row}
+
+  # we now iterate over all rows in the table that follows the header_row. 
+  # for each row we collect the elements at the same positions as the header_nodes.
+  # this is what we finally return from the method. 
+
+  (header_row.index_in_parent .. table.elements.size).collect do |inx|
+    row = table.elements[inx]
+    header_nodes.collect { |n| row.elements[ n.parent.elements.index(n) ].text }
+  end 
+end
+
+# Given a HTML table, this method returns a matrix (2-dim array), with all the
+# table-data elements correctly placed in it. 
+#
+# If there's a table data element which uses 'colspan', that node is stored in
+# at the current position of the row followed by (colspan-1) nil values.
+#
+# Example:
+#
+#   <table>
+#     <tr>
+#       <td>A</td>
+#       <td>B</td>
+#     </tr>
+#     <tr>
+#       <td colspan="2">C</td>
+#     </tr>
+#   </table>
+#
+# Result:
+#
+#   [
+#     [A, B],
+#     [C, nil]
+#   ]
+#
+# where A, B and C are the corresponding "<td>" nodes.
+#
+
+def table_to_matrix(table_node)
+  matrix = []
+
+  # for each row
+  table_node.elements.each('tr') {|r|
+    row = []
+    r.elements.each {|data|
+      next unless ['td', 'th'].include?(data.name)
+      row << data
+
+      # fill with empty elements
+      colspan = (data.attributes['colspan'] || 1).to_i
+      (colspan - 1).times { row << nil }
+    }
+    matrix << row
+  }
+
+  return matrix
+end

data/test/htdocs/form_select_none.html

@@ -4,6 +4,7 @@
       <select name="list">
         <option value="1">Option 1</option>
         <option value="2">Option 2</option>
+        <option>Option No Value</option>
         <option value="3">Option 3</option>
         <option value="4">Option 4</option>
         <option value="5">Option 5</option>

data/test/htdocs/link with space.html

@@ -0,0 +1,5 @@
+<html>
+  <body>
+    This is a webpage that has a space in the filename.
+  </body>
+</html>

data/test/htdocs/tc_links.html

@@ -0,0 +1,15 @@
+<html>
+  <body>
+    <a href="thing.html"><b>Bold Dude</b></a>
+    <a href="thing.html">Dude</a>
+    <a href="thing.html">Aaron <b>James</b> Patterson</a>
+    <a href="thing.html"><b>Aaron</b> Patterson</a>
+    <a href="thing.html">Ruby <b>Rocks!</b></a>
+    <!-- Testing a bug with escaped stuff in links:
+      http://rubyforge.org/pipermail/mechanize-users/2006-September/000002.html
+    -->
+    <a href="link%20with%20space.html">encoded space</a>
+    <a href="link with space.html">not encoded space</a>
+    <!-- End escaped bug -->
+  </body>
+</html>

data/test/htdocs/tc_referer.html

@@ -0,0 +1,10 @@
+<html>
+  <body>
+    <a href="/referer">Referer Servlet</a>
+    <br />
+    <form method="post" action="/referer">
+      <input type="text" name="first" /></br>
+      <input type="submit" value="Submit" />
+    </form>
+  </body>
+</html>

data/test/server.rb

@@ -23,6 +23,7 @@ s.mount("/file_upload", FileUploadTest)
 s.mount("/bad_content_type", BadContentTypeTest)
 s.mount("/content_type_test", ContentTypeTest)
 s.mount("/gzip", GzipServlet)
+s.mount("/referer", RefererServlet)
 
 htpasswd = WEBrick::HTTPAuth::Htpasswd.new(base_dir + '/data/htpasswd')
 auth = WEBrick::HTTPAuth::BasicAuth.new(

data/test/servlets.rb

@@ -4,6 +4,18 @@ require 'date'
 require 'zlib'
 require 'stringio'
 
+class RefererServlet < WEBrick::HTTPServlet::AbstractServlet
+  def do_GET(req, res)
+    res['Content-Type'] = "text/html"
+    res.body = req['Referer']
+  end
+
+  def do_POST(req, res)
+    res['Content-Type'] = "text/html"
+    res.body = req['Referer']
+  end
+end
+
 class GzipServlet < WEBrick::HTTPServlet::AbstractServlet
   def do_GET(req, res)
     if req['Accept-Encoding'] =~ /gzip/

data/test/tc_cookie_jar.rb

@@ -15,6 +15,34 @@ class CookieJarTest < Test::Unit::TestCase
     }
     c
   end
+
+  def test_domain_case
+    values = {  :name     => 'Foo',
+                :value    => 'Bar',
+                :path     => '/',
+                :expires  => Time.now + (10 * 86400),
+                :domain   => 'rubyforge.org'
+             }
+    url = URI.parse('http://rubyforge.org/')
+
+    jar = WWW::Mechanize::CookieJar.new
+    assert_equal(0, jar.cookies(url).length)
+
+    # Add one cookie with an expiration date in the future
+    cookie = cookie_from_hash(values)
+    jar.add(url, cookie)
+    assert_equal(1, jar.cookies(url).length)
+
+    jar.add(url, cookie_from_hash( values.merge(  :domain => 'RuByForge.Org',
+                                                  :name   => 'aaron'
+                                               ) ) )
+                  
+    assert_equal(2, jar.cookies(url).length)
+
+    url2 = URI.parse('http://RuByFoRgE.oRg/')
+    assert_equal(2, jar.cookies(url2).length)
+  end
+
   def test_add_future_cookies
     values = {  :name     => 'Foo',
                 :value    => 'Bar',

data/test/tc_forms.rb

@@ -39,6 +39,26 @@ class FormsMechTest < Test::Unit::TestCase
     assert_not_nil(page.links.text('first:Patterson').first)
   end
 
+  # Test calling submit on the form object
+  def test_submit_on_form
+    page = @agent.get("http://localhost:#{PORT}/form_multival.html")
+    form = page.forms.name('post_form').first
+
+    assert_not_nil(form)
+    assert_equal(2, form.fields.name('first').length)
+
+    form.fields.name('first')[0].value = 'Aaron'
+    form.fields.name('first')[1].value = 'Patterson'
+
+    page = form.submit
+
+    assert_not_nil(page)
+
+    assert_equal(2, page.links.length)
+    assert_not_nil(page.links.text('first:Aaron').first)
+    assert_not_nil(page.links.text('first:Patterson').first)
+  end
+
   # Test submitting form with two fields of the same name
   def test_get_multival
     page = @agent.get("http://localhost:#{PORT}/form_multival.html")

data/test/tc_links.rb

@@ -46,4 +46,45 @@ class LinksMechTest < Test::Unit::TestCase
     assert_equal("http://localhost:#{PORT}/form_test.html",
       @agent.history.last.uri.to_s)
   end
+
+  def test_click_method
+    page = @agent.get("http://localhost:#{PORT}/frame_test.html")
+    link = page.links.text("Form Test")
+    assert_not_nil(link)
+    assert_equal('Form Test', link.text)
+    page = link.click
+    assert_equal("http://localhost:#{PORT}/form_test.html",
+      @agent.history.last.uri.to_s)
+  end
+
+  def test_find_bold_link
+    page = @agent.get("http://localhost:#{PORT}/tc_links.html")
+    link = page.links.text(/Bold Dude/)
+    assert_equal(1, link.length)
+    assert_equal('Bold Dude', link.first.text)
+
+    link = page.links.text('Aaron James Patterson')
+    assert_equal(1, link.length)
+    assert_equal('Aaron James Patterson', link.first.text)
+
+    link = page.links.text('Aaron Patterson')
+    assert_equal(1, link.length)
+    assert_equal('Aaron Patterson', link.first.text)
+
+    link = page.links.text('Ruby Rocks!')
+    assert_equal(1, link.length)
+    assert_equal('Ruby Rocks!', link.first.text)
+  end
+
+  def test_link_with_encoded_space
+    page = @agent.get("http://localhost:#{PORT}/tc_links.html")
+    link = page.links.text('encoded space').first
+    page = @agent.click link
+  end
+
+  def test_link_with_space
+    page = @agent.get("http://localhost:#{PORT}/tc_links.html")
+    link = page.links.text('not encoded space').first
+    page = @agent.click link
+  end
 end

data/test/tc_referer.rb

@@ -0,0 +1,46 @@
+$:.unshift File.join(File.dirname(__FILE__), "..", "lib")
+
+require 'test/unit'
+require 'rubygems'
+require 'mechanize'
+require 'test_includes'
+
+class RefererTest < Test::Unit::TestCase
+  include TestMethods
+
+  def setup
+    @agent = WWW::Mechanize.new
+  end
+
+  def test_no_referer
+    page = @agent.get("http://localhost:#{PORT}/referer")
+    assert_equal('', page.body)
+  end
+
+  def test_send_referer
+    page = @agent.get("http://localhost:#{PORT}/tc_referer.html")
+    page = @agent.click page.links.first
+    assert_equal("http://localhost:#{PORT}/tc_referer.html", page.body)
+  end
+
+  def test_fetch_two
+    page1 = @agent.get("http://localhost:#{PORT}/tc_referer.html")
+    page2 = @agent.get("http://localhost:#{PORT}/tc_pretty_print.html")
+    page = @agent.click page1.links.first
+    assert_equal("http://localhost:#{PORT}/tc_referer.html", page.body)
+  end
+
+  def test_fetch_two_first
+    page1 = @agent.get("http://localhost:#{PORT}/tc_referer.html")
+    page2 = @agent.get("http://localhost:#{PORT}/tc_pretty_print.html")
+    page = @agent.click page1.links
+    assert_equal("http://localhost:#{PORT}/tc_referer.html", page.body)
+  end
+
+  def test_post_form
+    page1 = @agent.get("http://localhost:#{PORT}/tc_referer.html")
+    page2 = @agent.get("http://localhost:#{PORT}/tc_pretty_print.html")
+    page = @agent.submit page1.forms.first
+    assert_equal("http://localhost:#{PORT}/tc_referer.html", page.body)
+  end
+end

data/test/ts_mech.rb

@@ -40,6 +40,7 @@ require 'tc_pretty_print'
 require 'tc_textarea'
 require 'tc_no_attributes'
 require 'tc_gzipping'
+require 'tc_referer'
 #require 'tc_proxy'
 #require 'tc_ssl_server'
 

metadata

@@ -3,11 +3,11 @@ rubygems_version: 0.9.0
 specification_version: 1
 name: mechanize
 version: !ruby/object:Gem::Version 
-  version: 0.6.0
-date: 2006-09-06 00:00:00 -07:00
+  version: 0.6.1
+date: 2006-09-23 00:00:00 -07:00
 summary: Mechanize provides automated web-browsing
 require_paths: 
-- lib
+  - lib
 email: aaronp@rubyforge.org
 homepage: mechanize.rubyforge.org
 rubyforge_project: mechanize
@@ -18,140 +18,145 @@ bindir: bin
 has_rdoc: true
 required_ruby_version: !ruby/object:Gem::Version::Requirement 
   requirements: 
-  - - ">"
-    - !ruby/object:Gem::Version 
-      version: 0.0.0
+    - 
+      - ">"
+      - !ruby/object:Gem::Version 
+        version: 0.0.0
   version: 
 platform: ruby
 signing_key: 
 cert_chain: 
 post_install_message: 
 authors: 
-- Aaron Patterson
+  - Aaron Patterson
 files: 
-- test/tc_mech.rb
-- test/ts_mech.rb
-- test/tc_no_attributes.rb
-- test/tc_links.rb
-- test/tc_select_all.rb
-- test/tc_page.rb
-- test/test_includes.rb
-- test/tc_checkboxes.rb
-- test/tc_watches.rb
-- test/tc_cookies.rb
-- test/proxy.rb
-- test/data
-- test/tc_cookie_jar.rb
-- test/tc_forms.rb
-- test/tc_select_none.rb
-- test/tc_multi_select.rb
-- test/tc_pluggable_parser.rb
-- test/tc_select_noopts.rb
-- test/ssl_server.rb
-- test/tc_pretty_print.rb
-- test/tc_post_form.rb
-- test/tc_errors.rb
-- test/tc_gzipping.rb
-- test/tc_authenticate.rb
-- test/README
-- test/tc_radiobutton.rb
-- test/tc_form_no_inputname.rb
-- test/tc_upload.rb
-- test/tc_cookie_class.rb
-- test/tc_set_fields.rb
-- test/tc_select.rb
-- test/server.rb
-- test/htdocs
-- test/tc_ssl_server.rb
-- test/tc_textarea.rb
-- test/tc_proxy.rb
-- test/tc_frames.rb
-- test/tc_bad_links.rb
-- test/tc_response_code.rb
-- test/servlets.rb
-- test/tc_save_file.rb
-- test/data/server.key
-- test/data/server.csr
-- test/data/server.pem
-- test/data/server.crt
-- test/data/htpasswd
-- test/htdocs/file_upload.html
-- test/htdocs/tc_no_attributes.html
-- test/htdocs/iframe_test.html
-- test/htdocs/form_select_all.html
-- test/htdocs/form_no_action.html
-- test/htdocs/form_test.html
-- test/htdocs/bad_form_test.html
-- test/htdocs/alt_text.html
-- test/htdocs/frame_test.html
-- test/htdocs/tc_radiobuttons.html
-- test/htdocs/form_multi_select.html
-- test/htdocs/form_set_fields.html
-- test/htdocs/index.html
-- test/htdocs/find_link.html
-- test/htdocs/google.html
-- test/htdocs/no_title_test.html
-- test/htdocs/button.jpg
-- test/htdocs/form_multival.html
-- test/htdocs/tc_bad_links.html
-- test/htdocs/tc_checkboxes.html
-- test/htdocs/tc_textarea.html
-- test/htdocs/form_select_none.html
-- test/htdocs/form_select_noopts.html
-- test/htdocs/form_select.html
-- test/htdocs/form_no_input_name.html
-- test/htdocs/tc_pretty_print.html
-- lib/mechanize.rb
-- lib/mechanize
-- lib/mechanize/errors.rb
-- lib/mechanize/page.rb
-- lib/mechanize/form_elements.rb
-- lib/mechanize/net-overrides
-- lib/mechanize/cookie.rb
-- lib/mechanize/inspect.rb
-- lib/mechanize/mech_version.rb
-- lib/mechanize/list.rb
-- lib/mechanize/hpricot.rb
-- lib/mechanize/pluggable_parsers.rb
-- lib/mechanize/page_elements.rb
-- lib/mechanize/form.rb
-- lib/mechanize/net-overrides/net
-- lib/mechanize/net-overrides/net/http.rb
-- lib/mechanize/net-overrides/net/https.rb
-- lib/mechanize/net-overrides/net/protocol.rb
-- README
-- EXAMPLES
-- CHANGELOG
-- LICENSE
-- NOTES
-- GUIDE
+  - test/data
+  - test/htdocs
+  - test/proxy.rb
+  - test/README
+  - test/server.rb
+  - test/servlets.rb
+  - test/ssl_server.rb
+  - test/tc_authenticate.rb
+  - test/tc_bad_links.rb
+  - test/tc_checkboxes.rb
+  - test/tc_cookie_class.rb
+  - test/tc_cookie_jar.rb
+  - test/tc_cookies.rb
+  - test/tc_errors.rb
+  - test/tc_form_no_inputname.rb
+  - test/tc_forms.rb
+  - test/tc_frames.rb
+  - test/tc_gzipping.rb
+  - test/tc_links.rb
+  - test/tc_mech.rb
+  - test/tc_multi_select.rb
+  - test/tc_no_attributes.rb
+  - test/tc_page.rb
+  - test/tc_pluggable_parser.rb
+  - test/tc_post_form.rb
+  - test/tc_pretty_print.rb
+  - test/tc_proxy.rb
+  - test/tc_radiobutton.rb
+  - test/tc_referer.rb
+  - test/tc_response_code.rb
+  - test/tc_save_file.rb
+  - test/tc_select.rb
+  - test/tc_select_all.rb
+  - test/tc_select_none.rb
+  - test/tc_select_noopts.rb
+  - test/tc_set_fields.rb
+  - test/tc_ssl_server.rb
+  - test/tc_textarea.rb
+  - test/tc_upload.rb
+  - test/tc_watches.rb
+  - test/test_includes.rb
+  - test/ts_mech.rb
+  - test/data/htpasswd
+  - test/data/server.crt
+  - test/data/server.csr
+  - test/data/server.key
+  - test/data/server.pem
+  - test/htdocs/alt_text.html
+  - test/htdocs/bad_form_test.html
+  - test/htdocs/button.jpg
+  - test/htdocs/file_upload.html
+  - test/htdocs/find_link.html
+  - test/htdocs/form_multi_select.html
+  - test/htdocs/form_multival.html
+  - test/htdocs/form_no_action.html
+  - test/htdocs/form_no_input_name.html
+  - test/htdocs/form_select.html
+  - test/htdocs/form_select_all.html
+  - test/htdocs/form_select_none.html
+  - test/htdocs/form_select_noopts.html
+  - test/htdocs/form_set_fields.html
+  - test/htdocs/form_test.html
+  - test/htdocs/frame_test.html
+  - test/htdocs/google.html
+  - test/htdocs/iframe_test.html
+  - test/htdocs/index.html
+  - test/htdocs/link with space.html
+  - test/htdocs/no_title_test.html
+  - test/htdocs/tc_bad_links.html
+  - test/htdocs/tc_checkboxes.html
+  - test/htdocs/tc_links.html
+  - test/htdocs/tc_no_attributes.html
+  - test/htdocs/tc_pretty_print.html
+  - test/htdocs/tc_radiobuttons.html
+  - test/htdocs/tc_referer.html
+  - test/htdocs/tc_textarea.html
+  - lib/mechanize
+  - lib/mechanize.rb
+  - lib/mechanize/cookie.rb
+  - lib/mechanize/errors.rb
+  - lib/mechanize/form.rb
+  - lib/mechanize/form_elements.rb
+  - lib/mechanize/hpricot.rb
+  - lib/mechanize/inspect.rb
+  - lib/mechanize/list.rb
+  - lib/mechanize/mech_version.rb
+  - lib/mechanize/net-overrides
+  - lib/mechanize/page.rb
+  - lib/mechanize/page_elements.rb
+  - lib/mechanize/parsers
+  - lib/mechanize/pluggable_parsers.rb
+  - lib/mechanize/rexml.rb
+  - lib/mechanize/net-overrides/net
+  - lib/mechanize/net-overrides/net/http.rb
+  - lib/mechanize/net-overrides/net/https.rb
+  - lib/mechanize/net-overrides/net/protocol.rb
+  - lib/mechanize/parsers/rexml_page.rb
+  - README
+  - EXAMPLES
+  - CHANGELOG
+  - LICENSE
+  - NOTES
+  - GUIDE
 test_files: []
-
 rdoc_options: 
-- --main
-- README
-- --title
-- "'WWW::Mechanize RDoc'"
+  - "--main"
+  - README
+  - "--title"
+  - "'WWW::Mechanize RDoc'"
 extra_rdoc_files: 
-- README
-- EXAMPLES
-- CHANGELOG
-- LICENSE
-- NOTES
-- GUIDE
+  - README
+  - EXAMPLES
+  - CHANGELOG
+  - LICENSE
+  - NOTES
+  - GUIDE
 executables: []
-
 extensions: []
-
 requirements: []
-
 dependencies: 
-- !ruby/object:Gem::Dependency 
-  name: hpricot
-  version_requirement: 
-  version_requirements: !ruby/object:Gem::Version::Requirement 
-    requirements: 
-    - - ">"
-      - !ruby/object:Gem::Version 
-        version: 0.0.0
-    version: 
+  - !ruby/object:Gem::Dependency 
+    name: hpricot
+    version_requirement: 
+    version_requirements: !ruby/object:Gem::Version::Requirement 
+      requirements: 
+        - 
+          - ">"
+          - !ruby/object:Gem::Version 
+            version: 0.0.0
+      version: