RubyGems - tenderlove-nokogiri - Versions diffs - 0.0.0.20081001111445 - Mend

tenderlove-nokogiri 0.0.0.20081001111445

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (104) hide show

data/History.txt +6 -0
data/Manifest.txt +105 -0
data/README.txt +51 -0
data/Rakefile +70 -0
data/ext/nokogiri/extconf.rb +24 -0
data/ext/nokogiri/html_document.c +85 -0
data/ext/nokogiri/html_document.h +10 -0
data/ext/nokogiri/html_sax_parser.c +32 -0
data/ext/nokogiri/html_sax_parser.h +11 -0
data/ext/nokogiri/native.c +35 -0
data/ext/nokogiri/native.h +32 -0
data/ext/nokogiri/xml_cdata.c +36 -0
data/ext/nokogiri/xml_cdata.h +9 -0
data/ext/nokogiri/xml_document.c +159 -0
data/ext/nokogiri/xml_document.h +10 -0
data/ext/nokogiri/xml_node.c +573 -0
data/ext/nokogiri/xml_node.h +13 -0
data/ext/nokogiri/xml_node_set.c +90 -0
data/ext/nokogiri/xml_node_set.h +9 -0
data/ext/nokogiri/xml_reader.c +420 -0
data/ext/nokogiri/xml_reader.h +10 -0
data/ext/nokogiri/xml_sax_parser.c +161 -0
data/ext/nokogiri/xml_sax_parser.h +10 -0
data/ext/nokogiri/xml_text.c +25 -0
data/ext/nokogiri/xml_text.h +9 -0
data/ext/nokogiri/xml_xpath.c +39 -0
data/ext/nokogiri/xml_xpath.h +11 -0
data/ext/nokogiri/xml_xpath_context.c +69 -0
data/ext/nokogiri/xml_xpath_context.h +9 -0
data/ext/nokogiri/xslt_stylesheet.c +83 -0
data/ext/nokogiri/xslt_stylesheet.h +9 -0
data/lib/nokogiri.rb +45 -0
data/lib/nokogiri/css.rb +6 -0
data/lib/nokogiri/css/node.rb +95 -0
data/lib/nokogiri/css/parser.rb +24 -0
data/lib/nokogiri/css/parser.y +198 -0
data/lib/nokogiri/css/tokenizer.rb +9 -0
data/lib/nokogiri/css/tokenizer.rex +63 -0
data/lib/nokogiri/css/xpath_visitor.rb +153 -0
data/lib/nokogiri/decorators.rb +1 -0
data/lib/nokogiri/decorators/hpricot.rb +3 -0
data/lib/nokogiri/decorators/hpricot/node.rb +47 -0
data/lib/nokogiri/decorators/hpricot/node_set.rb +14 -0
data/lib/nokogiri/decorators/hpricot/xpath_visitor.rb +13 -0
data/lib/nokogiri/hpricot.rb +46 -0
data/lib/nokogiri/html.rb +64 -0
data/lib/nokogiri/html/builder.rb +9 -0
data/lib/nokogiri/html/document.rb +9 -0
data/lib/nokogiri/html/sax/parser.rb +21 -0
data/lib/nokogiri/version.rb +3 -0
data/lib/nokogiri/xml.rb +29 -0
data/lib/nokogiri/xml/after_handler.rb +18 -0
data/lib/nokogiri/xml/before_handler.rb +32 -0
data/lib/nokogiri/xml/builder.rb +79 -0
data/lib/nokogiri/xml/document.rb +22 -0
data/lib/nokogiri/xml/node.rb +162 -0
data/lib/nokogiri/xml/node_set.rb +136 -0
data/lib/nokogiri/xml/reader.rb +14 -0
data/lib/nokogiri/xml/sax.rb +9 -0
data/lib/nokogiri/xml/sax/document.rb +59 -0
data/lib/nokogiri/xml/sax/parser.rb +33 -0
data/lib/nokogiri/xml/text.rb +6 -0
data/lib/nokogiri/xml/xpath.rb +6 -0
data/lib/nokogiri/xslt.rb +11 -0
data/lib/nokogiri/xslt/stylesheet.rb +6 -0
data/nokogiri.gemspec +33 -0
data/test/css/test_nthiness.rb +141 -0
data/test/css/test_parser.rb +214 -0
data/test/css/test_tokenizer.rb +162 -0
data/test/files/staff.xml +57 -0
data/test/files/staff.xslt +32 -0
data/test/files/tlm.html +850 -0
data/test/helper.rb +70 -0
data/test/hpricot/files/basic.xhtml +17 -0
data/test/hpricot/files/boingboing.html +2266 -0
data/test/hpricot/files/cy0.html +3653 -0
data/test/hpricot/files/immob.html +400 -0
data/test/hpricot/files/pace_application.html +1320 -0
data/test/hpricot/files/tenderlove.html +16 -0
data/test/hpricot/files/uswebgen.html +220 -0
data/test/hpricot/files/utf8.html +1054 -0
data/test/hpricot/files/week9.html +1723 -0
data/test/hpricot/files/why.xml +19 -0
data/test/hpricot/load_files.rb +7 -0
data/test/hpricot/test_alter.rb +67 -0
data/test/hpricot/test_builder.rb +27 -0
data/test/hpricot/test_parser.rb +412 -0
data/test/hpricot/test_paths.rb +15 -0
data/test/hpricot/test_preserved.rb +72 -0
data/test/hpricot/test_xml.rb +26 -0
data/test/html/sax/test_parser.rb +27 -0
data/test/html/test_builder.rb +78 -0
data/test/html/test_document.rb +22 -0
data/test/test_convert_xpath.rb +173 -0
data/test/test_nokogiri.rb +36 -0
data/test/test_reader.rb +222 -0
data/test/test_xslt_transforms.rb +29 -0
data/test/xml/sax/test_parser.rb +93 -0
data/test/xml/test_builder.rb +16 -0
data/test/xml/test_document.rb +141 -0
data/test/xml/test_node.rb +148 -0
data/test/xml/test_node_set.rb +54 -0
data/test/xml/test_text.rb +13 -0
metadata +191 -0

data/test/hpricot/test_paths.rb ADDED

@@ -0,0 +1,15 @@
+require File.expand_path(File.join(File.dirname(__FILE__), '..', "helper"))
+require File.join(File.dirname(__FILE__),"load_files")
+class TestParser < Nokogiri::TestCase
+  include Nokogiri
+  def test_roundtrip
+    @basic = Hpricot.parse(TestFiles::BASIC)
+    %w[link link[2] body #link1 a p.ohmy].each do |css_sel|
+      ele = @basic.at(css_sel)
+      assert_equal ele, @basic.at(ele.css_path), ele.css_path
+      assert_equal ele, @basic.at(ele.xpath), ele.xpath
+    end
+  end
+end

data/test/hpricot/test_preserved.rb ADDED

@@ -0,0 +1,72 @@
+require File.expand_path(File.join(File.dirname(__FILE__), '..', "helper"))
+require File.join(File.dirname(__FILE__),"load_files")
+class TestPreserved < Nokogiri::TestCase
+  def assert_roundtrip str
+    doc = Nokogiri.Hpricot(str)
+    yield doc if block_given?
+    str2 = doc.to_original_html
+    [*str].zip([*str2]).each do |s1, s2|
+      assert_equal s1, s2
+    end
+  end
+  def assert_html str1, str2
+    doc = Nokogiri.Hpricot(str2)
+    yield doc if block_given?
+    assert_equal str1, doc.to_original_html
+  end
+  ####
+  # Not supporting to_original_html
+  #def test_simple
+  #  str = "<p>Hpricot is a <b>you know <i>uh</b> fine thing.</p>"
+  #  assert_html str, str
+  #  assert_html "<p class=\"new\">Hpricot is a <b>you know <i>uh</b> fine thing.</p>", str do |doc|
+  #    (doc/:p).set('class', 'new')
+  #  end
+  #end
+  ####
+  # Not supporting to_original_html
+  #def test_parent
+  #  str = "<html><base href='/'><head><title>Test</title></head><body><div id='wrap'><p>Paragraph one.</p><p>Paragraph two.</p></div></body></html>"
+  #  assert_html str, str
+  #  assert_html "<html><base href='/'><body><div id=\"all\"><div><p>Paragraph one.</p></div><div><p>Paragraph two.</p></div></div></body></html>", str do |doc|
+  #    (doc/:head).remove
+  #    (doc/:div).set('id', 'all')
+  #    (doc/:p).wrap('<div></div>')
+  #  end
+  #end
+  def test_escaping_of_contents
+    doc = Nokogiri.Hpricot(TestFiles::BOINGBOING)
+    assert_equal "Fukuda&#x2019;s Automatic Door opens around your body as you pass through it. The idea is to save energy and keep the room clean.", doc.at("img[@alt='200606131240']").next.to_s.strip
+  end
+  ####
+  # Modified.  No.
+  #def test_files
+  #  assert_roundtrip TestFiles::BASIC
+  #  assert_roundtrip TestFiles::BOINGBOING
+  #  assert_roundtrip TestFiles::CY0
+  #end
+  ####
+  # Modified..  When calling "to_html" on the document, proper html/doc tags
+  # are produced too.
+  def test_escaping_of_attrs
+    # ampersands in URLs
+    str = %{<a href="http://google.com/search?q=nokogiri&amp;l=en">Google</a>}
+    link = (doc = Nokogiri.Hpricot(str)).at(:a)
+    assert_equal "http://google.com/search?q=nokogiri&l=en", link['href']
+    assert_equal "http://google.com/search?q=nokogiri&l=en", link.attributes['href']
+    assert_equal "http://google.com/search?q=nokogiri&l=en", link.get_attribute('href')
+    assert_equal "http://google.com/search?q=nokogiri&l=en", link.raw_attributes['href']
+    assert_equal str, link.to_html
+    # alter the url
+    link['href'] = "javascript:alert(\"AGGA-KA-BOO!\")"
+    assert_equal %{<a href="javascript:alert(&quot;AGGA-KA-BOO!&quot;)">Google</a>}, link.to_html
+  end
+end

data/test/hpricot/test_xml.rb ADDED

@@ -0,0 +1,26 @@
+require File.expand_path(File.join(File.dirname(__FILE__), '..', "helper"))
+require File.join(File.dirname(__FILE__),"load_files")
+class TestParser < Nokogiri::TestCase
+  include Nokogiri
+  # normally, the link tags are empty HTML tags.
+  # contributed by laudney.
+  def test_normally_empty
+    doc = Hpricot::XML("<rss><channel><title>this is title</title><link>http://fake.com</link></channel></rss>")
+    assert_equal "this is title", (doc/:rss/:channel/:title).text
+    assert_equal "http://fake.com", (doc/:rss/:channel/:link).text
+  end
+  # make sure XML doesn't get downcased
+  def test_casing
+    doc = Hpricot::XML(TestFiles::WHY)
+    assert_equal "hourly", (doc.at "sy:updatePeriod").inner_html
+    assert_equal 1, (doc/"guid[@isPermaLink]").length
+  end
+  # be sure tags named "text" are ok
+  def test_text_tags
+    doc = Hpricot::XML("<feed><title>City Poisoned</title><text>Rita Lee has poisoned Brazil.</text></feed>")
+    assert_equal "City Poisoned", (doc/"title").text
+  end
+end

data/test/html/sax/test_parser.rb ADDED

@@ -0,0 +1,27 @@
+require File.expand_path(File.join(File.dirname(__FILE__), '..', '..', "helper"))
+module Nokogiri
+  module HTML
+    module SAX
+      class TestParser < Nokogiri::SAX::TestCase
+        def setup
+          @parser = HTML::SAX::Parser.new(Doc.new)
+        end
+        def test_parse_file
+          @parser.parse_file(HTML_FILE)
+          assert_equal 1110, @parser.document.end_elements.length
+        end
+        def test_parse_document
+          @parser.parse_memory(<<-eoxml)
+            <p>Paragraph 1</p>
+            <p>Paragraph 2</p>
+          eoxml
+          assert_equal([["html", []], ["body", []], ["p", []], ["p", []]],
+                       @parser.document.start_elements)
+        end
+      end
+    end
+  end
+end

data/test/html/test_builder.rb ADDED

@@ -0,0 +1,78 @@
+require File.expand_path(File.join(File.dirname(__FILE__), '..', "helper"))
+module Nokogiri
+  module HTML
+    class TestBuilder < Nokogiri::TestCase
+      def test_hash_as_attributes
+        builder = Nokogiri::HTML::Builder.new do
+          div(:id => 'awesome') {
+            h1 "america"
+          }
+        end
+        assert_equal('<div id="awesome"><h1>america</h1></div>',
+                     builder.to_html.gsub(/\n/, ''))
+      end
+      def test_has_ampersand
+        builder = Nokogiri::HTML::Builder.new do
+          div.rad.thing! {
+            text "<awe&some>"
+            b "hello & world"
+          }
+        end
+        assert_equal(
+          '<div class="rad" id="thing">&lt;awe&amp;some&gt;<b>hello &amp; world</b></div>',
+                     builder.to_html.gsub(/\n/, ''))
+      end
+      def test_multi_tags
+        builder = Nokogiri::HTML::Builder.new do
+          div.rad.thing! {
+            text "<awesome>"
+            b "hello"
+          }
+        end
+        assert_equal(
+          '<div class="rad" id="thing">&lt;awesome&gt;<b>hello</b></div>',
+                     builder.doc.to_html.gsub(/\n/, ''))
+      end
+      def test_attributes_plus_block
+        builder = Nokogiri::HTML::Builder.new do
+          div.rad.thing! {
+            text "<awesome>"
+          }
+        end
+        assert_equal('<div class="rad" id="thing">&lt;awesome&gt;</div>',
+                     builder.doc.to_html.chomp)
+      end
+      def test_builder_adds_attributes
+        builder = Nokogiri::HTML::Builder.new do
+          div.rad.thing! "tender div"
+        end
+        assert_equal('<div class="rad" id="thing">tender div</div>',
+                     builder.doc.to_html.chomp)
+      end
+      def test_bold_tag
+        builder = Nokogiri::HTML::Builder.new do
+          b "bold tag"
+        end
+        assert_equal('<b>bold tag</b>', builder.doc.to_html.chomp)
+      end
+      def test_html_then_body_tag
+        builder = Nokogiri::HTML::Builder.new do
+          html {
+            body {
+              b "bold tag"
+            }
+          }
+        end
+        assert_equal('<html><body><b>bold tag</b></body></html>',
+                     builder.doc.to_html.chomp)
+      end
+    end
+  end
+end

data/test/html/test_document.rb ADDED

@@ -0,0 +1,22 @@
+require File.expand_path(File.join(File.dirname(__FILE__), '..', "helper"))
+module Nokogiri
+  module HTML
+    class TestDocument < Nokogiri::TestCase
+      def setup
+        @html = Nokogiri::HTML.parse(File.read(HTML_FILE))
+      end
+      def test_html?
+        assert !@html.xml?
+        assert @html.html?
+      end
+      def test_serialize
+        assert @html.serialize
+        assert @html.to_html
+      end
+    end
+  end
+end

data/test/test_convert_xpath.rb ADDED

@@ -0,0 +1,173 @@
+require File.expand_path(File.join(File.dirname(__FILE__), "helper"))
+require 'rubygems'
+require 'hpricot'
+class TestConvertXPath < Nokogiri::TestCase
+  def setup
+    @N = Nokogiri(File.read(HTML_FILE))
+    @NH = Nokogiri.Hpricot(File.read(HTML_FILE)) # decorated document
+    @H = Hpricot(File.read(HTML_FILE))
+  end
+  def assert_syntactical_equivalence(hpath, xpath, match, &blk)
+    blk ||= lambda {|j| j.first}
+    assert_equal match, blk.call(@N.search(xpath)), "xpath result did not match"
+    assert_equal match, blk.call(@H.search(hpath)), "hpath result did not match"
+    assert_equal [xpath], @NH.convert_to_xpath(hpath), "converted hpath did not match xpath"
+  end
+  def test_ordinary_xpath_conversions
+    assert_equal(".//p", @NH.convert_to_xpath("p").first)
+    assert_equal(".//p", @NH.convert_to_xpath(:p).first)
+    assert_equal(".//p", @NH.convert_to_xpath("//p").first)
+    assert_equal(".//p", @NH.convert_to_xpath(".//p").first)
+  end
+  def test_child_tag
+    assert_syntactical_equivalence("h1[a]", ".//h1[child::a]", "Tender Lovemaking") do |j|
+      j.inner_text
+    end
+  end
+  def test_child_tag_equals
+    assert_syntactical_equivalence("h1[a='Tender Lovemaking']", ".//h1[child::a = 'Tender Lovemaking']", "Tender Lovemaking") do |j|
+      j.inner_text
+    end
+  end
+  def test_filter_contains
+    assert_syntactical_equivalence("title:contains('Tender')", ".//title[contains(., 'Tender')]",
+                                   "Tender Lovemaking  ") do |j|
+      j.inner_text
+    end
+  end
+  def test_filter_comment
+    assert_syntactical_equivalence("div comment()[2]", ".//div//comment()[position() = 2]", "<!-- end of header -->") do |j|
+      j.first.to_s
+    end
+  end
+  def test_filter_text
+    assert_syntactical_equivalence("a[text()]", ".//a[normalize-space(child::text())]", "<a href=\"http://tenderlovemaking.com\">Tender Lovemaking</a>") do |j|
+      j.first.to_s
+    end
+    assert_syntactical_equivalence("a[text()='Tender Lovemaking']", ".//a[normalize-space(child::text()) = 'Tender Lovemaking']", "<a href=\"http://tenderlovemaking.com\">Tender Lovemaking</a>") do |j|
+      j.first.to_s
+    end
+    assert_syntactical_equivalence("a/text()", ".//a/child::text()", "Tender Lovemaking") do |j|
+      j.first.to_s
+    end
+    assert_syntactical_equivalence("h2//a[text()!='Back Home!']", ".//h2//a[normalize-space(child::text()) != 'Back Home!']", "Meow meow meow meow meow") do |j|
+      j.first.inner_text
+    end
+  end
+  def test_filter_by_attr
+    assert_syntactical_equivalence("a[@href='http://blog.geminigeek.com/wordpress-theme']",
+                                   ".//a[@href = 'http://blog.geminigeek.com/wordpress-theme']",
+                                   "http://blog.geminigeek.com/wordpress-theme") do |j|
+      j.first["href"]
+    end
+  end
+  def test_css_id
+    assert_syntactical_equivalence("#linkcat-7", ".//*[@id = 'linkcat-7']", "linkcat-7") do |j|
+      j.first["id"]
+    end
+    assert_syntactical_equivalence("li#linkcat-7", ".//li[@id = 'linkcat-7']", "linkcat-7") do |j|
+      j.first["id"]
+    end
+  end
+  def test_css_class
+    assert_syntactical_equivalence(".cat-item-15", ".//*[contains(@class, 'cat-item-15')]",
+                                   "cat-item cat-item-15") do |j|
+      j.first["class"]
+    end
+    assert_syntactical_equivalence("li.cat-item-15", ".//li[contains(@class, 'cat-item-15')]",
+                                   "cat-item cat-item-15") do |j|
+      j.first["class"]
+    end
+  end
+  def test_css_tags
+    assert_syntactical_equivalence("div li a", ".//div//li//a", "http://brobinius.org/") do |j|
+      j.first.inner_text
+    end
+    assert_syntactical_equivalence("div li > a", ".//div//li/a", "http://brobinius.org/") do |j|
+      j.first.inner_text
+    end
+    assert_syntactical_equivalence("h1 ~ small", ".//small[preceding-sibling::h1]", "The act of making love, tenderly.") do |j|
+      j.first.inner_text
+    end
+    assert_syntactical_equivalence("h1 ~ small", ".//small[preceding-sibling::h1]", "The act of making love, tenderly.") do |j|
+      j.first.inner_text
+    end
+  end
+  def test_positional
+##
+#  we are intentionally NOT staying compatible with nth-and-friends, as Hpricot has an OB1 bug.
+#
+#     assert_syntactical_equivalence("div > div:eq(0)", ".//div/div[position() = 1]", "\r\nTender Lovemaking\r\nThe act of making love, tenderly.\r\n") do |j|
+#       j.first.inner_text
+#     end
+#     assert_syntactical_equivalence("div/div:eq(0)", ".//div/div[position() = 1]", "\r\nTender Lovemaking\r\nThe act of making love, tenderly.\r\n") do |j|
+#       j.first.inner_text
+#     end
+#     assert_syntactical_equivalence("div/div:nth(0)", ".//div/div[position() = 1]", "\r\nTender Lovemaking\r\nThe act of making love, tenderly.\r\n") do |j|
+#       j.first.inner_text
+#     end
+#     assert_syntactical_equivalence("div/div:nth-of-type(0)", ".//div/div[position() = 1]", "\r\nTender Lovemaking\r\nThe act of making love, tenderly.\r\n") do |j|
+#       j.first.inner_text
+#     end
+    assert_syntactical_equivalence("div/div:first()", ".//div/div[position() = 1]", "\r\nTender Lovemaking\r\nThe act of making love, tenderly.\r\n") do |j|
+      j.first.inner_text
+    end
+    assert_syntactical_equivalence("div/div:first", ".//div/div[position() = 1]", "\r\nTender Lovemaking\r\nThe act of making love, tenderly.\r\n") do |j|
+      j.first.inner_text
+    end
+    assert_syntactical_equivalence("div//a:last()", ".//div//a[position() = last()]", "Wordpress") do |j|
+      j.last.inner_text
+    end
+    assert_syntactical_equivalence("div//a:last", ".//div//a[position() = last()]", "Wordpress") do |j|
+      j.last.inner_text
+    end
+  end
+  def test_multiple_filters
+    assert_syntactical_equivalence("a[@rel='bookmark'][1]", ".//a[@rel = 'bookmark' and position() = 1]", "Back Home!") do |j|
+      j.first.inner_text
+    end
+  end
+  ##
+  #  'and' is not supported by hpricot
+#   def test_and
+#     assert_syntactical_equivalence("div[h1 and small]", ".//div[h1 and small]", "\r\nTender Lovemaking\r\nThe act of making love, tenderly.\r\n") do |j|
+#       j.inner_text
+#     end
+#   end
+# TODO:
+#       doc/'title ~ link' -> links that are siblings of title
+#       doc/'p[@class~="final"]' -> class includes string (whitespacy)
+#       doc/'p[text()*="final"]' -> class includes string (index) (broken: always returns true?)
+#       doc/'p[text()$="final"]' -> /final$/
+#       doc/'p[text()|="final"]' -> /^final$/
+#       doc/'p[text()^="final"]' -> string starts with 'final
+#       nth_first
+#       nth_last
+#       even
+#       odd
+#       first-child, nth-child, last-child, nth-last-child, nth-last-of-type
+#       only-of-type, only-child
+#       parent
+#       empty
+#       root
+end

data/test/test_nokogiri.rb ADDED

@@ -0,0 +1,36 @@
+require File.expand_path(File.join(File.dirname(__FILE__), "helper"))
+class TestNokogiri < Nokogiri::TestCase
+  def test_xml?
+    doc = Nokogiri.parse(File.read(XML_FILE))
+    assert doc.xml?
+    assert !doc.html?
+  end
+  def test_html?
+    doc = Nokogiri.parse(File.read(HTML_FILE))
+    assert !doc.xml?
+    assert doc.html?
+  end
+  def test_nokogiri_method_with_html
+    doc1 = Nokogiri(File.read(HTML_FILE))
+    doc2 = Nokogiri.parse(File.read(HTML_FILE))
+    assert_equal doc1.serialize, doc2.serialize
+  end
+  def test_nokogiri_method_with_block
+    doc = Nokogiri { b "bold tag" }
+    assert_equal('<b>bold tag</b>', doc.to_html.chomp)
+  end
+  def test_make_with_html
+    doc = Nokogiri.make("<b>bold tag</b>")
+    assert_equal('<b>bold tag</b>', doc.to_html.chomp)
+  end
+  def test_make_with_block
+    doc = Nokogiri.make { b "bold tag" }
+    assert_equal('<b>bold tag</b>', doc.to_html.chomp)
+  end
+end