RubyGems - nokogiri - Versions diffs - 1.9.0.rc1 → 1.9.0 - Mend

nokogiri 1.9.0.rc1 → 1.9.0

Potentially problematic release.

This version of nokogiri might be problematic. Click here for more details.

Files changed (137) hide show

checksums.yaml +4 -4
data/lib/nokogiri/css/parser.rb +61 -61
data/lib/nokogiri/version.rb +1 -1
metadata +4 -146
data/.autotest +0 -22
data/.cross_rubies +0 -8
data/.editorconfig +0 -17
data/.gemtest +0 -0
data/.travis.yml +0 -63
data/CHANGELOG.md +0 -1402
data/CONTRIBUTING.md +0 -42
data/C_CODING_STYLE.rdoc +0 -33
data/Gemfile +0 -23
data/Gemfile-libxml-ruby +0 -3
data/Manifest.txt +0 -371
data/ROADMAP.md +0 -111
data/Rakefile +0 -358
data/SECURITY.md +0 -19
data/STANDARD_RESPONSES.md +0 -47
data/Y_U_NO_GEMSPEC.md +0 -155
data/appveyor.yml +0 -29
data/build_all +0 -48
data/patches/sort-patches-by-date +0 -25
data/suppressions/README.txt +0 -1
data/suppressions/nokogiri_ruby-2.supp +0 -10
data/tasks/test.rb +0 -100
data/test/css/test_nthiness.rb +0 -226
data/test/css/test_parser.rb +0 -386
data/test/css/test_tokenizer.rb +0 -215
data/test/css/test_xpath_visitor.rb +0 -96
data/test/decorators/test_slop.rb +0 -23
data/test/files/2ch.html +0 -108
data/test/files/GH_1042.html +0 -18
data/test/files/address_book.rlx +0 -12
data/test/files/address_book.xml +0 -10
data/test/files/atom.xml +0 -344
data/test/files/bar/bar.xsd +0 -4
data/test/files/bogus.xml +0 -0
data/test/files/dont_hurt_em_why.xml +0 -422
data/test/files/encoding.html +0 -82
data/test/files/encoding.xhtml +0 -84
data/test/files/exslt.xml +0 -8
data/test/files/exslt.xslt +0 -35
data/test/files/foo/foo.xsd +0 -4
data/test/files/metacharset.html +0 -10
data/test/files/namespace_pressure_test.xml +0 -1684
data/test/files/noencoding.html +0 -47
data/test/files/po.xml +0 -32
data/test/files/po.xsd +0 -66
data/test/files/saml/saml20assertion_schema.xsd +0 -283
data/test/files/saml/saml20protocol_schema.xsd +0 -302
data/test/files/saml/xenc_schema.xsd +0 -146
data/test/files/saml/xmldsig_schema.xsd +0 -318
data/test/files/shift_jis.html +0 -10
data/test/files/shift_jis.xml +0 -5
data/test/files/shift_jis_no_charset.html +0 -9
data/test/files/slow-xpath.xml +0 -25509
data/test/files/snuggles.xml +0 -3
data/test/files/staff.dtd +0 -10
data/test/files/staff.xml +0 -59
data/test/files/staff.xslt +0 -32
data/test/files/test_document_url/bar.xml +0 -2
data/test/files/test_document_url/document.dtd +0 -4
data/test/files/test_document_url/document.xml +0 -6
data/test/files/tlm.html +0 -851
data/test/files/to_be_xincluded.xml +0 -2
data/test/files/valid_bar.xml +0 -2
data/test/files/xinclude.xml +0 -4
data/test/helper.rb +0 -271
data/test/html/sax/test_parser.rb +0 -168
data/test/html/sax/test_parser_context.rb +0 -46
data/test/html/sax/test_parser_text.rb +0 -163
data/test/html/sax/test_push_parser.rb +0 -87
data/test/html/test_attributes.rb +0 -85
data/test/html/test_builder.rb +0 -164
data/test/html/test_document.rb +0 -722
data/test/html/test_document_encoding.rb +0 -143
data/test/html/test_document_fragment.rb +0 -310
data/test/html/test_element_description.rb +0 -105
data/test/html/test_named_characters.rb +0 -14
data/test/html/test_node.rb +0 -212
data/test/html/test_node_encoding.rb +0 -91
data/test/namespaces/test_additional_namespaces_in_builder_doc.rb +0 -14
data/test/namespaces/test_namespaces_aliased_default.rb +0 -24
data/test/namespaces/test_namespaces_in_builder_doc.rb +0 -75
data/test/namespaces/test_namespaces_in_cloned_doc.rb +0 -31
data/test/namespaces/test_namespaces_in_created_doc.rb +0 -75
data/test/namespaces/test_namespaces_in_parsed_doc.rb +0 -80
data/test/namespaces/test_namespaces_preservation.rb +0 -31
data/test/test_convert_xpath.rb +0 -135
data/test/test_css_cache.rb +0 -47
data/test/test_encoding_handler.rb +0 -48
data/test/test_memory_leak.rb +0 -226
data/test/test_nokogiri.rb +0 -138
data/test/test_soap4r_sax.rb +0 -52
data/test/test_xslt_transforms.rb +0 -314
data/test/xml/node/test_save_options.rb +0 -28
data/test/xml/node/test_subclass.rb +0 -44
data/test/xml/sax/test_parser.rb +0 -402
data/test/xml/sax/test_parser_context.rb +0 -115
data/test/xml/sax/test_parser_text.rb +0 -202
data/test/xml/sax/test_push_parser.rb +0 -265
data/test/xml/test_attr.rb +0 -96
data/test/xml/test_attribute_decl.rb +0 -86
data/test/xml/test_builder.rb +0 -353
data/test/xml/test_c14n.rb +0 -180
data/test/xml/test_cdata.rb +0 -54
data/test/xml/test_comment.rb +0 -40
data/test/xml/test_document.rb +0 -982
data/test/xml/test_document_encoding.rb +0 -31
data/test/xml/test_document_fragment.rb +0 -312
data/test/xml/test_dtd.rb +0 -187
data/test/xml/test_dtd_encoding.rb +0 -31
data/test/xml/test_element_content.rb +0 -56
data/test/xml/test_element_decl.rb +0 -73
data/test/xml/test_entity_decl.rb +0 -122
data/test/xml/test_entity_reference.rb +0 -262
data/test/xml/test_namespace.rb +0 -96
data/test/xml/test_node.rb +0 -1379
data/test/xml/test_node_attributes.rb +0 -115
data/test/xml/test_node_encoding.rb +0 -75
data/test/xml/test_node_inheritance.rb +0 -32
data/test/xml/test_node_reparenting.rb +0 -661
data/test/xml/test_node_set.rb +0 -828
data/test/xml/test_parse_options.rb +0 -64
data/test/xml/test_processing_instruction.rb +0 -30
data/test/xml/test_reader.rb +0 -620
data/test/xml/test_reader_encoding.rb +0 -134
data/test/xml/test_relax_ng.rb +0 -60
data/test/xml/test_schema.rb +0 -142
data/test/xml/test_syntax_error.rb +0 -36
data/test/xml/test_text.rb +0 -69
data/test/xml/test_unparented_node.rb +0 -483
data/test/xml/test_xinclude.rb +0 -83
data/test/xml/test_xpath.rb +0 -470
data/test/xslt/test_custom_functions.rb +0 -133
data/test/xslt/test_exception_handling.rb +0 -37

data/test/html/sax/test_parser_context.rb DELETED

@@ -1,46 +0,0 @@
-# -*- coding: utf-8 -*-
-require "helper"
-module Nokogiri
-  module HTML
-    module SAX
-      class TestParserContext < Nokogiri::SAX::TestCase
-        def test_from_io
-          ctx = ParserContext.new StringIO.new('fo'), 'UTF-8'
-          assert ctx
-        end
-        def test_from_string
-          ctx = ParserContext.new 'blah blah'
-          assert ctx
-        end
-        def test_parse_with
-          ctx = ParserContext.new 'blah'
-          assert_raises ArgumentError do
-            ctx.parse_with nil
-          end
-        end
-        def test_parse_with_sax_parser
-          # assert_nothing_raised do
-            xml = "<root />"
-            ctx = ParserContext.new xml
-            parser = Parser.new Doc.new
-            ctx.parse_with parser
-          # end
-        end
-        def test_from_file
-          # assert_nothing_raised do
-            ctx = ParserContext.file HTML_FILE, 'UTF-8'
-            parser = Parser.new Doc.new
-            ctx.parse_with parser
-          # end
-        end
-      end
-    end
-  end
-end

data/test/html/sax/test_parser_text.rb DELETED

@@ -1,163 +0,0 @@
-# -*- coding: utf-8 -*-
-require "helper"
-module Nokogiri
-  module HTML
-    module SAX
-      class TestParserText < Nokogiri::SAX::TestCase
-        def setup
-          super
-          @doc    = DocWithOrderedItems.new
-          @parser = HTML::SAX::Parser.new @doc
-        end
-        def test_texts_order
-          html = <<-eohtml
-            <!DOCTYPE html>
-            <html>
-              <head></head>
-              <body>
-                text 0
-                <p>
-                  text 1
-                  <span>text 2</span>
-                  text 3
-                </p>
-                text 4
-                <!--
-                text 5
-                -->
-                <p>
-                  <!-- text 6 -->
-                  <span><!-- text 7 --></span>
-                  <!-- text 8 -->
-                </p>
-                <!-- text 9 -->
-              </body>
-            </html>
-          eohtml
-          @parser.parse html
-          items = @doc.items.get_root_content "body"
-          items = items.select_methods [
-            :start_element, :end_element,
-            :characters, :comment
-          ]
-          items.strip_text! [:characters, :comment]
-          assert_equal [
-            [:characters, 'text 0'],
-            [:start_element, 'p', []],
-            [:characters, 'text 1'],
-            [:start_element, 'span', []],
-            [:characters, 'text 2'],
-            [:end_element, 'span'],
-            [:characters, 'text 3'],
-            [:end_element, 'p'],
-            [:characters, 'text 4'],
-            [:comment, 'text 5'],
-            [:characters, ''],
-            [:start_element, 'p', []],
-            [:characters, ''],
-            [:comment, 'text 6'],
-            [:characters, ''],
-            [:start_element, 'span', []],
-            [:comment, 'text 7'],
-            [:end_element, 'span'],
-            [:characters, ''],
-            [:comment, 'text 8'],
-            [:characters, ''],
-            [:end_element, 'p'],
-            [:characters, ''],
-            [:comment, 'text 9'],
-            [:characters, '']
-          ], items
-          nil
-        end
-        def text_whitespace
-          html = <<-eohtml
-            <!DOCTYPE html>
-            <html>
-              <head></head>
-              <body>
-                <p>
-                  <span></span>
-                  <span> </span>
-                  <span>
-                  </span>
-                </p>
-                <p>
-                  <!---->
-                  <!-- -->
-                  <!--
-                  -->
-                </p>
-              </body>
-            </html>
-          eohtml
-          @parser.parse html
-          items = @doc.items.get_root_content "body"
-          items = items.select_methods [
-            :start_element, :end_element,
-            :characters, :comment
-          ]
-          items.strip_text! [:characters, :comment]
-          assert_equal [
-            [:characters, ''],
-            [:start_element, 'p', []],
-            [:characters, ''],
-            [:start_element, 'span', []],
-            [:end_element, 'span'],
-            [:characters, ''],
-            [:start_element, 'span', []],
-            [:characters, ''],
-            [:end_element, 'span'],
-            [:characters, ''],
-            [:start_element, 'span', []],
-            [:characters, ''],
-            [:end_element, 'span'],
-            [:characters, ''],
-            [:end_element, 'p'],
-            [:characters, ''],
-            [:start_element, 'p', []],
-            [:characters, ''],
-            [:comment, ''],
-            [:characters, ''],
-            [:comment, ''],
-            [:characters, ''],
-            [:comment, ''],
-            [:characters, ''],
-            [:end_element, 'p'],
-            [:characters, '']
-          ], items
-          nil
-        end
-      end
-    end
-  end
-end

data/test/html/sax/test_push_parser.rb DELETED

@@ -1,87 +0,0 @@
-# -*- coding: utf-8 -*-
-require "helper"
-module Nokogiri
-  module HTML
-    module SAX
-      class TestPushParser < Nokogiri::SAX::TestCase
-        def setup
-          super
-          @parser = HTML::SAX::PushParser.new(Doc.new)
-        end
-        def test_end_document_called
-          @parser.<<(<<-eoxml)
-            <p id="asdfasdf">
-              <!-- This is a comment -->
-              Paragraph 1
-            </p>
-          eoxml
-          assert ! @parser.document.end_document_called
-          @parser.finish
-          assert @parser.document.end_document_called
-        end
-        def test_start_element
-          @parser.<<(<<-eoxml)
-            <!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN" "http://www.w3.org/TR/REC-html40/loose.dtd">
-            <html><head><body><p id="asdfasdf">
-          eoxml
-          assert_equal [["html", []], ["head", []], ["body", []], ["p", [["id", "asdfasdf"]]]],
-            @parser.document.start_elements
-          @parser.<<(<<-eoxml)
-              <!-- This is a comment -->
-              Paragraph 1
-            </p></body></html>
-          eoxml
-          assert_equal [' This is a comment '], @parser.document.comments
-          @parser.finish
-        end
-        def test_chevron_partial_html
-          @parser.<<(<<-eoxml)
-            <p id="asdfasdf">
-          eoxml
-          @parser.<<(<<-eoxml)
-              <!-- This is a comment -->
-              Paragraph 1
-            </p>
-          eoxml
-          assert_equal [' This is a comment '], @parser.document.comments
-          @parser.finish
-        end
-        def test_chevron
-          @parser.<<(<<-eoxml)
-            <p id="asdfasdf">
-              <!-- This is a comment -->
-              Paragraph 1
-            </p>
-          eoxml
-          @parser.finish
-          assert_equal [' This is a comment '], @parser.document.comments
-        end
-        def test_default_options
-          assert_equal 0, @parser.options
-        end
-        def test_broken_encoding
-          skip("ultra hard to fix for pure Java version") if Nokogiri.jruby?
-          @parser.options |= XML::ParseOptions::RECOVER
-          # This is ISO_8859-1:
-          @parser.<< "<?xml version='1.0' encoding='UTF-8'?><r>Gau\337</r>"
-          @parser.finish
-          assert(@parser.document.errors.size >= 1)
-          assert_equal "Gau\337", @parser.document.data.join
-          assert_equal [["r"], ["body"], ["html"]], @parser.document.end_elements
-        end
-      end
-    end
-  end
-end

data/test/html/test_attributes.rb DELETED

@@ -1,85 +0,0 @@
-require "helper"
-module Nokogiri
-  module HTML
-    class TestAttr < Nokogiri::TestCase
-      unless Nokogiri::VersionInfo.instance.libxml2? && Nokogiri::VersionInfo.instance.libxml2_using_system?
-        #
-        #  libxml2 >= 2.9.2 fails to escape comments within some attributes. It
-        #  wants to ensure these comments can be treated as "server-side includes",
-        #  but as a result fails to ensure that serialization is well-formed,
-        #  resulting in an opportunity for XSS injection of code into a final
-        #  re-parsed document (presumably in a browser).
-        #
-        #  the offending commit is:
-        #
-        #    https://github.com/GNOME/libxml2/commit/960f0e2
-        #
-        #  we'll test this by parsing the HTML, serializing it, then
-        #  re-parsing it to ensure there isn't any ambiguity in the output
-        #  that might allow code injection into a browser consuming
-        #  "sanitized" output.
-        #
-        #  complaints have been made upstream about this behavior, notably at
-        #
-        #    https://bugzilla.gnome.org/show_bug.cgi?id=769760
-        #
-        #  and multiple CVEs have been declared and fixed in downstream
-        #  libraries as a result, a list is being kept up to date here:
-        #
-        #    https://github.com/flavorjones/loofah/issues/144
-        #
-        [
-          #
-          #  these tags and attributes are determined by the code at:
-          #
-          #    https://git.gnome.org/browse/libxml2/tree/HTMLtree.c?h=v2.9.2#n714
-          #
-          {tag: "a",   attr: "href"},
-          {tag: "div", attr: "href"},
-          {tag: "a",   attr: "action"},
-          {tag: "div", attr: "action"},
-          {tag: "a",   attr: "src"},
-          {tag: "div", attr: "src"},
-          {tag: "a",   attr: "name"},
-          #
-          #  note that div+name is _not_ affected by the libxml2 issue.
-          #  but we test it anyway to ensure our logic isn't modifying
-          #  attributes that don't need modifying.
-          #
-          {tag: "div", attr: "name", unescaped: true},
-        ].each do |config|
-          define_method "test_uri_escaping_of_#{config[:attr]}_attr_in_#{config[:tag]}_tag" do
-            html = %{<#{config[:tag]} #{config[:attr]}='examp<!--" unsafeattr=unsafevalue()>-->le.com'>test</#{config[:tag]}>}
-            reparsed = HTML.fragment(HTML.fragment(html).to_html)
-            attributes = reparsed.at_css(config[:tag]).attribute_nodes
-            assert_equal [config[:attr]], attributes.collect(&:name)
-            if Nokogiri::VersionInfo.instance.libxml2?
-              if config[:unescaped]
-                #
-                #  this attribute was emitted wrapped in single-quotes, so a double quote is A-OK.
-                #  assert that this attribute's serialization is unaffected.
-                #
-                assert_equal %{examp<!--" unsafeattr=unsafevalue()>-->le.com}, attributes.first.value
-              else
-                #
-                #  let's match the behavior in libxml < 2.9.2.
-                #  test that this attribute's serialization is well-formed and sanitized.
-                #
-                assert_equal %{examp<!--%22%20unsafeattr=unsafevalue()>-->le.com}, attributes.first.value
-              end
-            else
-              #
-              #  yay for consistency in javaland. move along, nothing to see here.
-              #
-              assert_equal %{examp<!--%22 unsafeattr=unsafevalue()>-->le.com}, attributes.first.value
-            end
-          end
-        end
-      end
-    end
-  end
-end

data/test/html/test_builder.rb DELETED

@@ -1,164 +0,0 @@
-require "helper"
-module Nokogiri
-  module HTML
-    class TestBuilder < Nokogiri::TestCase
-      def test_top_level_function_builds
-        foo = nil
-        Nokogiri() { |xml| foo = xml }
-        assert_instance_of Nokogiri::HTML::Builder, foo
-      end
-      def test_builder_with_explicit_tags
-        html_doc = Nokogiri::HTML::Builder.new {
-          div.slide(:class => 'another_class') {
-            node = Nokogiri::XML::Node.new("id", doc)
-            node.content = "hello"
-            insert(node)
-          }
-        }.doc
-        assert_equal 1, html_doc.css('div.slide > id').length
-        assert_equal 'hello', html_doc.at('div.slide > id').content
-      end
-      def test_hash_as_attributes_for_attribute_method
-        html = Nokogiri::HTML::Builder.new { ||
-          div.slide(:class => 'another_class') {
-            span 'Slide 1'
-          }
-        }.to_html
-        assert_match 'class="slide another_class"', html
-      end
-      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.doc.root.to_html.gsub(/\n/, '').gsub(/>\s*</, '><'))
-      end
-      def test_href_with_attributes
-        uri = 'http://tenderlovemaking.com/'
-        built = Nokogiri::XML::Builder.new {
-          div {
-            a('King Khan & The Shrines', :href => uri)
-          }
-        }
-        assert_equal 'http://tenderlovemaking.com/',
-          built.doc.at('a')[:href]
-      end
-      def test_tag_nesting
-        builder = Nokogiri::HTML::Builder.new do
-          body {
-            span.left ''
-            span.middle {
-              div.icon ''
-            }
-            span.right ''
-          }
-        end
-        assert node = builder.doc.css('span.right').first
-        assert_equal 'middle', node.previous_sibling['class']
-      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.doc.root.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.root.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.root.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.root.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.root.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.root.to_html.chomp.gsub(/>\s*</, '><'))
-      end
-      def test_instance_eval_with_delegation_to_block_context
-        class << self
-          def foo
-            "foo!"
-          end
-        end
-        builder = Nokogiri::HTML::Builder.new { text foo }
-        assert builder.to_html.include?("foo!")
-      end
-      def test_builder_with_param
-        doc = Nokogiri::HTML::Builder.new { |html|
-          html.body {
-            html.p "hello world"
-          }
-        }.doc
-        assert node = doc.xpath('//body/p').first
-        assert_equal 'hello world', node.content
-      end
-      def test_builder_with_id
-        text = "hello world"
-        doc = Nokogiri::HTML::Builder.new { |html|
-          html.body {
-            html.id_ text
-          }
-        }.doc
-        assert node = doc.xpath('//body/id').first
-        assert_equal text, node.content
-      end
-    end
-  end
-end