RubyGems - nokogiri - Versions diffs - 1.3.3-java → 1.4.0-java - Mend

nokogiri 1.3.3-java → 1.4.0-java

Potentially problematic release.

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

Files changed (205) hide show

data/CHANGELOG.ja.rdoc +48 -3
data/CHANGELOG.rdoc +42 -0
data/Manifest.txt +44 -29
data/README.ja.rdoc +0 -2
data/README.rdoc +4 -7
data/Rakefile +42 -6
data/bin/nokogiri +7 -5
data/ext/nokogiri/extconf.rb +5 -21
data/ext/nokogiri/html_document.c +14 -50
data/ext/nokogiri/html_element_description.c +7 -7
data/ext/nokogiri/html_entity_lookup.c +6 -4
data/ext/nokogiri/html_sax_parser_context.c +92 -0
data/ext/nokogiri/html_sax_parser_context.h +11 -0
data/ext/nokogiri/iconv.dll +0 -0
data/ext/nokogiri/libexslt.dll +0 -0
data/ext/nokogiri/libxml2.dll +0 -0
data/ext/nokogiri/libxslt.dll +0 -0
data/ext/nokogiri/nokogiri.c +9 -3
data/ext/nokogiri/nokogiri.h +16 -20
data/ext/nokogiri/xml_attr.c +1 -1
data/ext/nokogiri/xml_attribute_decl.c +67 -0
data/ext/nokogiri/xml_attribute_decl.h +9 -0
data/ext/nokogiri/xml_cdata.c +6 -5
data/ext/nokogiri/xml_comment.c +3 -2
data/ext/nokogiri/xml_document.c +93 -23
data/ext/nokogiri/xml_document_fragment.c +1 -3
data/ext/nokogiri/xml_dtd.c +63 -6
data/ext/nokogiri/xml_element_content.c +123 -0
data/ext/nokogiri/xml_element_content.h +10 -0
data/ext/nokogiri/xml_element_decl.c +69 -0
data/ext/nokogiri/xml_element_decl.h +9 -0
data/ext/nokogiri/xml_entity_decl.c +97 -0
data/ext/nokogiri/xml_entity_decl.h +10 -0
data/ext/nokogiri/xml_entity_reference.c +1 -1
data/ext/nokogiri/xml_io.c +10 -3
data/ext/nokogiri/xml_io.h +1 -0
data/ext/nokogiri/xml_namespace.c +2 -2
data/ext/nokogiri/xml_node.c +139 -34
data/ext/nokogiri/xml_node.h +0 -1
data/ext/nokogiri/xml_node_set.c +23 -16
data/ext/nokogiri/xml_processing_instruction.c +1 -1
data/ext/nokogiri/xml_reader.c +78 -50
data/ext/nokogiri/xml_sax_parser.c +109 -168
data/ext/nokogiri/xml_sax_parser.h +33 -0
data/ext/nokogiri/xml_sax_parser_context.c +155 -0
data/ext/nokogiri/xml_sax_parser_context.h +10 -0
data/ext/nokogiri/xml_sax_push_parser.c +11 -6
data/ext/nokogiri/xml_syntax_error.c +63 -12
data/ext/nokogiri/xml_text.c +4 -3
data/ext/nokogiri/xml_xpath.c +1 -1
data/ext/nokogiri/xml_xpath_context.c +12 -25
data/ext/nokogiri/xslt_stylesheet.c +3 -3
data/ext/nokogiri/zlib1.dll +0 -0
data/lib/nokogiri.rb +4 -4
data/lib/nokogiri/css/node.rb +1 -9
data/lib/nokogiri/css/xpath_visitor.rb +11 -21
data/lib/nokogiri/ffi/html/document.rb +0 -9
data/lib/nokogiri/ffi/html/sax/parser_context.rb +38 -0
data/lib/nokogiri/ffi/io_callbacks.rb +4 -2
data/lib/nokogiri/ffi/libxml.rb +44 -10
data/lib/nokogiri/ffi/structs/common_node.rb +1 -1
data/lib/nokogiri/ffi/structs/xml_attribute.rb +27 -0
data/lib/nokogiri/ffi/structs/xml_dtd.rb +3 -1
data/lib/nokogiri/ffi/structs/xml_element.rb +26 -0
data/lib/nokogiri/ffi/structs/xml_element_content.rb +17 -0
data/lib/nokogiri/ffi/structs/xml_entity.rb +32 -0
data/lib/nokogiri/ffi/structs/xml_enumeration.rb +12 -0
data/lib/nokogiri/ffi/structs/xml_parser_context.rb +19 -0
data/lib/nokogiri/ffi/structs/xml_sax_push_parser_context.rb +4 -3
data/lib/nokogiri/ffi/structs/xml_syntax_error.rb +1 -1
data/lib/nokogiri/ffi/xml/attribute_decl.rb +27 -0
data/lib/nokogiri/ffi/xml/comment.rb +2 -2
data/lib/nokogiri/ffi/xml/document.rb +29 -12
data/lib/nokogiri/ffi/xml/document_fragment.rb +0 -5
data/lib/nokogiri/ffi/xml/dtd.rb +14 -3
data/lib/nokogiri/ffi/xml/element_content.rb +43 -0
data/lib/nokogiri/ffi/xml/element_decl.rb +19 -0
data/lib/nokogiri/ffi/xml/entity_decl.rb +27 -0
data/lib/nokogiri/ffi/xml/node.rb +45 -5
data/lib/nokogiri/ffi/xml/node_set.rb +1 -1
data/lib/nokogiri/ffi/xml/reader.rb +45 -24
data/lib/nokogiri/ffi/xml/sax/parser.rb +27 -34
data/lib/nokogiri/ffi/xml/sax/parser_context.rb +67 -0
data/lib/nokogiri/ffi/xml/sax/push_parser.rb +5 -4
data/lib/nokogiri/ffi/xml/syntax_error.rb +31 -16
data/lib/nokogiri/ffi/xml/text.rb +2 -2
data/lib/nokogiri/html.rb +1 -0
data/lib/nokogiri/html/document.rb +39 -24
data/lib/nokogiri/html/sax/parser.rb +2 -2
data/lib/nokogiri/html/sax/parser_context.rb +16 -0
data/lib/nokogiri/version.rb +1 -1
data/lib/nokogiri/xml.rb +6 -1
data/lib/nokogiri/xml/attr.rb +5 -0
data/lib/nokogiri/xml/attribute_decl.rb +18 -0
data/lib/nokogiri/xml/builder.rb +121 -13
data/lib/nokogiri/xml/character_data.rb +7 -0
data/lib/nokogiri/xml/document.rb +43 -29
data/lib/nokogiri/xml/document_fragment.rb +26 -6
data/lib/nokogiri/xml/dtd.rb +5 -5
data/lib/nokogiri/xml/element_content.rb +36 -0
data/lib/nokogiri/xml/element_decl.rb +13 -0
data/lib/nokogiri/xml/entity_decl.rb +15 -0
data/lib/nokogiri/xml/fragment_handler.rb +22 -11
data/lib/nokogiri/xml/namespace.rb +6 -0
data/lib/nokogiri/xml/node.rb +33 -15
data/lib/nokogiri/xml/node_set.rb +66 -44
data/lib/nokogiri/xml/pp.rb +2 -0
data/lib/nokogiri/xml/pp/character_data.rb +18 -0
data/lib/nokogiri/xml/pp/node.rb +56 -0
data/lib/nokogiri/xml/reader.rb +8 -0
data/lib/nokogiri/xml/sax.rb +1 -1
data/lib/nokogiri/xml/sax/document.rb +18 -1
data/lib/nokogiri/xml/sax/parser.rb +15 -8
data/lib/nokogiri/xml/sax/parser_context.rb +16 -0
data/lib/nokogiri/xml/sax/push_parser.rb +0 -3
data/lib/nokogiri/xml/syntax_error.rb +4 -0
data/lib/nokogiri/xslt/stylesheet.rb +1 -1
data/test/css/test_nthiness.rb +1 -1
data/test/css/test_parser.rb +1 -1
data/test/css/test_tokenizer.rb +1 -1
data/test/css/test_xpath_visitor.rb +1 -1
data/test/ffi/test_document.rb +1 -1
data/test/files/shift_jis.html +10 -0
data/test/files/staff.dtd +10 -0
data/test/helper.rb +12 -3
data/test/html/sax/test_parser.rb +1 -1
data/test/html/sax/test_parser_context.rb +48 -0
data/test/html/test_builder.rb +8 -2
data/test/html/test_document.rb +23 -1
data/test/html/test_document_encoding.rb +15 -1
data/test/html/test_document_fragment.rb +10 -1
data/test/html/test_element_description.rb +1 -2
data/test/html/test_named_characters.rb +1 -1
data/test/html/test_node.rb +61 -1
data/test/html/test_node_encoding.rb +27 -0
data/test/test_convert_xpath.rb +1 -3
data/test/test_css_cache.rb +1 -1
data/test/test_gc.rb +1 -1
data/test/test_memory_leak.rb +1 -1
data/test/test_nokogiri.rb +3 -3
data/test/test_reader.rb +29 -1
data/test/test_xslt_transforms.rb +1 -1
data/test/xml/node/test_save_options.rb +1 -1
data/test/xml/node/test_subclass.rb +1 -1
data/test/xml/sax/test_parser.rb +64 -3
data/test/xml/sax/test_parser_context.rb +56 -0
data/test/xml/sax/test_push_parser.rb +11 -1
data/test/xml/test_attr.rb +1 -1
data/test/xml/test_attribute_decl.rb +82 -0
data/test/xml/test_builder.rb +95 -1
data/test/xml/test_cdata.rb +1 -1
data/test/xml/test_comment.rb +7 -1
data/test/xml/test_document.rb +147 -6
data/test/xml/test_document_encoding.rb +1 -1
data/test/xml/test_document_fragment.rb +55 -5
data/test/xml/test_dtd.rb +40 -5
data/test/xml/test_dtd_encoding.rb +3 -1
data/test/xml/test_element_content.rb +56 -0
data/test/xml/test_element_decl.rb +73 -0
data/test/xml/test_entity_decl.rb +83 -0
data/test/xml/test_entity_reference.rb +1 -1
data/test/xml/test_namespace.rb +21 -1
data/test/xml/test_node.rb +70 -4
data/test/xml/test_node_attributes.rb +1 -1
data/test/xml/test_node_encoding.rb +1 -1
data/test/xml/test_node_set.rb +136 -2
data/test/xml/test_parse_options.rb +1 -1
data/test/xml/test_processing_instruction.rb +1 -1
data/test/xml/test_reader_encoding.rb +1 -1
data/test/xml/test_relax_ng.rb +1 -1
data/test/xml/test_schema.rb +1 -1
data/test/xml/test_syntax_error.rb +27 -0
data/test/xml/test_text.rb +13 -1
data/test/xml/test_unparented_node.rb +1 -1
data/test/xml/test_xpath.rb +1 -1
metadata +100 -78
data/ext/nokogiri/html_sax_parser.c +0 -57
data/ext/nokogiri/html_sax_parser.h +0 -11
data/lib/action-nokogiri.rb +0 -38
data/lib/nokogiri/decorators.rb +0 -2
data/lib/nokogiri/decorators/hpricot.rb +0 -3
data/lib/nokogiri/decorators/hpricot/node.rb +0 -56
data/lib/nokogiri/decorators/hpricot/node_set.rb +0 -54
data/lib/nokogiri/decorators/hpricot/xpath_visitor.rb +0 -30
data/lib/nokogiri/ffi/html/sax/parser.rb +0 -21
data/lib/nokogiri/hpricot.rb +0 -92
data/lib/nokogiri/xml/entity_declaration.rb +0 -11
data/lib/nokogiri/xml/sax/legacy_handlers.rb +0 -65
data/test/hpricot/files/basic.xhtml +0 -17
data/test/hpricot/files/boingboing.html +0 -2266
data/test/hpricot/files/cy0.html +0 -3653
data/test/hpricot/files/immob.html +0 -400
data/test/hpricot/files/pace_application.html +0 -1320
data/test/hpricot/files/tenderlove.html +0 -16
data/test/hpricot/files/uswebgen.html +0 -220
data/test/hpricot/files/utf8.html +0 -1054
data/test/hpricot/files/week9.html +0 -1723
data/test/hpricot/files/why.xml +0 -19
data/test/hpricot/load_files.rb +0 -11
data/test/hpricot/test_alter.rb +0 -68
data/test/hpricot/test_builder.rb +0 -20
data/test/hpricot/test_parser.rb +0 -350
data/test/hpricot/test_paths.rb +0 -15
data/test/hpricot/test_preserved.rb +0 -77
data/test/hpricot/test_xml.rb +0 -30

data/test/hpricot/test_paths.rb DELETED Viewed

@@ -1,15 +0,0 @@
-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 = Nokogiri.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.path), ele.xpath
-    end
-  end
-end

data/test/hpricot/test_preserved.rb DELETED Viewed

@@ -1,77 +0,0 @@
-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
-  # Not really a valid test.  If libxml can figure out the encoding of the file,
-  # it will use that encoding, otherwise it uses the &#xwhatever so that no data
-  # is lost.
-  #
-  # libxml on OSX can't figure out the encoding, so this tests passes.  linux
-  # can figure out the encoding, so it fails.
-  #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(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.get_attribute('href')
-    assert_equal "http://google.com/search?q=nokogiri&l=en", link['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.gsub(/%22/, '&quot;')
-  end
-end

data/test/hpricot/test_xml.rb DELETED Viewed

@@ -1,30 +0,0 @@
-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 = Nokogiri::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 = Nokogiri::XML(TestFiles::WHY)
-    ### Modified.
-    # I don't want to differentiate pseudo classes from namespaces.  If
-    # you're parsing xml, use XPath.  That's what its for.  :-P
-    assert_equal "hourly", (doc.at "//sy:updatePeriod").content
-    assert_equal 1, (doc/"guid[@isPermaLink]").length
-  end
-  # be sure tags named "text" are ok
-  def test_text_tags
-    doc = Nokogiri::XML("<feed><title>City Poisoned</title><text>Rita Lee has poisoned Brazil.</text></feed>")
-    assert_equal "City Poisoned", (doc/"title").text
-  end
-end