libxml-ruby 4.1.2 → 6.0.0

data/test/test_canonicalize.rb

@@ -1,120 +1,122 @@
-# encoding: UTF-8
-require_relative './test_helper'
-
-class TestCanonicalize < Minitest::Test
-  def path(file)
-    File.join(File.dirname(__FILE__), file)
-  end
-  
-  # (www.w3.org) 3.1 PIs, Comments, and Outside of Document Element
-  # http://www.w3.org/TR/xml-c14n#Example-OutsideDoc
-  def test_canonicalize_with_w3c_c14n_3_1
-    given_doc = LibXML::XML::Document.file(self.path('c14n/given/example-1.xml'))
-
-    # With Comments
-    expected_with_comments = IO.read(self.path('c14n/result/with-comments/example-1'))
-    assert_equal(expected_with_comments, given_doc.canonicalize(:comments => true))
-
-    # Without Comments
-    expected_without_comments = IO.read(self.path('c14n/result/without-comments/example-1'))
-    assert_equal(expected_without_comments, given_doc.canonicalize)
-    assert_equal(expected_without_comments, given_doc.canonicalize(:comments => false))
-
-    # Without Comments (XML_C14N_1_1)
-    expected_1_1_without_comments = IO.read(self.path('c14n/result/1-1-without-comments/example-1'))
-    mode = LibXML::XML::Document::XML_C14N_1_1
-    assert_equal(expected_1_1_without_comments, given_doc.canonicalize(:mode => mode))
-  end#test_canonicalize_with_w3c_c14n_3_1
-
-
-  # (www.w3.org) 3.2 Whitespace in Document Content
-  # http://www.w3.org/TR/xml-c14n#Example-WhitespaceInContent
-  def test_canonicalize_with_w3c_c14n_3_2
-    given_doc = LibXML::XML::Document.file(self.path('c14n/given/example-2.xml'))
-    expected = IO.read(self.path('c14n/result/without-comments/example-2'))
-    assert_equal(expected, given_doc.canonicalize)
-
-    expected_1_1_without_comments = IO.read(self.path('c14n/result/1-1-without-comments/example-2'))
-    mode = LibXML::XML::Document::XML_C14N_1_1
-    assert_equal(expected_1_1_without_comments, given_doc.canonicalize(:mode => mode))
-  end
-
-  # (www.w3.org) 3.3 Start and End Tags
-  # http://www.w3.org/TR/xml-c14n#Example-SETags
-  # (2012-02-20) Test failing due to missing 'attr' in 'e9' node.
-  #   - Embedded DTD not parsed out of XML, therefore default attributes are
-  #     not applied to canonicalization.
-  def test_canonicalize_with_w3c_c14n_3_3
-    given_doc = LibXML::XML::Document.file(self.path('c14n/given/example-3.xml'))
-    expected = IO.read(self.path('c14n/result/without-comments/example-3'))
-    assert_equal(expected, given_doc.canonicalize)
-
-    expected_1_1_without_comments = IO.read(self.path('c14n/result/1-1-without-comments/example-3'))
-    mode = LibXML::XML::Document::XML_C14N_1_1
-    assert_equal(expected_1_1_without_comments, given_doc.canonicalize(:mode => mode))
-  end
-
-  # (www.w3.org) 3.4 Character Modifications and Character References
-  # http://www.w3.org/TR/xml-c14n#Example-Chars
-  def test_canonicalize_with_w3c_c14n_3_4
-    given_doc = LibXML::XML::Document.file(self.path('c14n/given/example-4.xml'))
-    expected = IO.read(self.path('c14n/result/without-comments/example-4'))
-    assert_equal(expected, given_doc.canonicalize)
-
-    expected_1_1_without_comments = IO.read(self.path('c14n/result/1-1-without-comments/example-4'))
-    mode = LibXML::XML::Document::XML_C14N_1_1
-    assert_equal(expected_1_1_without_comments, given_doc.canonicalize(:mode => mode))
-  end
-
-  # (www.w3.org) 3.5 Entity References
-  # http://www.w3.org/TR/xml-c14n#Example-Entities
-  # (2012-02-20) Failing likely due to a logic error
-  #   - libxml2(c14n.c:1788) XML_ENTITY_REF_NODE is invalid node for parsing.
-  def test_canonicalize_with_w3c_c14n_3_5
-    #given_doc = LibXML::XML::Document.file(self.path('c14n/given/example-5.xml'))
-
-    # With Comments
-    #expected_with_comments = IO.read(self.path('c14n/result/with-comments/example-5'))
-
-    # TODO - CANNOT COMPLETE TEST unless libxml2 supports additional node types.
-    #assert_equal(expected_with_comments, given_doc.canonicalize(:comments => true))
-
-    # Without Comments
-    #expected_without_comments = IO.read(self.path('c14n/result/without-comments/example-5'))
-    # TODO - CANNOT COMPLETE TEST unless libxml2 supports additional node types.
-    #assert_equal(expected_without_comments, given_doc.canonicalize(:comments => false))
-    #expected_1_1_without_comments = IO.read(self.path('c14n/result/1-1-without-comments/example-5'))
-    #mode = LibXML::XML::Document::XML_C14N_1_1
-
-    # TODO - CANNOT COMPLETE TEST unless libxml2 supports additional node types.
-    #assert_equal(expected_1_1_without_comments, given_doc.canonicalize(:mode => mode))
-  end
-
-  # (www.w3.org) 3.6 UTF-8 Encoding
-  # http://www.w3.org/TR/xml-c14n#Example-UTF8
-  def test_canonicalize_with_w3c_c14n_3_6
-    given_doc = LibXML::XML::Document.file(self.path('c14n/given/example-6.xml'))
-    expected = IO.read(self.path('c14n/result/without-comments/example-6'), :encoding => Encoding::UTF_8)
-    assert_equal(expected, given_doc.canonicalize)
-
-    expected_1_1_without_comments = IO.read(self.path('c14n/result/1-1-without-comments/example-6'), :encoding => Encoding::UTF_8)
-    mode = LibXML::XML::Document::XML_C14N_1_1
-    assert_equal(expected_1_1_without_comments, given_doc.canonicalize(:mode => mode))
-  end
-
-  # (www.w3.org) 3.7 Document Subsets
-  # http://www.w3.org/TR/xml-c14n#Example-DocSubsets
-  def test_canonicalize_with_w3c_c14n_3_7
-    # Non Canonicalized Document
-    # given_doc = LibXML::XML::Document.file(self.path('c14n/given/example-7.xml'))
-    #expected = IO.read(self.path('c14n/result/without-comments/example-7'))
-
-    # e1_node = given_doc.find_first('ietf:e1', 'ietf:http://www.ietf.org')
-
-    # Select current node, all child nodes, all attributes and namespace nodes
-    #subdoc_nodes = e1_node.find("(.//.|.//@id|namespace::*)")
-
-    # TODO - This fails because the namespace nodes aren't taken into account
-    # assert_equal(expected, given_doc.canonicalize(:nodes => subdoc_nodes))
-  end
-end
+# encoding: UTF-8
+require_relative './test_helper'
+
+class TestCanonicalize < Minitest::Test
+  def path(file)
+    File.join(File.dirname(__FILE__), file)
+  end
+  
+  # (www.w3.org) 3.1 PIs, Comments, and Outside of Document Element
+  # http://www.w3.org/TR/xml-c14n#Example-OutsideDoc
+  def test_canonicalize_with_w3c_c14n_3_1
+    given_doc = LibXML::XML::Document.file(self.path('c14n/given/example-1.xml'))
+
+    # With Comments
+    expected_with_comments = IO.read(self.path('c14n/result/with-comments/example-1'))
+    assert_equal(expected_with_comments, given_doc.canonicalize(:comments => true))
+
+    # Without Comments
+    expected_without_comments = IO.read(self.path('c14n/result/without-comments/example-1'))
+    assert_equal(expected_without_comments, given_doc.canonicalize)
+    assert_equal(expected_without_comments, given_doc.canonicalize(:comments => false))
+
+    # Without Comments (XML_C14N_1_1)
+    expected_1_1_without_comments = IO.read(self.path('c14n/result/1-1-without-comments/example-1'))
+    mode = LibXML::XML::Document::XML_C14N_1_1
+    assert_equal(expected_1_1_without_comments, given_doc.canonicalize(:mode => mode))
+  end
+
+  # (www.w3.org) 3.2 Whitespace in Document Content
+  # http://www.w3.org/TR/xml-c14n#Example-WhitespaceInContent
+  def test_canonicalize_with_w3c_c14n_3_2
+    given_doc = LibXML::XML::Document.file(self.path('c14n/given/example-2.xml'))
+    expected = IO.read(self.path('c14n/result/without-comments/example-2'))
+    assert_equal(expected, given_doc.canonicalize)
+
+    expected_1_1_without_comments = IO.read(self.path('c14n/result/1-1-without-comments/example-2'))
+    mode = LibXML::XML::Document::XML_C14N_1_1
+    assert_equal(expected_1_1_without_comments, given_doc.canonicalize(:mode => mode))
+  end
+
+  # (www.w3.org) 3.3 Start and End Tags
+  # http://www.w3.org/TR/xml-c14n#Example-SETags
+  # (2012-02-20) Test failing due to missing 'attr' in 'e9' node.
+  #   - Embedded DTD not parsed out of XML, therefore default attributes are
+  #     not applied to canonicalization.
+  def test_canonicalize_with_w3c_c14n_3_3
+    given_doc = LibXML::XML::Document.file(self.path('c14n/given/example-3.xml'))
+    expected = IO.read(self.path('c14n/result/without-comments/example-3'))
+    assert_equal(expected, given_doc.canonicalize)
+
+    expected_1_1_without_comments = IO.read(self.path('c14n/result/1-1-without-comments/example-3'))
+    mode = LibXML::XML::Document::XML_C14N_1_1
+    assert_equal(expected_1_1_without_comments, given_doc.canonicalize(:mode => mode))
+  end
+
+  # (www.w3.org) 3.4 Character Modifications and Character References
+  # http://www.w3.org/TR/xml-c14n#Example-Chars
+  def test_canonicalize_with_w3c_c14n_3_4
+    given_doc = LibXML::XML::Document.file(self.path('c14n/given/example-4.xml'))
+    expected = IO.read(self.path('c14n/result/without-comments/example-4'))
+    assert_equal(expected, given_doc.canonicalize)
+
+    expected_1_1_without_comments = IO.read(self.path('c14n/result/1-1-without-comments/example-4'))
+    mode = LibXML::XML::Document::XML_C14N_1_1
+    assert_equal(expected_1_1_without_comments, given_doc.canonicalize(:mode => mode))
+  end
+
+  # (www.w3.org) 3.5 Entity References
+  # http://www.w3.org/TR/xml-c14n#Example-Entities
+  def test_canonicalize_with_w3c_c14n_3_5
+    # NOENT resolves entity references, DTDLOAD loads the external entity
+    options = LibXML::XML::Parser::Options::NOENT | LibXML::XML::Parser::Options::DTDLOAD
+    given_doc = LibXML::XML::Document.file(self.path('c14n/given/example-5.xml'), options: options)
+
+    # With Comments
+    expected_with_comments = IO.read(self.path('c14n/result/with-comments/example-5'))
+    assert_equal(expected_with_comments, given_doc.canonicalize(:comments => true))
+
+    # Without Comments
+    expected_without_comments = IO.read(self.path('c14n/result/without-comments/example-5'))
+    assert_equal(expected_without_comments, given_doc.canonicalize(:comments => false))
+
+    # Without Comments (XML_C14N_1_1)
+    expected_1_1_without_comments = IO.read(self.path('c14n/result/1-1-without-comments/example-5'))
+    mode = LibXML::XML::Document::XML_C14N_1_1
+    assert_equal(expected_1_1_without_comments, given_doc.canonicalize(:mode => mode))
+  end
+
+  # (www.w3.org) 3.6 UTF-8 Encoding
+  # http://www.w3.org/TR/xml-c14n#Example-UTF8
+  def test_canonicalize_with_w3c_c14n_3_6
+    given_doc = LibXML::XML::Document.file(self.path('c14n/given/example-6.xml'))
+    expected = IO.read(self.path('c14n/result/without-comments/example-6'), :encoding => Encoding::UTF_8)
+    assert_equal(expected, given_doc.canonicalize)
+
+    expected_1_1_without_comments = IO.read(self.path('c14n/result/1-1-without-comments/example-6'), :encoding => Encoding::UTF_8)
+    mode = LibXML::XML::Document::XML_C14N_1_1
+    assert_equal(expected_1_1_without_comments, given_doc.canonicalize(:mode => mode))
+  end
+
+  # (www.w3.org) 3.7 Document Subsets
+  # http://www.w3.org/TR/xml-c14n#Example-DocSubsets
+  def test_canonicalize_with_w3c_c14n_3_7
+    # Parse with DTDATTR and DTDLOAD so default attributes and ID types
+    # from the internal DTD subset are materialized
+    options = LibXML::XML::Parser::Options::DTDATTR | LibXML::XML::Parser::Options::DTDLOAD
+    given_doc = LibXML::XML::Document.file(self.path('c14n/given/example-7.xml'),
+                                           options: options)
+    expected = IO.read(self.path('c14n/result/without-comments/example-7'))
+
+    ctx = given_doc.context
+    ctx.register_namespace('ietf', 'http://www.ietf.org')
+
+    # W3C C14N spec example 3.7 XPath expression for document subsets
+    subdoc_nodes = ctx.find(
+      "(//. | //@* | //namespace::*)" \
+      "[self::ietf:e1 or (parent::ietf:e1 and not(self::text() or self::e2))" \
+      " or count(id('E3')|ancestor-or-self::node()) = count(ancestor-or-self::node())]")
+
+    assert_equal(expected, given_doc.canonicalize(:nodes => subdoc_nodes))
+  end
+end

data/test/test_document.rb

@@ -1,132 +1,138 @@
-# encoding: UTF-8
-require_relative './test_helper'
-
-class TestDocument < Minitest::Test
-  def setup
-    xp = LibXML::XML::Parser.string('<ruby_array uga="booga" foo="bar"><fixnum>one</fixnum><fixnum>two</fixnum></ruby_array>')
-    assert_instance_of(LibXML::XML::Parser, xp)
-    @doc = xp.parse
-    assert_instance_of(LibXML::XML::Document, @doc)
-  end
-
-  def teardown
-    @doc = nil
-  end
-
-  def test_klass
-    assert_instance_of(LibXML::XML::Document, @doc)
-  end
-
-  def test_context
-    context = @doc.context
-    assert_instance_of(LibXML::XML::XPath::Context, context)
-  end
-
-  def test_find
-    set = @doc.find('/ruby_array/fixnum')
-    assert_instance_of(LibXML::XML::XPath::Object, set)
-    assert_raises(NoMethodError) {
-      set.xpath
-    }
-  end
-
-  def test_compression
-    if LibXML::XML.enabled_zlib?
-      0.upto(9) do |i|
-        assert_equal(i, @doc.compression = i)
-        assert_equal(i, @doc.compression)
-      end
-
-      9.downto(0) do |i|
-        assert_equal(i, @doc.compression = i)
-        assert_equal(i, @doc.compression)
-      end
-
-      10.upto(20) do |i|
-        # assert_equal(9, @doc.compression = i)
-        assert_equal(i, @doc.compression = i) # This works around a bug in Ruby 1.8
-        assert_equal(9, @doc.compression)
-      end
-
-      -1.downto(-10) do |i|
-        # assert_equal(0, @doc.compression = i)
-        assert_equal(i, @doc.compression = i) # FIXME This bug should get fixed ASAP
-        assert_equal(0, @doc.compression)
-      end
-    end
-  end
-
-  def test_version
-    assert_equal('1.0', @doc.version)
-
-    doc = LibXML::XML::Document.new('6.9')
-    assert_equal('6.9', doc.version)
-  end
-
-  def test_write_root
-    @doc.root = LibXML::XML::Node.new('rubynet')
-    assert_instance_of(LibXML::XML::Node, @doc.root)
-    assert_instance_of(LibXML::XML::Document, @doc.root.doc)
-    assert_equal("<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n<rubynet/>\n",
-                 @doc.to_s(:indent => false))
-  end
-
-  def test_doc_node_type
-    assert_equal(LibXML::XML::Node::DOCUMENT_NODE, LibXML::XML::Document.new.node_type)
-  end
-
-  def test_doc_node_type_name
-    assert_equal('document_xml', LibXML::XML::Document.new.node_type_name)
-  end
-
-  def test_xhtml
-		doc = LibXML::XML::Document.new
-		assert(!doc.xhtml?)
-    LibXML::XML::Dtd.new "-//W3C//DTD XHTML 1.0 Transitional//EN", "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd", nil, doc, true
-		assert(doc.xhtml?)
-  end
-
-  def test_document_root
-    doc1 = LibXML::XML::Document.string("<one/>")
-    doc2 = LibXML::XML::Document.string("<two/>")
-
-    error = assert_raises(LibXML::XML::Error) do
-      doc1.root = doc2.root
-    end
-    assert_equal(" Nodes belong to different documents.  You must first import the node by calling LibXML::XML::Document.import.",
-                 error.to_s)
-
-    doc2.root << doc2.import(doc1.root)
-    assert_equal('<one/>', doc1.root.to_s)
-    assert_equal('<two><one/></two>', doc2.root.to_s(:indent => false))
-
-    assert(!doc1.root.equal?(doc2.root))
-    assert(doc1.root.doc != doc2.root.doc)
-  end
-
-  def test_import_node
-    doc1 = LibXML::XML::Parser.string('<nums><one></one></nums>').parse
-    doc2 = LibXML::XML::Parser.string('<nums><two></two></nums>').parse
-
-    node = doc1.root.child
-
-    error = assert_raises(LibXML::XML::Error) do
-      doc2.root << node
-    end
-
-    assert_equal(" Nodes belong to different documents.  You must first import the node by calling LibXML::XML::Document.import.",
-                 error.to_s)
-
-    doc2.root << doc2.import(node)
-
-    assert_equal("<nums><two/><one/></nums>",
-                 doc2.root.to_s(:indent => false))
-  end
-
-  def test_nonet
-    xml_string = '<ruby_array uga="booga" foo="bar"><fixnum>one</fixnum><fixnum>two</fixnum></ruby_array>'
-    xml = LibXML::XML::Document.string(xml_string, options: LibXML::XML::Parser::Options::NONET)
-    file = File.join(File.dirname(__FILE__), 'model/atom.xml')
-    schema_document = LibXML::XML::Document.file(file, options: LibXML::XML::Parser::Options::NONET)
-  end
-end
+# encoding: UTF-8
+require_relative './test_helper'
+
+class TestDocument < Minitest::Test
+  def setup
+    xp = LibXML::XML::Parser.string('<ruby_array uga="booga" foo="bar"><fixnum>one</fixnum><fixnum>two</fixnum></ruby_array>')
+    assert_instance_of(LibXML::XML::Parser, xp)
+    @doc = xp.parse
+    assert_instance_of(LibXML::XML::Document, @doc)
+  end
+
+  def teardown
+    @doc = nil
+  end
+
+  def test_klass
+    assert_instance_of(LibXML::XML::Document, @doc)
+  end
+
+  def test_context
+    context = @doc.context
+    assert_instance_of(LibXML::XML::XPath::Context, context)
+  end
+
+  def test_find
+    set = @doc.find('/ruby_array/fixnum')
+    assert_instance_of(LibXML::XML::XPath::Object, set)
+    assert_raises(NoMethodError) {
+      set.xpath
+    }
+  end
+
+  def test_compression
+    if LibXML::XML.enabled_zlib?
+      0.upto(9) do |i|
+        assert_equal(i, @doc.compression = i)
+        assert_equal(i, @doc.compression)
+      end
+
+      9.downto(0) do |i|
+        assert_equal(i, @doc.compression = i)
+        assert_equal(i, @doc.compression)
+      end
+
+      10.upto(20) do |i|
+        assert_equal(i, @doc.compression = i)
+        assert_equal(9, @doc.compression)
+      end
+
+      -1.downto(-10) do |i|
+        @doc.compression = i
+        assert_equal(0, @doc.compression)
+      end
+    end
+  end
+
+  def test_version
+    assert_equal('1.0', @doc.version)
+
+    doc = LibXML::XML::Document.new('6.9')
+    assert_equal('6.9', doc.version)
+  end
+
+  def test_write_root
+    @doc.root = LibXML::XML::Node.new('rubynet')
+    assert_instance_of(LibXML::XML::Node, @doc.root)
+    assert_instance_of(LibXML::XML::Document, @doc.root.doc)
+    assert_equal("<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n<rubynet/>\n",
+                 @doc.to_s(:indent => false))
+  end
+
+  def test_doc_node_type
+    assert_equal(LibXML::XML::Node::DOCUMENT_NODE, LibXML::XML::Document.new.node_type)
+  end
+
+  def test_doc_node_type_name
+    assert_equal('document_xml', LibXML::XML::Document.new.node_type_name)
+  end
+
+  def test_xhtml
+		doc = LibXML::XML::Document.new
+		assert(!doc.xhtml?)
+    LibXML::XML::Dtd.new("-//W3C//DTD XHTML 1.0 Transitional//EN", "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd", nil, doc, true)
+		assert(doc.xhtml?)
+  end
+
+  def test_document_root
+    doc1 = LibXML::XML::Document.string("<one/>")
+    doc2 = LibXML::XML::Document.string("<two/>")
+
+    error = assert_raises(LibXML::XML::Error) do
+      doc1.root = doc2.root
+    end
+    assert_equal(" Nodes belong to different documents.  You must first import the node by calling LibXML::XML::Document.import.",
+                 error.to_s)
+
+    doc2.root << doc2.import(doc1.root)
+    assert_equal('<one/>', doc1.root.to_s)
+    assert_equal('<two><one/></two>', doc2.root.to_s(:indent => false))
+
+    assert(!doc1.root.equal?(doc2.root))
+    assert(doc1.root.doc != doc2.root.doc)
+  end
+
+  def test_import_node
+    doc1 = LibXML::XML::Parser.string('<nums><one></one></nums>').parse
+    doc2 = LibXML::XML::Parser.string('<nums><two></two></nums>').parse
+
+    node = doc1.root.child
+
+    error = assert_raises(LibXML::XML::Error) do
+      doc2.root << node
+    end
+
+    assert_equal(" Nodes belong to different documents.  You must first import the node by calling LibXML::XML::Document.import.",
+                 error.to_s)
+
+    doc2.root << doc2.import(node)
+
+    assert_equal("<nums><two/><one/></nums>",
+                 doc2.root.to_s(:indent => false))
+  end
+
+  def test_nonet
+    xml_string = '<ruby_array uga="booga" foo="bar"><fixnum>one</fixnum><fixnum>two</fixnum></ruby_array>'
+    xml = LibXML::XML::Document.string(xml_string, options: LibXML::XML::Parser::Options::NONET)
+    file = File.join(File.dirname(__FILE__), 'model/atom.xml')
+    schema_document = LibXML::XML::Document.file(file, options: LibXML::XML::Parser::Options::NONET)
+  end
+
+  def test_io
+    File.open(File.join(File.dirname(__FILE__), 'model/rubynet.xml')) do |io|
+      doc = LibXML::XML::Document.io(io)
+      assert_instance_of(LibXML::XML::Document, doc)
+    end
+  end
+
+end