nokogiri 1.3.1 → 1.3.2

data/lib/nokogiri/xml/sax/parser.rb

@@ -30,6 +30,9 @@ module Nokogiri
       # For more information about SAX parsers, see Nokogiri::XML::SAX.  Also
       # see Nokogiri::XML::SAX::Document for the available events.
       class Parser
+        class Attribute < Struct.new(:localname, :prefix, :uri, :value)
+        end
+
         # Encodinds this parser supports
         ENCODINGS = {
           'NONE'        => 0, # No char encoding detected
@@ -67,6 +70,7 @@ module Nokogiri
         def initialize(doc = Nokogiri::XML::SAX::Document.new, encoding = 'ASCII')
           @encoding = encoding
           @document = doc
+          @warned   = false
         end
 
         ###
@@ -95,6 +99,9 @@ module Nokogiri
           raise Errno::EISDIR if File.directory?(filename)
           native_parse_file filename
         end
+
+        private
+        include Nokogiri::XML::SAX::LegacyHandlers
       end
     end
   end

data/lib/nokogiri/xml/sax/push_parser.rb

@@ -54,6 +54,9 @@ module Nokogiri
         def finish
           write '', true
         end
+
+        private
+        include Nokogiri::XML::SAX::LegacyHandlers
       end
     end
   end

data/lib/nokogiri/xml/schema.rb

@@ -34,11 +34,7 @@ module Nokogiri
       # Create a new Nokogiri::XML::Schema object using a +string_or_io+
       # object.
       def self.new string_or_io
-        if string_or_io.respond_to?(:read)
-          string_or_io = string_or_io.read
-        end
-
-        read_memory(string_or_io)
+        from_document Nokogiri::XML(string_or_io)
       end
 
       ###

data/lib/xsd/xmlparser/nokogiri.rb

@@ -13,15 +13,16 @@ module XSD # :nodoc:
     # Example (using UW ITS Web Services):
     #
     #   require 'rubygems'
-    #   gem 'soap4r'
     #   require 'nokogiri'
-    #   require 'xsd/xmlparser/nokogiri'
+    #   gem 'soap4r'
     #   require 'defaultDriver'
-    #
+    #   require 'xsd/xmlparser/nokogiri'
+    #   
     #   obj = AvlPortType.new
-    #   obj.getLatestByRoute(obj.getAgencies, 8).each do |event|
-    #     ...
+    #   obj.getLatestByRoute(obj.getAgencies.first, 8).each do |bus|
+    #     p "#{bus.routeID}, #{bus.longitude}, #{bus.latitude}"
     #   end
+    #
     class Nokogiri < XSD::XMLParser::Parser
       ###
       # Create a new XSD parser with +host+ and +opt+
@@ -39,7 +40,13 @@ module XSD # :nodoc:
       ###
       # Handle the start_element event with +name+ and +attrs+
       def start_element name, attrs = []
-        super(name, Hash[*attrs])
+        super(name, Hash[*attrs.flatten])
+      end
+
+      ###
+      # Handle the end_element event with +name+
+      def end_element name
+        super
       end
 
       ###
@@ -55,7 +62,7 @@ module XSD # :nodoc:
         characters string
       end
 
-      %w{ start_document end_document comment }.each do |name|
+      %w{ start_document start_element_namespace end_element_namespace end_document comment }.each do |name|
         class_eval %{ def #{name}(*args); end }
       end
       add_factory(self)

data/tasks/test.rb

@@ -1,64 +1,3 @@
-# partial-loads-ok and undef-value-errors necessary to ignore
-# spurious (and eminently ignorable) warnings from the ruby
-# interpreter
-VALGRIND_BASIC_OPTS = "--num-callers=50 --error-limit=no --partial-loads-ok=yes --undef-value-errors=no"
-
-class NokogiriTestTask < Rake::TestTask
-  def initialize *args
-    super
-    %w[ ext lib bin test ].each do |dir|
-      self.libs << dir
-    end
-    self.test_files = FileList['test/**/test_*.rb'] +
-      FileList['test/**/*_test.rb']
-    self.verbose = "verbose"
-    self.warning = true
-  end
-end
-
-desc "run test suite under valgrind with basic ruby options"
-NokogiriTestTask.new('test:valgrind').extend(Module.new {
-  def ruby *args
-    run_with_env "valgrind #{VALGRIND_BASIC_OPTS} #{RUBY} #{args.join(' ')} test/test_nokogiri.rb --verbose=verbose"
-  end
-})
-
-desc "run test suite under valgrind with memory-fill ruby options"
-NokogiriTestTask.new('test:valgrind_mem').extend(Module.new {
-  def ruby *args
-    run_with_env "valgrind #{VALGRIND_BASIC_OPTS} --freelist-vol=100000000 --malloc-fill=6D --free-fill=66 #{RUBY} #{args.join(' ')} test/test_nokogiri.rb --verbose=verbose"
-  end
-})
-
-desc "run test suite under valgrind with memory-zero ruby options"
-NokogiriTestTask.new('test:valgrind_mem0').extend(Module.new {
-  def ruby *args
-    run_with_env "valgrind #{VALGRIND_BASIC_OPTS} --freelist-vol=100000000 --malloc-fill=00 --free-fill=00 #{RUBY} #{args.join(' ')} test/test_nokogiri.rb --verbose=verbose"
-  end
-})
-
-desc "run test suite under gdb"
-NokogiriTestTask.new('test:gdb').extend(Module.new {
-  def ruby *args
-    run_with_env "gdb --args #{RUBY} #{args.join(' ')}"
-  end
-})
-
-desc "test coverage"
-NokogiriTestTask.new('test:coverage').extend(Module.new {
-  def ruby *args
-    rm_rf "coverage"
-    run_with_env "rcov -x Library -I lib:ext:test #{args.join(' ')}"
-  end
-})
-
-desc "run test suite with verbose output"
-NokogiriTestTask.new('test:verbose').extend(Module.new {
-  def ruby *args
-    run_with_env "#{RUBY} #{args.join(' ')} test/test_nokogiri.rb --verbose=verbose"
-  end
-})
-
 def run_with_env(cmd)
   cmd = "LD_LIBRARY_PATH='#{ENV['LD_LIBRARY_PATH']}' #{cmd}"
   puts "=> #{cmd}"
@@ -142,7 +81,7 @@ namespace :test do
     directories = ENV['MULTIXML2_DIR'] ? [ENV['MULTIXML2_DIR']] : Dir[File.join(MULTI_XML, 'install', '*')]
     directories.sort.reverse.each do |xml2_version|
       next unless xml2_version =~ /libxml2/
-      extopts = "--with-xml2-include=#{xml2_version}/include/libxml2 --with-xml2-lib=#{xml2_version}/lib --with-xslt-dir=#{libxslt}"
+      extopts = "--with-xml2-include=#{xml2_version}/include/libxml2 --with-xml2-lib=#{xml2_version}/lib --with-xslt-dir=#{libxslt} --with-iconv-dir=/usr"
       cmd = "#{$0} clean test EXTOPTS='#{extopts}' LD_LIBRARY_PATH='#{xml2_version}/lib'"
 
       version = File.basename(xml2_version)

data/test/files/bar/bar.xsd

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema">
+    <xsd:element name="bar"/>
+</xsd:schema>

data/test/files/foo/foo.xsd

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema">
+    <xsd:include schemaLocation="../bar/bar.xsd"/>
+</xsd:schema>

data/test/files/snuggles.xml

@@ -0,0 +1,3 @@
+<x xmlns:tenderlove='http://tenderlovemaking.com/'>
+  <tenderlove:foo awesome='true'>snuggles!</tenderlove:foo>
+</x>

data/test/files/valid_bar.xml

@@ -0,0 +1,2 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<bar />

data/test/helper.rb

@@ -23,6 +23,7 @@ module Nokogiri
     PO_SCHEMA_FILE  = File.join(ASSETS_DIR, 'po.xsd')
     ADDRESS_SCHEMA_FILE = File.join(ASSETS_DIR, 'address_book.rlx')
     ADDRESS_XML_FILE = File.join(ASSETS_DIR, 'address_book.xml')
+    SNUGGLES_FILE   = File.join(ASSETS_DIR, 'snuggles.xml')
 
     unless RUBY_VERSION >= '1.9'
       undef :default_test
@@ -55,10 +56,10 @@ module Nokogiri
   module SAX
     class TestCase < Nokogiri::TestCase
       class Doc < XML::SAX::Document
-        attr_reader :start_elements, :start_elements_ns, :start_document_called
-        attr_reader :end_elements, :end_elements_ns, :end_document_called
-        attr_reader :data, :comments, :cdata_blocks
-        attr_reader :errors, :warnings
+        attr_reader :start_elements, :start_document_called
+        attr_reader :end_elements, :end_document_called
+        attr_reader :data, :comments, :cdata_blocks, :start_elements_namespace
+        attr_reader :errors, :warnings, :end_elements_namespace
 
         def start_document
           @start_document_called = true
@@ -85,8 +86,8 @@ module Nokogiri
           super
         end
 
-        def start_element_ns *args
-          (@start_elements_ns ||= []) << args
+        def start_element_namespace *args
+          (@start_elements_namespace ||= []) << args
           super
         end
 
@@ -95,8 +96,8 @@ module Nokogiri
           super
         end
 
-        def end_element_ns *args
-          (@end_elements_ns ||= []) << args
+        def end_element_namespace *args
+          (@end_elements_namespace ||= []) << args
           super
         end
 

data/test/html/test_document_fragment.rb

@@ -92,6 +92,20 @@ module Nokogiri
         assert_equal "<span>foo<br/></span><span>bar</span>", fragment.to_xml
       end
 
+      def test_fragment_script_tag_with_cdata
+        doc = HTML::Document.new
+        fragment = doc.fragment("<script>var foo = 'bar';</script>")
+        assert_equal("<script>var foo = 'bar';</script>",
+          fragment.to_s)
+      end
+
+      def test_fragment_with_comment
+        doc = HTML::Document.new
+        fragment = doc.fragment("<p>hello<!-- your ad here --></p>")
+        assert_equal("<p>hello<!-- your ad here --></p>",
+          fragment.to_s)
+      end
+
     end
   end
 end

data/test/test_reader.rb

@@ -3,11 +3,7 @@ require File.expand_path(File.join(File.dirname(__FILE__), "helper"))
 
 class TestReader < Nokogiri::TestCase
   def test_from_io_sets_io_as_source
-    io = StringIO.new(<<-eoxml)
-    <x xmlns:tenderlove='http://tenderlovemaking.com/'>
-      <tenderlove:foo awesome='true'>snuggles!</tenderlove:foo>
-    </x>
-    eoxml
+    io = File.open SNUGGLES_FILE
     reader = Nokogiri::XML::Reader.from_io(io)
     assert_equal io, reader.source
   end
@@ -33,11 +29,7 @@ class TestReader < Nokogiri::TestCase
   end
 
   def test_from_io
-    io = StringIO.new(<<-eoxml)
-    <x xmlns:tenderlove='http://tenderlovemaking.com/'>
-      <tenderlove:foo awesome='true'>snuggles!</tenderlove:foo>
-    </x>
-    eoxml
+    io = File.open SNUGGLES_FILE
     reader = Nokogiri::XML::Reader.from_io(io)
     assert_equal false, reader.default?
     assert_equal [false, false, false, false, false, false, false],
@@ -45,6 +37,14 @@ class TestReader < Nokogiri::TestCase
   end
 
   def test_io
+    io = File.open SNUGGLES_FILE
+    reader = Nokogiri::XML::Reader(io)
+    assert_equal false, reader.default?
+    assert_equal [false, false, false, false, false, false, false],
+      reader.map { |x| x.default? }
+  end
+
+  def test_string_io
     io = StringIO.new(<<-eoxml)
     <x xmlns:tenderlove='http://tenderlovemaking.com/'>
       <tenderlove:foo awesome='true'>snuggles!</tenderlove:foo>

data/test/xml/sax/test_parser.rb

@@ -9,12 +9,89 @@ module Nokogiri
           @parser = XML::SAX::Parser.new(Doc.new)
         end
 
+        def test_namespace_declaration_order_is_saved
+          @parser.parse <<-eoxml
+<root xmlns:foo='http://foo.example.com/' xmlns='http://example.com/'>
+  <a foo:bar='hello' />
+</root>
+          eoxml
+          assert_equal 2, @parser.document.start_elements_namespace.length
+          el = @parser.document.start_elements_namespace.first
+          namespaces = el.last
+          assert_equal ['foo', 'http://foo.example.com/'], namespaces.first
+          assert_equal [nil, 'http://example.com/'], namespaces.last
+        end
+
         def test_bad_document_calls_error_handler
           @parser.parse('<foo><bar></foo>')
           assert @parser.document.errors
           assert @parser.document.errors.length > 0
         end
 
+        def test_namespace_are_super_fun_to_parse
+          @parser.parse <<-eoxml
+<root xmlns:foo='http://foo.example.com/'>
+  <a foo:bar='hello' />
+  <b xmlns:foo='http://bar.example.com/'>
+    <a foo:bar='hello' />
+  </b>
+  <foo:bar>hello world</foo:bar>
+</root>
+          eoxml
+          assert @parser.document.start_elements_namespace.length > 0
+          el = @parser.document.start_elements_namespace[1]
+          assert_equal 'a', el.first
+          assert_equal 1, el[1].length
+
+          attribute = el[1].first
+          assert_equal 'bar', attribute.localname
+          assert_equal 'foo', attribute.prefix
+          assert_equal 'hello', attribute.value
+          assert_equal 'http://foo.example.com/', attribute.uri
+        end
+
+        def test_sax_v1_namespace_attribute_declarations
+          @parser.parse <<-eoxml
+<root xmlns:foo='http://foo.example.com/' xmlns='http://example.com/'>
+  <a foo:bar='hello' />
+  <b xmlns:foo='http://bar.example.com/'>
+    <a foo:bar='hello' />
+  </b>
+  <foo:bar>hello world</foo:bar>
+</root>
+          eoxml
+          assert @parser.document.start_elements.length > 0
+          elm = @parser.document.start_elements.first
+          assert_equal 'root', elm.first
+          assert elm[1].include?(['xmlns:foo', 'http://foo.example.com/'])
+          assert elm[1].include?(['xmlns', 'http://example.com/'])
+        end
+
+        def test_sax_v1_namespace_nodes
+          @parser.parse <<-eoxml
+<root xmlns:foo='http://foo.example.com/' xmlns='http://example.com/'>
+  <a foo:bar='hello' />
+  <b xmlns:foo='http://bar.example.com/'>
+    <a foo:bar='hello' />
+  </b>
+  <foo:bar>hello world</foo:bar>
+</root>
+          eoxml
+          assert_equal 5, @parser.document.start_elements.length
+          assert @parser.document.start_elements.map { |se|
+            se.first
+          }.include?('foo:bar')
+          assert @parser.document.end_elements.map { |se|
+            se.first
+          }.include?('foo:bar')
+        end
+
+        def test_start_is_called_without_namespace
+          @parser.parse('<foo:f><bar></foo:f>')
+          assert_equal ['foo:f', 'bar'],
+            @parser.document.start_elements.map { |x| x.first }
+        end
+
         def test_parser_sets_encoding
           parser = XML::SAX::Parser.new(Doc.new, 'UTF-8')
           assert_equal 'UTF-8', parser.encoding

data/test/xml/sax/test_push_parser.rb

@@ -43,12 +43,16 @@ module Nokogiri
             <stream:stream xmlns='jabber:client' xmlns:stream='http://etherx.jabber.org/streams' version='1.0' size='large'></stream:stream>
           eoxml
 
-          assert_equal [[ 'stream',
-                          {'version' => '1.0', 'size' => 'large'},
-                          'stream',
-                          'http://etherx.jabber.org/streams',
-                          {nil => 'jabber:client', 'stream' => 'http://etherx.jabber.org/streams'}]],
-            @parser.document.start_elements_ns
+          assert_equal 1, @parser.document.start_elements_namespace.length
+          el = @parser.document.start_elements_namespace.first
+
+          assert_equal 'stream', el.first
+          assert_equal 2, el[1].length
+          assert_equal [['version', '1.0'], ['size', 'large']],
+            el[1].map { |x| [x.localname, x.value] }
+
+          assert_equal 'stream', el[2]
+          assert_equal 'http://etherx.jabber.org/streams', el[3]
           @parser.finish
         end
 
@@ -58,7 +62,7 @@ module Nokogiri
           eoxml
 
           assert_equal [['stream', 'stream', 'http://etherx.jabber.org/streams']],
-            @parser.document.end_elements_ns
+            @parser.document.end_elements_namespace
           @parser.finish
         end
 

data/test/xml/test_document.rb

@@ -10,6 +10,31 @@ module Nokogiri
         @xml = Nokogiri::XML.parse(File.read(XML_FILE), XML_FILE)
       end
 
+      def test_validate
+        assert_equal 44, @xml.validate.length
+      end
+
+      def test_validate_no_internal_subset
+        doc = Nokogiri::XML('<test/>')
+        assert_nil doc.validate
+      end
+
+      def test_clone
+        assert @xml.clone
+      end
+
+      def test_document_should_not_have_default_ns
+        doc = Nokogiri::XML::Document.new
+
+        assert_raises NoMethodError do
+          doc.default_namespace = 'http://innernet.com/'
+        end
+
+        assert_raises NoMethodError do
+          doc.add_namespace_definition('foo', 'bar')
+        end
+      end
+
       def test_parse_takes_block
         options = nil
         Nokogiri::XML.parse(File.read(XML_FILE), XML_FILE) do |cfg|