nokogiri 1.2.3 → 1.3.0

data/test/ffi/test_document.rb

@@ -0,0 +1,35 @@
+require File.expand_path(File.join(File.dirname(__FILE__), "..", "helper"))
+
+if defined?(Nokogiri::LibXML)
+
+  class FFI::TestDocument < Nokogiri::TestCase
+
+    def test_ruby_doc_reflection
+      doc = Nokogiri::XML("<root><foo>foo</foo></root>")
+      assert_equal doc, doc.cstruct.ruby_doc
+    end
+
+    def test_ruby_doc_setter
+      doc = Nokogiri::XML("<root><foo>foo</foo></root>")
+      foo = "foobar"
+      doc.cstruct.ruby_doc = foo
+      assert_equal foo, doc.cstruct.ruby_doc
+    end
+
+    def test_node_set
+      doc = Nokogiri::XML("<root><foo>foo</foo></root>")
+      assert_instance_of Nokogiri::LibXML::XmlNodeSetCast, doc.cstruct.node_set
+    end
+
+    def test_node_set_contains_unlinked_nodes
+      doc = Nokogiri::XML("<root><foo>foo</foo></root>")
+      node = doc.xpath('//foo').first
+      assert_equal 0, doc.cstruct.node_set[:nodeNr]
+      node.unlink
+      assert_equal 1, doc.cstruct.node_set[:nodeNr]
+      assert_equal node.cstruct.pointer, doc.cstruct.node_set[:nodeTab].get_pointer(0)
+    end
+
+  end
+
+end

data/test/files/address_book.rlx

@@ -0,0 +1,12 @@
+<element name="addressBook" xmlns="http://relaxng.org/ns/structure/1.0">
+  <oneOrMore>
+    <element name="card">
+      <element name="name">
+        <text/>
+      </element>
+      <element name="email">
+        <text/>
+      </element>
+    </element>
+  </oneOrMore>
+</element>

data/test/files/address_book.xml

@@ -0,0 +1,10 @@
+<addressBook>
+  <card>
+    <name>John Smith</name>
+    <email>js@example.com</email>
+  </card>
+  <card>
+    <name>Fred Bloggs</name>
+    <email>fb@example.net</email>
+  </card>
+</addressBook>

data/test/files/po.xml

@@ -0,0 +1,32 @@
+<?xml version="1.0"?>
+<purchaseOrder orderDate="1999-10-20">
+   <shipTo country="US">
+      <name>Alice Smith</name>
+      <street>123 Maple Street</street>
+      <city>Mill Valley</city>
+      <state>CA</state>
+      <zip>90952</zip>
+   </shipTo>
+   <billTo country="US">
+      <name>Robert Smith</name>
+      <street>8 Oak Avenue</street>
+      <city>Old Town</city>
+      <state>PA</state>
+      <zip>95819</zip>
+   </billTo>
+   <comment>Hurry, my lawn is going wild!</comment>
+   <items>
+      <item partNum="872-AA">
+         <productName>Lawnmower</productName>
+         <quantity>1</quantity>
+         <USPrice>148.95</USPrice>
+         <comment>Confirm this is electric</comment>
+      </item>
+      <item partNum="926-AA">
+         <productName>Baby Monitor</productName>
+         <quantity>1</quantity>
+         <USPrice>39.98</USPrice>
+         <shipDate>1999-05-21</shipDate>
+      </item>
+   </items>
+</purchaseOrder>

data/test/files/po.xsd

@@ -0,0 +1,66 @@
+<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema">
+
+  <xsd:annotation>
+    <xsd:documentation xml:lang="en">
+     Purchase order schema for Example.com.
+     Copyright 2000 Example.com. All rights reserved.
+    </xsd:documentation>
+  </xsd:annotation>
+
+  <xsd:element name="purchaseOrder" type="PurchaseOrderType"/>
+
+  <xsd:element name="comment" type="xsd:string"/>
+
+  <xsd:complexType name="PurchaseOrderType">
+    <xsd:sequence>
+      <xsd:element name="shipTo" type="USAddress"/>
+      <xsd:element name="billTo" type="USAddress"/>
+      <xsd:element ref="comment" minOccurs="0"/>
+      <xsd:element name="items"  type="Items"/>
+    </xsd:sequence>
+    <xsd:attribute name="orderDate" type="xsd:date"/>
+  </xsd:complexType>
+
+  <xsd:complexType name="USAddress">
+    <xsd:sequence>
+      <xsd:element name="name"   type="xsd:string"/>
+      <xsd:element name="street" type="xsd:string"/>
+      <xsd:element name="city"   type="xsd:string"/>
+      <xsd:element name="state"  type="xsd:string"/>
+      <xsd:element name="zip"    type="xsd:decimal"/>
+    </xsd:sequence>
+    <xsd:attribute name="country" type="xsd:NMTOKEN"
+                   fixed="US"/>
+  </xsd:complexType>
+
+  <xsd:complexType name="Items">
+    <xsd:sequence>
+      <xsd:element name="item" minOccurs="0" maxOccurs="unbounded">
+        <xsd:complexType>
+          <xsd:sequence>
+            <xsd:element name="productName" type="xsd:string"/>
+            <xsd:element name="quantity">
+              <xsd:simpleType>
+                <xsd:restriction base="xsd:positiveInteger">
+                  <xsd:maxExclusive value="100"/>
+                </xsd:restriction>
+              </xsd:simpleType>
+            </xsd:element>
+            <xsd:element name="USPrice"  type="xsd:decimal"/>
+            <xsd:element ref="comment"   minOccurs="0"/>
+            <xsd:element name="shipDate" type="xsd:date" minOccurs="0"/>
+          </xsd:sequence>
+          <xsd:attribute name="partNum" type="SKU" use="required"/>
+        </xsd:complexType>
+      </xsd:element>
+    </xsd:sequence>
+  </xsd:complexType>
+
+  <!-- Stock Keeping Unit, a code for identifying products -->
+  <xsd:simpleType name="SKU">
+    <xsd:restriction base="xsd:string">
+      <xsd:pattern value="\d{3}-[A-Z]{2}"/>
+    </xsd:restriction>
+  </xsd:simpleType>
+
+</xsd:schema>

data/test/helper.rb

@@ -1,4 +1,6 @@
+Process.setrlimit(Process::RLIMIT_CORE, Process::RLIM_INFINITY) unless RUBY_PLATFORM =~ /(java|mswin|mingw)/i
 $VERBOSE = true
+require 'rubygems'
 require 'test/unit'
 
 %w(../lib ../ext).each do |path|
@@ -7,14 +9,20 @@ end
 
 require 'nokogiri'
 
+warn "#{__FILE__}:#{__LINE__}: libxml version info: #{Nokogiri::VERSION_INFO.inspect}"
+
 module Nokogiri
   class TestCase < Test::Unit::TestCase
-    ASSETS_DIR = File.join(File.dirname(__FILE__), 'files')
-    XML_FILE = File.join(ASSETS_DIR, 'staff.xml')
-    XSLT_FILE = File.join(ASSETS_DIR, 'staff.xslt')
-    EXSLT_FILE = File.join(ASSETS_DIR, 'exslt.xslt')
-    EXML_FILE = File.join(ASSETS_DIR, 'exslt.xml')
-    HTML_FILE = File.join(ASSETS_DIR, 'tlm.html')
+    ASSETS_DIR      = File.join(File.dirname(__FILE__), 'files')
+    XML_FILE        = File.join(ASSETS_DIR, 'staff.xml')
+    XSLT_FILE       = File.join(ASSETS_DIR, 'staff.xslt')
+    EXSLT_FILE      = File.join(ASSETS_DIR, 'exslt.xslt')
+    EXML_FILE       = File.join(ASSETS_DIR, 'exslt.xml')
+    HTML_FILE       = File.join(ASSETS_DIR, 'tlm.html')
+    PO_XML_FILE     = File.join(ASSETS_DIR, 'po.xml')
+    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')
 
     unless RUBY_VERSION >= '1.9'
       undef :default_test
@@ -30,13 +38,25 @@ module Nokogiri
         GC.start 
       end
     end
+
+    def assert_indent amount, doc, message = nil
+      nodes = []
+      doc.traverse do |node|
+        nodes << node if node.text? && node.blank?
+      end
+      assert nodes.length > 0
+      nodes.each do |node|
+        len = node.content.gsub(/[\r\n]/, '').length
+        assert_equal(0, len % amount, message)
+      end
+    end
   end
 
   module SAX
     class TestCase < Nokogiri::TestCase
       class Doc < XML::SAX::Document
-        attr_reader :start_elements, :start_document_called
-        attr_reader :end_elements, :end_document_called
+        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
 
@@ -65,11 +85,21 @@ module Nokogiri
           super
         end
 
+        def start_element_ns *args
+          (@start_elements_ns ||= []) << args
+          super
+        end
+
         def end_element *args
           (@end_elements ||= []) << args
           super
         end
 
+        def end_element_ns *args
+          (@end_elements_ns ||= []) << args
+          super
+        end
+
         def characters string
           @data ||= []
           @data += [string]

data/test/html/sax/test_parser.rb

@@ -14,6 +14,12 @@ module Nokogiri
           assert_equal 1110, @parser.document.end_elements.length
         end
 
+        def test_parse_file_nil_argument
+          assert_raises(ArgumentError) {
+            @parser.parse_file(nil)
+          }
+        end
+
         def test_parse_file_non_existant
           assert_raise Errno::ENOENT do
             @parser.parse_file('foo')
@@ -26,6 +32,12 @@ module Nokogiri
           end
         end
 
+        def test_parse_memory_nil
+          assert_raise ArgumentError do
+            @parser.parse_memory(nil)
+          end
+        end
+
         def test_parse_document
           @parser.parse_memory(<<-eoxml)
             <p>Paragraph 1</p>

data/test/html/test_builder.rb

@@ -16,7 +16,7 @@ module Nokogiri
       end
 
       def test_hash_as_attributes_for_attribute_method
-        html = Nokogiri::HTML::Builder.new {
+        html = Nokogiri::HTML::Builder.new { ||
           div.slide(:class => 'another_class') {
             span 'Slide 1'
           }
@@ -36,7 +36,7 @@ module Nokogiri
 
       def test_href_with_attributes
         uri = 'http://tenderlovemaking.com/'
-        built = Nokogiri::XML::Builder.new { |x|
+        built = Nokogiri::XML::Builder.new {
           div {
             a('King Khan & The Shrines', :href => uri)
           }
@@ -128,6 +128,29 @@ module Nokogiri
         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

data/test/html/test_document.rb

@@ -8,10 +8,86 @@ module Nokogiri
         @html = Nokogiri::HTML.parse(File.read(HTML_FILE))
       end
 
-      def test_emtpy_string_returns_empty_doc
+      def test_document_takes_config_block
+        options = nil
+        Nokogiri::HTML(File.read(HTML_FILE), HTML_FILE) do |cfg|
+          options = cfg
+          options.nonet.nowarning.dtdattr
+        end
+        assert options.nonet?
+        assert options.nowarning?
+        assert options.dtdattr?
+      end
+
+      def test_parse_takes_config_block
+        options = nil
+        Nokogiri::HTML.parse(File.read(HTML_FILE), HTML_FILE) do |cfg|
+          options = cfg
+          options.nonet.nowarning.dtdattr
+        end
+        assert options.nonet?
+        assert options.nowarning?
+        assert options.dtdattr?
+      end
+
+      def test_subclass
+        klass = Class.new(Nokogiri::HTML::Document)
+        doc = klass.new
+        assert_instance_of klass, doc
+      end
+
+      def test_subclass_initialize
+        klass = Class.new(Nokogiri::HTML::Document) do
+          attr_accessor :initialized_with
+
+          def initialize(*args)
+            @initialized_with = args
+          end
+        end
+        doc = klass.new("uri", "external_id", 1)
+        assert_equal ["uri", "external_id", 1], doc.initialized_with
+      end
+
+      def test_subclass_dup
+        klass = Class.new(Nokogiri::HTML::Document)
+        doc = klass.new.dup
+        assert_instance_of klass, doc
+      end
+
+      def test_subclass_parse
+        klass = Class.new(Nokogiri::HTML::Document)
+        doc = klass.parse(File.read(HTML_FILE))
+        assert_equal @html.to_s, doc.to_s
+        assert_instance_of klass, doc
+      end
+
+      def test_document_parse_method
+        html = Nokogiri::HTML::Document.parse(File.read(HTML_FILE))
+        assert_equal @html.to_s, html.to_s
+      end
+
+      def test_empty_string_returns_empty_doc
         doc = Nokogiri::HTML('')
       end
 
+      unless %w[2 6] === LIBXML_VERSION.split('.')[0..1]
+        # FIXME: this is a hack around broken libxml versions
+        def test_to_xhtml_with_indent
+          doc = Nokogiri::HTML('<html><body><a>foo</a></body></html>')
+          doc = Nokogiri::HTML(doc.to_xhtml(:indent => 2))
+          assert_indent 2, doc
+        end
+
+        def test_write_to_xhtml_with_indent
+          io = StringIO.new
+          doc = Nokogiri::HTML('<html><body><a>foo</a></body></html>')
+          doc.write_xhtml_to io, :indent => 5
+          io.rewind
+          doc = Nokogiri::HTML(io.read)
+          assert_indent 5, doc
+        end
+      end
+
       def test_swap_should_not_exist
         assert_raises(NoMethodError) {
           @html.swap
@@ -24,6 +100,15 @@ module Nokogiri
         }
       end
 
+      def test_meta_encoding
+        assert_equal 'UTF-8', @html.meta_encoding
+      end
+
+      def test_meta_encoding=
+        @html.meta_encoding = 'EUC-JP'
+        assert_equal 'EUC-JP', @html.meta_encoding
+      end
+
       def test_root_node_parent_is_document
         parent = @html.root.parent
         assert_equal @html, parent
@@ -44,14 +129,16 @@ module Nokogiri
 
       def test_parse_io
         assert doc = File.open(HTML_FILE, 'rb') { |f|
-          Document.read_io(f, nil, 'UTF-8', PARSE_NOERROR | PARSE_NOWARNING)
+          Document.read_io(f, nil, 'UTF-8',
+                           XML::ParseOptions::NOERROR | XML::ParseOptions::NOWARNING
+                          )
         }
       end
 
       def test_to_xhtml
         assert_match 'XHTML', @html.to_xhtml
-        assert_match 'XHTML', @html.to_xhtml('UTF-8')
-        assert_match 'UTF-8', @html.to_xhtml('UTF-8')
+        assert_match 'XHTML', @html.to_xhtml(:encoding => 'UTF-8')
+        assert_match 'UTF-8', @html.to_xhtml(:encoding => 'UTF-8')
       end
 
       def test_no_xml_header
@@ -211,22 +298,6 @@ module Nokogiri
         assert_equal 2, Nokogiri::HTML.fragment("<br/><hr/>").children.length
       end
 
-      def test_fragment
-        fragment = Nokogiri::HTML.fragment(<<-eohtml)
-          <div>
-            <b>Hello World</b>
-          </div>
-        eohtml
-        assert_equal 1, fragment.children.length
-        assert_equal 'div', fragment.children.first.name
-        assert_match(/Hello World/, fragment.to_html)
-
-        # libxml2 is broken in 2.6.16 and 2.6.17
-        unless [16, 17].include?(Nokogiri::LIBXML_VERSION.split('.').last.to_i)
-          assert_equal 1, fragment.css('div').length
-        end
-      end
-
       def test_relative_css_finder
         doc = Nokogiri::HTML(<<-eohtml)
           <html>