markup_validity 1.0.0

data/lib/markup_validity/xml.xsd

@@ -0,0 +1,286 @@
+<?xml version='1.0'?>
+<?xml-stylesheet href="../2008/09/xsd.xsl" type="text/xsl"?>
+<xs:schema targetNamespace="http://www.w3.org/XML/1998/namespace" 
+  xmlns:xs="http://www.w3.org/2001/XMLSchema" 
+  xmlns   ="http://www.w3.org/1999/xhtml"
+  xml:lang="en">
+
+ <xs:annotation>
+  <xs:documentation>
+   <div>
+    <h1>About the XML namespace</h1>
+
+    <div class="bodytext">
+     <p>
+      This schema document describes the XML namespace, in a form
+      suitable for import by other schema documents.
+     </p>
+     <p>
+      See <a href="http://www.w3.org/XML/1998/namespace.html">
+      http://www.w3.org/XML/1998/namespace.html</a> and
+      <a href="http://www.w3.org/TR/REC-xml">
+      http://www.w3.org/TR/REC-xml</a> for information 
+      about this namespace.
+     </p>
+     <p>
+      Note that local names in this namespace are intended to be
+      defined only by the World Wide Web Consortium or its subgroups.
+      The names currently defined in this namespace are listed below.
+      They should not be used with conflicting semantics by any Working
+      Group, specification, or document instance.
+     </p>
+     <p>   
+      See further below in this document for more information about <a
+      href="#usage">how to refer to this schema document from your own
+      XSD schema documents</a> and about <a href="#nsversioning">the
+      namespace-versioning policy governing this schema document</a>.
+     </p>
+    </div>
+   </div>
+  </xs:documentation>
+ </xs:annotation>
+
+ <xs:attribute name="lang">
+  <xs:annotation>
+   <xs:documentation>
+    <div>
+     
+      <h3>lang (as an attribute name)</h3>
+      <p>
+       denotes an attribute whose value
+       is a language code for the natural language of the content of
+       any element; its value is inherited.  This name is reserved
+       by virtue of its definition in the XML specification.</p>
+     
+    </div>
+    <div>
+     <h4>Notes</h4>
+     <p>
+      Attempting to install the relevant ISO 2- and 3-letter
+      codes as the enumerated possible values is probably never
+      going to be a realistic possibility.  
+     </p>
+     <p>
+      See BCP 47 at <a href="http://www.rfc-editor.org/rfc/bcp/bcp47.txt">
+       http://www.rfc-editor.org/rfc/bcp/bcp47.txt</a>
+      and the IANA language subtag registry at
+      <a href="http://www.iana.org/assignments/language-subtag-registry">
+       http://www.iana.org/assignments/language-subtag-registry</a>
+      for further information.
+     </p>
+     <p>
+      The union allows for the 'un-declaration' of xml:lang with
+      the empty string.
+     </p>
+    </div>
+   </xs:documentation>
+  </xs:annotation>
+  <xs:simpleType>
+   <xs:union memberTypes="xs:language">
+    <xs:simpleType>    
+     <xs:restriction base="xs:string">
+      <xs:enumeration value=""/>
+     </xs:restriction>
+    </xs:simpleType>
+   </xs:union>
+  </xs:simpleType>
+ </xs:attribute>
+
+ <xs:attribute name="space">
+  <xs:annotation>
+   <xs:documentation>
+    <div>
+     
+      <h3>space (as an attribute name)</h3>
+      <p>
+       denotes an attribute whose
+       value is a keyword indicating what whitespace processing
+       discipline is intended for the content of the element; its
+       value is inherited.  This name is reserved by virtue of its
+       definition in the XML specification.</p>
+     
+    </div>
+   </xs:documentation>
+  </xs:annotation>
+  <xs:simpleType>
+   <xs:restriction base="xs:NCName">
+    <xs:enumeration value="default"/>
+    <xs:enumeration value="preserve"/>
+   </xs:restriction>
+  </xs:simpleType>
+ </xs:attribute>
+ 
+ <xs:attribute name="base" type="xs:anyURI"> <xs:annotation>
+   <xs:documentation>
+    <div>
+     
+      <h3>base (as an attribute name)</h3>
+      <p>
+       denotes an attribute whose value
+       provides a URI to be used as the base for interpreting any
+       relative URIs in the scope of the element on which it
+       appears; its value is inherited.  This name is reserved
+       by virtue of its definition in the XML Base specification.</p>
+     
+     <p>
+      See <a
+      href="http://www.w3.org/TR/xmlbase/">http://www.w3.org/TR/xmlbase/</a>
+      for information about this attribute.
+     </p>
+    </div>
+   </xs:documentation>
+  </xs:annotation>
+ </xs:attribute>
+ 
+ <xs:attribute name="id" type="xs:ID">
+  <xs:annotation>
+   <xs:documentation>
+    <div>
+     
+      <h3>id (as an attribute name)</h3> 
+      <p>
+       denotes an attribute whose value
+       should be interpreted as if declared to be of type ID.
+       This name is reserved by virtue of its definition in the
+       xml:id specification.</p>
+     
+     <p>
+      See <a
+      href="http://www.w3.org/TR/xml-id/">http://www.w3.org/TR/xml-id/</a>
+      for information about this attribute.
+     </p>
+    </div>
+   </xs:documentation>
+  </xs:annotation>
+ </xs:attribute>
+
+ <xs:attributeGroup name="specialAttrs">
+  <xs:attribute ref="xml:base"/>
+  <xs:attribute ref="xml:lang"/>
+  <xs:attribute ref="xml:space"/>
+  <xs:attribute ref="xml:id"/>
+ </xs:attributeGroup>
+
+ <xs:annotation>
+  <xs:documentation>
+   <div>
+   
+    <h3>Father (in any context at all)</h3> 
+
+    <div class="bodytext">
+     <p>
+      denotes Jon Bosak, the chair of 
+      the original XML Working Group.  This name is reserved by 
+      the following decision of the W3C XML Plenary and 
+      XML Coordination groups:
+     </p>
+     <blockquote>
+       <p>
+	In appreciation for his vision, leadership and
+	dedication the W3C XML Plenary on this 10th day of
+	February, 2000, reserves for Jon Bosak in perpetuity
+	the XML name "xml:Father".
+       </p>
+     </blockquote>
+    </div>
+   </div>
+  </xs:documentation>
+ </xs:annotation>
+
+ <xs:annotation>
+  <xs:documentation>
+   <div xml:id="usage" id="usage">
+    <h2><a name="usage">About this schema document</a></h2>
+
+    <div class="bodytext">
+     <p>
+      This schema defines attributes and an attribute group suitable
+      for use by schemas wishing to allow <code>xml:base</code>,
+      <code>xml:lang</code>, <code>xml:space</code> or
+      <code>xml:id</code> attributes on elements they define.
+     </p>
+     <p>
+      To enable this, such a schema must import this schema for
+      the XML namespace, e.g. as follows:
+     </p>
+     <pre>
+          &lt;schema . . .>
+           . . .
+           &lt;import namespace="http://www.w3.org/XML/1998/namespace"
+                      schemaLocation="http://www.w3.org/2001/xml.xsd"/>
+     </pre>
+     <p>
+      or
+     </p>
+     <pre>
+           &lt;import namespace="http://www.w3.org/XML/1998/namespace"
+                      schemaLocation="http://www.w3.org/2009/01/xml.xsd"/>
+     </pre>
+     <p>
+      Subsequently, qualified reference to any of the attributes or the
+      group defined below will have the desired effect, e.g.
+     </p>
+     <pre>
+          &lt;type . . .>
+           . . .
+           &lt;attributeGroup ref="xml:specialAttrs"/>
+     </pre>
+     <p>
+      will define a type which will schema-validate an instance element
+      with any of those attributes.
+     </p>
+    </div>
+   </div>
+  </xs:documentation>
+ </xs:annotation>
+
+ <xs:annotation>
+  <xs:documentation>
+   <div id="nsversioning" xml:id="nsversioning">
+    <h2><a name="nsversioning">Versioning policy for this schema document</a></h2>
+    <div class="bodytext">
+     <p>
+      In keeping with the XML Schema WG's standard versioning
+      policy, this schema document will persist at
+      <a href="http://www.w3.org/2009/01/xml.xsd">
+       http://www.w3.org/2009/01/xml.xsd</a>.
+     </p>
+     <p>
+      At the date of issue it can also be found at
+      <a href="http://www.w3.org/2001/xml.xsd">
+       http://www.w3.org/2001/xml.xsd</a>.
+     </p>
+     <p>
+      The schema document at that URI may however change in the future,
+      in order to remain compatible with the latest version of XML
+      Schema itself, or with the XML namespace itself.  In other words,
+      if the XML Schema or XML namespaces change, the version of this
+      document at <a href="http://www.w3.org/2001/xml.xsd">
+       http://www.w3.org/2001/xml.xsd 
+      </a> 
+      will change accordingly; the version at 
+      <a href="http://www.w3.org/2009/01/xml.xsd">
+       http://www.w3.org/2009/01/xml.xsd 
+      </a> 
+      will not change.
+     </p>
+     <p>
+      Previous dated (and unchanging) versions of this schema 
+      document are at:
+     </p>
+     <ul>
+      <li><a href="http://www.w3.org/2009/01/xml.xsd">
+	http://www.w3.org/2009/01/xml.xsd</a></li>
+      <li><a href="http://www.w3.org/2007/08/xml.xsd">
+	http://www.w3.org/2007/08/xml.xsd</a></li>
+      <li><a href="http://www.w3.org/2004/10/xml.xsd">
+	http://www.w3.org/2004/10/xml.xsd</a></li>
+      <li><a href="http://www.w3.org/2001/03/xml.xsd">
+	http://www.w3.org/2001/03/xml.xsd</a></li>
+     </ul>
+    </div>
+   </div>
+  </xs:documentation>
+ </xs:annotation>
+
+</xs:schema>

data/spec/matcher_spec.rb

@@ -0,0 +1,47 @@
+require 'rubygems'
+require 'markup_validity'
+require 'test/helper'
+
+module Spec
+  module Matchers
+    extend MarkupValidity::TestHelper
+    describe "[actual.should] be_xhtml_transitional" do
+      it "is transitional xhtml" do
+        Matchers.valid_document.should be_xhtml_transitional
+      end
+
+      it "is xhtml" do
+        Matchers.valid_document.should be_xhtml
+      end
+
+      it "is strict xhtml" do
+        Matchers.valid_document.should be_xhtml_strict
+      end
+
+      it "is not transitional xhtml" do
+        Matchers.invalid_document.should_not be_xhtml_transitional
+      end
+
+      it "is not strict xhtml" do
+        Matchers.invalid_document.should_not be_xhtml_strict
+      end
+
+      XSD = File.read(
+        File.expand_path(
+          File.join(File.dirname(__FILE__),'..','test','assets','shipment.xsd')
+        )
+      )
+      XML = File.read(
+        File.join(File.dirname(__FILE__), '..','test', 'assets', 'order.xml')
+      )
+
+      it "is valid given spec" do
+        XML.should be_valid_with_schema XSD
+      end
+
+      it "is not valid given spec" do
+        XML.gsub(/<name>[^<]*<\/name>/, '').should_not be_valid_with_schema XSD
+      end
+    end
+  end
+end

data/test/assets/order.xml

@@ -0,0 +1,24 @@
+<?xml version="1.0" encoding="ISO-8859-1"?>
+
+<shiporder orderid="889923"
+xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+xsi:noNamespaceSchemaLocation="shiporder.xsd">
+  <orderperson>John Smith</orderperson>
+  <shipto>
+    <name>Ola Nordmann</name>
+    <address>Langgt 23</address>
+    <city>4000 Stavanger</city>
+    <country>Norway</country>
+  </shipto>
+  <item>
+    <title>Empire Burlesque</title>
+    <note>Special Edition</note>
+    <quantity>1</quantity>
+    <price>10.90</price>
+  </item>
+  <item>
+    <title>Hide your heart</title>
+    <quantity>1</quantity>
+    <price>9.90</price>
+  </item>
+</shiporder>

data/test/assets/shipment.xsd

@@ -0,0 +1,33 @@
+<?xml version="1.0" encoding="ISO-8859-1" ?>
+<xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema">
+
+<xs:element name="shiporder">
+  <xs:complexType>
+    <xs:sequence>
+      <xs:element name="orderperson" type="xs:string"/>
+      <xs:element name="shipto">
+        <xs:complexType>
+          <xs:sequence>
+            <xs:element name="name" type="xs:string"/>
+            <xs:element name="address" type="xs:string"/>
+            <xs:element name="city" type="xs:string"/>
+            <xs:element name="country" type="xs:string"/>
+          </xs:sequence>
+        </xs:complexType>
+      </xs:element>
+      <xs:element name="item" maxOccurs="unbounded">
+        <xs:complexType>
+          <xs:sequence>
+            <xs:element name="title" type="xs:string"/>
+            <xs:element name="note" type="xs:string" minOccurs="0"/>
+            <xs:element name="quantity" type="xs:positiveInteger"/>
+            <xs:element name="price" type="xs:decimal"/>
+          </xs:sequence>
+        </xs:complexType>
+      </xs:element>
+    </xs:sequence>
+    <xs:attribute name="orderid" type="xs:string" use="required"/>
+  </xs:complexType>
+</xs:element>
+
+</xs:schema>

data/test/helper.rb

@@ -0,0 +1,31 @@
+module MarkupValidity
+  module TestHelper
+    def valid_document
+      <<-eoxhtml
+<html xmlns="http://www.w3.org/1999/xhtml">
+  <head>
+    <title>hello world</title>
+  </head>
+  <body>
+  </body>
+</html>
+      eoxhtml
+    end
+
+    def invalid_document
+      <<-eoxhtml
+<html xmlns="http://www.w3.org/1999/xhtml">
+  <head>
+  </head>
+  <body>
+    <p>
+      <p>
+        Hello
+      </p>
+    </p>
+  </body>
+</html>
+      eoxhtml
+    end
+  end
+end

data/test/test_markup_validity.rb

@@ -0,0 +1,81 @@
+require "test/unit"
+require 'helper'
+require "markup_validity"
+
+class TestMarkupValidity < Test::Unit::TestCase
+  include MarkupValidity::TestHelper
+
+  class FakeUnit
+    include MarkupValidity::Assertions
+
+    attr_reader :assertions
+
+    def initialize
+      @assertions = []
+    end
+
+    def assert *args
+      @assertions << args
+    end
+  end
+
+  def setup
+    @fu = FakeUnit.new
+  end
+
+  def test_line_numbers_do_not_roll_over
+    validator = MarkupValidity::Validator.new('foo')
+    assert !validator.valid?
+    assert_no_match(/-1/, validator.inspect)
+  end
+
+  def test_line_numbers_do_not_roll_over_line_1
+    validator = MarkupValidity::Validator.new("\nfoo")
+    assert !validator.valid?
+    assert_no_match(/-1/, validator.inspect)
+  end
+
+  def test_valid_xhtml_transitional
+    @fu.assert_xhtml_transitional valid_document
+    assert_equal [true, ''], @fu.assertions.first
+    assert_xhtml_transitional valid_document
+  end
+
+  def test_valid_xhtml
+    @fu.assert_xhtml valid_document
+    assert_equal [true, ''], @fu.assertions.first
+  end
+
+  def test_valid_xhtml_strict
+    @fu.assert_xhtml_strict valid_document
+    assert_equal [true, ''], @fu.assertions.first
+  end
+
+  def test_invalid_xhtml
+    @fu.assert_xhtml_transitional invalid_document
+    assert_equal false, @fu.assertions.first.first
+    assert_match('Missing child element', @fu.assertions.first.last)
+  end
+
+  def test_invalid_xhtml_strict
+    @fu.assert_xhtml_strict invalid_document
+    assert_equal false, @fu.assertions.first.first
+    assert_match('Missing child element', @fu.assertions.first.last)
+  end
+
+  def test_valid_schema
+    xsd = File.join(File.dirname(__FILE__), 'assets', 'shipment.xsd')
+    xml = File.join(File.dirname(__FILE__), 'assets', 'order.xml')
+    @fu.assert_schema File.read(xsd), File.read(xml)
+    assert_equal [true, ''], @fu.assertions.first
+  end
+
+  def test_invalid_schema
+    xsd = File.join(File.dirname(__FILE__), 'assets', 'shipment.xsd')
+    xml = File.read File.join(File.dirname(__FILE__), 'assets', 'order.xml')
+    xml.gsub!(/<name>[^<]*<\/name>/, '')
+    @fu.assert_schema File.read(xsd), xml
+    assert_equal false, @fu.assertions.first.first
+    assert_match('This element is not', @fu.assertions.first.last)
+  end
+end