jhove-service 1.3.0 → 1.4.0

data/bin/cache/xhtml11.xsd

@@ -0,0 +1,104 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<xs:schema
+    xmlns:xs="http://www.w3.org/2001/XMLSchema"
+    targetNamespace="http://www.w3.org/1999/xhtml"
+    xmlns:xh11d="http://www.w3.org/1999/xhtml/datatypes/"
+    xmlns="http://www.w3.org/1999/xhtml"
+    elementFormDefault="qualified" >
+    <xs:annotation>
+        <xs:documentation>
+      This is the XML Schema driver for XHTML 1.1.
+      Please use this namespace for XHTML elements:
+
+         "http://www.w3.org/1999/xhtml"
+
+      $Id: xhtml11.xsd,v 1.7 2009/02/03 15:14:49 ahby Exp $
+    </xs:documentation>
+        <xs:documentation source="xhtml-copyright-1.xsd"/>
+    </xs:annotation>
+    <xs:annotation>
+        <xs:documentation>
+      This is XHTML, a reformulation of HTML as a modular XML application
+      The Extensible HyperText Markup Language (XHTML)
+      Copyright &#169;1998-2007 World Wide Web Consortium
+      (Massachusetts Institute of Technology, European Research Consortium
+       for Informatics and Mathematics, Keio University).
+      All Rights Reserved.
+
+      Permission to use, copy, modify and distribute the XHTML Schema
+      modules and their accompanying xs:documentation for any purpose
+      and without fee is hereby granted in perpetuity, provided that the above
+      copyright notice and this paragraph appear in all copies.
+      The copyright holders make no representation about the suitability of
+      these XML Schema modules for any purpose.
+
+      They are provided "as is" without expressed or implied warranty.
+    </xs:documentation>
+    </xs:annotation>
+    <xs:annotation>
+        <xs:documentation>
+      This is the Schema Driver file for XHTML1.1
+      Document Type
+
+     This schema
+        + imports external schemas (xml.xsd)
+        + refedines (and include)s schema modules for XHTML1.1 Document Type.
+        + includes Schema for Named content model for the
+          XHTML1.1 Document Type
+
+        XHTML1.1 Document Type includes the following Modules
+           XHTML Core modules (Required for XHTML Family Conformance)
+            +  text
+            +  hypertext
+            +  lists
+            +  structure
+           Other XHTML modules
+            +  Edit
+            +  Bdo
+            +  Presentational
+            +  Link
+            +  Meta
+            +  Base
+            +  Scripting
+            +  Style
+            +  Image
+            +  Applet
+            +  Object
+            +  Param (Applet/Object modules require Param Module)
+            +  Tables
+            +  Forms
+            +  Client side image maps
+            +  Server side image maps
+            +  Ruby
+    </xs:documentation>
+    </xs:annotation>
+    <xs:import
+        namespace="http://www.w3.org/XML/1998/namespace"
+        schemaLocation="http://www.w3.org/2001/xml.xsd">
+        <xs:annotation>
+            <xs:documentation>
+         This import brings in the XML namespace attributes
+         The XML attributes are used by various modules.
+       </xs:documentation>
+        </xs:annotation>
+    </xs:import>
+    <xs:include
+        schemaLocation="https://www.w3.org/MarkUp/SCHEMA/xhtml11-model-1.xsd">
+        <xs:annotation>
+            <xs:documentation>
+        Document Model module for the XHTML1.1 Document Type.
+        This schema file defines all named models used by XHTML
+        Modularization Framework for XHTML1.1 Document Type
+      </xs:documentation>
+        </xs:annotation>
+    </xs:include>
+    <xs:include
+        schemaLocation="https://www.w3.org/MarkUp/SCHEMA/xhtml11-modules-1.xsd">
+        <xs:annotation>
+            <xs:documentation>
+        Schema that includes all modules (and redefinitions)
+        for XHTML1.1 Document Type.
+           </xs:documentation>
+        </xs:annotation>
+    </xs:include>
+</xs:schema>

data/bin/cache/xml.xsd

@@ -0,0 +1,287 @@
+<?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/bin/jhove.conf

@@ -37,8 +37,46 @@
  </module>
  <module>
   <class>edu.harvard.hul.ois.jhove.module.XmlModule</class>
-  <param>schema=http://www.example.com/schema;/home/schemas/exampleschema.xsd</param>
- </module>
+  <param>schema=http://www.w3.org/markUp/schema/xhtml11.xsd;cache/xhtml11.xsd</param>
+  <param>schema=http://www.w3.org/2001/xml.xsd;cache/xml.xsd</param>
+  <param>schema=http://www.w3.org/markUp/schema/xhtml11-model-1.xsd;cache/xhtml11-model-1.xsd</param>
+  <param>schema=https://www.w3.org/markUp/schema/xhtml11-model-1.xsd;cache/xhtml11-model-1.xsd</param>
+  <param>schema=http://www.w3.org/markUp/schema/xhtml11-modules-1.xsd;cache/xhtml11-modules-1.xsd</param>
+  <param>schema=https://www.w3.org/markUp/schema/xhtml11-modules-1.xsd;cache/xhtml11-modules-1.xsd</param>
+  <param>schema=http://www.w3.org/markUp/schema/xhtml-attribs-1.xsd;cache/xhtml-attribs-1.xsd</param>
+  <param>schema=https://www.w3.org/markUp/schema/xhtml-attribs-1.xsd;cache/xhtml-attribs-1.xsd</param>
+  <param>schema=http://www.w3.org/markUp/schema/xhtml-base-1.xsd;cache/xhtml-base-1.xsd</param>
+  <param>schema=https://www.w3.org/markUp/schema/xhtml-blkphras-1.xsd;cache/xhtml-blkphras-1.xsd</param>
+  <param>schema=https://www.w3.org/markUp/schema/xhtml-blkpres-1.xsd;cache/xhtml-blkpres-1.xsd</param>
+  <param>schema=https://www.w3.org/markUp/schema/xhtml-blkstruct-1.xsd;cache/xhtml-blkstruct-1.xsd</param>
+  <param>schema=http://www.w3.org/markUp/schema/xhtml-bdo-1.xsd;cache/xhtml-bdo-1.xsd</param>
+  <param>schema=http://www.w3.org/markUp/schema/xhtml-csismap-1.xsd;cache/xhtml-csismap-1.xsd</param>
+  <param>schema=http://www.w3.org/markUp/schema/xhtml-datatypes-1.xsd;cache/xhtml-datatypes-1.xsd</param>
+  <param>schema=http://www.w3.org/markUp/schema/xhtml-edit-1.xsd;cache/xhtml-edit-1.xsd</param>
+  <param>schema=http://www.w3.org/markUp/schema/xhtml-events-1.xsd;cache/xhtml-events-1.xsd</param>
+  <param>schema=http://www.w3.org/markUp/schema/xhtml-form-1.xsd;cache/xhtml-form-1.xsd</param>
+  <param>schema=http://www.w3.org/markUp/schema/xhtml-framework-1.xsd;cache/xhtml-framework-1.xsd</param>
+  <param>schema=http://www.w3.org/markUp/schema/xhtml-hypertext-1.xsd;cache/xhtml-hypertext-1.xsd</param>
+  <param>schema=http://www.w3.org/markUp/schema/xhtml-image-1.xsd;cache/xhtml-image-1.xsd</param>
+  <param>schema=https://www.w3.org/markUp/schema/xhtml-inlphras-1.xsd;cache/xhtml-inlphras-1.xsd</param>
+  <param>schema=https://www.w3.org/markUp/schema/xhtml-inlpres-1.xsd;cache/xhtml-inlpres-1.xsd</param>
+  <param>schema=https://www.w3.org/markUp/schema/xhtml-inlstruct-1.xsd;cache/xhtml-inlstruct-1.xsd</param>
+  <param>schema=http://www.w3.org/markUp/schema/xhtml-inlstyle-1.xsd;cache/xhtml-inlstyle-1.xsd</param>
+  <param>schema=http://www.w3.org/markUp/schema/xhtml-link-1.xsd;cache/xhtml-link-1.xsd</param>
+  <param>schema=http://www.w3.org/markUp/schema/xhtml-list-1.xsd;cache/xhtml-list-1.xsd</param>
+  <param>schema=http://www.w3.org/markUp/schema/xhtml-meta-1.xsd;cache/xhtml-meta-1.xsd</param>
+  <param>schema=http://www.w3.org/markUp/schema/xhtml-object-1.xsd;cache/xhtml-object-1.xsd</param>
+  <param>schema=http://www.w3.org/markUp/schema/xhtml-param-1.xsd;cache/xhtml-param-1.xsd</param>
+  <param>schema=https://www.w3.org/markUp/schema/xhtml-param-1.xsd;cache/xhtml-param-1.xsd</param>
+  <param>schema=http://www.w3.org/markUp/schema/xhtml-pres-1.xsd;cache/xhtml-pres-1.xsd</param>
+  <param>schema=http://www.w3.org/markUp/schema/xhtml-ruby-1.xsd;cache/xhtml-ruby-1.xsd</param>
+  <param>schema=http://www.w3.org/markUp/schema/xhtml-script-1.xsd;cache/xhtml-script-1.xsd</param>
+  <param>schema=http://www.w3.org/markUp/schema/xhtml-ssismap-1.xsd;cache/xhtml-ssismap-1.xsd</param>
+  <param>schema=http://www.w3.org/markUp/schema/xhtml-struct-1.xsd;cache/xhtml-struct-1.xsd</param>
+  <param>schema=http://www.w3.org/markUp/schema/xhtml-style-1.xsd;cache/xhtml-style-1.xsd</param>
+  <param>schema=http://www.w3.org/markUp/schema/xhtml-table-1.xsd;cache/xhtml-table-1.xsd</param>
+  <param>schema=http://www.w3.org/markUp/schema/xhtml-target-1.xsd;cache/xhtml-target-1.xsd</param>
+  <param>schema=http://www.w3.org/markUp/schema/xhtml-text-1.xsd;cache/xhtml-text-1.xsd</param> </module>
  <module>
   <class>edu.harvard.hul.ois.jhove.module.HtmlModule</class>
  </module>

data/bin/jhoveToolkit.sh

@@ -30,14 +30,44 @@
 # adjust your shell's path or revert to the old way (commented out).
 # Configuration constants:
 
-JHOVE_HOME=`dirname $0`
-JHOVE_VERSION=1.20.1
+# Infer JHOVE_HOME from script location
+SCRIPT="${0}"
 
+echo ${SCRIPT}
+
+# Resolve absolute and relative symlinks
+while [ -h "${SCRIPT}" ]; do
+    LS=$( ls -ld "${SCRIPT}" )
+    LINK=$( expr "${LS}" : '.*-> \(.*\)$' )
+    if expr "${LINK}" : '/.*' > /dev/null; then
+        SCRIPT="${LINK}"
+    else
+        SCRIPT="$( dirname "${SCRIPT}" )/${LINK}"
+    fi
+done
+
+# Store absolute location
+CWD="$( pwd )"
+JHOVE_HOME="$( cd "$(dirname "${SCRIPT}" )" && pwd )"
+cd "${CWD}" || exit
 export JHOVE_HOME
+
+JHOVE_VERSION=1.24.0-RC1
 JAVA_HOME=/etc/alternatives/jre
 JAVA=/usr/bin/java
 
 CP=${JHOVE_HOME}/jhove-apps-${JHOVE_VERSION}.jar:${JHOVE_HOME}/jhove-ext-modules-${JHOVE_VERSION}.jar
+CP=${CP}:${JHOVE_HOME}/aiff-hul-1.6.1-RC1.jar
+CP=${CP}:${JHOVE_HOME}/ascii-hul-1.4.1.jar
+CP=${CP}:${JHOVE_HOME}/gif-hul-1.4.2-RC1.jar
+CP=${CP}:${JHOVE_HOME}/html-hul-1.4.1.jar
+CP=${CP}:${JHOVE_HOME}/jpeg-hul-1.5.2-RC1.jar
+CP=${CP}:${JHOVE_HOME}/jpeg2000-hul-1.4.2-RC1.jar
+CP=${CP}:${JHOVE_HOME}/pdf-hul-1.12.2-RC1.jar
+CP=${CP}:${JHOVE_HOME}/tiff-hul-1.9.2-RC1.jar
+CP=${CP}:${JHOVE_HOME}/utf8-hul-1.7.1.jar
+CP=${CP}:${JHOVE_HOME}/wave-hul-1.8.1-RC1.jar
+CP=${CP}:${JHOVE_HOME}/xml-hul-1.5.1.jar
 
 # Retrieve a copy of all command line arguments to pass to the application.
 # Since looping over the positional parameters is such a common thing to do in scripts,
@@ -51,5 +81,7 @@ for ARG do
     ARGS="$ARGS $ARG"
 done
 
+echo $JHOVE_HOME
+
 # Set the CLASSPATH and invoke the Java loader.
 ${JAVA} -Xms128M -Xmx6000M -classpath $CP Jhove $ARGS