Page Comparison

...

Table of Contents

minLevel	3

Modifications to existing config files

/config/spring/jhove2-framework-config.xml

Add the following section to the xml. This adds a developer BnF to Jhove2.

Code Block

title	jhove2-framework-config.xml
borderStyle	solid

	<!-- BnF (Bibliothéque nationale de France) agent bean -->
	<bean id="BnFAgent" class="org.jhove2.core.Agent" scope="singleton">
		<constructor-arg value="BibliothÃ¨que nationale de France"
		                 type="java.lang.String"/>
		<constructor-arg value="Corporate"
		                 type="org.jhove2.core.Agent$Type"/>
		<property name="URI" value="http://www.bnf.fr/"/>
	</bean>

/config/spring/persist/jhove2-persist-config.xml

Must be set to BerkeleyDB persistence because of several bugs in the InMemory persistence.

...

Code Block

title	jhove2-persist-config.xml
borderStyle	solid

	<bean id="BerkeleyDbPersistenceManager" class="org.jhove2.persist.berkeleydpl.BerkeleyDbPersistenceManager"
	     scope="singleton">
	     <!--property name="envHome" value="C:\"/-->
	     <property name="envHome" value="C:\Java\BerkeleyDb\"/>
	     <!--property name="envHome" value="/tmp/BerkeleyDb/"/-->
 	     <property name="entityStoreName" value="JHOVE2_Entity_Store"/>
 	     <property name="storeConfig" ref="StoreConfig"/>
	     <property name="envConfig" ref="EnvironmentConfig"/>
	</bean>

/config/droid/DROID_SignatureFile_V20.xml

The Droid signature file needs to be modified to recognize ARC and WARC files correctly.

...

Code Block

title	DROID_SignatureFile_V20.xml
borderStyle	solid

	<!-- ARC -->
        <FileFormat ID="310" Name="Alexa Archive File" PUID="x-fmt/219">
            <InternalSignatureID>123456</InternalSignatureID>
            <Extension>arc</Extension>
            <!-- If left out file is recognized as SGML -->
            <HasPriorityOverFileFormatID>638</HasPriorityOverFileFormatID>
            <HasPriorityOverFileFormatID>639</HasPriorityOverFileFormatID>
            <HasPriorityOverFileFormatID>640</HasPriorityOverFileFormatID>
            <HasPriorityOverFileFormatID>641</HasPriorityOverFileFormatID>
            <HasPriorityOverFileFormatID>642</HasPriorityOverFileFormatID>
            <HasPriorityOverFileFormatID>643</HasPriorityOverFileFormatID>
            <HasPriorityOverFileFormatID>644</HasPriorityOverFileFormatID>
            <HasPriorityOverFileFormatID>645</HasPriorityOverFileFormatID>
        </FileFormat>
	<!-- WARC -->
        <FileFormat ID="12345" Name="WARC file" Version="1.0" PUID="x-fmt/289">
            <InternalSignatureID>12345</InternalSignatureID>
       	    <Extension>warc</Extension>
            <!-- If left out file is recognized as SGML -->
            <HasPriorityOverFileFormatID>638</HasPriorityOverFileFormatID>
            <HasPriorityOverFileFormatID>639</HasPriorityOverFileFormatID>
            <HasPriorityOverFileFormatID>640</HasPriorityOverFileFormatID>
            <HasPriorityOverFileFormatID>641</HasPriorityOverFileFormatID>
            <HasPriorityOverFileFormatID>642</HasPriorityOverFileFormatID>
            <HasPriorityOverFileFormatID>643</HasPriorityOverFileFormatID>
            <HasPriorityOverFileFormatID>644</HasPriorityOverFileFormatID>
            <HasPriorityOverFileFormatID>645</HasPriorityOverFileFormatID>
        </FileFormat>

New configuration files

/config/spring/module/format/gzip/jhove2-gzip-config.xml

Added to allow Spring to recognize and load the GZipModule.

Code Block

title	jhove2-gzip-config.xml
borderStyle	solid

<?xml version="1.0" encoding="UTF-8"?>
<beans xmlns="http://www.springframework.org/schema/beans"
       xmlns:util="http://www.springframework.org/schema/util"
       xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
       xmlns:context="http://www.springframework.org/schema/context"
       xsi:schemaLocation="http://www.springframework.org/schema/beans http://www.springframework.org/schema/beans/spring-beans-2.5.xsd http://www.springframework.org/schema/context http://www.springframework.org/schema/context/spring-context-2.5.xsd http://www.springframework.org/schema/util http://www.springframework.org/schema/util/spring-util-2.0.xsd">

	<!-- GZip module bean -->
	<bean id="GZipModule" class="org.jhove2.module.format.gzip.GzipModule" scope="prototype">
		<constructor-arg ref="GZipFormat"/>
		<constructor-arg ref="FormatModuleAccessor"/>
		<property name="developers">
			<list value-type="org.jhove2.core.Agent">
				<ref bean="BnFAgent"/>
			</list>
		</property>
		<property name="recurse" value="true"/>
		<!--property name="parallelCharacterization" value="4"/-->
	</bean>

	<!-- GZip format bean -->
	<bean id="GZipFormat" class="org.jhove2.core.format.Format" scope="singleton">
		<constructor-arg type="java.lang.String" value="GZip"/>
		<constructor-arg ref="GZipIdentifier"/>
		<constructor-arg type="org.jhove2.core.format.Format$Type" value="Format"/>
		<constructor-arg type="org.jhove2.core.format.Format$Ambiguity" value="Unambiguous"/>
		<property name="aliasIdentifiers">
			<set value-type="org.jhove2.core.I8R">
				<!-- ref bean="GZipIdentifier"/ -->
				<ref bean="GZipXFmt266Identifier"/>
				<ref bean="GZipMimeIdentifier"/>
				<ref bean="GZipRFC1952Identifier"/>
				<ref bean="GZipAppleUTIIdentifier"/>
			</set>
		</property>
		<property name="aliasNames">
			<set>
				<value>GZIP</value>
			</set>
		</property>
		<property name="specifications">
			<list value-type="org.jhove2.core.Document">
				<ref bean="GZip43Specification"/>
			</list>
		</property>
	</bean>

	<!-- Alias Identifiers -->

	<!-- GZip identifier bean -->
	<bean id="GZipIdentifier" class="org.jhove2.core.I8R" scope="singleton">
		<constructor-arg type="java.lang.String" value="http://jhove2.org/terms/format/gzip"/>
	</bean>

        <!-- GZip PUID x-fmt/266 alias identifier bean -->
        <bean id="GZipXFmt266Identifier" class="org.jhove2.core.I8R" scope="singleton">
		<constructor-arg type="java.lang.String" value="x-fmt/266"/>
		<constructor-arg type="org.jhove2.core.I8R$Namespace" value="PUID"/>
        </bean>

        <!-- GZip MIME alias identifier bean -->
        <bean id="GZipMimeIdentifier" class="org.jhove2.core.I8R" scope="singleton">
		<constructor-arg type="java.lang.String" value="application/x-gzip"/>
		<constructor-arg type="org.jhove2.core.I8R$Namespace" value="MIME"/>
        </bean>

        <!-- GZip RFC 1952 alias identifier bean -->
        <bean id="GZipRFC1952Identifier" class="org.jhove2.core.I8R" scope="singleton">
		<constructor-arg type="java.lang.String" value="RFC 1952"/>
		<constructor-arg type="org.jhove2.core.I8R$Namespace" value="RFC"/>
        </bean>

        <!-- GZip Apple UTI alias identifier bean -->
        <bean id="GZipAppleUTIIdentifier" class="org.jhove2.core.I8R" scope="singleton">
		<constructor-arg type="java.lang.String" value="org.gnu.gnu-zip-archive"/>
		<constructor-arg type="org.jhove2.core.I8R$Namespace" value="UTI"/>
	</bean>

	<!-- Specifications -->

	<!-- GZIP file format version 4.3 specification bean -->
	<bean id="GZip43Specification" class="org.jhove2.core.Document" scope="singleton">
		<constructor-arg type="java.lang.String" value="GZIP file format specification version 4.3"/>
		<constructor-arg type="org.jhove2.core.Document$Type" value="Specification"/>
		<constructor-arg type="org.jhove2.core.Document$Intention" value="Authoritative"/>
		<property name="author" value="P. Deutsch"/>
		<property name="date" value="May 1996"/>
		<property name="edition" value="RFC 1952"/>
		<property name="identifiers">
		<list value-type="org.jhove2.core.I8R">
				<bean class="org.jhove2.core.I8R">
					<constructor-arg type="java.lang.String" value="http://tools.ietf.org/html/rfc1952"/>
					<constructor-arg type="org.jhove2.core.I8R$Namespace" value="URI"/>
				</bean>
			</list>
		</property>
		<property name="publisher" value="IETF"/>
	</bean>

	<!-- GZip module resources -->

  <!-- GZip header compression methods description resources -->
  <bean class="org.springframework.beans.factory.config.MethodInvokingFactoryBean">
    <property name="targetClass"
              value="org.jhove2.module.format.gzip.field.CompressionMethod"/>
    <property name="targetMethod" value="initValues"/>
    <property name="arguments">
      <list>
        <bean class="org.jhove2.config.spring.ModulePropertiesFactoryBean">
          <property name="propertyFileBaseName"
                    value="gzip/compression-methods"/>
        </bean>
      </list>
    </property>
  </bean>

  <!-- GZip header extra flags description resources -->
  <bean class="org.springframework.beans.factory.config.MethodInvokingFactoryBean">
    <property name="targetClass"
              value="org.jhove2.module.format.gzip.field.CompressionType"/>
    <property name="targetMethod" value="initValues"/>
    <property name="arguments">
      <list>
        <bean class="org.jhove2.config.spring.ModulePropertiesFactoryBean">
          <property name="propertyFileBaseName"
                    value="gzip/compression-types"/>
        </bean>
      </list>
    </property>
  </bean>

  <!-- GZip header operating systems description resources -->
  <bean class="org.springframework.beans.factory.config.MethodInvokingFactoryBean">
    <property name="targetClass"
              value="org.jhove2.module.format.gzip.field.OperatingSystem"/>
    <property name="targetMethod" value="initValues"/>
    <property name="arguments">
      <list>
        <bean class="org.jhove2.config.spring.ModulePropertiesFactoryBean">
          <property name="propertyFileBaseName"
                    value="gzip/operating-systems"/>
        </bean>
      </list>
    </property>
  </bean>

</beans>

/config/spring/module/format/arc/jhove2-arc-config.xml

Added to allow Spring to recognize and load the ArcModule.

Code Block

title	jhove2-arc-config.xml
borderStyle	solid

<?xml version="1.0" encoding="UTF-8"?>
<beans xmlns="http://www.springframework.org/schema/beans"
       xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
       xsi:schemaLocation="http://www.springframework.org/schema/beans http://www.springframework.org/schema/beans/spring-beans-2.5.xsd">

    <!-- ARC module bean -->
    <bean id="ArcModule" class="org.jhove2.module.format.arc.ArcModule" scope="prototype">
        <constructor-arg ref="AlexaArchiveFileFormat"/>
	<constructor-arg ref="FormatModuleAccessor"/>
	<property name="developers">
	    <list value-type="org.jhove2.core.Agent">
	      <ref bean="BnFAgent"/>
	    </list>
	</property>
	<property name="recurse" value="false"/>
	<property name="computeBlockDigest" value="true"/>
	<property name="blockDigestAlgorithm" value="sha1"/>
	<property name="blockDigestEncoding" value="base32"/>
	<property name="computePayloadDigest" value="true"/>
	<property name="payloadDigestAlgorithm" value="sha1"/>
	<property name="payloadDigestEncoding" value="base32"/>
	<!--property name="parallelCharacterization" value="0"/-->
    </bean>

    <!-- ARC format bean -->
    <bean id="AlexaArchiveFileFormat" class="org.jhove2.core.format.Format" scope="singleton">
        <constructor-arg type="java.lang.String" value="Alexa Archive File"/>
	<constructor-arg ref="AlexaArchiveFileIdentifier"/>
	<constructor-arg type="org.jhove2.core.format.Format$Type" value="Format"/>
	<constructor-arg type="org.jhove2.core.format.Format$Ambiguity" value="Unambiguous"/>

	<property name="aliasIdentifiers">
  	    <set value-type="org.jhove2.core.I8R">
	    <ref bean="AlexaArchiveFileIdentifier"/>
	    <!-- ARC PUID x-fmt/219 alias identifier bean -->
	    <bean class="org.jhove2.core.I8R">
	      <constructor-arg type="java.lang.String" value="x-fmt/219"/>
	      <constructor-arg type="org.jhove2.core.I8R$Namespace" value="PUID"/>
	    </bean>
	    <!-- ARC MIME alias identifier bean -->
	    <bean class="org.jhove2.core.I8R">
	      <constructor-arg type="java.lang.String" value="application/x-ia-arc"/>
	      <constructor-arg type="org.jhove2.core.I8R$Namespace" value="MIME"/>
	    </bean>
	  </set>
	</property>
	<property name="aliasNames">
	  <set>
	    <value>ARC</value>
	  </set>
	</property>
	<property name="specifications">
	  <list value-type="org.jhove2.core.Document">
	    <ref bean="Arc10Specification"/>
	  </list>
	</property>
    </bean>

  <!-- Arc identifier bean -->
  <bean id="AlexaArchiveFileIdentifier" class="org.jhove2.core.I8R" scope="singleton">
    <constructor-arg value="http://jhove2.org/terms/format/arc"
                     type="java.lang.String"/>
  </bean>

  <!-- ARC file format version 1.0 specification bean -->
  <bean id="Arc10Specification" class="org.jhove2.core.Document" scope="singleton">
    <constructor-arg type="java.lang.String"
                     value="ARC file format specification version 1.0"/>
    <constructor-arg type="org.jhove2.core.Document$Type"
                     value="Specification"/>
    <constructor-arg type="org.jhove2.core.Document$Intention"
                     value="Authoritative"/>

    <property name="author" value="Mike Burner and Brewster Kahle"/>
    <property name="date" value="September 15, 1996"/>
  </bean>

</beans>

/config/spring/module/format/warc/jhove2-warc-config.xml

Added to allow Spring to recognize and load the WarcModule.

Code Block

title	jhove2-warc-config.xml
borderStyle	solid

<?xml version="1.0" encoding="UTF-8"?>
<beans xmlns="http://www.springframework.org/schema/beans"
       xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
       xsi:schemaLocation="http://www.springframework.org/schema/beans http://www.springframework.org/schema/beans/spring-beans-2.5.xsd">

  <!-- WARC module bean -->
  <bean id="WarcModule" class="org.jhove2.module.format.warc.WarcModule" scope="prototype">
    <constructor-arg ref="WarcArchiveFileFormat"/>
    <constructor-arg ref="FormatModuleAccessor"/>
    <property name="developers">
      <list value-type="org.jhove2.core.Agent">
	<ref bean="BnFAgent"/>
      </list>
    </property>
    <property name="recurse" value="false"/>
    <property name="computeBlockDigest" value="true"/>
    <property name="blockDigestAlgorithm" value="sha1"/>
    <property name="blockDigestEncoding" value="base32"/>
    <property name="computePayloadDigest" value="true"/>
    <property name="payloadDigestAlgorithm" value="sha1"/>
    <property name="payloadDigestEncoding" value="base32"/>
    <!--property name="parallelCharacterization" value="0"/-->
  </bean>

  <!-- WARC format bean -->
  <bean id="WarcArchiveFileFormat" class="org.jhove2.core.format.Format" scope="singleton">
    <constructor-arg type="java.lang.String" value="Warc Archive File"/>
    <constructor-arg ref="WarcArchiveFileIdentifier"/>
    <constructor-arg type="org.jhove2.core.format.Format$Type" value="Format"/>
    <constructor-arg type="org.jhove2.core.format.Format$Ambiguity" value="Unambiguous"/>
    <property name="aliasIdentifiers">
      <set value-type="org.jhove2.core.I8R">
	<ref bean="WarcArchiveFileIdentifier"/>
	<!-- ARC PUID x-fmt/219 alias identifier bean -->
	<bean class="org.jhove2.core.I8R">
	  <constructor-arg type="java.lang.String" value="x-fmt/289"/>
	  <constructor-arg type="org.jhove2.core.I8R$Namespace" value="PUID"/>
	</bean>
	<!-- WARC MIME alias identifier bean -->
	<bean class="org.jhove2.core.I8R">
	  <constructor-arg type="java.lang.String" value="application/warc"/>
	  <constructor-arg type="org.jhove2.core.I8R$Namespace" value="MIME"/>
	</bean>
	<!-- WARC ISO 28500 -->
	<bean id="WarcISO28500" class="org.jhove2.core.I8R" scope="singleton">
	  <constructor-arg type="java.lang.String" value="ISO 28500:2009(E)" />
	  <constructor-arg type="org.jhove2.core.I8R$Namespace" value="ISO" />
	</bean>
      </set>
    </property>
    <property name="aliasNames">
      <set>
	<value>WARC</value>
      </set>
    </property>
    <property name="specifications">
      <list value-type="org.jhove2.core.Document">
	<ref bean="Warc10Specification"/>
      </list>
    </property>
  </bean>

  <!-- WARC identifier bean -->
  <bean id="WarcArchiveFileIdentifier" class="org.jhove2.core.I8R" scope="singleton">
    <constructor-arg value="http://jhove2.org/terms/format/warc" type="java.lang.String"/>
  </bean>

  <!-- WARC file format version 1.0 specification bean -->
  <bean id="Warc10Specification" class="org.jhove2.core.Document" scope="singleton">
    <constructor-arg type="java.lang.String"
                     value="WARC file format specification version 1.0"/>
    <constructor-arg type="org.jhove2.core.Document$Type"
                     value="Specification"/>
    <constructor-arg type="org.jhove2.core.Document$Intention"
                     value="Authoritative"/>

    <property name="author" value="Technical Committee ISO/TC 46"/>
    <property name="date" value="September 15, 1996"/>
    <property name="identifiers">
      <list value-type="org.jhove2.core.I8R">
	<ref bean="ISO28500WARCSpecificationURI"/>
      </list>
    </property>
    <property name="publisher" value="ISO"/>
    <!--property name="title" value="ISO 28500: Information and documentation - WARC file format"/-->
  </bean>

  <!-- ISO 28500 WARC specification URI bean -->
  <bean id="ISO28500WARCSpecificationURI" class="org.jhove2.core.I8R" scope="singleton">
    <constructor-arg type="java.lang.String" value="http://www.iso.org/iso/iso_catalogue/catalogue_tc/catalogue_detail.htm?csnumber=44717"/>
    <constructor-arg type="org.jhove2.core.I8R$Namespace" value="URI"/>
  </bean>

</beans>

Sources

/src/main/java/org/jhove2/module/format/gzip/

This folder contains all the GZipModule implementation sources.

/src/main/java/org/jhove2/module/format/arc/

This folder contains all the ArcModule implementation sources.

/src/main/java/org/jhove2/module/format/warc/

This folder contains all the WarcModule implementation sources.

...

Version	Old Version 15	New Version 16
Changes made by	Nicholas Clarke	Nicholas Clarke
Saved on	Jan 24, 2012	Jan 24, 2012

Versions Compared

Key

Modifications to existing config files

/config/spring/jhove2-framework-config.xml

/config/spring/persist/jhove2-persist-config.xml

/config/droid/DROID_SignatureFile_V20.xml

New configuration files

/config/spring/module/format/gzip/jhove2-gzip-config.xml

/config/spring/module/format/arc/jhove2-arc-config.xml

/config/spring/module/format/warc/jhove2-warc-config.xml

Sources

/src/main/java/org/jhove2/module/format/gzip/

/src/main/java/org/jhove2/module/format/arc/

/src/main/java/org/jhove2/module/format/warc/