behemoth-site.xml

<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>

<configuration>

	<!-- overriding Hadoop values -->

	<property>
		<name>mapred.child.java.opts</name>
		<value>-Xmx1024m</value>
	</property>

	<property>
		<name>mapred.compress.map.output</name>
		<value>true</value>
	</property>

	<property>
		<name>mapred.output.compress</name>
		<value>true</value>
	</property>

	<property>
		<name>mapred.output.compression.type</name>
		<value>BLOCK</value>
	</property>

	<property>
		<name>hadoop.job.history.user.location</name>
		<value>${hadoop.log.dir}/history/user</value>
		<description>Hadoop 0.17.x comes with a default setting to create
			user logs inside the output path of the job. This breaks some
			Hadoop classes, which expect the output to contain only
			part-XXXXX files. This setting changes the output to a
			subdirectory of the regular log directory.
		</description>
	</property>

	<!-- Properties for GATE -->

	<property>
		<name>gate.annotationset.input</name>
		<value></value>
		<description>Map the information at the behemoth format onto the
			select annotationset
		</description>
	</property>

	<property>
		<name>gate.annotationset.output</name>
		<value></value>
		<description>AnnotationSet to consider when serializing to the
			behemoth format
		</description>
	</property>

	<property>
		<name>gate.annotations.filter</name>
		<value>Token</value>
		<description>Annotations types to consider when serializing to the
			behemoth format, separated by commas
		</description>
	</property>

	<property>
		<name>gate.features.filter</name>
		<value>Token.string</value>
		<description>if specified, only the feature listed for a type will be
			kept
		</description>
	</property>

	<property>
		<name>gate.emptyannotationset</name>
		<value>false</value>
		<description>if specified all the annotations in the Behemoth document
			will be deleted before processing with GATE
		</description>
	</property>

	<!-- Properties for UIMA -->

	<property>
		<name>uima.annotations.filter</name>
		<value>org.apache.uima.TokenAnnotation,org.apache.uima.SentenceAnnotation</value>
		<description>Annotations types to consider when serializing to the
			behemoth format, separated by commas
		</description>
	</property>

	<property>
		<name>uima.features.filter</name>
		<value>org.apache.uima.TokenAnnotation:posTag</value>
		<description>Feature names to consider when serializing to the
			behemoth format, separated by commas
		</description>
	</property>

</configuration>