tags/-rc1/trunk/src/test/resources/descriptors/cas_multiplier/Segment_Annotate_Merge_AE.xml

<?xml version="1.0" encoding="UTF-8"?>
<!--
***************************************************************
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements.  See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership.  The ASF licenses this file
* to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance
* with the License.  You may obtain a copy of the License at
*
*   http://www.apache.org/licenses/LICENSE-2.0
* 
* Unless required by applicable law or agreed to in writing,
* software distributed under the License is distributed on an
* "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
* KIND, either express or implied.  See the License for the
* specific language governing permissions and limitations
* under the License.
***************************************************************
-->
<analysisEngineDescription xmlns="http://uima.apache.org/resourceSpecifier">
	<frameworkImplementation>org.apache.uima.java</frameworkImplementation>
	<primitive>false</primitive>
	
	<delegateAnalysisEngineSpecifiers>
		<delegateAnalysisEngine key="Segmenter">
			<import location="SimpleTextSegmenter.xml"/>
		</delegateAnalysisEngine>
		
		<delegateAnalysisEngine key="Tokenizer">
			<import
				location="../analysis_engine/SimpleTokenAndSentenceAnnotator.xml"/>
		</delegateAnalysisEngine>
		
		<delegateAnalysisEngine key="NameRecognizer">
			<import
				location="../analysis_engine/SimpleNameRecognizer_RegEx_TAE.xml"/>
		</delegateAnalysisEngine>
		
		<delegateAnalysisEngine key="Merger">
			<import location="SimpleTextMerger.xml"/>
		</delegateAnalysisEngine>
	</delegateAnalysisEngineSpecifiers>
		
	<flowController key="FixedFlowController">
		<import name="org.apache.uima.flow.FixedFlowController"/>
	</flowController>
		
	<analysisEngineMetaData>
		<name>Segment, Annotate, and Merge Example AE</name>
		<description>Splits a document into pieces and runs the tokenizer and name
			recognizer on each piece independently. Then runs the merger to reassemble the
			document, keeping the name annotations in the merged document but discarding
			the tokens. 
		
		    By default the intermediate segments are dropped after being processed by the merger, and
			are not output from the aggregate.  This behavior is configurable via the
			ActionForIntermediateSegments parameter.
		</description>
		<version>1.0</version>
		<vendor>The Apache Software Foundation</vendor>
		<flowConstraints>
			<fixedFlow>
				<node>Segmenter</node>
				<node>Tokenizer</node>
				<node>NameRecognizer</node>
				<node>Merger</node>
			</fixedFlow>
		</flowConstraints>
		
		<configurationParameters>
			<configurationParameter>
				<name>AnnotationTypesToPreserve</name>
				<description>Names of annotation types to be preserved in the merged CAS.</description>
				<type>String</type>
				<multiValued>true</multiValued>
				<mandatory>true</mandatory>
				<overrides>
					<parameter>Merger/AnnotationTypesToCopy</parameter>
				</overrides>
			</configurationParameter>
			
			  <configurationParameter>
				 <name>ActionForIntermediateSegments</name>
				 <description>Tells the flow controller what to do with intermediate segments after they are input to the merger.
				 Valid values are:
					continue - the CAS continues on to the next element in the flow
					stop - the CAS will no longer continue in the flow, and will be returned from the aggregate if possible.
					drop - the CAS will no longer continue in the flow, and will be dropped (not returned from the aggregate) if possible.	 
					dropIfNewCasProduced (the default) - if the CAS multiplier produced a new CAS as a result of processing this CAS, then this
						CAS will be dropped.  If not, then this CAS will continue.			 
				 </description>
				 <type>String</type>
				 <multiValued>false</multiValued>
				 <mandatory>false</mandatory>
				  <overrides>
					  <parameter>FixedFlowController/ActionAfterCasMultiplier</parameter>
				  </overrides>
			   </configurationParameter>			
			 </configurationParameters>
		
		<configurationParameterSettings>
			<nameValuePair>
				<name>AnnotationTypesToPreserve</name>
				<value>
					<array>
						<string>example.Name</string>
					</array>
				</value>
			</nameValuePair>
			<nameValuePair>
				<name>ActionForIntermediateSegments</name>
				<value>
					<string>drop</string>
				</value>
			</nameValuePair>
		</configurationParameterSettings>
		
		<capabilities>
			<capability>
				<inputs/>
				<outputs>
					<type allAnnotatorFeatures="true">
						org.apache.uima.examples.tokenizer.Sentence</type>
					<type allAnnotatorFeatures="true">
						org.apache.uima.examples.tokenizer.Token</type>
					<type allAnnotatorFeatures="true">example.Name</type>
				</outputs>
				<languagesSupported>
					<language>en</language>
				</languagesSupported>
			</capability>
		</capabilities>
		<operationalProperties>
			<modifiesCas>true</modifiesCas>
			<multipleDeploymentAllowed>true</multipleDeploymentAllowed>
			<outputsNewCASes>true</outputsNewCASes>
		</operationalProperties>
	</analysisEngineMetaData>
</analysisEngineDescription>