These were the changes I made to get the YTEX pipeline working with LVG (2008). 
It looks like there were just a couple of spots with some old hard-coded paths 
in SetupAUIFirstWord.java that were appropriate to the old ytex directory 
structure.

For now I have just swapped them out to fit with the new directory structure, 
but I suppose the correct fix may be to extract them out somewhere...  In any 
case I don't have write privileges, some someone else may want to fix this 
(Vijay?)

I also included the YTEXPipeline.xml descriptor file I fixed as well in case 
anybody needs it.

 -John


<?xml version="1.0" encoding="UTF-8"?>
<analysisEngineDescription xmlns="http://uima.apache.org/resourceSpecifier";>
	<frameworkImplementation>org.apache.uima.java</frameworkImplementation>
	<primitive>false</primitive>
	<delegateAnalysisEngineSpecifiers>
		<delegateAnalysisEngine key="AggregatePlaintextUMLSProcessor">
	      <import location="./AggregatePlaintextUMLSProcessor.xml"/>
		</delegateAnalysisEngine>
		<delegateAnalysisEngine key="DBConsumer">
	      <import location="./DBConsumer.xml"/>
		</delegateAnalysisEngine>
	</delegateAnalysisEngineSpecifiers>
	<analysisEngineMetaData>
		<name>YTEXPipeline</name>
		<description>ctakes AggregatePlaintextUMLSProcessor with following
			changes: Replaced cTAKES NegationAnnotator with YTEX NegexAnnotator,
			replaced cTAKES SimpleSegment with YTEX SegmentRegexAnnotator.
			Reconfigured DictionaryLookup to use YTEX dictionary.
			Added
			DateAnnotator, SenseDisambiguatorAnnotator,
			NamedEntityRegexAnnotator, DBConsumer
		</description>
		<version />
		<vendor />
		<configurationParameters searchStrategy="language_fallback">

			<configurationParameter>
				<name>xmiOutputDirectory</name>
				<type>String</type>
				<multiValued>false</multiValued>
				<mandatory>false</mandatory>
				<overrides>
					<parameter>DBConsumer/xmiOutputDirectory</parameter>
				</overrides>
			</configurationParameter>
		

			<configurationParameter>
				<name>analysisBatch</name>
				<type>String</type>
				<multiValued>false</multiValued>
				<mandatory>false</mandatory>
				<overrides>
					<parameter>DBConsumer/analysisBatch</parameter>
				</overrides>
			</configurationParameter>
			<configurationParameter>
				<name>storeDocText</name>
				<type>Boolean</type>
				<multiValued>false</multiValued>
				<mandatory>false</mandatory>
				<overrides>
					<parameter>DBConsumer/storeDocText</parameter>
				</overrides>
			</configurationParameter>
			<configurationParameter>
				<name>storeCAS</name>
				<type>Boolean</type>
				<multiValued>false</multiValued>
				<mandatory>false</mandatory>
				<overrides>
					<parameter>DBConsumer/storeCAS</parameter>
				</overrides>
			</configurationParameter>
			<configurationParameter>
				<name>typesToIgnore</name>
				<description>uima types (fully qualified class names) that should
					not be saved in the database.
				</description>
				<type>String</type>
				<multiValued>true</multiValued>
				<mandatory>false</mandatory>
				<overrides>
					<parameter>DBConsumer/typesToIgnore</parameter>
				</overrides>
			</configurationParameter>
			<configurationParameter>
				<name>insertAnnotationContainmentLinks</name>
				<description>should containment links be added
				</description>
				<type>Boolean</type>
				<multiValued>false</multiValued>
				<mandatory>false</mandatory>
				<overrides>
					<parameter>DBConsumer/insertAnnotationContainmentLinks</parameter>
				</overrides>
			</configurationParameter>
		</configurationParameters>
		<configurationParameterSettings>
			<nameValuePair>
				<name>xmiOutputDirectory</name>
				<value>
					<string>/home/josborne/Desktop</string>
				</value>
			</nameValuePair>
			<nameValuePair>
				<name>analysisBatch</name>
				<value>
					<string>test</string>
				</value>
			</nameValuePair>
			<nameValuePair>
				<name>storeDocText</name>
				<value>
					<boolean>true</boolean>
				</value>
			</nameValuePair>
			<nameValuePair>
				<name>storeCAS</name>
				<value>
					<boolean>true</boolean>
				</value>
			</nameValuePair>
			<nameValuePair>
				<name>insertAnnotationContainmentLinks</name>
				<value>
					<boolean>true</boolean>
				</value>
			</nameValuePair>
			<nameValuePair>
				<name>typesToIgnore</name>
				<value>
					<array>
						<string>org.apache.ctakes.typesystem.type.syntax.ContractionToken</string>
						<string>org.apache.ctakes.typesystem.type.syntax.NewlineToken</string>
						<string>org.apache.ctakes.typesystem.type.syntax.PunctuationToken
						</string>
						<string>org.apache.ctakes.typesystem.type.syntax.SymbolToken</string>
						<string>org.apache.ctakes.typesystem.type.textsem.RomanNumeralAnnotation
						</string>
						<string>org.apache.ctakes.typesystem.type.textsem.DateAnnotation</string>
						<string>org.apache.ctakes.typesystem.type.textsem.FractionAnnotation
						</string>
						<string>org.apache.ctakes.typesystem.type.textsem.MeasurementAnnotation
						</string>
						<string>org.apache.ctakes.typesystem.type.textsem.PersonTitleAnnotation
						</string>
						<string>org.apache.ctakes.typesystem.type.textsem.RangeAnnotation
						</string>
						<string>org.apache.ctakes.typesystem.type.textsem.TimeAnnotation</string>
						<string>org.apache.ctakes.typesystem.type.syntax.NP</string>
						<string>org.apache.ctakes.typesystem.type.syntax.VP</string>
					</array>
				</value>
			</nameValuePair>
		</configurationParameterSettings>
		<flowConstraints>
			<fixedFlow>
				<node>AggregatePlaintextUMLSProcessor</node>
				<node>DBConsumer</node>
			</fixedFlow>
		</flowConstraints>
		<operationalProperties>
			<modifiesCas>true</modifiesCas>
			<multipleDeploymentAllowed>true</multipleDeploymentAllowed>
			<outputsNewCASes>false</outputsNewCASes>
		</operationalProperties>
	</analysisEngineMetaData>
	<resourceManagerConfiguration />
</analysisEngineDescription>

Reply via email to