uimaj-2.3.0-incubating/uimaj-tools/src/main/resources/org/apache/uima/tools/components/XmlDetagger.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>true</primitive>
  <annotatorImplementationName>org.apache.uima.tools.components.XmlDetagger</annotatorImplementationName>
	<analysisEngineMetaData>
		<name>XML Detagger</name>
		<description>A multi-sofa annotator that does XML detagging. Reads XML data from
			the input Sofa (named "xmlDocument"); this data can be stored in the CAS as a
			string or array, or it can be a URI to a remote file. The XML is parsed using the JVM's
			default parser, and the plain-text content is written to a new sofa called
			"plainTextDocument". </description>
		<version>1.0</version>
		<vendor>The Apache Software Foundation</vendor>
		<configurationParameters>
			<configurationParameter>
				<name>XmlTagContainingText</name>
				<description>The name of an XML tag that appears in the files. Only text that
					falls within this XML tag will be considered part of the "document" that
					is put into the CAS. If omitted, the entire file will be considered the
					document.</description>
				<type>String</type>
				<multiValued>false</multiValued>
				<mandatory>false</mandatory>
			</configurationParameter>
		</configurationParameters>
		<typeSystemDescription/>
		<capabilities>
			<capability>
				<inputs/>
				<outputs/>
				<inputSofas>
					<sofaName>xmlDocument</sofaName>
				</inputSofas>
				<outputSofas>
					<sofaName>plainTextDocument</sofaName>
				</outputSofas>
				<languagesSupported>
					<language>en</language>
				</languagesSupported>
			</capability>
		</capabilities>
		<operationalProperties>
			<modifiesCas>true</modifiesCas>
			<multipleDeploymentAllowed>true</multipleDeploymentAllowed>
			<outputsNewCASes>false</outputsNewCASes>
		</operationalProperties>
	</analysisEngineMetaData>
</analysisEngineDescription>