blob: 381dbd1f07dd0f2de3a43309b84fe88f2ea1c825 [file] [log] [blame]
<?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="OpenNLPSentenceDetector">
<import location="OpenNLPSentenceDetector.xml"/>
</delegateAnalysisEngine>
<delegateAnalysisEngine key="OpenNLPTokenizer">
<import location="OpenNLPTokenizer.xml"/>
</delegateAnalysisEngine>
</delegateAnalysisEngineSpecifiers>
<analysisEngineMetaData>
<name>OpenNLPTokenAndSentenceAggregate</name>
<description>Aggregate analysis engine that performs sentence detection and tokenization using the OpenNLP sentence detector and tokenizer.</description>
<version>1.0</version>
<vendor>The Apache Software Foundation</vendor>
<configurationParameters searchStrategy="language_fallback">
<configurationParameter>
<name>SentenceDetectorModelFile</name>
<description>Filename of the Sentence Detector model file.</description>
<type>String</type>
<multiValued>false</multiValued>
<mandatory>true</mandatory>
<overrides>
<parameter>OpenNLPSentenceDetector/ModelFile</parameter>
</overrides>
</configurationParameter>
<configurationParameter>
<name>TokenizerModelFile</name>
<description>Filename of the Tokenizer model file.</description>
<type>String</type>
<multiValued>false</multiValued>
<mandatory>true</mandatory>
<overrides>
<parameter>OpenNLPTokenizer/ModelFile</parameter>
</overrides>
</configurationParameter>
</configurationParameters>
<configurationParameterSettings>
<nameValuePair>
<name>SentenceDetectorModelFile</name>
<value>
<string>C:\workspace\OpenNLP Models\sentdetect\EnglishSD.bin.gz</string>
</value>
</nameValuePair>
<nameValuePair>
<name>TokenizerModelFile</name>
<value>
<string>C:\workspace\OpenNLP Models\tokenize\EnglishTok.bin.gz</string>
</value>
</nameValuePair>
</configurationParameterSettings>
<flowConstraints>
<fixedFlow>
<node>OpenNLPSentenceDetector</node>
<node>OpenNLPTokenizer</node>
</fixedFlow>
</flowConstraints>
<capabilities>
<capability>
<inputs/>
<outputs>
<type>org.apache.uima.examples.opennlp.Token</type>
<type>org.apache.uima.examples.opennlp.Sentence</type>
</outputs>
<languagesSupported/>
</capability>
</capabilities>
<operationalProperties>
<modifiesCas>true</modifiesCas>
<multipleDeploymentAllowed>true</multipleDeploymentAllowed>
</operationalProperties>
</analysisEngineMetaData>
<resourceManagerConfiguration/>
</analysisEngineDescription>