uimaj-2.2.1-incubating/uimaj-examples/src/main/opennlp_wrappers/descriptors/OpenNLPTokenizer.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.examples.opennlp.annotator.Tokenizer</annotatorImplementationName>
  <analysisEngineMetaData>
    <name>OpenNLPTokenizer</name>
    <description>Tokenize the text and create token annotations that span the tokens.  The tokenization is performed using the  OpenNLP MaxEnt tokenizer, which tokenizes according to the  Penn Tree Bank tokenization standard.  In general, tokens are separated by white space, but punctuation marks (e.g., ".", ",", "!", "?", etc.) and apostrophed endings (e.g., "'s", "'nt", etc.) are separate tokens.</description>
    <version>1.0</version>
    <vendor>The Apache Software Foundation</vendor>
    <configurationParameters>
      <configurationParameter>
        <name>ModelFile</name>
        <description>OpenNLP MaxEnt model file for the tokenizer.</description>
        <type>String</type>
        <multiValued>false</multiValued>
        <mandatory>true</mandatory>
      </configurationParameter>
    </configurationParameters>
    <configurationParameterSettings>
      <nameValuePair>
        <name>ModelFile</name>
        <value>
          <string>C:\opennlp-models-1.3.0\english\tokenize\EnglishTok.bin.gz</string>
        </value>
      </nameValuePair>
    </configurationParameterSettings>
    <typeSystemDescription>
      <imports>
        <import name="org.apache.uima.examples.opennlp.OpenNLPExampleTypes"/>
      </imports>
    </typeSystemDescription>
    <capabilities>
      <capability>
        <inputs>
          <type>org.opennlp.Sentence</type>
        </inputs>
        <outputs>
          <type>org.opennlp.Token</type>
        </outputs>
        <languagesSupported/>
      </capability>
    </capabilities>
    <operationalProperties>
      <modifiesCas>true</modifiesCas>
      <multipleDeploymentAllowed>true</multipleDeploymentAllowed>
    </operationalProperties>
  </analysisEngineMetaData>
  <resourceManagerConfiguration/>
</analysisEngineDescription>