opennlp.uima.tokenize.WhitespaceTokenizer Maven / Gradle / Ivy

/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreemnets.  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.
 */

package opennlp.uima.tokenize;

import opennlp.tools.util.Span;

import org.apache.uima.UimaContext;
import org.apache.uima.cas.CAS;
import org.apache.uima.cas.text.AnnotationFS;

/**
 * OpenNLP Whitespace Tokenizer annotator.
 * 
 * Mandatory parameters
 * 
 *   
 *   
 *   
 * Type  Name  Description
String  opennlp.uima.SentenceType  The full name of the sentence type
String  opennlp.uima.TokenType  The full name of the token type
 */
public final class WhitespaceTokenizer extends AbstractTokenizer {
  
  /**
   * Initializes the current instance.
   *
   * Note: Use {@link #initialize(UimaContext) } to initialize 
   * this instance. Not use the constructor.
   */
  public WhitespaceTokenizer() {
      super("OpenNLP Whitespace Tokenizer");
    // must not be implemented !
  }
  
  @Override
  protected Span[] tokenize(CAS cas, AnnotationFS sentence) {
    return opennlp.tools.tokenize.WhitespaceTokenizer.INSTANCE.
        tokenizePos(sentence.getCoveredText());
  }
}

Type	Name	Description
String	opennlp.uima.SentenceType	The full name of the sentence type
String	opennlp.uima.TokenType	The full name of the token type