Package opennlp.tools.tokenize

Source Code of opennlp.tools.tokenize.DetokenizationDictionary

/*
* 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.
*/

package opennlp.tools.tokenize;

import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import java.util.HashMap;
import java.util.Iterator;
import java.util.Map;

import opennlp.tools.dictionary.serializer.Attributes;
import opennlp.tools.dictionary.serializer.DictionarySerializer;
import opennlp.tools.dictionary.serializer.Entry;
import opennlp.tools.dictionary.serializer.EntryInserter;
import opennlp.tools.util.InvalidFormatException;
import opennlp.tools.util.StringList;

public class DetokenizationDictionary {
 
  public static enum Operation {
   
    /**
     * Attaches the token to the token on the right side.
     */
    MOVE_RIGHT,
   
    /**
     * Attaches the token to the token on the left side.
     */
    MOVE_LEFT,
   
    /**
     * Attaches the token token to the right token on first occurrence, and
     * to the token on the left side on the second occurrence.
     */
    RIGHT_LEFT_MATCHING;
   
    public static Operation parse(String operation) {
     
      if (MOVE_RIGHT.toString().equals(operation)) {
        return MOVE_RIGHT;
      }
      else if (MOVE_LEFT.toString().equals(operation)) {
        return MOVE_LEFT;
      }
      else if (RIGHT_LEFT_MATCHING.toString().equals(operation)) {
        return RIGHT_LEFT_MATCHING;
      }
      else {
        return null;
      }
    }
  }
 
  private final Map<String, DetokenizationDictionary.Operation> operationTable =
      new HashMap<String, DetokenizationDictionary.Operation>();
  /**
   * Initializes the current instance.
   *
   * @param tokens
   * @param operations
   */
  public DetokenizationDictionary(String tokens[],
      DetokenizationDictionary.Operation operations[]) {
    if (tokens.length != operations.length)
      throw new IllegalArgumentException("tokens and ops must have the same length!");
   
    for (int i = 0; i < tokens.length; i++) {
      String token = tokens[i];
      DetokenizationDictionary.Operation operation = operations[i];
     
      if (token == null)
        throw new IllegalArgumentException("token at index " + i + " must not be null!");
     
      if (operation == null)
        throw new IllegalArgumentException("operation at index " + i + " must not be null!");
     
      operationTable.put(token, operation);
    }
  }
 
  public DetokenizationDictionary(InputStream in) throws IOException, InvalidFormatException{
   
    DictionarySerializer.create(in, new EntryInserter() {
      public void insert(Entry entry) throws InvalidFormatException {

        String operationString = entry.getAttributes().getValue("operation");

        StringList word = entry.getTokens();

        if (word.size() != 1)
          throw new InvalidFormatException("Each entry must have exactly one token! "+word);
       
        // parse operation
        Operation operation = Operation.parse(operationString);
       
        if (operation == null)
            throw new InvalidFormatException("Unkown operation type: " + operationString);
       
        operationTable.put(word.getToken(0), operation);
      }});
  }
 
  DetokenizationDictionary.Operation getOperation(String token) {
    return operationTable.get(token);
  }
 
  // serialize method
  public void serialize(OutputStream out) throws IOException {
    Iterator<Entry> entries = new Iterator<Entry>() {

      Iterator<String> iterator = operationTable.keySet().iterator();

      public boolean hasNext() {
        return iterator.hasNext();
      }

      public Entry next() {

        String token = iterator.next();

        Attributes attributes = new Attributes();
        attributes.setValue("operation", getOperation(token).toString());

        return new Entry(new StringList(token), attributes);
      }

      public void remove() {
        throw new UnsupportedOperationException();
      }
    };
   
    DictionarySerializer.serialize(out, entries, false);
  }
}
TOP

Related Classes of opennlp.tools.tokenize.DetokenizationDictionary

TOP
Copyright © 2018 www.massapi.com. All rights reserved.
All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.