eu.dicodeproject.analysis.lucene.IterableAnalyzer Maven / Gradle / Ivy

Go to download

Show more of this group Show more artifacts with this name
Show all versions of integration Show documentation

The examples module provides glue code implementation for extracting common phrases, key word distributions and more from tweets stored on HDFS/HBase. It builds on Mahout for more sophisticated analysis.

The newest version!

/**
 * Copyright (C) 2010, 2011 Neofonie GmbH
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of 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 eu.dicodeproject.analysis.lucene;

import org.apache.commons.lang.NotImplementedException;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;

import java.io.IOException;
import java.io.StringReader;
import java.util.Iterator;

/**
 * Wraps an analyzer in an iterable for strings.
 */
public class IterableAnalyzer implements Iterable, Iterator {

  private String buffer;
  private TokenStream tokenStream;
  private CharTermAttribute charTermAttribute;

  public IterableAnalyzer(Analyzer analyzer, String text) throws IOException {
    StringReader textReader = new StringReader(text);
    tokenStream = analyzer.tokenStream(null, textReader);
    charTermAttribute = tokenStream.getAttribute(CharTermAttribute.class);
    updateBuffer();
  }

  /**
   * Sets the next token to the string buffer.
   * Sets the buffer to null if the token stream does not contain any more tokens.
   * @throws IOException inherited from TokenStream.incrementToken.
   */
  private void updateBuffer() throws IOException {
    if (tokenStream.incrementToken()) {
      buffer = charTermAttribute.toString();
    }
    else {
      buffer = null;
    }
  }

  @Override
  public boolean hasNext() {
    return buffer != null;
  }

  @Override
  public String next() {
    String oldBuffer = buffer;
    try {
      updateBuffer();
    } catch (IOException e) {
      e.printStackTrace();
    }
    return oldBuffer;
  }

  @Override
  public void remove() {
    throw new NotImplementedException();
  }

  @Override
  public Iterator iterator() {
    return this;
  }
}