Source code

001/*
002 * Licensed to the Apache Software Foundation (ASF) under one
003 * or more contributor license agreements.  See the NOTICE file
004 * distributed with this work for additional information
005 * regarding copyright ownership.  The ASF licenses this file
006 * to you under the Apache License, Version 2.0 (the
007 * "License"); you may not use this file except in compliance
008 * with the License.  You may obtain a copy of the License at
009 *
010 *   http://www.apache.org/licenses/LICENSE-2.0
011 *
012 * Unless required by applicable law or agreed to in writing,
013 * software distributed under the License is distributed on an
014 * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
015 * KIND, either express or implied.  See the License for the
016 * specific language governing permissions and limitations
017 * under the License.
018 */
019package org.apache.reef.examples.group.bgd;
020
021import org.apache.hadoop.io.LongWritable;
022import org.apache.hadoop.io.Text;
023import org.apache.reef.examples.group.bgd.data.Example;
024import org.apache.reef.examples.group.bgd.data.parser.Parser;
025import org.apache.reef.io.data.loading.api.DataSet;
026import org.apache.reef.io.network.util.Pair;
027
028import javax.inject.Inject;
029import java.util.ArrayList;
030import java.util.List;
031import java.util.logging.Level;
032import java.util.logging.Logger;
033
034/**
035 * The list of BGD examples.
036 */
037public class ExampleList {
038
039  private static final Logger LOG = Logger.getLogger(ExampleList.class.getName());
040
041  private final List<Example> examples = new ArrayList<>();
042  private final DataSet<LongWritable, Text> dataSet;
043  private final Parser<String> parser;
044
045  @Inject
046  public ExampleList(final DataSet<LongWritable, Text> dataSet, final Parser<String> parser) {
047    this.dataSet = dataSet;
048    this.parser = parser;
049  }
050
051  /**
052   * @return the examples
053   */
054  public List<Example> getExamples() {
055    if (examples.isEmpty()) {
056      loadData();
057    }
058    return examples;
059  }
060
061  private void loadData() {
062    LOG.info("Loading data");
063    int i = 0;
064    for (final Pair<LongWritable, Text> examplePair : dataSet) {
065      final Example example = parser.parse(examplePair.getSecond().toString());
066      examples.add(example);
067      if (++i % 2000 == 0) {
068        LOG.log(Level.FINE, "Done parsing {0} lines", i);
069      }
070    }
071  }
072}