io.druid.indexer.path.GranularUnprocessedPathSpec.java Source code

Introduction

Here is the source code for io.druid.indexer.path.GranularUnprocessedPathSpec.java

Source

/*
 * Druid - a distributed column store.
 * Copyright 2012 - 2015 Metamarkets Group Inc.
 *
 * Licensed 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 io.druid.indexer.path;

import com.fasterxml.jackson.annotation.JsonProperty;
import com.google.common.base.Preconditions;
import com.google.common.collect.Lists;
import com.google.common.collect.Sets;
import com.metamx.common.Granularity;
import com.metamx.common.guava.Comparators;
import io.druid.indexer.HadoopDruidIndexerConfig;
import io.druid.indexer.hadoop.FSSpideringIterator;
import io.druid.segment.indexing.granularity.UniformGranularitySpec;
import org.apache.hadoop.fs.FileStatus;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.mapreduce.Job;
import org.joda.time.DateTime;
import org.joda.time.Interval;

import java.io.IOException;
import java.util.Map;
import java.util.Set;
import java.util.TreeMap;

/**
 */
public class GranularUnprocessedPathSpec extends GranularityPathSpec {
    private int maxBuckets;

    @JsonProperty
    public int getMaxBuckets() {
        return maxBuckets;
    }

    public void setMaxBuckets(int maxBuckets) {
        this.maxBuckets = maxBuckets;
    }

    @Override
    public Job addInputPaths(HadoopDruidIndexerConfig config, Job job) throws IOException {
        // This PathSpec breaks so many abstractions that we might as break some more
        Preconditions.checkState(config.getGranularitySpec() instanceof UniformGranularitySpec,
                String.format("Cannot use %s without %s", GranularUnprocessedPathSpec.class.getSimpleName(),
                        UniformGranularitySpec.class.getSimpleName()));

        final Path betaInput = new Path(getInputPath());
        final FileSystem fs = betaInput.getFileSystem(job.getConfiguration());
        final Granularity segmentGranularity = config.getGranularitySpec().getSegmentGranularity();

        Map<DateTime, Long> inputModifiedTimes = new TreeMap<>(Comparators.inverse(Comparators.comparable()));

        for (FileStatus status : FSSpideringIterator.spiderIterable(fs, betaInput)) {
            final DateTime key = segmentGranularity.toDate(status.getPath().toString());
            final Long currVal = inputModifiedTimes.get(key);
            final long mTime = status.getModificationTime();

            inputModifiedTimes.put(key, currVal == null ? mTime : Math.max(currVal, mTime));
        }

        Set<Interval> bucketsToRun = Sets.newTreeSet(Comparators.intervals());
        for (Map.Entry<DateTime, Long> entry : inputModifiedTimes.entrySet()) {
            DateTime timeBucket = entry.getKey();
            long mTime = entry.getValue();

            String bucketOutput = String.format("%s/%s", config.getSchema().getIOConfig().getSegmentOutputPath(),
                    segmentGranularity.toPath(timeBucket));
            for (FileStatus fileStatus : FSSpideringIterator.spiderIterable(fs, new Path(bucketOutput))) {
                if (fileStatus.getModificationTime() > mTime) {
                    bucketsToRun.add(new Interval(timeBucket, segmentGranularity.increment(timeBucket)));
                    break;
                }
            }

            if (bucketsToRun.size() >= maxBuckets) {
                break;
            }
        }

        config.setGranularitySpec(new UniformGranularitySpec(segmentGranularity,
                config.getGranularitySpec().getQueryGranularity(), Lists.newArrayList(bucketsToRun)));

        return super.addInputPaths(config, job);
    }
}