Examples with DataSchema org.apache.druid.segment.indexing.DataSchema used on opensource projects

Example 6 with DataSchema

use of org.apache.druid.segment.indexing.DataSchema in project druid by druid-io.

the class BatchDeltaIngestionTest method makeHadoopDruidIndexerConfig.

private HadoopDruidIndexerConfig makeHadoopDruidIndexerConfig(Map<String, Object> inputSpec, File tmpDir, AggregatorFactory[] aggregators) throws Exception {
    HadoopDruidIndexerConfig config = new HadoopDruidIndexerConfig(new HadoopIngestionSpec(new DataSchema("website", MAPPER.convertValue(new StringInputRowParser(new CSVParseSpec(new TimestampSpec("timestamp", "yyyyMMddHH", null), new DimensionsSpec(DimensionsSpec.getDefaultSchemas(ImmutableList.of("host"))), null, ImmutableList.of("timestamp", "host", "host2", "visited_num"), false, 0), null), Map.class), aggregators != null ? aggregators : new AggregatorFactory[] { new LongSumAggregatorFactory("visited_sum", "visited_num"), new HyperUniquesAggregatorFactory("unique_hosts", "host2") }, new UniformGranularitySpec(Granularities.DAY, Granularities.NONE, ImmutableList.of(INTERVAL_FULL)), null, MAPPER), new HadoopIOConfig(inputSpec, null, tmpDir.getCanonicalPath()), new HadoopTuningConfig(tmpDir.getCanonicalPath(), null, null, null, null, null, null, null, null, false, false, false, false, null, false, false, null, null, false, false, null, null, null, null, null)));
    config.setShardSpecs(ImmutableMap.of(INTERVAL_FULL.getStartMillis(), ImmutableList.of(new HadoopyShardSpec(new HashBasedNumberedShardSpec(0, 1, 0, 1, null, HashPartitionFunction.MURMUR3_32_ABS, HadoopDruidIndexerConfig.JSON_MAPPER), 0))));
    config = HadoopDruidIndexerConfig.fromSpec(config.getSchema());
    return config;
}

Example 7 with DataSchema

use of org.apache.druid.segment.indexing.DataSchema in project druid by druid-io.

the class HadoopIngestionSpecUpdateDatasourcePathSpecSegmentsTest method testRunUpdateSegmentListIfDatasourcePathSpecIsUsed.

private HadoopDruidIndexerConfig testRunUpdateSegmentListIfDatasourcePathSpecIsUsed(PathSpec datasourcePathSpec, @Nullable Interval jobInterval) throws Exception {
    HadoopIngestionSpec spec = new HadoopIngestionSpec(new DataSchema("foo", null, new AggregatorFactory[0], new UniformGranularitySpec(Granularities.DAY, null, ImmutableList.of(Intervals.of("2010-01-01/P1D"))), null, jsonMapper), new HadoopIOConfig(jsonMapper.convertValue(datasourcePathSpec, Map.class), null, null), null);
    spec = jsonMapper.readValue(jsonMapper.writeValueAsString(spec), HadoopIngestionSpec.class);
    UsedSegmentsRetriever segmentsRetriever = EasyMock.createMock(UsedSegmentsRetriever.class);
    EasyMock.expect(segmentsRetriever.retrieveUsedSegmentsForIntervals(TEST_DATA_SOURCE, Collections.singletonList(jobInterval != null ? jobInterval.overlap(TEST_DATA_SOURCE_INTERVAL) : null), Segments.ONLY_VISIBLE)).andReturn(ImmutableList.of(SEGMENT));
    EasyMock.expect(segmentsRetriever.retrieveUsedSegmentsForIntervals(TEST_DATA_SOURCE2, Collections.singletonList(jobInterval != null ? jobInterval.overlap(TEST_DATA_SOURCE_INTERVAL2) : null), Segments.ONLY_VISIBLE)).andReturn(ImmutableList.of(SEGMENT2));
    EasyMock.replay(segmentsRetriever);
    HadoopIngestionSpec.updateSegmentListIfDatasourcePathSpecIsUsed(spec, jsonMapper, segmentsRetriever);
    return HadoopDruidIndexerConfig.fromString(jsonMapper.writeValueAsString(spec));
}

Example 8 with DataSchema

use of org.apache.druid.segment.indexing.DataSchema in project druid by druid-io.

the class IndexGeneratorCombinerTest method setUp.

@Before
public void setUp() throws Exception {
    HadoopDruidIndexerConfig config = new HadoopDruidIndexerConfig(new HadoopIngestionSpec(new DataSchema("website", HadoopDruidIndexerConfig.JSON_MAPPER.convertValue(new StringInputRowParser(new TimeAndDimsParseSpec(new TimestampSpec("timestamp", "yyyyMMddHH", null), new DimensionsSpec(DimensionsSpec.getDefaultSchemas(ImmutableList.of("host", "keywords")))), null), Map.class), new AggregatorFactory[] { new LongSumAggregatorFactory("visited_sum", "visited"), new HyperUniquesAggregatorFactory("unique_hosts", "host") }, new UniformGranularitySpec(Granularities.DAY, Granularities.NONE, ImmutableList.of(Intervals.of("2010/2011"))), null, HadoopDruidIndexerConfig.JSON_MAPPER), new HadoopIOConfig(ImmutableMap.of("paths", "/tmp/dummy", "type", "static"), null, "/tmp/dummy"), HadoopTuningConfig.makeDefaultTuningConfig().withWorkingPath("/tmp/work").withVersion("ver")));
    Configuration hadoopConfig = new Configuration();
    hadoopConfig.set(HadoopDruidIndexerConfig.CONFIG_PROPERTY, HadoopDruidIndexerConfig.JSON_MAPPER.writeValueAsString(config));
    Reducer.Context context = EasyMock.createMock(Reducer.Context.class);
    EasyMock.expect(context.getConfiguration()).andReturn(hadoopConfig);
    EasyMock.replay(context);
    aggregators = config.getSchema().getDataSchema().getAggregators();
    combiner = new IndexGeneratorJob.IndexGeneratorCombiner();
    combiner.setup(context);
}

Example 9 with DataSchema

use of org.apache.druid.segment.indexing.DataSchema in project druid by druid-io.

the class StaticPathSpecTest method testAddingPaths.

@Test
public void testAddingPaths() throws Exception {
    Job job = new Job();
    StaticPathSpec pathSpec = new StaticPathSpec("/a/c,/a/b/{c,d}", null);
    DataSchema schema = new DataSchema("ds", null, new AggregatorFactory[0], null, null, jsonMapper);
    HadoopIOConfig io = new HadoopIOConfig(null, null, null);
    pathSpec.addInputPaths(new HadoopDruidIndexerConfig(new HadoopIngestionSpec(schema, io, null)), job);
    String paths = job.getConfiguration().get(MultipleInputs.DIR_FORMATS);
    String formatter = TextInputFormat.class.getName();
    String[] expected = { "/a/c;" + formatter, "/a/b/c;" + formatter, "/a/b/d;" + formatter };
    Assert.assertArrayEquals(expected, paths.split(","));
}

Example 10 with DataSchema

use of org.apache.druid.segment.indexing.DataSchema in project druid by druid-io.

the class GranularityPathSpecTest method testIntervalTrimming.

@Test
public void testIntervalTrimming() throws Exception {
    UserGroupInformation.setLoginUser(UserGroupInformation.createUserForTesting("test", new String[] { "testGroup" }));
    HadoopIngestionSpec spec = new HadoopIngestionSpec(new DataSchema("foo", null, new AggregatorFactory[0], new UniformGranularitySpec(Granularities.DAY, Granularities.ALL, ImmutableList.of(Intervals.of("2015-01-01T11Z/2015-01-02T05Z"))), null, jsonMapper), new HadoopIOConfig(null, null, null), DEFAULT_TUNING_CONFIG);
    granularityPathSpec.setDataGranularity(Granularities.HOUR);
    granularityPathSpec.setPathFormat("yyyy/MM/dd/HH");
    granularityPathSpec.setFilePattern(".*");
    granularityPathSpec.setInputFormat(TextInputFormat.class);
    Job job = Job.getInstance();
    String formatStr = "file:%s/%s;org.apache.hadoop.mapreduce.lib.input.TextInputFormat";
    createFile(testFolder, "test/2015/01/01/00/file1", "test/2015/01/01/10/file2", "test/2015/01/01/18/file3", "test/2015/01/02/00/file1", "test/2015/01/02/03/file2", "test/2015/01/02/05/file3", "test/2015/01/02/07/file4", "test/2015/01/02/09/file5");
    granularityPathSpec.setInputPath(testFolder.getRoot().getPath() + "/test");
    granularityPathSpec.addInputPaths(HadoopDruidIndexerConfig.fromSpec(spec), job);
    String actual = job.getConfiguration().get("mapreduce.input.multipleinputs.dir.formats");
    String expected = Joiner.on(",").join(Lists.newArrayList(StringUtils.format(formatStr, testFolder.getRoot(), "test/2015/01/01/18/file3"), StringUtils.format(formatStr, testFolder.getRoot(), "test/2015/01/02/00/file1"), StringUtils.format(formatStr, testFolder.getRoot(), "test/2015/01/02/03/file2")));
    Assert.assertEquals("Did not find expected input paths", expected, actual);
}