use of org.apache.druid.query.dimension.ExtractionDimensionSpec in project druid by druid-io.
the class GroupByLimitPushDownMultiNodeMergeTest method testPartialLimitPushDownMerge.
@Test
public void testPartialLimitPushDownMerge() {
// one segment's results use limit push down, the other doesn't because of insufficient buffer capacity
QueryToolChest<ResultRow, GroupByQuery> toolChest = groupByFactory.getToolchest();
QueryRunner<ResultRow> theRunner = new FinalizeResultsQueryRunner<>(toolChest.mergeResults(groupByFactory.mergeRunners(executorService, getRunner1(0))), (QueryToolChest) toolChest);
QueryRunner<ResultRow> theRunner2 = new FinalizeResultsQueryRunner<>(toolChest.mergeResults(groupByFactory2.mergeRunners(executorService, getRunner2(1))), (QueryToolChest) toolChest);
QueryRunner<ResultRow> finalRunner = new FinalizeResultsQueryRunner<>(toolChest.mergeResults(new QueryRunner<ResultRow>() {
@Override
public Sequence<ResultRow> run(QueryPlus<ResultRow> queryPlus, ResponseContext responseContext) {
return Sequences.simple(ImmutableList.of(theRunner.run(queryPlus, responseContext), theRunner2.run(queryPlus, responseContext))).flatMerge(Function.identity(), queryPlus.getQuery().getResultOrdering());
}
}), (QueryToolChest) toolChest);
QuerySegmentSpec intervalSpec = new MultipleIntervalSegmentSpec(Collections.singletonList(Intervals.utc(1500000000000L, 1600000000000L)));
GroupByQuery query = GroupByQuery.builder().setDataSource("blah").setQuerySegmentSpec(intervalSpec).setDimensions(new DefaultDimensionSpec("dimA", "dimA"), new ExtractionDimensionSpec(ColumnHolder.TIME_COLUMN_NAME, "hour", ColumnType.LONG, new TimeFormatExtractionFn(null, null, null, new PeriodGranularity(new Period("PT1H"), null, DateTimeZone.UTC), true))).setAggregatorSpecs(new LongSumAggregatorFactory("metASum", "metA")).setLimitSpec(new DefaultLimitSpec(Arrays.asList(new OrderByColumnSpec("hour", OrderByColumnSpec.Direction.ASCENDING, StringComparators.NUMERIC), new OrderByColumnSpec("dimA", OrderByColumnSpec.Direction.ASCENDING)), 1000)).setContext(ImmutableMap.of(GroupByQueryConfig.CTX_KEY_APPLY_LIMIT_PUSH_DOWN, true)).setGranularity(Granularities.ALL).build();
Sequence<ResultRow> queryResult = finalRunner.run(QueryPlus.wrap(query), ResponseContext.createEmpty());
List<ResultRow> results = queryResult.toList();
ResultRow expectedRow0 = GroupByQueryRunnerTestHelper.createExpectedRow(query, "2017-07-14T02:40:00.000Z", "dimA", "mango", "hour", 1505260800000L, "metASum", 26L);
ResultRow expectedRow1 = GroupByQueryRunnerTestHelper.createExpectedRow(query, "2017-07-14T02:40:00.000Z", "dimA", "pomegranate", "hour", 1505260800000L, "metASum", 7113L);
ResultRow expectedRow2 = GroupByQueryRunnerTestHelper.createExpectedRow(query, "2017-07-14T02:40:00.000Z", "dimA", "mango", "hour", 1505264400000L, "metASum", 10L);
ResultRow expectedRow3 = GroupByQueryRunnerTestHelper.createExpectedRow(query, "2017-07-14T02:40:00.000Z", "dimA", "pomegranate", "hour", 1505264400000L, "metASum", 7726L);
Assert.assertEquals(4, results.size());
Assert.assertEquals(expectedRow0, results.get(0));
Assert.assertEquals(expectedRow1, results.get(1));
Assert.assertEquals(expectedRow2, results.get(2));
Assert.assertEquals(expectedRow3, results.get(3));
}
use of org.apache.druid.query.dimension.ExtractionDimensionSpec in project druid by druid-io.
the class TopNQueryRunnerTest method testTopNLexicographicDimExtractionUnOptimalNamespace.
@Test
public void testTopNLexicographicDimExtractionUnOptimalNamespace() {
TopNQuery query = new TopNQueryBuilder().dataSource(QueryRunnerTestHelper.DATA_SOURCE).granularity(QueryRunnerTestHelper.ALL_GRAN).dimension(new ExtractionDimensionSpec(QueryRunnerTestHelper.MARKET_DIMENSION, QueryRunnerTestHelper.MARKET_DIMENSION, new LookupExtractionFn(new MapLookupExtractor(ImmutableMap.of("spot", "2spot", "total_market", "3total_market", "upfront", "1upfront"), false), true, null, false, false))).metric(new DimensionTopNMetricSpec(null, StringComparators.LEXICOGRAPHIC)).threshold(4).intervals(QueryRunnerTestHelper.FIRST_TO_THIRD).aggregators(commonAggregators).postAggregators(QueryRunnerTestHelper.ADD_ROWS_INDEX_CONSTANT).build();
List<Result<TopNResultValue>> expectedResults = Collections.singletonList(new Result<>(DateTimes.of("2011-04-01T00:00:00.000Z"), new TopNResultValue(Arrays.<Map<String, Object>>asList(ImmutableMap.of(QueryRunnerTestHelper.MARKET_DIMENSION, "1upfront", "rows", 4L, "index", 4875.669692D, "addRowsIndexConstant", 4880.669692D, "uniques", QueryRunnerTestHelper.UNIQUES_2), ImmutableMap.of(QueryRunnerTestHelper.MARKET_DIMENSION, "2spot", "rows", 18L, "index", 2231.876812D, "addRowsIndexConstant", 2250.876812D, "uniques", QueryRunnerTestHelper.UNIQUES_9), ImmutableMap.of(QueryRunnerTestHelper.MARKET_DIMENSION, "3total_market", "rows", 4L, "index", 5351.814783D, "addRowsIndexConstant", 5356.814783D, "uniques", QueryRunnerTestHelper.UNIQUES_2)))));
assertExpectedResults(expectedResults, query);
}
use of org.apache.druid.query.dimension.ExtractionDimensionSpec in project druid by druid-io.
the class TopNQueryRunnerTest method testTopNDimExtractionFastTopNUnOptimal.
@Test
public // Test query path that must rebucket the data
void testTopNDimExtractionFastTopNUnOptimal() {
TopNQuery query = new TopNQueryBuilder().dataSource(QueryRunnerTestHelper.DATA_SOURCE).granularity(QueryRunnerTestHelper.ALL_GRAN).dimension(new ExtractionDimensionSpec(QueryRunnerTestHelper.MARKET_DIMENSION, QueryRunnerTestHelper.MARKET_DIMENSION, new LookupExtractionFn(new MapLookupExtractor(ImmutableMap.of("spot", "spot0", "total_market", "total_market0", "upfront", "upfront0"), false), true, null, false, false))).metric("rows").threshold(4).intervals(QueryRunnerTestHelper.FIRST_TO_THIRD).aggregators(commonAggregators).postAggregators(QueryRunnerTestHelper.ADD_ROWS_INDEX_CONSTANT).build();
List<Result<TopNResultValue>> expectedResults = Collections.singletonList(new Result<>(DateTimes.of("2011-04-01T00:00:00.000Z"), new TopNResultValue(Arrays.<Map<String, Object>>asList(ImmutableMap.of(QueryRunnerTestHelper.MARKET_DIMENSION, "spot0", "rows", 18L, "index", 2231.876812D, "addRowsIndexConstant", 2250.876812D, "uniques", QueryRunnerTestHelper.UNIQUES_9), ImmutableMap.of(QueryRunnerTestHelper.MARKET_DIMENSION, "total_market0", "rows", 4L, "index", 5351.814783D, "addRowsIndexConstant", 5356.814783D, "uniques", QueryRunnerTestHelper.UNIQUES_2), ImmutableMap.of(QueryRunnerTestHelper.MARKET_DIMENSION, "upfront0", "rows", 4L, "index", 4875.669692D, "addRowsIndexConstant", 4880.669692D, "uniques", QueryRunnerTestHelper.UNIQUES_2)))));
assertExpectedResults(expectedResults, query);
}
use of org.apache.druid.query.dimension.ExtractionDimensionSpec in project druid by druid-io.
the class TopNQueryRunnerTest method testTopNDimExtraction.
@Test
public void testTopNDimExtraction() {
TopNQuery query = new TopNQueryBuilder().dataSource(QueryRunnerTestHelper.DATA_SOURCE).granularity(QueryRunnerTestHelper.ALL_GRAN).dimension(new ExtractionDimensionSpec(QueryRunnerTestHelper.MARKET_DIMENSION, QueryRunnerTestHelper.MARKET_DIMENSION, new RegexDimExtractionFn("(.)", false, null))).metric("rows").threshold(4).intervals(QueryRunnerTestHelper.FIRST_TO_THIRD).aggregators(commonAggregators).postAggregators(QueryRunnerTestHelper.ADD_ROWS_INDEX_CONSTANT).build();
List<Result<TopNResultValue>> expectedResults = Collections.singletonList(new Result<>(DateTimes.of("2011-04-01T00:00:00.000Z"), new TopNResultValue(Arrays.<Map<String, Object>>asList(ImmutableMap.of(QueryRunnerTestHelper.MARKET_DIMENSION, "s", "rows", 18L, "index", 2231.876812D, "addRowsIndexConstant", 2250.876812D, "uniques", QueryRunnerTestHelper.UNIQUES_9), ImmutableMap.of(QueryRunnerTestHelper.MARKET_DIMENSION, "t", "rows", 4L, "index", 5351.814783D, "addRowsIndexConstant", 5356.814783D, "uniques", QueryRunnerTestHelper.UNIQUES_2), ImmutableMap.of(QueryRunnerTestHelper.MARKET_DIMENSION, "u", "rows", 4L, "index", 4875.669692D, "addRowsIndexConstant", 4880.669692D, "uniques", QueryRunnerTestHelper.UNIQUES_2)))));
assertExpectedResults(expectedResults, query);
}
use of org.apache.druid.query.dimension.ExtractionDimensionSpec in project druid by druid-io.
the class TopNQueryRunnerTest method testFullOnTopNDimExtractionAllNulls.
@Test
public void testFullOnTopNDimExtractionAllNulls() {
String jsFn = "function(str) { return null; }";
ExtractionFn jsExtractionFn = new JavaScriptExtractionFn(jsFn, false, JavaScriptConfig.getEnabledInstance());
TopNQuery query = new TopNQueryBuilder().dataSource(QueryRunnerTestHelper.DATA_SOURCE).granularity(QueryRunnerTestHelper.ALL_GRAN).dimension(new ExtractionDimensionSpec(QueryRunnerTestHelper.MARKET_DIMENSION, QueryRunnerTestHelper.MARKET_DIMENSION, jsExtractionFn)).metric(QueryRunnerTestHelper.INDEX_METRIC).threshold(4).intervals(QueryRunnerTestHelper.FULL_ON_INTERVAL_SPEC).aggregators(Lists.newArrayList(Iterables.concat(commonAggregators, Lists.newArrayList(new DoubleMaxAggregatorFactory("maxIndex", "index"), new DoubleMinAggregatorFactory("minIndex", "index"))))).postAggregators(QueryRunnerTestHelper.ADD_ROWS_INDEX_CONSTANT).build();
Map<String, Object> expectedMap = new HashMap<>();
expectedMap.put(QueryRunnerTestHelper.MARKET_DIMENSION, null);
expectedMap.put("rows", 1209L);
expectedMap.put("index", 503332.5071372986D);
expectedMap.put("addRowsIndexConstant", 504542.5071372986D);
expectedMap.put("uniques", 9.019833517963864);
expectedMap.put("maxIndex", 1870.061029D);
expectedMap.put("minIndex", 59.02102279663086D);
List<Result<TopNResultValue>> expectedResults = Collections.singletonList(new Result<>(DateTimes.of("2011-01-12T00:00:00.000Z"), new TopNResultValue(Collections.singletonList(expectedMap))));
assertExpectedResults(expectedResults, query);
}
Aggregations