Examples with TableDataSource org.apache.druid.query.TableDataSource used on opensource projects

Example 1 with TableDataSource

use of org.apache.druid.query.TableDataSource in project druid by druid-io.

the class DataSourcesResource method getServedSegmentsInInterval.

/**
 * Provides serverView for a datasource and Interval which gives details about servers hosting segments for an
 * interval. Used by the realtime tasks to fetch a view of the interval they are interested in.
 */
@GET
@Path("/{dataSourceName}/intervals/{interval}/serverview")
@Produces(MediaType.APPLICATION_JSON)
@ResourceFilters(DatasourceResourceFilter.class)
public Response getServedSegmentsInInterval(@PathParam("dataSourceName") String dataSourceName, @PathParam("interval") String interval, @QueryParam("partial") final boolean partial) {
    TimelineLookup<String, SegmentLoadInfo> timeline = serverInventoryView.getTimeline(new TableDataSource(dataSourceName));
    final Interval theInterval = Intervals.of(interval.replace('_', '/'));
    if (timeline == null) {
        log.debug("No timeline found for datasource[%s]", dataSourceName);
        return Response.ok(new ArrayList<ImmutableSegmentLoadInfo>()).build();
    }
    return Response.ok(prepareServedSegmentsInInterval(timeline, theInterval)).build();
}

Example 2 with TableDataSource

use of org.apache.druid.query.TableDataSource in project druid by druid-io.

the class DefaultRequestLogEventTest method testDefaultRequestLogEventSerde.

@Test
public void testDefaultRequestLogEventSerde() throws Exception {
    RequestLogLine nativeLine = RequestLogLine.forNative(new TimeseriesQuery(new TableDataSource("dummy"), new MultipleIntervalSegmentSpec(ImmutableList.of(Intervals.of("2015-01-01/2015-01-02"))), true, VirtualColumns.EMPTY, null, Granularities.ALL, ImmutableList.of(), ImmutableList.of(), 5, ImmutableMap.of("key", "value")), DateTimes.of(2019, 12, 12, 3, 1), "127.0.0.1", new QueryStats(ImmutableMap.of("query/time", 13L, "query/bytes", 10L, "success", true, "identity", "allowAll")));
    DefaultRequestLogEvent defaultRequestLogEvent = new DefaultRequestLogEvent(ImmutableMap.of("service", "druid-service", "host", "127.0.0.1"), "feed", nativeLine);
    String logEventJson = objectMapper.writeValueAsString(defaultRequestLogEvent);
    String expected = "{\"feed\":\"feed\",\"query\":{\"queryType\":\"timeseries\",\"dataSource\":{\"type\":\"table\",\"name\":\"dummy\"},\"intervals\":{\"type\":\"intervals\",\"intervals\":[\"2015-01-01T00:00:00.000Z/2015-01-02T00:00:00.000Z\"]},\"descending\":true,\"virtualColumns\":[],\"filter\":null,\"granularity\":{\"type\":\"all\"},\"aggregations\":[],\"postAggregations\":[],\"limit\":5,\"context\":{\"key\":\"value\"}},\"host\":\"127.0.0.1\",\"timestamp\":\"2019-12-12T03:01:00.000Z\",\"service\":\"druid-service\",\"sql\":null,\"sqlQueryContext\":{},\"remoteAddr\":\"127.0.0.1\",\"queryStats\":{\"query/time\":13,\"query/bytes\":10,\"success\":true,\"identity\":\"allowAll\"}}";
    Assert.assertEquals(objectMapper.readTree(expected), objectMapper.readTree(logEventJson));
}

Example 3 with TableDataSource

use of org.apache.druid.query.TableDataSource in project druid by druid-io.

the class CalciteQueryTest method testRequireTimeConditionPositive.

@Test
public void testRequireTimeConditionPositive() throws Exception {
    // simple timeseries
    testQuery(PLANNER_CONFIG_REQUIRE_TIME_CONDITION, "SELECT SUM(cnt), gran FROM (\n" + "  SELECT __time as t, floor(__time TO month) AS gran,\n" + "  cnt FROM druid.foo\n" + ") AS x\n" + "WHERE t >= '2000-01-01' and t < '2002-01-01'" + "GROUP BY gran\n" + "ORDER BY gran", CalciteTests.REGULAR_USER_AUTH_RESULT, ImmutableList.of(Druids.newTimeseriesQueryBuilder().dataSource(CalciteTests.DATASOURCE1).intervals(querySegmentSpec(Intervals.of("2000-01-01/2002-01-01"))).granularity(Granularities.MONTH).aggregators(aggregators(new LongSumAggregatorFactory("a0", "cnt"))).context(getTimeseriesContextWithFloorTime(TIMESERIES_CONTEXT_BY_GRAN, "d0")).build()), ImmutableList.of(new Object[] { 3L, timestamp("2000-01-01") }, new Object[] { 3L, timestamp("2001-01-01") }));
    // nested groupby only requires time condition for inner most query
    testQuery(PLANNER_CONFIG_REQUIRE_TIME_CONDITION, "SELECT\n" + "  SUM(cnt),\n" + "  COUNT(*)\n" + "FROM (SELECT dim2, SUM(cnt) AS cnt FROM druid.foo WHERE __time >= '2000-01-01' GROUP BY dim2)", CalciteTests.REGULAR_USER_AUTH_RESULT, ImmutableList.of(GroupByQuery.builder().setDataSource(new QueryDataSource(GroupByQuery.builder().setDataSource(CalciteTests.DATASOURCE1).setInterval(querySegmentSpec(Intervals.utc(DateTimes.of("2000-01-01").getMillis(), JodaUtils.MAX_INSTANT))).setGranularity(Granularities.ALL).setDimensions(dimensions(new DefaultDimensionSpec("dim2", "d0"))).setAggregatorSpecs(aggregators(new LongSumAggregatorFactory("a0", "cnt"))).setContext(QUERY_CONTEXT_DEFAULT).build())).setInterval(querySegmentSpec(Filtration.eternity())).setGranularity(Granularities.ALL).setAggregatorSpecs(aggregators(new LongSumAggregatorFactory("_a0", "a0"), new CountAggregatorFactory("_a1"))).setContext(QUERY_CONTEXT_DEFAULT).build()), NullHandling.replaceWithDefault() ? ImmutableList.of(new Object[] { 6L, 3L }) : ImmutableList.of(new Object[] { 6L, 4L }));
    // Cannot vectorize next test due to extraction dimension spec.
    cannotVectorize();
    // semi-join requires time condition on both left and right query
    testQuery(PLANNER_CONFIG_REQUIRE_TIME_CONDITION, "SELECT COUNT(*) FROM druid.foo\n" + "WHERE __time >= '2000-01-01' AND SUBSTRING(dim2, 1, 1) IN (\n" + "  SELECT SUBSTRING(dim1, 1, 1) FROM druid.foo\n" + "  WHERE dim1 <> '' AND __time >= '2000-01-01'\n" + ")", CalciteTests.REGULAR_USER_AUTH_RESULT, ImmutableList.of(Druids.newTimeseriesQueryBuilder().dataSource(join(new TableDataSource(CalciteTests.DATASOURCE1), new QueryDataSource(GroupByQuery.builder().setDataSource(CalciteTests.DATASOURCE1).setInterval(querySegmentSpec(Intervals.utc(DateTimes.of("2000-01-01").getMillis(), JodaUtils.MAX_INSTANT))).setDimFilter(not(selector("dim1", NullHandling.sqlCompatible() ? "" : null, null))).setGranularity(Granularities.ALL).setDimensions(new ExtractionDimensionSpec("dim1", "d0", ColumnType.STRING, new SubstringDimExtractionFn(0, 1))).setContext(QUERY_CONTEXT_DEFAULT).build()), "j0.", equalsCondition(makeExpression("substring(\"dim2\", 0, 1)"), DruidExpression.ofColumn(ColumnType.STRING, "j0.d0")), JoinType.INNER)).intervals(querySegmentSpec(Intervals.utc(DateTimes.of("2000-01-01").getMillis(), JodaUtils.MAX_INSTANT))).granularity(Granularities.ALL).aggregators(aggregators(new CountAggregatorFactory("a0"))).context(QUERY_CONTEXT_DEFAULT).build()), ImmutableList.of(new Object[] { 3L }));
}

Example 4 with TableDataSource

use of org.apache.druid.query.TableDataSource in project druid by druid-io.

the class CalciteQueryTest method testSelfJoin.

@Test
public void testSelfJoin() throws Exception {
    // Cannot vectorize due to virtual columns.
    cannotVectorize();
    testQuery("SELECT COUNT(*) FROM druid.foo x, druid.foo y\n", ImmutableList.of(Druids.newTimeseriesQueryBuilder().dataSource(join(new TableDataSource(CalciteTests.DATASOURCE1), new QueryDataSource(newScanQueryBuilder().dataSource(CalciteTests.DATASOURCE1).intervals(querySegmentSpec(Filtration.eternity())).columns(ImmutableList.of("__time", "cnt", "dim1", "dim2", "dim3", "m1", "m2", "unique_dim1")).resultFormat(ScanQuery.ResultFormat.RESULT_FORMAT_COMPACTED_LIST).context(QUERY_CONTEXT_DEFAULT).build()), "j0.", "1", JoinType.INNER)).intervals(querySegmentSpec(Filtration.eternity())).granularity(Granularities.ALL).aggregators(aggregators(new CountAggregatorFactory("a0"))).context(QUERY_CONTEXT_DEFAULT).build()), ImmutableList.of(new Object[] { 36L }));
}

Example 5 with TableDataSource

use of org.apache.druid.query.TableDataSource in project druid by druid-io.

the class CalciteQueryTest method testViewAndJoin.

@Test
public void testViewAndJoin() throws Exception {
    cannotVectorize();
    Map<String, Object> queryContext = withLeftDirectAccessEnabled(QUERY_CONTEXT_DEFAULT);
    testQuery("SELECT COUNT(*) FROM view.cview as a INNER JOIN druid.foo d on d.dim2 = a.dim2 WHERE a.dim1_firstchar <> 'z' ", queryContext, ImmutableList.of(Druids.newTimeseriesQueryBuilder().dataSource(join(join(new TableDataSource(CalciteTests.DATASOURCE1), new QueryDataSource(newScanQueryBuilder().dataSource(CalciteTests.DATASOURCE3).intervals(querySegmentSpec(Filtration.eternity())).columns("dim2").context(queryContext).build()), "j0.", "(\"dim2\" == \"j0.dim2\")", JoinType.INNER, bound("dim2", "a", "a", false, false, null, null)), new QueryDataSource(newScanQueryBuilder().dataSource(CalciteTests.DATASOURCE1).intervals(querySegmentSpec(Filtration.eternity())).columns("dim2").context(queryContext).build()), "_j0.", "('a' == \"_j0.dim2\")", JoinType.INNER)).intervals(querySegmentSpec(Filtration.eternity())).filters(not(selector("dim1", "z", new SubstringDimExtractionFn(0, 1)))).granularity(Granularities.ALL).aggregators(aggregators(new CountAggregatorFactory("a0"))).context(withLeftDirectAccessEnabled(QUERY_CONTEXT_DEFAULT)).build()), ImmutableList.of(new Object[] { 8L }));
}