Examples with TimeseriesQuery org.apache.druid.query.timeseries.TimeseriesQuery used on opensource projects

Example 51 with TimeseriesQuery

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

the class MaterializedViewUtilsTest method testGetRequiredFieldsFromTimeseriesQuery.

@Test
public void testGetRequiredFieldsFromTimeseriesQuery() throws Exception {
    String queryStr = "{\n" + "  \"queryType\": \"timeseries\",\n" + "  \"dataSource\": \"sample_datasource\",\n" + "  \"granularity\": \"day\",\n" + "  \"descending\": \"true\",\n" + "  \"filter\": {\n" + "    \"type\": \"and\",\n" + "    \"fields\": [\n" + "      { \"type\": \"selector\", \"dimension\": \"sample_dimension1\", \"value\": \"sample_value1\" },\n" + "      { \"type\": \"or\",\n" + "        \"fields\": [\n" + "          { \"type\": \"selector\", \"dimension\": \"sample_dimension2\", \"value\": \"sample_value2\" },\n" + "          { \"type\": \"selector\", \"dimension\": \"sample_dimension3\", \"value\": \"sample_value3\" }\n" + "        ]\n" + "      }\n" + "    ]\n" + "  },\n" + "  \"aggregations\": [\n" + "    { \"type\": \"longSum\", \"name\": \"sample_name1\", \"fieldName\": \"sample_fieldName1\" },\n" + "    { \"type\": \"doubleSum\", \"name\": \"sample_name2\", \"fieldName\": \"sample_fieldName2\" }\n" + "  ],\n" + "  \"postAggregations\": [\n" + "    { \"type\": \"arithmetic\",\n" + "      \"name\": \"sample_divide\",\n" + "      \"fn\": \"/\",\n" + "      \"fields\": [\n" + "        { \"type\": \"fieldAccess\", \"name\": \"postAgg__sample_name1\", \"fieldName\": \"sample_name1\" },\n" + "        { \"type\": \"fieldAccess\", \"name\": \"postAgg__sample_name2\", \"fieldName\": \"sample_name2\" }\n" + "      ]\n" + "    }\n" + "  ],\n" + "  \"intervals\": [ \"2012-01-01T00:00:00.000/2012-01-03T00:00:00.000\" ]\n" + "}";
    TimeseriesQuery query = jsonMapper.readValue(queryStr, TimeseriesQuery.class);
    Set<String> fields = MaterializedViewUtils.getRequiredFields(query);
    Assert.assertEquals(Sets.newHashSet("sample_dimension1", "sample_dimension2", "sample_dimension3", "sample_fieldName1", "sample_fieldName2"), fields);
}

Example 52 with TimeseriesQuery

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

the class MomentSketchAggregatorFactoryTest method testResultArraySignature.

@Test
public void testResultArraySignature() {
    final TimeseriesQuery query = Druids.newTimeseriesQueryBuilder().dataSource("dummy").intervals("2000/3000").granularity(Granularities.HOUR).aggregators(new CountAggregatorFactory("count"), new MomentSketchAggregatorFactory("moment", "col", null, null), new MomentSketchMergeAggregatorFactory("momentMerge", null, null)).postAggregators(new FieldAccessPostAggregator("moment-access", "moment"), new FinalizingFieldAccessPostAggregator("moment-finalize", "moment"), new FieldAccessPostAggregator("momentMerge-access", "momentMerge"), new FinalizingFieldAccessPostAggregator("momentMerge-finalize", "momentMerge")).build();
    Assert.assertEquals(RowSignature.builder().addTimeColumn().add("count", ColumnType.LONG).add("moment", MomentSketchAggregatorFactory.TYPE).add("momentMerge", MomentSketchAggregatorFactory.TYPE).add("moment-access", MomentSketchAggregatorFactory.TYPE).add("moment-finalize", MomentSketchAggregatorFactory.TYPE).add("momentMerge-access", MomentSketchAggregatorFactory.TYPE).add("momentMerge-finalize", MomentSketchAggregatorFactory.TYPE).build(), new TimeseriesQueryQueryToolChest().resultArraySignature(query));
}

Example 53 with TimeseriesQuery

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

the class MovingAverageQueryRunner method run.

@Override
public Sequence<Row> run(QueryPlus<Row> query, ResponseContext responseContext) {
    MovingAverageQuery maq = (MovingAverageQuery) query.getQuery();
    List<Interval> intervals;
    final Period period;
    // Get the largest bucket from the list of averagers
    Optional<Integer> opt = maq.getAveragerSpecs().stream().map(AveragerFactory::getNumBuckets).max(Integer::compare);
    int buckets = opt.orElse(0);
    // Extend the interval beginning by specified bucket - 1
    if (maq.getGranularity() instanceof PeriodGranularity) {
        period = ((PeriodGranularity) maq.getGranularity()).getPeriod();
        int offset = buckets <= 0 ? 0 : (1 - buckets);
        intervals = maq.getIntervals().stream().map(i -> new Interval(i.getStart().withPeriodAdded(period, offset), i.getEnd())).collect(Collectors.toList());
    } else {
        throw new ISE("Only PeriodGranulaity is supported for movingAverage queries");
    }
    Sequence<Row> resultsSeq;
    DataSource dataSource = maq.getDataSource();
    if (maq.getDimensions() != null && !maq.getDimensions().isEmpty() && (dataSource instanceof TableDataSource || dataSource instanceof UnionDataSource || dataSource instanceof QueryDataSource)) {
        // build groupBy query from movingAverage query
        GroupByQuery.Builder builder = GroupByQuery.builder().setDataSource(dataSource).setInterval(intervals).setDimFilter(maq.getFilter()).setGranularity(maq.getGranularity()).setDimensions(maq.getDimensions()).setAggregatorSpecs(maq.getAggregatorSpecs()).setPostAggregatorSpecs(maq.getPostAggregatorSpecs()).setContext(maq.getContext());
        GroupByQuery gbq = builder.build();
        ResponseContext gbqResponseContext = ResponseContext.createEmpty();
        gbqResponseContext.merge(responseContext);
        gbqResponseContext.putQueryFailDeadlineMs(System.currentTimeMillis() + QueryContexts.getTimeout(gbq));
        Sequence<ResultRow> results = gbq.getRunner(walker).run(QueryPlus.wrap(gbq), gbqResponseContext);
        try {
            // use localhost for remote address
            requestLogger.logNativeQuery(RequestLogLine.forNative(gbq, DateTimes.nowUtc(), "127.0.0.1", new QueryStats(ImmutableMap.of("query/time", 0, "query/bytes", 0, "success", true))));
        } catch (Exception e) {
            throw Throwables.propagate(e);
        }
        resultsSeq = results.map(row -> row.toMapBasedRow(gbq));
    } else {
        // no dimensions, so optimize this as a TimeSeries
        TimeseriesQuery tsq = new TimeseriesQuery(dataSource, new MultipleIntervalSegmentSpec(intervals), false, null, maq.getFilter(), maq.getGranularity(), maq.getAggregatorSpecs(), maq.getPostAggregatorSpecs(), 0, maq.getContext());
        ResponseContext tsqResponseContext = ResponseContext.createEmpty();
        tsqResponseContext.merge(responseContext);
        tsqResponseContext.putQueryFailDeadlineMs(System.currentTimeMillis() + QueryContexts.getTimeout(tsq));
        Sequence<Result<TimeseriesResultValue>> results = tsq.getRunner(walker).run(QueryPlus.wrap(tsq), tsqResponseContext);
        try {
            // use localhost for remote address
            requestLogger.logNativeQuery(RequestLogLine.forNative(tsq, DateTimes.nowUtc(), "127.0.0.1", new QueryStats(ImmutableMap.of("query/time", 0, "query/bytes", 0, "success", true))));
        } catch (Exception e) {
            throw Throwables.propagate(e);
        }
        resultsSeq = Sequences.map(results, new TimeseriesResultToRow());
    }
    // Process into period buckets
    Sequence<RowBucket> bucketedMovingAvgResults = Sequences.simple(new RowBucketIterable(resultsSeq, intervals, period));
    // Apply the windows analysis functions
    Sequence<Row> movingAvgResults = Sequences.simple(new MovingAverageIterable(bucketedMovingAvgResults, maq.getDimensions(), maq.getAveragerSpecs(), maq.getPostAggregatorSpecs(), maq.getAggregatorSpecs()));
    // Apply any postAveragers
    Sequence<Row> movingAvgResultsWithPostAveragers = Sequences.map(movingAvgResults, new PostAveragerAggregatorCalculator(maq));
    // remove rows outside the reporting window
    List<Interval> reportingIntervals = maq.getIntervals();
    movingAvgResults = Sequences.filter(movingAvgResultsWithPostAveragers, row -> reportingIntervals.stream().anyMatch(i -> i.contains(row.getTimestamp())));
    // Apply any having, sorting, and limits
    movingAvgResults = maq.applyLimit(movingAvgResults);
    return movingAvgResults;
}

Example 54 with TimeseriesQuery

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

the class TDigestSketchAggregatorFactoryTest method testResultArraySignature.

@Test
public void testResultArraySignature() {
    final TimeseriesQuery query = Druids.newTimeseriesQueryBuilder().dataSource("dummy").intervals("2000/3000").granularity(Granularities.HOUR).aggregators(new CountAggregatorFactory("count"), new TDigestSketchAggregatorFactory("tdigest", "col", null)).postAggregators(new FieldAccessPostAggregator("tdigest-access", "tdigest"), new FinalizingFieldAccessPostAggregator("tdigest-finalize", "tdigest")).build();
    Assert.assertEquals(RowSignature.builder().addTimeColumn().add("count", ColumnType.LONG).add("tdigest", TDigestSketchAggregatorFactory.TYPE).add("tdigest-access", TDigestSketchAggregatorFactory.TYPE).add("tdigest-finalize", TDigestSketchAggregatorFactory.TYPE).build(), new TimeseriesQueryQueryToolChest().resultArraySignature(query));
}

Example 55 with TimeseriesQuery

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

the class DoublesSketchToHistogramPostAggregatorTest method testResultArraySignature.

@Test
public void testResultArraySignature() {
    final TimeseriesQuery query = Druids.newTimeseriesQueryBuilder().dataSource("dummy").intervals("2000/3000").granularity(Granularities.HOUR).aggregators(new DoublesSketchAggregatorFactory("sketch", "col", 8)).postAggregators(new DoublesSketchToHistogramPostAggregator("a", new FieldAccessPostAggregator("field", "sketch"), new double[] { 3.5 }, null)).build();
    Assert.assertEquals(RowSignature.builder().addTimeColumn().add("sketch", null).add("a", ColumnType.DOUBLE_ARRAY).build(), new TimeseriesQueryQueryToolChest().resultArraySignature(query));
}