Examples with RegexDimExtractionFn org.apache.druid.query.extraction.RegexDimExtractionFn used on opensource projects

Example 36 with RegexDimExtractionFn

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

the class IntervalDimFilterTest method testGetCacheKey.

@Test
public void testGetCacheKey() {
    DimFilter intervalFilter1 = new IntervalDimFilter(ColumnHolder.TIME_COLUMN_NAME, Arrays.asList(Intervals.of("1970-01-01T00:00:00.001Z/1970-01-01T00:00:00.004Z"), Intervals.of("1975-01-01T00:00:00.001Z/1980-01-01T00:00:00.004Z")), null);
    DimFilter intervalFilter2 = new IntervalDimFilter(ColumnHolder.TIME_COLUMN_NAME, Arrays.asList(Intervals.of("1970-01-01T00:00:00.001Z/1970-01-01T00:00:00.004Z"), Intervals.of("1976-01-01T00:00:00.001Z/1980-01-01T00:00:00.004Z")), null);
    Assert.assertNotEquals(intervalFilter1.getCacheKey(), intervalFilter2.getCacheKey());
    RegexDimExtractionFn regexFn = new RegexDimExtractionFn(".*", false, null);
    DimFilter intervalFilter3 = new IntervalDimFilter(ColumnHolder.TIME_COLUMN_NAME, Arrays.asList(Intervals.of("1970-01-01T00:00:00.001Z/1970-01-01T00:00:00.004Z"), Intervals.of("1975-01-01T00:00:00.001Z/1980-01-01T00:00:00.004Z")), regexFn);
    DimFilter intervalFilter4 = new IntervalDimFilter(ColumnHolder.TIME_COLUMN_NAME, Arrays.asList(Intervals.of("1970-01-01T00:00:00.001Z/1970-01-01T00:00:00.004Z"), Intervals.of("1976-01-01T00:00:00.001Z/1980-01-01T00:00:00.004Z")), regexFn);
    Assert.assertNotEquals(intervalFilter3.getCacheKey(), intervalFilter4.getCacheKey());
}

Example 37 with RegexDimExtractionFn

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

the class TopNQueryRunnerTest method testTopNLexicographicDimExtractionWithPreviousStop.

@Test
public void testTopNLexicographicDimExtractionWithPreviousStop() {
    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(new DimensionTopNMetricSpec("s", 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, "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);
}

Example 38 with RegexDimExtractionFn

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

the class TopNQueryRunnerTest method testTopNCollapsingDimExtraction.

@Test
public void testTopNCollapsingDimExtraction() {
    TopNQuery query = new TopNQueryBuilder().dataSource(QueryRunnerTestHelper.DATA_SOURCE).granularity(QueryRunnerTestHelper.ALL_GRAN).dimension(new ExtractionDimensionSpec(QueryRunnerTestHelper.QUALITY_DIMENSION, QueryRunnerTestHelper.QUALITY_DIMENSION, new RegexDimExtractionFn(".(.)", false, null))).metric("index").threshold(2).intervals(QueryRunnerTestHelper.FULL_ON_INTERVAL_SPEC).aggregators(QueryRunnerTestHelper.ROWS_COUNT, QueryRunnerTestHelper.INDEX_DOUBLE_SUM).postAggregators(QueryRunnerTestHelper.ADD_ROWS_INDEX_CONSTANT).build();
    List<Result<TopNResultValue>> expectedResults = Collections.singletonList(new Result<>(DateTimes.of("2011-01-12T00:00:00.000Z"), new TopNResultValue(Arrays.<Map<String, Object>>asList(ImmutableMap.of(QueryRunnerTestHelper.QUALITY_DIMENSION, "e", "rows", 558L, "index", 246645.1204032898, "addRowsIndexConstant", 247204.1204032898), ImmutableMap.of(QueryRunnerTestHelper.QUALITY_DIMENSION, "r", "rows", 372L, "index", 222051.08961486816, "addRowsIndexConstant", 222424.08961486816)))));
    assertExpectedResults(expectedResults, query);
    query = query.withAggregatorSpecs(Arrays.asList(QueryRunnerTestHelper.ROWS_COUNT, new DoubleSumAggregatorFactory("index", null, "-index + 100", ExprMacroTable.nil())));
    expectedResults = Collections.singletonList(TopNQueryRunnerTestHelper.createExpectedRows("2011-01-12T00:00:00.000Z", new String[] { QueryRunnerTestHelper.QUALITY_DIMENSION, "rows", "index", "addRowsIndexConstant" }, Arrays.asList(new Object[] { "n", 93L, -2786.4727909999997, -2692.4727909999997 }, new Object[] { "u", 186L, -3949.824348000002, -3762.824348000002 })));
    assertExpectedResults(expectedResults, query);
}

Example 39 with RegexDimExtractionFn

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

the class DimensionSelectorHavingSpecTest method testEquals.

@Test
public void testEquals() {
    ExtractionFn extractionFn1 = new RegexDimExtractionFn("^([^,]*),", false, "");
    ExtractionFn extractionFn2 = new RegexDimExtractionFn(",(.*)", false, "");
    ExtractionFn extractionFn3 = new RegexDimExtractionFn("^([^,]*),", false, "");
    HavingSpec dimHavingSpec1 = new DimensionSelectorHavingSpec("dim", "v", extractionFn1);
    HavingSpec dimHavingSpec2 = new DimensionSelectorHavingSpec("dim", "v", extractionFn3);
    HavingSpec dimHavingSpec3 = new DimensionSelectorHavingSpec("dim1", "v", null);
    HavingSpec dimHavingSpec4 = new DimensionSelectorHavingSpec("dim2", "v", null);
    HavingSpec dimHavingSpec5 = new DimensionSelectorHavingSpec("dim", "v1", null);
    HavingSpec dimHavingSpec6 = new DimensionSelectorHavingSpec("dim", "v2", null);
    HavingSpec dimHavingSpec7 = new DimensionSelectorHavingSpec("dim", null, null);
    HavingSpec dimHavingSpec8 = new DimensionSelectorHavingSpec("dim", null, null);
    HavingSpec dimHavingSpec9 = new DimensionSelectorHavingSpec("dim1", null, null);
    HavingSpec dimHavingSpec10 = new DimensionSelectorHavingSpec("dim2", null, null);
    HavingSpec dimHavingSpec11 = new DimensionSelectorHavingSpec("dim1", "v", null);
    HavingSpec dimHavingSpec12 = new DimensionSelectorHavingSpec("dim2", null, null);
    HavingSpec dimHavingSpec13 = new DimensionSelectorHavingSpec("dim", "value", extractionFn1);
    HavingSpec dimHavingSpec14 = new DimensionSelectorHavingSpec("dim", "value", extractionFn2);
    Assert.assertEquals(dimHavingSpec1, dimHavingSpec2);
    Assert.assertNotEquals(dimHavingSpec3, dimHavingSpec4);
    Assert.assertNotEquals(dimHavingSpec5, dimHavingSpec6);
    Assert.assertEquals(dimHavingSpec7, dimHavingSpec8);
    Assert.assertNotEquals(dimHavingSpec9, dimHavingSpec10);
    Assert.assertNotEquals(dimHavingSpec11, dimHavingSpec12);
    Assert.assertNotEquals(dimHavingSpec13, dimHavingSpec14);
}

Example 40 with RegexDimExtractionFn

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

the class NestedQueryPushDownTest method testSubqueryWithExtractionFnInOuterQuery.

@Test
public void testSubqueryWithExtractionFnInOuterQuery() {
    QuerySegmentSpec intervalSpec = new MultipleIntervalSegmentSpec(Collections.singletonList(Intervals.utc(1500000000000L, 1600000000000L)));
    GroupByQuery query = GroupByQuery.builder().setDataSource("blah").setDimensions(new DefaultDimensionSpec("dimA", "dimA"), new DefaultDimensionSpec("dimB", "dimB")).setAggregatorSpecs(new LongSumAggregatorFactory("metASum", "metA"), new LongSumAggregatorFactory("metBSum", "metB")).setGranularity(Granularities.ALL).setQuerySegmentSpec(intervalSpec).build();
    GroupByQuery nestedQuery = GroupByQuery.builder().setDataSource(query).setDimensions(new ExtractionDimensionSpec("dimA", "extractedDimA", new RegexDimExtractionFn("^(p)", true, "replacement"))).setAggregatorSpecs(new LongSumAggregatorFactory("finalSum", "metASum")).setContext(ImmutableMap.of(GroupByQueryConfig.CTX_KEY_FORCE_PUSH_DOWN_NESTED_QUERY, true)).setGranularity(Granularities.ALL).setQuerySegmentSpec(intervalSpec).build();
    ResultRow expectedRow0 = GroupByQueryRunnerTestHelper.createExpectedRow(nestedQuery, "2017-07-14T02:40:00.000Z", "finalSum", 4000L, "extractedDimA", "p");
    ResultRow expectedRow1 = GroupByQueryRunnerTestHelper.createExpectedRow(nestedQuery, "2017-07-14T02:40:00.000Z", "finalSum", 4000L, "extractedDimA", "replacement");
    Sequence<ResultRow> queryResult = runNestedQueryWithForcePushDown(nestedQuery);
    List<ResultRow> results = queryResult.toList();
    Assert.assertEquals(2, results.size());
    Assert.assertEquals(expectedRow0, results.get(0));
    Assert.assertEquals(expectedRow1, results.get(1));
}