Examples with ExtractionDimensionSpec org.apache.druid.query.dimension.ExtractionDimensionSpec used on opensource projects

Example 31 with ExtractionDimensionSpec

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

the class GroupByQueryRunnerTest method testGroupByCardinalityAggWithExtractionFn.

@Test
public void testGroupByCardinalityAggWithExtractionFn() {
    // Cannot vectorize due to extraction dimension spec.
    cannotVectorize();
    String helloJsFn = "function(str) { return 'hello' }";
    ExtractionFn helloFn = new JavaScriptExtractionFn(helloJsFn, false, JavaScriptConfig.getEnabledInstance());
    GroupByQuery query = makeQueryBuilder().setDataSource(QueryRunnerTestHelper.DATA_SOURCE).setQuerySegmentSpec(QueryRunnerTestHelper.FIRST_TO_THIRD).setDimensions(new DefaultDimensionSpec("market", "alias")).setAggregatorSpecs(QueryRunnerTestHelper.ROWS_COUNT, new CardinalityAggregatorFactory("numVals", ImmutableList.of(new ExtractionDimensionSpec(QueryRunnerTestHelper.QUALITY_DIMENSION, QueryRunnerTestHelper.QUALITY_DIMENSION, helloFn)), false)).setGranularity(QueryRunnerTestHelper.DAY_GRAN).build();
    List<ResultRow> expectedResults = Arrays.asList(makeRow(query, "2011-04-01", "alias", "spot", "rows", 9L, "numVals", 1.0002442201269182d), makeRow(query, "2011-04-01", "alias", "total_market", "rows", 2L, "numVals", 1.0002442201269182d), makeRow(query, "2011-04-01", "alias", "upfront", "rows", 2L, "numVals", 1.0002442201269182d), makeRow(query, "2011-04-02", "alias", "spot", "rows", 9L, "numVals", 1.0002442201269182d), makeRow(query, "2011-04-02", "alias", "total_market", "rows", 2L, "numVals", 1.0002442201269182d), makeRow(query, "2011-04-02", "alias", "upfront", "rows", 2L, "numVals", 1.0002442201269182d));
    Iterable<ResultRow> results = GroupByQueryRunnerTestHelper.runQuery(factory, runner, query);
    TestHelper.assertExpectedObjects(expectedResults, results, "cardinality-agg");
}

Example 32 with ExtractionDimensionSpec

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

the class GroupByQueryRunnerTest method testGroupByWithSimpleRenameRetainMissing.

@Test
public void testGroupByWithSimpleRenameRetainMissing() {
    Map<String, String> map = new HashMap<>();
    map.put("automotive", "automotive0");
    map.put("business", "business0");
    map.put("entertainment", "entertainment0");
    map.put("health", "health0");
    map.put("mezzanine", "mezzanine0");
    map.put("news", "news0");
    map.put("premium", "premium0");
    map.put("technology", "technology0");
    map.put("travel", "travel0");
    GroupByQuery query = makeQueryBuilder().setDataSource(QueryRunnerTestHelper.DATA_SOURCE).setQuerySegmentSpec(QueryRunnerTestHelper.FIRST_TO_THIRD).setDimensions(new ExtractionDimensionSpec("quality", "alias", new LookupExtractionFn(new MapLookupExtractor(map, false), true, null, true, false))).setAggregatorSpecs(QueryRunnerTestHelper.ROWS_COUNT, new LongSumAggregatorFactory("idx", "index")).setGranularity(QueryRunnerTestHelper.DAY_GRAN).build();
    List<ResultRow> expectedResults = Arrays.asList(makeRow(query, "2011-04-01", "alias", "automotive0", "rows", 1L, "idx", 135L), makeRow(query, "2011-04-01", "alias", "business0", "rows", 1L, "idx", 118L), makeRow(query, "2011-04-01", "alias", "entertainment0", "rows", 1L, "idx", 158L), makeRow(query, "2011-04-01", "alias", "health0", "rows", 1L, "idx", 120L), makeRow(query, "2011-04-01", "alias", "mezzanine0", "rows", 3L, "idx", 2870L), makeRow(query, "2011-04-01", "alias", "news0", "rows", 1L, "idx", 121L), makeRow(query, "2011-04-01", "alias", "premium0", "rows", 3L, "idx", 2900L), makeRow(query, "2011-04-01", "alias", "technology0", "rows", 1L, "idx", 78L), makeRow(query, "2011-04-01", "alias", "travel0", "rows", 1L, "idx", 119L), makeRow(query, "2011-04-02", "alias", "automotive0", "rows", 1L, "idx", 147L), makeRow(query, "2011-04-02", "alias", "business0", "rows", 1L, "idx", 112L), makeRow(query, "2011-04-02", "alias", "entertainment0", "rows", 1L, "idx", 166L), makeRow(query, "2011-04-02", "alias", "health0", "rows", 1L, "idx", 113L), makeRow(query, "2011-04-02", "alias", "mezzanine0", "rows", 3L, "idx", 2447L), makeRow(query, "2011-04-02", "alias", "news0", "rows", 1L, "idx", 114L), makeRow(query, "2011-04-02", "alias", "premium0", "rows", 3L, "idx", 2505L), makeRow(query, "2011-04-02", "alias", "technology0", "rows", 1L, "idx", 97L), makeRow(query, "2011-04-02", "alias", "travel0", "rows", 1L, "idx", 126L));
    Iterable<ResultRow> results = GroupByQueryRunnerTestHelper.runQuery(factory, runner, query);
    TestHelper.assertExpectedObjects(expectedResults, results, "retain-missing");
}

Example 33 with ExtractionDimensionSpec

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

the class GroupByQueryRunnerTest method testExtractionStringArraySpecWithMultiValueVirtualDimAsInput.

@Test
public void testExtractionStringArraySpecWithMultiValueVirtualDimAsInput() {
    if (config.getDefaultStrategy().equals(GroupByStrategySelector.STRATEGY_V1)) {
        expectedException.expect(UnsupportedOperationException.class);
        expectedException.expectMessage("GroupBy v1 only supports dimensions with an outputType of STRING");
    } else if (!vectorize) {
        expectedException.expect(RuntimeException.class);
        expectedException.expectMessage("Not supported for multi-value dimensions");
    }
    cannotVectorize();
    GroupByQuery query = makeQueryBuilder().setDataSource(QueryRunnerTestHelper.DATA_SOURCE).setQuerySegmentSpec(QueryRunnerTestHelper.FIRST_TO_THIRD).setVirtualColumns(new ExpressionVirtualColumn("v0", "mv_to_array(placementish)", ColumnType.STRING_ARRAY, ExprMacroTable.nil())).setDimensions(new ExtractionDimensionSpec("v0", "alias", ColumnType.STRING_ARRAY, new SubstringDimExtractionFn(1, 1))).setAggregatorSpecs(QueryRunnerTestHelper.ROWS_COUNT, new LongSumAggregatorFactory("idx", "index")).setGranularity(QueryRunnerTestHelper.ALL_GRAN).build();
    GroupByQueryRunnerTestHelper.runQuery(factory, runner, query);
}

Example 34 with ExtractionDimensionSpec

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

the class GroupByQueryRunnerTest method testGroupByTimeExtractionNamedUnderUnderTime.

@Test
public void testGroupByTimeExtractionNamedUnderUnderTime() {
    expectedException.expect(IAE.class);
    expectedException.expectMessage("'__time' cannot be used as an output name for dimensions, aggregators, or post-aggregators.");
    makeQueryBuilder().setDataSource(QueryRunnerTestHelper.DATA_SOURCE).setQuerySegmentSpec(QueryRunnerTestHelper.FULL_ON_INTERVAL_SPEC).setDimensions(new DefaultDimensionSpec("market", "market"), new ExtractionDimensionSpec(ColumnHolder.TIME_COLUMN_NAME, ColumnHolder.TIME_COLUMN_NAME, new TimeFormatExtractionFn("EEEE", null, null, null, false))).setAggregatorSpecs(QueryRunnerTestHelper.ROWS_COUNT, QueryRunnerTestHelper.INDEX_DOUBLE_SUM).setPostAggregatorSpecs(Collections.singletonList(QueryRunnerTestHelper.ADD_ROWS_INDEX_CONSTANT)).setGranularity(QueryRunnerTestHelper.ALL_GRAN).setDimFilter(new OrDimFilter(Arrays.asList(new SelectorDimFilter("market", "spot", null), new SelectorDimFilter("market", "upfront", null)))).setLimitSpec(new DefaultLimitSpec(ImmutableList.of(), 1)).build();
}

Example 35 with ExtractionDimensionSpec

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

the class GroupByQueryRunnerTest method testGroupByWithAlphaNumericDimensionOrder.

@Test
public void testGroupByWithAlphaNumericDimensionOrder() {
    // Cannot vectorize due to extraction dimension spec.
    cannotVectorize();
    Map<String, String> map = new HashMap<>();
    map.put("automotive", "health105");
    map.put("business", "health20");
    map.put("entertainment", "travel47");
    map.put("health", "health55");
    map.put("mezzanine", "health09");
    map.put("news", "health0000");
    map.put("premium", "health999");
    map.put("technology", "travel123");
    map.put("travel", "travel555");
    GroupByQuery query = makeQueryBuilder().setDataSource(QueryRunnerTestHelper.DATA_SOURCE).setQuerySegmentSpec(QueryRunnerTestHelper.FIRST_TO_THIRD).setDimensions(new ExtractionDimensionSpec("quality", "alias", new LookupExtractionFn(new MapLookupExtractor(map, false), false, null, false, false))).setAggregatorSpecs(QueryRunnerTestHelper.ROWS_COUNT, new LongSumAggregatorFactory("idx", "index")).setLimitSpec(new DefaultLimitSpec(Collections.singletonList(new OrderByColumnSpec("alias", null, StringComparators.ALPHANUMERIC)), null)).setGranularity(QueryRunnerTestHelper.DAY_GRAN).build();
    List<ResultRow> expectedResults = Arrays.asList(makeRow(query, "2011-04-01", "alias", "health0000", "rows", 1L, "idx", 121L), makeRow(query, "2011-04-01", "alias", "health09", "rows", 3L, "idx", 2870L), makeRow(query, "2011-04-01", "alias", "health20", "rows", 1L, "idx", 118L), makeRow(query, "2011-04-01", "alias", "health55", "rows", 1L, "idx", 120L), makeRow(query, "2011-04-01", "alias", "health105", "rows", 1L, "idx", 135L), makeRow(query, "2011-04-01", "alias", "health999", "rows", 3L, "idx", 2900L), makeRow(query, "2011-04-01", "alias", "travel47", "rows", 1L, "idx", 158L), makeRow(query, "2011-04-01", "alias", "travel123", "rows", 1L, "idx", 78L), makeRow(query, "2011-04-01", "alias", "travel555", "rows", 1L, "idx", 119L), makeRow(query, "2011-04-02", "alias", "health0000", "rows", 1L, "idx", 114L), makeRow(query, "2011-04-02", "alias", "health09", "rows", 3L, "idx", 2447L), makeRow(query, "2011-04-02", "alias", "health20", "rows", 1L, "idx", 112L), makeRow(query, "2011-04-02", "alias", "health55", "rows", 1L, "idx", 113L), makeRow(query, "2011-04-02", "alias", "health105", "rows", 1L, "idx", 147L), makeRow(query, "2011-04-02", "alias", "health999", "rows", 3L, "idx", 2505L), makeRow(query, "2011-04-02", "alias", "travel47", "rows", 1L, "idx", 166L), makeRow(query, "2011-04-02", "alias", "travel123", "rows", 1L, "idx", 97L), makeRow(query, "2011-04-02", "alias", "travel555", "rows", 1L, "idx", 126L));
    Iterable<ResultRow> results = GroupByQueryRunnerTestHelper.runQuery(factory, runner, query);
    TestHelper.assertExpectedObjects(expectedResults, results, "alphanumeric-dimension-order");
}