Search in sources :

Example 1 with CascadeExtractionFn

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

the class GroupByQueryRunnerTest method testGroupByTimeExtractionWithNulls.

@Test
public void testGroupByTimeExtractionWithNulls() {
    // Cannot vectorize due to extraction dimension specs.
    cannotVectorize();
    final DimExtractionFn nullWednesdays = new DimExtractionFn() {

        @Override
        public String apply(String dimValue) {
            if ("Wednesday".equals(dimValue)) {
                return null;
            } else {
                return dimValue;
            }
        }

        @Override
        public byte[] getCacheKey() {
            throw new UnsupportedOperationException();
        }

        @Override
        public boolean preservesOrdering() {
            return false;
        }

        @Override
        public ExtractionType getExtractionType() {
            return ExtractionType.MANY_TO_ONE;
        }
    };
    GroupByQuery query = makeQueryBuilder().setDataSource(QueryRunnerTestHelper.DATA_SOURCE).setQuerySegmentSpec(QueryRunnerTestHelper.FULL_ON_INTERVAL_SPEC).setDimensions(new DefaultDimensionSpec("market", "market"), new ExtractionDimensionSpec(ColumnHolder.TIME_COLUMN_NAME, "dayOfWeek", new CascadeExtractionFn(new ExtractionFn[] { new TimeFormatExtractionFn("EEEE", null, null, null, false), nullWednesdays }))).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)))).build();
    List<ResultRow> expectedResults = Arrays.asList(makeRow(query, "1970-01-01", "dayOfWeek", null, "market", "spot", "index", 14271.368591308594, "rows", 126L, "addRowsIndexConstant", 14398.368591308594), makeRow(query, "1970-01-01", "dayOfWeek", "Friday", "market", "spot", "index", 13219.574157714844, "rows", 117L, "addRowsIndexConstant", 13337.574157714844), makeRow(query, "1970-01-01", "dayOfWeek", "Monday", "market", "spot", "index", 13557.738830566406, "rows", 117L, "addRowsIndexConstant", 13675.738830566406), makeRow(query, "1970-01-01", "dayOfWeek", "Saturday", "market", "spot", "index", 13493.751281738281, "rows", 117L, "addRowsIndexConstant", 13611.751281738281), makeRow(query, "1970-01-01", "dayOfWeek", "Sunday", "market", "spot", "index", 13585.541015625, "rows", 117L, "addRowsIndexConstant", 13703.541015625), makeRow(query, "1970-01-01", "dayOfWeek", "Thursday", "market", "spot", "index", 14279.127197265625, "rows", 126L, "addRowsIndexConstant", 14406.127197265625), makeRow(query, "1970-01-01", "dayOfWeek", "Tuesday", "market", "spot", "index", 13199.471435546875, "rows", 117L, "addRowsIndexConstant", 13317.471435546875), makeRow(query, "1970-01-01", "dayOfWeek", null, "market", "upfront", "index", 28985.5751953125, "rows", 28L, "addRowsIndexConstant", 29014.5751953125), makeRow(query, "1970-01-01", "dayOfWeek", "Friday", "market", "upfront", "index", 27297.8623046875, "rows", 26L, "addRowsIndexConstant", 27324.8623046875), makeRow(query, "1970-01-01", "dayOfWeek", "Monday", "market", "upfront", "index", 27619.58447265625, "rows", 26L, "addRowsIndexConstant", 27646.58447265625), makeRow(query, "1970-01-01", "dayOfWeek", "Saturday", "market", "upfront", "index", 27820.83154296875, "rows", 26L, "addRowsIndexConstant", 27847.83154296875), makeRow(query, "1970-01-01", "dayOfWeek", "Sunday", "market", "upfront", "index", 24791.223876953125, "rows", 26L, "addRowsIndexConstant", 24818.223876953125), makeRow(query, "1970-01-01", "dayOfWeek", "Thursday", "market", "upfront", "index", 28562.748901367188, "rows", 28L, "addRowsIndexConstant", 28591.748901367188), makeRow(query, "1970-01-01", "dayOfWeek", "Tuesday", "market", "upfront", "index", 26968.280639648438, "rows", 26L, "addRowsIndexConstant", 26995.280639648438));
    Iterable<ResultRow> results = GroupByQueryRunnerTestHelper.runQuery(factory, runner, query);
    TestHelper.assertExpectedObjects(expectedResults, results, "time-extraction");
}
Also used : TimeFormatExtractionFn(org.apache.druid.query.extraction.TimeFormatExtractionFn) DefaultDimensionSpec(org.apache.druid.query.dimension.DefaultDimensionSpec) CascadeExtractionFn(org.apache.druid.query.extraction.CascadeExtractionFn) RegexDimExtractionFn(org.apache.druid.query.extraction.RegexDimExtractionFn) StringFormatExtractionFn(org.apache.druid.query.extraction.StringFormatExtractionFn) LookupExtractionFn(org.apache.druid.query.lookup.LookupExtractionFn) CascadeExtractionFn(org.apache.druid.query.extraction.CascadeExtractionFn) StrlenExtractionFn(org.apache.druid.query.extraction.StrlenExtractionFn) SubstringDimExtractionFn(org.apache.druid.query.extraction.SubstringDimExtractionFn) ExtractionFn(org.apache.druid.query.extraction.ExtractionFn) DimExtractionFn(org.apache.druid.query.extraction.DimExtractionFn) JavaScriptExtractionFn(org.apache.druid.query.extraction.JavaScriptExtractionFn) SearchQuerySpecDimExtractionFn(org.apache.druid.query.extraction.SearchQuerySpecDimExtractionFn) TimeFormatExtractionFn(org.apache.druid.query.extraction.TimeFormatExtractionFn) SelectorDimFilter(org.apache.druid.query.filter.SelectorDimFilter) OrDimFilter(org.apache.druid.query.filter.OrDimFilter) RegexDimExtractionFn(org.apache.druid.query.extraction.RegexDimExtractionFn) SubstringDimExtractionFn(org.apache.druid.query.extraction.SubstringDimExtractionFn) DimExtractionFn(org.apache.druid.query.extraction.DimExtractionFn) SearchQuerySpecDimExtractionFn(org.apache.druid.query.extraction.SearchQuerySpecDimExtractionFn) ExtractionDimensionSpec(org.apache.druid.query.dimension.ExtractionDimensionSpec) InitializedNullHandlingTest(org.apache.druid.testing.InitializedNullHandlingTest) Test(org.junit.Test)

Aggregations

DefaultDimensionSpec (org.apache.druid.query.dimension.DefaultDimensionSpec)1 ExtractionDimensionSpec (org.apache.druid.query.dimension.ExtractionDimensionSpec)1 CascadeExtractionFn (org.apache.druid.query.extraction.CascadeExtractionFn)1 DimExtractionFn (org.apache.druid.query.extraction.DimExtractionFn)1 ExtractionFn (org.apache.druid.query.extraction.ExtractionFn)1 JavaScriptExtractionFn (org.apache.druid.query.extraction.JavaScriptExtractionFn)1 RegexDimExtractionFn (org.apache.druid.query.extraction.RegexDimExtractionFn)1 SearchQuerySpecDimExtractionFn (org.apache.druid.query.extraction.SearchQuerySpecDimExtractionFn)1 StringFormatExtractionFn (org.apache.druid.query.extraction.StringFormatExtractionFn)1 StrlenExtractionFn (org.apache.druid.query.extraction.StrlenExtractionFn)1 SubstringDimExtractionFn (org.apache.druid.query.extraction.SubstringDimExtractionFn)1 TimeFormatExtractionFn (org.apache.druid.query.extraction.TimeFormatExtractionFn)1 OrDimFilter (org.apache.druid.query.filter.OrDimFilter)1 SelectorDimFilter (org.apache.druid.query.filter.SelectorDimFilter)1 LookupExtractionFn (org.apache.druid.query.lookup.LookupExtractionFn)1 InitializedNullHandlingTest (org.apache.druid.testing.InitializedNullHandlingTest)1 Test (org.junit.Test)1