Examples with ExtractionDimFilter org.apache.druid.query.filter.ExtractionDimFilter used on opensource projects

Example 11 with ExtractionDimFilter

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

the class GroupByQueryRunnerTest method testGroupByWithExtractionDimFilterOptimazitionManyToOne.

@Test
public void testGroupByWithExtractionDimFilterOptimazitionManyToOne() {
    Map<String, String> extractionMap = new HashMap<>();
    extractionMap.put("mezzanine", "newsANDmezzanine");
    extractionMap.put("news", "newsANDmezzanine");
    MapLookupExtractor mapLookupExtractor = new MapLookupExtractor(extractionMap, false);
    LookupExtractionFn lookupExtractionFn = new LookupExtractionFn(mapLookupExtractor, false, null, true, true);
    GroupByQuery query = makeQueryBuilder().setDataSource(QueryRunnerTestHelper.DATA_SOURCE).setQuerySegmentSpec(QueryRunnerTestHelper.FIRST_TO_THIRD).setDimensions(new DefaultDimensionSpec("quality", "alias")).setAggregatorSpecs(QueryRunnerTestHelper.ROWS_COUNT, new LongSumAggregatorFactory("idx", "index")).setGranularity(QueryRunnerTestHelper.DAY_GRAN).setDimFilter(new ExtractionDimFilter("quality", "newsANDmezzanine", lookupExtractionFn, null)).build();
    List<ResultRow> expectedResults = Arrays.asList(makeRow(query, "2011-04-01", "alias", "mezzanine", "rows", 3L, "idx", 2870L), makeRow(query, "2011-04-01", "alias", "news", "rows", 1L, "idx", 121L), makeRow(query, "2011-04-02", "alias", "mezzanine", "rows", 3L, "idx", 2447L), makeRow(query, "2011-04-02", "alias", "news", "rows", 1L, "idx", 114L));
    Iterable<ResultRow> results = GroupByQueryRunnerTestHelper.runQuery(factory, runner, query);
    TestHelper.assertExpectedObjects(expectedResults, results, "extraction-dim-filter");
}

Example 12 with ExtractionDimFilter

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

the class GroupByQueryRunnerTest method testGroupByWithAggregatorFilterAndExtractionFunction.

@Test
public void testGroupByWithAggregatorFilterAndExtractionFunction() {
    Map<String, String> extractionMap = new HashMap<>();
    extractionMap.put("automotive", "automotive0");
    extractionMap.put("business", "business0");
    extractionMap.put("entertainment", "entertainment0");
    extractionMap.put("health", "health0");
    extractionMap.put("mezzanine", "mezzanineANDnews");
    extractionMap.put("news", "mezzanineANDnews");
    extractionMap.put("premium", "premium0");
    extractionMap.put("technology", "technology0");
    extractionMap.put("travel", "travel0");
    MapLookupExtractor mapLookupExtractor = new MapLookupExtractor(extractionMap, false);
    LookupExtractionFn lookupExtractionFn = new LookupExtractionFn(mapLookupExtractor, false, "missing", true, false);
    DimFilter filter = new ExtractionDimFilter("quality", "mezzanineANDnews", lookupExtractionFn, null);
    GroupByQuery query = makeQueryBuilder().setDataSource(QueryRunnerTestHelper.DATA_SOURCE).setQuerySegmentSpec(QueryRunnerTestHelper.FIRST_TO_THIRD).setDimensions(new DefaultDimensionSpec("quality", "alias")).setAggregatorSpecs(new FilteredAggregatorFactory(QueryRunnerTestHelper.ROWS_COUNT, filter), new FilteredAggregatorFactory(new LongSumAggregatorFactory("idx", "index"), filter)).setGranularity(QueryRunnerTestHelper.DAY_GRAN).build();
    List<ResultRow> expectedResults = Arrays.asList(makeRow(query, "2011-04-01", "alias", "automotive", "rows", 0L, "idx", NullHandling.defaultLongValue()), makeRow(query, "2011-04-01", "alias", "business", "rows", 0L, "idx", NullHandling.defaultLongValue()), makeRow(query, "2011-04-01", "alias", "entertainment", "rows", 0L, "idx", NullHandling.defaultLongValue()), makeRow(query, "2011-04-01", "alias", "health", "rows", 0L, "idx", NullHandling.defaultLongValue()), makeRow(query, "2011-04-01", "alias", "mezzanine", "rows", 3L, "idx", 2870L), makeRow(query, "2011-04-01", "alias", "news", "rows", 1L, "idx", 121L), makeRow(query, "2011-04-01", "alias", "premium", "rows", 0L, "idx", NullHandling.defaultLongValue()), makeRow(query, "2011-04-01", "alias", "technology", "rows", 0L, "idx", NullHandling.defaultLongValue()), makeRow(query, "2011-04-01", "alias", "travel", "rows", 0L, "idx", NullHandling.defaultLongValue()), makeRow(query, "2011-04-02", "alias", "automotive", "rows", 0L, "idx", NullHandling.defaultLongValue()), makeRow(query, "2011-04-02", "alias", "business", "rows", 0L, "idx", NullHandling.defaultLongValue()), makeRow(query, "2011-04-02", "alias", "entertainment", "rows", 0L, "idx", NullHandling.defaultLongValue()), makeRow(query, "2011-04-02", "alias", "health", "rows", 0L, "idx", NullHandling.defaultLongValue()), makeRow(query, "2011-04-02", "alias", "mezzanine", "rows", 3L, "idx", 2447L), makeRow(query, "2011-04-02", "alias", "news", "rows", 1L, "idx", 114L), makeRow(query, "2011-04-02", "alias", "premium", "rows", 0L, "idx", NullHandling.defaultLongValue()), makeRow(query, "2011-04-02", "alias", "technology", "rows", 0L, "idx", NullHandling.defaultLongValue()), makeRow(query, "2011-04-02", "alias", "travel", "rows", 0L, "idx", NullHandling.defaultLongValue()));
    Iterable<ResultRow> results = GroupByQueryRunnerTestHelper.runQuery(factory, runner, query);
    TestHelper.assertExpectedObjects(expectedResults, results, "agg-filter");
}

Example 13 with ExtractionDimFilter

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

the class GroupByQueryRunnerTest method testGroupByWithExtractionDimFilterWhenSearchValueNotInTheMap.

@Test
public void testGroupByWithExtractionDimFilterWhenSearchValueNotInTheMap() {
    Map<String, String> extractionMap = new HashMap<>();
    MapLookupExtractor mapLookupExtractor = new MapLookupExtractor(extractionMap, false);
    LookupExtractionFn lookupExtractionFn = new LookupExtractionFn(mapLookupExtractor, false, null, true, false);
    GroupByQuery query = makeQueryBuilder().setDataSource(QueryRunnerTestHelper.DATA_SOURCE).setQuerySegmentSpec(QueryRunnerTestHelper.FIRST_TO_THIRD).setDimensions(new DefaultDimensionSpec("quality", "alias")).setAggregatorSpecs(QueryRunnerTestHelper.ROWS_COUNT, new LongSumAggregatorFactory("idx", "index")).setGranularity(QueryRunnerTestHelper.DAY_GRAN).setDimFilter(new ExtractionDimFilter("quality", "NOT_THERE", lookupExtractionFn, null)).build();
    List<ResultRow> expectedResults = Collections.emptyList();
    Iterable<ResultRow> results = GroupByQueryRunnerTestHelper.runQuery(factory, runner, query);
    TestHelper.assertExpectedObjects(expectedResults, results, "dim-extraction");
}

Example 14 with ExtractionDimFilter

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

the class TopNQueryRunnerTest method testTopNWithExtractionFilterAndFilteredAggregatorCaseNoExistingValue.

@Test
public void testTopNWithExtractionFilterAndFilteredAggregatorCaseNoExistingValue() {
    Map<String, String> extractionMap = new HashMap<>();
    MapLookupExtractor mapLookupExtractor = new MapLookupExtractor(extractionMap, false);
    LookupExtractionFn lookupExtractionFn;
    if (NullHandling.replaceWithDefault()) {
        lookupExtractionFn = new LookupExtractionFn(mapLookupExtractor, false, null, true, false);
        extractionMap.put("", "NULL");
    } else {
        lookupExtractionFn = new LookupExtractionFn(mapLookupExtractor, false, "NULL", true, false);
    }
    DimFilter extractionFilter = new ExtractionDimFilter("null_column", "NULL", lookupExtractionFn, null);
    TopNQueryBuilder topNQueryBuilder = new TopNQueryBuilder().dataSource(QueryRunnerTestHelper.DATA_SOURCE).granularity(QueryRunnerTestHelper.ALL_GRAN).dimension("null_column").metric(QueryRunnerTestHelper.INDEX_METRIC).threshold(4).intervals(QueryRunnerTestHelper.FULL_ON_INTERVAL_SPEC).aggregators(Lists.newArrayList(Iterables.concat(commonAggregators, Lists.newArrayList(new FilteredAggregatorFactory(new DoubleMaxAggregatorFactory("maxIndex", "index"), extractionFilter), new DoubleMinAggregatorFactory("minIndex", "index"))))).postAggregators(QueryRunnerTestHelper.ADD_ROWS_INDEX_CONSTANT);
    TopNQuery topNQueryWithNULLValueExtraction = topNQueryBuilder.filters(extractionFilter).build();
    Map<String, Object> map = new HashMap<>();
    map.put("null_column", null);
    map.put("rows", 1209L);
    map.put("index", 503332.5071372986D);
    map.put("addRowsIndexConstant", 504542.5071372986D);
    map.put("uniques", QueryRunnerTestHelper.UNIQUES_9);
    map.put("maxIndex", 1870.061029D);
    map.put("minIndex", 59.02102279663086D);
    List<Result<TopNResultValue>> expectedResults = Collections.singletonList(new Result<>(DateTimes.of("2011-01-12T00:00:00.000Z"), new TopNResultValue(Collections.singletonList(map))));
    assertExpectedResults(expectedResults, topNQueryWithNULLValueExtraction);
}

Example 15 with ExtractionDimFilter

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

the class ExtractionDimFilterTest method testAnd.

@Test
public void testAnd() {
    Assert.assertEquals(1, Filters.toFilter(DimFilters.or(new ExtractionDimFilter("foo", "extractDimVal", DIM_EXTRACTION_FN, null))).getBitmapIndex(BITMAP_INDEX_SELECTOR).size());
    Assert.assertEquals(1, Filters.toFilter(DimFilters.and(new ExtractionDimFilter("foo", "extractDimVal", DIM_EXTRACTION_FN, null), new ExtractionDimFilter("foo", "extractDimVal", DIM_EXTRACTION_FN, null))).getBitmapIndex(BITMAP_INDEX_SELECTOR).size());
}