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

Example 6 with ExtractionDimFilter

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

the class TopNQueryRunnerTest method testTopNWithExtractionFilter.

@Test
public void testTopNWithExtractionFilter() {
    Map<String, String> extractionMap = new HashMap<>();
    extractionMap.put("spot", "spot0");
    MapLookupExtractor mapLookupExtractor = new MapLookupExtractor(extractionMap, false);
    LookupExtractionFn lookupExtractionFn = new LookupExtractionFn(mapLookupExtractor, false, null, true, false);
    TopNQuery query = new TopNQueryBuilder().dataSource(QueryRunnerTestHelper.DATA_SOURCE).granularity(QueryRunnerTestHelper.ALL_GRAN).dimension(QueryRunnerTestHelper.MARKET_DIMENSION).metric("rows").threshold(3).intervals(QueryRunnerTestHelper.FIRST_TO_THIRD).aggregators(commonAggregators).postAggregators(QueryRunnerTestHelper.ADD_ROWS_INDEX_CONSTANT).filters(new ExtractionDimFilter(QueryRunnerTestHelper.MARKET_DIMENSION, "spot0", lookupExtractionFn, null)).build();
    List<Result<TopNResultValue>> expectedResults = Collections.singletonList(new Result<>(DateTimes.of("2011-04-01T00:00:00.000Z"), new TopNResultValue(Collections.<Map<String, Object>>singletonList(ImmutableMap.of(QueryRunnerTestHelper.MARKET_DIMENSION, "spot", "rows", 18L, "index", 2231.876812D, "addRowsIndexConstant", 2250.876812D, "uniques", QueryRunnerTestHelper.UNIQUES_9)))));
    assertExpectedResults(expectedResults, query);
    // Assert the optimization path as well
    final Sequence<Result<TopNResultValue>> retval = runWithPreMergeAndMerge(query);
    TestHelper.assertExpectedResults(expectedResults, retval);
}

Example 7 with ExtractionDimFilter

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

the class SearchQueryRunnerTest method testSearchWithExtractionFilter1.

@Test
public void testSearchWithExtractionFilter1() {
    final String automotiveSnowman = "automotive☃";
    List<SearchHit> expectedHits = new ArrayList<>();
    expectedHits.add(new SearchHit(QueryRunnerTestHelper.QUALITY_DIMENSION, automotiveSnowman, 93));
    final LookupExtractionFn lookupExtractionFn = new LookupExtractionFn(new MapLookupExtractor(ImmutableMap.of("automotive", automotiveSnowman), false), true, null, true, true);
    SearchQuery query = Druids.newSearchQueryBuilder().dataSource(QueryRunnerTestHelper.DATA_SOURCE).granularity(QueryRunnerTestHelper.ALL_GRAN).filters(new ExtractionDimFilter(QueryRunnerTestHelper.QUALITY_DIMENSION, automotiveSnowman, lookupExtractionFn, null)).intervals(QueryRunnerTestHelper.FULL_ON_INTERVAL_SPEC).dimensions(new ExtractionDimensionSpec(QueryRunnerTestHelper.QUALITY_DIMENSION, null, lookupExtractionFn)).query("☃").build();
    checkSearchQuery(query, expectedHits);
}

Example 8 with ExtractionDimFilter

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

the class GroupByQueryRunnerTest method testGroupByWithExtractionDimFilterCaseMappingValueIsNullOrEmpty.

@Test
public void testGroupByWithExtractionDimFilterCaseMappingValueIsNullOrEmpty() {
    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", null);
    extractionMap.put("news", "");
    extractionMap.put("premium", "premium0");
    extractionMap.put("technology", "technology0");
    extractionMap.put("travel", "travel0");
    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", "", lookupExtractionFn, null)).build();
    List<ResultRow> expectedResults;
    if (NullHandling.replaceWithDefault()) {
        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));
    } else {
        // Only empty string should match, nulls will not match
        expectedResults = Arrays.asList(makeRow(query, "2011-04-01", "alias", "news", "rows", 1L, "idx", 121L), makeRow(query, "2011-04-02", "alias", "news", "rows", 1L, "idx", 114L));
    }
    Iterable<ResultRow> results = GroupByQueryRunnerTestHelper.runQuery(factory, runner, query);
    TestHelper.assertExpectedObjects(expectedResults, results, "dim-extraction");
}

Example 9 with ExtractionDimFilter

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

the class GroupByQueryRunnerTest method testGroupByWithExtractionDimFilterNullDims.

@Test
public void testGroupByWithExtractionDimFilterNullDims() {
    Map<String, String> extractionMap = new HashMap<>();
    extractionMap.put("", "EMPTY");
    MapLookupExtractor mapLookupExtractor = new MapLookupExtractor(extractionMap, false);
    LookupExtractionFn lookupExtractionFn;
    if (NullHandling.replaceWithDefault()) {
        extractionMap.put("", "EMPTY");
        lookupExtractionFn = new LookupExtractionFn(mapLookupExtractor, false, null, true, true);
    } else {
        extractionMap.put("", "SHOULD_NOT_BE_USED");
        lookupExtractionFn = new LookupExtractionFn(mapLookupExtractor, false, "EMPTY", true, true);
    }
    GroupByQuery query = makeQueryBuilder().setDataSource(QueryRunnerTestHelper.DATA_SOURCE).setQuerySegmentSpec(QueryRunnerTestHelper.FIRST_TO_THIRD).setDimensions(new DefaultDimensionSpec("null_column", "alias")).setAggregatorSpecs(QueryRunnerTestHelper.ROWS_COUNT, new LongSumAggregatorFactory("idx", "index")).setGranularity(QueryRunnerTestHelper.DAY_GRAN).setDimFilter(new ExtractionDimFilter("null_column", "EMPTY", lookupExtractionFn, null)).build();
    List<ResultRow> expectedResults = Arrays.asList(makeRow(query, "2011-04-01", "alias", null, "rows", 13L, "idx", 6619L), makeRow(query, "2011-04-02", "alias", null, "rows", 13L, "idx", 5827L));
    Iterable<ResultRow> results = GroupByQueryRunnerTestHelper.runQuery(factory, runner, query);
    TestHelper.assertExpectedObjects(expectedResults, results, "extraction-dim-filter");
}

Example 10 with ExtractionDimFilter

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

the class GroupByQueryRunnerTest method testGroupByWithExtractionDimFilter.

// Extraction Filters testing
@Test
public void testGroupByWithExtractionDimFilter() {
    Map<String, String> extractionMap = new HashMap<>();
    extractionMap.put("automotive", "automotiveAndBusinessAndNewsAndMezzanine");
    extractionMap.put("business", "automotiveAndBusinessAndNewsAndMezzanine");
    extractionMap.put("mezzanine", "automotiveAndBusinessAndNewsAndMezzanine");
    extractionMap.put("news", "automotiveAndBusinessAndNewsAndMezzanine");
    MapLookupExtractor mapLookupExtractor = new MapLookupExtractor(extractionMap, false);
    LookupExtractionFn lookupExtractionFn = new LookupExtractionFn(mapLookupExtractor, false, null, true, false);
    List<DimFilter> dimFilters = Lists.newArrayList(new ExtractionDimFilter("quality", "automotiveAndBusinessAndNewsAndMezzanine", lookupExtractionFn, null), new SelectorDimFilter("quality", "entertainment", null), new SelectorDimFilter("quality", "health", null), new SelectorDimFilter("quality", "premium", null), new SelectorDimFilter("quality", "technology", null), new SelectorDimFilter("quality", "travel", null));
    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 OrDimFilter(dimFilters)).build();
    List<ResultRow> expectedResults = Arrays.asList(makeRow(query, "2011-04-01", "alias", "automotive", "rows", 1L, "idx", 135L), makeRow(query, "2011-04-01", "alias", "business", "rows", 1L, "idx", 118L), makeRow(query, "2011-04-01", "alias", "entertainment", "rows", 1L, "idx", 158L), makeRow(query, "2011-04-01", "alias", "health", "rows", 1L, "idx", 120L), 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", 3L, "idx", 2900L), makeRow(query, "2011-04-01", "alias", "technology", "rows", 1L, "idx", 78L), makeRow(query, "2011-04-01", "alias", "travel", "rows", 1L, "idx", 119L), makeRow(query, "2011-04-02", "alias", "automotive", "rows", 1L, "idx", 147L), makeRow(query, "2011-04-02", "alias", "business", "rows", 1L, "idx", 112L), makeRow(query, "2011-04-02", "alias", "entertainment", "rows", 1L, "idx", 166L), makeRow(query, "2011-04-02", "alias", "health", "rows", 1L, "idx", 113L), 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", 3L, "idx", 2505L), makeRow(query, "2011-04-02", "alias", "technology", "rows", 1L, "idx", 97L), makeRow(query, "2011-04-02", "alias", "travel", "rows", 1L, "idx", 126L));
    Iterable<ResultRow> results = GroupByQueryRunnerTestHelper.runQuery(factory, runner, query);
    TestHelper.assertExpectedObjects(expectedResults, results, "dim-extraction");
}