Examples with ExtractionDimFilter io.druid.query.filter.ExtractionDimFilter used on opensource projects

Example 6 with ExtractionDimFilter

use of io.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 = GroupByQuery.builder().setDataSource(QueryRunnerTestHelper.dataSource).setQuerySegmentSpec(QueryRunnerTestHelper.firstToThird).setDimensions(Lists.<DimensionSpec>newArrayList(new DefaultDimensionSpec("quality", "alias"))).setAggregatorSpecs(Arrays.asList(new FilteredAggregatorFactory(QueryRunnerTestHelper.rowsCount, filter), (AggregatorFactory) new FilteredAggregatorFactory(new LongSumAggregatorFactory("idx", "index"), filter))).setGranularity(QueryRunnerTestHelper.dayGran).build();
    List<Row> expectedResults = Arrays.asList(GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "alias", "automotive", "rows", 0L, "idx", 0L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "alias", "business", "rows", 0L, "idx", 0L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "alias", "entertainment", "rows", 0L, "idx", 0L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "alias", "health", "rows", 0L, "idx", 0L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "alias", "mezzanine", "rows", 3L, "idx", 2870L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "alias", "news", "rows", 1L, "idx", 121L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "alias", "premium", "rows", 0L, "idx", 0L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "alias", "technology", "rows", 0L, "idx", 0L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "alias", "travel", "rows", 0L, "idx", 0L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "alias", "automotive", "rows", 0L, "idx", 0L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "alias", "business", "rows", 0L, "idx", 0L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "alias", "entertainment", "rows", 0L, "idx", 0L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "alias", "health", "rows", 0L, "idx", 0L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "alias", "mezzanine", "rows", 3L, "idx", 2447L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "alias", "news", "rows", 1L, "idx", 114L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "alias", "premium", "rows", 0L, "idx", 0L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "alias", "technology", "rows", 0L, "idx", 0L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "alias", "travel", "rows", 0L, "idx", 0L));
    Iterable<Row> results = GroupByQueryRunnerTestHelper.runQuery(factory, runner, query);
    TestHelper.assertExpectedObjects(expectedResults, results, "");
}

Example 7 with ExtractionDimFilter

use of io.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 = GroupByQuery.builder().setDataSource(QueryRunnerTestHelper.dataSource).setQuerySegmentSpec(QueryRunnerTestHelper.firstToThird).setDimensions(Lists.<DimensionSpec>newArrayList(new DefaultDimensionSpec("quality", "alias"))).setAggregatorSpecs(Arrays.asList(QueryRunnerTestHelper.rowsCount, new LongSumAggregatorFactory("idx", "index"))).setGranularity(QueryRunnerTestHelper.dayGran).setDimFilter(new ExtractionDimFilter("quality", "", lookupExtractionFn, null)).build();
    List<Row> expectedResults = Arrays.asList(GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "alias", "mezzanine", "rows", 3L, "idx", 2870L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "alias", "news", "rows", 1L, "idx", 121L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "alias", "mezzanine", "rows", 3L, "idx", 2447L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "alias", "news", "rows", 1L, "idx", 114L));
    Iterable<Row> results = GroupByQueryRunnerTestHelper.runQuery(factory, runner, query);
    TestHelper.assertExpectedObjects(expectedResults, results, "");
}

Example 8 with ExtractionDimFilter

use of io.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.dataSource).granularity(QueryRunnerTestHelper.allGran).dimension(QueryRunnerTestHelper.marketDimension).metric("rows").threshold(3).intervals(QueryRunnerTestHelper.firstToThird).aggregators(QueryRunnerTestHelper.commonAggregators).postAggregators(Arrays.<PostAggregator>asList(QueryRunnerTestHelper.addRowsIndexConstant)).filters(new ExtractionDimFilter(QueryRunnerTestHelper.marketDimension, "spot0", lookupExtractionFn, null)).build();
    List<Result<TopNResultValue>> expectedResults = Arrays.asList(new Result<>(new DateTime("2011-04-01T00:00:00.000Z"), new TopNResultValue(Arrays.<Map<String, Object>>asList(ImmutableMap.<String, Object>of(QueryRunnerTestHelper.marketDimension, "spot", "rows", 18L, "index", 2231.8768157958984D, "addRowsIndexConstant", 2250.8768157958984D, "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 9 with ExtractionDimFilter

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

the class TopNQueryRunnerTest method testTopNWithExtractionFilterNoExistingValue.

@Test
public void testTopNWithExtractionFilterNoExistingValue() {
    Map<String, String> extractionMap = new HashMap<>();
    extractionMap.put("", "NULL");
    MapLookupExtractor mapLookupExtractor = new MapLookupExtractor(extractionMap, false);
    LookupExtractionFn lookupExtractionFn = new LookupExtractionFn(mapLookupExtractor, false, null, true, true);
    DimFilter extractionFilter = new ExtractionDimFilter("null_column", "NULL", lookupExtractionFn, null);
    TopNQueryBuilder topNQueryBuilder = new TopNQueryBuilder().dataSource(QueryRunnerTestHelper.dataSource).granularity(QueryRunnerTestHelper.allGran).dimension("null_column").metric(QueryRunnerTestHelper.indexMetric).threshold(4).intervals(QueryRunnerTestHelper.fullOnInterval).aggregators(Lists.newArrayList(Iterables.concat(QueryRunnerTestHelper.commonAggregators, Lists.newArrayList(new FilteredAggregatorFactory(new DoubleMaxAggregatorFactory("maxIndex", "index"), extractionFilter), //new DoubleMaxAggregatorFactory("maxIndex", "index"),
    new DoubleMinAggregatorFactory("minIndex", "index"))))).postAggregators(Arrays.<PostAggregator>asList(QueryRunnerTestHelper.addRowsIndexConstant));
    TopNQuery topNQueryWithNULLValueExtraction = topNQueryBuilder.filters(extractionFilter).build();
    Map<String, Object> map = Maps.newHashMap();
    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", 1870.06103515625D);
    map.put("minIndex", 59.02102279663086D);
    List<Result<TopNResultValue>> expectedResults = Arrays.asList(new Result<>(new DateTime("2011-01-12T00:00:00.000Z"), new TopNResultValue(Arrays.asList(map))));
    assertExpectedResults(expectedResults, topNQueryWithNULLValueExtraction);
    // Assert the optimization path as well
    final Sequence<Result<TopNResultValue>> retval = runWithPreMergeAndMerge(topNQueryWithNULLValueExtraction);
    TestHelper.assertExpectedResults(expectedResults, retval);
}

Example 10 with ExtractionDimFilter

use of io.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<>();
    extractionMap.put("", "NULL");
    MapLookupExtractor mapLookupExtractor = new MapLookupExtractor(extractionMap, false);
    LookupExtractionFn lookupExtractionFn = new LookupExtractionFn(mapLookupExtractor, false, null, true, false);
    DimFilter extractionFilter = new ExtractionDimFilter("null_column", "NULL", lookupExtractionFn, null);
    TopNQueryBuilder topNQueryBuilder = new TopNQueryBuilder().dataSource(QueryRunnerTestHelper.dataSource).granularity(QueryRunnerTestHelper.allGran).dimension("null_column").metric(QueryRunnerTestHelper.indexMetric).threshold(4).intervals(QueryRunnerTestHelper.fullOnInterval).aggregators(Lists.newArrayList(Iterables.concat(QueryRunnerTestHelper.commonAggregators, Lists.newArrayList(new FilteredAggregatorFactory(new DoubleMaxAggregatorFactory("maxIndex", "index"), extractionFilter), new DoubleMinAggregatorFactory("minIndex", "index"))))).postAggregators(Arrays.<PostAggregator>asList(QueryRunnerTestHelper.addRowsIndexConstant));
    TopNQuery topNQueryWithNULLValueExtraction = topNQueryBuilder.filters(extractionFilter).build();
    Map<String, Object> map = Maps.newHashMap();
    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", 1870.06103515625D);
    map.put("minIndex", 59.02102279663086D);
    List<Result<TopNResultValue>> expectedResults = Arrays.asList(new Result<>(new DateTime("2011-01-12T00:00:00.000Z"), new TopNResultValue(Arrays.asList(map))));
    assertExpectedResults(expectedResults, topNQueryWithNULLValueExtraction);
}