Examples with ExtractionDimensionSpec io.druid.query.dimension.ExtractionDimensionSpec used on opensource projects

Example 6 with ExtractionDimensionSpec

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

the class GroupByQueryRunnerTest method testGroupByWithSimpleRename.

@Test
public void testGroupByWithSimpleRename() {
    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 = GroupByQuery.builder().setDataSource(QueryRunnerTestHelper.dataSource).setQuerySegmentSpec(QueryRunnerTestHelper.firstToThird).setDimensions(Lists.<DimensionSpec>newArrayList(new ExtractionDimensionSpec("quality", "alias", new LookupExtractionFn(new MapLookupExtractor(map, false), false, null, true, false)))).setAggregatorSpecs(Arrays.asList(QueryRunnerTestHelper.rowsCount, new LongSumAggregatorFactory("idx", "index"))).setGranularity(QueryRunnerTestHelper.dayGran).build();
    List<Row> expectedResults = Arrays.asList(GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "alias", "automotive0", "rows", 1L, "idx", 135L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "alias", "business0", "rows", 1L, "idx", 118L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "alias", "entertainment0", "rows", 1L, "idx", 158L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "alias", "health0", "rows", 1L, "idx", 120L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "alias", "mezzanine0", "rows", 3L, "idx", 2870L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "alias", "news0", "rows", 1L, "idx", 121L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "alias", "premium0", "rows", 3L, "idx", 2900L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "alias", "technology0", "rows", 1L, "idx", 78L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "alias", "travel0", "rows", 1L, "idx", 119L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "alias", "automotive0", "rows", 1L, "idx", 147L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "alias", "business0", "rows", 1L, "idx", 112L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "alias", "entertainment0", "rows", 1L, "idx", 166L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "alias", "health0", "rows", 1L, "idx", 113L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "alias", "mezzanine0", "rows", 3L, "idx", 2447L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "alias", "news0", "rows", 1L, "idx", 114L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "alias", "premium0", "rows", 3L, "idx", 2505L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "alias", "technology0", "rows", 1L, "idx", 97L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "alias", "travel0", "rows", 1L, "idx", 126L));
    Iterable<Row> results = GroupByQueryRunnerTestHelper.runQuery(factory, runner, query);
    TestHelper.assertExpectedObjects(expectedResults, results, "");
}

Example 7 with ExtractionDimensionSpec

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

the class GroupByQueryRunnerTest method testGroupByWithNullProducingDimExtractionFn.

@Test
public void testGroupByWithNullProducingDimExtractionFn() {
    final ExtractionFn nullExtractionFn = new RegexDimExtractionFn("(\\w{1})", false, null) {

        @Override
        public byte[] getCacheKey() {
            return new byte[] { (byte) 0xFF };
        }

        @Override
        public String apply(String dimValue) {
            return dimValue.equals("mezzanine") ? null : super.apply(dimValue);
        }
    };
    GroupByQuery query = GroupByQuery.builder().setDataSource(QueryRunnerTestHelper.dataSource).setQuerySegmentSpec(QueryRunnerTestHelper.firstToThird).setAggregatorSpecs(Arrays.asList(QueryRunnerTestHelper.rowsCount, new LongSumAggregatorFactory("idx", "index"))).setGranularity(QueryRunnerTestHelper.dayGran).setDimensions(Lists.<DimensionSpec>newArrayList(new ExtractionDimensionSpec("quality", "alias", nullExtractionFn))).build();
    List<Row> expectedResults = Arrays.asList(GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "alias", null, "rows", 3L, "idx", 2870L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "alias", "a", "rows", 1L, "idx", 135L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "alias", "b", "rows", 1L, "idx", 118L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "alias", "e", "rows", 1L, "idx", 158L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "alias", "h", "rows", 1L, "idx", 120L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "alias", "n", "rows", 1L, "idx", 121L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "alias", "p", "rows", 3L, "idx", 2900L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-01", "alias", "t", "rows", 2L, "idx", 197L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "alias", null, "rows", 3L, "idx", 2447L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "alias", "a", "rows", 1L, "idx", 147L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "alias", "b", "rows", 1L, "idx", 112L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "alias", "e", "rows", 1L, "idx", 166L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "alias", "h", "rows", 1L, "idx", 113L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "alias", "n", "rows", 1L, "idx", 114L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "alias", "p", "rows", 3L, "idx", 2505L), GroupByQueryRunnerTestHelper.createExpectedRow("2011-04-02", "alias", "t", "rows", 2L, "idx", 223L));
    TestHelper.assertExpectedObjects(expectedResults, GroupByQueryRunnerTestHelper.runQuery(factory, runner, query), "");
}

Example 8 with ExtractionDimensionSpec

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

the class SearchQueryRunnerTest method testSearchOnTime.

@Test
public void testSearchOnTime() {
    SearchQuery searchQuery = Druids.newSearchQueryBuilder().dataSource(QueryRunnerTestHelper.dataSource).granularity(QueryRunnerTestHelper.allGran).intervals(QueryRunnerTestHelper.fullOnInterval).query("Friday").dimensions(new ExtractionDimensionSpec(Column.TIME_COLUMN_NAME, "__time2", new TimeFormatExtractionFn("EEEE", null, null, null, false))).build();
    List<SearchHit> expectedHits = Lists.newLinkedList();
    expectedHits.add(new SearchHit("__time2", "Friday", 169));
    checkSearchQuery(searchQuery, expectedHits);
}

Example 9 with ExtractionDimensionSpec

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

the class SelectQueryRunnerTest method testFullOnSelectWithLongAndFloatWithExFn.

@Test
public void testFullOnSelectWithLongAndFloatWithExFn() {
    String jsFn = "function(str) { return 'super-' + str; }";
    ExtractionFn jsExtractionFn = new JavaScriptExtractionFn(jsFn, false, JavaScriptConfig.getEnabledInstance());
    List<DimensionSpec> dimSpecs = Arrays.<DimensionSpec>asList(new ExtractionDimensionSpec(QueryRunnerTestHelper.indexMetric, "floatIndex", jsExtractionFn), new ExtractionDimensionSpec(Column.TIME_COLUMN_NAME, "longTime", jsExtractionFn));
    SelectQuery query = newTestQuery().dimensionSpecs(dimSpecs).metrics(Arrays.asList(Column.TIME_COLUMN_NAME, "index")).intervals(I_0112_0114).build();
    HashMap<String, Object> context = new HashMap<String, Object>();
    Iterable<Result<SelectResultValue>> results = Sequences.toList(runner.run(query, context), Lists.<Result<SelectResultValue>>newArrayList());
    List<Result<SelectResultValue>> expectedResultsAsc = Arrays.asList(new Result<SelectResultValue>(new DateTime("2011-01-12T00:00:00.000Z"), new SelectResultValue(ImmutableMap.of(QueryRunnerTestHelper.segmentId, 2), Sets.newHashSet("null_column", "floatIndex", "longTime"), Sets.newHashSet("__time", "index"), Arrays.asList(new EventHolder(QueryRunnerTestHelper.segmentId, 0, new ImmutableMap.Builder<String, Object>().put(EventHolder.timestampKey, new DateTime("2011-01-12T00:00:00.000Z")).put("longTime", "super-1294790400000").put("floatIndex", "super-100").put(QueryRunnerTestHelper.indexMetric, 100.000000F).put(Column.TIME_COLUMN_NAME, 1294790400000L).build()), new EventHolder(QueryRunnerTestHelper.segmentId, 1, new ImmutableMap.Builder<String, Object>().put(EventHolder.timestampKey, new DateTime("2011-01-12T00:00:00.000Z")).put("longTime", "super-1294790400000").put("floatIndex", "super-100").put(QueryRunnerTestHelper.indexMetric, 100.000000F).put(Column.TIME_COLUMN_NAME, 1294790400000L).build()), new EventHolder(QueryRunnerTestHelper.segmentId, 2, new ImmutableMap.Builder<String, Object>().put(EventHolder.timestampKey, new DateTime("2011-01-12T00:00:00.000Z")).put("longTime", "super-1294790400000").put("floatIndex", "super-100").put(QueryRunnerTestHelper.indexMetric, 100.000000F).put(Column.TIME_COLUMN_NAME, 1294790400000L).build())))));
    List<Result<SelectResultValue>> expectedResultsDsc = Arrays.asList(new Result<SelectResultValue>(new DateTime("2011-01-12T00:00:00.000Z"), new SelectResultValue(ImmutableMap.of(QueryRunnerTestHelper.segmentId, -3), Sets.newHashSet("null_column", "floatIndex", "longTime"), Sets.newHashSet("__time", "index"), Arrays.asList(new EventHolder(QueryRunnerTestHelper.segmentId, -1, new ImmutableMap.Builder<String, Object>().put(EventHolder.timestampKey, new DateTime("2011-01-13T00:00:00.000Z")).put("longTime", "super-1294876800000").put("floatIndex", "super-1564.61767578125").put(QueryRunnerTestHelper.indexMetric, 1564.6177f).put(Column.TIME_COLUMN_NAME, 1294876800000L).build()), new EventHolder(QueryRunnerTestHelper.segmentId, -2, new ImmutableMap.Builder<String, Object>().put(EventHolder.timestampKey, new DateTime("2011-01-13T00:00:00.000Z")).put("longTime", "super-1294876800000").put("floatIndex", "super-826.0601806640625").put(QueryRunnerTestHelper.indexMetric, 826.0602f).put(Column.TIME_COLUMN_NAME, 1294876800000L).build()), new EventHolder(QueryRunnerTestHelper.segmentId, -3, new ImmutableMap.Builder<String, Object>().put(EventHolder.timestampKey, new DateTime("2011-01-13T00:00:00.000Z")).put("longTime", "super-1294876800000").put("floatIndex", "super-1689.0128173828125").put(QueryRunnerTestHelper.indexMetric, 1689.0128f).put(Column.TIME_COLUMN_NAME, 1294876800000L).build())))));
    verify(descending ? expectedResultsDsc : expectedResultsAsc, populateNullColumnAtLastForQueryableIndexCase(results, "null_column"));
}

Example 10 with ExtractionDimensionSpec

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

the class SelectQueryRunnerTest method testFullOnSelectWithDimensionSpec.

@Test
public void testFullOnSelectWithDimensionSpec() {
    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");
    SelectQuery query = newTestQuery().dimensionSpecs(Arrays.<DimensionSpec>asList(new DefaultDimensionSpec(QueryRunnerTestHelper.marketDimension, "mar"), new ExtractionDimensionSpec(QueryRunnerTestHelper.qualityDimension, "qual", new LookupExtractionFn(new MapLookupExtractor(map, true), false, null, true, false)), new DefaultDimensionSpec(QueryRunnerTestHelper.placementDimension, "place"))).build();
    HashMap<String, Object> context = new HashMap<String, Object>();
    Iterable<Result<SelectResultValue>> results = Sequences.toList(runner.run(query, context), Lists.<Result<SelectResultValue>>newArrayList());
    List<Result<SelectResultValue>> expectedResultsAsc = Arrays.asList(new Result<SelectResultValue>(new DateTime("2011-01-12T00:00:00.000Z"), new SelectResultValue(ImmutableMap.of(QueryRunnerTestHelper.segmentId, 2), Sets.newHashSet("mar", "qual", "place"), Sets.newHashSet("index", "quality_uniques", "indexMin", "indexMaxPlusTen"), Arrays.asList(new EventHolder(QueryRunnerTestHelper.segmentId, 0, new ImmutableMap.Builder<String, Object>().put(EventHolder.timestampKey, new DateTime("2011-01-12T00:00:00.000Z")).put("mar", "spot").put("qual", "automotive0").put("place", "preferred").put(QueryRunnerTestHelper.indexMetric, 100.000000F).build()), new EventHolder(QueryRunnerTestHelper.segmentId, 1, new ImmutableMap.Builder<String, Object>().put(EventHolder.timestampKey, new DateTime("2011-01-12T00:00:00.000Z")).put("mar", "spot").put("qual", "business0").put("place", "preferred").put(QueryRunnerTestHelper.indexMetric, 100.000000F).build()), new EventHolder(QueryRunnerTestHelper.segmentId, 2, new ImmutableMap.Builder<String, Object>().put(EventHolder.timestampKey, new DateTime("2011-01-12T00:00:00.000Z")).put("mar", "spot").put("qual", "entertainment0").put("place", "preferred").put(QueryRunnerTestHelper.indexMetric, 100.000000F).build())))));
    List<Result<SelectResultValue>> expectedResultsDsc = Arrays.asList(new Result<SelectResultValue>(new DateTime("2011-01-12T00:00:00.000Z"), new SelectResultValue(ImmutableMap.of(QueryRunnerTestHelper.segmentId, -3), Sets.newHashSet("mar", "qual", "place"), Sets.newHashSet("index", "quality_uniques", "indexMin", "indexMaxPlusTen"), Arrays.asList(new EventHolder(QueryRunnerTestHelper.segmentId, -1, new ImmutableMap.Builder<String, Object>().put(EventHolder.timestampKey, new DateTime("2011-04-15T00:00:00.000Z")).put("mar", "upfront").put("qual", "premium0").put("place", "preferred").put(QueryRunnerTestHelper.indexMetric, 780.27197265625F).build()), new EventHolder(QueryRunnerTestHelper.segmentId, -2, new ImmutableMap.Builder<String, Object>().put(EventHolder.timestampKey, new DateTime("2011-04-15T00:00:00.000Z")).put("mar", "upfront").put("qual", "mezzanine0").put("place", "preferred").put(QueryRunnerTestHelper.indexMetric, 962.731201171875F).build()), new EventHolder(QueryRunnerTestHelper.segmentId, -3, new ImmutableMap.Builder<String, Object>().put(EventHolder.timestampKey, new DateTime("2011-04-15T00:00:00.000Z")).put("mar", "total_market").put("qual", "premium0").put("place", "preferred").put(QueryRunnerTestHelper.indexMetric, 1029.0570068359375F).build())))));
    verify(descending ? expectedResultsDsc : expectedResultsAsc, results);
}