Search in sources :

Example 16 with ExtractionDimensionSpec

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

the class TopNQueryRunnerTest method testFullOnTopNLongColumnWithExFn.

@Test
public void testFullOnTopNLongColumnWithExFn() {
    String jsFn = "function(str) { return 'super-' + str; }";
    ExtractionFn jsExtractionFn = new JavaScriptExtractionFn(jsFn, false, JavaScriptConfig.getEnabledInstance());
    TopNQuery query = new TopNQueryBuilder().dataSource(QueryRunnerTestHelper.dataSource).granularity(QueryRunnerTestHelper.allGran).dimension(new ExtractionDimensionSpec("qualityLong", "ql_alias", jsExtractionFn)).metric("maxIndex").threshold(4).intervals(QueryRunnerTestHelper.fullOnInterval).aggregators(Lists.<AggregatorFactory>newArrayList(Iterables.concat(QueryRunnerTestHelper.commonAggregators, Lists.newArrayList(new DoubleMaxAggregatorFactory("maxIndex", "index"), new DoubleMinAggregatorFactory("minIndex", "index"))))).postAggregators(Arrays.<PostAggregator>asList(QueryRunnerTestHelper.addRowsIndexConstant)).build();
    List<Result<TopNResultValue>> expectedResults = Arrays.asList(new Result<TopNResultValue>(new DateTime("2011-01-12T00:00:00.000Z"), new TopNResultValue(Arrays.<Map<String, Object>>asList(ImmutableMap.<String, Object>builder().put("ql_alias", "super-1400").put(QueryRunnerTestHelper.indexMetric, 217725.42022705078D).put("rows", 279L).put("addRowsIndexConstant", 218005.42022705078D).put("uniques", QueryRunnerTestHelper.UNIQUES_1).put("maxIndex", 1870.06103515625D).put("minIndex", 91.27055358886719D).build(), ImmutableMap.<String, Object>builder().put("ql_alias", "super-1600").put(QueryRunnerTestHelper.indexMetric, 210865.67966461182D).put("rows", 279L).put("addRowsIndexConstant", 211145.67966461182D).put("uniques", QueryRunnerTestHelper.UNIQUES_1).put("maxIndex", 1862.7379150390625D).put("minIndex", 99.2845230102539D).build(), ImmutableMap.<String, Object>builder().put("ql_alias", "super-1000").put(QueryRunnerTestHelper.indexMetric, 12270.807106018066D).put("rows", 93L).put("addRowsIndexConstant", 12364.807106018066D).put("uniques", QueryRunnerTestHelper.UNIQUES_1).put("maxIndex", 277.2735290527344D).put("minIndex", 71.31593322753906D).build(), ImmutableMap.<String, Object>builder().put("ql_alias", "super-1200").put(QueryRunnerTestHelper.indexMetric, 12086.472755432129D).put("rows", 93L).put("addRowsIndexConstant", 12180.472755432129D).put("uniques", QueryRunnerTestHelper.UNIQUES_1).put("maxIndex", 193.78756713867188D).put("minIndex", 84.71052551269531D).build()))));
    assertExpectedResults(expectedResults, query);
}
Also used : DoubleMaxAggregatorFactory(io.druid.query.aggregation.DoubleMaxAggregatorFactory) HyperUniqueFinalizingPostAggregator(io.druid.query.aggregation.hyperloglog.HyperUniqueFinalizingPostAggregator) PostAggregator(io.druid.query.aggregation.PostAggregator) JavaScriptExtractionFn(io.druid.query.extraction.JavaScriptExtractionFn) DoubleMinAggregatorFactory(io.druid.query.aggregation.DoubleMinAggregatorFactory) DateTime(org.joda.time.DateTime) Result(io.druid.query.Result) LookupExtractionFn(io.druid.query.lookup.LookupExtractionFn) ExtractionFn(io.druid.query.extraction.ExtractionFn) RegexDimExtractionFn(io.druid.query.extraction.RegexDimExtractionFn) DimExtractionFn(io.druid.query.extraction.DimExtractionFn) StrlenExtractionFn(io.druid.query.extraction.StrlenExtractionFn) JavaScriptExtractionFn(io.druid.query.extraction.JavaScriptExtractionFn) TimeFormatExtractionFn(io.druid.query.extraction.TimeFormatExtractionFn) ExtractionDimensionSpec(io.druid.query.dimension.ExtractionDimensionSpec) Test(org.junit.Test)

Example 17 with ExtractionDimensionSpec

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

the class TopNQueryRunnerTest method testFullOnTopNFloatColumnWithExFn.

@Test
public void testFullOnTopNFloatColumnWithExFn() {
    String jsFn = "function(str) { return 'super-' + str; }";
    ExtractionFn jsExtractionFn = new JavaScriptExtractionFn(jsFn, false, JavaScriptConfig.getEnabledInstance());
    TopNQuery query = new TopNQueryBuilder().dataSource(QueryRunnerTestHelper.dataSource).granularity(QueryRunnerTestHelper.allGran).dimension(new ExtractionDimensionSpec(QueryRunnerTestHelper.indexMetric, "index_alias", jsExtractionFn)).metric(QueryRunnerTestHelper.indexMetric).threshold(4).intervals(QueryRunnerTestHelper.fullOnInterval).aggregators(Lists.<AggregatorFactory>newArrayList(Iterables.concat(QueryRunnerTestHelper.commonAggregators, Lists.newArrayList(new DoubleMaxAggregatorFactory("maxIndex", "index"), new DoubleMinAggregatorFactory("minIndex", "index"))))).postAggregators(Arrays.<PostAggregator>asList(QueryRunnerTestHelper.addRowsIndexConstant)).build();
    List<Result<TopNResultValue>> expectedResults = Arrays.asList(new Result<TopNResultValue>(new DateTime("2011-01-12T00:00:00.000Z"), new TopNResultValue(Arrays.<Map<String, Object>>asList(ImmutableMap.<String, Object>builder().put("index_alias", "super-1000").put(QueryRunnerTestHelper.indexMetric, 2000.0D).put("rows", 2L).put("addRowsIndexConstant", 2003.0D).put("uniques", QueryRunnerTestHelper.UNIQUES_2).put("maxIndex", 1000.0D).put("minIndex", 1000.0D).build(), ImmutableMap.<String, Object>builder().put("index_alias", "super-1870.06103515625").put(QueryRunnerTestHelper.indexMetric, 1870.06103515625D).put("rows", 1L).put("addRowsIndexConstant", 1872.06103515625D).put("uniques", QueryRunnerTestHelper.UNIQUES_1).put("maxIndex", 1870.06103515625D).put("minIndex", 1870.06103515625D).build(), ImmutableMap.<String, Object>builder().put("index_alias", "super-1862.7379150390625").put(QueryRunnerTestHelper.indexMetric, 1862.7379150390625D).put("rows", 1L).put("addRowsIndexConstant", 1864.7379150390625D).put("uniques", QueryRunnerTestHelper.UNIQUES_1).put("maxIndex", 1862.7379150390625D).put("minIndex", 1862.7379150390625D).build(), ImmutableMap.<String, Object>builder().put("index_alias", "super-1743.9217529296875").put(QueryRunnerTestHelper.indexMetric, 1743.9217529296875D).put("rows", 1L).put("addRowsIndexConstant", 1745.9217529296875D).put("uniques", QueryRunnerTestHelper.UNIQUES_1).put("maxIndex", 1743.9217529296875D).put("minIndex", 1743.9217529296875D).build()))));
    assertExpectedResults(expectedResults, query);
}
Also used : DoubleMaxAggregatorFactory(io.druid.query.aggregation.DoubleMaxAggregatorFactory) HyperUniqueFinalizingPostAggregator(io.druid.query.aggregation.hyperloglog.HyperUniqueFinalizingPostAggregator) PostAggregator(io.druid.query.aggregation.PostAggregator) JavaScriptExtractionFn(io.druid.query.extraction.JavaScriptExtractionFn) DoubleMinAggregatorFactory(io.druid.query.aggregation.DoubleMinAggregatorFactory) DateTime(org.joda.time.DateTime) Result(io.druid.query.Result) LookupExtractionFn(io.druid.query.lookup.LookupExtractionFn) ExtractionFn(io.druid.query.extraction.ExtractionFn) RegexDimExtractionFn(io.druid.query.extraction.RegexDimExtractionFn) DimExtractionFn(io.druid.query.extraction.DimExtractionFn) StrlenExtractionFn(io.druid.query.extraction.StrlenExtractionFn) JavaScriptExtractionFn(io.druid.query.extraction.JavaScriptExtractionFn) TimeFormatExtractionFn(io.druid.query.extraction.TimeFormatExtractionFn) ExtractionDimensionSpec(io.druid.query.dimension.ExtractionDimensionSpec) Test(org.junit.Test)

Example 18 with ExtractionDimensionSpec

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

the class TopNQueryRunnerTest method testTopNDimExtractionFastTopNUnOptimal.

@Test
public // Test query path that must rebucket the data
void testTopNDimExtractionFastTopNUnOptimal() {
    TopNQuery query = new TopNQueryBuilder().dataSource(QueryRunnerTestHelper.dataSource).granularity(QueryRunnerTestHelper.allGran).dimension(new ExtractionDimensionSpec(QueryRunnerTestHelper.marketDimension, QueryRunnerTestHelper.marketDimension, new LookupExtractionFn(new MapLookupExtractor(ImmutableMap.of("spot", "spot0", "total_market", "total_market0", "upfront", "upfront0"), false), true, null, false, false))).metric("rows").threshold(4).intervals(QueryRunnerTestHelper.firstToThird).aggregators(QueryRunnerTestHelper.commonAggregators).postAggregators(Arrays.<PostAggregator>asList(QueryRunnerTestHelper.addRowsIndexConstant)).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, "spot0", "rows", 18L, "index", 2231.8768157958984D, "addRowsIndexConstant", 2250.8768157958984D, "uniques", QueryRunnerTestHelper.UNIQUES_9), ImmutableMap.<String, Object>of(QueryRunnerTestHelper.marketDimension, "total_market0", "rows", 4L, "index", 5351.814697265625D, "addRowsIndexConstant", 5356.814697265625D, "uniques", QueryRunnerTestHelper.UNIQUES_2), ImmutableMap.<String, Object>of(QueryRunnerTestHelper.marketDimension, "upfront0", "rows", 4L, "index", 4875.669677734375D, "addRowsIndexConstant", 4880.669677734375D, "uniques", QueryRunnerTestHelper.UNIQUES_2)))));
    assertExpectedResults(expectedResults, query);
}
Also used : HyperUniqueFinalizingPostAggregator(io.druid.query.aggregation.hyperloglog.HyperUniqueFinalizingPostAggregator) PostAggregator(io.druid.query.aggregation.PostAggregator) DateTime(org.joda.time.DateTime) Result(io.druid.query.Result) LookupExtractionFn(io.druid.query.lookup.LookupExtractionFn) MapLookupExtractor(io.druid.query.extraction.MapLookupExtractor) ExtractionDimensionSpec(io.druid.query.dimension.ExtractionDimensionSpec) Test(org.junit.Test)

Example 19 with ExtractionDimensionSpec

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

the class TopNQueryRunnerTest method testTopNLexicographicDimExtractionWithSortingPreservedAndPreviousStop.

@Test
public void testTopNLexicographicDimExtractionWithSortingPreservedAndPreviousStop() {
    TopNQuery query = new TopNQueryBuilder().dataSource(QueryRunnerTestHelper.dataSource).granularity(QueryRunnerTestHelper.allGran).dimension(new ExtractionDimensionSpec(QueryRunnerTestHelper.marketDimension, QueryRunnerTestHelper.marketDimension, new DimExtractionFn() {

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

        @Override
        public String apply(String value) {
            return value.substring(0, 1);
        }

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

        @Override
        public ExtractionType getExtractionType() {
            return ExtractionType.MANY_TO_ONE;
        }
    })).metric(new DimensionTopNMetricSpec("s", StringComparators.LEXICOGRAPHIC)).threshold(4).intervals(QueryRunnerTestHelper.firstToThird).aggregators(QueryRunnerTestHelper.commonAggregators).postAggregators(Arrays.<PostAggregator>asList(QueryRunnerTestHelper.addRowsIndexConstant)).build();
    List<Result<TopNResultValue>> expectedResults = Arrays.asList(new Result<TopNResultValue>(new DateTime("2011-04-01T00:00:00.000Z"), new TopNResultValue(Arrays.<Map<String, Object>>asList(ImmutableMap.<String, Object>of(QueryRunnerTestHelper.marketDimension, "t", "rows", 4L, "index", 5351.814697265625D, "addRowsIndexConstant", 5356.814697265625D, "uniques", QueryRunnerTestHelper.UNIQUES_2), ImmutableMap.<String, Object>of(QueryRunnerTestHelper.marketDimension, "u", "rows", 4L, "index", 4875.669677734375D, "addRowsIndexConstant", 4880.669677734375D, "uniques", QueryRunnerTestHelper.UNIQUES_2)))));
    assertExpectedResults(expectedResults, query);
}
Also used : HyperUniqueFinalizingPostAggregator(io.druid.query.aggregation.hyperloglog.HyperUniqueFinalizingPostAggregator) PostAggregator(io.druid.query.aggregation.PostAggregator) DateTime(org.joda.time.DateTime) Result(io.druid.query.Result) ExtractionDimensionSpec(io.druid.query.dimension.ExtractionDimensionSpec) RegexDimExtractionFn(io.druid.query.extraction.RegexDimExtractionFn) DimExtractionFn(io.druid.query.extraction.DimExtractionFn) Test(org.junit.Test)

Example 20 with ExtractionDimensionSpec

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

the class TopNQueryRunnerTest method testTopNDimExtractionFastTopNUnOptimalWithReplaceMissing.

@Test
public void testTopNDimExtractionFastTopNUnOptimalWithReplaceMissing() {
    TopNQuery query = new TopNQueryBuilder().dataSource(QueryRunnerTestHelper.dataSource).granularity(QueryRunnerTestHelper.allGran).dimension(new ExtractionDimensionSpec(QueryRunnerTestHelper.marketDimension, QueryRunnerTestHelper.marketDimension, new LookupExtractionFn(new MapLookupExtractor(ImmutableMap.of("spot", "2spot0", "total_market", "1total_market0", "upfront", "3upfront0"), false), false, "MISSING", false, false))).metric("rows").threshold(4).intervals(QueryRunnerTestHelper.firstToThird).aggregators(QueryRunnerTestHelper.commonAggregators).postAggregators(Arrays.<PostAggregator>asList(QueryRunnerTestHelper.addRowsIndexConstant)).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, "2spot0", "rows", 18L, "index", 2231.8768157958984D, "addRowsIndexConstant", 2250.8768157958984D, "uniques", QueryRunnerTestHelper.UNIQUES_9), ImmutableMap.<String, Object>of(QueryRunnerTestHelper.marketDimension, "1total_market0", "rows", 4L, "index", 5351.814697265625D, "addRowsIndexConstant", 5356.814697265625D, "uniques", QueryRunnerTestHelper.UNIQUES_2), ImmutableMap.<String, Object>of(QueryRunnerTestHelper.marketDimension, "3upfront0", "rows", 4L, "index", 4875.669677734375D, "addRowsIndexConstant", 4880.669677734375D, "uniques", QueryRunnerTestHelper.UNIQUES_2)))));
    assertExpectedResults(expectedResults, query);
}
Also used : HyperUniqueFinalizingPostAggregator(io.druid.query.aggregation.hyperloglog.HyperUniqueFinalizingPostAggregator) PostAggregator(io.druid.query.aggregation.PostAggregator) DateTime(org.joda.time.DateTime) Result(io.druid.query.Result) LookupExtractionFn(io.druid.query.lookup.LookupExtractionFn) MapLookupExtractor(io.druid.query.extraction.MapLookupExtractor) ExtractionDimensionSpec(io.druid.query.dimension.ExtractionDimensionSpec) Test(org.junit.Test)

Aggregations

ExtractionDimensionSpec (io.druid.query.dimension.ExtractionDimensionSpec)59 Test (org.junit.Test)56 LookupExtractionFn (io.druid.query.lookup.LookupExtractionFn)36 Result (io.druid.query.Result)29 DateTime (org.joda.time.DateTime)29 RegexDimExtractionFn (io.druid.query.extraction.RegexDimExtractionFn)26 PostAggregator (io.druid.query.aggregation.PostAggregator)24 HyperUniqueFinalizingPostAggregator (io.druid.query.aggregation.hyperloglog.HyperUniqueFinalizingPostAggregator)24 TimeFormatExtractionFn (io.druid.query.extraction.TimeFormatExtractionFn)23 JavaScriptExtractionFn (io.druid.query.extraction.JavaScriptExtractionFn)19 DefaultDimensionSpec (io.druid.query.dimension.DefaultDimensionSpec)18 ExtractionFn (io.druid.query.extraction.ExtractionFn)18 MapLookupExtractor (io.druid.query.extraction.MapLookupExtractor)18 Row (io.druid.data.input.Row)17 DimExtractionFn (io.druid.query.extraction.DimExtractionFn)17 LongSumAggregatorFactory (io.druid.query.aggregation.LongSumAggregatorFactory)16 StrlenExtractionFn (io.druid.query.extraction.StrlenExtractionFn)15 DimensionSpec (io.druid.query.dimension.DimensionSpec)13 ListFilteredDimensionSpec (io.druid.query.dimension.ListFilteredDimensionSpec)10 RegexFilteredDimensionSpec (io.druid.query.dimension.RegexFilteredDimensionSpec)10