use of org.apache.druid.query.filter.RegexDimFilter in project druid by druid-io.
the class FilteredAggregatorBenchmark method setup.
/**
* Setup everything common for benchmarking both the incremental-index and the queriable-index.
*/
@Setup
public void setup() {
log.info("SETUP CALLED AT " + System.currentTimeMillis());
ComplexMetrics.registerSerde("hyperUnique", new HyperUniquesSerde());
schemaInfo = GeneratorBasicSchemas.SCHEMA_MAP.get(schema);
generator = new DataGenerator(schemaInfo.getColumnSchemas(), RNG_SEED, schemaInfo.getDataInterval(), rowsPerSegment);
filter = new OrDimFilter(Arrays.asList(new BoundDimFilter("dimSequential", "-1", "-1", true, true, null, null, StringComparators.ALPHANUMERIC), new RegexDimFilter("dimSequential", "X", null), new SearchQueryDimFilter("dimSequential", new ContainsSearchQuerySpec("X", false), null), new InDimFilter("dimSequential", Collections.singletonList("X"), null)));
filteredMetric = new FilteredAggregatorFactory(new CountAggregatorFactory("rows"), filter);
factory = new TimeseriesQueryRunnerFactory(new TimeseriesQueryQueryToolChest(), new TimeseriesQueryEngine(), QueryBenchmarkUtil.NOOP_QUERYWATCHER);
GeneratorSchemaInfo basicSchema = GeneratorBasicSchemas.SCHEMA_MAP.get("basic");
QuerySegmentSpec intervalSpec = new MultipleIntervalSegmentSpec(Collections.singletonList(basicSchema.getDataInterval()));
List<AggregatorFactory> queryAggs = Collections.singletonList(filteredMetric);
query = Druids.newTimeseriesQueryBuilder().dataSource("blah").granularity(Granularities.ALL).intervals(intervalSpec).aggregators(queryAggs).descending(descending).build();
}
use of org.apache.druid.query.filter.RegexDimFilter in project druid by druid-io.
the class IncrementalIndexReadBenchmark method readWithFilters.
@Benchmark
@BenchmarkMode(Mode.AverageTime)
@OutputTimeUnit(TimeUnit.MICROSECONDS)
public void readWithFilters(Blackhole blackhole) {
DimFilter filter = new OrDimFilter(Arrays.asList(new BoundDimFilter("dimSequential", "-1", "-1", true, true, null, null, StringComparators.ALPHANUMERIC), new JavaScriptDimFilter("dimSequential", "function(x) { return false }", null, JavaScriptConfig.getEnabledInstance()), new RegexDimFilter("dimSequential", "X", null), new SearchQueryDimFilter("dimSequential", new ContainsSearchQuerySpec("X", false), null), new InDimFilter("dimSequential", Collections.singletonList("X"), null)));
IncrementalIndexStorageAdapter sa = new IncrementalIndexStorageAdapter(incIndex);
Sequence<Cursor> cursors = makeCursors(sa, filter);
Cursor cursor = cursors.limit(1).toList().get(0);
List<DimensionSelector> selectors = new ArrayList<>();
selectors.add(makeDimensionSelector(cursor, "dimSequential"));
selectors.add(makeDimensionSelector(cursor, "dimZipf"));
selectors.add(makeDimensionSelector(cursor, "dimUniform"));
selectors.add(makeDimensionSelector(cursor, "dimSequentialHalfNull"));
cursor.reset();
while (!cursor.isDone()) {
for (DimensionSelector selector : selectors) {
IndexedInts row = selector.getRow();
blackhole.consume(selector.lookupName(row.get(0)));
}
cursor.advance();
}
}
use of org.apache.druid.query.filter.RegexDimFilter in project druid by druid-io.
the class TimeseriesQueryRunnerTest method testTimeseriesWithRegexFilter.
@Test
public void testTimeseriesWithRegexFilter() {
TimeseriesQuery query = Druids.newTimeseriesQueryBuilder().dataSource(QueryRunnerTestHelper.DATA_SOURCE).granularity(QueryRunnerTestHelper.DAY_GRAN).filters(new RegexDimFilter(QueryRunnerTestHelper.MARKET_DIMENSION, "^.p.*$", null)).intervals(QueryRunnerTestHelper.FIRST_TO_THIRD).aggregators(QueryRunnerTestHelper.ROWS_COUNT, QueryRunnerTestHelper.INDEX_LONG_SUM, QueryRunnerTestHelper.QUALITY_UNIQUES).postAggregators(QueryRunnerTestHelper.ADD_ROWS_INDEX_CONSTANT).descending(descending).context(makeContext()).build();
List<Result<TimeseriesResultValue>> expectedResults = Arrays.asList(new Result<>(DateTimes.of("2011-04-01"), new TimeseriesResultValue(ImmutableMap.of("rows", 11L, "index", 3783L, "addRowsIndexConstant", 3795.0, "uniques", QueryRunnerTestHelper.UNIQUES_9))), new Result<>(DateTimes.of("2011-04-02"), new TimeseriesResultValue(ImmutableMap.of("rows", 11L, "index", 3313L, "addRowsIndexConstant", 3325.0, "uniques", QueryRunnerTestHelper.UNIQUES_9))));
Iterable<Result<TimeseriesResultValue>> results = runner.run(QueryPlus.wrap(query)).toList();
assertExpectedResults(expectedResults, results);
}
use of org.apache.druid.query.filter.RegexDimFilter in project druid by druid-io.
the class TimeFilteringTest method testTimeFilterWithExtractionFn.
@Test
public void testTimeFilterWithExtractionFn() {
final Map<String, String> stringMap = new HashMap<>();
stringMap.put("0", "Monday");
stringMap.put("1", "Tuesday");
stringMap.put("2", "Wednesday");
stringMap.put("3", "Thursday");
stringMap.put("4", "Friday");
stringMap.put("5", "Saturday");
LookupExtractor mapExtractor = new MapLookupExtractor(stringMap, false);
LookupExtractionFn exfn = new LookupExtractionFn(mapExtractor, false, "UNKNOWN", false, true);
assertFilterMatches(new SelectorDimFilter(ColumnHolder.TIME_COLUMN_NAME, "Monday", exfn), ImmutableList.of("0"));
assertFilterMatches(new SelectorDimFilter(ColumnHolder.TIME_COLUMN_NAME, "Notaday", exfn), ImmutableList.of());
assertFilterMatches(new BoundDimFilter(ColumnHolder.TIME_COLUMN_NAME, "Fridax", "Fridaz", false, false, null, exfn, StringComparators.ALPHANUMERIC), ImmutableList.of("4"));
assertFilterMatches(new BoundDimFilter(ColumnHolder.TIME_COLUMN_NAME, "Friday", "Friday", true, true, null, exfn, StringComparators.ALPHANUMERIC), ImmutableList.of());
assertFilterMatches(new InDimFilter(ColumnHolder.TIME_COLUMN_NAME, Arrays.asList("Caturday", "Saturday", "Tuesday"), exfn), ImmutableList.of("1", "5"));
// test InFilter HashSet implementation
List<String> bigList = Arrays.asList("Saturday", "Tuesday", "Caturday", "Xanaday", "Vojuday", "Gribaday", "Kipoday", "Dheferday", "Fakeday", "Qeearaday", "Hello", "World", "1", "2", "3", "4", "5", "6", "7");
assertFilterMatches(new InDimFilter(ColumnHolder.TIME_COLUMN_NAME, bigList, exfn), ImmutableList.of("1", "5"));
String jsFn = "function(x) { return(x === 'Wednesday' || x === 'Thursday') }";
assertFilterMatchesSkipVectorize(new JavaScriptDimFilter(ColumnHolder.TIME_COLUMN_NAME, jsFn, exfn, JavaScriptConfig.getEnabledInstance()), ImmutableList.of("2", "3"));
assertFilterMatches(new RegexDimFilter(ColumnHolder.TIME_COLUMN_NAME, ".*day", exfn), ImmutableList.of("0", "1", "2", "3", "4", "5"));
assertFilterMatches(new SearchQueryDimFilter(ColumnHolder.TIME_COLUMN_NAME, new ContainsSearchQuerySpec("s", true), exfn), ImmutableList.of("1", "2", "3"));
}
use of org.apache.druid.query.filter.RegexDimFilter in project druid by druid-io.
the class TimeFilteringTest method testTimeFilterAsLong.
@Test
public void testTimeFilterAsLong() {
assertFilterMatches(new SelectorDimFilter(ColumnHolder.TIME_COLUMN_NAME, "0", null), ImmutableList.of("0"));
assertFilterMatches(new SelectorDimFilter(ColumnHolder.TIME_COLUMN_NAME, "9000", null), ImmutableList.of());
assertFilterMatches(new BoundDimFilter(ColumnHolder.TIME_COLUMN_NAME, "0", "4", false, false, null, null, StringComparators.NUMERIC), ImmutableList.of("0", "1", "2", "3", "4"));
assertFilterMatches(new BoundDimFilter(ColumnHolder.TIME_COLUMN_NAME, "0", "4", true, true, null, null, StringComparators.NUMERIC), ImmutableList.of("1", "2", "3"));
assertFilterMatches(new InDimFilter(ColumnHolder.TIME_COLUMN_NAME, Arrays.asList("2", "4", "8"), null), ImmutableList.of("2", "4"));
// cross the hashing threshold to test hashset implementation, filter on even values
List<String> infilterValues = new ArrayList<>(NUM_FILTER_VALUES);
for (int i = 0; i < NUM_FILTER_VALUES; i++) {
infilterValues.add(String.valueOf(i * 2));
}
assertFilterMatches(new InDimFilter(ColumnHolder.TIME_COLUMN_NAME, infilterValues, null), ImmutableList.of("0", "2", "4"));
String jsFn = "function(x) { return(x === 3 || x === 5) }";
assertFilterMatchesSkipVectorize(new JavaScriptDimFilter(ColumnHolder.TIME_COLUMN_NAME, jsFn, null, JavaScriptConfig.getEnabledInstance()), ImmutableList.of("3", "5"));
assertFilterMatches(new RegexDimFilter(ColumnHolder.TIME_COLUMN_NAME, "4", null), ImmutableList.of("4"));
assertFilterMatches(new SearchQueryDimFilter(ColumnHolder.TIME_COLUMN_NAME, new ContainsSearchQuerySpec("2", true), null), ImmutableList.of("2"));
}
Aggregations