Search in sources :

Example 16 with JSONParseSpec

use of org.apache.druid.data.input.impl.JSONParseSpec in project druid by druid-io.

the class ProtobufParserBenchmark method setup.

@Setup
public void setup() {
    nestedParseSpec = new JSONParseSpec(new TimestampSpec("timestamp", "iso", null), new DimensionsSpec(Lists.newArrayList(new StringDimensionSchema("event"), new StringDimensionSchema("id"), new StringDimensionSchema("someOtherId"), new StringDimensionSchema("isValid"))), new JSONPathSpec(true, Lists.newArrayList(new JSONPathFieldSpec(JSONPathFieldType.ROOT, "eventType", "eventType"), new JSONPathFieldSpec(JSONPathFieldType.PATH, "foobar", "$.foo.bar"), new JSONPathFieldSpec(JSONPathFieldType.PATH, "bar0", "$.bar[0].bar"))), null, null);
    flatParseSpec = new JSONParseSpec(new TimestampSpec("timestamp", "iso", null), new DimensionsSpec(Lists.newArrayList(new StringDimensionSchema("event"), new StringDimensionSchema("id"), new StringDimensionSchema("someOtherId"), new StringDimensionSchema("isValid"))), null, null, null);
    decoder = new FileBasedProtobufBytesDecoder("prototest.desc", "ProtoTestEvent");
    protoFilePath = "ProtoFile";
    protoInputs = getProtoInputs(protoFilePath);
    nestedParser = new ProtobufInputRowParser(nestedParseSpec, decoder, null, null);
    flatParser = new ProtobufInputRowParser(flatParseSpec, decoder, null, null);
}
Also used : ProtobufInputRowParser(org.apache.druid.data.input.protobuf.ProtobufInputRowParser) TimestampSpec(org.apache.druid.data.input.impl.TimestampSpec) DimensionsSpec(org.apache.druid.data.input.impl.DimensionsSpec) JSONPathSpec(org.apache.druid.java.util.common.parsers.JSONPathSpec) FileBasedProtobufBytesDecoder(org.apache.druid.data.input.protobuf.FileBasedProtobufBytesDecoder) JSONPathFieldSpec(org.apache.druid.java.util.common.parsers.JSONPathFieldSpec) JSONParseSpec(org.apache.druid.data.input.impl.JSONParseSpec) StringDimensionSchema(org.apache.druid.data.input.impl.StringDimensionSchema) Setup(org.openjdk.jmh.annotations.Setup)

Example 17 with JSONParseSpec

use of org.apache.druid.data.input.impl.JSONParseSpec in project druid by druid-io.

the class IndexTaskTest method testMultipleParseExceptionsSuccess.

@Test
public void testMultipleParseExceptionsSuccess() throws Exception {
    final File tmpDir = temporaryFolder.newFolder();
    final File tmpFile = File.createTempFile("druid", "index", tmpDir);
    try (BufferedWriter writer = Files.newWriter(tmpFile, StandardCharsets.UTF_8)) {
        // unparseable time
        writer.write("{\"time\":\"unparseable\",\"dim\":\"a\",\"dimLong\":2,\"dimFloat\":3.0,\"val\":1}\n");
        // valid row
        writer.write("{\"time\":\"2014-01-01T00:00:10Z\",\"dim\":\"a\",\"dimLong\":2,\"dimFloat\":3.0,\"val\":1}\n");
        writer.write(// row with invalid long dimension
        "{\"time\":\"2014-01-01T00:00:10Z\",\"dim\":\"b\",\"dimLong\":\"notnumber\",\"dimFloat\":3.0,\"val\":1}\n");
        writer.write(// row with invalid float dimension
        "{\"time\":\"2014-01-01T00:00:10Z\",\"dim\":\"b\",\"dimLong\":2,\"dimFloat\":\"notnumber\",\"val\":1}\n");
        writer.write(// row with invalid metric
        "{\"time\":\"2014-01-01T00:00:10Z\",\"dim\":\"b\",\"dimLong\":2,\"dimFloat\":4.0,\"val\":\"notnumber\"}\n");
        // invalid JSON
        writer.write("{\"time\":9.0x,\"dim\":\"a\",\"dimLong\":2,\"dimFloat\":3.0,\"val\":1}\n");
        writer.write(// thrown away
        "{\"time\":\"3014-03-01T00:00:10Z\",\"dim\":\"outsideofinterval\",\"dimLong\":2,\"dimFloat\":3.0,\"val\":1}\n");
        // unparseable time
        writer.write("{\"time\":\"99999999999-01-01T00:00:10Z\",\"dim\":\"b\",\"dimLong\":2,\"dimFloat\":3.0,\"val\":1}\n");
        // invalid JSON
        writer.write("this is not JSON\n");
    }
    final IndexTuningConfig tuningConfig = new IndexTuningConfig(null, null, null, null, null, null, null, null, null, null, new HashedPartitionsSpec(2, null, null), INDEX_SPEC, null, null, true, false, null, null, null, true, 7, 7, null, null);
    final TimestampSpec timestampSpec = new TimestampSpec("time", "auto", null);
    final DimensionsSpec dimensionsSpec = new DimensionsSpec(Arrays.asList(new StringDimensionSchema("dim"), new LongDimensionSchema("dimLong"), new FloatDimensionSchema("dimFloat")));
    final IndexIngestionSpec ingestionSpec;
    if (useInputFormatApi) {
        ingestionSpec = createIngestionSpec(jsonMapper, tmpDir, timestampSpec, dimensionsSpec, new JsonInputFormat(null, null, null), null, null, tuningConfig, false, false);
    } else {
        ingestionSpec = createIngestionSpec(jsonMapper, tmpDir, new JSONParseSpec(timestampSpec, dimensionsSpec, null, null, null), null, null, tuningConfig, false, false);
    }
    IndexTask indexTask = new IndexTask(null, null, ingestionSpec, null);
    TaskStatus status = runTask(indexTask).lhs;
    Assert.assertEquals(TaskState.SUCCESS, status.getStatusCode());
    Assert.assertEquals(null, status.getErrorMsg());
    IngestionStatsAndErrorsTaskReportData reportData = getTaskReportData();
    Map<String, Object> expectedMetrics = ImmutableMap.of(RowIngestionMeters.DETERMINE_PARTITIONS, ImmutableMap.of(RowIngestionMeters.PROCESSED_WITH_ERROR, 0, RowIngestionMeters.PROCESSED, 4, RowIngestionMeters.UNPARSEABLE, 4, RowIngestionMeters.THROWN_AWAY, 1), RowIngestionMeters.BUILD_SEGMENTS, ImmutableMap.of(RowIngestionMeters.PROCESSED_WITH_ERROR, 3, RowIngestionMeters.PROCESSED, 1, RowIngestionMeters.UNPARSEABLE, 4, RowIngestionMeters.THROWN_AWAY, 1));
    Assert.assertEquals(expectedMetrics, reportData.getRowStats());
    List<LinkedHashMap> parseExceptionReports = (List<LinkedHashMap>) reportData.getUnparseableEvents().get(RowIngestionMeters.BUILD_SEGMENTS);
    List<String> expectedMessages;
    if (useInputFormatApi) {
        expectedMessages = Arrays.asList(StringUtils.format("Unable to parse row [this is not JSON] (Path: %s, Record: 6, Line: 9)", tmpFile.toURI()), StringUtils.format("Timestamp[99999999999-01-01T00:00:10Z] is unparseable! Event: {time=99999999999-01-01T00:00:10Z, dim=b, dimLong=2, dimFloat=3.0, val=1} (Path: %s, Record: 6, Line: 8)", tmpFile.toURI()), StringUtils.format("Unable to parse row [{\"time\":9.0x,\"dim\":\"a\",\"dimLong\":2,\"dimFloat\":3.0,\"val\":1}] (Path: %s, Record: 5, Line: 6)", tmpFile.toURI()), "Unable to parse value[notnumber] for field[val]", "could not convert value [notnumber] to float", "could not convert value [notnumber] to long", StringUtils.format("Timestamp[unparseable] is unparseable! Event: {time=unparseable, dim=a, dimLong=2, dimFloat=3.0, val=1} (Path: %s, Record: 1, Line: 1)", tmpFile.toURI()));
    } else {
        expectedMessages = Arrays.asList("Unable to parse row [this is not JSON]", "Timestamp[99999999999-01-01T00:00:10Z] is unparseable! Event: {time=99999999999-01-01T00:00:10Z, dim=b, dimLong=2, dimFloat=3.0, val=1}", "Unable to parse row [{\"time\":9.0x,\"dim\":\"a\",\"dimLong\":2,\"dimFloat\":3.0,\"val\":1}]", "Unable to parse value[notnumber] for field[val]", "could not convert value [notnumber] to float", "could not convert value [notnumber] to long", "Timestamp[unparseable] is unparseable! Event: {time=unparseable, dim=a, dimLong=2, dimFloat=3.0, val=1}");
    }
    List<String> actualMessages = parseExceptionReports.stream().map((r) -> {
        return ((List<String>) r.get("details")).get(0);
    }).collect(Collectors.toList());
    Assert.assertEquals(expectedMessages, actualMessages);
    List<String> expectedInputs = Arrays.asList("this is not JSON", "{time=99999999999-01-01T00:00:10Z, dim=b, dimLong=2, dimFloat=3.0, val=1}", "{\"time\":9.0x,\"dim\":\"a\",\"dimLong\":2,\"dimFloat\":3.0,\"val\":1}", "{time=2014-01-01T00:00:10Z, dim=b, dimLong=2, dimFloat=4.0, val=notnumber}", "{time=2014-01-01T00:00:10Z, dim=b, dimLong=2, dimFloat=notnumber, val=1}", "{time=2014-01-01T00:00:10Z, dim=b, dimLong=notnumber, dimFloat=3.0, val=1}", "{time=unparseable, dim=a, dimLong=2, dimFloat=3.0, val=1}");
    List<String> actualInputs = parseExceptionReports.stream().map((r) -> {
        return (String) r.get("input");
    }).collect(Collectors.toList());
    Assert.assertEquals(expectedInputs, actualInputs);
    parseExceptionReports = (List<LinkedHashMap>) reportData.getUnparseableEvents().get(RowIngestionMeters.DETERMINE_PARTITIONS);
    if (useInputFormatApi) {
        expectedMessages = Arrays.asList(StringUtils.format("Unable to parse row [this is not JSON] (Path: %s, Record: 6, Line: 9)", tmpFile.toURI()), StringUtils.format("Timestamp[99999999999-01-01T00:00:10Z] is unparseable! Event: {time=99999999999-01-01T00:00:10Z, dim=b, dimLong=2, dimFloat=3.0, val=1} (Path: %s, Record: 6, Line: 8)", tmpFile.toURI()), StringUtils.format("Unable to parse row [{\"time\":9.0x,\"dim\":\"a\",\"dimLong\":2,\"dimFloat\":3.0,\"val\":1}] (Path: %s, Record: 5, Line: 6)", tmpFile.toURI()), StringUtils.format("Timestamp[unparseable] is unparseable! Event: {time=unparseable, dim=a, dimLong=2, dimFloat=3.0, val=1} (Path: %s, Record: 1, Line: 1)", tmpFile.toURI()));
    } else {
        expectedMessages = Arrays.asList("Unable to parse row [this is not JSON]", "Timestamp[99999999999-01-01T00:00:10Z] is unparseable! Event: {time=99999999999-01-01T00:00:10Z, dim=b, dimLong=2, dimFloat=3.0, val=1}", "Unable to parse row [{\"time\":9.0x,\"dim\":\"a\",\"dimLong\":2,\"dimFloat\":3.0,\"val\":1}]", "Timestamp[unparseable] is unparseable! Event: {time=unparseable, dim=a, dimLong=2, dimFloat=3.0, val=1}");
    }
    actualMessages = parseExceptionReports.stream().map((r) -> {
        return ((List<String>) r.get("details")).get(0);
    }).collect(Collectors.toList());
    Assert.assertEquals(expectedMessages, actualMessages);
    expectedInputs = Arrays.asList("this is not JSON", "{time=99999999999-01-01T00:00:10Z, dim=b, dimLong=2, dimFloat=3.0, val=1}", "{\"time\":9.0x,\"dim\":\"a\",\"dimLong\":2,\"dimFloat\":3.0,\"val\":1}", "{time=unparseable, dim=a, dimLong=2, dimFloat=3.0, val=1}");
    actualInputs = parseExceptionReports.stream().map((r) -> {
        return (String) r.get("input");
    }).collect(Collectors.toList());
    Assert.assertEquals(expectedInputs, actualInputs);
}
Also used : TaskReport(org.apache.druid.indexing.common.TaskReport) TaskToolbox(org.apache.druid.indexing.common.TaskToolbox) Arrays(java.util.Arrays) IndexSpec(org.apache.druid.segment.IndexSpec) Pair(org.apache.druid.java.util.common.Pair) Map(java.util.Map) ExpressionTransform(org.apache.druid.segment.transform.ExpressionTransform) AppenderatorsManager(org.apache.druid.segment.realtime.appenderator.AppenderatorsManager) JsonInputFormat(org.apache.druid.data.input.impl.JsonInputFormat) IAE(org.apache.druid.java.util.common.IAE) InputFormat(org.apache.druid.data.input.InputFormat) IngestionStatsAndErrorsTaskReportData(org.apache.druid.indexing.common.IngestionStatsAndErrorsTaskReportData) Set(java.util.Set) NoopSegmentHandoffNotifierFactory(org.apache.druid.segment.realtime.plumber.NoopSegmentHandoffNotifierFactory) EqualsVerifier(nl.jqno.equalsverifier.EqualsVerifier) StringDimensionSchema(org.apache.druid.data.input.impl.StringDimensionSchema) StandardCharsets(java.nio.charset.StandardCharsets) TaskState(org.apache.druid.indexer.TaskState) CountDownLatch(java.util.concurrent.CountDownLatch) PartitionIds(org.apache.druid.timeline.partition.PartitionIds) IndexTuningConfig(org.apache.druid.indexing.common.task.IndexTask.IndexTuningConfig) RowIngestionMetersFactory(org.apache.druid.segment.incremental.RowIngestionMetersFactory) SegmentLocalCacheManager(org.apache.druid.segment.loading.SegmentLocalCacheManager) SegmentId(org.apache.druid.timeline.SegmentId) TransformSpec(org.apache.druid.segment.transform.TransformSpec) Granularity(org.apache.druid.java.util.common.granularity.Granularity) SegmentLoaderConfig(org.apache.druid.segment.loading.SegmentLoaderConfig) HashBasedNumberedShardSpec(org.apache.druid.timeline.partition.HashBasedNumberedShardSpec) RunWith(org.junit.runner.RunWith) TaskStatus(org.apache.druid.indexer.TaskStatus) ArrayList(java.util.ArrayList) LinkedHashMap(java.util.LinkedHashMap) Interval(org.joda.time.Interval) StringInputRowParser(org.apache.druid.data.input.impl.StringInputRowParser) PartitionsSpec(org.apache.druid.indexer.partitions.PartitionsSpec) Nullable(javax.annotation.Nullable) HashPartitionFunction(org.apache.druid.timeline.partition.HashPartitionFunction) Before(org.junit.Before) BufferedWriter(java.io.BufferedWriter) GranularitySpec(org.apache.druid.segment.indexing.granularity.GranularitySpec) DimensionsSpec(org.apache.druid.data.input.impl.DimensionsSpec) Test(org.junit.Test) IOException(java.io.IOException) EasyMock(org.easymock.EasyMock) File(java.io.File) Preconditions(com.google.common.base.Preconditions) Assert(org.junit.Assert) DataSchema(org.apache.druid.segment.indexing.DataSchema) CoreMatchers(org.hamcrest.CoreMatchers) ArbitraryGranularitySpec(org.apache.druid.segment.indexing.granularity.ArbitraryGranularitySpec) IndexIOConfig(org.apache.druid.indexing.common.task.IndexTask.IndexIOConfig) LocalInputSource(org.apache.druid.data.input.impl.LocalInputSource) LongDimensionSchema(org.apache.druid.data.input.impl.LongDimensionSchema) TimestampSpec(org.apache.druid.data.input.impl.TimestampSpec) DefaultDimensionSpec(org.apache.druid.query.dimension.DefaultDimensionSpec) CSVParseSpec(org.apache.druid.data.input.impl.CSVParseSpec) LongSumAggregatorFactory(org.apache.druid.query.aggregation.LongSumAggregatorFactory) SelectorDimFilter(org.apache.druid.query.filter.SelectorDimFilter) Event(org.apache.druid.java.util.emitter.core.Event) DynamicPartitionsSpec(org.apache.druid.indexer.partitions.DynamicPartitionsSpec) TypeReference(com.fasterxml.jackson.core.type.TypeReference) Parameterized(org.junit.runners.Parameterized) ParseSpec(org.apache.druid.data.input.impl.ParseSpec) Sequence(org.apache.druid.java.util.common.guava.Sequence) ShardSpec(org.apache.druid.timeline.partition.ShardSpec) LocalFirehoseFactory(org.apache.druid.segment.realtime.firehose.LocalFirehoseFactory) ImmutableMap(com.google.common.collect.ImmutableMap) AggregatorFactory(org.apache.druid.query.aggregation.AggregatorFactory) NumberedShardSpec(org.apache.druid.timeline.partition.NumberedShardSpec) StringUtils(org.apache.druid.java.util.common.StringUtils) CsvInputFormat(org.apache.druid.data.input.impl.CsvInputFormat) HashedPartitionsSpec(org.apache.druid.indexer.partitions.HashedPartitionsSpec) Collectors(java.util.stream.Collectors) Sets(com.google.common.collect.Sets) LockGranularity(org.apache.druid.indexing.common.LockGranularity) ExprMacroTable(org.apache.druid.math.expr.ExprMacroTable) IndexIngestionSpec(org.apache.druid.indexing.common.task.IndexTask.IndexIngestionSpec) List(java.util.List) UniformGranularitySpec(org.apache.druid.segment.indexing.granularity.UniformGranularitySpec) ServiceEmitter(org.apache.druid.java.util.emitter.service.ServiceEmitter) DataSegment(org.apache.druid.timeline.DataSegment) SegmentHandoffNotifierFactory(org.apache.druid.segment.handoff.SegmentHandoffNotifierFactory) SegmentAllocateAction(org.apache.druid.indexing.common.actions.SegmentAllocateAction) Intervals(org.apache.druid.java.util.common.Intervals) HashMap(java.util.HashMap) RowIngestionMeters(org.apache.druid.segment.incremental.RowIngestionMeters) HashSet(java.util.HashSet) ImmutableList(com.google.common.collect.ImmutableList) FloatDimensionSchema(org.apache.druid.data.input.impl.FloatDimensionSchema) Files(com.google.common.io.Files) NumberedOverwriteShardSpec(org.apache.druid.timeline.partition.NumberedOverwriteShardSpec) DimensionSelector(org.apache.druid.segment.DimensionSelector) ExpectedException(org.junit.rules.ExpectedException) SegmentHandoffNotifier(org.apache.druid.segment.handoff.SegmentHandoffNotifier) NoopServiceEmitter(org.apache.druid.server.metrics.NoopServiceEmitter) QueryableIndexStorageAdapter(org.apache.druid.segment.QueryableIndexStorageAdapter) VirtualColumns(org.apache.druid.segment.VirtualColumns) WindowedStorageAdapter(org.apache.druid.segment.realtime.firehose.WindowedStorageAdapter) ObjectMapper(com.fasterxml.jackson.databind.ObjectMapper) JSONParseSpec(org.apache.druid.data.input.impl.JSONParseSpec) StorageLocationConfig(org.apache.druid.segment.loading.StorageLocationConfig) Granularities(org.apache.druid.java.util.common.granularity.Granularities) TimeUnit(java.util.concurrent.TimeUnit) Rule(org.junit.Rule) SingleDimensionPartitionsSpec(org.apache.druid.indexer.partitions.SingleDimensionPartitionsSpec) Cursor(org.apache.druid.segment.Cursor) SegmentCacheManager(org.apache.druid.segment.loading.SegmentCacheManager) IndexIO(org.apache.druid.segment.IndexIO) Collections(java.util.Collections) TemporaryFolder(org.junit.rules.TemporaryFolder) HashedPartitionsSpec(org.apache.druid.indexer.partitions.HashedPartitionsSpec) IngestionStatsAndErrorsTaskReportData(org.apache.druid.indexing.common.IngestionStatsAndErrorsTaskReportData) LongDimensionSchema(org.apache.druid.data.input.impl.LongDimensionSchema) FloatDimensionSchema(org.apache.druid.data.input.impl.FloatDimensionSchema) TaskStatus(org.apache.druid.indexer.TaskStatus) BufferedWriter(java.io.BufferedWriter) StringDimensionSchema(org.apache.druid.data.input.impl.StringDimensionSchema) LinkedHashMap(java.util.LinkedHashMap) IndexIngestionSpec(org.apache.druid.indexing.common.task.IndexTask.IndexIngestionSpec) JsonInputFormat(org.apache.druid.data.input.impl.JsonInputFormat) TimestampSpec(org.apache.druid.data.input.impl.TimestampSpec) DimensionsSpec(org.apache.druid.data.input.impl.DimensionsSpec) ArrayList(java.util.ArrayList) List(java.util.List) ImmutableList(com.google.common.collect.ImmutableList) File(java.io.File) JSONParseSpec(org.apache.druid.data.input.impl.JSONParseSpec) IndexTuningConfig(org.apache.druid.indexing.common.task.IndexTask.IndexTuningConfig) Test(org.junit.Test)

Example 18 with JSONParseSpec

use of org.apache.druid.data.input.impl.JSONParseSpec in project druid by druid-io.

the class IndexGeneratorJobTest method constructFeed.

@Parameterized.Parameters(name = "useCombiner={0}, partitionType={1}, interval={2}, shardInfoForEachSegment={3}, " + "data={4}, inputFormatName={5}, inputRowParser={6}, maxRowsInMemory={7}, " + "maxBytesInMemory={8}, aggs={9}, datasourceName={10}, forceExtendableShardSpecs={11}")
public static Collection<Object[]> constructFeed() {
    final Object[][] baseConstructors = new Object[][] { { false, "single", "2014-10-22T00:00:00Z/P2D", new String[][][] { { { null, "c.example.com" }, { "c.example.com", "e.example.com" }, { "e.example.com", "g.example.com" }, { "g.example.com", "i.example.com" }, { "i.example.com", null } }, { { null, "c.example.com" }, { "c.example.com", "e.example.com" }, { "e.example.com", "g.example.com" }, { "g.example.com", "i.example.com" }, { "i.example.com", null } } }, ImmutableList.of("2014102200,a.example.com,100", "2014102200,b.exmaple.com,50", "2014102200,c.example.com,200", "2014102200,d.example.com,250", "2014102200,e.example.com,123", "2014102200,f.example.com,567", "2014102200,g.example.com,11", "2014102200,h.example.com,251", "2014102200,i.example.com,963", "2014102200,j.example.com,333", "2014102300,a.example.com,100", "2014102300,b.exmaple.com,50", "2014102300,c.example.com,200", "2014102300,d.example.com,250", "2014102300,e.example.com,123", "2014102300,f.example.com,567", "2014102300,g.example.com,11", "2014102300,h.example.com,251", "2014102300,i.example.com,963", "2014102300,j.example.com,333"), null, new StringInputRowParser(new CSVParseSpec(new TimestampSpec("timestamp", "yyyyMMddHH", null), new DimensionsSpec(DimensionsSpec.getDefaultSchemas(ImmutableList.of("host"))), null, ImmutableList.of("timestamp", "host", "visited_num"), false, 0), null), null, null, AGGS1, "website" }, { false, "hashed", "2014-10-22T00:00:00Z/P1D", new Integer[][][] { { { 0, 4 }, { 1, 4 }, { 2, 4 }, { 3, 4 } } }, ImmutableList.of("2014102200,a.example.com,100", "2014102201,b.exmaple.com,50", "2014102202,c.example.com,200", "2014102203,d.example.com,250", "2014102204,e.example.com,123", "2014102205,f.example.com,567", "2014102206,g.example.com,11", "2014102207,h.example.com,251", "2014102208,i.example.com,963", "2014102209,j.example.com,333", "2014102210,k.example.com,253", "2014102211,l.example.com,321", "2014102212,m.example.com,3125", "2014102213,n.example.com,234", "2014102214,o.example.com,325", "2014102215,p.example.com,3533", "2014102216,q.example.com,500", "2014102216,q.example.com,87"), null, new HadoopyStringInputRowParser(new CSVParseSpec(new TimestampSpec("timestamp", "yyyyMMddHH", null), new DimensionsSpec(DimensionsSpec.getDefaultSchemas(ImmutableList.of("host"))), null, ImmutableList.of("timestamp", "host", "visited_num"), false, 0)), null, null, AGGS1, "website" }, { true, "hashed", "2014-10-22T00:00:00Z/P1D", new Integer[][][] { { { 0, 4 }, { 1, 4 }, { 2, 4 }, { 3, 4 } } }, ImmutableList.of("2014102200,a.example.com,100", "2014102201,b.exmaple.com,50", "2014102202,c.example.com,200", "2014102203,d.example.com,250", "2014102204,e.example.com,123", "2014102205,f.example.com,567", "2014102206,g.example.com,11", "2014102207,h.example.com,251", "2014102208,i.example.com,963", "2014102209,j.example.com,333", "2014102210,k.example.com,253", "2014102211,l.example.com,321", "2014102212,m.example.com,3125", "2014102213,n.example.com,234", "2014102214,o.example.com,325", "2014102215,p.example.com,3533", "2014102216,q.example.com,500", "2014102216,q.example.com,87"), null, new StringInputRowParser(new CSVParseSpec(new TimestampSpec("timestamp", "yyyyMMddHH", null), new DimensionsSpec(DimensionsSpec.getDefaultSchemas(ImmutableList.of("host"))), null, ImmutableList.of("timestamp", "host", "visited_num"), false, 0), null), null, null, AGGS1, "website" }, { false, "single", "2014-10-22T00:00:00Z/P2D", new String[][][] { { { null, "c.example.com" }, { "c.example.com", "e.example.com" }, { "e.example.com", "g.example.com" }, { "g.example.com", "i.example.com" }, { "i.example.com", null } }, { { null, "c.example.com" }, { "c.example.com", "e.example.com" }, { "e.example.com", "g.example.com" }, { "g.example.com", "i.example.com" }, { "i.example.com", null } } }, ImmutableList.of("2014102200,a.example.com,100", "2014102200,b.exmaple.com,50", "2014102200,c.example.com,200", "2014102200,d.example.com,250", "2014102200,e.example.com,123", "2014102200,f.example.com,567", "2014102200,g.example.com,11", "2014102200,h.example.com,251", "2014102200,i.example.com,963", "2014102200,j.example.com,333", "2014102300,a.example.com,100", "2014102300,b.exmaple.com,50", "2014102300,c.example.com,200", "2014102300,d.example.com,250", "2014102300,e.example.com,123", "2014102300,f.example.com,567", "2014102300,g.example.com,11", "2014102300,h.example.com,251", "2014102300,i.example.com,963", "2014102300,j.example.com,333"), SequenceFileInputFormat.class.getName(), new HadoopyStringInputRowParser(new CSVParseSpec(new TimestampSpec("timestamp", "yyyyMMddHH", null), new DimensionsSpec(DimensionsSpec.getDefaultSchemas(ImmutableList.of("host"))), null, ImmutableList.of("timestamp", "host", "visited_num"), false, 0)), null, null, AGGS1, "website" }, { // Tests that new indexes inherit the dimension order from previous index
    false, "hashed", "2014-10-22T00:00:00Z/P1D", new Integer[][][] { { // use a single partition, dimension order inheritance is not supported across partitions
    { 0, 1 } } }, ImmutableList.of("{\"ts\":\"2014102200\", \"X\":\"x.example.com\"}", "{\"ts\":\"2014102201\", \"Y\":\"y.example.com\"}", "{\"ts\":\"2014102202\", \"M\":\"m.example.com\"}", "{\"ts\":\"2014102203\", \"Q\":\"q.example.com\"}", "{\"ts\":\"2014102204\", \"B\":\"b.example.com\"}", "{\"ts\":\"2014102205\", \"F\":\"f.example.com\"}"), null, new StringInputRowParser(new JSONParseSpec(new TimestampSpec("ts", "yyyyMMddHH", null), DimensionsSpec.EMPTY, null, null, null), null), // force 1 row max per index for easier testing
    1, null, AGGS2, "inherit_dims" }, { // Tests that pre-specified dim order is maintained across indexes.
    false, "hashed", "2014-10-22T00:00:00Z/P1D", new Integer[][][] { { { 0, 1 } } }, ImmutableList.of("{\"ts\":\"2014102200\", \"X\":\"x.example.com\"}", "{\"ts\":\"2014102201\", \"Y\":\"y.example.com\"}", "{\"ts\":\"2014102202\", \"M\":\"m.example.com\"}", "{\"ts\":\"2014102203\", \"Q\":\"q.example.com\"}", "{\"ts\":\"2014102204\", \"B\":\"b.example.com\"}", "{\"ts\":\"2014102205\", \"F\":\"f.example.com\"}"), null, new StringInputRowParser(new JSONParseSpec(new TimestampSpec("ts", "yyyyMMddHH", null), new DimensionsSpec(DimensionsSpec.getDefaultSchemas(ImmutableList.of("B", "F", "M", "Q", "X", "Y"))), null, null, null), null), // force 1 row max per index for easier testing
    1, null, AGGS2, "inherit_dims2" } };
    // Run each baseConstructor with/without forceExtendableShardSpecs.
    final List<Object[]> constructors = new ArrayList<>();
    for (Object[] baseConstructor : baseConstructors) {
        for (int forceExtendableShardSpecs = 0; forceExtendableShardSpecs < 2; forceExtendableShardSpecs++) {
            final Object[] fullConstructor = new Object[baseConstructor.length + 1];
            System.arraycopy(baseConstructor, 0, fullConstructor, 0, baseConstructor.length);
            fullConstructor[baseConstructor.length] = forceExtendableShardSpecs == 0;
            constructors.add(fullConstructor);
        }
    }
    return constructors;
}
Also used : SequenceFileInputFormat(org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFormat) ArrayList(java.util.ArrayList) CSVParseSpec(org.apache.druid.data.input.impl.CSVParseSpec) StringInputRowParser(org.apache.druid.data.input.impl.StringInputRowParser) TimestampSpec(org.apache.druid.data.input.impl.TimestampSpec) DimensionsSpec(org.apache.druid.data.input.impl.DimensionsSpec) JSONParseSpec(org.apache.druid.data.input.impl.JSONParseSpec)

Example 19 with JSONParseSpec

use of org.apache.druid.data.input.impl.JSONParseSpec in project druid by druid-io.

the class StreamChunkParserTest method testBothParserAndInputFormatParseProperlyUsingInputFormat.

@Test
public void testBothParserAndInputFormatParseProperlyUsingInputFormat() throws IOException {
    final InputRowParser<ByteBuffer> parser = new StringInputRowParser(new JSONParseSpec(TIMESTAMP_SPEC, DimensionsSpec.EMPTY, JSONPathSpec.DEFAULT, Collections.emptyMap(), false), StringUtils.UTF8_STRING);
    final TrackingJsonInputFormat inputFormat = new TrackingJsonInputFormat(JSONPathSpec.DEFAULT, Collections.emptyMap());
    final StreamChunkParser<ByteEntity> chunkParser = new StreamChunkParser<>(parser, inputFormat, new InputRowSchema(TIMESTAMP_SPEC, DimensionsSpec.EMPTY, ColumnsFilter.all()), TransformSpec.NONE, temporaryFolder.newFolder(), row -> true, rowIngestionMeters, parseExceptionHandler);
    parseAndAssertResult(chunkParser);
    Assert.assertTrue(inputFormat.props.used);
}
Also used : ByteEntity(org.apache.druid.data.input.impl.ByteEntity) StringInputRowParser(org.apache.druid.data.input.impl.StringInputRowParser) InputRowSchema(org.apache.druid.data.input.InputRowSchema) ByteBuffer(java.nio.ByteBuffer) JSONParseSpec(org.apache.druid.data.input.impl.JSONParseSpec) Test(org.junit.Test)

Example 20 with JSONParseSpec

use of org.apache.druid.data.input.impl.JSONParseSpec in project druid by druid-io.

the class RealtimePlumberSchoolTest method setUp.

@Before
public void setUp() throws Exception {
    tmpDir = FileUtils.createTempDir();
    ObjectMapper jsonMapper = new DefaultObjectMapper();
    schema = new DataSchema("test", jsonMapper.convertValue(new StringInputRowParser(new JSONParseSpec(new TimestampSpec("timestamp", "auto", null), DimensionsSpec.EMPTY, null, null, null), null), Map.class), new AggregatorFactory[] { new CountAggregatorFactory("rows") }, new UniformGranularitySpec(Granularities.HOUR, Granularities.NONE, null), null, jsonMapper);
    schema2 = new DataSchema("test", jsonMapper.convertValue(new StringInputRowParser(new JSONParseSpec(new TimestampSpec("timestamp", "auto", null), DimensionsSpec.EMPTY, null, null, null), null), Map.class), new AggregatorFactory[] { new CountAggregatorFactory("rows") }, new UniformGranularitySpec(Granularities.YEAR, Granularities.NONE, null), null, jsonMapper);
    announcer = EasyMock.createMock(DataSegmentAnnouncer.class);
    announcer.announceSegment(EasyMock.anyObject());
    EasyMock.expectLastCall().anyTimes();
    segmentPublisher = EasyMock.createNiceMock(SegmentPublisher.class);
    dataSegmentPusher = EasyMock.createNiceMock(DataSegmentPusher.class);
    handoffNotifierFactory = EasyMock.createNiceMock(SegmentHandoffNotifierFactory.class);
    handoffNotifier = EasyMock.createNiceMock(SegmentHandoffNotifier.class);
    EasyMock.expect(handoffNotifierFactory.createSegmentHandoffNotifier(EasyMock.anyString())).andReturn(handoffNotifier).anyTimes();
    EasyMock.expect(handoffNotifier.registerSegmentHandoffCallback(EasyMock.anyObject(), EasyMock.anyObject(), EasyMock.anyObject())).andReturn(true).anyTimes();
    emitter = EasyMock.createMock(ServiceEmitter.class);
    EasyMock.replay(announcer, segmentPublisher, dataSegmentPusher, handoffNotifierFactory, handoffNotifier, emitter);
    tuningConfig = new RealtimeTuningConfig(null, 1, null, null, null, null, null, new IntervalStartVersioningPolicy(), rejectionPolicy, null, null, null, null, 0, 0, false, null, null, null, null);
    realtimePlumberSchool = new RealtimePlumberSchool(emitter, new DefaultQueryRunnerFactoryConglomerate(new HashMap<>()), dataSegmentPusher, announcer, segmentPublisher, handoffNotifierFactory, DirectQueryProcessingPool.INSTANCE, NoopJoinableFactory.INSTANCE, TestHelper.getTestIndexMergerV9(segmentWriteOutMediumFactory), TestHelper.getTestIndexIO(), MapCache.create(0), FireDepartmentTest.NO_CACHE_CONFIG, new CachePopulatorStats(), TestHelper.makeJsonMapper());
    metrics = new FireDepartmentMetrics();
    plumber = (RealtimePlumber) realtimePlumberSchool.findPlumber(schema, tuningConfig, metrics);
}
Also used : ServiceEmitter(org.apache.druid.java.util.emitter.service.ServiceEmitter) DataSegmentPusher(org.apache.druid.segment.loading.DataSegmentPusher) DataSegmentAnnouncer(org.apache.druid.server.coordination.DataSegmentAnnouncer) SegmentHandoffNotifier(org.apache.druid.segment.handoff.SegmentHandoffNotifier) DefaultQueryRunnerFactoryConglomerate(org.apache.druid.query.DefaultQueryRunnerFactoryConglomerate) AggregatorFactory(org.apache.druid.query.aggregation.AggregatorFactory) CountAggregatorFactory(org.apache.druid.query.aggregation.CountAggregatorFactory) RealtimeTuningConfig(org.apache.druid.segment.indexing.RealtimeTuningConfig) SegmentHandoffNotifierFactory(org.apache.druid.segment.handoff.SegmentHandoffNotifierFactory) DataSchema(org.apache.druid.segment.indexing.DataSchema) UniformGranularitySpec(org.apache.druid.segment.indexing.granularity.UniformGranularitySpec) SegmentPublisher(org.apache.druid.segment.realtime.SegmentPublisher) FireDepartmentMetrics(org.apache.druid.segment.realtime.FireDepartmentMetrics) CountAggregatorFactory(org.apache.druid.query.aggregation.CountAggregatorFactory) CachePopulatorStats(org.apache.druid.client.cache.CachePopulatorStats) StringInputRowParser(org.apache.druid.data.input.impl.StringInputRowParser) TimestampSpec(org.apache.druid.data.input.impl.TimestampSpec) DefaultObjectMapper(org.apache.druid.jackson.DefaultObjectMapper) JSONParseSpec(org.apache.druid.data.input.impl.JSONParseSpec) ObjectMapper(com.fasterxml.jackson.databind.ObjectMapper) DefaultObjectMapper(org.apache.druid.jackson.DefaultObjectMapper) Before(org.junit.Before)

Aggregations

JSONParseSpec (org.apache.druid.data.input.impl.JSONParseSpec)28 TimestampSpec (org.apache.druid.data.input.impl.TimestampSpec)26 StringInputRowParser (org.apache.druid.data.input.impl.StringInputRowParser)16 Test (org.junit.Test)16 DimensionsSpec (org.apache.druid.data.input.impl.DimensionsSpec)13 ArbitraryGranularitySpec (org.apache.druid.segment.indexing.granularity.ArbitraryGranularitySpec)11 IdUtilsTest (org.apache.druid.common.utils.IdUtilsTest)10 DoubleSumAggregatorFactory (org.apache.druid.query.aggregation.DoubleSumAggregatorFactory)10 InitializedNullHandlingTest (org.apache.druid.testing.InitializedNullHandlingTest)10 ArrayList (java.util.ArrayList)7 JSONPathFieldSpec (org.apache.druid.java.util.common.parsers.JSONPathFieldSpec)6 JSONPathSpec (org.apache.druid.java.util.common.parsers.JSONPathSpec)6 Before (org.junit.Before)6 MapInputRowParser (org.apache.druid.data.input.impl.MapInputRowParser)5 DefaultObjectMapper (org.apache.druid.jackson.DefaultObjectMapper)5 ObjectMapper (com.fasterxml.jackson.databind.ObjectMapper)4 CountAggregatorFactory (org.apache.druid.query.aggregation.CountAggregatorFactory)4 CSVParseSpec (org.apache.druid.data.input.impl.CSVParseSpec)3 StringDimensionSchema (org.apache.druid.data.input.impl.StringDimensionSchema)3 AggregatorFactory (org.apache.druid.query.aggregation.AggregatorFactory)3