use of org.apache.druid.data.input.impl.DimensionsSpec in project druid by druid-io.
the class KafkaInputFormatTest method testTimestampFromHeader.
@Test
public void testTimestampFromHeader() throws IOException {
Iterable<Header> sample_header_with_ts = Iterables.unmodifiableIterable(Iterables.concat(SAMPLE_HEADERS, ImmutableList.of(new Header() {
@Override
public String key() {
return "headerTs";
}
@Override
public byte[] value() {
return "2021-06-24".getBytes(StandardCharsets.UTF_8);
}
})));
final byte[] key = StringUtils.toUtf8("{\n" + " \"key\": \"sampleKey\"\n" + "}");
final byte[] payload = StringUtils.toUtf8("{\n" + " \"timestamp\": \"2021-06-24\",\n" + " \"bar\": null,\n" + " \"foo\": \"x\",\n" + " \"baz\": 4,\n" + " \"o\": {\n" + " \"mg\": 1\n" + " }\n" + "}");
Headers headers = new RecordHeaders(sample_header_with_ts);
inputEntity = new KafkaRecordEntity(new ConsumerRecord<byte[], byte[]>("sample", 0, 0, timestamp, null, null, 0, 0, key, payload, headers));
final InputEntityReader reader = format.createReader(new InputRowSchema(new TimestampSpec("kafka.newheader.headerTs", "iso", null), new DimensionsSpec(DimensionsSpec.getDefaultSchemas(ImmutableList.of("bar", "foo", "kafka.newheader.encoding", "kafka.newheader.kafkapkc"))), ColumnsFilter.all()), inputEntity, null);
final int numExpectedIterations = 1;
try (CloseableIterator<InputRow> iterator = reader.read()) {
int numActualIterations = 0;
while (iterator.hasNext()) {
final InputRow row = iterator.next();
final MapBasedInputRow mrow = (MapBasedInputRow) row;
// Payload verifications
Assert.assertEquals(DateTimes.of("2021-06-24"), row.getTimestamp());
Assert.assertEquals("x", Iterables.getOnlyElement(row.getDimension("foo")));
Assert.assertEquals("4", Iterables.getOnlyElement(row.getDimension("baz")));
Assert.assertEquals("4", Iterables.getOnlyElement(row.getDimension("root_baz")));
Assert.assertEquals("1", Iterables.getOnlyElement(row.getDimension("path_omg")));
Assert.assertEquals("1", Iterables.getOnlyElement(row.getDimension("jq_omg")));
// Header verification
Assert.assertEquals("application/json", Iterables.getOnlyElement(row.getDimension("kafka.newheader.encoding")));
Assert.assertEquals("pkc-bar", Iterables.getOnlyElement(row.getDimension("kafka.newheader.kafkapkc")));
Assert.assertEquals(String.valueOf(DateTimes.of("2021-06-24").getMillis()), Iterables.getOnlyElement(row.getDimension("kafka.newts.timestamp")));
Assert.assertEquals("2021-06-24", Iterables.getOnlyElement(row.getDimension("kafka.newheader.headerTs")));
Assert.assertEquals("2021-06-24", Iterables.getOnlyElement(row.getDimension("timestamp")));
// Key verification
Assert.assertEquals("sampleKey", Iterables.getOnlyElement(row.getDimension("kafka.newkey.key")));
Assert.assertTrue(row.getDimension("root_baz2").isEmpty());
Assert.assertTrue(row.getDimension("path_omg2").isEmpty());
Assert.assertTrue(row.getDimension("jq_omg2").isEmpty());
Assert.assertTrue(row.getDimension("jq_omg2").isEmpty());
numActualIterations++;
}
Assert.assertEquals(numExpectedIterations, numActualIterations);
}
}
use of org.apache.druid.data.input.impl.DimensionsSpec in project druid by druid-io.
the class KafkaIndexTaskTest method testKafkaInputFormat.
@Test(timeout = 60_000L)
public void testKafkaInputFormat() throws Exception {
// Insert data
insertData(Iterables.limit(records, 3));
final KafkaIndexTask task = createTask(null, new DataSchema("test_ds", new TimestampSpec("timestamp", "iso", null), new DimensionsSpec(Arrays.asList(new StringDimensionSchema("dim1"), new StringDimensionSchema("dim1t"), new StringDimensionSchema("dim2"), new LongDimensionSchema("dimLong"), new FloatDimensionSchema("dimFloat"), new StringDimensionSchema("kafka.testheader.encoding"))), new AggregatorFactory[] { new DoubleSumAggregatorFactory("met1sum", "met1"), new CountAggregatorFactory("rows") }, new UniformGranularitySpec(Granularities.DAY, Granularities.NONE, null), null), new KafkaIndexTaskIOConfig(0, "sequence0", new SeekableStreamStartSequenceNumbers<>(topic, ImmutableMap.of(0, 0L), ImmutableSet.of()), new SeekableStreamEndSequenceNumbers<>(topic, ImmutableMap.of(0, 5L)), kafkaServer.consumerProperties(), KafkaSupervisorIOConfig.DEFAULT_POLL_TIMEOUT_MILLIS, true, null, null, KAFKA_INPUT_FORMAT));
Assert.assertTrue(task.supportsQueries());
final ListenableFuture<TaskStatus> future = runTask(task);
while (countEvents(task) != 3) {
Thread.sleep(25);
}
Assert.assertEquals(Status.READING, task.getRunner().getStatus());
final QuerySegmentSpec interval = OBJECT_MAPPER.readValue("\"2008/2012\"", QuerySegmentSpec.class);
List<ScanResultValue> scanResultValues = scanData(task, interval);
// verify that there are no records indexed in the rollbacked time period
Assert.assertEquals(3, Iterables.size(scanResultValues));
int i = 0;
for (ScanResultValue result : scanResultValues) {
final Map<String, Object> event = ((List<Map<String, Object>>) result.getEvents()).get(0);
Assert.assertEquals("application/json", event.get("kafka.testheader.encoding"));
Assert.assertEquals("y", event.get("dim2"));
}
// insert remaining data
insertData(Iterables.skip(records, 3));
// Wait for task to exit
Assert.assertEquals(TaskState.SUCCESS, future.get().getStatusCode());
// Check metrics
Assert.assertEquals(4, task.getRunner().getRowIngestionMeters().getProcessed());
Assert.assertEquals(0, task.getRunner().getRowIngestionMeters().getUnparseable());
Assert.assertEquals(0, task.getRunner().getRowIngestionMeters().getThrownAway());
}
use of org.apache.druid.data.input.impl.DimensionsSpec in project druid by druid-io.
the class KafkaSupervisorTest method getDataSchema.
private static DataSchema getDataSchema(String dataSource) {
List<DimensionSchema> dimensions = new ArrayList<>();
dimensions.add(StringDimensionSchema.create("dim1"));
dimensions.add(StringDimensionSchema.create("dim2"));
return new DataSchema(dataSource, new TimestampSpec("timestamp", "iso", null), new DimensionsSpec(dimensions), new AggregatorFactory[] { new CountAggregatorFactory("rows") }, new UniformGranularitySpec(Granularities.HOUR, Granularities.NONE, ImmutableList.of()), null);
}
use of org.apache.druid.data.input.impl.DimensionsSpec in project druid by druid-io.
the class OrcReaderTest method testOrcFile11Format.
// This test is migrated from OrcHadoopInputRowParserTest
@Test
public void testOrcFile11Format() throws IOException {
final OrcInputFormat inputFormat = new OrcInputFormat(new JSONPathSpec(true, ImmutableList.of(new JSONPathFieldSpec(JSONPathFieldType.PATH, "struct_list_struct_int", "$.middle.list[1].int1"), new JSONPathFieldSpec(JSONPathFieldType.PATH, "struct_list_struct_intlist", "$.middle.list[*].int1"), new JSONPathFieldSpec(JSONPathFieldType.PATH, "struct_list_struct_middleListLength", "$.middle.list.length()"), new JSONPathFieldSpec(JSONPathFieldType.PATH, "list_struct_string", "$.list[0].string1"), new JSONPathFieldSpec(JSONPathFieldType.PATH, "map_struct_int", "$.map.chani.int1"))), null, new Configuration());
final InputEntityReader reader = createReader(new TimestampSpec("ts", "millis", null), new DimensionsSpec(null), inputFormat, "example/orc-file-11-format.orc");
try (CloseableIterator<InputRow> iterator = reader.read()) {
int actualRowCount = 0;
// Check the first row
Assert.assertTrue(iterator.hasNext());
InputRow row = iterator.next();
actualRowCount++;
Assert.assertEquals("false", Iterables.getOnlyElement(row.getDimension("boolean1")));
Assert.assertEquals("1", Iterables.getOnlyElement(row.getDimension("byte1")));
Assert.assertEquals("1024", Iterables.getOnlyElement(row.getDimension("short1")));
Assert.assertEquals("65536", Iterables.getOnlyElement(row.getDimension("int1")));
Assert.assertEquals("9223372036854775807", Iterables.getOnlyElement(row.getDimension("long1")));
Assert.assertEquals("1.0", Iterables.getOnlyElement(row.getDimension("float1")));
Assert.assertEquals("-15.0", Iterables.getOnlyElement(row.getDimension("double1")));
Assert.assertEquals("AAECAwQAAA==", Iterables.getOnlyElement(row.getDimension("bytes1")));
Assert.assertEquals("hi", Iterables.getOnlyElement(row.getDimension("string1")));
Assert.assertEquals("1.23456786547456E7", Iterables.getOnlyElement(row.getDimension("decimal1")));
Assert.assertEquals("2", Iterables.getOnlyElement(row.getDimension("struct_list_struct_int")));
Assert.assertEquals(ImmutableList.of("1", "2"), row.getDimension("struct_list_struct_intlist"));
Assert.assertEquals("good", Iterables.getOnlyElement(row.getDimension("list_struct_string")));
Assert.assertEquals("2", Iterables.getOnlyElement(row.getDimension("struct_list_struct_middleListLength")));
Assert.assertEquals(DateTimes.of("2000-03-12T15:00:00.0Z"), row.getTimestamp());
while (iterator.hasNext()) {
actualRowCount++;
row = iterator.next();
}
// Check the last row
Assert.assertEquals("true", Iterables.getOnlyElement(row.getDimension("boolean1")));
Assert.assertEquals("100", Iterables.getOnlyElement(row.getDimension("byte1")));
Assert.assertEquals("2048", Iterables.getOnlyElement(row.getDimension("short1")));
Assert.assertEquals("65536", Iterables.getOnlyElement(row.getDimension("int1")));
Assert.assertEquals("9223372036854775807", Iterables.getOnlyElement(row.getDimension("long1")));
Assert.assertEquals("2.0", Iterables.getOnlyElement(row.getDimension("float1")));
Assert.assertEquals("-5.0", Iterables.getOnlyElement(row.getDimension("double1")));
Assert.assertEquals("", Iterables.getOnlyElement(row.getDimension("bytes1")));
Assert.assertEquals("bye", Iterables.getOnlyElement(row.getDimension("string1")));
Assert.assertEquals("1.23456786547457E7", Iterables.getOnlyElement(row.getDimension("decimal1")));
Assert.assertEquals("2", Iterables.getOnlyElement(row.getDimension("struct_list_struct_int")));
Assert.assertEquals(ImmutableList.of("1", "2"), row.getDimension("struct_list_struct_intlist"));
Assert.assertEquals("cat", Iterables.getOnlyElement(row.getDimension("list_struct_string")));
Assert.assertEquals("5", Iterables.getOnlyElement(row.getDimension("map_struct_int")));
Assert.assertEquals(DateTimes.of("2000-03-12T15:00:01.000Z"), row.getTimestamp());
Assert.assertEquals(7500, actualRowCount);
}
}
use of org.apache.druid.data.input.impl.DimensionsSpec in project druid by druid-io.
the class OrcReaderTest method testTest2.
// This test is migrated from OrcHadoopInputRowParserTest
@Test
public void testTest2() throws IOException {
final InputFormat inputFormat = new OrcInputFormat(new JSONPathSpec(true, Collections.singletonList(new JSONPathFieldSpec(JSONPathFieldType.PATH, "col7-subcol7", "$.col7.subcol7"))), null, new Configuration());
final InputEntityReader reader = createReader(new TimestampSpec("timestamp", "auto", null), new DimensionsSpec(null), inputFormat, "example/test_2.orc");
try (CloseableIterator<InputRow> iterator = reader.read()) {
Assert.assertTrue(iterator.hasNext());
final InputRow row = iterator.next();
Assert.assertEquals(DateTimes.of("2016-01-01T00:00:00.000Z"), row.getTimestamp());
Assert.assertEquals("bar", Iterables.getOnlyElement(row.getDimension("col1")));
Assert.assertEquals(ImmutableList.of("dat1", "dat2", "dat3"), row.getDimension("col2"));
Assert.assertEquals("1.1", Iterables.getOnlyElement(row.getDimension("col3")));
Assert.assertEquals("2", Iterables.getOnlyElement(row.getDimension("col4")));
Assert.assertEquals("3.5", Iterables.getOnlyElement(row.getDimension("col5")));
Assert.assertTrue(row.getDimension("col6").isEmpty());
Assert.assertFalse(iterator.hasNext());
}
}
Aggregations