Search in sources :

Example 6 with QueryResult

use of com.amazonaws.services.timestreamquery.model.QueryResult in project aws-athena-query-federation by awslabs.

the class TimestreamRecordHandler method readWithConstraint.

/**
 * Scans TimeStream.
 *
 * @see RecordHandler
 */
@Override
protected void readWithConstraint(BlockSpiller spiller, ReadRecordsRequest recordsRequest, QueryStatusChecker queryStatusChecker) {
    TableName tableName = recordsRequest.getTableName();
    SelectQueryBuilder queryBuilder = queryFactory.createSelectQueryBuilder(GlueMetadataHandler.VIEW_METADATA_FIELD);
    String query = queryBuilder.withDatabaseName(tableName.getSchemaName()).withTableName(tableName.getTableName()).withProjection(recordsRequest.getSchema()).withConjucts(recordsRequest.getConstraints()).build();
    logger.info("readWithConstraint: query[{}]", query);
    GeneratedRowWriter rowWriter = buildRowWriter(recordsRequest);
    String nextToken = null;
    long numRows = 0;
    do {
        QueryResult queryResult = tsQuery.query(new QueryRequest().withQueryString(query).withNextToken(nextToken));
        List<Row> data = queryResult.getRows();
        if (data != null) {
            numRows += data.size();
            for (Row nextRow : data) {
                spiller.writeRows((Block block, int rowNum) -> rowWriter.writeRow(block, rowNum, nextRow) ? 1 : 0);
            }
        }
        nextToken = queryResult.getNextToken();
        logger.info("readWithConstraint: numRows[{}]", numRows);
    } while (nextToken != null && !nextToken.isEmpty());
}
Also used : TableName(com.amazonaws.athena.connector.lambda.domain.TableName) GeneratedRowWriter(com.amazonaws.athena.connector.lambda.data.writers.GeneratedRowWriter) QueryResult(com.amazonaws.services.timestreamquery.model.QueryResult) QueryRequest(com.amazonaws.services.timestreamquery.model.QueryRequest) SelectQueryBuilder(com.amazonaws.athena.connectors.timestream.query.SelectQueryBuilder) Block(com.amazonaws.athena.connector.lambda.data.Block) Row(com.amazonaws.services.timestreamquery.model.Row)

Example 7 with QueryResult

use of com.amazonaws.services.timestreamquery.model.QueryResult in project amazon-timestream-tools by awslabs.

the class QueryExample method cancelQuery.

public void cancelQuery() {
    System.out.println("Starting query: " + SELECT_ALL_QUERY);
    QueryRequest queryRequest = new QueryRequest();
    queryRequest.setQueryString(SELECT_ALL_QUERY);
    QueryResult queryResult = queryClient.query(queryRequest);
    System.out.println("Cancelling the query: " + SELECT_ALL_QUERY);
    final CancelQueryRequest cancelQueryRequest = new CancelQueryRequest();
    cancelQueryRequest.setQueryId(queryResult.getQueryId());
    try {
        queryClient.cancelQuery(cancelQueryRequest);
        System.out.println("Query has been successfully cancelled");
    } catch (Exception e) {
        System.out.println("Could not cancel the query: " + SELECT_ALL_QUERY + " = " + e);
    }
}
Also used : QueryResult(com.amazonaws.services.timestreamquery.model.QueryResult) QueryRequest(com.amazonaws.services.timestreamquery.model.QueryRequest) CancelQueryRequest(com.amazonaws.services.timestreamquery.model.CancelQueryRequest) CancelQueryRequest(com.amazonaws.services.timestreamquery.model.CancelQueryRequest)

Example 8 with QueryResult

use of com.amazonaws.services.timestreamquery.model.QueryResult in project aws-athena-query-federation by awslabs.

the class TimestreamRecordHandlerTest method readRecordsView.

@Test
public void readRecordsView() throws Exception {
    logger.info("readRecordsView - enter");
    Schema schemaForReadView = SchemaBuilder.newBuilder().addField("measure_name", Types.MinorType.VARCHAR.getType()).addField("az", Types.MinorType.VARCHAR.getType()).addField("value", Types.MinorType.FLOAT8.getType()).addField("num_samples", Types.MinorType.BIGINT.getType()).addMetadata(VIEW_METADATA_FIELD, "select measure_name, az,sum(\"measure_value::double\") as value, count(*) as num_samples from \"" + DEFAULT_SCHEMA + "\".\"" + TEST_TABLE + "\" group by measure_name, az").build();
    String expectedQuery = "WITH t1 AS ( select measure_name, az,sum(\"measure_value::double\") as value, count(*) as num_samples from \"my_schema\".\"my_table\" group by measure_name, az )  SELECT measure_name, az, value, num_samples FROM t1 WHERE (\"az\" IN ('us-east-1a','us-east-1b'))";
    QueryResult mockResult = makeMockQueryResult(schemaForReadView, 1_000);
    when(mockClient.query(any(QueryRequest.class))).thenAnswer((Answer<QueryResult>) invocationOnMock -> {
        QueryRequest request = (QueryRequest) invocationOnMock.getArguments()[0];
        assertEquals(expectedQuery, request.getQueryString().replace("\n", ""));
        return mockResult;
    });
    S3SpillLocation splitLoc = S3SpillLocation.newBuilder().withBucket(UUID.randomUUID().toString()).withSplitId(UUID.randomUUID().toString()).withQueryId(UUID.randomUUID().toString()).withIsDirectory(true).build();
    Split split = Split.newBuilder(splitLoc, null).build();
    Map<String, ValueSet> constraintsMap = new HashMap<>();
    constraintsMap.put("az", EquatableValueSet.newBuilder(allocator, Types.MinorType.VARCHAR.getType(), true, true).add("us-east-1a").add("us-east-1b").build());
    ReadRecordsRequest request = new ReadRecordsRequest(IDENTITY, "default", "queryId-" + System.currentTimeMillis(), new TableName(DEFAULT_SCHEMA, TEST_VIEW), schemaForReadView, split, new Constraints(constraintsMap), // 100GB don't expect this to spill
    100_000_000_000L, 100_000_000_000L);
    RecordResponse rawResponse = handler.doReadRecords(allocator, request);
    ReadRecordsResponse response = (ReadRecordsResponse) rawResponse;
    logger.info("readRecordsView: rows[{}]", response.getRecordCount());
    for (int i = 0; i < response.getRecordCount() && i < 10; i++) {
        logger.info("readRecordsView: {}", BlockUtils.rowToString(response.getRecords(), i));
    }
    logger.info("readRecordsView - exit");
}
Also used : QueryResult(com.amazonaws.services.timestreamquery.model.QueryResult) Schema(org.apache.arrow.vector.types.pojo.Schema) Types(org.apache.arrow.vector.types.Types) LoggerFactory(org.slf4j.LoggerFactory) BlockAllocator(com.amazonaws.athena.connector.lambda.data.BlockAllocator) SpillLocation(com.amazonaws.athena.connector.lambda.domain.spill.SpillLocation) Block(com.amazonaws.athena.connector.lambda.data.Block) ByteArrayInputStream(java.io.ByteArrayInputStream) After(org.junit.After) Map(java.util.Map) ValueSet(com.amazonaws.athena.connector.lambda.domain.predicate.ValueSet) AmazonTimestreamQuery(com.amazonaws.services.timestreamquery.AmazonTimestreamQuery) BlockAllocatorImpl(com.amazonaws.athena.connector.lambda.data.BlockAllocatorImpl) Split(com.amazonaws.athena.connector.lambda.domain.Split) ReadRecordsResponse(com.amazonaws.athena.connector.lambda.records.ReadRecordsResponse) UUID(java.util.UUID) TableName(com.amazonaws.athena.connector.lambda.domain.TableName) RecordResponse(com.amazonaws.athena.connector.lambda.records.RecordResponse) Matchers.any(org.mockito.Matchers.any) List(java.util.List) ByteStreams(com.google.common.io.ByteStreams) BlockUtils(com.amazonaws.athena.connector.lambda.data.BlockUtils) S3ObjectInputStream(com.amazonaws.services.s3.model.S3ObjectInputStream) EncryptionKeyFactory(com.amazonaws.athena.connector.lambda.security.EncryptionKeyFactory) Mockito.mock(org.mockito.Mockito.mock) Mock(org.mockito.Mock) EquatableValueSet(com.amazonaws.athena.connector.lambda.domain.predicate.EquatableValueSet) RunWith(org.junit.runner.RunWith) HashMap(java.util.HashMap) Matchers.anyString(org.mockito.Matchers.anyString) ArrayList(java.util.ArrayList) RemoteReadRecordsResponse(com.amazonaws.athena.connector.lambda.records.RemoteReadRecordsResponse) Answer(org.mockito.stubbing.Answer) InvocationOnMock(org.mockito.invocation.InvocationOnMock) S3Object(com.amazonaws.services.s3.model.S3Object) SchemaBuilder(com.amazonaws.athena.connector.lambda.data.SchemaBuilder) TestName(org.junit.rules.TestName) LocalKeyFactory(com.amazonaws.athena.connector.lambda.security.LocalKeyFactory) Matchers.anyObject(org.mockito.Matchers.anyObject) AmazonS3(com.amazonaws.services.s3.AmazonS3) FederatedIdentity(com.amazonaws.athena.connector.lambda.security.FederatedIdentity) PutObjectResult(com.amazonaws.services.s3.model.PutObjectResult) S3BlockSpillReader(com.amazonaws.athena.connector.lambda.data.S3BlockSpillReader) Before(org.junit.Before) Logger(org.slf4j.Logger) AmazonAthena(com.amazonaws.services.athena.AmazonAthena) Assert.assertNotNull(org.junit.Assert.assertNotNull) ReadRecordsRequest(com.amazonaws.athena.connector.lambda.records.ReadRecordsRequest) Assert.assertTrue(org.junit.Assert.assertTrue) AWSSecretsManager(com.amazonaws.services.secretsmanager.AWSSecretsManager) Test(org.junit.Test) IOException(java.io.IOException) Mockito.when(org.mockito.Mockito.when) FieldBuilder(com.amazonaws.athena.connector.lambda.data.FieldBuilder) Constraints(com.amazonaws.athena.connector.lambda.domain.predicate.Constraints) S3SpillLocation(com.amazonaws.athena.connector.lambda.domain.spill.S3SpillLocation) Rule(org.junit.Rule) MockitoJUnitRunner(org.mockito.runners.MockitoJUnitRunner) QueryRequest(com.amazonaws.services.timestreamquery.model.QueryRequest) TestUtils.makeMockQueryResult(com.amazonaws.athena.connectors.timestream.TestUtils.makeMockQueryResult) VIEW_METADATA_FIELD(com.amazonaws.athena.connector.lambda.handlers.GlueMetadataHandler.VIEW_METADATA_FIELD) Collections(java.util.Collections) Assert.assertEquals(org.junit.Assert.assertEquals) InputStream(java.io.InputStream) QueryRequest(com.amazonaws.services.timestreamquery.model.QueryRequest) HashMap(java.util.HashMap) ReadRecordsResponse(com.amazonaws.athena.connector.lambda.records.ReadRecordsResponse) RemoteReadRecordsResponse(com.amazonaws.athena.connector.lambda.records.RemoteReadRecordsResponse) Schema(org.apache.arrow.vector.types.pojo.Schema) Matchers.anyString(org.mockito.Matchers.anyString) RecordResponse(com.amazonaws.athena.connector.lambda.records.RecordResponse) TableName(com.amazonaws.athena.connector.lambda.domain.TableName) QueryResult(com.amazonaws.services.timestreamquery.model.QueryResult) TestUtils.makeMockQueryResult(com.amazonaws.athena.connectors.timestream.TestUtils.makeMockQueryResult) ReadRecordsRequest(com.amazonaws.athena.connector.lambda.records.ReadRecordsRequest) Constraints(com.amazonaws.athena.connector.lambda.domain.predicate.Constraints) S3SpillLocation(com.amazonaws.athena.connector.lambda.domain.spill.S3SpillLocation) Split(com.amazonaws.athena.connector.lambda.domain.Split) ValueSet(com.amazonaws.athena.connector.lambda.domain.predicate.ValueSet) EquatableValueSet(com.amazonaws.athena.connector.lambda.domain.predicate.EquatableValueSet) Test(org.junit.Test)

Example 9 with QueryResult

use of com.amazonaws.services.timestreamquery.model.QueryResult in project aws-athena-query-federation by awslabs.

the class TimestreamRecordHandlerTest method doReadRecordsSpill.

@Test
public void doReadRecordsSpill() throws Exception {
    String expectedQuery = "SELECT measure_name, measure_value::double, az, time, hostname, region FROM \"my_schema\".\"my_table\" WHERE (\"az\" IN ('us-east-1a','us-east-1b'))";
    QueryResult mockResult = makeMockQueryResult(schemaForRead, 100_000);
    when(mockClient.query(any(QueryRequest.class))).thenAnswer((Answer<QueryResult>) invocationOnMock -> {
        QueryRequest request = (QueryRequest) invocationOnMock.getArguments()[0];
        assertEquals(expectedQuery, request.getQueryString().replace("\n", ""));
        return mockResult;
    });
    Map<String, ValueSet> constraintsMap = new HashMap<>();
    constraintsMap.put("az", EquatableValueSet.newBuilder(allocator, Types.MinorType.VARCHAR.getType(), true, true).add("us-east-1a").add("us-east-1b").build());
    S3SpillLocation splitLoc = S3SpillLocation.newBuilder().withBucket(UUID.randomUUID().toString()).withSplitId(UUID.randomUUID().toString()).withQueryId(UUID.randomUUID().toString()).withIsDirectory(true).build();
    Split.Builder splitBuilder = Split.newBuilder(splitLoc, keyFactory.create());
    ReadRecordsRequest request = new ReadRecordsRequest(IDENTITY, DEFAULT_CATALOG, "queryId-" + System.currentTimeMillis(), new TableName(DEFAULT_SCHEMA, TEST_TABLE), schemaForRead, splitBuilder.build(), new Constraints(constraintsMap), // ~1.5MB so we should see some spill
    1_500_000L, 0L);
    RecordResponse rawResponse = handler.doReadRecords(allocator, request);
    assertTrue(rawResponse instanceof RemoteReadRecordsResponse);
    try (RemoteReadRecordsResponse response = (RemoteReadRecordsResponse) rawResponse) {
        logger.info("doReadRecordsSpill: remoteBlocks[{}]", response.getRemoteBlocks().size());
        assertTrue(response.getNumberBlocks() > 1);
        int blockNum = 0;
        for (SpillLocation next : response.getRemoteBlocks()) {
            S3SpillLocation spillLocation = (S3SpillLocation) next;
            try (Block block = spillReader.read(spillLocation, response.getEncryptionKey(), response.getSchema())) {
                logger.info("doReadRecordsSpill: blockNum[{}] and recordCount[{}]", blockNum++, block.getRowCount());
                // assertTrue(++blockNum < response.getRemoteBlocks().size() && block.getRowCount() > 10_000);
                logger.info("doReadRecordsSpill: {}", BlockUtils.rowToString(block, 0));
                assertNotNull(BlockUtils.rowToString(block, 0));
            }
        }
    }
}
Also used : QueryResult(com.amazonaws.services.timestreamquery.model.QueryResult) Schema(org.apache.arrow.vector.types.pojo.Schema) Types(org.apache.arrow.vector.types.Types) LoggerFactory(org.slf4j.LoggerFactory) BlockAllocator(com.amazonaws.athena.connector.lambda.data.BlockAllocator) SpillLocation(com.amazonaws.athena.connector.lambda.domain.spill.SpillLocation) Block(com.amazonaws.athena.connector.lambda.data.Block) ByteArrayInputStream(java.io.ByteArrayInputStream) After(org.junit.After) Map(java.util.Map) ValueSet(com.amazonaws.athena.connector.lambda.domain.predicate.ValueSet) AmazonTimestreamQuery(com.amazonaws.services.timestreamquery.AmazonTimestreamQuery) BlockAllocatorImpl(com.amazonaws.athena.connector.lambda.data.BlockAllocatorImpl) Split(com.amazonaws.athena.connector.lambda.domain.Split) ReadRecordsResponse(com.amazonaws.athena.connector.lambda.records.ReadRecordsResponse) UUID(java.util.UUID) TableName(com.amazonaws.athena.connector.lambda.domain.TableName) RecordResponse(com.amazonaws.athena.connector.lambda.records.RecordResponse) Matchers.any(org.mockito.Matchers.any) List(java.util.List) ByteStreams(com.google.common.io.ByteStreams) BlockUtils(com.amazonaws.athena.connector.lambda.data.BlockUtils) S3ObjectInputStream(com.amazonaws.services.s3.model.S3ObjectInputStream) EncryptionKeyFactory(com.amazonaws.athena.connector.lambda.security.EncryptionKeyFactory) Mockito.mock(org.mockito.Mockito.mock) Mock(org.mockito.Mock) EquatableValueSet(com.amazonaws.athena.connector.lambda.domain.predicate.EquatableValueSet) RunWith(org.junit.runner.RunWith) HashMap(java.util.HashMap) Matchers.anyString(org.mockito.Matchers.anyString) ArrayList(java.util.ArrayList) RemoteReadRecordsResponse(com.amazonaws.athena.connector.lambda.records.RemoteReadRecordsResponse) Answer(org.mockito.stubbing.Answer) InvocationOnMock(org.mockito.invocation.InvocationOnMock) S3Object(com.amazonaws.services.s3.model.S3Object) SchemaBuilder(com.amazonaws.athena.connector.lambda.data.SchemaBuilder) TestName(org.junit.rules.TestName) LocalKeyFactory(com.amazonaws.athena.connector.lambda.security.LocalKeyFactory) Matchers.anyObject(org.mockito.Matchers.anyObject) AmazonS3(com.amazonaws.services.s3.AmazonS3) FederatedIdentity(com.amazonaws.athena.connector.lambda.security.FederatedIdentity) PutObjectResult(com.amazonaws.services.s3.model.PutObjectResult) S3BlockSpillReader(com.amazonaws.athena.connector.lambda.data.S3BlockSpillReader) Before(org.junit.Before) Logger(org.slf4j.Logger) AmazonAthena(com.amazonaws.services.athena.AmazonAthena) Assert.assertNotNull(org.junit.Assert.assertNotNull) ReadRecordsRequest(com.amazonaws.athena.connector.lambda.records.ReadRecordsRequest) Assert.assertTrue(org.junit.Assert.assertTrue) AWSSecretsManager(com.amazonaws.services.secretsmanager.AWSSecretsManager) Test(org.junit.Test) IOException(java.io.IOException) Mockito.when(org.mockito.Mockito.when) FieldBuilder(com.amazonaws.athena.connector.lambda.data.FieldBuilder) Constraints(com.amazonaws.athena.connector.lambda.domain.predicate.Constraints) S3SpillLocation(com.amazonaws.athena.connector.lambda.domain.spill.S3SpillLocation) Rule(org.junit.Rule) MockitoJUnitRunner(org.mockito.runners.MockitoJUnitRunner) QueryRequest(com.amazonaws.services.timestreamquery.model.QueryRequest) TestUtils.makeMockQueryResult(com.amazonaws.athena.connectors.timestream.TestUtils.makeMockQueryResult) VIEW_METADATA_FIELD(com.amazonaws.athena.connector.lambda.handlers.GlueMetadataHandler.VIEW_METADATA_FIELD) Collections(java.util.Collections) Assert.assertEquals(org.junit.Assert.assertEquals) InputStream(java.io.InputStream) RemoteReadRecordsResponse(com.amazonaws.athena.connector.lambda.records.RemoteReadRecordsResponse) QueryRequest(com.amazonaws.services.timestreamquery.model.QueryRequest) SpillLocation(com.amazonaws.athena.connector.lambda.domain.spill.SpillLocation) S3SpillLocation(com.amazonaws.athena.connector.lambda.domain.spill.S3SpillLocation) HashMap(java.util.HashMap) Matchers.anyString(org.mockito.Matchers.anyString) RecordResponse(com.amazonaws.athena.connector.lambda.records.RecordResponse) TableName(com.amazonaws.athena.connector.lambda.domain.TableName) QueryResult(com.amazonaws.services.timestreamquery.model.QueryResult) TestUtils.makeMockQueryResult(com.amazonaws.athena.connectors.timestream.TestUtils.makeMockQueryResult) ReadRecordsRequest(com.amazonaws.athena.connector.lambda.records.ReadRecordsRequest) Constraints(com.amazonaws.athena.connector.lambda.domain.predicate.Constraints) S3SpillLocation(com.amazonaws.athena.connector.lambda.domain.spill.S3SpillLocation) Block(com.amazonaws.athena.connector.lambda.data.Block) Split(com.amazonaws.athena.connector.lambda.domain.Split) ValueSet(com.amazonaws.athena.connector.lambda.domain.predicate.ValueSet) EquatableValueSet(com.amazonaws.athena.connector.lambda.domain.predicate.EquatableValueSet) Test(org.junit.Test)

Aggregations

QueryResult (com.amazonaws.services.timestreamquery.model.QueryResult)9 QueryRequest (com.amazonaws.services.timestreamquery.model.QueryRequest)8 TableName (com.amazonaws.athena.connector.lambda.domain.TableName)7 ArrayList (java.util.ArrayList)6 Block (com.amazonaws.athena.connector.lambda.data.Block)5 BlockUtils (com.amazonaws.athena.connector.lambda.data.BlockUtils)5 SchemaBuilder (com.amazonaws.athena.connector.lambda.data.SchemaBuilder)5 HashMap (java.util.HashMap)5 List (java.util.List)5 BlockAllocator (com.amazonaws.athena.connector.lambda.data.BlockAllocator)4 BlockAllocatorImpl (com.amazonaws.athena.connector.lambda.data.BlockAllocatorImpl)4 FieldBuilder (com.amazonaws.athena.connector.lambda.data.FieldBuilder)4 S3BlockSpillReader (com.amazonaws.athena.connector.lambda.data.S3BlockSpillReader)4 Split (com.amazonaws.athena.connector.lambda.domain.Split)4 Constraints (com.amazonaws.athena.connector.lambda.domain.predicate.Constraints)4 EquatableValueSet (com.amazonaws.athena.connector.lambda.domain.predicate.EquatableValueSet)4 ValueSet (com.amazonaws.athena.connector.lambda.domain.predicate.ValueSet)4 S3SpillLocation (com.amazonaws.athena.connector.lambda.domain.spill.S3SpillLocation)4 SpillLocation (com.amazonaws.athena.connector.lambda.domain.spill.SpillLocation)4 VIEW_METADATA_FIELD (com.amazonaws.athena.connector.lambda.handlers.GlueMetadataHandler.VIEW_METADATA_FIELD)4