Search in sources :

Example 6 with ReadRecordsRequest

use of com.amazonaws.athena.connector.lambda.records.ReadRecordsRequest in project aws-athena-query-federation by awslabs.

the class BigQueryRecordHandlerTest method getObjectFromFieldValue.

@Test
public void getObjectFromFieldValue() throws Exception {
    org.apache.arrow.vector.types.pojo.Schema testSchema = SchemaBuilder.newBuilder().addDateDayField("datecol").addDateMilliField("datetimecol").addStringField("timestampcol").build();
    try (ReadRecordsRequest request = new ReadRecordsRequest(federatedIdentity, BigQueryTestUtils.PROJECT_1_NAME, "queryId", new TableName("dataset1", "table1"), testSchema, Split.newBuilder(S3SpillLocation.newBuilder().withBucket(bucket).withPrefix(prefix).withSplitId(UUID.randomUUID().toString()).withQueryId(UUID.randomUUID().toString()).withIsDirectory(true).build(), keyFactory.create()).build(), new Constraints(Collections.EMPTY_MAP), // This is ignored when directly calling readWithConstraints.
    0, 0)) {
        // This is ignored when directly calling readWithConstraints.
        // Always return try for the evaluator to keep all rows.
        ConstraintEvaluator evaluator = mock(ConstraintEvaluator.class);
        when(evaluator.apply(any(String.class), any(Object.class))).thenAnswer((InvocationOnMock invocationOnMock) -> {
            return true;
        });
        // added schema with columns datecol, datetimecol, timestampcol
        List<com.google.cloud.bigquery.Field> testSchemaFields = Arrays.asList(com.google.cloud.bigquery.Field.of("datecol", LegacySQLTypeName.DATE), com.google.cloud.bigquery.Field.of("datetimecol", LegacySQLTypeName.DATETIME), com.google.cloud.bigquery.Field.of("timestampcol", LegacySQLTypeName.TIMESTAMP));
        com.google.cloud.bigquery.Schema tableSchema = com.google.cloud.bigquery.Schema.of(testSchemaFields);
        // mocked table rows
        List<FieldValue> firstRowValues = Arrays.asList(FieldValue.of(FieldValue.Attribute.PRIMITIVE, "2016-02-05"), FieldValue.of(FieldValue.Attribute.PRIMITIVE, "2021-10-30T10:10:10"), FieldValue.of(FieldValue.Attribute.PRIMITIVE, "2014-12-03T12:30:00.450Z"));
        FieldValueList firstRow = FieldValueList.of(firstRowValues, FieldList.of(testSchemaFields));
        List<FieldValueList> tableRows = Arrays.asList(firstRow);
        Page<FieldValueList> fieldValueList = new BigQueryPage<>(tableRows);
        TableResult result = new TableResult(tableSchema, tableRows.size(), fieldValueList);
        // Mock out the Google BigQuery Job.
        Job mockBigQueryJob = mock(Job.class);
        when(mockBigQueryJob.isDone()).thenReturn(false).thenReturn(true);
        when(mockBigQueryJob.getQueryResults()).thenReturn(result);
        when(bigQuery.create(any(JobInfo.class))).thenReturn(mockBigQueryJob);
        QueryStatusChecker queryStatusChecker = mock(QueryStatusChecker.class);
        when(queryStatusChecker.isQueryRunning()).thenReturn(true);
        // Execute the test
        bigQueryRecordHandler.readWithConstraint(spillWriter, request, queryStatusChecker);
        PowerMockito.mockStatic(System.class);
        PowerMockito.when(System.getenv(anyString())).thenReturn("test");
        logger.info("Project Name: " + BigQueryUtils.getProjectName(request.getCatalogName()));
    }
}
Also used : Schema(org.apache.arrow.vector.types.pojo.Schema) ConstraintEvaluator(com.amazonaws.athena.connector.lambda.domain.predicate.ConstraintEvaluator) Field(org.apache.arrow.vector.types.pojo.Field) com.google.cloud.bigquery(com.google.cloud.bigquery) TableName(com.amazonaws.athena.connector.lambda.domain.TableName) ReadRecordsRequest(com.amazonaws.athena.connector.lambda.records.ReadRecordsRequest) Constraints(com.amazonaws.athena.connector.lambda.domain.predicate.Constraints) QueryStatusChecker(com.amazonaws.athena.connector.lambda.QueryStatusChecker) InvocationOnMock(org.mockito.invocation.InvocationOnMock) S3Object(com.amazonaws.services.s3.model.S3Object) PrepareForTest(org.powermock.core.classloader.annotations.PrepareForTest) Test(org.junit.Test)

Example 7 with ReadRecordsRequest

use of com.amazonaws.athena.connector.lambda.records.ReadRecordsRequest in project aws-athena-query-federation by awslabs.

the class HiveMuxRecordHandlerTest method buildSplitSql.

@Test
public void buildSplitSql() throws SQLException {
    ReadRecordsRequest readRecordsRequest = Mockito.mock(ReadRecordsRequest.class);
    Mockito.when(readRecordsRequest.getCatalogName()).thenReturn("recordHive");
    Connection jdbcConnection = Mockito.mock(Connection.class);
    TableName tableName = new TableName("testSchema", "tableName");
    Schema schema = Mockito.mock(Schema.class);
    Constraints constraints = Mockito.mock(Constraints.class);
    Split split = Mockito.mock(Split.class);
    this.jdbcRecordHandler.buildSplitSql(jdbcConnection, "recordHive", tableName, schema, constraints, split);
    Mockito.verify(this.hiveRecordHandler, Mockito.times(1)).buildSplitSql(Mockito.eq(jdbcConnection), Mockito.eq("recordHive"), Mockito.eq(tableName), Mockito.eq(schema), Mockito.eq(constraints), Mockito.eq(split));
}
Also used : TableName(com.amazonaws.athena.connector.lambda.domain.TableName) ReadRecordsRequest(com.amazonaws.athena.connector.lambda.records.ReadRecordsRequest) Constraints(com.amazonaws.athena.connector.lambda.domain.predicate.Constraints) Schema(org.apache.arrow.vector.types.pojo.Schema) Connection(java.sql.Connection) Split(com.amazonaws.athena.connector.lambda.domain.Split) Test(org.junit.Test)

Example 8 with ReadRecordsRequest

use of com.amazonaws.athena.connector.lambda.records.ReadRecordsRequest in project aws-athena-query-federation by awslabs.

the class JdbcRecordHandlerTest method readWithConstraint.

@Test
public void readWithConstraint() throws SQLException {
    ConstraintEvaluator constraintEvaluator = Mockito.mock(ConstraintEvaluator.class);
    Mockito.when(constraintEvaluator.apply(Mockito.anyString(), Mockito.any())).thenReturn(true);
    TableName inputTableName = new TableName("testSchema", "testTable");
    SchemaBuilder expectedSchemaBuilder = SchemaBuilder.newBuilder();
    expectedSchemaBuilder.addField(FieldBuilder.newBuilder("testCol1", org.apache.arrow.vector.types.Types.MinorType.INT.getType()).build());
    expectedSchemaBuilder.addField(FieldBuilder.newBuilder("testCol2", org.apache.arrow.vector.types.Types.MinorType.VARCHAR.getType()).build());
    expectedSchemaBuilder.addField(FieldBuilder.newBuilder("testPartitionCol", org.apache.arrow.vector.types.Types.MinorType.VARCHAR.getType()).build());
    Schema fieldSchema = expectedSchemaBuilder.build();
    BlockAllocator allocator = new BlockAllocatorImpl();
    S3SpillLocation s3SpillLocation = S3SpillLocation.newBuilder().withIsDirectory(true).build();
    Split.Builder splitBuilder = Split.newBuilder(s3SpillLocation, null).add("testPartitionCol", String.valueOf("testPartitionValue"));
    Constraints constraints = Mockito.mock(Constraints.class, Mockito.RETURNS_DEEP_STUBS);
    String[] schema = { "testCol1", "testCol2" };
    int[] columnTypes = { Types.INTEGER, Types.VARCHAR };
    Object[][] values = { { 1, "testVal1" }, { 2, "testVal2" } };
    AtomicInteger rowNumber = new AtomicInteger(-1);
    ResultSet resultSet = mockResultSet(schema, columnTypes, values, rowNumber);
    Mockito.when(this.preparedStatement.executeQuery()).thenReturn(resultSet);
    SpillConfig spillConfig = Mockito.mock(SpillConfig.class);
    Mockito.when(spillConfig.getSpillLocation()).thenReturn(s3SpillLocation);
    BlockSpiller s3Spiller = new S3BlockSpiller(this.amazonS3, spillConfig, allocator, fieldSchema, constraintEvaluator);
    ReadRecordsRequest readRecordsRequest = new ReadRecordsRequest(this.federatedIdentity, "testCatalog", "testQueryId", inputTableName, fieldSchema, splitBuilder.build(), constraints, 1024, 1024);
    Mockito.when(amazonS3.putObject(Mockito.anyString(), Mockito.anyString(), Mockito.any(), Mockito.any())).thenAnswer((Answer<PutObjectResult>) invocation -> {
        ByteArrayInputStream byteArrayInputStream = (ByteArrayInputStream) invocation.getArguments()[2];
        int n = byteArrayInputStream.available();
        byte[] bytes = new byte[n];
        byteArrayInputStream.read(bytes, 0, n);
        String data = new String(bytes, StandardCharsets.UTF_8);
        Assert.assertTrue(data.contains("testVal1") || data.contains("testVal2") || data.contains("testPartitionValue"));
        return new PutObjectResult();
    });
    this.jdbcRecordHandler.readWithConstraint(s3Spiller, readRecordsRequest, queryStatusChecker);
}
Also used : Schema(org.apache.arrow.vector.types.pojo.Schema) Connection(java.sql.Connection) S3BlockSpiller(com.amazonaws.athena.connector.lambda.data.S3BlockSpiller) com.amazonaws.athena.connector.lambda.data.writers.extractors(com.amazonaws.athena.connector.lambda.data.writers.extractors) BlockAllocator(com.amazonaws.athena.connector.lambda.data.BlockAllocator) ConstraintEvaluator(com.amazonaws.athena.connector.lambda.domain.predicate.ConstraintEvaluator) Answer(org.mockito.stubbing.Answer) BlockSpiller(com.amazonaws.athena.connector.lambda.data.BlockSpiller) SQLException(java.sql.SQLException) JdbcCredentialProvider(com.amazonaws.athena.connectors.jdbc.connection.JdbcCredentialProvider) ByteArrayInputStream(java.io.ByteArrayInputStream) AtomicInteger(java.util.concurrent.atomic.AtomicInteger) SchemaBuilder(com.amazonaws.athena.connector.lambda.data.SchemaBuilder) ResultSet(java.sql.ResultSet) Map(java.util.Map) TestBase(com.amazonaws.athena.connectors.jdbc.TestBase) AmazonS3(com.amazonaws.services.s3.AmazonS3) QueryStatusChecker(com.amazonaws.athena.connector.lambda.QueryStatusChecker) BlockAllocatorImpl(com.amazonaws.athena.connector.lambda.data.BlockAllocatorImpl) FederatedIdentity(com.amazonaws.athena.connector.lambda.security.FederatedIdentity) PutObjectResult(com.amazonaws.services.s3.model.PutObjectResult) GetSecretValueResult(com.amazonaws.services.secretsmanager.model.GetSecretValueResult) Before(org.junit.Before) AmazonAthena(com.amazonaws.services.athena.AmazonAthena) Split(com.amazonaws.athena.connector.lambda.domain.Split) ReadRecordsRequest(com.amazonaws.athena.connector.lambda.records.ReadRecordsRequest) AWSSecretsManager(com.amazonaws.services.secretsmanager.AWSSecretsManager) Test(org.junit.Test) DatabaseConnectionConfig(com.amazonaws.athena.connectors.jdbc.connection.DatabaseConnectionConfig) PreparedStatement(java.sql.PreparedStatement) TableName(com.amazonaws.athena.connector.lambda.domain.TableName) StandardCharsets(java.nio.charset.StandardCharsets) FieldBuilder(com.amazonaws.athena.connector.lambda.data.FieldBuilder) Constraints(com.amazonaws.athena.connector.lambda.domain.predicate.Constraints) Mockito(org.mockito.Mockito) S3SpillLocation(com.amazonaws.athena.connector.lambda.domain.spill.S3SpillLocation) SpillConfig(com.amazonaws.athena.connector.lambda.data.SpillConfig) Assert(org.junit.Assert) JdbcConnectionFactory(com.amazonaws.athena.connectors.jdbc.connection.JdbcConnectionFactory) Collections(java.util.Collections) GetSecretValueRequest(com.amazonaws.services.secretsmanager.model.GetSecretValueRequest) Types(java.sql.Types) PutObjectResult(com.amazonaws.services.s3.model.PutObjectResult) Schema(org.apache.arrow.vector.types.pojo.Schema) ConstraintEvaluator(com.amazonaws.athena.connector.lambda.domain.predicate.ConstraintEvaluator) TableName(com.amazonaws.athena.connector.lambda.domain.TableName) Constraints(com.amazonaws.athena.connector.lambda.domain.predicate.Constraints) SpillConfig(com.amazonaws.athena.connector.lambda.data.SpillConfig) ReadRecordsRequest(com.amazonaws.athena.connector.lambda.records.ReadRecordsRequest) BlockAllocatorImpl(com.amazonaws.athena.connector.lambda.data.BlockAllocatorImpl) AtomicInteger(java.util.concurrent.atomic.AtomicInteger) ByteArrayInputStream(java.io.ByteArrayInputStream) S3SpillLocation(com.amazonaws.athena.connector.lambda.domain.spill.S3SpillLocation) BlockAllocator(com.amazonaws.athena.connector.lambda.data.BlockAllocator) SchemaBuilder(com.amazonaws.athena.connector.lambda.data.SchemaBuilder) ResultSet(java.sql.ResultSet) S3BlockSpiller(com.amazonaws.athena.connector.lambda.data.S3BlockSpiller) Split(com.amazonaws.athena.connector.lambda.domain.Split) S3BlockSpiller(com.amazonaws.athena.connector.lambda.data.S3BlockSpiller) BlockSpiller(com.amazonaws.athena.connector.lambda.data.BlockSpiller) Test(org.junit.Test)

Example 9 with ReadRecordsRequest

use of com.amazonaws.athena.connector.lambda.records.ReadRecordsRequest in project aws-athena-query-federation by awslabs.

the class MultiplexingJdbcRecordHandlerTest method readWithConstraint.

@Test
public void readWithConstraint() {
    BlockSpiller blockSpiller = Mockito.mock(BlockSpiller.class);
    ReadRecordsRequest readRecordsRequest = Mockito.mock(ReadRecordsRequest.class);
    Mockito.when(readRecordsRequest.getCatalogName()).thenReturn("fakedatabase");
    this.jdbcRecordHandler.readWithConstraint(blockSpiller, readRecordsRequest, queryStatusChecker);
    Mockito.verify(this.fakeJdbcRecordHandler, Mockito.times(1)).readWithConstraint(Mockito.eq(blockSpiller), Mockito.eq(readRecordsRequest), Mockito.eq(queryStatusChecker));
}
Also used : ReadRecordsRequest(com.amazonaws.athena.connector.lambda.records.ReadRecordsRequest) BlockSpiller(com.amazonaws.athena.connector.lambda.data.BlockSpiller) Test(org.junit.Test)

Example 10 with ReadRecordsRequest

use of com.amazonaws.athena.connector.lambda.records.ReadRecordsRequest in project aws-athena-query-federation by awslabs.

the class MultiplexingJdbcRecordHandlerTest method readWithConstraintWithUnsupportedCatalog.

@Test(expected = RuntimeException.class)
public void readWithConstraintWithUnsupportedCatalog() {
    BlockSpiller blockSpiller = Mockito.mock(BlockSpiller.class);
    ReadRecordsRequest readRecordsRequest = Mockito.mock(ReadRecordsRequest.class);
    Mockito.when(readRecordsRequest.getCatalogName()).thenReturn("unsupportedCatalog");
    this.jdbcRecordHandler.readWithConstraint(blockSpiller, readRecordsRequest, queryStatusChecker);
}
Also used : ReadRecordsRequest(com.amazonaws.athena.connector.lambda.records.ReadRecordsRequest) BlockSpiller(com.amazonaws.athena.connector.lambda.data.BlockSpiller) Test(org.junit.Test)

Aggregations

ReadRecordsRequest (com.amazonaws.athena.connector.lambda.records.ReadRecordsRequest)85 Test (org.junit.Test)82 Constraints (com.amazonaws.athena.connector.lambda.domain.predicate.Constraints)55 TableName (com.amazonaws.athena.connector.lambda.domain.TableName)40 Split (com.amazonaws.athena.connector.lambda.domain.Split)35 RecordResponse (com.amazonaws.athena.connector.lambda.records.RecordResponse)33 BlockSpiller (com.amazonaws.athena.connector.lambda.data.BlockSpiller)31 HashMap (java.util.HashMap)28 Schema (org.apache.arrow.vector.types.pojo.Schema)28 ValueSet (com.amazonaws.athena.connector.lambda.domain.predicate.ValueSet)27 ReadRecordsResponse (com.amazonaws.athena.connector.lambda.records.ReadRecordsResponse)27 S3SpillLocation (com.amazonaws.athena.connector.lambda.domain.spill.S3SpillLocation)23 Matchers.anyString (org.mockito.Matchers.anyString)23 RemoteReadRecordsResponse (com.amazonaws.athena.connector.lambda.records.RemoteReadRecordsResponse)20 ArrayList (java.util.ArrayList)16 InvocationOnMock (org.mockito.invocation.InvocationOnMock)16 Connection (java.sql.Connection)15 Block (com.amazonaws.athena.connector.lambda.data.Block)14 SpillLocation (com.amazonaws.athena.connector.lambda.domain.spill.SpillLocation)12 EquatableValueSet (com.amazonaws.athena.connector.lambda.domain.predicate.EquatableValueSet)11