use of com.amazonaws.athena.connector.lambda.records.ReadRecordsRequest in project aws-athena-query-federation by awslabs.
the class BigQueryRecordHandlerTest method testReadWithConstraint.
@Test
public void testReadWithConstraint() throws Exception {
try (ReadRecordsRequest request = new ReadRecordsRequest(federatedIdentity, BigQueryTestUtils.PROJECT_1_NAME, "queryId", new TableName("dataset1", "table1"), BigQueryTestUtils.getBlockTestSchema(), 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;
});
// Populate the schema and data that the mocked Google BigQuery client will return.
com.google.cloud.bigquery.Schema tableSchema = BigQueryTestUtils.getTestSchema();
List<FieldValueList> tableRows = Arrays.asList(BigQueryTestUtils.getBigQueryFieldValueList(false, 1000, "test1", 123123.12312), BigQueryTestUtils.getBigQueryFieldValueList(true, 500, "test2", 5345234.22111), BigQueryTestUtils.getBigQueryFieldValueList(false, 700, "test3", 324324.23423), BigQueryTestUtils.getBigQueryFieldValueList(true, 900, null, null), BigQueryTestUtils.getBigQueryFieldValueList(null, null, "test5", 2342.234234), BigQueryTestUtils.getBigQueryFieldValueList(true, 1200, "test6", 1123.12312), BigQueryTestUtils.getBigQueryFieldValueList(false, 100, "test7", 1313.12312), BigQueryTestUtils.getBigQueryFieldValueList(true, 120, "test8", 12313.1312), BigQueryTestUtils.getBigQueryFieldValueList(false, 300, "test9", 12323.1312));
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()));
// Ensure that there was a spill so that we can read the spilled block.
assertTrue(spillWriter.spilled());
}
}
use of com.amazonaws.athena.connector.lambda.records.ReadRecordsRequest in project aws-athena-query-federation by awslabs.
the class HbaseRecordHandlerTest method doReadRecordsSpill.
@Test
public void doReadRecordsSpill() throws Exception {
List<Result> results = TestUtils.makeResults(10_000);
ResultScanner mockScanner = mock(ResultScanner.class);
when(mockScanner.iterator()).thenReturn(results.iterator());
when(mockClient.scanTable(anyObject(), any(Scan.class), anyObject())).thenAnswer((InvocationOnMock invocationOnMock) -> {
ResultProcessor processor = (ResultProcessor) invocationOnMock.getArguments()[2];
return processor.scan(mockScanner);
});
Map<String, ValueSet> constraintsMap = new HashMap<>();
constraintsMap.put("family1:col3", SortedRangeSet.copyOf(Types.MinorType.BIGINT.getType(), ImmutableList.of(Range.greaterThan(allocator, Types.MinorType.BIGINT.getType(), 0L)), true));
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()).add(HBASE_CONN_STR, "fake_con_str").add(START_KEY_FIELD, "fake_start_key").add(END_KEY_FIELD, "fake_end_key").add(REGION_ID_FIELD, "fake_region_id").add(REGION_NAME_FIELD, "fake_region_name");
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));
}
}
}
}
use of com.amazonaws.athena.connector.lambda.records.ReadRecordsRequest in project aws-athena-query-federation by awslabs.
the class HiveMuxRecordHandlerTest method readWithConstraint.
@Test
public void readWithConstraint() throws SQLException {
BlockSpiller blockSpiller = Mockito.mock(BlockSpiller.class);
ReadRecordsRequest readRecordsRequest = Mockito.mock(ReadRecordsRequest.class);
Mockito.when(readRecordsRequest.getCatalogName()).thenReturn("recordHive");
this.jdbcRecordHandler.readWithConstraint(blockSpiller, readRecordsRequest, queryStatusChecker);
Mockito.verify(this.hiveRecordHandler, Mockito.times(1)).readWithConstraint(Mockito.eq(blockSpiller), Mockito.eq(readRecordsRequest), Mockito.eq(queryStatusChecker));
}
use of com.amazonaws.athena.connector.lambda.records.ReadRecordsRequest in project aws-athena-query-federation by awslabs.
the class HiveMuxRecordHandlerTest method readWithConstraintWithUnsupportedCatalog.
@Test(expected = RuntimeException.class)
public void readWithConstraintWithUnsupportedCatalog() throws SQLException {
BlockSpiller blockSpiller = Mockito.mock(BlockSpiller.class);
ReadRecordsRequest readRecordsRequest = Mockito.mock(ReadRecordsRequest.class);
Mockito.when(readRecordsRequest.getCatalogName()).thenReturn("unsupportedCatalog");
this.jdbcRecordHandler.readWithConstraint(blockSpiller, readRecordsRequest, queryStatusChecker);
}
use of com.amazonaws.athena.connector.lambda.records.ReadRecordsRequest in project aws-athena-query-federation by awslabs.
the class MultiplexingJdbcRecordHandlerTest method buildSplitSql.
@Test
public void buildSplitSql() throws SQLException {
ReadRecordsRequest readRecordsRequest = Mockito.mock(ReadRecordsRequest.class);
Mockito.when(readRecordsRequest.getCatalogName()).thenReturn("fakedatabase");
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, "fakedatabase", tableName, schema, constraints, split);
Mockito.verify(this.fakeJdbcRecordHandler, Mockito.times(1)).buildSplitSql(Mockito.eq(jdbcConnection), Mockito.eq("fakedatabase"), Mockito.eq(tableName), Mockito.eq(schema), Mockito.eq(constraints), Mockito.eq(split));
}
Aggregations