Search in sources :

Example 6 with HoodieInsertException

use of org.apache.hudi.exception.HoodieInsertException in project hudi by apache.

the class HoodieTable method validateSchema.

/**
 * Ensure that the current writerSchema is compatible with the latest schema of this dataset.
 *
 * When inserting/updating data, we read records using the last used schema and convert them to the
 * GenericRecords with writerSchema. Hence, we need to ensure that this conversion can take place without errors.
 */
private void validateSchema() throws HoodieUpsertException, HoodieInsertException {
    if (!config.getAvroSchemaValidate() || getActiveTimeline().getCommitsTimeline().filterCompletedInstants().empty()) {
        // Check not required
        return;
    }
    Schema tableSchema;
    Schema writerSchema;
    boolean isValid;
    try {
        TableSchemaResolver schemaResolver = new TableSchemaResolver(getMetaClient());
        writerSchema = HoodieAvroUtils.createHoodieWriteSchema(config.getSchema());
        tableSchema = HoodieAvroUtils.createHoodieWriteSchema(schemaResolver.getTableAvroSchemaWithoutMetadataFields());
        isValid = TableSchemaResolver.isSchemaCompatible(tableSchema, writerSchema);
    } catch (Exception e) {
        throw new HoodieException("Failed to read schema/check compatibility for base path " + metaClient.getBasePath(), e);
    }
    if (!isValid) {
        throw new HoodieException("Failed schema compatibility check for writerSchema :" + writerSchema + ", table schema :" + tableSchema + ", base path :" + metaClient.getBasePath());
    }
}
Also used : Schema(org.apache.avro.Schema) TableSchemaResolver(org.apache.hudi.common.table.TableSchemaResolver) HoodieException(org.apache.hudi.exception.HoodieException) HoodieException(org.apache.hudi.exception.HoodieException) HoodieUpsertException(org.apache.hudi.exception.HoodieUpsertException) TimeoutException(java.util.concurrent.TimeoutException) HoodieInsertException(org.apache.hudi.exception.HoodieInsertException) IOException(java.io.IOException) HoodieIOException(org.apache.hudi.exception.HoodieIOException)

Example 7 with HoodieInsertException

use of org.apache.hudi.exception.HoodieInsertException in project hudi by apache.

the class HoodieCreateHandle method close.

/**
 * Performs actions to durably, persist the current changes and returns a WriteStatus object.
 */
@Override
public List<WriteStatus> close() {
    LOG.info("Closing the file " + writeStatus.getFileId() + " as we are done with all the records " + recordsWritten);
    try {
        fileWriter.close();
        setupWriteStatus();
        LOG.info(String.format("CreateHandle for partitionPath %s fileID %s, took %d ms.", writeStatus.getStat().getPartitionPath(), writeStatus.getStat().getFileId(), writeStatus.getStat().getRuntimeStats().getTotalCreateTime()));
        return Collections.singletonList(writeStatus);
    } catch (IOException e) {
        throw new HoodieInsertException("Failed to close the Insert Handle for path " + path, e);
    }
}
Also used : HoodieInsertException(org.apache.hudi.exception.HoodieInsertException) IOException(java.io.IOException)

Example 8 with HoodieInsertException

use of org.apache.hudi.exception.HoodieInsertException in project hudi by apache.

the class TestHoodieClientOnCopyOnWriteStorage method testPreCommitValidationFailureOnInsert.

@Test
public void testPreCommitValidationFailureOnInsert() throws Exception {
    int numRecords = 200;
    HoodiePreCommitValidatorConfig validatorConfig = HoodiePreCommitValidatorConfig.newBuilder().withPreCommitValidator(SqlQuerySingleResultPreCommitValidator.class.getName()).withPrecommitValidatorSingleResultSqlQueries(COUNT_SQL_QUERY_FOR_VALIDATION + "#" + 500).build();
    HoodieWriteConfig config = getConfigBuilder().withPreCommitValidatorConfig(validatorConfig).build();
    String newCommitTime = HoodieActiveTimeline.createNewInstantTime();
    try (SparkRDDWriteClient client = getHoodieWriteClient(config)) {
        Function3<JavaRDD<WriteStatus>, SparkRDDWriteClient, JavaRDD<HoodieRecord>, String> writeFn = (writeClient, recordRDD, instantTime) -> writeClient.bulkInsert(recordRDD, instantTime, Option.empty());
        JavaRDD<WriteStatus> result = insertFirstBatch(config, client, newCommitTime, "000", numRecords, writeFn, false, false, numRecords);
        fail("Expected validation to fail because we only insert 200 rows. Validation is configured to expect 500 rows");
    } catch (HoodieInsertException e) {
        if (e.getCause() instanceof HoodieValidationException) {
        // expected because wrong value passed
        } else {
            throw e;
        }
    }
    assertFalse(testTable.commitExists(newCommitTime));
}
Also used : HoodieTable(org.apache.hudi.table.HoodieTable) BeforeEach(org.junit.jupiter.api.BeforeEach) Arrays(java.util.Arrays) FileIOUtils(org.apache.hudi.common.util.FileIOUtils) HoodieUpsertException(org.apache.hudi.exception.HoodieUpsertException) SparkSingleFileSortPlanStrategy(org.apache.hudi.client.clustering.plan.strategy.SparkSingleFileSortPlanStrategy) SparkTaskContextSupplier(org.apache.hudi.client.SparkTaskContextSupplier) HoodieWriteHelper(org.apache.hudi.table.action.commit.HoodieWriteHelper) BaseKeyGenerator(org.apache.hudi.keygen.BaseKeyGenerator) Future(java.util.concurrent.Future) Map(java.util.Map) EAGER(org.apache.hudi.common.model.HoodieFailedWritesCleaningPolicy.EAGER) Tag(org.junit.jupiter.api.Tag) HoodieWriteResult(org.apache.hudi.client.HoodieWriteResult) REQUESTED(org.apache.hudi.common.table.timeline.HoodieInstant.State.REQUESTED) HoodieWriteMetadata(org.apache.hudi.table.action.HoodieWriteMetadata) HoodieFileGroupId(org.apache.hudi.common.model.HoodieFileGroupId) HoodieActiveTimeline(org.apache.hudi.common.table.timeline.HoodieActiveTimeline) FSDataInputStream(org.apache.hadoop.fs.FSDataInputStream) BaseHoodieWriteClient(org.apache.hudi.client.BaseHoodieWriteClient) IndexType(org.apache.hudi.index.HoodieIndex.IndexType) HoodieClusteringPlan(org.apache.hudi.avro.model.HoodieClusteringPlan) Set(java.util.Set) VERSION_0(org.apache.hudi.common.table.timeline.versioning.TimelineLayoutVersion.VERSION_0) Arguments(org.junit.jupiter.params.provider.Arguments) HoodieIndex(org.apache.hudi.index.HoodieIndex) Executors(java.util.concurrent.Executors) HoodieBaseFile(org.apache.hudi.common.model.HoodieBaseFile) Stream(java.util.stream.Stream) FileSystemViewStorageConfig(org.apache.hudi.common.table.view.FileSystemViewStorageConfig) Assertions.assertTrue(org.junit.jupiter.api.Assertions.assertTrue) ClusteringUtils(org.apache.hudi.common.util.ClusteringUtils) HoodieClientTestUtils(org.apache.hudi.testutils.HoodieClientTestUtils) SqlQuerySingleResultPreCommitValidator(org.apache.hudi.client.validator.SqlQuerySingleResultPreCommitValidator) DEFAULT_THIRD_PARTITION_PATH(org.apache.hudi.common.testutils.HoodieTestDataGenerator.DEFAULT_THIRD_PARTITION_PATH) Mockito.mock(org.mockito.Mockito.mock) HoodieClientTestBase(org.apache.hudi.testutils.HoodieClientTestBase) Assertions.assertThrows(org.junit.jupiter.api.Assertions.assertThrows) Assertions.fail(org.junit.jupiter.api.Assertions.fail) Dataset(org.apache.spark.sql.Dataset) Assertions.assertNull(org.junit.jupiter.api.Assertions.assertNull) Option(org.apache.hudi.common.util.Option) HoodieEngineContext(org.apache.hudi.common.engine.HoodieEngineContext) DEFAULT_FIRST_PARTITION_PATH(org.apache.hudi.common.testutils.HoodieTestDataGenerator.DEFAULT_FIRST_PARTITION_PATH) HoodieValidationException(org.apache.hudi.exception.HoodieValidationException) ArrayList(java.util.ArrayList) MarkerType(org.apache.hudi.common.table.marker.MarkerType) StringUtils(org.apache.hudi.common.util.StringUtils) KeyGenerator(org.apache.hudi.keygen.KeyGenerator) BulkInsertPartitioner(org.apache.hudi.table.BulkInsertPartitioner) Transformations.recordsToRecordKeySet(org.apache.hudi.common.testutils.Transformations.recordsToRecordKeySet) EXECUTION_STRATEGY_CLASS_NAME(org.apache.hudi.config.HoodieClusteringConfig.EXECUTION_STRATEGY_CLASS_NAME) Assertions.assertEquals(org.junit.jupiter.api.Assertions.assertEquals) JavaRDD(org.apache.spark.api.java.JavaRDD) TimelineLayoutVersion(org.apache.hudi.common.table.timeline.versioning.TimelineLayoutVersion) ValueSource(org.junit.jupiter.params.provider.ValueSource) ConsistencyGuardConfig(org.apache.hudi.common.fs.ConsistencyGuardConfig) HoodieRecord(org.apache.hudi.common.model.HoodieRecord) Assertions.assertNoWriteErrors(org.apache.hudi.testutils.Assertions.assertNoWriteErrors) HoodieData(org.apache.hudi.common.data.HoodieData) RDDCustomColumnsSortPartitioner(org.apache.hudi.execution.bulkinsert.RDDCustomColumnsSortPartitioner) Properties(java.util.Properties) HoodieWriteConfig(org.apache.hudi.config.HoodieWriteConfig) WriteMarkersFactory(org.apache.hudi.table.marker.WriteMarkersFactory) BaseFileOnlyView(org.apache.hudi.common.table.view.TableFileSystemView.BaseFileOnlyView) SqlQueryEqualityPreCommitValidator(org.apache.hudi.client.validator.SqlQueryEqualityPreCommitValidator) DEFAULT_SECOND_PARTITION_PATH(org.apache.hudi.common.testutils.HoodieTestDataGenerator.DEFAULT_SECOND_PARTITION_PATH) HoodieTestTable(org.apache.hudi.common.testutils.HoodieTestTable) HoodieCommitMetadata(org.apache.hudi.common.model.HoodieCommitMetadata) IOException(java.io.IOException) Row(org.apache.spark.sql.Row) HoodieAvroRecord(org.apache.hudi.common.model.HoodieAvroRecord) HoodieCompactionConfig(org.apache.hudi.config.HoodieCompactionConfig) ParameterizedTest(org.junit.jupiter.params.ParameterizedTest) HoodieCleanMetadata(org.apache.hudi.avro.model.HoodieCleanMetadata) HoodieCorruptedDataException(org.apache.hudi.exception.HoodieCorruptedDataException) HoodieKey(org.apache.hudi.common.model.HoodieKey) HoodieSparkWriteableTestTable(org.apache.hudi.testutils.HoodieSparkWriteableTestTable) HoodieIOException(org.apache.hudi.exception.HoodieIOException) HoodieTestUtils(org.apache.hudi.common.testutils.HoodieTestUtils) COMPLETED(org.apache.hudi.common.table.timeline.HoodieInstant.State.COMPLETED) REPLACE_COMMIT_ACTION(org.apache.hudi.common.table.timeline.HoodieTimeline.REPLACE_COMMIT_ACTION) HoodieFailedWritesCleaningPolicy(org.apache.hudi.common.model.HoodieFailedWritesCleaningPolicy) HoodieInstant(org.apache.hudi.common.table.timeline.HoodieInstant) HoodieTestDataGenerator(org.apache.hudi.common.testutils.HoodieTestDataGenerator) CollectionUtils(org.apache.hudi.common.util.CollectionUtils) HoodieJavaRDD(org.apache.hudi.data.HoodieJavaRDD) Logger(org.apache.log4j.Logger) HoodieMergeHandle(org.apache.hudi.io.HoodieMergeHandle) CLEAN_ACTION(org.apache.hudi.common.table.timeline.HoodieTimeline.CLEAN_ACTION) Assertions.assertFalse(org.junit.jupiter.api.Assertions.assertFalse) HoodieStorageConfig(org.apache.hudi.config.HoodieStorageConfig) Path(org.apache.hadoop.fs.Path) HoodieSparkKeyGeneratorFactory(org.apache.hudi.keygen.factory.HoodieSparkKeyGeneratorFactory) MethodSource(org.junit.jupiter.params.provider.MethodSource) HoodieRollbackException(org.apache.hudi.exception.HoodieRollbackException) SparkSingleFileSortExecutionStrategy(org.apache.hudi.client.clustering.run.strategy.SparkSingleFileSortExecutionStrategy) HoodiePreCommitValidatorConfig(org.apache.hudi.config.HoodiePreCommitValidatorConfig) TRIP_EXAMPLE_SCHEMA(org.apache.hudi.common.testutils.HoodieTestDataGenerator.TRIP_EXAMPLE_SCHEMA) IOType(org.apache.hudi.common.model.IOType) RawTripTestPayload(org.apache.hudi.common.testutils.RawTripTestPayload) Collection(java.util.Collection) TimelineMetadataUtils(org.apache.hudi.common.table.timeline.TimelineMetadataUtils) MarkerUtils(org.apache.hudi.common.util.MarkerUtils) UUID(java.util.UUID) Collectors(java.util.stream.Collectors) Test(org.junit.jupiter.api.Test) List(java.util.List) FileCreateUtils.getBaseFileCountsForPaths(org.apache.hudi.common.testutils.FileCreateUtils.getBaseFileCountsForPaths) HoodieWriteStat(org.apache.hudi.common.model.HoodieWriteStat) ROLLBACK_ACTION(org.apache.hudi.common.table.timeline.HoodieTimeline.ROLLBACK_ACTION) WriteOperationType(org.apache.hudi.common.model.WriteOperationType) NotNull(org.jetbrains.annotations.NotNull) HoodieInsertException(org.apache.hudi.exception.HoodieInsertException) Transformations.randomSelectAsHoodieKeys(org.apache.hudi.common.testutils.Transformations.randomSelectAsHoodieKeys) INFLIGHT(org.apache.hudi.common.table.timeline.HoodieInstant.State.INFLIGHT) COMMIT_ACTION(org.apache.hudi.common.table.timeline.HoodieTimeline.COMMIT_ACTION) BaseFileUtils(org.apache.hudi.common.util.BaseFileUtils) FileSlice(org.apache.hudi.common.model.FileSlice) HoodieCommitException(org.apache.hudi.exception.HoodieCommitException) EnumSource(org.junit.jupiter.params.provider.EnumSource) HashMap(java.util.HashMap) HashSet(java.util.HashSet) HoodieSparkTable(org.apache.hudi.table.HoodieSparkTable) HoodieRequestedReplaceMetadata(org.apache.hudi.avro.model.HoodieRequestedReplaceMetadata) HoodieTableMetaClient(org.apache.hudi.common.table.HoodieTableMetaClient) HoodieSparkCopyOnWriteTable(org.apache.hudi.table.HoodieSparkCopyOnWriteTable) HoodieTimeline(org.apache.hudi.common.table.timeline.HoodieTimeline) ExecutorService(java.util.concurrent.ExecutorService) GenericRecord(org.apache.avro.generic.GenericRecord) ASYNC_CLUSTERING_ENABLE(org.apache.hudi.config.HoodieClusteringConfig.ASYNC_CLUSTERING_ENABLE) TypedProperties(org.apache.hudi.common.config.TypedProperties) NULL_SCHEMA(org.apache.hudi.common.testutils.HoodieTestDataGenerator.NULL_SCHEMA) Mockito.when(org.mockito.Mockito.when) FileCreateUtils(org.apache.hudi.common.testutils.FileCreateUtils) WriteStatus(org.apache.hudi.client.WriteStatus) HoodieRecordPayload(org.apache.hudi.common.model.HoodieRecordPayload) ClusteringTestUtils(org.apache.hudi.common.testutils.ClusteringTestUtils) SparkPreCommitValidator(org.apache.hudi.client.validator.SparkPreCommitValidator) SparkRDDWriteClient(org.apache.hudi.client.SparkRDDWriteClient) HoodieIndexConfig(org.apache.hudi.config.HoodieIndexConfig) HoodieClusteringConfig(org.apache.hudi.config.HoodieClusteringConfig) LogManager(org.apache.log4j.LogManager) Collections(java.util.Collections) FSUtils(org.apache.hudi.common.fs.FSUtils) Pair(org.apache.hudi.common.util.collection.Pair) SparkRDDWriteClient(org.apache.hudi.client.SparkRDDWriteClient) HoodieWriteConfig(org.apache.hudi.config.HoodieWriteConfig) HoodieInsertException(org.apache.hudi.exception.HoodieInsertException) JavaRDD(org.apache.spark.api.java.JavaRDD) HoodieJavaRDD(org.apache.hudi.data.HoodieJavaRDD) HoodieValidationException(org.apache.hudi.exception.HoodieValidationException) SqlQuerySingleResultPreCommitValidator(org.apache.hudi.client.validator.SqlQuerySingleResultPreCommitValidator) HoodiePreCommitValidatorConfig(org.apache.hudi.config.HoodiePreCommitValidatorConfig) WriteStatus(org.apache.hudi.client.WriteStatus) ParameterizedTest(org.junit.jupiter.params.ParameterizedTest) Test(org.junit.jupiter.api.Test)

Aggregations

HoodieInsertException (org.apache.hudi.exception.HoodieInsertException)8 IOException (java.io.IOException)4 HoodieWriteConfig (org.apache.hudi.config.HoodieWriteConfig)4 HoodieUpsertException (org.apache.hudi.exception.HoodieUpsertException)4 Test (org.junit.jupiter.api.Test)3 SqlQuerySingleResultPreCommitValidator (org.apache.hudi.client.validator.SqlQuerySingleResultPreCommitValidator)2 HoodieRecord (org.apache.hudi.common.model.HoodieRecord)2 HoodieIOException (org.apache.hudi.exception.HoodieIOException)2 ParameterizedTest (org.junit.jupiter.params.ParameterizedTest)2 ArrayList (java.util.ArrayList)1 Arrays (java.util.Arrays)1 Collection (java.util.Collection)1 Collections (java.util.Collections)1 HashMap (java.util.HashMap)1 HashSet (java.util.HashSet)1 List (java.util.List)1 Map (java.util.Map)1 Properties (java.util.Properties)1 Set (java.util.Set)1 UUID (java.util.UUID)1