This is an automated email from the ASF dual-hosted git repository.
vhs pushed a change to branch phase-18-HoodieAvroUtils-removal
in repository https://gitbox.apache.org/repos/asf/hudi.git
omit a4939d12b7d9 Fix test: testValidateDataTypeForSecondaryIndex
omit a88ae9de253e Fix test: test Secondary Index With All DataTypes
omit 3bd409f28d01 Address comments
omit 37cd2425506e Address comments
omit 1235700739b3 Address comments
omit a7fd9fa3f96d Remove HoodieAvroUtils from hudi-client-common Additional
compilation error fixes - AvroOrcUtils - HoodieBootstrapSchemaProvider -
HoodieSparkBootstrapSchemaProvider - TestOrcBootstrap
add 3ffa725fb53f chore(ci): Retry spark downloads (#17732)
add 35b2e3b4d216 remove arg line overrides (#17741)
add 23df870b8dc3 perf: optimize rollback validation by checking lazy
rollback policy before clustering validation (#17537)
add d640774f9953 perf: use shallow projection where applicable (#17682)
add 1ea15c158183 chore(ci): upgrade to newer plugins and new test
dependencies that required java11+ (#17657)
add 351efaef4f3a docs: Improve the annotation format of examples (#17749)
add ede951394e39 refactor: Replace HoodieHadoopStorage instantiation with
HoodieStorageFactory (#17661)
add a74d00a1b673 feat: Implement SparkColumnarFileReader for Datasource
integration with Lance (#17660)
add e9c74139f03e chore(ci): add cache arg (#17738)
add 46738d00bdf3 feat(schema): Migrate hudi spark client to use
HoodieSchema (#17743)
new 82240333bb0f Remove HoodieAvroUtils from hudi-client-common Additional
compilation error fixes - AvroOrcUtils - HoodieBootstrapSchemaProvider -
HoodieSparkBootstrapSchemaProvider - TestOrcBootstrap - Enable float support in
secondary index - Fix test: test Secondary Index With All DataTypes - Fix test:
testValidateDataTypeForSecondaryIndex
This update added new revisions after undoing existing revisions.
That is to say, some revisions that were in the old version of the
branch are not in the new version. This situation occurs
when a user --force pushes a change and generates a repository
containing something like this:
* -- * -- B -- O -- O -- O (a4939d12b7d9)
\
N -- N -- N refs/heads/phase-18-HoodieAvroUtils-removal
(82240333bb0f)
You should already have received notification emails for all of the O
revisions, and so the following emails describe only the N revisions
from the common base, B.
Any revisions marked "omit" are not gone; other references still
refer to them. Any revisions marked "discard" are gone forever.
The 1 revisions listed above as "new" are entirely new to this
repository and will be described in separate emails. The revisions
listed as "add" were already present in the repository and have only
been added to this reference.
Summary of changes:
.github/workflows/bot.yml | 99 ++++++-----
azure-pipelines-20230430.yml | 14 +-
hudi-aws/pom.xml | 5 -
.../main/java/org/apache/hudi/cli/HoodieCLI.java | 6 +-
.../hudi/cli/commands/TestRepairsCommand.java | 12 +-
hudi-client/hudi-client-common/pom.xml | 5 -
.../partition/PartitionBucketIndexUtils.java | 5 +-
.../java/org/apache/hudi/io/HoodieCDCLogger.java | 17 +-
.../rollback/BaseRollbackActionExecutor.java | 69 ++++----
.../timeline/TestHoodieTimelineArchiver.java | 4 +-
.../hudi/index/simple/TestGlobalSimpleIndex.java | 5 +-
.../apache/hudi/index/simple/TestSimpleIndex.java | 5 +-
.../GenericRecordValidationTestUtils.java | 4 +-
.../read/HoodieFileGroupReaderOnJavaTestBase.java | 4 +-
.../hadoop/TestHoodieFileGroupReaderOnHive.java | 7 +-
.../MultipleSparkJobExecutionStrategy.java | 6 +-
...SparkJobConsistentHashingExecutionStrategy.java | 13 +-
...onsistentBucketClusteringExecutionStrategy.java | 3 +-
.../SparkSingleFileSortExecutionStrategy.java | 5 +-
.../SparkSortAndSizeExecutionStrategy.java | 5 +-
.../client/utils/SparkMetadataWriterUtils.java | 10 +-
.../hudi/common/model/HoodieSparkRecord.java | 33 ++--
.../hudi/execution/SparkLazyInsertIterable.java | 15 +-
.../bulkinsert/RDDBucketIndexPartitioner.java | 11 +-
.../bulkinsert/RDDSpatialCurveSortPartitioner.java | 2 +-
.../io/storage/HoodieSparkFileWriterFactory.java | 16 +-
.../hudi/io/storage/HoodieSparkLanceReader.java | 119 +-------------
.../hudi/io/storage/HoodieSparkParquetReader.java | 12 +-
.../hudi/io/storage/LanceRecordIterator.java | 183 +++++++++++++++++++++
.../apache/hudi/merge/SparkRecordMergingUtils.java | 4 +-
.../bootstrap/BaseBootstrapMetadataHandler.java | 11 +-
.../bootstrap/OrcBootstrapMetadataHandler.java | 12 +-
.../bootstrap/ParquetBootstrapMetadataHandler.java | 16 +-
.../hudi/BaseSparkInternalRecordContext.java | 15 +-
.../hudi/BaseSparkInternalRowReaderContext.java | 2 +-
.../hudi/HoodieDatasetBulkInsertHelper.scala | 7 +-
.../scala/org/apache/hudi/HoodieSparkUtils.scala | 5 +-
.../SparkFileFormatInternalRecordContext.scala | 13 +-
.../SparkFileFormatInternalRowReaderContext.scala | 4 +-
.../apache/spark/sql/HoodieInternalRowUtils.scala | 26 ++-
.../org/apache/spark/sql/hudi/SparkAdapter.scala | 14 ++
.../callback/TestHoodieClientInitCallback.java | 16 +-
.../hudi/client/TestUpdateSchemaEvolution.java | 5 +-
.../functional/TestExternalPathHandling.java | 12 +-
.../functional/TestHoodieBackedTableMetadata.java | 7 +-
.../hudi/keygen/KeyGeneratorTestUtilities.java | 8 +-
.../hudi/testutils/FunctionalTestHarness.java | 10 +-
.../SparkClientFunctionalTestHarness.java | 4 +-
hudi-common/pom.xml | 7 -
.../java/org/apache/hudi/avro/HoodieAvroUtils.java | 40 +++++
.../apache/hudi/common/model/HoodieAvroRecord.java | 2 +-
.../apache/hudi/common/model/HoodieFileFormat.java | 6 +-
.../hudi/io/storage/HoodieFileWriterFactory.java | 10 ++
.../examples/spark/HoodieDataSourceExample.scala | 5 +-
.../examples/spark/HoodieMorCompactionJob.scala | 2 +
hudi-flink-datasource/hudi-flink/pom.xml | 5 -
.../sink/partitioner/profile/WriteProfiles.java | 3 +-
.../hudi/table/format/InternalSchemaManager.java | 4 +-
.../hudi/table/format/cdc/CdcInputFormat.java | 5 +-
hudi-gcp/pom.xml | 6 -
.../org/apache/hudi/common/fs/TestFSUtils.java | 13 +-
.../common/fs/TestHoodieWrapperFileSystem.java | 6 +-
.../common/functional/TestHoodieLogFormat.java | 12 +-
.../TestHoodieLogFormatAppendFailure.java | 8 +-
.../hudi/common/table/TestTableSchemaResolver.java | 7 +-
.../reader/HoodieFileGroupReaderTestHarness.java | 4 +-
.../hudi/hadoop/HoodieParquetInputFormat.java | 6 +-
.../hudi/hadoop/HoodieROTablePathFilter.java | 4 +-
.../apache/hudi/hadoop/SchemaEvolutionContext.java | 8 +-
.../hadoop/hive/HoodieCombineHiveInputFormat.java | 7 +-
.../hive/TestHoodieCombineHiveInputFormat.java | 7 +-
.../TestHoodieMergeOnReadTableInputFormat.java | 7 +-
.../realtime/TestHoodieRealtimeRecordReader.java | 6 +-
.../hudi/hadoop/testutils/InputFormatTestUtil.java | 6 +-
.../scala/org/apache/hudi/AvroProjection.scala | 44 -----
.../main/scala/org/apache/hudi/DefaultSource.scala | 3 +-
.../org/apache/hudi/HoodieCreateRecordUtils.scala | 4 +-
.../org/apache/hudi/HoodieSparkSqlWriter.scala | 2 +-
.../org/apache/hudi/cdc/CDCFileGroupIterator.scala | 2 +-
.../datasources/lance/SparkLanceReaderBase.scala | 140 ++++++++++++++++
.../HoodieFileGroupReaderBasedFileFormat.scala | 6 +
.../parquet/ParquetSchemaEvolutionUtils.scala | 5 +-
.../procedures/ShowInvalidParquetProcedure.scala | 4 +-
.../ShowMetadataTablePartitionsProcedure.scala | 5 +-
.../org/apache/hudi/ColumnStatsIndexHelper.java | 5 +-
.../hudi/functional/TestBufferedRecordMerger.java | 2 +-
.../hudi/TestParquetReaderCompatibility.scala | 5 +-
.../read/TestHoodieFileGroupReaderOnSpark.scala | 2 +-
.../hudi/functional/TestLanceDataSource.scala | 132 +++++++++++++++
.../TestMetadataTableWithSparkDataSource.scala | 6 +-
.../functional/TestParquetColumnProjection.scala | 6 +-
.../hudi/common/TestHoodieInternalRowUtils.scala | 8 +-
.../apache/spark/sql/adapter/Spark3_3Adapter.scala | 7 +
.../Spark33LegacyHoodieParquetFileFormat.scala | 5 +-
.../apache/spark/sql/adapter/Spark3_4Adapter.scala | 8 +
.../Spark34LegacyHoodieParquetFileFormat.scala | 5 +-
.../apache/spark/sql/adapter/Spark3_5Adapter.scala | 8 +
.../Spark35LegacyHoodieParquetFileFormat.scala | 5 +-
.../apache/spark/sql/adapter/Spark4_0Adapter.scala | 8 +
.../Spark40LegacyHoodieParquetFileFormat.scala | 4 +-
.../hudi/sync/datahub/TestDataHubSyncClient.java | 2 +-
.../apache/hudi/hive/testutils/HiveTestUtil.java | 6 +-
hudi-tests-common/pom.xml | 10 +-
.../hudi/utilities/HoodieSnapshotExporter.java | 5 +-
.../org/apache/hudi/utilities/TableSizeStats.java | 4 +-
.../hudi/utilities/sources/HoodieIncrSource.java | 6 +-
.../hudi/utilities/streamer/HoodieStreamer.java | 6 +-
.../apache/hudi/utilities/streamer/StreamSync.java | 5 +-
.../utilities/testutils/UtilitiesTestBase.java | 7 +-
packaging/bundle-validation/azure/Dockerfile | 2 +-
.../docker_java17/docker_java17_test.sh | 2 +-
pom.xml | 84 +++++++---
112 files changed, 1061 insertions(+), 590 deletions(-)
create mode 100644
hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/io/storage/LanceRecordIterator.java
delete mode 100644
hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/hudi/AvroProjection.scala
create mode 100644
hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/spark/sql/execution/datasources/lance/SparkLanceReaderBase.scala
create mode 100644
hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/hudi/functional/TestLanceDataSource.scala
