This is an automated email from the ASF dual-hosted git repository.
github-actions[bot] pushed a change to branch bot/trino-pin
in repository https://gitbox.apache.org/repos/asf/hudi.git
discard ec2a38de7d95 chore(trino): advance trino master pin to 1404575b02a9
add 2fc6486f9b29 perf(spark): ship file group reader scan state once per
executor (#20077)
add fa254c28c2d1 fix(metadata): skip the meta folder when listing
partitions from the file system (#20080)
add 8e0402db7cc7 fix(hfile): bound compressed block decompression (#19930)
add 76da56fd81de refactor(core): read file groups from a table state
instead of a meta client (#20078)
add 1c30d058c579 perf(spark): stop per-file Hadoop configuration parsing
and copies on the parquet read path (#20079)
add 438c0d372569 fix(spark): group file slices by partition in the file
index listing (#20115)
add 862f4b9a5c92 fix(metadata): key RLI and SI write stats by file group,
not file id (#20188)
new ad3a455d1666 chore(trino): advance trino master pin to a02b3257cebd
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 (ec2a38de7d95)
\
N -- N -- N refs/heads/bot/trino-pin (ad3a455d1666)
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:
.../hudi/cli/commands/HoodieLogFileCommand.java | 3 +-
.../SecondaryIndexRecordGenerationUtils.java | 22 +-
.../metadata/index/record/BaseRecordIndexer.java | 18 +-
.../hudi/io/storage/HoodieSparkParquetReader.java | 26 +-
.../common/schema/internal/InternalSchema.java | 56 +--
.../apache/hudi/common/schema/internal/Types.java | 31 +-
.../hudi/common/table/HoodieTableMetaClient.java | 4 +-
.../table/log/BaseHoodieLogRecordReader.java | 17 +-
.../table/log/HoodieLogBlockMetadataScanner.java | 3 +-
.../common/table/log/HoodieLogFormatReader.java | 25 +-
.../table/log/HoodieMergedLogRecordReader.java | 20 +-
.../hudi/common/table/read/CommittedInstants.java | 115 ++++++
.../table/read/FileGroupReaderSchemaHandler.java | 22 +-
.../common/table/read/HoodieFileGroupReader.java | 35 +-
.../read/ParquetRowIndexBasedSchemaHandler.java | 15 +-
.../apache/hudi/common/table/read/TableState.java | 227 ++++++++++++
.../buffer/DefaultFileGroupRecordBufferLoader.java | 16 +-
.../table/read/buffer/FileGroupRecordBuffer.java | 2 -
.../read/buffer/FileGroupRecordBufferLoader.java | 4 +-
.../read/buffer/KeyBasedFileGroupRecordBuffer.java | 15 +-
.../read/buffer/LogScanningRecordBufferLoader.java | 6 +-
.../buffer/PositionBasedFileGroupRecordBuffer.java | 18 +-
.../ReusableFileGroupRecordBufferLoader.java | 12 +-
.../read/buffer/ReusableKeyBasedRecordBuffer.java | 6 +-
.../SortedKeyBasedFileGroupRecordBuffer.java | 4 +-
.../StreamingFileGroupRecordBufferLoader.java | 10 +-
.../read/buffer/UnmergedFileGroupRecordBuffer.java | 4 +-
.../table/read/lsm/HoodieLsmFileGroupReader.java | 33 +-
.../table/read/lsm/LsmFileGroupRecordIterator.java | 48 ++-
.../common/table/read/lsm/LsmFileIterators.java | 13 +-
.../metadata/FileSystemBackedTableMetadata.java | 6 +-
.../hudi/metadata/HoodieTableMetadataUtil.java | 8 +-
.../hudi/common/table/read/TestTableState.java | 183 ++++++++++
.../read/buffer/BaseTestFileGroupRecordBuffer.java | 3 +-
.../buffer/TestFileGroupRecordBufferLoader.java | 3 +-
.../buffer/TestReusableKeyBasedRecordBuffer.java | 4 +-
.../TestSortedKeyBasedFileGroupRecordBuffer.java | 5 +-
.../read/lsm/TestLsmFileGroupRecordIterator.java | 9 +-
.../org/apache/hudi/common/util/ParquetUtils.java | 22 ++
.../io/storage/hadoop/HoodieAvroParquetReader.java | 9 +-
.../apache/parquet/avro/HoodieAvroReadSupport.java | 2 +-
.../common/table/TestHoodieTableMetaClient.java | 41 +++
.../common/table/read/TestTableStateSnapshot.java | 100 ++++++
.../testutils/FooterKeyDecryptionFactory.java | 96 +++++
.../HadoopDefaultResourceLoadCounter.java | 68 ++++
.../hudi/hadoop/fs/RecordingLocalFileSystem.java | 388 +++++++++++++++++++++
.../hadoop/TestHoodieAvroParquetReader.java | 100 ++++++
.../TestFileSystemBackedTableMetadata.java | 46 +++
.../java/org/apache/hudi/io/hfile/HFileBlock.java | 17 +-
.../org/apache/hudi/io/hfile/TestHFileReader.java | 6 +
.../hudi_1_0_hbase_2_4_9_512KB_GZ_20000.hfile | Bin 101870 -> 101870 bytes
.../scala/org/apache/hudi/HoodieFileIndex.scala | 35 +-
.../hudi/HoodieHadoopFsRelationFactory.scala | 2 +-
.../apache/hudi/HoodieIncrementalFileIndex.scala | 10 +-
.../org/apache/hudi/HoodieMergeOnReadRDDV2.scala | 23 +-
.../apache/hudi/PartitionDirectoryConverter.scala | 55 ++-
.../org/apache/hudi/cdc/CDCFileGroupIterator.scala | 49 ++-
.../HoodieFileGroupReaderBasedFileFormat.scala | 313 ++---------------
.../parquet/HoodieFileGroupReaderFunction.scala | 376 ++++++++++++++++++++
.../parquet/ParquetSchemaEvolutionUtils.scala | 46 ++-
.../parquet/SparkParquetReaderBase.scala | 5 +-
.../parquet/TestParquetSchemaEvolutionUtils.scala | 51 ++-
.../procedures/PartitionBucketIndexManager.scala | 9 +-
.../TestExternalFileRecordAndSecondaryIndex.java | 36 ++
.../TestMetadataUtilRLIandSIRecordGeneration.java | 48 +++
.../TestMergeOnReadSkipsUncommittedLogBlocks.java | 175 ++++++++++
.../TestReadOptionsDoNotOverrideTableConfig.java | 247 +++++++++++++
.../io/storage/TestHoodieSparkParquetReader.java | 133 +++++++
.../io/storage/TestParquetReadOptionsParity.java | 148 ++++++++
.../TestSparkNonBlockingConcurrencyControl.java | 70 +++-
.../org/apache/hudi/TestHoodieFileIndex.scala | 255 +++++++++++++-
.../hudi/TestPartitionDirectoryConverter.scala | 46 ++-
.../hudi/functional/TestBasicSchemaEvolution.scala | 34 +-
.../functional/cdc/TestCDCDataFrameSuite.scala | 15 +-
.../io/storage/ParquetPerFileReadBenchmark.scala | 179 ++++++++++
.../TestHoodieFileGroupReaderFunction.scala | 112 ++++++
.../Spark3LegacyHoodieParquetFileFormat.scala | 2 +-
.../datasources/parquet/Spark33ParquetReader.scala | 8 +-
.../datasources/parquet/Spark34ParquetReader.scala | 8 +-
.../datasources/parquet/Spark35ParquetReader.scala | 8 +-
.../Spark40LegacyHoodieParquetFileFormat.scala | 2 +-
.../datasources/parquet/Spark40ParquetReader.scala | 8 +-
.../Spark41LegacyHoodieParquetFileFormat.scala | 2 +-
.../datasources/parquet/Spark41ParquetReader.scala | 8 +-
.../Spark42LegacyHoodieParquetFileFormat.scala | 2 +-
.../datasources/parquet/Spark42ParquetReader.scala | 8 +-
pom.xml | 2 +-
87 files changed, 3861 insertions(+), 615 deletions(-)
create mode 100644
hudi-common/src/main/java/org/apache/hudi/common/table/read/CommittedInstants.java
create mode 100644
hudi-common/src/main/java/org/apache/hudi/common/table/read/TableState.java
create mode 100644
hudi-common/src/test/java/org/apache/hudi/common/table/read/TestTableState.java
create mode 100644
hudi-hadoop-common/src/test/java/org/apache/hudi/common/table/read/TestTableStateSnapshot.java
create mode 100644
hudi-hadoop-common/src/test/java/org/apache/hudi/common/testutils/FooterKeyDecryptionFactory.java
create mode 100644
hudi-hadoop-common/src/test/java/org/apache/hudi/common/testutils/HadoopDefaultResourceLoadCounter.java
create mode 100644
hudi-hadoop-common/src/test/java/org/apache/hudi/hadoop/fs/RecordingLocalFileSystem.java
create mode 100644
hudi-hadoop-common/src/test/java/org/apache/hudi/io/storage/hadoop/TestHoodieAvroParquetReader.java
create mode 100644
hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/HoodieFileGroupReaderFunction.scala
create mode 100644
hudi-spark-datasource/hudi-spark/src/test/java/org/apache/hudi/functional/TestMergeOnReadSkipsUncommittedLogBlocks.java
create mode 100644
hudi-spark-datasource/hudi-spark/src/test/java/org/apache/hudi/functional/TestReadOptionsDoNotOverrideTableConfig.java
create mode 100644
hudi-spark-datasource/hudi-spark/src/test/java/org/apache/hudi/io/storage/TestHoodieSparkParquetReader.java
create mode 100644
hudi-spark-datasource/hudi-spark/src/test/java/org/apache/hudi/io/storage/TestParquetReadOptionsParity.java
create mode 100644
hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/hudi/io/storage/ParquetPerFileReadBenchmark.scala
create mode 100644
hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/TestHoodieFileGroupReaderFunction.scala
