This is an automated email from the ASF dual-hosted git repository.
lzljs3620320 pushed a change to branch release-1.0
in repository https://gitbox.apache.org/repos/asf/paimon.git
from 3df6b2a004 [core] Fix Add min_partition_stats and max_partition_stats
columns to manifests system table
new 6513f1eaf6 [hotfix] [docs] Fix cdc doc url and some typos (#4968)
new 4a43901b62 [parquet] Refactory parquet reader using spark code. (#4982)
new b7cdb3da43 [hotfix] Fix compile errors from cherry-pick
new 0d3aa1b0a3 [test][flink] Add tests back in PreAggregationITCase which
deleted by #4982
new e1b70da24c [parquet] Parquet ColumnarBatch should return
ColumnarRowIterator for nested schema
new 30b0651a3a [parquet] Introduce LongIterator to Parquet
RowIndexGenerator (#4991)
new a4610cd9ef [hotfix] Fix NPE in ColumnarRowIterator.reset
The 7 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:
LICENSE | 14 +
docs/content/cdc-ingestion/kafka-cdc.md | 4 +-
docs/content/cdc-ingestion/mongo-cdc.md | 4 +-
docs/content/cdc-ingestion/postgres-cdc.md | 2 +-
docs/content/cdc-ingestion/pulsar-cdc.md | 4 +-
.../shortcodes/generated/kafka_sync_database.html | 2 +-
.../shortcodes/generated/kafka_sync_table.html | 2 +-
.../generated/mongodb_sync_database.html | 2 +-
.../shortcodes/generated/mysql_sync_database.html | 6 +-
.../shortcodes/generated/mysql_sync_table.html | 4 +-
.../shortcodes/generated/postgres_sync_table.html | 2 +-
.../shortcodes/generated/pulsar_sync_database.html | 2 +-
.../shortcodes/generated/pulsar_sync_table.html | 2 +-
.../converter/Arrow2PaimonVectorConverter.java | 11 +-
.../paimon/arrow/writer/ArrowFieldWriters.java | 4 +-
.../apache/paimon/data/columnar/ColumnVector.java | 9 +
.../paimon/data/columnar/ColumnarRowIterator.java | 20 +-
.../paimon/data/columnar/MapColumnVector.java | 4 -
.../data/columnar/VectorizedRowIterator.java | 3 +-
.../columnar/heap/AbstractArrayBasedVector.java | 80 ++
.../data/columnar/heap/AbstractHeapVector.java | 33 +-
.../data/columnar/heap/AbstractStructVector.java | 35 +-
.../columnar/heap/CastedArrayColumnVector.java | 51 +-
.../data/columnar/heap/CastedMapColumnVector.java | 61 ++
...apRowVector.java => CastedRowColumnVector.java} | 49 +-
.../data/columnar/heap/ElementCountable.java | 2 +-
.../paimon/data/columnar/heap/HeapArrayVector.java | 54 +-
.../data/columnar/heap/HeapBooleanVector.java | 37 +
.../paimon/data/columnar/heap/HeapByteVector.java | 17 +
.../paimon/data/columnar/heap/HeapBytesVector.java | 77 +-
.../data/columnar/heap/HeapDoubleVector.java | 17 +
.../paimon/data/columnar/heap/HeapFloatVector.java | 17 +
.../paimon/data/columnar/heap/HeapIntVector.java | 37 +
.../paimon/data/columnar/heap/HeapLongVector.java | 17 +
.../paimon/data/columnar/heap/HeapMapVector.java | 50 +-
.../paimon/data/columnar/heap/HeapRowVector.java | 33 +-
.../paimon/data/columnar/heap/HeapShortVector.java | 17 +
.../data/columnar/heap/HeapTimestampVector.java | 27 +-
.../columnar/writable/AbstractWritableVector.java | 72 +-
.../columnar/writable/WritableBooleanVector.java | 6 +
.../columnar/writable/WritableBytesVector.java | 2 +-
.../columnar/writable/WritableColumnVector.java | 16 +
.../data/columnar/writable/WritableIntVector.java | 4 +
.../java/org/apache/paimon/utils/LongIterator.java | 69 ++
.../apache/paimon/utils/VectorMappingUtils.java | 24 -
.../data/calumnar/heap/RowColumnVectorTest.java | 69 ++
.../apache/paimon/format/FormatReadWriteTest.java | 99 +-
.../{BinPackingTest.java => LongIteratorTest.java} | 33 +-
.../src/main/java/org/apache/orc/OrcConf.java | 2 +-
.../format/orc/reader/OrcMapColumnVector.java | 9 +-
.../format/parquet/ParquetReaderFactory.java | 40 +-
.../format/parquet/newreader/ColumnarBatch.java | 72 ++
.../parquet/newreader/ParquetColumnVector.java | 378 +++++++
.../{reader => newreader}/ParquetReadState.java | 96 +-
.../parquet/newreader/ParquetVectorUpdater.java | 98 ++
.../newreader/ParquetVectorUpdaterFactory.java | 805 +++++++++++++++
.../parquet/newreader/RowIndexGenerator.java | 62 ++
.../parquet/newreader/VectorizedColumnReader.java | 369 +++++++
.../VectorizedDeltaBinaryPackedReader.java | 299 ++++++
.../newreader/VectorizedDeltaByteArrayReader.java | 153 +++
.../VectorizedDeltaLengthByteArrayReader.java | 95 ++
.../newreader/VectorizedParquetRecordReader.java | 349 +++++++
.../newreader/VectorizedPlainValuesReader.java | 319 ++++++
.../parquet/newreader/VectorizedReaderBase.java | 147 +++
.../newreader/VectorizedRleValuesReader.java | 1046 ++++++++++++++++++++
.../parquet/newreader/VectorizedValuesReader.java | 122 +++
.../format/parquet/reader/BytesColumnReader.java | 6 +-
.../reader/FixedLenBytesBinaryColumnReader.java | 4 +-
.../reader/FixedLenBytesDecimalColumnReader.java | 4 +-
.../format/parquet/reader/NestedColumnReader.java | 13 +-
.../reader/NestedPrimitiveColumnReader.java | 10 +-
.../parquet/reader/ParquetDecimalVector.java | 94 +-
.../parquet/reader/ParquetSplitReaderUtil.java | 26 +-
.../format/parquet/reader/RowColumnReader.java | 2 +-
.../paimon/format/parquet/type/ParquetField.java | 15 +-
.../format/parquet/type/ParquetGroupField.java | 10 +-
.../format/parquet/type/ParquetPrimitiveField.java | 10 +-
.../format/parquet/ParquetColumnVectorTest.java | 473 ++-------
.../format/parquet/ParquetReadWriteTest.java | 8 +-
.../spark/sql/InsertOverwriteTableTestBase.scala | 13 +-
80 files changed, 5492 insertions(+), 863 deletions(-)
create mode 100644
paimon-common/src/main/java/org/apache/paimon/data/columnar/heap/AbstractArrayBasedVector.java
copy
paimon-core/src/main/java/org/apache/paimon/mergetree/compact/aggregate/FieldFirstNonNullValueAgg.java
=>
paimon-common/src/main/java/org/apache/paimon/data/columnar/heap/AbstractStructVector.java
(53%)
copy
paimon-format/src/main/java/org/apache/paimon/format/orc/reader/OrcArrayColumnVector.java
=>
paimon-common/src/main/java/org/apache/paimon/data/columnar/heap/CastedArrayColumnVector.java
(51%)
create mode 100644
paimon-common/src/main/java/org/apache/paimon/data/columnar/heap/CastedMapColumnVector.java
copy
paimon-common/src/main/java/org/apache/paimon/data/columnar/heap/{HeapRowVector.java
=> CastedRowColumnVector.java} (53%)
create mode 100644
paimon-common/src/main/java/org/apache/paimon/utils/LongIterator.java
create mode 100644
paimon-common/src/test/java/org/apache/paimon/data/calumnar/heap/RowColumnVectorTest.java
copy paimon-common/src/test/java/org/apache/paimon/utils/{BinPackingTest.java
=> LongIteratorTest.java} (54%)
create mode 100644
paimon-format/src/main/java/org/apache/paimon/format/parquet/newreader/ColumnarBatch.java
create mode 100644
paimon-format/src/main/java/org/apache/paimon/format/parquet/newreader/ParquetColumnVector.java
copy paimon-format/src/main/java/org/apache/paimon/format/parquet/{reader =>
newreader}/ParquetReadState.java (57%)
create mode 100644
paimon-format/src/main/java/org/apache/paimon/format/parquet/newreader/ParquetVectorUpdater.java
create mode 100644
paimon-format/src/main/java/org/apache/paimon/format/parquet/newreader/ParquetVectorUpdaterFactory.java
create mode 100644
paimon-format/src/main/java/org/apache/paimon/format/parquet/newreader/RowIndexGenerator.java
create mode 100644
paimon-format/src/main/java/org/apache/paimon/format/parquet/newreader/VectorizedColumnReader.java
create mode 100644
paimon-format/src/main/java/org/apache/paimon/format/parquet/newreader/VectorizedDeltaBinaryPackedReader.java
create mode 100644
paimon-format/src/main/java/org/apache/paimon/format/parquet/newreader/VectorizedDeltaByteArrayReader.java
create mode 100644
paimon-format/src/main/java/org/apache/paimon/format/parquet/newreader/VectorizedDeltaLengthByteArrayReader.java
create mode 100644
paimon-format/src/main/java/org/apache/paimon/format/parquet/newreader/VectorizedParquetRecordReader.java
create mode 100644
paimon-format/src/main/java/org/apache/paimon/format/parquet/newreader/VectorizedPlainValuesReader.java
create mode 100644
paimon-format/src/main/java/org/apache/paimon/format/parquet/newreader/VectorizedReaderBase.java
create mode 100644
paimon-format/src/main/java/org/apache/paimon/format/parquet/newreader/VectorizedRleValuesReader.java
create mode 100644
paimon-format/src/main/java/org/apache/paimon/format/parquet/newreader/VectorizedValuesReader.java