[WIP] [parquet] Refactory parquet reader using spark code. #4982
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
leaves12138
force-pushed
the
newParquetReader
branch
from
3df041e to
0254422
Compare
JingsongLi
reviewed
Jan 23, 2025
|
|
||
| @Override | ||
| public VectorizedColumnBatch getBatch() { | ||
| return new VectorizedColumnBatch(children); |
There was a problem hiding this comment.
use batch from constructor
JingsongLi
reviewed
Jan 23, 2025
| import org.apache.paimon.data.columnar.MapColumnVector; | ||
|
|
||
| /** Wrap for MapColumnVector. */ | ||
| public class WrapMapColumnVector implements MapColumnVector { |
JingsongLi
reviewed
Jan 23, 2025
| import org.apache.paimon.data.columnar.ColumnarArray; | ||
|
|
||
| /** Wrap for ArrayColumnVector. */ | ||
| public class WrapArrayColumnVector implements ArrayColumnVector { |
There was a problem hiding this comment.
CastedArrayColumnVector
JingsongLi
reviewed
Jan 23, 2025
| import org.apache.paimon.data.columnar.VectorizedColumnBatch; | ||
|
|
||
| /** Wrap for RowColumnVector. */ | ||
| public class WrapRowColumnVector implements RowColumnVector { |
JingsongLi
reviewed
Jan 23, 2025
| implements WritableColumnVector { | ||
|
|
||
| protected ColumnVector[] children; | ||
| protected long[] offsets; |
There was a problem hiding this comment.
We should introduce a AbstractArrayBasedVector for array and map to contain offsets and lenths..
JingsongLi
reviewed
Jan 23, 2025
| columnarRow.setRowId(i); | ||
| return columnarRow; | ||
| } | ||
|
|
||
| @Override | ||
| public VectorizedColumnBatch getBatch() { | ||
| return new VectorizedColumnBatch(fields); | ||
| return new VectorizedColumnBatch(children); |
There was a problem hiding this comment.
use vectorizedColumnBatch
JingsongLi
reviewed
Jan 23, 2025
| import org.apache.paimon.data.columnar.ColumnVector; | ||
| import org.apache.paimon.data.columnar.ColumnarArray; | ||
|
|
||
| /** Wrap for ArrayColumnVector. */ |
JingsongLi
reviewed
Jan 23, 2025
| import org.apache.paimon.data.columnar.ColumnarMap; | ||
| import org.apache.paimon.data.columnar.MapColumnVector; | ||
|
|
||
| /** Wrap for MapColumnVector. */ |
JingsongLi
reviewed
Jan 23, 2025
| import org.apache.paimon.data.columnar.RowColumnVector; | ||
| import org.apache.paimon.data.columnar.VectorizedColumnBatch; | ||
|
|
||
| /** Test for RowColumnVector. */ |
JingsongLi
reviewed
Jan 23, 2025
| @@ -46,4 +46,10 @@ public interface WritableIntVector extends WritableColumnVector, IntColumnVector | |||
|
|
|||
| /** Fill the column vector with the provided value. */ | |||
| void fill(int value); | |||
|
|
|||
| @SuppressWarnings("unused") | |||
| int appendInt(int v); | |||
JingsongLi
reviewed
Jan 23, 2025
| int appendInt(int v); | ||
|
|
||
| @SuppressWarnings("unused") | ||
| int appendInts(int count, int v); |
JingsongLi
reviewed
Jan 23, 2025
| @@ -204,6 +213,16 @@ public void fill(int value) { | |||
| } | |||
| } | |||
|
|
|||
| @Override | |||
| public int appendInt(int v) { | |||
| return 0; | |||
There was a problem hiding this comment.
if (vector instanceof WritableBytesVector) {
xxxxxx
}
JingsongLi
reviewed
Jan 23, 2025
|
|
||
| @Override | ||
| public int appendInts(int count, int v) { | ||
| return 0; |
JingsongLi
reviewed
Jan 23, 2025
| @@ -262,7 +275,7 @@ void testContinuousRepetition(int rowGroupSize) throws IOException { | |||
| @ParameterizedTest | |||
| @MethodSource("parameters") | |||
| void testLargeValue(int rowGroupSize) throws IOException { | |||
| int number = 10000; | |||
| int number = 1000; | |||
JingsongLi
reviewed
Jan 23, 2025
| @@ -569,15 +569,9 @@ abstract class InsertOverwriteTableTestBase extends PaimonSparkTestBase { | |||
| s"CREATE TABLE t (i INT, s STRUCT<f1: INT, f2: INT>) TBLPROPERTIES ('file.format' = '$format')") | |||
| sql( | |||
| "INSERT INTO t VALUES (1, STRUCT(1, 1)), (2, null), (3, STRUCT(1, null)), (4, STRUCT(null, null))") | |||
| if (format.equals("parquet")) { | |||
There was a problem hiding this comment.
@Zouxxyy Fix the bug here.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Purpose
This pull request is not ready.
This closes #4785 too
Tests
API and Format
Documentation