LuciferYang commented on a change in pull request #35262:
URL: https://github.com/apache/spark/pull/35262#discussion_r789320438
##########
File path:
sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedDeltaByteArrayReader.java
##########
@@ -16,51 +16,133 @@
*/
package org.apache.spark.sql.execution.datasources.parquet;
+import static org.apache.spark.sql.types.DataTypes.BinaryType;
+import static org.apache.spark.sql.types.DataTypes.IntegerType;
+
import org.apache.parquet.bytes.ByteBufferInputStream;
-import org.apache.parquet.column.values.deltastrings.DeltaByteArrayReader;
+import org.apache.parquet.column.values.RequiresPreviousReader;
+import org.apache.parquet.column.values.ValuesReader;
import org.apache.parquet.io.api.Binary;
+import org.apache.spark.memory.MemoryMode;
+import org.apache.spark.sql.execution.vectorized.OffHeapColumnVector;
+import org.apache.spark.sql.execution.vectorized.OnHeapColumnVector;
import org.apache.spark.sql.execution.vectorized.WritableColumnVector;
import java.io.IOException;
import java.nio.ByteBuffer;
/**
- * An implementation of the Parquet DELTA_BYTE_ARRAY decoder that supports the
vectorized interface.
+ * An implementation of the Parquet DELTA_BYTE_ARRAY decoder that supports the
vectorized
+ * interface.
*/
-public class VectorizedDeltaByteArrayReader extends VectorizedReaderBase {
- private final DeltaByteArrayReader deltaByteArrayReader = new
DeltaByteArrayReader();
+public class VectorizedDeltaByteArrayReader extends VectorizedReaderBase
+ implements VectorizedValuesReader, RequiresPreviousReader {
+
+ private final MemoryMode memoryMode;
+ private int valueCount;
+ private final VectorizedDeltaBinaryPackedReader prefixLengthReader =
+ new VectorizedDeltaBinaryPackedReader();
+ private final VectorizedDeltaLengthByteArrayReader suffixReader;
+ private WritableColumnVector prefixLengthVector;
+ private WritableColumnVector suffixVector;
+ private byte[] previous = new byte[0];
+ private int currentRow = 0;
+
+ //temporary variable used by getBinary
+ Binary binaryVal;
+
+ VectorizedDeltaByteArrayReader(MemoryMode memoryMode){
+ this.memoryMode = memoryMode;
+ this.suffixReader = new VectorizedDeltaLengthByteArrayReader(memoryMode);
+ }
@Override
public void initFromPage(int valueCount, ByteBufferInputStream in) throws
IOException {
- deltaByteArrayReader.initFromPage(valueCount, in);
+ this.valueCount = valueCount;
Review comment:
hmm... may be a stupid question, why does
`VectorizedDeltaByteArrayReader` need to hold `valueCount`?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]