Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/13680#discussion_r69392506
--- Diff:
sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/UnsafeArrayData.java
---
@@ -341,63 +325,115 @@ public UnsafeArrayData copy() {
return arrayCopy;
}
- public static UnsafeArrayData fromPrimitiveArray(int[] arr) {
- if (arr.length > (Integer.MAX_VALUE - 4) / 8) {
- throw new UnsupportedOperationException("Cannot convert this array
to unsafe format as " +
- "it's too big.");
- }
+ @Override
+ public boolean[] toBooleanArray() {
+ int size = numElements();
+ boolean[] values = new boolean[size];
+ Platform.copyMemory(
+ baseObject, baseOffset + headerInBytes, values,
Platform.BYTE_ARRAY_OFFSET, size);
+ return values;
+ }
- final int offsetRegionSize = 4 * arr.length;
- final int valueRegionSize = 4 * arr.length;
- final int totalSize = 4 + offsetRegionSize + valueRegionSize;
- final byte[] data = new byte[totalSize];
+ @Override
+ public byte[] toByteArray() {
+ int size = numElements();
+ byte[] values = new byte[size];
+ Platform.copyMemory(
+ baseObject, baseOffset + headerInBytes, values,
Platform.BYTE_ARRAY_OFFSET, size);
+ return values;
+ }
- Platform.putInt(data, Platform.BYTE_ARRAY_OFFSET, arr.length);
+ @Override
+ public short[] toShortArray() {
+ int size = numElements();
+ short[] values = new short[size];
+ Platform.copyMemory(
+ baseObject, baseOffset + headerInBytes, values,
Platform.SHORT_ARRAY_OFFSET, size * 2);
+ return values;
+ }
- int offsetPosition = Platform.BYTE_ARRAY_OFFSET + 4;
- int valueOffset = 4 + offsetRegionSize;
- for (int i = 0; i < arr.length; i++) {
- Platform.putInt(data, offsetPosition, valueOffset);
- offsetPosition += 4;
- valueOffset += 4;
- }
+ @Override
+ public int[] toIntArray() {
+ int size = numElements();
+ int[] values = new int[size];
+ Platform.copyMemory(
+ baseObject, baseOffset + headerInBytes, values,
Platform.INT_ARRAY_OFFSET, size * 4);
+ return values;
+ }
- Platform.copyMemory(arr, Platform.INT_ARRAY_OFFSET, data,
- Platform.BYTE_ARRAY_OFFSET + 4 + offsetRegionSize, valueRegionSize);
+ @Override
+ public long[] toLongArray() {
+ int size = numElements();
+ long[] values = new long[size];
+ Platform.copyMemory(
+ baseObject, baseOffset + headerInBytes, values,
Platform.LONG_ARRAY_OFFSET, size * 8);
+ return values;
+ }
- UnsafeArrayData result = new UnsafeArrayData();
- result.pointTo(data, Platform.BYTE_ARRAY_OFFSET, totalSize);
- return result;
+ @Override
+ public float[] toFloatArray() {
+ int size = numElements();
+ float[] values = new float[size];
+ Platform.copyMemory(
+ baseObject, baseOffset + headerInBytes, values,
Platform.FLOAT_ARRAY_OFFSET, size * 4);
+ return values;
}
- public static UnsafeArrayData fromPrimitiveArray(double[] arr) {
- if (arr.length > (Integer.MAX_VALUE - 4) / 12) {
+ @Override
+ public double[] toDoubleArray() {
+ int size = numElements();
+ double[] values = new double[size];
+ Platform.copyMemory(
+ baseObject, baseOffset + headerInBytes, values,
Platform.DOUBLE_ARRAY_OFFSET, size * 8);
+ return values;
+ }
+
+ private static UnsafeArrayData fromPrimitiveArray(
+ Object arr, int offset, int length, int elementSize) {
+ final long headerSize = calculateHeaderPortionInBytes(length);
+ final long valueRegionSize = (long)elementSize * (long)length;
+ final long allocationSize = (headerSize + valueRegionSize + 7) / 8;
+ if (allocationSize > (long)Integer.MAX_VALUE) {
throw new UnsupportedOperationException("Cannot convert this array
to unsafe format as " +
"it's too big.");
}
- final int offsetRegionSize = 4 * arr.length;
- final int valueRegionSize = 8 * arr.length;
- final int totalSize = 4 + offsetRegionSize + valueRegionSize;
- final byte[] data = new byte[totalSize];
+ final long[] data = new long[(int)allocationSize];
- Platform.putInt(data, Platform.BYTE_ARRAY_OFFSET, arr.length);
-
- int offsetPosition = Platform.BYTE_ARRAY_OFFSET + 4;
- int valueOffset = 4 + offsetRegionSize;
- for (int i = 0; i < arr.length; i++) {
- Platform.putInt(data, offsetPosition, valueOffset);
- offsetPosition += 4;
- valueOffset += 8;
- }
-
- Platform.copyMemory(arr, Platform.DOUBLE_ARRAY_OFFSET, data,
- Platform.BYTE_ARRAY_OFFSET + 4 + offsetRegionSize, valueRegionSize);
+ Platform.putInt(data, Platform.LONG_ARRAY_OFFSET, length);
+ Platform.copyMemory(arr, offset, data,
+ Platform.LONG_ARRAY_OFFSET + headerSize, valueRegionSize);
UnsafeArrayData result = new UnsafeArrayData();
- result.pointTo(data, Platform.BYTE_ARRAY_OFFSET, totalSize);
+ result.pointTo(data, Platform.LONG_ARRAY_OFFSET, (int)allocationSize *
8);
--- End diff --
`allocationSize` can be `Integer.MAX_VALUE`, looks like we may overflow
here?
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
