Skip to content

ARROW-1192: [JAVA] Use buffer slice for splitAndTransfer in List and Union Vectors. #901

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
siddharthteotia wants to merge 2 commits into from
Closed

ARROW-1192: [JAVA] Use buffer slice for splitAndTransfer in List and Union Vectors. #901

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
035e886
Use buffer slice for splitAndTransfer in List and Union vectors
StevenMPhillips Jun 30, 2017
3d89c99
ARROW-1192: splitAndTransfer changes for ListVector,UnionVector and c…
siddharthteotia Jul 27, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 2 additions & 4 deletions java/vector/src/main/codegen/templates/UnionVector.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -321,10 +321,8 @@ public void transfer() {

@Override
public void splitAndTransfer(int startIndex, int length) {
to.allocateNew();
for (int i = 0; i < length; i++) {
to.copyFromSafe(startIndex + i, i, org.apache.arrow.vector.complex.UnionVector.this);
}
internalMapVectorTransferPair.splitAndTransfer(startIndex, length);
typeVectorTransferPair.splitAndTransfer(startIndex, length);
to.getMutator().setValueCount(length);
}

Expand Down
30 changes: 23 additions & 7 deletions java/vector/src/main/java/org/apache/arrow/vector/complex/ListVector.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,6 +38,7 @@
import org.apache.arrow.vector.FieldVector;
import org.apache.arrow.vector.UInt4Vector;
import org.apache.arrow.vector.ValueVector;
import org.apache.arrow.vector.VarCharVector;
import org.apache.arrow.vector.ZeroVector;
import org.apache.arrow.vector.complex.impl.ComplexCopier;
import org.apache.arrow.vector.complex.impl.UnionListReader;
Expand Down Expand Up @@ -179,7 +180,11 @@ public TransferPair makeTransferPair(ValueVector target) {
private class TransferImpl implements TransferPair {

ListVector to;
TransferPair pairs[] = new TransferPair[3];
TransferPair bitsTransferPair;
TransferPair offsetsTransferPair;
TransferPair dataTransferPair;

TransferPair[] pairs;

public TransferImpl(String name, BufferAllocator allocator, CallBack callBack) {
this(new ListVector(name, allocator, fieldType, callBack));
Expand All @@ -188,12 +193,13 @@ public TransferImpl(String name, BufferAllocator allocator, CallBack callBack) {
public TransferImpl(ListVector to) {
this.to = to;
to.addOrGetVector(vector.getField().getFieldType());
pairs[0] = offsets.makeTransferPair(to.offsets);
pairs[1] = bits.makeTransferPair(to.bits);
offsetsTransferPair = offsets.makeTransferPair(to.offsets);
bitsTransferPair = bits.makeTransferPair(to.bits);
if (to.getDataVector() instanceof ZeroVector) {
to.addOrGetVector(vector.getField().getFieldType());
}
pairs[2] = getDataVector().makeTransferPair(to.getDataVector());
dataTransferPair = getDataVector().makeTransferPair(to.getDataVector());
pairs = new TransferPair[] { bitsTransferPair, offsetsTransferPair, dataTransferPair };
}

@Override
Expand All @@ -206,10 +212,20 @@ public void transfer() {

@Override
public void splitAndTransfer(int startIndex, int length) {
to.allocateNew();
for (int i = 0; i < length; i++) {
copyValueSafe(startIndex + i, i);
UInt4Vector.Accessor offsetVectorAccessor = ListVector.this.offsets.getAccessor();
final int startPoint = offsetVectorAccessor.get(startIndex);
final int sliceLength = offsetVectorAccessor.get(startIndex + length) - startPoint;
to.clear();
to.offsets.allocateNew(length + 1);
offsetVectorAccessor = ListVector.this.offsets.getAccessor();
final UInt4Vector.Mutator targetOffsetVectorMutator = to.offsets.getMutator();
for (int i = 0; i < length + 1; i++) {
targetOffsetVectorMutator.set(i, offsetVectorAccessor.get(startIndex + i) - startPoint);
}
bitsTransferPair.splitAndTransfer(startIndex, length);
dataTransferPair.splitAndTransfer(startPoint, sliceLength);
to.lastSet = length;
to.mutator.setValueCount(length);
}

@Override
Expand Down
199 changes: 199 additions & 0 deletions java/vector/src/test/java/org/apache/arrow/vector/TestListVector.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,8 @@

import static org.junit.Assert.assertEquals;
import static org.junit.Assert.assertNull;
import static org.junit.Assert.assertTrue;
import static org.junit.Assert.assertFalse;

import org.apache.arrow.memory.BufferAllocator;
import org.apache.arrow.vector.complex.ListVector;
Expand All @@ -30,6 +32,7 @@
import org.apache.arrow.vector.types.Types;
import org.apache.arrow.vector.types.Types.*;
import org.apache.arrow.vector.types.pojo.FieldType;
import org.apache.arrow.vector.util.TransferPair;
import org.junit.After;
import org.junit.Assert;
import org.junit.Before;
Expand Down Expand Up @@ -234,4 +237,200 @@ public void testSetLastSetUsage() throws Exception {
assertNull(actual);
}
}

@Test
public void testSplitAndTransfer() throws Exception {
try (ListVector listVector = ListVector.empty("sourceVector", allocator)) {

/* Explicitly add the dataVector */
MinorType type = MinorType.BIGINT;
listVector.addOrGetVector(FieldType.nullable(type.getType()));

UnionListWriter listWriter = listVector.getWriter();

/* allocate memory */
listWriter.allocate();

/* populate data */
listWriter.setPosition(0);
listWriter.startList();
listWriter.bigInt().writeBigInt(10);
listWriter.bigInt().writeBigInt(11);
listWriter.bigInt().writeBigInt(12);
listWriter.endList();

listWriter.setPosition(1);
listWriter.startList();
listWriter.bigInt().writeBigInt(13);
listWriter.bigInt().writeBigInt(14);
listWriter.endList();

listWriter.setPosition(2);
listWriter.startList();
listWriter.bigInt().writeBigInt(15);
listWriter.bigInt().writeBigInt(16);
listWriter.bigInt().writeBigInt(17);
listWriter.bigInt().writeBigInt(18);
listWriter.endList();

listWriter.setPosition(3);
listWriter.startList();
listWriter.bigInt().writeBigInt(19);
listWriter.endList();

listWriter.setPosition(4);
listWriter.startList();
listWriter.bigInt().writeBigInt(20);
listWriter.bigInt().writeBigInt(21);
listWriter.bigInt().writeBigInt(22);
listWriter.bigInt().writeBigInt(23);
listWriter.endList();

listVector.getMutator().setValueCount(5);

assertEquals(5, listVector.getMutator().getLastSet());

/* get offsetVector */
UInt4Vector offsetVector = (UInt4Vector)listVector.getOffsetVector();

/* get dataVector */
NullableBigIntVector dataVector = (NullableBigIntVector)listVector.getDataVector();

/* check the vector output */
final UInt4Vector.Accessor offsetAccessor = offsetVector.getAccessor();
final ValueVector.Accessor valueAccessor = dataVector.getAccessor();

int index = 0;
int offset = 0;
Object actual = null;

/* index 0 */
assertFalse(listVector.getAccessor().isNull(index));
offset = offsetAccessor.get(index);
assertEquals(Integer.toString(0), Integer.toString(offset));

actual = valueAccessor.getObject(offset);
assertEquals(new Long(10), (Long)actual);
offset++;
actual = valueAccessor.getObject(offset);
assertEquals(new Long(11), (Long)actual);
offset++;
actual = valueAccessor.getObject(offset);
assertEquals(new Long(12), (Long)actual);

/* index 1 */
index++;
assertFalse(listVector.getAccessor().isNull(index));
offset = offsetAccessor.get(index);
assertEquals(Integer.toString(3), Integer.toString(offset));

actual = valueAccessor.getObject(offset);
assertEquals(new Long(13), (Long)actual);
offset++;
actual = valueAccessor.getObject(offset);
assertEquals(new Long(14), (Long)actual);

/* index 2 */
index++;
assertFalse(listVector.getAccessor().isNull(index));
offset = offsetAccessor.get(index);
assertEquals(Integer.toString(5), Integer.toString(offset));

actual = valueAccessor.getObject(offset);
assertEquals(new Long(15), (Long)actual);
offset++;
actual = valueAccessor.getObject(offset);
assertEquals(new Long(16), (Long)actual);
offset++;
actual = valueAccessor.getObject(offset);
assertEquals(new Long(17), (Long)actual);
offset++;
actual = valueAccessor.getObject(offset);
assertEquals(new Long(18), (Long)actual);

/* index 3 */
index++;
assertFalse(listVector.getAccessor().isNull(index));
offset = offsetAccessor.get(index);
assertEquals(Integer.toString(9), Integer.toString(offset));

actual = valueAccessor.getObject(offset);
assertEquals(new Long(19), (Long)actual);

/* index 4 */
index++;
assertFalse(listVector.getAccessor().isNull(index));
offset = offsetAccessor.get(index);
assertEquals(Integer.toString(10), Integer.toString(offset));

actual = valueAccessor.getObject(offset);
assertEquals(new Long(20), (Long)actual);
offset++;
actual = valueAccessor.getObject(offset);
assertEquals(new Long(21), (Long)actual);
offset++;
actual = valueAccessor.getObject(offset);
assertEquals(new Long(22), (Long)actual);
offset++;
actual = valueAccessor.getObject(offset);
assertEquals(new Long(23), (Long)actual);

/* index 5 */
index++;
assertTrue(listVector.getAccessor().isNull(index));
offset = offsetAccessor.get(index);
assertEquals(Integer.toString(14), Integer.toString(offset));

/* do split and transfer */
try (ListVector toVector = ListVector.empty("toVector", allocator)) {

TransferPair transferPair = listVector.makeTransferPair(toVector);

int[][] transferLengths = { {0, 2},
{3, 1},
{4, 1}
};

for (final int[] transferLength : transferLengths) {
int start = transferLength[0];
int splitLength = transferLength[1];

int dataLength1 = 0;
int dataLength2 = 0;

int offset1 = 0;
int offset2 = 0;

transferPair.splitAndTransfer(start, splitLength);

/* get offsetVector of toVector */
UInt4Vector offsetVector1 = (UInt4Vector)toVector.getOffsetVector();
UInt4Vector.Accessor offsetAccessor1 = offsetVector1.getAccessor();

/* get dataVector of toVector */
NullableBigIntVector dataVector1 = (NullableBigIntVector)toVector.getDataVector();
NullableBigIntVector.Accessor valueAccessor1 = dataVector1.getAccessor();

for(int i = 0; i < splitLength; i++) {
dataLength1 = offsetAccessor.get(start + i + 1) - offsetAccessor.get(start + i);
dataLength2 = offsetAccessor1.get(i + 1) - offsetAccessor1.get(i);

assertEquals("Different data lengths at index: " + i + " and start: " + start,
dataLength1, dataLength2);

offset1 = offsetAccessor.get(start + i);
offset2 = offsetAccessor1.get(i);

for(int j = 0; j < dataLength1; j++) {
assertEquals("Different data at indexes: " + offset1 + " and " + offset2,
valueAccessor.getObject(offset1), valueAccessor1.getObject(offset2));

offset1++;
offset2++;
}
}
}
}
}
}
}
Loading