Skip to content

GH-43643: [Java] LargeListViewVector IPC Integration #43681

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

Merged
lidavidm merged 3 commits into from
Aug 14, 2024
Merged

GH-43643: [Java] LargeListViewVector IPC Integration #43681

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
bb32ee8
feat: adding initial interfaces:
vibhatha Aug 13, 2024
f49b270
fix: adding missing listview tests
vibhatha Aug 14, 2024
802f23e
fix: adding listview and largelistview json file tests
vibhatha Aug 14, 2024
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
9 changes: 7 additions & 2 deletions java/vector/src/main/java/org/apache/arrow/vector/ipc/JsonFileReader.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -73,6 +73,7 @@
import org.apache.arrow.vector.ipc.message.ArrowFieldNode;
import org.apache.arrow.vector.types.Types.MinorType;
import org.apache.arrow.vector.types.pojo.ArrowType;
import org.apache.arrow.vector.types.pojo.ArrowType.LargeListView;
import org.apache.arrow.vector.types.pojo.ArrowType.ListView;
import org.apache.arrow.vector.types.pojo.ArrowType.Union;
import org.apache.arrow.vector.types.pojo.Field;
Expand Down Expand Up @@ -729,7 +730,8 @@ private List<ArrowBuf> readIntoBuffer(
} else if (bufferType.equals(OFFSET) || bufferType.equals(SIZE)) {
if (type == MinorType.LARGELIST
|| type == MinorType.LARGEVARCHAR
|| type == MinorType.LARGEVARBINARY) {
|| type == MinorType.LARGEVARBINARY
|| type == MinorType.LARGELISTVIEW) {
reader = helper.INT8;
} else {
reader = helper.INT4;
Expand Down Expand Up @@ -890,7 +892,10 @@ private void readFromJsonIntoVector(Field field, FieldVector vector) throws IOEx
BufferType bufferType = vectorTypes.get(v);
nextFieldIs(bufferType.getName());
int innerBufferValueCount = valueCount;
if (bufferType.equals(OFFSET) && !(type instanceof Union) && !(type instanceof ListView)) {
if (bufferType.equals(OFFSET)
&& !(type instanceof Union)
&& !(type instanceof ListView)
&& !(type instanceof LargeListView)) {
/* offset buffer has 1 additional value capacity except for dense unions and ListView */
innerBufferValueCount = valueCount + 1;
}
Expand Down
16 changes: 14 additions & 2 deletions java/vector/src/main/java/org/apache/arrow/vector/ipc/JsonFileWriter.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -73,6 +73,7 @@
import org.apache.arrow.vector.UInt4Vector;
import org.apache.arrow.vector.UInt8Vector;
import org.apache.arrow.vector.VectorSchemaRoot;
import org.apache.arrow.vector.complex.BaseLargeRepeatedValueViewVector;
import org.apache.arrow.vector.complex.BaseRepeatedValueViewVector;
import org.apache.arrow.vector.dictionary.Dictionary;
import org.apache.arrow.vector.dictionary.DictionaryProvider;
Expand Down Expand Up @@ -232,7 +233,8 @@ private void writeFromVectorIntoJson(Field field, FieldVector vector) throws IOE
final int bufferValueCount =
(bufferType.equals(OFFSET)
&& vector.getMinorType() != MinorType.DENSEUNION
&& vector.getMinorType() != MinorType.LISTVIEW)
&& vector.getMinorType() != MinorType.LISTVIEW
&& vector.getMinorType() != MinorType.LARGELISTVIEW)
? valueCount + 1
: valueCount;
for (int i = 0; i < bufferValueCount; i++) {
Expand Down Expand Up @@ -274,6 +276,7 @@ private void writeFromVectorIntoJson(Field field, FieldVector vector) throws IOE
} else if (bufferType.equals(OFFSET)
&& vector.getValueCount() == 0
&& (vector.getMinorType() == MinorType.LARGELIST
|| vector.getMinorType() == MinorType.LARGELISTVIEW
|| vector.getMinorType() == MinorType.LARGEVARBINARY
|| vector.getMinorType() == MinorType.LARGEVARCHAR)) {
// Empty vectors may not have allocated an offsets buffer
Expand Down Expand Up @@ -427,6 +430,10 @@ private void writeValueToGenerator(
generator.writeNumber(
buffer.getInt((long) index * BaseRepeatedValueViewVector.OFFSET_WIDTH));
break;
case LARGELISTVIEW:
generator.writeNumber(
buffer.getInt((long) index * BaseLargeRepeatedValueViewVector.OFFSET_WIDTH));
break;
case LARGELIST:
case LARGEVARBINARY:
case LARGEVARCHAR:
Expand Down Expand Up @@ -582,7 +589,12 @@ private void writeValueToGenerator(
throw new UnsupportedOperationException("minor type: " + vector.getMinorType());
}
} else if (bufferType.equals(SIZE)) {
generator.writeNumber(buffer.getInt((long) index * BaseRepeatedValueViewVector.SIZE_WIDTH));
if (vector.getMinorType() == MinorType.LISTVIEW) {
generator.writeNumber(buffer.getInt((long) index * BaseRepeatedValueViewVector.SIZE_WIDTH));
} else {
generator.writeNumber(
buffer.getInt((long) index * BaseLargeRepeatedValueViewVector.SIZE_WIDTH));
}
}
}

Expand Down
8 changes: 8 additions & 0 deletions java/vector/src/test/java/org/apache/arrow/vector/ipc/TestJSONFile.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -437,10 +437,18 @@ public void testRoundtripEmptyVector() throws Exception {
"list",
FieldType.nullable(ArrowType.List.INSTANCE),
Collections.singletonList(Field.nullable("items", new ArrowType.Int(32, true)))),
new Field(
"listview",
FieldType.nullable(ArrowType.ListView.INSTANCE),
Collections.singletonList(Field.nullable("items", new ArrowType.Int(32, true)))),
Comment on lines +440 to +443
Copy link
Contributor Author

@vibhatha vibhatha Aug 14, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Added a missed case when adding IPC support for ListViewVector

new Field(
"largelist",
FieldType.nullable(ArrowType.LargeList.INSTANCE),
Collections.singletonList(Field.nullable("items", new ArrowType.Int(32, true)))),
new Field(
"largelistview",
FieldType.nullable(ArrowType.LargeListView.INSTANCE),
Collections.singletonList(Field.nullable("items", new ArrowType.Int(32, true)))),
new Field(
"map",
FieldType.nullable(new ArrowType.Map(/*keyssorted*/ false)),
Expand Down