Skip to content
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.

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

ARROW-400: set struct length on load #234

Closed
wants to merge 2 commits into from
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
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
237 changes: 237 additions & 0 deletions integration/data/struct_example.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,237 @@
{
"schema": {
"fields": [
{
"name": "struct_nullable",
"type": {
"name": "struct"
},
"nullable": true,
"children": [
{
"name": "f1",
"type": {
"name": "int",
"isSigned": true,
"bitWidth": 32
},
"nullable": true,
"children": [],
"typeLayout": {
"vectors": [
{
"type": "VALIDITY",
"typeBitWidth": 1
},
{
"type": "DATA",
"typeBitWidth": 32
}
]
}
},
{
"name": "f2",
"type": {
"name": "utf8"
},
"nullable": true,
"children": [],
"typeLayout": {
"vectors": [
{
"type": "VALIDITY",
"typeBitWidth": 1
},
{
"type": "OFFSET",
"typeBitWidth": 32
},
{
"type": "DATA",
"typeBitWidth": 8
}
]
}
}
],
"typeLayout": {
"vectors": [
{
"type": "VALIDITY",
"typeBitWidth": 1
}
]
}
}
]
},
"batches": [
{
"count": 7,
"columns": [
{
"name": "struct_nullable",
"count": 7,
"VALIDITY": [
0,
1,
1,
1,
0,
1,
0
],
"children": [
{
"name": "f1",
"count": 7,
"VALIDITY": [
1,
0,
1,
1,
1,
0,
0
],
"DATA": [
1402032511,
290876774,
137773603,
410361374,
1959836418,
1995074679,
-163525262
]
},
{
"name": "f2",
"count": 7,
"VALIDITY": [
0,
1,
1,
1,
0,
1,
0
],
"OFFSET": [
0,
0,
7,
14,
21,
21,
28,
28
],
"DATA": [
"",
"MhRNxD4",
"3F9HBxK",
"aVd88fp",
"",
"3loZrRf",
""
]
}
]
}
]
},
{
"count": 10,
"columns": [
{
"name": "struct_nullable",
"count": 10,
"VALIDITY": [
0,
1,
1,
0,
1,
0,
0,
1,
1,
1
],
"children": [
{
"name": "f1",
"count": 10,
"VALIDITY": [
0,
0,
0,
0,
0,
0,
1,
0,
0,
0
],
"DATA": [
-2041500147,
1715692943,
-35444996,
1425496657,
112765084,
1760754983,
413888857,
2039738337,
-1924327700,
670528518
]
},
{
"name": "f2",
"count": 10,
"VALIDITY": [
1,
0,
0,
1,
1,
1,
1,
1,
1,
0
],
"OFFSET": [
0,
7,
7,
7,
14,
21,
28,
35,
42,
49,
49
],
"DATA": [
"AS5oARE",
"",
"",
"JGdagcX",
"78SLiRw",
"vbGf7OY",
"5uh5fTs",
"0ilsf82",
"LjS9MbU",
""
]
}
]
}
]
}
]
}
Original file line number Diff line number Diff line change
Expand Up @@ -50,7 +50,7 @@ public class MapVector extends AbstractMapVector {
private final SingleMapReaderImpl reader = new SingleMapReaderImpl(this);
private final Accessor accessor = new Accessor();
private final Mutator mutator = new Mutator();
int valueCount;
public int valueCount;

public MapVector(String name, BufferAllocator allocator, CallBack callBack) {
super(name, allocator, callBack);
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -47,6 +47,7 @@
import org.apache.arrow.vector.ValueVector.Mutator;
import org.apache.arrow.vector.VarCharVector;
import org.apache.arrow.vector.VectorSchemaRoot;
import org.apache.arrow.vector.complex.NullableMapVector;
import org.apache.arrow.vector.schema.ArrowVectorType;
import org.apache.arrow.vector.types.pojo.Field;
import org.apache.arrow.vector.types.pojo.Schema;
Expand Down Expand Up @@ -153,6 +154,9 @@ private void readVector(Field field, FieldVector vector) throws JsonParseExcepti
}
readToken(END_ARRAY);
}
if (vector instanceof NullableMapVector) {
((NullableMapVector)vector).valueCount = count;
}
}
readToken(END_OBJECT);
}
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -21,11 +21,13 @@
import java.io.IOException;

import org.apache.arrow.memory.BufferAllocator;
import org.apache.arrow.vector.FieldVector;
import org.apache.arrow.vector.VectorSchemaRoot;
import org.apache.arrow.vector.complex.MapVector;
import org.apache.arrow.vector.complex.NullableMapVector;
import org.apache.arrow.vector.file.BaseFileTest;
import org.apache.arrow.vector.types.pojo.Schema;
import org.junit.Assert;
import org.junit.Test;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
Expand Down Expand Up @@ -117,4 +119,22 @@ public void testWriteReadUnionJSON() throws IOException {
}
}

@Test
public void testSetStructLength() throws IOException {
File file = new File("../../integration/data/struct_example.json");
try (
BufferAllocator readerAllocator = allocator.newChildAllocator("reader", 0, Integer.MAX_VALUE);
) {
JsonFileReader reader = new JsonFileReader(file, readerAllocator);
Schema schema = reader.start();
LOGGER.debug("reading schema: " + schema);

// initialize vectors
try (VectorSchemaRoot root = reader.read();) {
FieldVector vector = root.getVector("struct_nullable");
Assert.assertEquals(7, vector.getAccessor().getValueCount());
}
}
}

}