/
JavaBatchDataSourceV2.java
112 lines (93 loc) · 3.26 KB
/
JavaBatchDataSourceV2.java
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package test.org.apache.spark.sql.sources.v2;
import java.io.IOException;
import java.util.List;
import org.apache.spark.sql.execution.vectorized.OnHeapColumnVector;
import org.apache.spark.sql.sources.v2.DataSourceV2;
import org.apache.spark.sql.sources.v2.DataSourceV2Options;
import org.apache.spark.sql.sources.v2.ReadSupport;
import org.apache.spark.sql.sources.v2.reader.*;
import org.apache.spark.sql.types.DataTypes;
import org.apache.spark.sql.types.StructType;
import org.apache.spark.sql.vectorized.ColumnVector;
import org.apache.spark.sql.vectorized.ColumnarBatch;
public class JavaBatchDataSourceV2 implements DataSourceV2, ReadSupport {
class Reader implements DataSourceV2Reader, SupportsScanColumnarBatch {
private final StructType schema = new StructType().add("i", "int").add("j", "int");
@Override
public StructType readSchema() {
return schema;
}
@Override
public List<ReadTask<ColumnarBatch>> createBatchReadTasks() {
return java.util.Arrays.asList(new JavaBatchReadTask(0, 50), new JavaBatchReadTask(50, 90));
}
}
static class JavaBatchReadTask implements ReadTask<ColumnarBatch>, DataReader<ColumnarBatch> {
private int start;
private int end;
private static final int BATCH_SIZE = 20;
private OnHeapColumnVector i;
private OnHeapColumnVector j;
private ColumnarBatch batch;
JavaBatchReadTask(int start, int end) {
this.start = start;
this.end = end;
}
@Override
public DataReader<ColumnarBatch> createDataReader() {
this.i = new OnHeapColumnVector(BATCH_SIZE, DataTypes.IntegerType);
this.j = new OnHeapColumnVector(BATCH_SIZE, DataTypes.IntegerType);
ColumnVector[] vectors = new ColumnVector[2];
vectors[0] = i;
vectors[1] = j;
this.batch = new ColumnarBatch(vectors);
return this;
}
@Override
public boolean next() {
i.reset();
j.reset();
int count = 0;
while (start < end && count < BATCH_SIZE) {
i.putInt(count, start);
j.putInt(count, -start);
start += 1;
count += 1;
}
if (count == 0) {
return false;
} else {
batch.setNumRows(count);
return true;
}
}
@Override
public ColumnarBatch get() {
return batch;
}
@Override
public void close() throws IOException {
batch.close();
}
}
@Override
public DataSourceV2Reader createReader(DataSourceV2Options options) {
return new Reader();
}
}