blob: dbea8521be2064893f68500434e16682145beff5 (
plain) (
blame)
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
|
/*
* 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 org.apache.spark.sql.execution;
import java.io.IOException;
import java.util.LinkedList;
import scala.collection.Iterator;
import org.apache.spark.TaskContext;
import org.apache.spark.sql.catalyst.InternalRow;
import org.apache.spark.sql.catalyst.expressions.UnsafeRow;
/**
* An iterator interface used to pull the output from generated function for multiple operators
* (whole stage codegen).
*/
public abstract class BufferedRowIterator {
protected LinkedList<InternalRow> currentRows = new LinkedList<>();
// used when there is no column in output
protected UnsafeRow unsafeRow = new UnsafeRow(0);
private long startTimeNs = System.nanoTime();
public boolean hasNext() throws IOException {
if (currentRows.isEmpty()) {
processNext();
}
return !currentRows.isEmpty();
}
public InternalRow next() {
return currentRows.remove();
}
/**
* Returns the elapsed time since this object is created. This object represents a pipeline so
* this is a measure of how long the pipeline has been running.
*/
public long durationMs() {
return (System.nanoTime() - startTimeNs) / (1000 * 1000);
}
/**
* Initializes from array of iterators of InternalRow.
*/
public abstract void init(Iterator<InternalRow> iters[]);
/**
* Append a row to currentRows.
*/
protected void append(InternalRow row) {
currentRows.add(row);
}
/**
* Returns whether `processNext()` should stop processing next row from `input` or not.
*
* If it returns true, the caller should exit the loop (return from processNext()).
*/
protected boolean shouldStop() {
return !currentRows.isEmpty();
}
/**
* Increase the peak execution memory for current task.
*/
protected void incPeakExecutionMemory(long size) {
TaskContext.get().taskMetrics().incPeakExecutionMemory(size);
}
/**
* Processes the input until have a row as output (currentRow).
*
* After it's called, if currentRow is still null, it means no more rows left.
*/
protected abstract void processNext() throws IOException;
}
|