1
|
|
|
<?php |
2
|
|
|
declare(strict_types=1); |
3
|
|
|
|
4
|
|
|
namespace Level23\Druid\Aggregations; |
5
|
|
|
|
6
|
|
|
class DoublesSketchAggregator implements AggregatorInterface |
7
|
|
|
{ |
8
|
|
|
/** |
9
|
|
|
* A String for the name of the input field (can contain sketches or raw numeric values). |
10
|
|
|
* |
11
|
|
|
* @var string |
12
|
|
|
*/ |
13
|
|
|
protected $metricName; |
14
|
|
|
|
15
|
|
|
/** |
16
|
|
|
* A String for the output (result) name of the calculation. |
17
|
|
|
* |
18
|
|
|
* @var string |
19
|
|
|
*/ |
20
|
|
|
protected $outputName; |
21
|
|
|
|
22
|
|
|
/** |
23
|
|
|
* Parameter that determines the accuracy and size of the sketch. Higher k means higher accuracy but more space to |
24
|
|
|
* store sketches. Must be a power of 2 from 2 to 32768. See accuracy information in the DataSketches documentation |
25
|
|
|
* for details. |
26
|
|
|
* |
27
|
|
|
* @var int|null |
28
|
|
|
*/ |
29
|
|
|
protected $sizeAndAccuracy; |
30
|
|
|
|
31
|
|
|
/** |
32
|
|
|
* This parameter is a temporary solution to avoid a known issue. It may be removed in a future release after the |
33
|
|
|
* bug is fixed. This parameter defines the maximum number of items to store in each sketch. If a sketch reaches |
34
|
|
|
* the limit, the query can throw IllegalStateException. To workaround this issue, increase the maximum stream |
35
|
|
|
* length. See accuracy information in the DataSketches documentation for how many bytes are required per stream |
36
|
|
|
* length. |
37
|
|
|
* |
38
|
|
|
* @var int|null |
39
|
|
|
*/ |
40
|
|
|
protected $maxStreamLength; |
41
|
|
|
|
42
|
|
|
/** |
43
|
|
|
* @param string $metricName A String for the name of the input field (can contain sketches or raw numeric |
44
|
|
|
* values). |
45
|
|
|
* @param string $outputName A String for the output (result) name of the calculation. |
46
|
|
|
* @param int|null $sizeAndAccuracy Parameter that determines the accuracy and size of the sketch. Higher k means |
47
|
|
|
* higher accuracy but more space to store sketches. Must be a power of 2 from 2 |
48
|
|
|
* to 32768. See accuracy information in the DataSketches documentation for |
49
|
|
|
* details. |
50
|
|
|
* @param int|null $maxStreamLength This parameter is a temporary solution to avoid a known issue. It may be |
51
|
|
|
* removed in a future release after the bug is fixed. This parameter defines the |
52
|
|
|
* maximum number of items to store in each sketch. If a sketch reaches the limit, |
53
|
|
|
* the query can throw IllegalStateException. To workaround this issue, increase |
54
|
|
|
* the maximum stream length. See accuracy information in the DataSketches |
55
|
|
|
* documentation for how many bytes are required per stream length. |
56
|
|
|
* |
57
|
|
|
* @see https://druid.apache.org/docs/latest/development/extensions-core/datasketches-quantiles.html |
58
|
|
|
*/ |
59
|
4 |
|
public function __construct( |
60
|
|
|
string $metricName, |
61
|
|
|
string $outputName = '', |
62
|
|
|
?int $sizeAndAccuracy = null, |
63
|
|
|
?int $maxStreamLength = null |
64
|
|
|
) { |
65
|
4 |
|
$this->metricName = $metricName; |
66
|
4 |
|
$this->outputName = $outputName ?: $metricName; |
67
|
4 |
|
$this->sizeAndAccuracy = $sizeAndAccuracy; |
68
|
4 |
|
$this->maxStreamLength = $maxStreamLength; |
69
|
|
|
} |
70
|
|
|
|
71
|
4 |
|
public function toArray(): array |
72
|
|
|
{ |
73
|
4 |
|
$result = [ |
74
|
|
|
'type' => 'quantilesDoublesSketch', |
75
|
4 |
|
'name' => $this->outputName, |
76
|
4 |
|
'fieldName' => $this->metricName, |
77
|
|
|
]; |
78
|
|
|
|
79
|
4 |
|
if ($this->sizeAndAccuracy !== null) { |
80
|
2 |
|
$result['k'] = $this->sizeAndAccuracy; |
81
|
|
|
} |
82
|
|
|
|
83
|
4 |
|
if ($this->maxStreamLength !== null) { |
84
|
2 |
|
$result['maxStreamLength'] = $this->maxStreamLength; |
85
|
|
|
} |
86
|
|
|
|
87
|
4 |
|
return $result; |
88
|
|
|
} |
89
|
|
|
} |