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
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
|
/*
* Licensed to Elasticsearch under one or more contributor
* license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright
* ownership. Elasticsearch 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.elasticsearch.search.aggregations.bucket.geogrid;
import org.apache.lucene.index.LeafReaderContext;
import org.apache.lucene.index.SortedNumericDocValues;
import org.elasticsearch.common.lease.Releasables;
import org.elasticsearch.common.util.LongHash;
import org.elasticsearch.search.aggregations.Aggregator;
import org.elasticsearch.search.aggregations.AggregatorFactories;
import org.elasticsearch.search.aggregations.LeafBucketCollector;
import org.elasticsearch.search.aggregations.LeafBucketCollectorBase;
import org.elasticsearch.search.aggregations.bucket.BucketsAggregator;
import org.elasticsearch.search.aggregations.pipeline.PipelineAggregator;
import org.elasticsearch.search.internal.SearchContext;
import java.io.IOException;
import java.util.Arrays;
import java.util.Collections;
import java.util.List;
import java.util.Map;
/**
* Aggregates data expressed as GeoHash longs (for efficiency's sake) but formats results as Geohash strings.
*/
public class GeoHashGridAggregator extends BucketsAggregator {
private final int requiredSize;
private final int shardSize;
private final GeoGridAggregationBuilder.CellIdSource valuesSource;
private final LongHash bucketOrds;
GeoHashGridAggregator(String name, AggregatorFactories factories, GeoGridAggregationBuilder.CellIdSource valuesSource,
int requiredSize, int shardSize, SearchContext aggregationContext, Aggregator parent, List<PipelineAggregator> pipelineAggregators,
Map<String, Object> metaData) throws IOException {
super(name, factories, aggregationContext, parent, pipelineAggregators, metaData);
this.valuesSource = valuesSource;
this.requiredSize = requiredSize;
this.shardSize = shardSize;
bucketOrds = new LongHash(1, aggregationContext.bigArrays());
}
@Override
public boolean needsScores() {
return (valuesSource != null && valuesSource.needsScores()) || super.needsScores();
}
@Override
public LeafBucketCollector getLeafCollector(LeafReaderContext ctx,
final LeafBucketCollector sub) throws IOException {
final SortedNumericDocValues values = valuesSource.longValues(ctx);
return new LeafBucketCollectorBase(sub, null) {
@Override
public void collect(int doc, long bucket) throws IOException {
assert bucket == 0;
if (values.advanceExact(doc)) {
final int valuesCount = values.docValueCount();
long previous = Long.MAX_VALUE;
for (int i = 0; i < valuesCount; ++i) {
final long val = values.nextValue();
if (previous != val || i == 0) {
long bucketOrdinal = bucketOrds.add(val);
if (bucketOrdinal < 0) { // already seen
bucketOrdinal = -1 - bucketOrdinal;
collectExistingBucket(sub, doc, bucketOrdinal);
} else {
collectBucket(sub, doc, bucketOrdinal);
}
previous = val;
}
}
}
}
};
}
// private impl that stores a bucket ord. This allows for computing the aggregations lazily.
static class OrdinalBucket extends InternalGeoHashGrid.Bucket {
long bucketOrd;
OrdinalBucket() {
super(0, 0, null);
}
}
@Override
public InternalGeoHashGrid buildAggregation(long owningBucketOrdinal) throws IOException {
assert owningBucketOrdinal == 0;
final int size = (int) Math.min(bucketOrds.size(), shardSize);
InternalGeoHashGrid.BucketPriorityQueue ordered = new InternalGeoHashGrid.BucketPriorityQueue(size);
OrdinalBucket spare = null;
for (long i = 0; i < bucketOrds.size(); i++) {
if (spare == null) {
spare = new OrdinalBucket();
}
spare.geohashAsLong = bucketOrds.get(i);
spare.docCount = bucketDocCount(i);
spare.bucketOrd = i;
spare = (OrdinalBucket) ordered.insertWithOverflow(spare);
}
final InternalGeoHashGrid.Bucket[] list = new InternalGeoHashGrid.Bucket[ordered.size()];
for (int i = ordered.size() - 1; i >= 0; --i) {
final OrdinalBucket bucket = (OrdinalBucket) ordered.pop();
bucket.aggregations = bucketAggregations(bucket.bucketOrd);
list[i] = bucket;
}
return new InternalGeoHashGrid(name, requiredSize, Arrays.asList(list), pipelineAggregators(), metaData());
}
@Override
public InternalGeoHashGrid buildEmptyAggregation() {
return new InternalGeoHashGrid(name, requiredSize, Collections.emptyList(), pipelineAggregators(), metaData());
}
@Override
public void doClose() {
Releasables.close(bucketOrds);
}
}
|
