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
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
|
/**
* Copyright (C) 2018-present MongoDB, Inc.
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the Server Side Public License, version 1,
* as published by MongoDB, Inc.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* Server Side Public License for more details.
*
* You should have received a copy of the Server Side Public License
* along with this program. If not, see
* <http://www.mongodb.com/licensing/server-side-public-license>.
*
* As a special exception, the copyright holders give permission to link the
* code of portions of this program with the OpenSSL library under certain
* conditions as described in each individual source file and distribute
* linked combinations including the program with the OpenSSL library. You
* must comply with the Server Side Public License in all respects for
* all of the code used other than as permitted herein. If you modify file(s)
* with this exception, you may extend this exception to your version of the
* file(s), but you are not obligated to do so. If you do not wish to do so,
* delete this exception statement from your version. If you delete this
* exception statement from all source files in the program, then also delete
* it in the license file.
*/
#pragma once
#include "mongo/db/pipeline/accumulation_statement.h"
#include "mongo/db/pipeline/accumulator.h"
#include "mongo/db/pipeline/document_source.h"
#include "mongo/db/pipeline/expression.h"
#include "mongo/db/pipeline/granularity_rounder.h"
#include "mongo/db/sorter/sorter.h"
namespace mongo {
/**
* The $bucketAuto stage takes a user-specified number of buckets and automatically determines
* boundaries such that the values are approximately equally distributed between those buckets.
*/
class DocumentSourceBucketAuto final : public DocumentSource {
public:
static constexpr StringData kStageName = "$bucketAuto"_sd;
Value serialize(SerializationOptions opts = SerializationOptions()) const final override;
DepsTracker::State getDependencies(DepsTracker* deps) const final;
void addVariableRefs(std::set<Variables::Id>* refs) const final;
const char* getSourceName() const final;
boost::intrusive_ptr<DocumentSource> optimize() final;
StageConstraints constraints(Pipeline::SplitState pipeState) const final {
return {StreamType::kBlocking,
PositionRequirement::kNone,
HostTypeRequirement::kNone,
DiskUseRequirement::kWritesTmpData,
FacetRequirement::kAllowed,
TransactionRequirement::kAllowed,
LookupRequirement::kAllowed,
UnionRequirement::kAllowed};
}
/**
* The $bucketAuto stage must be run on the merging shard.
*/
boost::optional<DistributedPlanLogic> distributedPlanLogic() final {
// {shardsStage, mergingStage, sortPattern}
return DistributedPlanLogic{nullptr, this, boost::none};
}
static const uint64_t kDefaultMaxMemoryUsageBytes = 100 * 1024 * 1024;
/**
* Convenience method to create a $bucketAuto stage.
*
* If 'accumulationStatements' is the empty vector, it will be filled in with the statement
* 'count: {$sum: 1}'.
*/
static boost::intrusive_ptr<DocumentSourceBucketAuto> create(
const boost::intrusive_ptr<ExpressionContext>& expCtx,
const boost::intrusive_ptr<Expression>& groupByExpression,
int numBuckets,
std::vector<AccumulationStatement> accumulationStatements = {},
const boost::intrusive_ptr<GranularityRounder>& granularityRounder = nullptr,
uint64_t maxMemoryUsageBytes = kDefaultMaxMemoryUsageBytes);
/**
* Parses a $bucketAuto stage from the user-supplied BSON.
*/
static boost::intrusive_ptr<DocumentSource> createFromBson(
BSONElement elem, const boost::intrusive_ptr<ExpressionContext>& pExpCtx);
/**
* Returns the groupBy expression. The mutable getter can be used to alter
* the expression, but should not be used after execution has begun.
*/
boost::intrusive_ptr<Expression> getGroupByExpression() const;
boost::intrusive_ptr<Expression>& getMutableGroupByExpression();
/**
* Returns the accumulated fields expressions. The mutable getter can be used to alter
* the expression, but should not be used after execution has begun.
*/
const std::vector<AccumulationStatement>& getAccumulatedFields() const;
std::vector<AccumulationStatement>& getMutableAccumulatedFields();
protected:
GetNextResult doGetNext() final;
void doDispose() final;
private:
DocumentSourceBucketAuto(const boost::intrusive_ptr<ExpressionContext>& pExpCtx,
const boost::intrusive_ptr<Expression>& groupByExpression,
int numBuckets,
std::vector<AccumulationStatement> accumulationStatements,
const boost::intrusive_ptr<GranularityRounder>& granularityRounder,
uint64_t maxMemoryUsageBytes);
// struct for holding information about a bucket.
struct Bucket {
Bucket(const boost::intrusive_ptr<ExpressionContext>& expCtx,
Value min,
Value max,
const std::vector<AccumulationStatement>& accumulationStatements);
Value _min;
Value _max;
std::vector<boost::intrusive_ptr<AccumulatorState>> _accums;
};
struct BucketDetails {
int currentBucketNum;
long long approxBucketSize = 0;
boost::optional<Value> previousMax;
boost::optional<std::pair<Value, Document>> currentMin;
};
/**
* Consumes all of the documents from the source in the pipeline and sorts them by their
* 'groupBy' value. This method might not be able to finish populating the sorter in a single
* call if 'pSource' returns a DocumentSource::GetNextResult::kPauseExecution, so this returns
* the last GetNextResult encountered, which may be either kEOF or kPauseExecution.
*/
GetNextResult populateSorter();
void initializeBucketIteration();
/**
* Computes the 'groupBy' expression value for 'doc'.
*/
Value extractKey(const Document& doc);
/**
* Returns the next bucket if exists. boost::none if none exist.
*/
boost::optional<Bucket> populateNextBucket();
boost::optional<std::pair<Value, Document>> adjustBoundariesAndGetMinForNextBucket(
Bucket* currentBucket);
/**
* Adds the document in 'entry' to 'bucket' by updating the accumulators in 'bucket'.
*/
void addDocumentToBucket(const std::pair<Value, Document>& entry, Bucket& bucket);
/**
* Makes a document using the information from bucket. This is what is returned when getNext()
* is called.
*/
Document makeDocument(const Bucket& bucket);
std::unique_ptr<Sorter<Value, Document>> _sorter;
std::unique_ptr<Sorter<Value, Document>::Iterator> _sortedInput;
std::vector<AccumulationStatement> _accumulatedFields;
uint64_t _maxMemoryUsageBytes;
bool _populated = false;
boost::intrusive_ptr<Expression> _groupByExpression;
boost::intrusive_ptr<GranularityRounder> _granularityRounder;
int _nBuckets;
long long _nDocuments = 0;
BucketDetails _currentBucketDetails;
};
} // namespace mongo
|
