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
|
/*
* 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.drill.exec.physical.base;
import com.fasterxml.jackson.annotation.JsonIgnore;
import java.util.Collection;
import java.util.List;
import org.apache.drill.common.exceptions.ExecutionSetupException;
import org.apache.drill.common.expression.LogicalExpression;
import org.apache.drill.common.expression.SchemaPath;
import org.apache.drill.exec.expr.fn.FunctionImplementationRegistry;
import org.apache.drill.exec.ops.UdfUtilities;
import org.apache.drill.exec.physical.PhysicalOperatorSetupException;
import org.apache.drill.exec.planner.physical.PlannerSettings;
import org.apache.drill.exec.proto.CoordinationProtos.DrillbitEndpoint;
import org.apache.drill.exec.server.options.OptionManager;
import org.apache.drill.shaded.guava.com.google.common.collect.ImmutableList;
/**
* A GroupScan operator represents all data which will be scanned by a given physical
* plan. It is the superset of all SubScans for the plan.
*/
public interface GroupScan extends Scan, HasAffinity{
/**
* columns list in GroupScan : 1) empty_column is for skipAll query.
* 2) NULL is interpreted as ALL_COLUMNS.
* How to handle skipAll query is up to each storage plugin, with different policy in corresponding RecordReader.
*/
List<SchemaPath> ALL_COLUMNS = ImmutableList.of(SchemaPath.STAR_COLUMN);
long NO_COLUMN_STATS = -1;
void applyAssignments(List<DrillbitEndpoint> endpoints) throws PhysicalOperatorSetupException;
SubScan getSpecificScan(int minorFragmentId) throws ExecutionSetupException;
@JsonIgnore
int getMaxParallelizationWidth();
@JsonIgnore
boolean isDistributed();
/**
* At minimum, the GroupScan requires these many fragments to run.
* Currently, this is used in {@link org.apache.drill.exec.planner.fragment.SimpleParallelizer}
* @return the minimum number of fragments that should run
*/
@JsonIgnore
int getMinParallelizationWidth();
/**
* Check if GroupScan enforces width to be maximum parallelization width.
* Currently, this is used in {@link org.apache.drill.exec.planner.physical.visitor.ExcessiveExchangeIdentifier}
* @return if maximum width should be enforced
*
* @deprecated Use {@link #getMinParallelizationWidth()} to determine whether this GroupScan spans more than one
* fragment.
*/
@JsonIgnore
@Deprecated
boolean enforceWidth();
/**
* Returns a signature of the {@link GroupScan} which should usually be composed of
* all its attributes which could describe it uniquely.
*/
@JsonIgnore
String getDigest();
@JsonIgnore
ScanStats getScanStats(PlannerSettings settings);
/**
* Returns a clone of GroupScan instance, except that the new GroupScan will use the provided list of columns .
*/
GroupScan clone(List<SchemaPath> columns);
/**
* GroupScan should check the list of columns, and see if it could support all the columns in the list.
*/
boolean canPushdownProjects(List<SchemaPath> columns);
/**
* Return the number of non-null value in the specified column. Raise exception, if groupscan does not
* have exact column row count.
*/
long getColumnValueCount(SchemaPath column);
/**
* Whether or not this GroupScan supports pushdown of partition filters (directories for filesystems)
*/
boolean supportsPartitionFilterPushdown();
/**
* Returns a list of columns scanned by this group scan
*
*/
List<SchemaPath> getColumns();
/**
* Returns a list of columns that can be used for partition pruning
*
*/
@JsonIgnore
List<SchemaPath> getPartitionColumns();
/**
* Whether or not this GroupScan supports limit pushdown
*/
boolean supportsLimitPushdown();
/**
* Apply rowcount based prune for "LIMIT n" query.
* @param maxRecords : the number of rows requested from group scan.
* @return a new instance of group scan if the prune is successful.
* null when either if row-based prune is not supported, or if prune is not successful.
*/
GroupScan applyLimit(int maxRecords);
/**
* Return true if this GroupScan can return its selection as a list of file names (retrieved by getFiles()).
*/
@JsonIgnore
boolean hasFiles();
/**
* Returns a collection of file names associated with this GroupScan. This should be called after checking
* hasFiles(). If this GroupScan cannot provide file names, it returns null.
*/
Collection<String> getFiles();
@JsonIgnore
LogicalExpression getFilter();
GroupScan applyFilter(LogicalExpression filterExpr, UdfUtilities udfUtilities,
FunctionImplementationRegistry functionImplementationRegistry, OptionManager optionManager);
}
|
