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
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
|
/*
* 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
import java.beans.{BeanInfo, Introspector}
import java.util.Properties
import java.util.concurrent.atomic.AtomicReference
import scala.collection.JavaConverters._
import scala.collection.immutable
import scala.reflect.runtime.universe.TypeTag
import org.apache.spark.{SparkContext, SparkException}
import org.apache.spark.annotation.{DeveloperApi, Experimental}
import org.apache.spark.api.java.{JavaRDD, JavaSparkContext}
import org.apache.spark.rdd.RDD
import org.apache.spark.scheduler.{SparkListener, SparkListenerApplicationEnd}
import org.apache.spark.sql.{execution => sparkexecution}
import org.apache.spark.sql.SQLConf.SQLConfEntry
import org.apache.spark.sql.catalyst.{InternalRow, _}
import org.apache.spark.sql.catalyst.analysis._
import org.apache.spark.sql.catalyst.encoders.encoderFor
import org.apache.spark.sql.catalyst.expressions._
import org.apache.spark.sql.catalyst.optimizer.Optimizer
import org.apache.spark.sql.catalyst.plans.logical.{LocalRelation, LogicalPlan, Range}
import org.apache.spark.sql.catalyst.rules.RuleExecutor
import org.apache.spark.sql.execution._
import org.apache.spark.sql.execution.datasources._
import org.apache.spark.sql.execution.ui.{SQLListener, SQLTab}
import org.apache.spark.sql.sources.BaseRelation
import org.apache.spark.sql.types._
import org.apache.spark.sql.util.ExecutionListenerManager
import org.apache.spark.util.Utils
/**
* The entry point for working with structured data (rows and columns) in Spark. Allows the
* creation of [[DataFrame]] objects as well as the execution of SQL queries.
*
* @groupname basic Basic Operations
* @groupname ddl_ops Persistent Catalog DDL
* @groupname cachemgmt Cached Table Management
* @groupname genericdata Generic Data Sources
* @groupname specificdata Specific Data Sources
* @groupname config Configuration
* @groupname dataframes Custom DataFrame Creation
* @groupname Ungrouped Support functions for language integrated queries
*
* @since 1.0.0
*/
class SQLContext private[sql](
@transient val sparkContext: SparkContext,
@transient protected[sql] val cacheManager: CacheManager,
@transient private[sql] val listener: SQLListener,
val isRootContext: Boolean)
extends org.apache.spark.Logging with Serializable {
self =>
def this(sparkContext: SparkContext) = {
this(sparkContext, new CacheManager, SQLContext.createListenerAndUI(sparkContext), true)
}
def this(sparkContext: JavaSparkContext) = this(sparkContext.sc)
// If spark.sql.allowMultipleContexts is true, we will throw an exception if a user
// wants to create a new root SQLContext (a SLQContext that is not created by newSession).
private val allowMultipleContexts =
sparkContext.conf.getBoolean(
SQLConf.ALLOW_MULTIPLE_CONTEXTS.key,
SQLConf.ALLOW_MULTIPLE_CONTEXTS.defaultValue.get)
// Assert no root SQLContext is running when allowMultipleContexts is false.
{
if (!allowMultipleContexts && isRootContext) {
SQLContext.getInstantiatedContextOption() match {
case Some(rootSQLContext) =>
val errMsg = "Only one SQLContext/HiveContext may be running in this JVM. " +
s"It is recommended to use SQLContext.getOrCreate to get the instantiated " +
s"SQLContext/HiveContext. To ignore this error, " +
s"set ${SQLConf.ALLOW_MULTIPLE_CONTEXTS.key} = true in SparkConf."
throw new SparkException(errMsg)
case None => // OK
}
}
}
/**
* Returns a SQLContext as new session, with separated SQL configurations, temporary tables,
* registered functions, but sharing the same SparkContext, CacheManager, SQLListener and SQLTab.
*
* @since 1.6.0
*/
def newSession(): SQLContext = {
new SQLContext(
sparkContext = sparkContext,
cacheManager = cacheManager,
listener = listener,
isRootContext = false)
}
/**
* @return Spark SQL configuration
*/
protected[sql] lazy val conf = new SQLConf
/**
* Set Spark SQL configuration properties.
*
* @group config
* @since 1.0.0
*/
def setConf(props: Properties): Unit = conf.setConf(props)
/** Set the given Spark SQL configuration property. */
private[sql] def setConf[T](entry: SQLConfEntry[T], value: T): Unit = conf.setConf(entry, value)
/**
* Set the given Spark SQL configuration property.
*
* @group config
* @since 1.0.0
*/
def setConf(key: String, value: String): Unit = conf.setConfString(key, value)
/**
* Return the value of Spark SQL configuration property for the given key.
*
* @group config
* @since 1.0.0
*/
def getConf(key: String): String = conf.getConfString(key)
/**
* Return the value of Spark SQL configuration property for the given key. If the key is not set
* yet, return `defaultValue` in [[SQLConfEntry]].
*/
private[sql] def getConf[T](entry: SQLConfEntry[T]): T = conf.getConf(entry)
/**
* Return the value of Spark SQL configuration property for the given key. If the key is not set
* yet, return `defaultValue`. This is useful when `defaultValue` in SQLConfEntry is not the
* desired one.
*/
private[sql] def getConf[T](entry: SQLConfEntry[T], defaultValue: T): T = {
conf.getConf(entry, defaultValue)
}
/**
* Return the value of Spark SQL configuration property for the given key. If the key is not set
* yet, return `defaultValue`.
*
* @group config
* @since 1.0.0
*/
def getConf(key: String, defaultValue: String): String = conf.getConfString(key, defaultValue)
/**
* Return all the configuration properties that have been set (i.e. not the default).
* This creates a new copy of the config properties in the form of a Map.
*
* @group config
* @since 1.0.0
*/
def getAllConfs: immutable.Map[String, String] = conf.getAllConfs
@transient
lazy val listenerManager: ExecutionListenerManager = new ExecutionListenerManager
@transient
protected[sql] lazy val catalog: Catalog = new SimpleCatalog(conf)
@transient
protected[sql] lazy val functionRegistry: FunctionRegistry = FunctionRegistry.builtin.copy()
@transient
protected[sql] lazy val analyzer: Analyzer =
new Analyzer(catalog, functionRegistry, conf) {
override val extendedResolutionRules =
ExtractPythonUDFs ::
PreInsertCastAndRename ::
(if (conf.runSQLOnFile) new ResolveDataSource(self) :: Nil else Nil)
override val extendedCheckRules = Seq(
datasources.PreWriteCheck(catalog)
)
}
@transient
protected[sql] lazy val optimizer: Optimizer = new SparkOptimizer(this)
@transient
protected[sql] val sqlParser: ParserDialect = new SparkSQLParser(new SparkQl(conf))
@transient
protected[sql] val ddlParser: DDLParser = new DDLParser(sqlParser)
protected[sql] def parseSql(sql: String): LogicalPlan = ddlParser.parse(sql, false)
protected[sql] def executeSql(sql: String):
org.apache.spark.sql.execution.QueryExecution = executePlan(parseSql(sql))
protected[sql] def executePlan(plan: LogicalPlan) =
new sparkexecution.QueryExecution(this, plan)
/**
* Add a jar to SQLContext
*/
protected[sql] def addJar(path: String): Unit = {
sparkContext.addJar(path)
}
{
// We extract spark sql settings from SparkContext's conf and put them to
// Spark SQL's conf.
// First, we populate the SQLConf (conf). So, we can make sure that other values using
// those settings in their construction can get the correct settings.
// For example, metadataHive in HiveContext may need both spark.sql.hive.metastore.version
// and spark.sql.hive.metastore.jars to get correctly constructed.
val properties = new Properties
sparkContext.getConf.getAll.foreach {
case (key, value) if key.startsWith("spark.sql") => properties.setProperty(key, value)
case _ =>
}
// We directly put those settings to conf to avoid of calling setConf, which may have
// side-effects. For example, in HiveContext, setConf may cause executionHive and metadataHive
// get constructed. If we call setConf directly, the constructed metadataHive may have
// wrong settings, or the construction may fail.
conf.setConf(properties)
// After we have populated SQLConf, we call setConf to populate other confs in the subclass
// (e.g. hiveconf in HiveContext).
properties.asScala.foreach {
case (key, value) => setConf(key, value)
}
}
/**
* :: Experimental ::
* A collection of methods that are considered experimental, but can be used to hook into
* the query planner for advanced functionality.
*
* @group basic
* @since 1.3.0
*/
@Experimental
@transient
val experimental: ExperimentalMethods = new ExperimentalMethods(this)
/**
* :: Experimental ::
* Returns a [[DataFrame]] with no rows or columns.
*
* @group basic
* @since 1.3.0
*/
@Experimental
@transient
lazy val emptyDataFrame: DataFrame = createDataFrame(sparkContext.emptyRDD[Row], StructType(Nil))
/**
* A collection of methods for registering user-defined functions (UDF).
*
* The following example registers a Scala closure as UDF:
* {{{
* sqlContext.udf.register("myUDF", (arg1: Int, arg2: String) => arg2 + arg1)
* }}}
*
* The following example registers a UDF in Java:
* {{{
* sqlContext.udf().register("myUDF",
* new UDF2<Integer, String, String>() {
* @Override
* public String call(Integer arg1, String arg2) {
* return arg2 + arg1;
* }
* }, DataTypes.StringType);
* }}}
*
* Or, to use Java 8 lambda syntax:
* {{{
* sqlContext.udf().register("myUDF",
* (Integer arg1, String arg2) -> arg2 + arg1,
* DataTypes.StringType);
* }}}
*
* @group basic
* @since 1.3.0
* TODO move to SQLSession?
*/
@transient
val udf: UDFRegistration = new UDFRegistration(this)
/**
* Returns true if the table is currently cached in-memory.
* @group cachemgmt
* @since 1.3.0
*/
def isCached(tableName: String): Boolean = {
cacheManager.lookupCachedData(table(tableName)).nonEmpty
}
/**
* Returns true if the [[Queryable]] is currently cached in-memory.
* @group cachemgmt
* @since 1.3.0
*/
private[sql] def isCached(qName: Queryable): Boolean = {
cacheManager.lookupCachedData(qName).nonEmpty
}
/**
* Caches the specified table in-memory.
* @group cachemgmt
* @since 1.3.0
*/
def cacheTable(tableName: String): Unit = {
cacheManager.cacheQuery(table(tableName), Some(tableName))
}
/**
* Removes the specified table from the in-memory cache.
* @group cachemgmt
* @since 1.3.0
*/
def uncacheTable(tableName: String): Unit = cacheManager.uncacheQuery(table(tableName))
/**
* Removes all cached tables from the in-memory cache.
* @since 1.3.0
*/
def clearCache(): Unit = cacheManager.clearCache()
// scalastyle:off
// Disable style checker so "implicits" object can start with lowercase i
/**
* :: Experimental ::
* (Scala-specific) Implicit methods available in Scala for converting
* common Scala objects into [[DataFrame]]s.
*
* {{{
* val sqlContext = new SQLContext(sc)
* import sqlContext.implicits._
* }}}
*
* @group basic
* @since 1.3.0
*/
@Experimental
object implicits extends SQLImplicits with Serializable {
protected override def _sqlContext: SQLContext = self
/**
* Converts $"col name" into an [[Column]].
* @since 1.3.0
*/
// This must live here to preserve binary compatibility with Spark < 1.5.
implicit class StringToColumn(val sc: StringContext) {
def $(args: Any*): ColumnName = {
new ColumnName(sc.s(args: _*))
}
}
}
// scalastyle:on
/**
* :: Experimental ::
* Creates a DataFrame from an RDD of Product (e.g. case classes, tuples).
*
* @group dataframes
* @since 1.3.0
*/
@Experimental
def createDataFrame[A <: Product : TypeTag](rdd: RDD[A]): DataFrame = {
SQLContext.setActive(self)
val schema = ScalaReflection.schemaFor[A].dataType.asInstanceOf[StructType]
val attributeSeq = schema.toAttributes
val rowRDD = RDDConversions.productToRowRdd(rdd, schema.map(_.dataType))
DataFrame(self, LogicalRDD(attributeSeq, rowRDD)(self))
}
/**
* :: Experimental ::
* Creates a DataFrame from a local Seq of Product.
*
* @group dataframes
* @since 1.3.0
*/
@Experimental
def createDataFrame[A <: Product : TypeTag](data: Seq[A]): DataFrame = {
SQLContext.setActive(self)
val schema = ScalaReflection.schemaFor[A].dataType.asInstanceOf[StructType]
val attributeSeq = schema.toAttributes
DataFrame(self, LocalRelation.fromProduct(attributeSeq, data))
}
/**
* Convert a [[BaseRelation]] created for external data sources into a [[DataFrame]].
*
* @group dataframes
* @since 1.3.0
*/
def baseRelationToDataFrame(baseRelation: BaseRelation): DataFrame = {
DataFrame(this, LogicalRelation(baseRelation))
}
/**
* :: DeveloperApi ::
* Creates a [[DataFrame]] from an [[RDD]] containing [[Row]]s using the given schema.
* It is important to make sure that the structure of every [[Row]] of the provided RDD matches
* the provided schema. Otherwise, there will be runtime exception.
* Example:
* {{{
* import org.apache.spark.sql._
* import org.apache.spark.sql.types._
* val sqlContext = new org.apache.spark.sql.SQLContext(sc)
*
* val schema =
* StructType(
* StructField("name", StringType, false) ::
* StructField("age", IntegerType, true) :: Nil)
*
* val people =
* sc.textFile("examples/src/main/resources/people.txt").map(
* _.split(",")).map(p => Row(p(0), p(1).trim.toInt))
* val dataFrame = sqlContext.createDataFrame(people, schema)
* dataFrame.printSchema
* // root
* // |-- name: string (nullable = false)
* // |-- age: integer (nullable = true)
*
* dataFrame.registerTempTable("people")
* sqlContext.sql("select name from people").collect.foreach(println)
* }}}
*
* @group dataframes
* @since 1.3.0
*/
@DeveloperApi
def createDataFrame(rowRDD: RDD[Row], schema: StructType): DataFrame = {
createDataFrame(rowRDD, schema, needsConversion = true)
}
/**
* Creates a DataFrame from an RDD[Row]. User can specify whether the input rows should be
* converted to Catalyst rows.
*/
private[sql]
def createDataFrame(rowRDD: RDD[Row], schema: StructType, needsConversion: Boolean) = {
// TODO: use MutableProjection when rowRDD is another DataFrame and the applied
// schema differs from the existing schema on any field data type.
val catalystRows = if (needsConversion) {
val converter = CatalystTypeConverters.createToCatalystConverter(schema)
rowRDD.map(converter(_).asInstanceOf[InternalRow])
} else {
rowRDD.map{r: Row => InternalRow.fromSeq(r.toSeq)}
}
val logicalPlan = LogicalRDD(schema.toAttributes, catalystRows)(self)
DataFrame(this, logicalPlan)
}
def createDataset[T : Encoder](data: Seq[T]): Dataset[T] = {
val enc = encoderFor[T]
val attributes = enc.schema.toAttributes
val encoded = data.map(d => enc.toRow(d).copy())
val plan = new LocalRelation(attributes, encoded)
new Dataset[T](this, plan)
}
def createDataset[T : Encoder](data: RDD[T]): Dataset[T] = {
val enc = encoderFor[T]
val attributes = enc.schema.toAttributes
val encoded = data.map(d => enc.toRow(d))
val plan = LogicalRDD(attributes, encoded)(self)
new Dataset[T](this, plan)
}
def createDataset[T : Encoder](data: java.util.List[T]): Dataset[T] = {
createDataset(data.asScala)
}
/**
* Creates a DataFrame from an RDD[Row]. User can specify whether the input rows should be
* converted to Catalyst rows.
*/
private[sql]
def internalCreateDataFrame(catalystRows: RDD[InternalRow], schema: StructType) = {
// TODO: use MutableProjection when rowRDD is another DataFrame and the applied
// schema differs from the existing schema on any field data type.
val logicalPlan = LogicalRDD(schema.toAttributes, catalystRows)(self)
DataFrame(this, logicalPlan)
}
/**
* :: DeveloperApi ::
* Creates a [[DataFrame]] from an [[JavaRDD]] containing [[Row]]s using the given schema.
* It is important to make sure that the structure of every [[Row]] of the provided RDD matches
* the provided schema. Otherwise, there will be runtime exception.
*
* @group dataframes
* @since 1.3.0
*/
@DeveloperApi
def createDataFrame(rowRDD: JavaRDD[Row], schema: StructType): DataFrame = {
createDataFrame(rowRDD.rdd, schema)
}
/**
* :: DeveloperApi ::
* Creates a [[DataFrame]] from an [[java.util.List]] containing [[Row]]s using the given schema.
* It is important to make sure that the structure of every [[Row]] of the provided List matches
* the provided schema. Otherwise, there will be runtime exception.
*
* @group dataframes
* @since 1.6.0
*/
@DeveloperApi
def createDataFrame(rows: java.util.List[Row], schema: StructType): DataFrame = {
DataFrame(self, LocalRelation.fromExternalRows(schema.toAttributes, rows.asScala))
}
/**
* Applies a schema to an RDD of Java Beans.
*
* WARNING: Since there is no guaranteed ordering for fields in a Java Bean,
* SELECT * queries will return the columns in an undefined order.
* @group dataframes
* @since 1.3.0
*/
def createDataFrame(rdd: RDD[_], beanClass: Class[_]): DataFrame = {
val attributeSeq: Seq[AttributeReference] = getSchema(beanClass)
val className = beanClass.getName
val rowRdd = rdd.mapPartitions { iter =>
// BeanInfo is not serializable so we must rediscover it remotely for each partition.
val localBeanInfo = Introspector.getBeanInfo(Utils.classForName(className))
SQLContext.beansToRows(iter, localBeanInfo, attributeSeq)
}
DataFrame(this, LogicalRDD(attributeSeq, rowRdd)(this))
}
/**
* Applies a schema to an RDD of Java Beans.
*
* WARNING: Since there is no guaranteed ordering for fields in a Java Bean,
* SELECT * queries will return the columns in an undefined order.
* @group dataframes
* @since 1.3.0
*/
def createDataFrame(rdd: JavaRDD[_], beanClass: Class[_]): DataFrame = {
createDataFrame(rdd.rdd, beanClass)
}
/**
* Applies a schema to an List of Java Beans.
*
* WARNING: Since there is no guaranteed ordering for fields in a Java Bean,
* SELECT * queries will return the columns in an undefined order.
* @group dataframes
* @since 1.6.0
*/
def createDataFrame(data: java.util.List[_], beanClass: Class[_]): DataFrame = {
val attrSeq = getSchema(beanClass)
val className = beanClass.getName
val beanInfo = Introspector.getBeanInfo(beanClass)
val rows = SQLContext.beansToRows(data.asScala.iterator, beanInfo, attrSeq)
DataFrame(self, LocalRelation(attrSeq, rows.toSeq))
}
/**
* :: Experimental ::
* Returns a [[DataFrameReader]] that can be used to read data in as a [[DataFrame]].
* {{{
* sqlContext.read.parquet("/path/to/file.parquet")
* sqlContext.read.schema(schema).json("/path/to/file.json")
* }}}
*
* @group genericdata
* @since 1.4.0
*/
@Experimental
def read: DataFrameReader = new DataFrameReader(this)
/**
* :: Experimental ::
* Creates an external table from the given path and returns the corresponding DataFrame.
* It will use the default data source configured by spark.sql.sources.default.
*
* @group ddl_ops
* @since 1.3.0
*/
@Experimental
def createExternalTable(tableName: String, path: String): DataFrame = {
val dataSourceName = conf.defaultDataSourceName
createExternalTable(tableName, path, dataSourceName)
}
/**
* :: Experimental ::
* Creates an external table from the given path based on a data source
* and returns the corresponding DataFrame.
*
* @group ddl_ops
* @since 1.3.0
*/
@Experimental
def createExternalTable(
tableName: String,
path: String,
source: String): DataFrame = {
createExternalTable(tableName, source, Map("path" -> path))
}
/**
* :: Experimental ::
* Creates an external table from the given path based on a data source and a set of options.
* Then, returns the corresponding DataFrame.
*
* @group ddl_ops
* @since 1.3.0
*/
@Experimental
def createExternalTable(
tableName: String,
source: String,
options: java.util.Map[String, String]): DataFrame = {
createExternalTable(tableName, source, options.asScala.toMap)
}
/**
* :: Experimental ::
* (Scala-specific)
* Creates an external table from the given path based on a data source and a set of options.
* Then, returns the corresponding DataFrame.
*
* @group ddl_ops
* @since 1.3.0
*/
@Experimental
def createExternalTable(
tableName: String,
source: String,
options: Map[String, String]): DataFrame = {
val tableIdent = sqlParser.parseTableIdentifier(tableName)
val cmd =
CreateTableUsing(
tableIdent,
userSpecifiedSchema = None,
source,
temporary = false,
options,
allowExisting = false,
managedIfNoPath = false)
executePlan(cmd).toRdd
table(tableIdent)
}
/**
* :: Experimental ::
* Create an external table from the given path based on a data source, a schema and
* a set of options. Then, returns the corresponding DataFrame.
*
* @group ddl_ops
* @since 1.3.0
*/
@Experimental
def createExternalTable(
tableName: String,
source: String,
schema: StructType,
options: java.util.Map[String, String]): DataFrame = {
createExternalTable(tableName, source, schema, options.asScala.toMap)
}
/**
* :: Experimental ::
* (Scala-specific)
* Create an external table from the given path based on a data source, a schema and
* a set of options. Then, returns the corresponding DataFrame.
*
* @group ddl_ops
* @since 1.3.0
*/
@Experimental
def createExternalTable(
tableName: String,
source: String,
schema: StructType,
options: Map[String, String]): DataFrame = {
val tableIdent = sqlParser.parseTableIdentifier(tableName)
val cmd =
CreateTableUsing(
tableIdent,
userSpecifiedSchema = Some(schema),
source,
temporary = false,
options,
allowExisting = false,
managedIfNoPath = false)
executePlan(cmd).toRdd
table(tableIdent)
}
/**
* Registers the given [[DataFrame]] as a temporary table in the catalog. Temporary tables exist
* only during the lifetime of this instance of SQLContext.
*/
private[sql] def registerDataFrameAsTable(df: DataFrame, tableName: String): Unit = {
catalog.registerTable(TableIdentifier(tableName), df.logicalPlan)
}
/**
* Drops the temporary table with the given table name in the catalog. If the table has been
* cached/persisted before, it's also unpersisted.
*
* @param tableName the name of the table to be unregistered.
*
* @group basic
* @since 1.3.0
*/
def dropTempTable(tableName: String): Unit = {
cacheManager.tryUncacheQuery(table(tableName))
catalog.unregisterTable(TableIdentifier(tableName))
}
/**
* :: Experimental ::
* Creates a [[DataFrame]] with a single [[LongType]] column named `id`, containing elements
* in an range from 0 to `end` (exclusive) with step value 1.
*
* @since 1.4.1
* @group dataframe
*/
@Experimental
def range(end: Long): DataFrame = range(0, end)
/**
* :: Experimental ::
* Creates a [[DataFrame]] with a single [[LongType]] column named `id`, containing elements
* in an range from `start` to `end` (exclusive) with step value 1.
*
* @since 1.4.0
* @group dataframe
*/
@Experimental
def range(start: Long, end: Long): DataFrame = {
range(start, end, step = 1, numPartitions = sparkContext.defaultParallelism)
}
/**
* :: Experimental ::
* Creates a [[DataFrame]] with a single [[LongType]] column named `id`, containing elements
* in an range from `start` to `end` (exclusive) with an step value.
*
* @since 2.0.0
* @group dataframe
*/
@Experimental
def range(start: Long, end: Long, step: Long): DataFrame = {
range(start, end, step, numPartitions = sparkContext.defaultParallelism)
}
/**
* :: Experimental ::
* Creates a [[DataFrame]] with a single [[LongType]] column named `id`, containing elements
* in an range from `start` to `end` (exclusive) with an step value, with partition number
* specified.
*
* @since 1.4.0
* @group dataframe
*/
@Experimental
def range(start: Long, end: Long, step: Long, numPartitions: Int): DataFrame = {
DataFrame(this, Range(start, end, step, numPartitions))
}
/**
* Executes a SQL query using Spark, returning the result as a [[DataFrame]]. The dialect that is
* used for SQL parsing can be configured with 'spark.sql.dialect'.
*
* @group basic
* @since 1.3.0
*/
def sql(sqlText: String): DataFrame = {
DataFrame(this, parseSql(sqlText))
}
/**
* Returns the specified table as a [[DataFrame]].
*
* @group ddl_ops
* @since 1.3.0
*/
def table(tableName: String): DataFrame = {
table(sqlParser.parseTableIdentifier(tableName))
}
private def table(tableIdent: TableIdentifier): DataFrame = {
DataFrame(this, catalog.lookupRelation(tableIdent))
}
/**
* Returns a [[DataFrame]] containing names of existing tables in the current database.
* The returned DataFrame has two columns, tableName and isTemporary (a Boolean
* indicating if a table is a temporary one or not).
*
* @group ddl_ops
* @since 1.3.0
*/
def tables(): DataFrame = {
DataFrame(this, ShowTablesCommand(None))
}
/**
* Returns a [[DataFrame]] containing names of existing tables in the given database.
* The returned DataFrame has two columns, tableName and isTemporary (a Boolean
* indicating if a table is a temporary one or not).
*
* @group ddl_ops
* @since 1.3.0
*/
def tables(databaseName: String): DataFrame = {
DataFrame(this, ShowTablesCommand(Some(databaseName)))
}
/**
* Returns the names of tables in the current database as an array.
*
* @group ddl_ops
* @since 1.3.0
*/
def tableNames(): Array[String] = {
catalog.getTables(None).map {
case (tableName, _) => tableName
}.toArray
}
/**
* Returns the names of tables in the given database as an array.
*
* @group ddl_ops
* @since 1.3.0
*/
def tableNames(databaseName: String): Array[String] = {
catalog.getTables(Some(databaseName)).map {
case (tableName, _) => tableName
}.toArray
}
@transient
protected[sql] val planner: sparkexecution.SparkPlanner = new sparkexecution.SparkPlanner(this)
@transient
protected[sql] lazy val emptyResult = sparkContext.parallelize(Seq.empty[InternalRow], 1)
/**
* Prepares a planned SparkPlan for execution by inserting shuffle operations and internal
* row format conversions as needed.
*/
@transient
protected[sql] val prepareForExecution = new RuleExecutor[SparkPlan] {
val batches = Seq(
Batch("Add exchange", Once, EnsureRequirements(self)),
Batch("Whole stage codegen", Once, CollapseCodegenStages(self))
)
}
/**
* Parses the data type in our internal string representation. The data type string should
* have the same format as the one generated by `toString` in scala.
* It is only used by PySpark.
*/
protected[sql] def parseDataType(dataTypeString: String): DataType = {
DataType.fromJson(dataTypeString)
}
/**
* Apply a schema defined by the schemaString to an RDD. It is only used by PySpark.
*/
protected[sql] def applySchemaToPythonRDD(
rdd: RDD[Array[Any]],
schemaString: String): DataFrame = {
val schema = parseDataType(schemaString).asInstanceOf[StructType]
applySchemaToPythonRDD(rdd, schema)
}
/**
* Apply a schema defined by the schema to an RDD. It is only used by PySpark.
*/
protected[sql] def applySchemaToPythonRDD(
rdd: RDD[Array[Any]],
schema: StructType): DataFrame = {
val rowRdd = rdd.map(r => EvaluatePython.fromJava(r, schema).asInstanceOf[InternalRow])
DataFrame(this, LogicalRDD(schema.toAttributes, rowRdd)(self))
}
/**
* Returns a Catalyst Schema for the given java bean class.
*/
protected def getSchema(beanClass: Class[_]): Seq[AttributeReference] = {
val (dataType, _) = JavaTypeInference.inferDataType(beanClass)
dataType.asInstanceOf[StructType].fields.map { f =>
AttributeReference(f.name, f.dataType, f.nullable)()
}
}
// Register a successfully instantiated context to the singleton. This should be at the end of
// the class definition so that the singleton is updated only if there is no exception in the
// construction of the instance.
sparkContext.addSparkListener(new SparkListener {
override def onApplicationEnd(applicationEnd: SparkListenerApplicationEnd): Unit = {
SQLContext.clearInstantiatedContext()
SQLContext.clearSqlListener()
}
})
SQLContext.setInstantiatedContext(self)
}
/**
* This SQLContext object contains utility functions to create a singleton SQLContext instance,
* or to get the created SQLContext instance.
*
* It also provides utility functions to support preference for threads in multiple sessions
* scenario, setActive could set a SQLContext for current thread, which will be returned by
* getOrCreate instead of the global one.
*/
object SQLContext {
/**
* The active SQLContext for the current thread.
*/
private val activeContext: InheritableThreadLocal[SQLContext] =
new InheritableThreadLocal[SQLContext]
/**
* Reference to the created SQLContext.
*/
@transient private val instantiatedContext = new AtomicReference[SQLContext]()
@transient private val sqlListener = new AtomicReference[SQLListener]()
/**
* Get the singleton SQLContext if it exists or create a new one using the given SparkContext.
*
* This function can be used to create a singleton SQLContext object that can be shared across
* the JVM.
*
* If there is an active SQLContext for current thread, it will be returned instead of the global
* one.
*
* @since 1.5.0
*/
def getOrCreate(sparkContext: SparkContext): SQLContext = {
val ctx = activeContext.get()
if (ctx != null && !ctx.sparkContext.isStopped) {
return ctx
}
synchronized {
val ctx = instantiatedContext.get()
if (ctx == null || ctx.sparkContext.isStopped) {
new SQLContext(sparkContext)
} else {
ctx
}
}
}
private[sql] def clearInstantiatedContext(): Unit = {
instantiatedContext.set(null)
}
private[sql] def setInstantiatedContext(sqlContext: SQLContext): Unit = {
synchronized {
val ctx = instantiatedContext.get()
if (ctx == null || ctx.sparkContext.isStopped) {
instantiatedContext.set(sqlContext)
}
}
}
private[sql] def getInstantiatedContextOption(): Option[SQLContext] = {
Option(instantiatedContext.get())
}
private[sql] def clearSqlListener(): Unit = {
sqlListener.set(null)
}
/**
* Changes the SQLContext that will be returned in this thread and its children when
* SQLContext.getOrCreate() is called. This can be used to ensure that a given thread receives
* a SQLContext with an isolated session, instead of the global (first created) context.
*
* @since 1.6.0
*/
def setActive(sqlContext: SQLContext): Unit = {
activeContext.set(sqlContext)
}
/**
* Clears the active SQLContext for current thread. Subsequent calls to getOrCreate will
* return the first created context instead of a thread-local override.
*
* @since 1.6.0
*/
def clearActive(): Unit = {
activeContext.remove()
}
private[sql] def getActive(): Option[SQLContext] = {
Option(activeContext.get())
}
/**
* Converts an iterator of Java Beans to InternalRow using the provided
* bean info & schema. This is not related to the singleton, but is a static
* method for internal use.
*/
private def beansToRows(data: Iterator[_], beanInfo: BeanInfo, attrs: Seq[AttributeReference]):
Iterator[InternalRow] = {
val extractors =
beanInfo.getPropertyDescriptors.filterNot(_.getName == "class").map(_.getReadMethod)
val methodsToConverts = extractors.zip(attrs).map { case (e, attr) =>
(e, CatalystTypeConverters.createToCatalystConverter(attr.dataType))
}
data.map{ element =>
new GenericInternalRow(
methodsToConverts.map { case (e, convert) => convert(e.invoke(element)) }.toArray[Any]
): InternalRow
}
}
/**
* Create a SQLListener then add it into SparkContext, and create an SQLTab if there is SparkUI.
*/
private[sql] def createListenerAndUI(sc: SparkContext): SQLListener = {
if (sqlListener.get() == null) {
val listener = new SQLListener(sc.conf)
if (sqlListener.compareAndSet(null, listener)) {
sc.addSparkListener(listener)
sc.ui.foreach(new SQLTab(listener, _))
}
}
sqlListener.get()
}
}
|