在下面的 Spark-shell 中，我尝试连接到 S3 并加载文件以创建数据帧：
spark-shell --packages com.databricks:spark-csv_2.10:1.5.0
scala> val sqlContext = new org.apache.spark.sql.SQLContext(sc)
scala> sc.hadoopConfiguration.set("fs.s3a.access.key", "")
scala> sc.hadoopConfiguration.set("fs.s3a.secret.key", "")
scala> val weekly =
sqlContext.read.format("com.databricks.spark.csv").option("header", "true").option("delimiter", ",").load("s3://usr_bucket/data/file.csv")
scala> print(weekly)
scala> weekly.show()
错误消息：
java.lang.VerifyError: Bad type on operand stack
Exception Details:
Location:
org/apache/hadoop/fs/s3/Jets3tFileSystemStore.initialize(Ljava/net/URI;Lorg/apache/hadoop/conf/Configuration;)V @43: invokespecial
Reason:
Type 'org/jets3t/service/security/AWSCredentials' (current frame, stack[3]) is not assignable to 'org/jets3t/service/security/ProviderCredentials'
Current Frame:
bci: @43
flags: { }
locals: { 'org/apache/hadoop/fs/s3/Jets3tFileSystemStore', 'java/net/URI', 'org/apache/hadoop/conf/Configuration', 'org/apache/hadoop/fs/s3/S3Credentials', 'org/jets3t/service/security/AWSCredentials' }
stack: { 'org/apache/hadoop/fs/s3/Jets3tFileSystemStore', uninitialized 37, uninitialized 37, 'org/jets3t/service/security/AWSCredentials' }
Bytecode:
0000000: 2a2c b500 02bb 0003 59b7 0004 4e2d 2b2c
0000010: b600 05bb 0006 592d b600 072d b600 08b7
0000020: 0009 3a04 2abb 000a 5919 04b7 000b b500
0000030: 0ca7 0023 3a04 1904 b600 0ec1 000f 9900
0000040: 0c19 04b6 000e c000 0fbf bb00 1059 1904
0000050: b700 11bf 2abb 0012 592b b600 13b7 0014
0000060: b500 152a 2c12 1611 1000 b600 17b5 0018
0000070: b1
Exception Handler Table:
bci [19, 49] => handler: 52
Stackmap Table:
full_frame(@52,{Object[#194],Object[#195],Object[#196],Object[#197]},{Object[#198]})
append_frame(@74,Object[#198])
chop_frame(@84,1)
at org.apache.hadoop.fs.s3.S3FileSystem.createDefaultStore(S3FileSystem.java:119)
at org.apache.hadoop.fs.s3.S3FileSystem.initialize(S3FileSystem.java:109)
at org.apache.hadoop.fs.FileSystem.createFileSystem(FileSystem.java:2816)
at org.apache.hadoop.fs.FileSystem.access$200(FileSystem.java:98)
at org.apache.hadoop.fs.FileSystem$Cache.getInternal(FileSystem.java:2853)
at org.apache.hadoop.fs.FileSystem$Cache.get(FileSystem.java:2835)
at org.apache.hadoop.fs.FileSystem.get(FileSystem.java:387)
at org.apache.hadoop.fs.Path.getFileSystem(Path.java:296)
at org.apache.hadoop.mapred.FileInputFormat.singleThreadedListStatus(FileInputFormat.java:258)
at org.apache.hadoop.mapred.FileInputFormat.listStatus(FileInputFormat.java:229)
at org.apache.hadoop.mapred.FileInputFormat.getSplits(FileInputFormat.java:315)
at org.apache.spark.rdd.HadoopRDD.getPartitions(HadoopRDD.scala:202)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
at org.apache.spark.rdd.RDD$$anonfun$take$1.apply(RDD.scala:1307)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
at org.apache.spark.rdd.RDD.take(RDD.scala:1302)
at org.apache.spark.rdd.RDD$$anonfun$first$1.apply(RDD.scala:1342)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
at org.apache.spark.rdd.RDD.first(RDD.scala:1341)
at com.databricks.spark.csv.CsvRelation.firstLine$lzycompute(CsvRelation.scala:269)
at com.databricks.spark.csv.CsvRelation.firstLine(CsvRelation.scala:265)
at com.databricks.spark.csv.CsvRelation.inferSchema(CsvRelation.scala:242)
at com.databricks.spark.csv.CsvRelation.<init>(CsvRelation.scala:74)
at com.databricks.spark.csv.DefaultSource.createRelation(DefaultSource.scala:171)
at com.databricks.spark.csv.DefaultSource.createRelation(DefaultSource.scala:44)
at org.apache.spark.sql.execution.datasources.ResolvedDataSource$.apply(ResolvedDataSource.scala:158)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:119)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:109)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:35)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:40)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:42)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:44)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:46)
at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:48)
at $iwC$$iwC$$iwC$$iwC.<init>(<console>:50)
at $iwC$$iwC$$iwC.<init>(<console>:52)
at $iwC$$iwC.<init>(<console>:54)
at $iwC.<init>(<console>:56)
at <init>(<console>:58)
at .<init>(<console>:62)
at .<clinit>(<console>)
at .<init>(<console>:7)
at .<clinit>(<console>)
at $print(<console>)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1045)
at org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1326)
at org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:821)
at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:852)
at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:800)
at org.apache.spark.repl.SparkILoop.reallyInterpret$1(SparkILoop.scala:857)
at org.apache.spark.repl.SparkILoop.interpretStartingWith(SparkILoop.scala:902)
at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:814)
at org.apache.spark.repl.SparkILoop.processLine$1(SparkILoop.scala:657)
at org.apache.spark.repl.SparkILoop.innerLoop$1(SparkILoop.scala:665)
at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$loop(SparkILoop.scala:670)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply$mcZ$sp(SparkILoop.scala:997)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
at scala.tools.nsc.util.ScalaClassLoader$.savingContextLoader(ScalaClassLoader.scala:135)
at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$process(SparkILoop.scala:945)
at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:1064)
at org.apache.spark.repl.Main$.main(Main.scala:35)
at org.apache.spark.repl.Main.main(Main.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:730)
at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:181)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:206)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:121)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
