1
nach einem einfachen Code, der eine HIVE-Tabelle zu erstellen versucht ::HIVE Tabelle nicht gefunden
import java.util.Properties
import org.apache.spark.SparkContext
import org.apache.spark.SparkConf
import org.apache.spark.sql.SQLContext
import sqlContext.implicits._
val conf = new SparkConf().setAppName("HIVE_Test").setMaster("local").set("spark.executor.memory","1g").set("spark.driver.allowMultipleContexts", "true");
val sc = new SparkContext(conf)
val sqlContext = new org.apache.spark.sql.hive.HiveContext(sc)
sqlContext.sql("CREATE TABLE amitesh_test(VND_ID INT,VND_NM STRING,VND_SHORT_NM STRING,VND_ADR_LN_1_TXT STRING,VND_ADR_LN_2_TXT STRING,VND_CITY_CD STRING,VND_ZIP_CD INT,LOAD_TS FLOAT,UPDT_TS FLOAT, PROMO_STTS_CD STRING, VND_STTS_CD STRING);");
sqlContext.sql("LOAD DATA INPATH 'path_to/part-m-00000' INTO TABLE amitesh_test");
exit()
Ich habe zwei Anfragen wie folgt ::
1) Da diese scala Code versucht, einen Tabellennamen amitesh_test erstellen, dann, warum immer ich den Fehler
17/03/15 04:34:40 ERROR ClientWrapper:
======================
HIVE FAILURE OUTPUT
======================
SET hive.support.sql11.reserved.keywords=false
FAILED: SemanticException [Error 10001]: Line 1:64 Table not found 'amitesh_test'
======================
END HIVE FAILURE OUTPUT
======================
2) Wie die SqlContext die HIVE-Datenbank zu verwenden, erstellen HIVE Tabelle kennen würde?
Spark-Version 1.6.1, scala 2.10.5. Ich bin mir ziemlich sicher, dass ich an vielen Stellen an dieser Stelle vermisse. Bitte schlage vor.
Vollstacktrace wie unten ::
Using Scala version 2.10.5 (OpenJDK 64-Bit Server VM, Java 1.8.0_77)
Type in expressions to have them evaluated.
Type :help for more information.
spark.yarn.driver.memoryOverhead is set but does not apply in client mode.
Spark context available as sc.
SQL context available as sqlContext.
Loading scala_code_to_import_db_tbl_to_hive.scala...
import java.util.Properties
import org.apache.spark.SparkContext
import org.apache.spark.SparkConf
import org.apache.spark.sql.SQLContext
import sqlContext.implicits._
conf: org.apache.spark.SparkConf = [email protected]
sc: org.apache.spark.SparkContext = [email protected]
sqlContext: org.apache.spark.sql.hive.HiveContext = [email protected]
org.apache.spark.sql.AnalysisException: extraneous input ';' expecting EOF near '<EOF>'; line 1 pos 223
at org.apache.spark.sql.hive.HiveQl$.createPlan(HiveQl.scala:318)
at org.apache.spark.sql.hive.ExtendedHiveQlParser$$anonfun$hiveQl$1.apply(ExtendedHiveQlParser.scala:41)
at org.apache.spark.sql.hive.ExtendedHiveQlParser$$anonfun$hiveQl$1.apply(ExtendedHiveQlParser.scala:40)
at scala.util.parsing.combinator.Parsers$Success.map(Parsers.scala:136)
at scala.util.parsing.combinator.Parsers$Success.map(Parsers.scala:135)
at scala.util.parsing.combinator.Parsers$Parser$$anonfun$map$1.apply(Parsers.scala:242)
at scala.util.parsing.combinator.Parsers$Parser$$anonfun$map$1.apply(Parsers.scala:242)
at scala.util.parsing.combinator.Parsers$$anon$3.apply(Parsers.scala:222)
at scala.util.parsing.combinator.Parsers$Parser$$anonfun$append$1$$anonfun$apply$2.apply(Parsers.scala:254)
at scala.util.parsing.combinator.Parsers$Parser$$anonfun$append$1$$anonfun$apply$2.apply(Parsers.scala:254)
at scala.util.parsing.combinator.Parsers$Failure.append(Parsers.scala:202)
at scala.util.parsing.combinator.Parsers$Parser$$anonfun$append$1.apply(Parsers.scala:254)
at scala.util.parsing.combinator.Parsers$Parser$$anonfun$append$1.apply(Parsers.scala:254)
at scala.util.parsing.combinator.Parsers$$anon$3.apply(Parsers.scala:222)
at scala.util.parsing.combinator.Parsers$$anon$2$$anonfun$apply$14.apply(Parsers.scala:891)
at scala.util.parsing.combinator.Parsers$$anon$2$$anonfun$apply$14.apply(Parsers.scala:891)
at scala.util.DynamicVariable.withValue(DynamicVariable.scala:57)
at scala.util.parsing.combinator.Parsers$$anon$2.apply(Parsers.scala:890)
at scala.util.parsing.combinator.PackratParsers$$anon$1.apply(PackratParsers.scala:110)
at org.apache.spark.sql.catalyst.AbstractSparkSQLParser.parse(AbstractSparkSQLParser.scala:34)
at org.apache.spark.sql.hive.HiveQl$.parseSql(HiveQl.scala:295)
at org.apache.spark.sql.hive.HiveQLDialect$$anonfun$parse$1.apply(HiveContext.scala:66)
at org.apache.spark.sql.hive.HiveQLDialect$$anonfun$parse$1.apply(HiveContext.scala:66)
at org.apache.spark.sql.hive.client.ClientWrapper$$anonfun$withHiveState$1.apply(ClientWrapper.scala:290)
at org.apache.spark.sql.hive.client.ClientWrapper.liftedTree1$1(ClientWrapper.scala:237)
at org.apache.spark.sql.hive.client.ClientWrapper.retryLocked(ClientWrapper.scala:236)
at org.apache.spark.sql.hive.client.ClientWrapper.withHiveState(ClientWrapper.scala:279)
at org.apache.spark.sql.hive.HiveQLDialect.parse(HiveContext.scala:65)
at org.apache.spark.sql.SQLContext$$anonfun$2.apply(SQLContext.scala:211)
at org.apache.spark.sql.SQLContext$$anonfun$2.apply(SQLContext.scala:211)
at org.apache.spark.sql.execution.SparkSQLParser$$anonfun$org$apache$spark$sql$execution$SparkSQLParser$$others$1.apply(SparkSQLParser.scala:114)
at org.apache.spark.sql.execution.SparkSQLParser$$anonfun$org$apache$spark$sql$execution$SparkSQLParser$$others$1.apply(SparkSQLParser.scala:113)
at scala.util.parsing.combinator.Parsers$Success.map(Parsers.scala:136)
at scala.util.parsing.combinator.Parsers$Success.map(Parsers.scala:135)
at scala.util.parsing.combinator.Parsers$Parser$$anonfun$map$1.apply(Parsers.scala:242)
at scala.util.parsing.combinator.Parsers$Parser$$anonfun$map$1.apply(Parsers.scala:242)
at scala.util.parsing.combinator.Parsers$$anon$3.apply(Parsers.scala:222)
at scala.util.parsing.combinator.Parsers$Parser$$anonfun$append$1$$anonfun$apply$2.apply(Parsers.scala:254)
at scala.util.parsing.combinator.Parsers$Parser$$anonfun$append$1$$anonfun$apply$2.apply(Parsers.scala:254)
at scala.util.parsing.combinator.Parsers$Failure.append(Parsers.scala:202)
at scala.util.parsing.combinator.Parsers$Parser$$anonfun$append$1.apply(Parsers.scala:254)
at scala.util.parsing.combinator.Parsers$Parser$$anonfun$append$1.apply(Parsers.scala:254)
at scala.util.parsing.combinator.Parsers$$anon$3.apply(Parsers.scala:222)
at scala.util.parsing.combinator.Parsers$$anon$2$$anonfun$apply$14.apply(Parsers.scala:891)
at scala.util.parsing.combinator.Parsers$$anon$2$$anonfun$apply$14.apply(Parsers.scala:891)
at scala.util.DynamicVariable.withValue(DynamicVariable.scala:57)
at scala.util.parsing.combinator.Parsers$$anon$2.apply(Parsers.scala:890)
at scala.util.parsing.combinator.PackratParsers$$anon$1.apply(PackratParsers.scala:110)
at org.apache.spark.sql.catalyst.AbstractSparkSQLParser.parse(AbstractSparkSQLParser.scala:34)
at org.apache.spark.sql.SQLContext$$anonfun$1.apply(SQLContext.scala:208)
at org.apache.spark.sql.SQLContext$$anonfun$1.apply(SQLContext.scala:208)
at org.apache.spark.sql.execution.datasources.DDLParser.parse(DDLParser.scala:43)
at org.apache.spark.sql.SQLContext.parseSql(SQLContext.scala:231)
at org.apache.spark.sql.hive.HiveContext.parseSql(HiveContext.scala:331)
at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:817)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:39)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:44)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:46)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:48)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:50)
at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:52)
at $iwC$$iwC$$iwC$$iwC.<init>(<console>:54)
at $iwC$$iwC$$iwC.<init>(<console>:56)
at $iwC$$iwC.<init>(<console>:58)
at $iwC.<init>(<console>:60)
at <init>(<console>:62)
at .<init>(<console>:66)
at .<clinit>(<console>)
at .<init>(<console>:7)
at .<clinit>(<console>)
at $print(<console>)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1065)
at org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1346)
at org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:840)
at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:871)
at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:819)
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$$interpretAllFrom$1$$anonfun$apply$mcV$sp$1$$anonfun$apply$mcV$sp$2.apply(SparkILoop.scala:680)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$interpretAllFrom$1$$anonfun$apply$mcV$sp$1$$anonfun$apply$mcV$sp$2.apply(SparkILoop.scala:677)
at scala.reflect.io.Streamable$Chars$class.applyReader(Streamable.scala:104)
at scala.reflect.io.File.applyReader(File.scala:82)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$interpretAllFrom$1$$anonfun$apply$mcV$sp$1.apply$mcV$sp(SparkILoop.scala:677)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$interpretAllFrom$1$$anonfun$apply$mcV$sp$1.apply(SparkILoop.scala:677)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$interpretAllFrom$1$$anonfun$apply$mcV$sp$1.apply(SparkILoop.scala:677)
at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$savingReplayStack(SparkILoop.scala:162)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$interpretAllFrom$1.apply$mcV$sp(SparkILoop.scala:676)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$interpretAllFrom$1.apply(SparkILoop.scala:676)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$interpretAllFrom$1.apply(SparkILoop.scala:676)
at org.apache.spark.repl.SparkILoop.savingReader(SparkILoop.scala:167)
at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$interpretAllFrom(SparkILoop.scala:675)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$loadCommand$1.apply(SparkILoop.scala:740)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$loadCommand$1.apply(SparkILoop.scala:739)
at org.apache.spark.repl.SparkILoop.withFile(SparkILoop.scala:733)
at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$loadCommand(SparkILoop.scala:739)
at org.apache.spark.repl.SparkILoop$$anonfun$standardCommands$7.apply(SparkILoop.scala:344)
at org.apache.spark.repl.SparkILoop$$anonfun$standardCommands$7.apply(SparkILoop.scala:344)
at scala.tools.nsc.interpreter.LoopCommands$LineCmd.apply(LoopCommands.scala:81)
at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:809)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$loadFiles$1.apply(SparkILoop.scala:910)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$loadFiles$1.apply(SparkILoop.scala:908)
at scala.collection.immutable.List.foreach(List.scala:318)
at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$loadFiles(SparkILoop.scala:908)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply$mcZ$sp(SparkILoop.scala:995)
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$$process(SparkILoop.scala:945)
at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:1059)
at org.apache.spark.repl.Main$.main(Main.scala:31)
at org.apache.spark.repl.Main.main(Main.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:731)
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$.main(SparkSubmit.scala:121)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
17/03/15 04:34:40 ERROR Hive: Table amitesh_test not found: default.amitesh_test table not found
17/03/15 04:34:40 ERROR Driver: FAILED: SemanticException [Error 10001]: Line 1:64 Table not found 'amitesh_test'
org.apache.hadoop.hive.ql.parse.SemanticException: Line 1:64 Table not found 'amitesh_test'
at org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer$TableSpec.<init>(BaseSemanticAnalyzer.java:769)
at org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer$TableSpec.<init>(BaseSemanticAnalyzer.java:731)
at org.apache.hadoop.hive.ql.parse.LoadSemanticAnalyzer.analyzeInternal(LoadSemanticAnalyzer.java:202)
at org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:227)
at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:424)
at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:308)
at org.apache.hadoop.hive.ql.Driver.compileInternal(Driver.java:1122)
at org.apache.hadoop.hive.ql.Driver.runInternal(Driver.java:1170)
at org.apache.hadoop.hive.ql.Driver.run(Driver.java:1059)
at org.apache.hadoop.hive.ql.Driver.run(Driver.java:1049)
at org.apache.spark.sql.hive.client.ClientWrapper$$anonfun$runHive$1.apply(ClientWrapper.scala:495)
at org.apache.spark.sql.hive.client.ClientWrapper$$anonfun$runHive$1.apply(ClientWrapper.scala:484)
at org.apache.spark.sql.hive.client.ClientWrapper$$anonfun$withHiveState$1.apply(ClientWrapper.scala:290)
at org.apache.spark.sql.hive.client.ClientWrapper.liftedTree1$1(ClientWrapper.scala:237)
at org.apache.spark.sql.hive.client.ClientWrapper.retryLocked(ClientWrapper.scala:236)
at org.apache.spark.sql.hive.client.ClientWrapper.withHiveState(ClientWrapper.scala:279)
at org.apache.spark.sql.hive.client.ClientWrapper.runHive(ClientWrapper.scala:484)
at org.apache.spark.sql.hive.client.ClientWrapper.runSqlHive(ClientWrapper.scala:474)
at org.apache.spark.sql.hive.HiveContext.runSqlHive(HiveContext.scala:605)
at org.apache.spark.sql.hive.execution.HiveNativeCommand.run(HiveNativeCommand.scala:33)
at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult$lzycompute(commands.scala:58)
at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult(commands.scala:56)
at org.apache.spark.sql.execution.ExecutedCommand.doExecute(commands.scala:70)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:132)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:130)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:130)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:55)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:55)
at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:145)
at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:130)
at org.apache.spark.sql.DataFrame$.apply(DataFrame.scala:52)
at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:817)
at $line32.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:39)
at $line32.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:44)
at $line32.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:46)
at $line32.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:48)
at $line32.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:50)
at $line32.$read$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:52)
at $line32.$read$$iwC$$iwC$$iwC$$iwC.<init>(<console>:54)
at $line32.$read$$iwC$$iwC$$iwC.<init>(<console>:56)
at $line32.$read$$iwC$$iwC.<init>(<console>:58)
at $line32.$read$$iwC.<init>(<console>:60)
at $line32.$read.<init>(<console>:62)
at $line32.$read$.<init>(<console>:66)
at $line32.$read$.<clinit>(<console>)
at $line32.$eval$.<init>(<console>:7)
at $line32.$eval$.<clinit>(<console>)
at $line32.$eval.$print(<console>)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1065)
at org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1346)
at org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:840)
at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:871)
at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:819)
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$$interpretAllFrom$1$$anonfun$apply$mcV$sp$1$$anonfun$apply$mcV$sp$2.apply(SparkILoop.scala:680)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$interpretAllFrom$1$$anonfun$apply$mcV$sp$1$$anonfun$apply$mcV$sp$2.apply(SparkILoop.scala:677)
at scala.reflect.io.Streamable$Chars$class.applyReader(Streamable.scala:104)
at scala.reflect.io.File.applyReader(File.scala:82)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$interpretAllFrom$1$$anonfun$apply$mcV$sp$1.apply$mcV$sp(SparkILoop.scala:677)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$interpretAllFrom$1$$anonfun$apply$mcV$sp$1.apply(SparkILoop.scala:677)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$interpretAllFrom$1$$anonfun$apply$mcV$sp$1.apply(SparkILoop.scala:677)
at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$savingReplayStack(SparkILoop.scala:162)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$interpretAllFrom$1.apply$mcV$sp(SparkILoop.scala:676)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$interpretAllFrom$1.apply(SparkILoop.scala:676)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$interpretAllFrom$1.apply(SparkILoop.scala:676)
at org.apache.spark.repl.SparkILoop.savingReader(SparkILoop.scala:167)
at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$interpretAllFrom(SparkILoop.scala:675)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$loadCommand$1.apply(SparkILoop.scala:740)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$loadCommand$1.apply(SparkILoop.scala:739)
at org.apache.spark.repl.SparkILoop.withFile(SparkILoop.scala:733)
at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$loadCommand(SparkILoop.scala:739)
at org.apache.spark.repl.SparkILoop$$anonfun$standardCommands$7.apply(SparkILoop.scala:344)
at org.apache.spark.repl.SparkILoop$$anonfun$standardCommands$7.apply(SparkILoop.scala:344)
at scala.tools.nsc.interpreter.LoopCommands$LineCmd.apply(LoopCommands.scala:81)
at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:809)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$loadFiles$1.apply(SparkILoop.scala:910)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$loadFiles$1.apply(SparkILoop.scala:908)
at scala.collection.immutable.List.foreach(List.scala:318)
at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$loadFiles(SparkILoop.scala:908)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply$mcZ$sp(SparkILoop.scala:995)
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$$process(SparkILoop.scala:945)
at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:1059)
at org.apache.spark.repl.Main$.main(Main.scala:31)
at org.apache.spark.repl.Main.main(Main.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:731)
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$.main(SparkSubmit.scala:121)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: org.apache.hadoop.hive.ql.metadata.InvalidTableException: Table not found amitesh_test
at org.apache.hadoop.hive.ql.metadata.Hive.getTable(Hive.java:1119)
at org.apache.hadoop.hive.ql.metadata.Hive.getTable(Hive.java:1070)
at org.apache.hadoop.hive.ql.metadata.Hive.getTable(Hive.java:1057)
at org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer$TableSpec.<init>(BaseSemanticAnalyzer.java:766)
... 105 more
17/03/15 04:34:40 ERROR ClientWrapper:
======================
HIVE FAILURE OUTPUT
======================
SET hive.support.sql11.reserved.keywords=false
FAILED: SemanticException [Error 10001]: Line 1:64 Table not found 'amitesh_test'
======================
END HIVE FAILURE OUTPUT
======================
Ich habe einige Veränderungen in meinem Code, die Datei zu laden, wie der Speicherort der Datei in HDFS ist ::
import java.util.Properties
import org.apache.spark.SparkContext
import org.apache.spark.SparkConf
import org.apache.spark.sql.SQLContext
import sqlContext.implicits._
val conf = new SparkConf().setAppName("HIVE_Test").setMaster("local").set("spark.executor.memory","1g").set("spark.driver.allowMultipleContexts", "true");
val sc = new SparkContext(conf);
val sqlContext = new org.apache.spark.sql.hive.HiveContext(sc);
sqlContext.sql("CREATE TABLE amitesh_test(VND_ID INT,VND_NM STRING,VND_SHORT_NM STRING,VND_ADR_LN_1_TXT STRING,VND_ADR_LN_2_TXT STRING,VND_CITY_CD STRING,VND_ZIP_CD INT,LOAD_TS FLOAT,UPDT_TS FLOAT, PROMO_STTS_CD STRING, VND_STTS_CD STRING)");
val text_input=sc.textFile("hdfs://server-name:port/path_to/part-m-00000");
sqlContext.sql("LOAD DATA INPATH 'hdfs://server-name:port/path_to/part-m-00000' INTO TABLE amitesh_test");
exit()
ich Störung erhalte ::
============================
17/03/15 07:14:15 ERROR ClientWrapper:
======================
HIVE FAILURE OUTPUT
======================
SET hive.support.sql11.reserved.keywords=false
OK
FAILED: SemanticException [Error 10028]: Line 1:17 Path is not legal ''hdfs://server_name/path_to/part-m-00000'': Move from: hdfs://server_name:port/path_to/part-m-00000 to: hdfs://xxx.xxx.com:port/path_to/amitesh_test is not valid. Please check that values for params "default.fs.name" and "hive.metastore.warehouse.dir" do not conflict.
======================
END HIVE FAILURE OUTPUT
======================
ich habe die "default.fs.name" in Kern-site.xml geprüft, und verwendet es dann in meinem Code. Also bin ich sicher, dass ich den Pfad in "LOAD INPATH" nicht richtig angegeben habe, das ist der Grund, ich sehe den Fehler. Bitte korrigieren Sie meinen Fehler.
Warum erstellen Sie nicht einfach eine externe Tabelle * von Hive * über 'path_to /'? –
Oder 'sc.textFile (" path_to/part-m-00000 ")' zu einem DataFrame, und speichern Sie das in einer Tabelle? –
wird es für die Standarddatenbank gehen, aber es ist immer die beste Praxis, die Datenbank zu erwähnen. –