Я использую Spark 2.4.3 в локальном режиме и могу загружать файлы, но не могу записать их обратно в Redshift.Мне нужно знать правильные зависимости, чтобы сделать это.
Я обнаружил, что исторически были проблемы с avro-зависимостями, однако я не могу определить правильные зависимости для spark 2.4.3.Я перепробовал все виды комбинаций, но ни одна из них не позволяет мне написать обратно в красное смещение.
spark = SparkSession.builder.master("local").appName("Test")\
.config("spark.jars", 'RedshiftJDBC4-1.2.1.1001.jar,jets3t-0.9.0.jar,spark-avro_2.11-4.0.0.jar,hadoop-aws-2.7.4.jar')\
.config("spark.jars.packages", 'com.databricks:spark-redshift_2.10:0.5.0,com.amazonaws:aws-java-sdk:1.10.34,org.apache.hadoop:hadoop-aws:2.7.4')\
.config("driver.memory", '5g')\
.getOrCreate()
...
fact_table.write \
.format("com.databricks.spark.redshift") \
.option("url", jdbcUrl) \
.option("dbtable", "my_table") \
.option("tempdir", tempDir) \
.option('forward_spark_s3_credentials',True) \
.mode("error") \
.save()
Я получаю следующую ошибку:
: java.lang.AbstractMethodError: com.databricks.spark.redshift.DefaultSource.createRelation(Lorg/apache/spark/sql/SQLContext;Lorg/apache/spark/sql/SaveMode;Lscala/collection/immutable/Map;Lorg/apache/spark/sql/Dataset;)Lorg/apache/spark/sql/sources/BaseRelation;
at org.apache.spark.sql.execution.datasources.SaveIntoDataSourceCommand.run(SaveIntoDataSourceCommand.scala:45)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:86)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:131)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:127)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:155)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:80)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:80)
at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:676)
at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:676)
at org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:78)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:73)
at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:676)
at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:285)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:271)
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 py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:282)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:238)
at java.lang.Thread.run(Thread.java:748)