使用Apache Phoenix和Spark在HBase中保存CSV＃spark2.2 #intelliJIdea

Question

我一直在尝试使用Spark从CSV加载数据并将其写入HBase。我能够轻松地在Spark 1.6中完成，但不能在Spark 2.2中完成。我已经尝试了多种方法，最后/最终一切都导致我使用Spark 2.2出现同样的错误：

  

线程“main”中的异常java.lang.IllegalArgumentException：无法从空字符串创建路径

知道为什么会这样。 共享代码段：

def main(args : Array[String]) {
val spark = SparkSession.builder
  .appName("PhoenixSpark")
  .master("local[*]")
  .getOrCreate

val df = spark.read
  .option("delimiter", "\001")
  .csv("/Users/11130/small")

val hBaseDf = spark.read
  .format("org.apache.phoenix.spark")
  .option("table", "EVENTS_DATA")
  .option("zkUrl", "localhost:2181")
  .load()

val tableSchema = hBaseDf.schema
val rowKeyDf = df.withColumn("row_key", concat(col("_c3"), lit("_"), col("_c5"), lit("_"), col("_c0")))
rowKeyDf.createOrReplaceTempView("mytable")

val correctedDf = spark.sql("Select row_key, _c0, _c1, _c2, _c3, _c4, _c5, _c6, _c7," +
  "_c8, _c9, _c10, _c11, _c12, _c13, _c14, _c15, _c16, _c17, _c18, _c19 from mytable")
val rdd = correctedDf.rdd
val finalDf= spark.createDataFrame(rdd, tableSchema)

finalDf.write
  .format("org.apache.phoenix.spark")
  .mode("overwrite")
  .option("table", "EVENTS_DATA")
  .option("zkUrl", "localhost:2181")
  .save()

spark.stop()

}

这是我的pom.xml，scala编译器版本也是2.11.8，它匹配所有依赖项的scala版本，包括 phoenix-spark ，我发现它是在2.11.8中构建的

<build>
    <plugins>
        <plugin>
            <groupId>org.apache.maven.plugins</groupId>
            <artifactId>maven-compiler-plugin</artifactId>
            <configuration>
                <source>1.8</source>
                <target>1.8</target>
            </configuration>
        </plugin>
    </plugins>
</build>

<dependencies>
    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-core_2.11</artifactId>
        <version>2.2.0</version>
        <!--<scope>provided</scope>-->
    </dependency>

    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-sql_2.11</artifactId>
        <version>2.2.0</version>
        <!--<scope>provided</scope>-->
    </dependency>

    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-hive_2.11</artifactId>
        <version>2.2.0</version>
        <!--<scope>provided</scope>-->
    </dependency>

    <dependency>
        <groupId>org.apache.phoenix</groupId>
        <artifactId>phoenix-spark</artifactId>
        <version>4.11.0-HBase-1.2</version>
        <!--<scope>provided</scope>-->
    </dependency>

</dependencies>

堆栈跟踪

java.lang.IllegalArgumentException: Can not create a Path from an empty string
at org.apache.hadoop.fs.Path.checkPathArg(Path.java:126)
at org.apache.hadoop.fs.Path.<init>(Path.java:134)
at org.apache.hadoop.fs.Path.<init>(Path.java:88)
at org.apache.spark.internal.io.HadoopMapReduceCommitProtocol.absPathStagingDir(HadoopMapReduceCommitProtocol.scala:58)
at org.apache.spark.internal.io.HadoopMapReduceCommitProtocol.commitJob(HadoopMapReduceCommitProtocol.scala:132)
at org.apache.spark.internal.io.SparkHadoopMapReduceWriter$.write(SparkHadoopMapReduceWriter.scala:101)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1.apply$mcV$sp(PairRDDFunctions.scala:1085)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1.apply(PairRDDFunctions.scala:1085)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1.apply(PairRDDFunctions.scala:1085)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:362)
at org.apache.spark.rdd.PairRDDFunctions.saveAsNewAPIHadoopDataset(PairRDDFunctions.scala:1084)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopFile$2.apply$mcV$sp(PairRDDFunctions.scala:1003)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopFile$2.apply(PairRDDFunctions.scala:994)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopFile$2.apply(PairRDDFunctions.scala:994)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:362)
at org.apache.spark.rdd.PairRDDFunctions.saveAsNewAPIHadoopFile(PairRDDFunctions.scala:994)
at org.apache.phoenix.spark.DataFrameFunctions.saveToPhoenix(DataFrameFunctions.scala:59)
at org.apache.phoenix.spark.DataFrameFunctions.saveToPhoenix(DataFrameFunctions.scala:28)
at org.apache.phoenix.spark.DefaultSource.createRelation(DefaultSource.scala:47)
at org.apache.spark.sql.execution.datasources.DataSource.write(DataSource.scala:472)
at org.apache.spark.sql.execution.datasources.SaveIntoDataSourceCommand.run(SaveIntoDataSourceCommand.scala:48)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:58)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:56)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:74)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:138)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:135)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:116)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:92)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:92)
at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:610)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:233)
at com.mynra.analytics.chronicles.PhoenixSpark$.main(PhoenixSpark.scala:56)
at com.mynra.analytics.chronicles.PhoenixSpark.main(PhoenixSpark.scala)

Exception in thread "main" java.lang.IllegalArgumentException: Can not create a Path from an empty string
at org.apache.hadoop.fs.Path.checkPathArg(Path.java:126)
at org.apache.hadoop.fs.Path.<init>(Path.java:134)
at org.apache.hadoop.fs.Path.<init>(Path.java:88)
at org.apache.spark.internal.io.HadoopMapReduceCommitProtocol.absPathStagingDir(HadoopMapReduceCommitProtocol.scala:58)
at org.apache.spark.internal.io.HadoopMapReduceCommitProtocol.abortJob(HadoopMapReduceCommitProtocol.scala:141)
at org.apache.spark.internal.io.SparkHadoopMapReduceWriter$.write(SparkHadoopMapReduceWriter.scala:106)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1.apply$mcV$sp(PairRDDFunctions.scala:1085)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1.apply(PairRDDFunctions.scala:1085)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopDataset$1.apply(PairRDDFunctions.scala:1085)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:362)
at org.apache.spark.rdd.PairRDDFunctions.saveAsNewAPIHadoopDataset(PairRDDFunctions.scala:1084)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopFile$2.apply$mcV$sp(PairRDDFunctions.scala:1003)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopFile$2.apply(PairRDDFunctions.scala:994)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsNewAPIHadoopFile$2.apply(PairRDDFunctions.scala:994)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:362)
at org.apache.spark.rdd.PairRDDFunctions.saveAsNewAPIHadoopFile(PairRDDFunctions.scala:994)
at org.apache.phoenix.spark.DataFrameFunctions.saveToPhoenix(DataFrameFunctions.scala:59)
at org.apache.phoenix.spark.DataFrameFunctions.saveToPhoenix(DataFrameFunctions.scala:28)
at org.apache.phoenix.spark.DefaultSource.createRelation(DefaultSource.scala:47)
at org.apache.spark.sql.execution.datasources.DataSource.write(DataSource.scala:472)
at org.apache.spark.sql.execution.datasources.SaveIntoDataSourceCommand.run(SaveIntoDataSourceCommand.scala:48)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:58)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:56)
at org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:74)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:138)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:135)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:116)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:92)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:92)
at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:610)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:233)
at com.mynra.analytics.chronicles.PhoenixSpark$.main(PhoenixSpark.scala:56)
at com.mynra.analytics.chronicles.PhoenixSpark.main(PhoenixSpark.scala)