hive - Morphline readAvroParquetFile と solar を使用して寄木細工のファイルから 10 進数値を読み取る方法

Question

2 つの列 (名前の文字列、給与の 10 進数 (10,3)) を持つテーブルで、ハイブに寄木細工の形式で格納されます。Morphline とソーラーを使用してインデックス作成を実行すると、次の例外が発生します。

ERROR morphline.MorphlineMapRunner: Unable to process file <parquet file>
java.lang.ClassCastException: org.apache.avro.generic.GenericData$Record cannot be cast to java.io.InputStream
        at org.kitesdk.morphline.stdio.AbstractParser.getAttachmentInputStream(AbstractParser.java:184)
        at org.kitesdk.morphline.stdio.AbstractParser.doProcess(AbstractParser.java:94)
        at org.kitesdk.morphline.base.AbstractCommand.process(AbstractCommand.java:161)
        at org.kitesdk.morphline.base.Connector.process(Connector.java:64)
        at org.kitesdk.morphline.base.AbstractCommand.doProcess(AbstractCommand.java:186)
        at org.kitesdk.morphline.stdlib.ConvertTimestampBuilder$ConvertTimestamp.doProcess(ConvertTimestampBuilder.java:161)
        at org.kitesdk.morphline.base.AbstractCommand.process(AbstractCommand.java:161)
        at org.kitesdk.morphline.base.Connector.process(Connector.java:64)
        at org.kitesdk.morphline.base.AbstractCommand.doProcess(AbstractCommand.java:186)
        at org.kitesdk.morphline.stdlib.GenerateUUIDBuilder$GenerateUUID.doProcess(GenerateUUIDBuilder.java:98)
        at org.kitesdk.morphline.base.AbstractCommand.process(AbstractCommand.java:161)
        at org.kitesdk.morphline.base.Connector.process(Connector.java:64)
        at org.kitesdk.morphline.avro.ExtractAvroPathsBuilder$ExtractAvroPaths.doProcess(ExtractAvroPathsBuilder.java:143)
        at org.kitesdk.morphline.base.AbstractCommand.process(AbstractCommand.java:161)
        at org.kitesdk.morphline.base.Connector.process(Connector.java:64)
        at org.kitesdk.morphline.hadoop.parquet.avro.ReadAvroParquetFileBuilder$ReadAvroParquetFile.extract(ReadAvroParquetFileBuilder.java:201)
        at org.kitesdk.morphline.hadoop.parquet.avro.ReadAvroParquetFileBuilder$ReadAvroParquetFile.doProcess(ReadAvroParquetFileBuilder.java:180)
        at org.kitesdk.morphline.base.AbstractCommand.process(AbstractCommand.java:161)
        at org.kitesdk.morphline.base.AbstractCommand.doProcess(AbstractCommand.java:186)
        at org.kitesdk.morphline.base.AbstractCommand.process(AbstractCommand.java:161)
        at org.apache.solr.hadoop.morphline.MorphlineMapRunner.map(MorphlineMapRunner.java:208)
        at org.apache.solr.hadoop.MapReduceIndexerTool.dryRun(MapReduceIndexerTool.java:1250)
        at org.apache.solr.hadoop.MapReduceIndexerTool.run(MapReduceIndexerTool.java:875)
        at org.apache.solr.hadoop.MapReduceIndexerTool.run(MapReduceIndexerTool.java:700)
        at org.apache.hadoop.util.ToolRunner.run(ToolRunner.java:70)
        at org.apache.solr.hadoop.MapReduceIndexerTool.main(MapReduceIndexerTool.java:687)
        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:497)
        at org.apache.hadoop.util.RunJar.run(RunJar.java:221)
        at org.apache.hadoop.util.RunJar.main(RunJar.java:136)
Exception in thread "main" org.kitesdk.morphline.api.MorphlineRuntimeException: java.lang.ClassCastException: org.apache.avro.generic.GenericData$Record cannot be cast to java.io.InputStream
        at org.kitesdk.morphline.base.FaultTolerance.handleException(FaultTolerance.java:73)
        at org.apache.solr.hadoop.morphline.MorphlineMapRunner.map(MorphlineMapRunner.java:220)
        at org.apache.solr.hadoop.MapReduceIndexerTool.dryRun(MapReduceIndexerTool.java:1250)
        at org.apache.solr.hadoop.MapReduceIndexerTool.run(MapReduceIndexerTool.java:875)
        at org.apache.solr.hadoop.MapReduceIndexerTool.run(MapReduceIndexerTool.java:700)
        at org.apache.hadoop.util.ToolRunner.run(ToolRunner.java:70)
        at org.apache.solr.hadoop.MapReduceIndexerTool.main(MapReduceIndexerTool.java:687)
        at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
        at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
        at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
        at java.lang.reflect.Method.invoke(Method.java:497)
        at org.apache.hadoop.util.RunJar.run(RunJar.java:221)
        at org.apache.hadoop.util.RunJar.main(RunJar.java:136)
Caused by: java.lang.ClassCastException: org.apache.avro.generic.GenericData$Record cannot be cast to java.io.InputStream
        at org.kitesdk.morphline.stdio.AbstractParser.getAttachmentInputStream(AbstractParser.java:184)
        at org.kitesdk.morphline.stdio.AbstractParser.doProcess(AbstractParser.java:94)
        at org.kitesdk.morphline.base.AbstractCommand.process(AbstractCommand.java:161)
        at org.kitesdk.morphline.base.Connector.process(Connector.java:64)
        at org.kitesdk.morphline.base.AbstractCommand.doProcess(AbstractCommand.java:186)
        at org.kitesdk.morphline.stdlib.ConvertTimestampBuilder$ConvertTimestamp.doProcess(ConvertTimestampBuilder.java:161)
        at org.kitesdk.morphline.base.AbstractCommand.process(AbstractCommand.java:161)
        at org.kitesdk.morphline.base.Connector.process(Connector.java:64)
        at org.kitesdk.morphline.base.AbstractCommand.doProcess(AbstractCommand.java:186)
        at org.kitesdk.morphline.stdlib.GenerateUUIDBuilder$GenerateUUID.doProcess(GenerateUUIDBuilder.java:98)
        at org.kitesdk.morphline.base.AbstractCommand.process(AbstractCommand.java:161)
        at org.kitesdk.morphline.base.Connector.process(Connector.java:64)
        at org.kitesdk.morphline.avro.ExtractAvroPathsBuilder$ExtractAvroPaths.doProcess(ExtractAvroPathsBuilder.java:143)
        at org.kitesdk.morphline.base.AbstractCommand.process(AbstractCommand.java:161)
        at org.kitesdk.morphline.base.Connector.process(Connector.java:64)
        at org.kitesdk.morphline.hadoop.parquet.avro.ReadAvroParquetFileBuilder$ReadAvroParquetFile.extract(ReadAvroParquetFileBuilder.java:201)
        at org.kitesdk.morphline.hadoop.parquet.avro.ReadAvroParquetFileBuilder$ReadAvroParquetFile.doProcess(ReadAvroParquetFileBuilder.java:180)
        at org.kitesdk.morphline.base.AbstractCommand.process(AbstractCommand.java:161)
        at org.kitesdk.morphline.base.AbstractCommand.doProcess(AbstractCommand.java:186)
        at org.kitesdk.morphline.base.AbstractCommand.process(AbstractCommand.java:161)
        at org.apache.solr.hadoop.morphline.MorphlineMapRunner.map(MorphlineMapRunner.java:208)
        ... 11 more

Morphline ファイルの次のコンテンツ:

{
  readAvroParquetFile {
   readerSchemaString:"""{"type":"record","name":"employee","fields":[
     {"name":"name","type":["string","null"],"default":""},
     {"name": "salary","type":

["bytes","null"],"logicalType":"decimal","precision":10,"scale":4,"default":0 }
   ]}"""
  }
}

テーブルの寄木細工のファイルにインデックスを付ける方法に関するヘルプには、Morphline とソーラーを使用した 10 進数の列が含まれています。