【无标题】

Error log :

2022-01-26 11:04:14,689 ERROR counter.SparkCounters: counter[HIVE, RECORDS_OUT_OPERATOR_RS_34] has not initialized before.
2022-01-26 11:04:26,091 ERROR spark.SparkMapRecordHandler: Error processing row: org.apache.hadoop.hive.ql.metadata.HiveException: Hive Runtime Error while processing row
org.apache.hadoop.hive.ql.metadata.HiveException: Hive Runtime Error while processing row
        at org.apache.hadoop.hive.ql.exec.vector.VectorMapOperator.process(VectorMapOperator.java:973)
        at org.apache.hadoop.hive.ql.exec.spark.SparkMapRecordHandler.processRow(SparkMapRecordHandler.java:136)
        at org.apache.hadoop.hive.ql.exec.spark.HiveMapFunctionResultList.processNextRecord(HiveMapFunctionResultList.java:48)
        at org.apache.hadoop.hive.ql.exec.spark.HiveMapFunctionResultList.processNextRecord(HiveMapFunctionResultList.java:27)
        at org.apache.hadoop.hive.ql.exec.spark.HiveBaseFunctionResultList.hasNext(HiveBaseFunctionResultList.java:85)
        at scala.collection.convert.Wrappers$JIteratorWrapper.hasNext(Wrappers.scala:42)
        at org.apache.spark.util.collection.ExternalSorter.insertAll(ExternalSorter.scala:199)
        at org.apache.spark.shuffle.sort.SortShuffleWriter.write(SortShuffleWriter.scala:63)
        at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:96)
        at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53)
        at org.apache.spark.scheduler.Task.run(Task.scala:109)
        at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:345)
        at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
        at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
        at java.lang.Thread.run(Thread.java:748)
Caused by: org.apache.hadoop.hive.serde2.SerDeException: Row is not a valid JSON Object - JSONException: Unterminated string at 51 [character 52 line 1]
        at org.openx.data.jsonserde.JsonSerDe.onMalformedJson(JsonSerDe.java:424)
        at org.openx.data.jsonserde.JsonSerDe.deserialize(JsonSerDe.java:183)
        at org.apache.hadoop.hive.ql.exec.vector.VectorMapOperator.process(VectorMapOperator.java:936)
        ... 14 more
2022-01-26 11:04:26,096 ERROR executor.Executor: Exception in task 72.1 in stage 1.0 (TID 82)
java.lang.RuntimeException: Error processing row: org.apache.hadoop.hive.ql.metadata.HiveException: Hive Runtime Error while processing row
        at org.apache.hadoop.hive.ql.exec.spark.SparkMapRecordHandler.processRow(SparkMapRecordHandler.java:149)
        at org.apache.hadoop.hive.ql.exec.spark.HiveMapFunctionResultList.processNextRecord(HiveMapFunctionResultList.java:48)
        at org.apache.hadoop.hive.ql.exec.spark.HiveMapFunctionResultList.processNextRecord(HiveMapFunctionResultList.java:27)
        at org.apache.hadoop.hive.ql.exec.spark.HiveBaseFunctionResultList.hasNext(HiveBaseFunctionResultList.java:85)
        at scala.collection.convert.Wrappers$JIteratorWrapper.hasNext(Wrappers.scala:42)
        at org.apache.spark.util.collection.ExternalSorter.insertAll(ExternalSorter.scala:199)
        at org.apache.spark.shuffle.sort.SortShuffleWriter.write(SortShuffleWriter.scala:63)
        at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:96)
        at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53)
        at org.apache.spark.scheduler.Task.run(Task.scala:109)
        at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:345)
        at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
        at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
                                                                                                         

使用json格式解析hive表数据时，由于存在json格式异常的数据，导致执行时遇到该数据默认是抛出异常的，导致程序的中断。
解决：
ALTER TABLE tableName SET SERDEPROPERTIES ( “ignore.malformed.json” = “true”);