Apache spark 在使用Spark结构化流处理Databricks Delta表中的流数据时处理重复数据？

我将Spark结构化流媒体与Azure Databricks Delta一起使用，我在其中写入Delta表（Delta表名称为raw）。我从Azure文件中读取数据，接收到无序数据，其中有两列“

smtUidNr

”和“

msgTs

”。我试图通过在代码中使用Upsert来处理重复项，但当我查询增量表“

raw

”时。我在delta表中看到以下重复记录

    smtUidNr                                 msgTs
    57A94ADA218547DC8AE2F3E7FB14339D    2019-08-26T08:58:46.000+0000
    57A94ADA218547DC8AE2F3E7FB14339D    2019-08-26T08:58:46.000+0000
    57A94ADA218547DC8AE2F3E7FB14339D    2019-08-26T08:58:46.000+0000

以下是我的代码：

import org.apache.spark._
import org.apache.spark.sql._
import org.apache.spark.sql.functions._


// merge duplicates
def upsertToDelta(microBatchOutputDF: DataFrame, batchId: Long) {


  microBatchOutputDF.createOrReplaceTempView("updates")


  microBatchOutputDF.sparkSession.sql(s"""
    MERGE INTO raw t
    USING updates s
    ON (s.smtUidNr = t.smtUidNr and s.msgTs>t.msgTs) 
    WHEN MATCHED THEN UPDATE SET * 
    WHEN NOT MATCHED THEN INSERT *
  """)
}


val df=spark.readStream.format("delta").load("abfss://abc@hjklinfo.dfs.core.windows.net/entrypacket/")
df.createOrReplaceTempView("table1")
val entrypacket_DF=spark.sql("""SELECT details as dcl,invdetails as inv,eventdetails as evt,smtdetails as smt,msgHdr.msgTs,msgHdr.msgInfSrcCd FROM table1 LATERAL VIEW explode(dcl) dcl AS details LATERAL VIEW explode(inv) inv AS invdetails LATERAL VIEW explode(evt) evt as eventdetails LATERAL VIEW explode(smt) smt as smtdetails""").dropDuplicates()


entrypacket_DF.createOrReplaceTempView("ucdx")

//Here, we are adding a column date_timestamp which converts msgTs timestamp to YYYYMMDD format in column date_timestamp which eliminates duplicate for today & then we drop this column meaning which we are not tampering with msgTs column
val resultDF=spark.sql("select dcl.smtUidNr,dcl,inv,evt,smt,cast(msgTs as timestamp)msgTs,msgInfSrcCd from ucdx").withColumn("date_timestamp",to_date(col("msgTs"))).dropDuplicates(Seq("smtUidNr","date_timestamp")).drop("date_timestamp")

resultDF.createOrReplaceTempView("final_tab")

val finalDF=spark.sql("select distinct smtUidNr,max(dcl) as dcl,max(inv) as inv,max(evt) as evt,max(smt) as smt,max(msgTs) as msgTs,max(msgInfSrcCd) as msgInfSrcCd from final_tab group by smtUidNr")


finalDF.writeStream.format("delta").foreachBatch(upsertToDelta _).outputMode("update").start()

---

结构化流不支持聚合、窗口函数和order by子句？我可以做些什么来修改我的代码，以便我只能有一条特定smtUidNr记录？

您需要做的是在

foreachBatch

方法中进行重复数据消除，这样您就可以确保每个批合并只为每个键写入一个值

在您的示例中，您将执行以下操作：

def upsertToDelta(microBatchOutputDF: DataFrame, batchId: Long) {

  microBatchOutputDF
    .select('smtUidNr, struct('msgTs, 'dcl, 'inv, 'evt, 'smt, 'msgInfSrcCd).as("cols"))
    .groupBy('smtUidNr)
    .agg(max('cols).as("latest"))
    .select("smtUidNr", "latest.*")
    .createOrReplaceTempView("updates")

  microBatchOutputDF.sparkSession.sql(s"""
    MERGE INTO raw t
    USING updates s
    ON (s.smtUidNr = t.smtUidNr and s.msgTs>t.msgTs) 
    WHEN MATCHED THEN UPDATE SET * 
    WHEN NOT MATCHED THEN INSERT *
  """)
}

finalDF.writeStream.foreachBatch(upsertToDelta _).outputMode("update").start()

---

您可以在文档中看到更多示例，

如果存在多个具有相同唯一id的行，则以下代码段可以帮助您查找最新记录。如果多个行完全相同，则仅拾取一行

将用于筛选行/记录的唯一键设置为“id”。 您有一个“timestamp”列来查找相同id的最新记录

def upsertToDelta(micro_batch_df, batchId) :
   delta_table = DeltaTable.forName(spark, f'{database}.{table_name}')
   df = micro_batch_df.dropDuplicates(['id']) \
       .withColumn("r", rank().over(Window.partitionBy('id') \
       .orderBy(col('timestamp').desc()))).filter("r==1").drop("r")
   delta_table.alias("t") \
      .merge(df.alias("s"), 's.id = t.id') \
      .whenMatchedUpdateAll() \
      .whenNotMatchedInsertAll() \
      .execute()
final_df.writeStream \
  .foreachBatch(upsertToDelta) \
  .option('checkpointLocation', '/mnt/path/checkpoint') \
  .outputMode('update') \
  .start()