Apache Hudi Spark Guide

Spark Guide | Apache Hudi

        使用Spark数据源，我们将浏览代码片段，这些代码片段允许您插入和更新默认表类型的Hudi表：Copy on Write。在每次写入操作之后，我们还将演示如何以快照和增量方式读取数据。

Spark 3 Support Matrix

Hudi	Supported Spark 3 version
0.12.x	3.3.x (default build), 3.2.x, 3.1.x
0.11.x	3.2.x (default build, Spark bundle only), 3.1.x
0.10.x	3.1.x (default build), 3.0.x
0.7.0 - 0.9.0	3.0.x
0.6.0 and prior	not supported

SCALA

# Spark 3.3
spark-shell \
  --packages org.apache.hudi:hudi-spark3.3-bundle_2.12:0.12.1 \
  --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
  --conf 'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog' \
  --conf 'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'

# Spark 3.2
spark-shell \
  --packages org.apache.hudi:hudi-spark3.2-bundle_2.12:0.12.1 \
  --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
  --conf 'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog' \
  --conf 'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'

# Spark 3.1
spark-shell \
  --packages org.apache.hudi:hudi-spark3.1-bundle_2.12:0.12.1 \
  --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
  --conf 'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'

# Spark 2.4
spark-shell \
  --packages org.apache.hudi:hudi-spark2.4-bundle_2.11:0.12.1 \
  --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
  --conf 'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'

SQL

# Spark 3.3
spark-sql --packages org.apache.hudi:hudi-spark3.3-bundle_2.12:0.12.1 \
--conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
--conf 'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
--conf 'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'

# Spark 3.2
spark-sql --packages org.apache.hudi:hudi-spark3.2-bundle_2.12:0.12.1 \
--conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
--conf 'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
--conf 'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'

# Spark 3.1
spark-sql --packages org.apache.hudi:hudi-spark3.1-bundle_2.12:0.12.1 \
--conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
--conf 'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'

# Spark 2.4
spark-sql --packages org.apache.hudi:hudi-spark2.4-bundle_2.11:0.12.1 \
--conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
--conf 'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'

Setup table name, base path and a data generator to generate records for this guide.

// spark-shell
import org.apache.hudi.QuickstartUtils._
import scala.collection.JavaConversions._
import org.apache.spark.sql.SaveMode._
import org.apache.hudi.DataSourceReadOptions._
import org.apache.hudi.DataSourceWriteOptions._
import org.apache.hudi.config.HoodieWriteConfig._
import org.apache.hudi.common.model.HoodieRecord

val tableName = "hudi_trips_cow"
val basePath = "file:///tmp/hudi_trips_cow"
val dataGen = new DataGenerator

Insert data​

// spark-shell
val inserts = convertToStringList(dataGen.generateInserts(10))
val df = spark.read.json(spark.sparkContext.parallelize(inserts, 2))
df.write.format("hudi").
  options(getQuickstartWriteConfigs).
  option(PRECOMBINE_FIELD_OPT_KEY, "ts").
  option(RECORDKEY_FIELD_OPT_KEY, "uuid").
  option(PARTITIONPATH_FIELD_OPT_KEY, "partitionpath").
  option(TABLE_NAME, tableName).
  mode(Overwrite).
  save(basePath)

Query data

// spark-shell
val tripsSnapshotDF = spark.
  read.
  format("hudi").
  load(basePath)
tripsSnapshotDF.createOrReplaceTempView("hudi_trips_snapshot")

spark.sql("select fare, begin_lon, begin_lat, ts from  hudi_trips_snapshot where fare > 20.0").show()
spark.sql("select _hoodie_commit_time, _hoodie_record_key, _hoodie_partition_path, rider, driver, fare from  hudi_trips_snapshot").show()

Update data​

Deletes data

// spark-shell
// fetch total records count
spark.sql("select uuid, partitionpath from hudi_trips_snapshot").count()
// fetch two records to be deleted
val ds = spark.sql("select uuid, partitionpath from hudi_trips_snapshot").limit(2)

// issue deletes
val deletes = dataGen.generateDeletes(ds.collectAsList())
val hardDeleteDf = spark.read.json(spark.sparkContext.parallelize(deletes, 2))

hardDeleteDf.write.format("hudi").
  options(getQuickstartWriteConfigs).
  option(OPERATION_OPT_KEY, "delete").
  option(PRECOMBINE_FIELD_OPT_KEY, "ts").
  option(RECORDKEY_FIELD_OPT_KEY, "uuid").
  option(PARTITIONPATH_FIELD_OPT_KEY, "partitionpath").
  option(TABLE_NAME, tableName).
  mode(Append).
  save(basePath)

// run the same read query as above.
val roAfterDeleteViewDF = spark.
  read.
  format("hudi").
  load(basePath)

roAfterDeleteViewDF.registerTempTable("hudi_trips_snapshot")
// fetch should return (total - 2) records
spark.sql("select uuid, partitionpath from hudi_trips_snapshot").count()