Hudi（二）Spark操作Hudi

1、Spark-shell读写Hudi

1.1、Spark-shell启动

// spark-shell for spark 3
spark-shell \
  --packages org.apache.hudi:hudi-spark3-bundle_2.12:0.10.0,org.apache.spark:spark-avro_2.12:3.1.2 \
  --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer'
  
// spark-shell for spark 2 with scala 2.12
spark-shell \
  --packages org.apache.hudi:hudi-spark-bundle_2.12:0.10.0,org.apache.spark:spark-avro_2.12:2.4.4 \
  --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer'
  
// spark-shell for spark 2 with scala 2.11
spark-shell \
  --packages org.apache.hudi:hudi-spark-bundle_2.11:0.10.0,org.apache.spark:spark-avro_2.11:2.4.4 \
  --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer'

1.2、设置表名

        设置表名，基本路径和数据生成器

// 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._

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

1.3、数据写入

// 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)

1.4、查询数据

// spark-shell
val tripsSnapshotDF = spark.
  read.
  format("hudi").
  load(basePath)
//load(basePath) use "/partitionKey=partitionValue" folder structure for Spark auto partition discovery
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()

1.5、修改数据

// spark-shell
val updates = convertToStringList(dataGen.generateUpdates(10))
val df = spark.read.json(spark.sparkContext.parallelize(updates, 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(Append).
  save(basePath)

1.6、增量查询

// spark-shell
// reload data
spark.
  read.
  format("hudi").
  load(basePath).
  createOrReplaceTempView("hudi_trips_snapshot")

val commits = spark.sql("select distinct(_hoodie_commit_time) as commitTime from  hudi_trips_snapshot order by commitTime").map(k => k.getString(0)).take(50)
val beginTime = commits(commits.length - 2) // commit time we are interested in

// incrementally query data
val tripsIncrementalDF = spark.read.format("hudi").
  option(QUERY_TYPE_OPT_KEY, QUERY_TYPE_INCREMENTAL_OPT_VAL).
  option(BEGIN_INSTANTTIME_OPT_KEY, beginTime).
  load(basePath)
tripsIncrementalDF.createOrReplaceTempView("hudi_trips_incremental")

spark.sql("select `_hoodie_commit_time`, fare, begin_lon, begin_lat, ts from  hudi_trips_incremental where fare > 20.0").show()

1.7、时间点查询

// spark-shell
val beginTime = "000" // Represents all commits > this time.
val endTime = commits(commits.length - 2) // commit time we are interested in

//incrementally query data
val tripsPointInTimeDF = spark.read.format("hudi").
  option(QUERY_TYPE_OPT_KEY, QUERY_TYPE_INCREMENTAL_OPT_VAL).
  option(BEGIN_INSTANTTIME_OPT_KEY, beginTime).
  option(END_INSTANTTIME_OPT_KEY, endTime).
  load(basePath)
tripsPointInTimeDF.createOrReplaceTempView("hudi_trips_point_in_time")
spark.sql("select `_hoodie_commit_time`, fare, begin_lon, begin_lat, ts from hudi_trips_point_in_time where f