hi,all
The environment I use is CDH6.3,
Use hadoop3 maven dependency to compile hudi,
<hadoop.version>3.0.0</hadoop.version>
execute quickstart,
bin / spark-shell --jars
/home/t3cx/apps/hudi/hudi-spark-bundle-0.5.1-SNAPSHOT.jar --conf
'spark.serializer = org.apache.spark.serializer.KryoSerializer'
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_cow_table"
val basePath = "file: /// tmp / hudi_cow_table"
val dataGen = new DataGenerator
val inserts = convertToStringList (dataGen.generateInserts (10))
val df = spark.read.json (spark.sparkContext.parallelize (inserts, 2))
df.write.format ("org.apache.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);
/ tmp / hudi_cow_table / No data in this directory
please help
[email protected]
