[
https://issues.apache.org/jira/browse/HUDI-1485?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
wangxianghu updated HUDI-1485:
------------------------------
Description:
step to reproduce:
just use the delete demo in the quickstart
```
// 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 df = spark.read.json(spark.sparkContext.parallelize(deletes, 2))
df.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)
```
was:
use the delete demo in quickstart
```
// 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 df = spark.read.json(spark.sparkContext.parallelize(deletes, 2))
df.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)
```
> Fix Deletes issued without any prior commits exception
> ------------------------------------------------------
>
> Key: HUDI-1485
> URL: https://issues.apache.org/jira/browse/HUDI-1485
> Project: Apache Hudi
> Issue Type: Bug
> Reporter: wangxianghu
> Assignee: wangxianghu
> Priority: Major
>
> step to reproduce:
> just use the delete demo in the quickstart
> ```
> // 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 df = spark.read.json(spark.sparkContext.parallelize(deletes, 2))
> df.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)
> ```
>
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
