You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hudi.apache.org by si...@apache.org on 2020/08/24 13:58:46 UTC
[hudi] branch asf-site updated: [HUDI-1103 Improve the code format
of Delete data demo in Quick-Start Guide] (#2015)
This is an automated email from the ASF dual-hosted git repository.
sivabalan pushed a commit to branch asf-site
in repository https://gitbox.apache.org/repos/asf/hudi.git
The following commit(s) were added to refs/heads/asf-site by this push:
new 1d30581 [HUDI-1103 Improve the code format of Delete data demo in Quick-Start Guide] (#2015)
1d30581 is described below
commit 1d30581ef8ddfa08a56b2a70f29370b927c649ca
Author: Trevor <wo...@gmail.com>
AuthorDate: Mon Aug 24 21:58:33 2020 +0800
[HUDI-1103 Improve the code format of Delete data demo in Quick-Start Guide] (#2015)
Co-authored-by: miaomiaomiao <33...@users.noreply.github.com>
---
docs/_docs/1_1_quick_start_guide.md | 34 +++++++++++++++-------------------
1 file changed, 15 insertions(+), 19 deletions(-)
diff --git a/docs/_docs/1_1_quick_start_guide.md b/docs/_docs/1_1_quick_start_guide.md
index 003fafb..e59fa94 100644
--- a/docs/_docs/1_1_quick_start_guide.md
+++ b/docs/_docs/1_1_quick_start_guide.md
@@ -192,27 +192,23 @@ val ds = spark.sql("select uuid, partitionpath from hudi_trips_snapshot").limit(
// 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)
+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)
// run the same read query as above.
-val roAfterDeleteViewDF = spark
- .read
- .format("hudi")
- .load(basePath + "/*/*/*/*")
+val roAfterDeleteViewDF = spark.
+ read.
+ format("hudi").
+ load(basePath + "/*/*/*/*")
roAfterDeleteViewDF.registerTempTable("hudi_trips_snapshot")
// fetch should return (total - 2) records