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 2024/02/16 04:39:35 UTC

(hudi) branch master updated: [MINOR] Clarify config descriptions (#10681)

This is an automated email from the ASF dual-hosted git repository.

sivabalan pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/hudi.git


The following commit(s) were added to refs/heads/master by this push:
     new 9da1f2b15e2 [MINOR] Clarify config descriptions (#10681)
9da1f2b15e2 is described below

commit 9da1f2b15e2bf873a7d3db56dbc0183479c38c4c
Author: Bhavani Sudha Saktheeswaran <21...@users.noreply.github.com>
AuthorDate: Thu Feb 15 20:39:30 2024 -0800

    [MINOR] Clarify config descriptions (#10681)
    
    This aligns with the doc change here: https://github.com/apache/hudi/pull/10680
---
 .../src/main/scala/org/apache/hudi/DataSourceOptions.scala          | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/hudi/DataSourceOptions.scala b/hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/hudi/DataSourceOptions.scala
index 99080629e17..47a7c61a60f 100644
--- a/hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/hudi/DataSourceOptions.scala
+++ b/hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/hudi/DataSourceOptions.scala
@@ -500,7 +500,9 @@ object DataSourceWriteOptions {
     .defaultValue("false")
     .markAdvanced()
     .withDocumentation("If set to true, records from the incoming dataframe will not overwrite existing records with the same key during the write operation. " +
-      "This config is deprecated as of 0.14.0. Please use hoodie.datasource.insert.dup.policy instead.");
+      "<br /> **Note** Just for Insert operation in Spark SQL writing since 0.14.0, users can switch to the config `hoodie.datasource.insert.dup.policy` instead " +
+      "for a simplified duplicate handling experience. The new config will be incorporated into all other writing flows and this config will be fully deprecated " +
+      "in future releases.");
 
   val PARTITIONS_TO_DELETE: ConfigProperty[String] = ConfigProperty
     .key("hoodie.datasource.write.partitions.to.delete")
@@ -597,7 +599,7 @@ object DataSourceWriteOptions {
     .withValidValues(NONE_INSERT_DUP_POLICY, DROP_INSERT_DUP_POLICY, FAIL_INSERT_DUP_POLICY)
     .markAdvanced()
     .sinceVersion("0.14.0")
-    .withDocumentation("When operation type is set to \"insert\", users can optionally enforce a dedup policy. This policy will be employed "
+    .withDocumentation("**Note** This is only applicable to Spark SQL writing.<br />When operation type is set to \"insert\", users can optionally enforce a dedup policy. This policy will be employed "
       + " when records being ingested already exists in storage. Default policy is none and no action will be taken. Another option is to choose " +
       " \"drop\", on which matching records from incoming will be dropped and the rest will be ingested. Third option is \"fail\" which will " +
       "fail the write operation when same records are re-ingested. In other words, a given record as deduced by the key generation policy " +