This is an automated email from the ASF dual-hosted git repository.
JingsongLi pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/paimon.git
The following commit(s) were added to refs/heads/master by this push:
new b8527c4920 [spark][test] Use explicit Paimon provider in feature tests
(#9145)
b8527c4920 is described below
commit b8527c492087cd88a8f7c4541fe6b0241afe5e80
Author: Zouxxyy <[email protected]>
AuthorDate: Tue Aug 11 13:26:04 2026 +0800
[spark][test] Use explicit Paimon provider in feature tests (#9145)
---
.../apache/paimon/spark/SparkChainTableITCase.java | 51 +++++++++++-----------
.../paimon/spark/SparkDataEvolutionITCase.java | 12 ++---
.../apache/paimon/spark/SparkMultimodalITCase.java | 6 +--
3 files changed, 35 insertions(+), 34 deletions(-)
diff --git
a/paimon-spark/paimon-spark-ut/src/test/java/org/apache/paimon/spark/SparkChainTableITCase.java
b/paimon-spark/paimon-spark-ut/src/test/java/org/apache/paimon/spark/SparkChainTableITCase.java
index ed3814ab78..f3a396c481 100644
---
a/paimon-spark/paimon-spark-ut/src/test/java/org/apache/paimon/spark/SparkChainTableITCase.java
+++
b/paimon-spark/paimon-spark-ut/src/test/java/org/apache/paimon/spark/SparkChainTableITCase.java
@@ -114,9 +114,9 @@ public class SparkChainTableITCase {
+ " `t1` BIGINT COMMENT 't1',\n"
+ " `t2` BIGINT COMMENT 't2',\n"
+ " `t3` STRING COMMENT 't3'\n"
- + " ) PARTITIONED BY (`dt` STRING COMMENT 'dt') ROW
FORMAT SERDE 'org.apache.paimon.hive.PaimonSerDe'\n"
- + "WITH\n"
- + " SERDEPROPERTIES ('serialization.format' = '1')
STORED AS INPUTFORMAT 'org.apache.paimon.hive.mapred.PaimonInputFormat'
OUTPUTFORMAT 'org.apache.paimon.hive.mapred.PaimonOutputFormat' TBLPROPERTIES
(\n"
+ + " ) USING paimon\n"
+ + "PARTITIONED BY (`dt` STRING COMMENT 'dt')\n"
+ + "TBLPROPERTIES (\n"
+ " 'bucket-key' = 't1',\n"
+ " 'primary-key' = 'dt,t1',\n"
+ " 'partition.timestamp-pattern' = '$dt',\n"
@@ -349,9 +349,9 @@ public class SparkChainTableITCase {
+ " `t1` BIGINT COMMENT 't1',\n"
+ " `t2` BIGINT COMMENT 't2',\n"
+ " `t3` STRING COMMENT 't3'\n"
- + " ) PARTITIONED BY (`dt` STRING COMMENT 'dt',
`hour` STRING COMMENT 'hour') ROW FORMAT SERDE
'org.apache.paimon.hive.PaimonSerDe'\n"
- + "WITH\n"
- + " SERDEPROPERTIES ('serialization.format' = '1')
STORED AS INPUTFORMAT 'org.apache.paimon.hive.mapred.PaimonInputFormat'
OUTPUTFORMAT 'org.apache.paimon.hive.mapred.PaimonOutputFormat' TBLPROPERTIES
(\n"
+ + " ) USING paimon\n"
+ + "PARTITIONED BY (`dt` STRING COMMENT 'dt', `hour`
STRING COMMENT 'hour')\n"
+ + "TBLPROPERTIES (\n"
+ " 'bucket-key' = 't1',\n"
+ " 'primary-key' = 'dt,hour,t1',\n"
+ " 'partition.timestamp-pattern' = '$dt
$hour:00:00',\n"
@@ -592,9 +592,9 @@ public class SparkChainTableITCase {
+ " `seq` BIGINT COMMENT 'seq',\n"
+ " `v1` STRING COMMENT 'v1',\n"
+ " `v2` STRING COMMENT 'v2'\n"
- + " ) PARTITIONED BY (`dt` STRING COMMENT 'dt') ROW
FORMAT SERDE 'org.apache.paimon.hive.PaimonSerDe'\n"
- + "WITH\n"
- + " SERDEPROPERTIES ('serialization.format' = '1')
STORED AS INPUTFORMAT 'org.apache.paimon.hive.mapred.PaimonInputFormat'
OUTPUTFORMAT 'org.apache.paimon.hive.mapred.PaimonOutputFormat' TBLPROPERTIES
(\n"
+ + " ) USING paimon\n"
+ + "PARTITIONED BY (`dt` STRING COMMENT 'dt')\n"
+ + "TBLPROPERTIES (\n"
+ " 'bucket-key' = 'key',\n"
+ " 'primary-key' = 'dt,key',\n"
+ " 'partition.timestamp-pattern' = '$dt',\n"
@@ -748,9 +748,9 @@ public class SparkChainTableITCase {
+ " `t1` BIGINT COMMENT 't1',\n"
+ " `t2` BIGINT COMMENT 't2',\n"
+ " `t3` STRING COMMENT 't3'\n"
- + " ) PARTITIONED BY (`dt` STRING COMMENT 'dt') ROW
FORMAT SERDE 'org.apache.paimon.hive.PaimonSerDe'\n"
- + "WITH\n"
- + " SERDEPROPERTIES ('serialization.format' = '1')
STORED AS INPUTFORMAT 'org.apache.paimon.hive.mapred.PaimonInputFormat'
OUTPUTFORMAT 'org.apache.paimon.hive.mapred.PaimonOutputFormat' TBLPROPERTIES
(\n"
+ + " ) USING paimon\n"
+ + "PARTITIONED BY (`dt` STRING COMMENT 'dt')\n"
+ + "TBLPROPERTIES (\n"
+ " 'bucket-key' = 't1',\n"
+ " 'primary-key' = 'dt,t1',\n"
+ " 'partition.timestamp-pattern' = '$dt',\n"
@@ -822,7 +822,7 @@ public class SparkChainTableITCase {
+ " `t1` string ,"
+ " `t2` string ,"
+ " `t3` string"
- + ") PARTITIONED BY (`date` string)"
+ + ") USING paimon PARTITIONED BY (`date` string) "
+ "TBLPROPERTIES ("
+ " 'chain-table.enabled' = 'true'"
+ " ,'primary-key' = 'date,t1'"
@@ -878,9 +878,9 @@ public class SparkChainTableITCase {
+ " `t1` BIGINT COMMENT 't1',\n"
+ " `t2` BIGINT COMMENT 't2',\n"
+ " `t3` STRING COMMENT 't3'\n"
- + " ) PARTITIONED BY (`region` STRING, `dt` STRING
COMMENT 'dt') ROW FORMAT SERDE 'org.apache.paimon.hive.PaimonSerDe'\n"
- + "WITH\n"
- + " SERDEPROPERTIES ('serialization.format' = '1')
STORED AS INPUTFORMAT 'org.apache.paimon.hive.mapred.PaimonInputFormat'
OUTPUTFORMAT 'org.apache.paimon.hive.mapred.PaimonOutputFormat' TBLPROPERTIES
(\n"
+ + " ) USING paimon\n"
+ + "PARTITIONED BY (`region` STRING, `dt` STRING
COMMENT 'dt')\n"
+ + "TBLPROPERTIES (\n"
+ " 'bucket-key' = 't1',\n"
+ " 'primary-key' = 'region,dt,t1',\n"
+ " 'partition.timestamp-pattern' = '$dt',\n"
@@ -1310,9 +1310,9 @@ public class SparkChainTableITCase {
+ " `t1` BIGINT COMMENT 't1',\n"
+ " `t2` BIGINT COMMENT 't2',\n"
+ " `t3` STRING COMMENT 't3'\n"
- + " ) PARTITIONED BY (`region` STRING, `dt` STRING
COMMENT 'dt', `hour` STRING COMMENT 'hour') ROW FORMAT SERDE
'org.apache.paimon.hive.PaimonSerDe'\n"
- + "WITH\n"
- + " SERDEPROPERTIES ('serialization.format' = '1')
STORED AS INPUTFORMAT 'org.apache.paimon.hive.mapred.PaimonInputFormat'
OUTPUTFORMAT 'org.apache.paimon.hive.mapred.PaimonOutputFormat' TBLPROPERTIES
(\n"
+ + " ) USING paimon\n"
+ + "PARTITIONED BY (`region` STRING, `dt` STRING
COMMENT 'dt', `hour` STRING COMMENT 'hour')\n"
+ + "TBLPROPERTIES (\n"
+ " 'bucket-key' = 't1',\n"
+ " 'primary-key' = 'region,dt,hour,t1',\n"
+ " 'partition.timestamp-pattern' = '$dt
$hour:00:00',\n"
@@ -1767,9 +1767,9 @@ public class SparkChainTableITCase {
+ " `t1` BIGINT COMMENT 't1',\n"
+ " `t2` BIGINT COMMENT 't2',\n"
+ " `t3` STRING COMMENT 't3'\n"
- + " ) PARTITIONED BY (`region` STRING, `biz_type`
STRING COMMENT 'biz_type', `dt` STRING COMMENT 'dt') ROW FORMAT SERDE
'org.apache.paimon.hive.PaimonSerDe'\n"
- + "WITH\n"
- + " SERDEPROPERTIES ('serialization.format' = '1')
STORED AS INPUTFORMAT 'org.apache.paimon.hive.mapred.PaimonInputFormat'
OUTPUTFORMAT 'org.apache.paimon.hive.mapred.PaimonOutputFormat' TBLPROPERTIES
(\n"
+ + " ) USING paimon\n"
+ + "PARTITIONED BY (`region` STRING, `biz_type` STRING
COMMENT 'biz_type', `dt` STRING COMMENT 'dt')\n"
+ + "TBLPROPERTIES (\n"
+ " 'bucket-key' = 't1',\n"
+ " 'primary-key' = 'region,biz_type,dt,t1',\n"
+ " 'partition.timestamp-pattern' = '$dt',\n"
@@ -2314,7 +2314,7 @@ public class SparkChainTableITCase {
+ " `t1` BIGINT,\n"
+ " `t2` BIGINT,\n"
+ " `t3` STRING\n"
- + ") PARTITIONED BY (`dt` STRING)\n"
+ + ") USING paimon PARTITIONED BY (`dt` STRING)\n"
+ "TBLPROPERTIES (\n"
+ " 'bucket-key' = 't1',\n"
+ " 'primary-key' = 'dt,t1',\n"
@@ -2378,7 +2378,7 @@ public class SparkChainTableITCase {
+ " `t1` BIGINT COMMENT 't1',\n"
+ " `t2` BIGINT COMMENT 't2',\n"
+ " `t3` STRING COMMENT 't3'\n"
- + ") PARTITIONED BY (`dt` STRING, `hr` STRING)\n"
+ + ") USING paimon PARTITIONED BY (`dt` STRING, `hr`
STRING)\n"
+ "TBLPROPERTIES (\n"
+ " 'bucket-key' = 't1',\n"
+ " 'primary-key' = 'dt,hr,t1',\n"
@@ -2436,7 +2436,8 @@ public class SparkChainTableITCase {
+ " `t1` BIGINT COMMENT 't1',\n"
+ " `t2` BIGINT COMMENT 't2',\n"
+ " `t3` STRING COMMENT 't3'\n"
- + ") PARTITIONED BY (`region` STRING COMMENT 'region',
`date` STRING COMMENT 'date')\n"
+ + ") USING paimon\n"
+ + "PARTITIONED BY (`region` STRING COMMENT 'region',
`date` STRING COMMENT 'date')\n"
+ "TBLPROPERTIES (\n"
+ " 'chain-table.enabled' = 'true',\n"
+ " 'deletion-vectors.enabled' = 'true',\n"
diff --git
a/paimon-spark/paimon-spark-ut/src/test/java/org/apache/paimon/spark/SparkDataEvolutionITCase.java
b/paimon-spark/paimon-spark-ut/src/test/java/org/apache/paimon/spark/SparkDataEvolutionITCase.java
index d9a8c6c711..f6b48d9e69 100644
---
a/paimon-spark/paimon-spark-ut/src/test/java/org/apache/paimon/spark/SparkDataEvolutionITCase.java
+++
b/paimon-spark/paimon-spark-ut/src/test/java/org/apache/paimon/spark/SparkDataEvolutionITCase.java
@@ -105,9 +105,9 @@ public class SparkDataEvolutionITCase {
+ " `g_1_2` BIGINT COMMENT 'g_1_2',\n"
+ " `g_2_1` BIGINT COMMENT 'g_2_1',\n"
+ " `g_2_2` BIGINT COMMENT 'g_2_2'\n"
- + " ) PARTITIONED BY (`dt` STRING COMMENT 'dt') ROW
FORMAT SERDE 'org.apache.paimon.hive.PaimonSerDe'\n"
- + "WITH\n"
- + " SERDEPROPERTIES ('serialization.format' = '1')
STORED AS INPUTFORMAT 'org.apache.paimon.hive.mapred.PaimonInputFormat'
OUTPUTFORMAT 'org.apache.paimon.hive.mapred.PaimonOutputFormat' TBLPROPERTIES
(\n"
+ + " ) USING paimon\n"
+ + "PARTITIONED BY (`dt` STRING COMMENT 'dt')\n"
+ + "TBLPROPERTIES (\n"
+ " 'file.compression' = 'snappy',\n"
+ " 'manifest.compression' = 'snappy',\n"
+ " 'row-tracking.enabled' = 'true',\n"
@@ -124,9 +124,9 @@ public class SparkDataEvolutionITCase {
+ " `id` BIGINT COMMENT 'id',\n"
+ " `g_2_1` BIGINT COMMENT 'g_2_1',\n"
+ " `g_2_2` BIGINT COMMENT 'g_2_2'\n"
- + " ) PARTITIONED BY (`dt` STRING COMMENT 'dt') ROW
FORMAT SERDE 'org.apache.paimon.hive.PaimonSerDe'\n"
- + "WITH\n"
- + " SERDEPROPERTIES ('serialization.format' = '1')
STORED AS INPUTFORMAT 'org.apache.paimon.hive.mapred.PaimonInputFormat'
OUTPUTFORMAT 'org.apache.paimon.hive.mapred.PaimonOutputFormat' TBLPROPERTIES
(\n"
+ + " ) USING paimon\n"
+ + "PARTITIONED BY (`dt` STRING COMMENT 'dt')\n"
+ + "TBLPROPERTIES (\n"
+ " 'file.compression' = 'snappy',\n"
+ " 'manifest.compression' = 'snappy',\n"
+ " 'partition.timestamp-pattern' = '$dt',\n"
diff --git
a/paimon-spark/paimon-spark-ut/src/test/java/org/apache/paimon/spark/SparkMultimodalITCase.java
b/paimon-spark/paimon-spark-ut/src/test/java/org/apache/paimon/spark/SparkMultimodalITCase.java
index 6166d257fc..c75662d1d1 100644
---
a/paimon-spark/paimon-spark-ut/src/test/java/org/apache/paimon/spark/SparkMultimodalITCase.java
+++
b/paimon-spark/paimon-spark-ut/src/test/java/org/apache/paimon/spark/SparkMultimodalITCase.java
@@ -85,9 +85,9 @@ public class SparkMultimodalITCase {
spark.sql(
"\n"
+ "CREATE TABLE my_db1.vector_test (gid BIGINT, sid
STRING, embs ARRAY<FLOAT>)"
- + " PARTITIONED BY (`date` STRING COMMENT 'date') ROW
FORMAT SERDE 'org.apache.paimon.hive.PaimonSerDe'\n"
- + "WITH\n"
- + " SERDEPROPERTIES ('serialization.format' = '1')
STORED AS INPUTFORMAT 'org.apache.paimon.hive.mapred.PaimonInputFormat'
OUTPUTFORMAT 'org.apache.paimon.hive.mapred.PaimonOutputFormat' TBLPROPERTIES
(\n"
+ + " USING paimon\n"
+ + "PARTITIONED BY (`date` STRING COMMENT 'date')\n"
+ + "TBLPROPERTIES (\n"
+ " 'vector.file.format'='lance',\n"
+ " 'vector-field'='embs',\n"
+ " 'field.embs.vector-dim'='4',\n"
