Skip to content

[spark][test] Use explicit Paimon provider in feature tests #9145

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Zouxxyy wants to merge 1 commit into
base: master
Choose a base branch
from
Open

[spark][test] Use explicit Paimon provider in feature tests #9145

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
51 changes: 26 additions & 25 deletions ...on-spark/paimon-spark-ut/src/test/java/org/apache/paimon/spark/SparkChainTableITCase.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -114,9 +114,9 @@ public void testChainTable(@TempDir java.nio.file.Path tempDir) throws IOExcepti
+ " `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' = '$dt',\n"
Expand Down Expand Up @@ -349,9 +349,9 @@ public void testHourlyChainTable(@TempDir java.nio.file.Path tempDir) throws IOE
+ " `t1` BIGINT COMMENT 't1',\n"
+ " `t2` BIGINT COMMENT 't2',\n"
+ " `t3` STRING COMMENT 't3'\n"
+ " ) PARTITIONED BY (`dt` STRING COMMENT 'dt', `hour` STRING COMMENT 'hour') ROW FORMAT SERDE 'org.apache.paimon.hive.PaimonSerDe'\n"
+ "WITH\n"
+ " SERDEPROPERTIES ('serialization.format' = '1') STORED AS INPUTFORMAT 'org.apache.paimon.hive.mapred.PaimonInputFormat' OUTPUTFORMAT 'org.apache.paimon.hive.mapred.PaimonOutputFormat' TBLPROPERTIES (\n"
+ " ) USING paimon\n"
+ "PARTITIONED BY (`dt` STRING COMMENT 'dt', `hour` STRING COMMENT 'hour')\n"
+ "TBLPROPERTIES (\n"
+ " 'bucket-key' = 't1',\n"
+ " 'primary-key' = 'dt,hour,t1',\n"
+ " 'partition.timestamp-pattern' = '$dt $hour:00:00',\n"
Expand Down Expand Up @@ -592,9 +592,9 @@ public void testChainTableWithPartialUpdate(@TempDir java.nio.file.Path tempDir)
+ " `seq` BIGINT COMMENT 'seq',\n"
+ " `v1` STRING COMMENT 'v1',\n"
+ " `v2` STRING COMMENT 'v2'\n"
+ " ) PARTITIONED BY (`dt` STRING COMMENT 'dt') ROW FORMAT SERDE 'org.apache.paimon.hive.PaimonSerDe'\n"
+ "WITH\n"
+ " SERDEPROPERTIES ('serialization.format' = '1') STORED AS INPUTFORMAT 'org.apache.paimon.hive.mapred.PaimonInputFormat' OUTPUTFORMAT 'org.apache.paimon.hive.mapred.PaimonOutputFormat' TBLPROPERTIES (\n"
+ " ) USING paimon\n"
+ "PARTITIONED BY (`dt` STRING COMMENT 'dt')\n"
+ "TBLPROPERTIES (\n"
+ " 'bucket-key' = 'key',\n"
+ " 'primary-key' = 'dt,key',\n"
+ " 'partition.timestamp-pattern' = '$dt',\n"
Expand Down Expand Up @@ -748,9 +748,9 @@ public void testDropSnapshotPartition(@TempDir java.nio.file.Path tempDir) throw
+ " `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' = '$dt',\n"
Expand Down Expand Up @@ -822,7 +822,7 @@ public void testChainTableCacheInvalidation(@TempDir java.nio.file.Path tempDir)
+ " `t1` string ,"
+ " `t2` string ,"
+ " `t3` string"
+ ") PARTITIONED BY (`date` string)"
+ ") USING paimon PARTITIONED BY (`date` string) "
+ "TBLPROPERTIES ("
+ " 'chain-table.enabled' = 'true'"
+ " ,'primary-key' = 'date,t1'"
Expand Down Expand Up @@ -878,9 +878,9 @@ public void testChainTableWithGroupPartition(@TempDir java.nio.file.Path tempDir
+ " `t1` BIGINT COMMENT 't1',\n"
+ " `t2` BIGINT COMMENT 't2',\n"
+ " `t3` STRING COMMENT 't3'\n"
+ " ) PARTITIONED BY (`region` STRING, `dt` STRING COMMENT 'dt') ROW FORMAT SERDE 'org.apache.paimon.hive.PaimonSerDe'\n"
+ "WITH\n"
+ " SERDEPROPERTIES ('serialization.format' = '1') STORED AS INPUTFORMAT 'org.apache.paimon.hive.mapred.PaimonInputFormat' OUTPUTFORMAT 'org.apache.paimon.hive.mapred.PaimonOutputFormat' TBLPROPERTIES (\n"
+ " ) USING paimon\n"
+ "PARTITIONED BY (`region` STRING, `dt` STRING COMMENT 'dt')\n"
+ "TBLPROPERTIES (\n"
+ " 'bucket-key' = 't1',\n"
+ " 'primary-key' = 'region,dt,t1',\n"
+ " 'partition.timestamp-pattern' = '$dt',\n"
Expand Down Expand Up @@ -1310,9 +1310,9 @@ public void testHourlyChainTableWithGroupPartition(@TempDir java.nio.file.Path t
+ " `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 $hour:00:00',\n"
Expand Down Expand Up @@ -1767,9 +1767,9 @@ public void testChainTableWithMultiGroupPartition(@TempDir java.nio.file.Path te
+ " `t1` BIGINT COMMENT 't1',\n"
+ " `t2` BIGINT COMMENT 't2',\n"
+ " `t3` STRING COMMENT 't3'\n"
+ " ) PARTITIONED BY (`region` STRING, `biz_type` STRING COMMENT 'biz_type', `dt` STRING COMMENT 'dt') ROW FORMAT SERDE 'org.apache.paimon.hive.PaimonSerDe'\n"
+ "WITH\n"
+ " SERDEPROPERTIES ('serialization.format' = '1') STORED AS INPUTFORMAT 'org.apache.paimon.hive.mapred.PaimonInputFormat' OUTPUTFORMAT 'org.apache.paimon.hive.mapred.PaimonOutputFormat' TBLPROPERTIES (\n"
+ " ) USING paimon\n"
+ "PARTITIONED BY (`region` STRING, `biz_type` STRING COMMENT 'biz_type', `dt` STRING COMMENT 'dt')\n"
+ "TBLPROPERTIES (\n"
+ " 'bucket-key' = 't1',\n"
+ " 'primary-key' = 'region,biz_type,dt,t1',\n"
+ " 'partition.timestamp-pattern' = '$dt',\n"
Expand Down Expand Up @@ -2314,7 +2314,7 @@ public void testChainTableWithBranchOption(@TempDir java.nio.file.Path tempDir)
+ " `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"
Expand Down Expand Up @@ -2378,7 +2378,7 @@ public void testChainTableWithMultiChainKeys(@TempDir java.nio.file.Path tempDir
+ " `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"
Expand Down Expand Up @@ -2436,7 +2436,8 @@ public void testChainTableWithDeletionVectors(@TempDir java.nio.file.Path tempDi
+ " `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"
Expand Down
12 changes: 6 additions & 6 deletions ...spark/paimon-spark-ut/src/test/java/org/apache/paimon/spark/SparkDataEvolutionITCase.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -105,9 +105,9 @@ public void testDataEvolution(@TempDir java.nio.file.Path tempDir) throws IOExce
+ " `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"
Expand All @@ -124,9 +124,9 @@ public void testDataEvolution(@TempDir java.nio.file.Path tempDir) throws IOExce
+ " `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"
Expand Down
6 changes: 3 additions & 3 deletions ...on-spark/paimon-spark-ut/src/test/java/org/apache/paimon/spark/SparkMultimodalITCase.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -85,9 +85,9 @@ public void testVector(@TempDir java.nio.file.Path tempDir) throws IOException {
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"
Expand Down
Loading