This is an automated email from the ASF dual-hosted git repository.
deniskuzZ pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/hive.git
The following commit(s) were added to refs/heads/master by this push:
new f7f3671b290 HIVE-30130: Iceberg: remove iceberg.delete.skiprowdata
(#6862)
f7f3671b290 is described below
commit f7f3671b29069f4b857076857a54243c99295a64
Author: Raghav Aggarwal <[email protected]>
AuthorDate: Thu Oct 15 04:54:18 2026 +0530
HIVE-30130: Iceberg: remove iceberg.delete.skiprowdata (#6862)
---
.../mr/hive/writer/HiveIcebergDeleteWriter.java | 6 -
.../iceberg/mr/hive/writer/WriterBuilder.java | 10 -
.../mr/hive/writer/HiveIcebergWriterTestBase.java | 24 +-
.../src/test/queries/positive/delete_all_iceberg.q | 2 +-
.../src/test/queries/positive/iceberg_v2_deletes.q | 93 ------
.../positive/vectorized_iceberg_merge_mixed.q | 2 +-
.../test/results/positive/delete_all_iceberg.q.out | 5 +-
.../test/results/positive/iceberg_v2_deletes.q.out | 342 ---------------------
.../positive/vectorized_iceberg_merge_mixed.q.out | 4 +-
9 files changed, 13 insertions(+), 475 deletions(-)
diff --git
a/iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/hive/writer/HiveIcebergDeleteWriter.java
b/iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/hive/writer/HiveIcebergDeleteWriter.java
index f4526189e86..85cf6bfdf7e 100644
---
a/iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/hive/writer/HiveIcebergDeleteWriter.java
+++
b/iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/hive/writer/HiveIcebergDeleteWriter.java
@@ -41,7 +41,6 @@
class HiveIcebergDeleteWriter extends HiveIcebergWriterBase {
private final GenericRecord rowDataTemplate;
- private final boolean skipRowData;
private final boolean isMergeTask;
HiveIcebergDeleteWriter(
@@ -51,7 +50,6 @@ class HiveIcebergDeleteWriter extends HiveIcebergWriterBase {
super(table, newDeleteWriter(table, rewritableDeletes, writerFactory,
deleteFileFactory, context));
this.rowDataTemplate = GenericRecord.create(table.schema());
- this.skipRowData = context.skipRowData();
this.isMergeTask = context.isMergeTask();
}
@@ -62,10 +60,6 @@ public void write(Writable row) throws IOException {
int specId = IcebergAcidUtil.parseSpecId(rec);
PartitionKey partitionKey = isMergeTask ?
IcebergAcidUtil.parsePartitionKey(rec) :
partition(rowDataTemplate, specId);
- if (skipRowData) {
- // Set null as the row data as we intend to avoid writing the actual row
data in the delete file.
- positionDelete.set(positionDelete.path(), positionDelete.pos());
- }
writer.write(positionDelete, specs.get(specId), partitionKey);
}
diff --git
a/iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/hive/writer/WriterBuilder.java
b/iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/hive/writer/WriterBuilder.java
index 20386be3ffe..d92efbb1fa6 100644
---
a/iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/hive/writer/WriterBuilder.java
+++
b/iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/hive/writer/WriterBuilder.java
@@ -79,8 +79,6 @@ public class WriterBuilder {
private static AtomicInteger operationNum = new AtomicInteger(0);
// To specify whether to write the actual row data while writing the delete
files.
- public static final String ICEBERG_DELETE_SKIPROWDATA =
"iceberg.delete.skiprowdata";
- public static final boolean ICEBERG_DELETE_SKIPROWDATA_DEFAULT = true;
private boolean shouldAddRowLineageColumns = false;
private WriterBuilder(Table table, UnaryOperator<String> ops) {
@@ -224,7 +222,6 @@ static class Context {
private final boolean useFanoutWriter;
private final boolean inputOrdered;
private final boolean isMergeTask;
- private final boolean skipRowData;
private final boolean useDVs;
private final Set<String> missingColumns;
@@ -249,9 +246,6 @@ static class Context {
this.deleteGranularity = DeleteGranularity.PARTITION;
this.useDVs = IcebergTableUtil.formatVersion(properties) > 2;
- this.skipRowData = useDVs ||
- PropertyUtil.propertyAsBoolean(properties,
- ICEBERG_DELETE_SKIPROWDATA, ICEBERG_DELETE_SKIPROWDATA_DEFAULT);
this.missingColumns =
Optional.ofNullable(ops.apply(SessionStateUtil.MISSING_COLUMNS))
.map(columns ->
Arrays.stream(columns.split(",")).collect(Collectors.toCollection(HashSet::new)))
@@ -290,10 +284,6 @@ boolean isMergeTask() {
return isMergeTask;
}
- boolean skipRowData() {
- return skipRowData;
- }
-
public boolean useDVs() {
return useDVs;
}
diff --git
a/iceberg/iceberg-handler/src/test/java/org/apache/iceberg/mr/hive/writer/HiveIcebergWriterTestBase.java
b/iceberg/iceberg-handler/src/test/java/org/apache/iceberg/mr/hive/writer/HiveIcebergWriterTestBase.java
index cd912525164..bdb19f1b677 100644
---
a/iceberg/iceberg-handler/src/test/java/org/apache/iceberg/mr/hive/writer/HiveIcebergWriterTestBase.java
+++
b/iceberg/iceberg-handler/src/test/java/org/apache/iceberg/mr/hive/writer/HiveIcebergWriterTestBase.java
@@ -22,7 +22,6 @@
import java.io.File;
import java.io.IOException;
import java.util.Collection;
-import java.util.Collections;
import java.util.List;
import java.util.Set;
import org.apache.hadoop.hive.conf.HiveConf;
@@ -86,24 +85,16 @@ public class HiveIcebergWriterTestBase {
@Parameterized.Parameter(1)
public boolean partitioned;
- @Parameterized.Parameter(2)
- public boolean skipRowData;
-
- @Parameterized.Parameters(name = "fileFormat={0}, partitioned={1},
skipRowData={2}")
+ @Parameterized.Parameters(name = "fileFormat={0}, partitioned={1}")
public static Collection<Object[]> parameters() {
return Lists.newArrayList(new Object[][] {
- { FileFormat.PARQUET, true, true },
- { FileFormat.ORC, true, true },
- { FileFormat.AVRO, true, true },
- { FileFormat.PARQUET, false, true },
- { FileFormat.PARQUET, true, false },
- { FileFormat.ORC, true, false },
- { FileFormat.AVRO, true, false },
- { FileFormat.PARQUET, false, false },
+ { FileFormat.PARQUET, true },
+ { FileFormat.ORC, true },
+ { FileFormat.AVRO, true },
+ { FileFormat.PARQUET, false },
// Skip this until the ORC reader is fixed - test only issue
// { FileFormat.ORC, false },
- { FileFormat.AVRO, false, true },
- { FileFormat.AVRO, false, false }
+ { FileFormat.AVRO, false }
});
}
@@ -116,8 +107,7 @@ public void init() throws IOException {
PartitionSpec.builderFor(SCHEMA)
.bucket("data", 3)
.build();
- this.helper = new TestHelper(new HiveConf(), tables, location.toString(),
SCHEMA, spec, fileFormat,
- Collections.singletonMap(WriterBuilder.ICEBERG_DELETE_SKIPROWDATA,
String.valueOf(skipRowData)), temp);
+ this.helper = new TestHelper(new HiveConf(), tables, location.toString(),
SCHEMA, spec, fileFormat, temp);
this.table = helper.createTable();
helper.appendToTable(RECORDS);
diff --git
a/iceberg/iceberg-handler/src/test/queries/positive/delete_all_iceberg.q
b/iceberg/iceberg-handler/src/test/queries/positive/delete_all_iceberg.q
index 2191604ab03..cf1e859e71b 100644
--- a/iceberg/iceberg-handler/src/test/queries/positive/delete_all_iceberg.q
+++ b/iceberg/iceberg-handler/src/test/queries/positive/delete_all_iceberg.q
@@ -17,7 +17,7 @@
set hive.vectorized.execution.enabled=true;
create table ice01 (id int, key int) Stored by Iceberg stored as ORC
- TBLPROPERTIES('format-version'='2', 'iceberg.delete.skiprowdata'='false');
+ TBLPROPERTIES('format-version'='2');
insert into ice01 values (1,1),(2,1),(3,1),(4,1);
insert into ice01 values (1,2),(2,2),(3,2),(4,2);
diff --git
a/iceberg/iceberg-handler/src/test/queries/positive/iceberg_v2_deletes.q
b/iceberg/iceberg-handler/src/test/queries/positive/iceberg_v2_deletes.q
deleted file mode 100644
index 4c1fb37fb78..00000000000
--- a/iceberg/iceberg-handler/src/test/queries/positive/iceberg_v2_deletes.q
+++ /dev/null
@@ -1,93 +0,0 @@
--- Mask random uuid
---! qt:replace:/(\s+'uuid'=')\S+('\s*)/$1#Masked#$2/
--- Mask a random snapshot id
---! qt:replace:/(\s\'current-snapshot-id\'=\')(\d+)(\')/$1#Masked#$3/
--- Mask added file size
---! qt:replace:/(\S+\"added-files-size\":\")(\d+)(\")/$1#Masked#$3/
--- Mask total file size
---! qt:replace:/(\S+\"total-files-size\":\")(\d+)(\")/$1#Masked#$3/
--- Mask current-snapshot-timestamp-ms
---! qt:replace:/(\s\'current-snapshot-timestamp-ms\'=\')(\d+)(\')/$1#Masked#$3/
--- Mask iceberg version
---!
qt:replace:/("iceberg-version":")(\w+\s\w+\s\d+\.\d+\.\d+\s\(\w+\s\w+\))/$1#Masked#/
-
--- create an unpartitioned table with skip delete data set to false
- create table ice01 (id int) Stored by Iceberg stored as ORC
- TBLPROPERTIES('format-version'='2', 'iceberg.delete.skiprowdata'='false');
-
--- check the property value
-show create table ice01;
-
--- insert some values
-insert into ice01 values (1),(2),(3),(4);
-
--- check the inserted values
-select * from ice01;
-
--- delete some values
-delete from ice01 where id>2;
-
--- check the values, the delete value should be there
-select * from ice01 order by id;
-
--- insert some more data
- insert into ice01 values (5),(6),(7),(8);
-
--- check the values, only the delete value shouldn't be there
-select * from ice01 order by id;
-
--- delete one value
-delete from ice01 where id=7;
-
--- change to skip the row data now
-Alter table ice01 set TBLPROPERTIES('iceberg.delete.skiprowdata'='true');
-
--- check the property value
-show create table ice01;
-
--- delete some more rows now
-delete from ice01 where id=5;
-
--- check the entries, the deleted entries shouldn't be there.
-select * from ice01 order by id;
-
--- create a partitioned table with skip row data set to false
- create table icepart01 (id int) partitioned by (part int) Stored by Iceberg
stored as ORC
- TBLPROPERTIES('format-version'='2', 'iceberg.delete.skiprowdata'='false');
-
--- insert some values
-insert into icepart01 values (1,1),(2,1),(3,2),(4,2);
-
--- check the inserted values
-select * from icepart01 order by id;
-
--- delete some values
-delete from icepart01 where id>=2 AND id<4;
-
--- check the values, the delete value should be there
-select * from icepart01;
-
--- insert some more data
- insert into icepart01 values (5,1),(6,2),(7,1),(8,2);
-
--- check the values, only the delete value shouldn't be there
-select * from icepart01 order by id;
-
--- delete one value
-delete from icepart01 where id=7;
-
--- change to skip the row data now
-Alter table icepart01 set TBLPROPERTIES('iceberg.delete.skiprowdata'='true');
-
--- check the property value
-show create table icepart01;
-
--- delete some more rows now
-delete from icepart01 where id=5;
-
--- check the entries, the deleted entries shouldn't be there.
-select * from icepart01 order by id;
-
--- clean up
-drop table ice01;
-drop table icepart01;
\ No newline at end of file
diff --git
a/iceberg/iceberg-handler/src/test/queries/positive/vectorized_iceberg_merge_mixed.q
b/iceberg/iceberg-handler/src/test/queries/positive/vectorized_iceberg_merge_mixed.q
index 227934e7e7c..b89a8cd1b42 100644
---
a/iceberg/iceberg-handler/src/test/queries/positive/vectorized_iceberg_merge_mixed.q
+++
b/iceberg/iceberg-handler/src/test/queries/positive/vectorized_iceberg_merge_mixed.q
@@ -41,7 +41,7 @@ create table store_sales (
)
partitioned by spec (ss_customer_sk, bucket(3, ss_item_sk))
stored by ICEBERG stored as PARQUET
- TBLPROPERTIES('format-version'='2', 'iceberg.delete.skiprowdata'='true');
+ TBLPROPERTIES('format-version'='2');
insert into store_sales (ss_customer_sk, ss_item_sk, ss_sold_date_sk) values
(1,1501,"2451181"), (2,1502,"2451181"), (3,1503,"2451181"), (4,1504,"2451181"),
(5,1505,"2451181");
delete from store_sales where ss_customer_sk > 2;
diff --git
a/iceberg/iceberg-handler/src/test/results/positive/delete_all_iceberg.q.out
b/iceberg/iceberg-handler/src/test/results/positive/delete_all_iceberg.q.out
index 21b948bae78..ac1195830c0 100644
--- a/iceberg/iceberg-handler/src/test/results/positive/delete_all_iceberg.q.out
+++ b/iceberg/iceberg-handler/src/test/results/positive/delete_all_iceberg.q.out
@@ -1,10 +1,10 @@
PREHOOK: query: create table ice01 (id int, key int) Stored by Iceberg stored
as ORC
- TBLPROPERTIES('format-version'='2', 'iceberg.delete.skiprowdata'='false')
+ TBLPROPERTIES('format-version'='2')
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@ice01
POSTHOOK: query: create table ice01 (id int, key int) Stored by Iceberg stored
as ORC
- TBLPROPERTIES('format-version'='2', 'iceberg.delete.skiprowdata'='false')
+ TBLPROPERTIES('format-version'='2')
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@ice01
@@ -116,7 +116,6 @@ Table Parameters:
current-snapshot-summary
{\"manifests-created\":\"5\",\"manifests-kept\":\"0\",\"manifests-replaced\":\"5\",\"deleted-data-files\":\"5\",\"deleted-records\":\"20\",\"removed-files-size\":\"#Masked#\",\"changed-partition-count\":\"1\",\"total-records\":\"0\",\"total-files-size\":\"#Masked#\",\"total-data-files\":\"0\",\"total-delete-files\":\"0\",\"total-position-deletes\":\"0\",\"total-equality-deletes\":\"0\",\"iceberg-version\":\"#Masked#\"}
current-snapshot-timestamp-ms #Masked#
format-version 2
- iceberg.delete.skiprowdata false
metadata_location hdfs://### HDFS PATH ###
numFiles 0
numRows 0
diff --git
a/iceberg/iceberg-handler/src/test/results/positive/iceberg_v2_deletes.q.out
b/iceberg/iceberg-handler/src/test/results/positive/iceberg_v2_deletes.q.out
deleted file mode 100644
index b9b87dfdb46..00000000000
--- a/iceberg/iceberg-handler/src/test/results/positive/iceberg_v2_deletes.q.out
+++ /dev/null
@@ -1,342 +0,0 @@
-PREHOOK: query: create table ice01 (id int) Stored by Iceberg stored as ORC
- TBLPROPERTIES('format-version'='2', 'iceberg.delete.skiprowdata'='false')
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@ice01
-POSTHOOK: query: create table ice01 (id int) Stored by Iceberg stored as ORC
- TBLPROPERTIES('format-version'='2', 'iceberg.delete.skiprowdata'='false')
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@ice01
-PREHOOK: query: show create table ice01
-PREHOOK: type: SHOW_CREATETABLE
-PREHOOK: Input: default@ice01
-POSTHOOK: query: show create table ice01
-POSTHOOK: type: SHOW_CREATETABLE
-POSTHOOK: Input: default@ice01
-CREATE EXTERNAL TABLE `ice01`(
- `id` int)
-ROW FORMAT SERDE
- 'org.apache.iceberg.mr.hive.HiveIcebergSerDe'
-STORED BY
- 'org.apache.iceberg.mr.hive.HiveIcebergStorageHandler'
-
-LOCATION
- 'hdfs://### HDFS PATH ###'
-TBLPROPERTIES (
- 'bucketing_version'='2',
-
'current-schema'='{"type":"struct","schema-id":0,"fields":[{"id":1,"name":"id","required":false,"type":"int"}]}',
- 'format-version'='2',
- 'iceberg.delete.skiprowdata'='false',
- 'metadata_location'='hdfs://### HDFS PATH ###',
- 'parquet.compression'='zstd',
- 'serialization.format'='1',
- 'snapshot-count'='0',
- 'table_type'='ICEBERG',
-#### A masked pattern was here ####
- 'uuid'='#Masked#',
- 'write.delete.mode'='merge-on-read',
- 'write.format.default'='orc',
- 'write.merge.mode'='merge-on-read',
- 'write.metadata.delete-after-commit.enabled'='true',
- 'write.update.mode'='merge-on-read')
-PREHOOK: query: insert into ice01 values (1),(2),(3),(4)
-PREHOOK: type: QUERY
-PREHOOK: Input: _dummy_database@_dummy_table
-PREHOOK: Output: default@ice01
-POSTHOOK: query: insert into ice01 values (1),(2),(3),(4)
-POSTHOOK: type: QUERY
-POSTHOOK: Input: _dummy_database@_dummy_table
-POSTHOOK: Output: default@ice01
-PREHOOK: query: select * from ice01
-PREHOOK: type: QUERY
-PREHOOK: Input: default@ice01
-PREHOOK: Output: hdfs://### HDFS PATH ###
-POSTHOOK: query: select * from ice01
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@ice01
-POSTHOOK: Output: hdfs://### HDFS PATH ###
-1
-2
-3
-4
-PREHOOK: query: delete from ice01 where id>2
-PREHOOK: type: QUERY
-PREHOOK: Input: default@ice01
-PREHOOK: Output: default@ice01
-POSTHOOK: query: delete from ice01 where id>2
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@ice01
-POSTHOOK: Output: default@ice01
-PREHOOK: query: select * from ice01 order by id
-PREHOOK: type: QUERY
-PREHOOK: Input: default@ice01
-PREHOOK: Output: hdfs://### HDFS PATH ###
-POSTHOOK: query: select * from ice01 order by id
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@ice01
-POSTHOOK: Output: hdfs://### HDFS PATH ###
-1
-2
-PREHOOK: query: insert into ice01 values (5),(6),(7),(8)
-PREHOOK: type: QUERY
-PREHOOK: Input: _dummy_database@_dummy_table
-PREHOOK: Output: default@ice01
-POSTHOOK: query: insert into ice01 values (5),(6),(7),(8)
-POSTHOOK: type: QUERY
-POSTHOOK: Input: _dummy_database@_dummy_table
-POSTHOOK: Output: default@ice01
-PREHOOK: query: select * from ice01 order by id
-PREHOOK: type: QUERY
-PREHOOK: Input: default@ice01
-PREHOOK: Output: hdfs://### HDFS PATH ###
-POSTHOOK: query: select * from ice01 order by id
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@ice01
-POSTHOOK: Output: hdfs://### HDFS PATH ###
-1
-2
-5
-6
-7
-8
-PREHOOK: query: delete from ice01 where id=7
-PREHOOK: type: QUERY
-PREHOOK: Input: default@ice01
-PREHOOK: Output: default@ice01
-POSTHOOK: query: delete from ice01 where id=7
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@ice01
-POSTHOOK: Output: default@ice01
-PREHOOK: query: Alter table ice01 set
TBLPROPERTIES('iceberg.delete.skiprowdata'='true')
-PREHOOK: type: ALTERTABLE_PROPERTIES
-PREHOOK: Input: default@ice01
-PREHOOK: Output: default@ice01
-POSTHOOK: query: Alter table ice01 set
TBLPROPERTIES('iceberg.delete.skiprowdata'='true')
-POSTHOOK: type: ALTERTABLE_PROPERTIES
-POSTHOOK: Input: default@ice01
-POSTHOOK: Output: default@ice01
-PREHOOK: query: show create table ice01
-PREHOOK: type: SHOW_CREATETABLE
-PREHOOK: Input: default@ice01
-POSTHOOK: query: show create table ice01
-POSTHOOK: type: SHOW_CREATETABLE
-POSTHOOK: Input: default@ice01
-CREATE EXTERNAL TABLE `ice01`(
- `id` int)
-ROW FORMAT SERDE
- 'org.apache.iceberg.mr.hive.HiveIcebergSerDe'
-STORED BY
- 'org.apache.iceberg.mr.hive.HiveIcebergStorageHandler'
-
-LOCATION
- 'hdfs://### HDFS PATH ###'
-TBLPROPERTIES (
- 'bucketing_version'='2',
-
'current-schema'='{"type":"struct","schema-id":0,"fields":[{"id":1,"name":"id","required":false,"type":"int"}]}',
- 'current-snapshot-id'='#Masked#',
-
'current-snapshot-summary'='{"manifests-created":"1","manifests-kept":"3","manifests-replaced":"0","added-position-delete-files":"1","added-delete-files":"1","added-files-size":"#Masked#","added-position-deletes":"1","changed-partition-count":"1","total-records":"8","total-files-size":"#Masked#","total-data-files":"2","total-delete-files":"2","total-position-deletes":"3","total-equality-deletes":"0","iceberg-version":"#Masked#"}',
- 'current-snapshot-timestamp-ms'='#Masked#',
- 'format-version'='2',
- 'iceberg.delete.skiprowdata'='true',
-#### A masked pattern was here ####
- 'metadata_location'='hdfs://### HDFS PATH ###',
- 'parquet.compression'='zstd',
- 'previous_metadata_location'='hdfs://### HDFS PATH ###',
- 'serialization.format'='1',
- 'snapshot-count'='4',
- 'table_type'='ICEBERG',
-#### A masked pattern was here ####
- 'uuid'='#Masked#',
- 'write.delete.mode'='merge-on-read',
- 'write.format.default'='orc',
- 'write.merge.mode'='merge-on-read',
- 'write.metadata.delete-after-commit.enabled'='true',
- 'write.update.mode'='merge-on-read')
-PREHOOK: query: delete from ice01 where id=5
-PREHOOK: type: QUERY
-PREHOOK: Input: default@ice01
-PREHOOK: Output: default@ice01
-POSTHOOK: query: delete from ice01 where id=5
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@ice01
-POSTHOOK: Output: default@ice01
-PREHOOK: query: select * from ice01 order by id
-PREHOOK: type: QUERY
-PREHOOK: Input: default@ice01
-PREHOOK: Output: hdfs://### HDFS PATH ###
-POSTHOOK: query: select * from ice01 order by id
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@ice01
-POSTHOOK: Output: hdfs://### HDFS PATH ###
-1
-2
-6
-8
-PREHOOK: query: create table icepart01 (id int) partitioned by (part int)
Stored by Iceberg stored as ORC
- TBLPROPERTIES('format-version'='2', 'iceberg.delete.skiprowdata'='false')
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@icepart01
-POSTHOOK: query: create table icepart01 (id int) partitioned by (part int)
Stored by Iceberg stored as ORC
- TBLPROPERTIES('format-version'='2', 'iceberg.delete.skiprowdata'='false')
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@icepart01
-PREHOOK: query: insert into icepart01 values (1,1),(2,1),(3,2),(4,2)
-PREHOOK: type: QUERY
-PREHOOK: Input: _dummy_database@_dummy_table
-PREHOOK: Output: default@icepart01
-POSTHOOK: query: insert into icepart01 values (1,1),(2,1),(3,2),(4,2)
-POSTHOOK: type: QUERY
-POSTHOOK: Input: _dummy_database@_dummy_table
-POSTHOOK: Output: default@icepart01
-PREHOOK: query: select * from icepart01 order by id
-PREHOOK: type: QUERY
-PREHOOK: Input: default@icepart01
-PREHOOK: Output: hdfs://### HDFS PATH ###
-POSTHOOK: query: select * from icepart01 order by id
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@icepart01
-POSTHOOK: Output: hdfs://### HDFS PATH ###
-1 1
-2 1
-3 2
-4 2
-PREHOOK: query: delete from icepart01 where id>=2 AND id<4
-PREHOOK: type: QUERY
-PREHOOK: Input: default@icepart01
-PREHOOK: Output: default@icepart01
-POSTHOOK: query: delete from icepart01 where id>=2 AND id<4
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@icepart01
-POSTHOOK: Output: default@icepart01
-PREHOOK: query: select * from icepart01
-PREHOOK: type: QUERY
-PREHOOK: Input: default@icepart01
-PREHOOK: Output: hdfs://### HDFS PATH ###
-POSTHOOK: query: select * from icepart01
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@icepart01
-POSTHOOK: Output: hdfs://### HDFS PATH ###
-1 1
-4 2
-PREHOOK: query: insert into icepart01 values (5,1),(6,2),(7,1),(8,2)
-PREHOOK: type: QUERY
-PREHOOK: Input: _dummy_database@_dummy_table
-PREHOOK: Output: default@icepart01
-POSTHOOK: query: insert into icepart01 values (5,1),(6,2),(7,1),(8,2)
-POSTHOOK: type: QUERY
-POSTHOOK: Input: _dummy_database@_dummy_table
-POSTHOOK: Output: default@icepart01
-PREHOOK: query: select * from icepart01 order by id
-PREHOOK: type: QUERY
-PREHOOK: Input: default@icepart01
-PREHOOK: Output: hdfs://### HDFS PATH ###
-POSTHOOK: query: select * from icepart01 order by id
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@icepart01
-POSTHOOK: Output: hdfs://### HDFS PATH ###
-1 1
-4 2
-5 1
-6 2
-7 1
-8 2
-PREHOOK: query: delete from icepart01 where id=7
-PREHOOK: type: QUERY
-PREHOOK: Input: default@icepart01
-PREHOOK: Output: default@icepart01
-POSTHOOK: query: delete from icepart01 where id=7
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@icepart01
-POSTHOOK: Output: default@icepart01
-PREHOOK: query: Alter table icepart01 set
TBLPROPERTIES('iceberg.delete.skiprowdata'='true')
-PREHOOK: type: ALTERTABLE_PROPERTIES
-PREHOOK: Input: default@icepart01
-PREHOOK: Output: default@icepart01
-POSTHOOK: query: Alter table icepart01 set
TBLPROPERTIES('iceberg.delete.skiprowdata'='true')
-POSTHOOK: type: ALTERTABLE_PROPERTIES
-POSTHOOK: Input: default@icepart01
-POSTHOOK: Output: default@icepart01
-PREHOOK: query: show create table icepart01
-PREHOOK: type: SHOW_CREATETABLE
-PREHOOK: Input: default@icepart01
-POSTHOOK: query: show create table icepart01
-POSTHOOK: type: SHOW_CREATETABLE
-POSTHOOK: Input: default@icepart01
-CREATE EXTERNAL TABLE `icepart01`(
- `id` int,
- `part` int)
-PARTITIONED BY SPEC (
-`part`)
-ROW FORMAT SERDE
- 'org.apache.iceberg.mr.hive.HiveIcebergSerDe'
-STORED BY
- 'org.apache.iceberg.mr.hive.HiveIcebergStorageHandler'
-
-LOCATION
- 'hdfs://### HDFS PATH ###'
-TBLPROPERTIES (
- 'bucketing_version'='2',
-
'current-schema'='{"type":"struct","schema-id":0,"fields":[{"id":1,"name":"id","required":false,"type":"int"},{"id":2,"name":"part","required":false,"type":"int"}]}',
- 'current-snapshot-id'='#Masked#',
-
'current-snapshot-summary'='{"manifests-created":"1","manifests-kept":"3","manifests-replaced":"0","added-position-delete-files":"1","added-delete-files":"1","added-files-size":"#Masked#","added-position-deletes":"1","changed-partition-count":"1","total-records":"8","total-files-size":"#Masked#","total-data-files":"4","total-delete-files":"3","total-position-deletes":"3","total-equality-deletes":"0","iceberg-version":"#Masked#"}',
- 'current-snapshot-timestamp-ms'='#Masked#',
-
'default-partition-spec'='{"spec-id":0,"fields":[{"name":"part","transform":"identity","source-id":2,"field-id":1000}]}',
- 'format-version'='2',
- 'iceberg.delete.skiprowdata'='true',
-#### A masked pattern was here ####
- 'metadata_location'='hdfs://### HDFS PATH ###',
- 'parquet.compression'='zstd',
- 'previous_metadata_location'='hdfs://### HDFS PATH ###',
- 'serialization.format'='1',
- 'snapshot-count'='4',
- 'table_type'='ICEBERG',
-#### A masked pattern was here ####
- 'uuid'='#Masked#',
- 'write.delete.mode'='merge-on-read',
- 'write.format.default'='orc',
- 'write.merge.mode'='merge-on-read',
- 'write.metadata.delete-after-commit.enabled'='true',
- 'write.update.mode'='merge-on-read')
-PREHOOK: query: delete from icepart01 where id=5
-PREHOOK: type: QUERY
-PREHOOK: Input: default@icepart01
-PREHOOK: Output: default@icepart01
-POSTHOOK: query: delete from icepart01 where id=5
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@icepart01
-POSTHOOK: Output: default@icepart01
-PREHOOK: query: select * from icepart01 order by id
-PREHOOK: type: QUERY
-PREHOOK: Input: default@icepart01
-PREHOOK: Output: hdfs://### HDFS PATH ###
-POSTHOOK: query: select * from icepart01 order by id
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@icepart01
-POSTHOOK: Output: hdfs://### HDFS PATH ###
-1 1
-4 2
-6 2
-8 2
-PREHOOK: query: drop table ice01
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@ice01
-PREHOOK: Output: database:default
-PREHOOK: Output: default@ice01
-POSTHOOK: query: drop table ice01
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@ice01
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@ice01
-PREHOOK: query: drop table icepart01
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@icepart01
-PREHOOK: Output: database:default
-PREHOOK: Output: default@icepart01
-POSTHOOK: query: drop table icepart01
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@icepart01
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@icepart01
diff --git
a/iceberg/iceberg-handler/src/test/results/positive/vectorized_iceberg_merge_mixed.q.out
b/iceberg/iceberg-handler/src/test/results/positive/vectorized_iceberg_merge_mixed.q.out
index c4c9a0ace26..0629c117cdf 100644
---
a/iceberg/iceberg-handler/src/test/results/positive/vectorized_iceberg_merge_mixed.q.out
+++
b/iceberg/iceberg-handler/src/test/results/positive/vectorized_iceberg_merge_mixed.q.out
@@ -37,7 +37,7 @@ PREHOOK: query: create table store_sales (
)
partitioned by spec (ss_customer_sk, bucket(3, ss_item_sk))
stored by ICEBERG stored as PARQUET
- TBLPROPERTIES('format-version'='2', 'iceberg.delete.skiprowdata'='true')
+ TBLPROPERTIES('format-version'='2')
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@store_sales
@@ -68,7 +68,7 @@ POSTHOOK: query: create table store_sales (
)
partitioned by spec (ss_customer_sk, bucket(3, ss_item_sk))
stored by ICEBERG stored as PARQUET
- TBLPROPERTIES('format-version'='2', 'iceberg.delete.skiprowdata'='true')
+ TBLPROPERTIES('format-version'='2')
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@store_sales
