This is an automated email from the ASF dual-hosted git repository.
ayushsaxena 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 8d711b3fa45 HIVE-29540: Iceberg: [V3] Support filtering with ROW
LINEAGE columns (#6403)
8d711b3fa45 is described below
commit 8d711b3fa4501fc8ca7e021da9577f89adf93aa7
Author: Ayush Saxena <[email protected]>
AuthorDate: Fri Apr 3 02:46:17 2026 +0530
HIVE-29540: Iceberg: [V3] Support filtering with ROW LINEAGE columns (#6403)
---
.../iceberg/mr/hive/HiveIcebergStorageHandler.java | 7 +++-
.../src/test/queries/positive/row_lineage.q | 7 ++++
.../src/test/results/positive/row_lineage.q.out | 48 ++++++++++++++++++++++
3 files changed, 60 insertions(+), 2 deletions(-)
diff --git
a/iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/hive/HiveIcebergStorageHandler.java
b/iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/hive/HiveIcebergStorageHandler.java
index 042ffbba192..1c48407bf68 100644
---
a/iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/hive/HiveIcebergStorageHandler.java
+++
b/iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/hive/HiveIcebergStorageHandler.java
@@ -210,9 +210,11 @@
import org.slf4j.LoggerFactory;
import static org.apache.hadoop.hive.ql.metadata.VirtualColumn.FILE_PATH;
+import static
org.apache.hadoop.hive.ql.metadata.VirtualColumn.LAST_UPDATED_SEQUENCE_NUMBER;
import static org.apache.hadoop.hive.ql.metadata.VirtualColumn.PARTITION_HASH;
import static
org.apache.hadoop.hive.ql.metadata.VirtualColumn.PARTITION_PROJECTION;
import static
org.apache.hadoop.hive.ql.metadata.VirtualColumn.PARTITION_SPEC_ID;
+import static org.apache.hadoop.hive.ql.metadata.VirtualColumn.ROW_LINEAGE_ID;
import static org.apache.hadoop.hive.ql.metadata.VirtualColumn.ROW_POSITION;
import static org.apache.iceberg.SnapshotSummary.ADDED_RECORDS_PROP;
import static org.apache.iceberg.SnapshotSummary.DELETED_RECORDS_PROP;
@@ -392,8 +394,9 @@ public DecomposedPredicate decomposePredicate(JobConf
jobConf, Deserializer dese
ExprNodeDesc pushedPredicate = exprNodeDesc.clone();
List<ExprNodeDesc> subExprNodes = pushedPredicate.getChildren();
- Set<String> skipList = Stream.of(FILE_PATH, PARTITION_SPEC_ID,
PARTITION_HASH)
- .map(VirtualColumn::getName).collect(Collectors.toSet());
+ Set<String> skipList =
+ Stream.of(FILE_PATH, PARTITION_SPEC_ID, PARTITION_HASH,
ROW_LINEAGE_ID, LAST_UPDATED_SEQUENCE_NUMBER)
+ .map(VirtualColumn::getName).collect(Collectors.toSet());
if (subExprNodes.removeIf(nodeDesc -> nodeDesc.getCols() != null &&
nodeDesc.getCols().stream().anyMatch(skipList::contains))) {
diff --git a/iceberg/iceberg-handler/src/test/queries/positive/row_lineage.q
b/iceberg/iceberg-handler/src/test/queries/positive/row_lineage.q
index 446feb11041..8e44b8a5ef6 100644
--- a/iceberg/iceberg-handler/src/test/queries/positive/row_lineage.q
+++ b/iceberg/iceberg-handler/src/test/queries/positive/row_lineage.q
@@ -6,6 +6,13 @@ update ice_t set balance = 500 where id = 2;
select id, name, balance, ROW__LINEAGE__ID, LAST__UPDATED__SEQUENCE__NUMBER
from ice_t order by id;
+-- Test filtering with row lineage columns
+select id, name, ROW__LINEAGE__ID, LAST__UPDATED__SEQUENCE__NUMBER from ice_t
where ROW__LINEAGE__ID = 1;
+select id, name, balance, ROW__LINEAGE__ID, LAST__UPDATED__SEQUENCE__NUMBER
from ice_t where LAST__UPDATED__SEQUENCE__NUMBER = 1;
+select *, ROW__LINEAGE__ID, LAST__UPDATED__SEQUENCE__NUMBER from ice_t where
LAST__UPDATED__SEQUENCE__NUMBER = 2 OR ROW__LINEAGE__ID = 1;
+delete from ice_t where ROW__LINEAGE__ID = 1 OR
LAST__UPDATED__SEQUENCE__NUMBER = 2;
+select id, name, balance, ROW__LINEAGE__ID, LAST__UPDATED__SEQUENCE__NUMBER
from ice_t order by id;
+
-- copy-on-write
create table ice_t_cow (id int, name string, balance int) stored by iceberg
TBLPROPERTIES ('format-version'='3', 'write.update.mode'='copy-on-write');
insert into ice_t_cow values (1, 'aaa', 25),(2, 'bbb', 35),(3, 'ccc', 82),(4,
'ddd', 91);
diff --git
a/iceberg/iceberg-handler/src/test/results/positive/row_lineage.q.out
b/iceberg/iceberg-handler/src/test/results/positive/row_lineage.q.out
index 4350e994417..046576fa9bf 100644
--- a/iceberg/iceberg-handler/src/test/results/positive/row_lineage.q.out
+++ b/iceberg/iceberg-handler/src/test/results/positive/row_lineage.q.out
@@ -48,6 +48,54 @@ POSTHOOK: Output: hdfs://### HDFS PATH ###
2 bbb 500 1 2
3 ccc 82 2 1
4 ddd 91 3 1
+PREHOOK: query: select id, name, ROW__LINEAGE__ID,
LAST__UPDATED__SEQUENCE__NUMBER from ice_t where ROW__LINEAGE__ID = 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@ice_t
+PREHOOK: Output: hdfs://### HDFS PATH ###
+POSTHOOK: query: select id, name, ROW__LINEAGE__ID,
LAST__UPDATED__SEQUENCE__NUMBER from ice_t where ROW__LINEAGE__ID = 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@ice_t
+POSTHOOK: Output: hdfs://### HDFS PATH ###
+2 bbb 1 2
+PREHOOK: query: select id, name, balance, ROW__LINEAGE__ID,
LAST__UPDATED__SEQUENCE__NUMBER from ice_t where
LAST__UPDATED__SEQUENCE__NUMBER = 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@ice_t
+PREHOOK: Output: hdfs://### HDFS PATH ###
+POSTHOOK: query: select id, name, balance, ROW__LINEAGE__ID,
LAST__UPDATED__SEQUENCE__NUMBER from ice_t where
LAST__UPDATED__SEQUENCE__NUMBER = 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@ice_t
+POSTHOOK: Output: hdfs://### HDFS PATH ###
+1 aaa 25 0 1
+3 ccc 82 2 1
+4 ddd 91 3 1
+PREHOOK: query: select *, ROW__LINEAGE__ID, LAST__UPDATED__SEQUENCE__NUMBER
from ice_t where LAST__UPDATED__SEQUENCE__NUMBER = 2 OR ROW__LINEAGE__ID = 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@ice_t
+PREHOOK: Output: hdfs://### HDFS PATH ###
+POSTHOOK: query: select *, ROW__LINEAGE__ID, LAST__UPDATED__SEQUENCE__NUMBER
from ice_t where LAST__UPDATED__SEQUENCE__NUMBER = 2 OR ROW__LINEAGE__ID = 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@ice_t
+POSTHOOK: Output: hdfs://### HDFS PATH ###
+2 bbb 500 1 2
+PREHOOK: query: delete from ice_t where ROW__LINEAGE__ID = 1 OR
LAST__UPDATED__SEQUENCE__NUMBER = 2
+PREHOOK: type: QUERY
+PREHOOK: Input: default@ice_t
+PREHOOK: Output: default@ice_t
+POSTHOOK: query: delete from ice_t where ROW__LINEAGE__ID = 1 OR
LAST__UPDATED__SEQUENCE__NUMBER = 2
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@ice_t
+POSTHOOK: Output: default@ice_t
+PREHOOK: query: select id, name, balance, ROW__LINEAGE__ID,
LAST__UPDATED__SEQUENCE__NUMBER from ice_t order by id
+PREHOOK: type: QUERY
+PREHOOK: Input: default@ice_t
+PREHOOK: Output: hdfs://### HDFS PATH ###
+POSTHOOK: query: select id, name, balance, ROW__LINEAGE__ID,
LAST__UPDATED__SEQUENCE__NUMBER from ice_t order by id
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@ice_t
+POSTHOOK: Output: hdfs://### HDFS PATH ###
+1 aaa 25 0 1
+3 ccc 82 2 1
+4 ddd 91 3 1
PREHOOK: query: create table ice_t_cow (id int, name string, balance int)
stored by iceberg TBLPROPERTIES ('format-version'='3',
'write.update.mode'='copy-on-write')
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
