Skip to content

[Iceberg] Fix querying data_sequence_number with equality deletes #25293

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

Merged
hantangwangd merged 1 commit into from
Jun 15, 2025
Merged

[Iceberg] Fix querying data_sequence_number with equality deletes #25293

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
7 changes: 4 additions & 3 deletions ...berg/src/main/java/com/facebook/presto/iceberg/optimizer/IcebergEqualityDeleteAsJoin.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -266,9 +266,10 @@ public PlanNode visitTableScan(TableScanNode node, RewriteContext<Void> context)
new SpecialFormExpression(SpecialFormExpression.Form.IS_NULL, BooleanType.BOOLEAN,
new SpecialFormExpression(SpecialFormExpression.Form.COALESCE, BigintType.BIGINT, deleteVersionColumns)));

boolean hasExplicitDataSequenceNumberCol = node.getAssignments().containsValue(DATA_SEQUENCE_NUMBER_COLUMN_HANDLE);
Assignments.Builder assignmentsBuilder = Assignments.builder();
filter.getOutputVariables().stream()
.filter(variableReferenceExpression -> !variableReferenceExpression.getName().startsWith(DATA_SEQUENCE_NUMBER_COLUMN_HANDLE.getName()))
.filter(variableReferenceExpression -> hasExplicitDataSequenceNumberCol || !variableReferenceExpression.getName().startsWith(DATA_SEQUENCE_NUMBER_COLUMN_HANDLE.getName()))
.forEach(variableReferenceExpression -> assignmentsBuilder.put(variableReferenceExpression, variableReferenceExpression));
return new ProjectNode(Optional.empty(), idAllocator.getNextId(), filter, assignmentsBuilder.build(), ProjectNode.Locality.LOCAL);
}
Expand Down Expand Up @@ -368,12 +369,12 @@ private TableScanNode createNewRoot(TableScanNode node, IcebergTableHandle icebe

VariableReferenceExpression dataSequenceNumberVariableReference = toVariableReference(DATA_SEQUENCE_NUMBER_COLUMN_HANDLE);
ImmutableMap.Builder<VariableReferenceExpression, ColumnHandle> assignmentsBuilder = ImmutableMap.<VariableReferenceExpression, ColumnHandle>builder()
.put(dataSequenceNumberVariableReference, DATA_SEQUENCE_NUMBER_COLUMN_HANDLE)
.putAll(unselectedAssignments)
.putAll(node.getAssignments());
ImmutableList.Builder<VariableReferenceExpression> outputsBuilder = ImmutableList.builder();
outputsBuilder.addAll(node.getOutputVariables());
if (!node.getAssignments().containsKey(dataSequenceNumberVariableReference)) {
if (!node.getAssignments().containsValue(DATA_SEQUENCE_NUMBER_COLUMN_HANDLE)) {
assignmentsBuilder.put(dataSequenceNumberVariableReference, DATA_SEQUENCE_NUMBER_COLUMN_HANDLE);
outputsBuilder.add(dataSequenceNumberVariableReference);
}
outputsBuilder.addAll(unselectedAssignments.keySet());
Expand Down
30 changes: 30 additions & 0 deletions presto-iceberg/src/test/java/com/facebook/presto/iceberg/IcebergDistributedTestBase.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1423,6 +1423,36 @@ public void testEqualityDeletesWithHiddenPartitionsEvolution(String fileFormat,
assertQuery(session, "SELECT * FROM " + tableName, "VALUES (1, '1001', NULL, NULL), (3, '1003', NULL, NULL), (6, '1004', 1, NULL), (6, '1006', 2, 'th002')");
}

@Test(dataProvider = "equalityDeleteOptions")
public void testEqualityDeletesWithDataSequenceNumber(String fileFormat, boolean joinRewriteEnabled)
throws Exception
{
Session session = deleteAsJoinEnabled(joinRewriteEnabled);
String tableName = "test_v2_row_delete_" + randomTableSuffix();
String tableName2 = "test_v2_row_delete_2_" + randomTableSuffix();
assertUpdate("CREATE TABLE " + tableName + "(id int, data varchar) WITH (\"write.format.default\" = '" + fileFormat + "')");
assertUpdate("INSERT INTO " + tableName + " VALUES (1, 'a')", 1);

assertUpdate("CREATE TABLE " + tableName2 + "(id int, data varchar) WITH (\"write.format.default\" = '" + fileFormat + "')");
assertUpdate("INSERT INTO " + tableName2 + " VALUES (1, 'a')", 1);

Table icebergTable = updateTable(tableName);
writeEqualityDeleteToNationTable(icebergTable, ImmutableMap.of("id", 1));

Table icebergTable2 = updateTable(tableName2);
writeEqualityDeleteToNationTable(icebergTable2, ImmutableMap.of("id", 1));

assertUpdate("INSERT INTO " + tableName + " VALUES (1, 'b'), (2, 'a'), (3, 'a')", 3);
assertUpdate("INSERT INTO " + tableName2 + " VALUES (1, 'b'), (2, 'a'), (3, 'a')", 3);

assertQuery(session, "SELECT * FROM " + tableName, "VALUES (1, 'b'), (2, 'a'), (3, 'a')");

assertQuery(session, "SELECT \"$data_sequence_number\", * FROM " + tableName, "VALUES (3, 1, 'b'), (3, 2, 'a'), (3, 3, 'a')");

assertQuery(session, "SELECT a.\"$data_sequence_number\", b.\"$data_sequence_number\" from " + tableName + " as a, " + tableName2 + " as b where a.id = b.id",
"VALUES (3, 3), (3, 3), (3, 3)");
}

@Test
public void testPartShowStatsWithFilters()
{
Expand Down
Loading