Skip to content

[core] Add validation to prevent primary key in sequence-group (#7052) #7656

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
dark2momo wants to merge 1 commit into
base: master
Choose a base branch
from
+80 −2
Open

[core] Add validation to prevent primary key in sequence-group (#7052) #7656

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
19 changes: 17 additions & 2 deletions ...on-core/src/main/java/org/apache/paimon/mergetree/compact/PartialUpdateMergeFunction.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -420,20 +420,35 @@ private Factory(Options options, RowType rowType, List<String> primaryKeys) {
.map(fieldName -> requireField(fieldName, fieldNames))
.forEach(
field -> {
String protectedFieldName = fieldNames.get(field);
if (primaryKeys.contains(protectedFieldName)) {
throw new IllegalArgumentException(
String.format(
"The sequence-group '%s' contains primary key field '%s', "
+ "which is not allowed. Primary key columns cannot be put in sequence-group.",
k, protectedFieldName));
}
if (fieldSeqComparators.containsKey(field)) {
throw new IllegalArgumentException(
String.format(
"Field %s is defined repeatedly by multiple groups: %s",
fieldNames.get(field), k));
}
fieldSeqComparators.put(field, userDefinedSeqComparator);
fieldsProtectedBySequenceGroup.add(fieldNames.get(field));
fieldsProtectedBySequenceGroup.add(protectedFieldName);
});

// add self
for (int index : sequenceFields) {
allSequenceFields.add(fieldNames.get(index));
String fieldName = fieldNames.get(index);
if (primaryKeys.contains(fieldName)) {
throw new IllegalArgumentException(
String.format(
"The sequence-group '%s' contains primary key field '%s', "
+ "which is not allowed. Primary key columns cannot be put in sequence-group.",
k, fieldName));
}
allSequenceFields.add(fieldName);
fieldSeqComparators.put(index, userDefinedSeqComparator);
sequenceGroupMap.put(fieldName, index);
}
Expand Down
63 changes: 63 additions & 0 deletions ...ore/src/test/java/org/apache/paimon/mergetree/compact/PartialUpdateMergeFunctionTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -887,6 +887,69 @@ public void testAggregationWithoutSequenceGroup() {
"Must use sequence group for aggregation functions but not found for field f1."));
}

@Test
public void testSequenceGroupCannotContainPrimaryKey() {
// Issue #7052: Putting a primary key column in sequence-group should be forbidden
// as it causes Parquet decoding failures during compaction
Options options = new Options();
options.set("fields.f0.sequence-group", "f1,f2");
RowType rowType =
RowType.of(DataTypes.INT(), DataTypes.INT(), DataTypes.INT(), DataTypes.INT());
assertThatThrownBy(
() ->
PartialUpdateMergeFunction.factory(
options, rowType, ImmutableList.of("f0")))
.hasMessageContaining(
"The sequence-group 'fields.f0.sequence-group' contains primary key field 'f0', "
+ "which is not allowed. Primary key columns cannot be put in sequence-group.");
}

@Test
public void testMultiSequenceFieldsCannotContainPrimaryKey() {
// Issue #7052: Multi-field sequence-group also cannot contain primary key columns
// The sequence fields (f2,f3) are the "self" part, they must not contain PKs
Options options = new Options();
options.set("fields.f2,f3.sequence-group", "f0,f4");
RowType rowType =
RowType.of(
DataTypes.INT(),
DataTypes.INT(),
DataTypes.INT(),
DataTypes.INT(),
DataTypes.INT(),
DataTypes.INT());
assertThatThrownBy(
() ->
PartialUpdateMergeFunction.factory(
options, rowType, ImmutableList.of("f2")))
.hasMessageContaining(
"The sequence-group 'fields.f2,f3.sequence-group' contains primary key field 'f2', "
+ "which is not allowed. Primary key columns cannot be put in sequence-group.");
}

@Test
public void testMultiPrimaryKeyCannotBeInSequenceGroup() {
// Issue #7052: With composite primary keys, none of them can be in sequence-group
// f2 is a PK and appears in the value part of the sequence-group
Options options = new Options();
options.set("fields.f4.sequence-group", "f1,f2");
RowType rowType =
RowType.of(
DataTypes.INT(),
DataTypes.INT(),
DataTypes.INT(),
DataTypes.INT(),
DataTypes.INT(),
DataTypes.INT());
assertThatThrownBy(
() ->
PartialUpdateMergeFunction.factory(
options, rowType, ImmutableList.of("f2")))
.hasMessageContaining(
"The sequence-group 'fields.f4.sequence-group' contains primary key field 'f2', "
+ "which is not allowed. Primary key columns cannot be put in sequence-group.");
}

@Test
public void testDeleteReproduceCorrectSequenceNumber() {
Options options = new Options();
Expand Down
Loading