Skip to content

[core] Reject dot-paths in fields.* options on row columns #7757

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
ArnavBalyan wants to merge 1 commit into
base: master
Choose a base branch
from
+47 −1
Open

[core] Reject dot-paths in fields.* options on row columns #7757

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
20 changes: 19 additions & 1 deletion paimon-core/src/main/java/org/apache/paimon/schema/SchemaValidation.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -487,7 +487,8 @@ private static void validateFieldsPrefix(TableSchema schema, CoreOptions options
.forEach(
k -> {
if (k.startsWith(FIELDS_PREFIX)) {
String[] fields = k.split("\\.")[1].split(FIELDS_SEPARATOR);
String[] segments = k.split("\\.");
String[] fields = segments[1].split(FIELDS_SEPARATOR);
for (String field : fields) {
checkArgument(
DEFAULT_AGG_FUNCTION.equals(field)
Expand All @@ -496,6 +497,23 @@ private static void validateFieldsPrefix(TableSchema schema, CoreOptions options
"Field %s can not be found in table schema.",
field));
}
// PAIMON-6471: dot paths into a ROW field's members
// (e.g. fields.row.inner.aggregate-function) are silently
// dropped today and produce wrong results. This check
// rejects them.
if (segments.length > 3 && fields.length == 1) {
String parent = fields[0];
schema.fields().stream()
.filter(f -> f.name().equals(parent))
.findFirst()
.ifPresent(
f ->
checkArgument(
!(f.type() instanceof RowType),
"Nested-field path is not supported on ROW field '%s': %s",
parent,
k));
}
}
});
}
Expand Down
28 changes: 28 additions & 0 deletions paimon-core/src/test/java/org/apache/paimon/schema/SchemaValidationTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -180,6 +180,34 @@ public void testPartialUpdateTableAggregateFunctionWithoutSequenceGroup() {
assertThatCode(() -> validateTableSchemaExec(options)).doesNotThrowAnyException();
}

@Test
public void testNestedRowAggregateOptionRejected() {
// PAIMON-6471: nested-path agg config was silently ignored, leaving the parent ROW
// on the default aggregator and producing wrong results without any error.
List<DataField> fields =
Arrays.asList(
new DataField(0, "id", DataTypes.INT()),
new DataField(
1,
"data",
DataTypes.ROW(
DataTypes.FIELD(2, "num", DataTypes.INT()),
DataTypes.FIELD(3, "info", DataTypes.STRING()))));

Map<String, String> options = new HashMap<>();
options.put("merge-engine", "aggregation");
options.put("fields.data.num.aggregate-function", "sum");
options.put("fields.data.sequence-group", "data");
options.put(BUCKET.key(), "1");

TableSchema schema =
new TableSchema(1, fields, 10, emptyList(), singletonList("id"), options, "");

assertThatThrownBy(() -> validateTableSchema(schema))
.hasMessageContaining("Nested-field path is not supported on ROW field 'data'")
.hasMessageContaining("fields.data.num.aggregate-function");
}

@Test
public void testChainTableAllowsNonDeduplicateMergeEngine() {
Map<String, String> options = new HashMap<>();
Expand Down