Skip to content

[core] Validate the changelog format's type limits at DDL time #10262

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
LuciferYang wants to merge 1 commit into
base: master
Choose a base branch
from
+45 −0
Open

[core] Validate the changelog format's type limits at DDL time #10262

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
11 changes: 11 additions & 0 deletions 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 @@ -101,6 +101,7 @@
import static org.apache.paimon.CoreOptions.SNAPSHOT_NUM_RETAINED_MAX;
import static org.apache.paimon.CoreOptions.SNAPSHOT_NUM_RETAINED_MIN;
import static org.apache.paimon.CoreOptions.STREAMING_READ_OVERWRITE;
import static org.apache.paimon.CoreOptions.normalizeFileFormat;
import static org.apache.paimon.format.FileFormat.vectorFileFormat;
import static org.apache.paimon.mergetree.compact.PartialUpdateMergeFunction.isSequenceGroupOption;
import static org.apache.paimon.mergetree.compact.PartialUpdateMergeFunction.isSequenceGroupOptionCandidate;
Expand Down Expand Up @@ -277,6 +278,16 @@ public static void validateTableSchema(TableSchema schema, Set<String> dynamicOp
}
fileFormat.validateDataFields(new RowType(fieldsInNormalFile));

// changelog files are written with the changelog format, whose type limits can
// differ from the data format's
String changelogFormatIdentifier = normalizeFileFormat(options.changelogFileFormat());
if (changelogFormatIdentifier != null
&& !changelogFormatIdentifier.equalsIgnoreCase(
normalizeFileFormat(options.formatType()))) {
FileFormat.fromIdentifier(changelogFormatIdentifier, new Options(schema.options()))
.validateDataFields(new RowType(fieldsInNormalFile));
}

for (Map.Entry<Integer, String> entry : options.fileFormatPerLevel().entrySet()) {
if (!"avro".equalsIgnoreCase(entry.getValue())) {
continue;
Expand Down
34 changes: 34 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 @@ -74,6 +74,40 @@ void testNullablePrimaryKeyRequiresPrimaryKeyTable() {
"Option 'primary-key.nullable' can only be enabled for a table with primary keys.");
}

@Test
public void testChangelogFileFormatRejectsUnsupportedTypes() {
// the changelog format writes the same fields: Avro's type limits apply at DDL
// time instead of crashing the first changelog write
Map<String, String> options = new HashMap<>();
options.put(CoreOptions.CHANGELOG_FILE_FORMAT.key(), "avro");
options.put(BUCKET.key(), String.valueOf(-1));
TableSchema schema =
new TableSchema(
1,
singletonList(new DataField(0, "f0", DataTypes.TIMESTAMP(9))),
10,
emptyList(),
emptyList(),
options,
"");
assertThatThrownBy(() -> validateTableSchema(schema))
.hasMessageContaining("Avro does not support TIMESTAMP type with precision: 9");

// both formats hold the type and stay accepted, exercising the differing-format
// validation path
options.put(CoreOptions.FILE_FORMAT.key(), "parquet");
options.put(CoreOptions.CHANGELOG_FILE_FORMAT.key(), "orc");
validateTableSchema(
new TableSchema(
1,
singletonList(new DataField(0, "f0", DataTypes.TIMESTAMP(9))),
10,
emptyList(),
emptyList(),
options,
""));
}

private void validateTableSchemaExec(Map<String, String> options) {
List<DataField> fields =
Arrays.asList(
Expand Down
Loading