Skip to content

[core] Reject per level avro format with high precision timestamps #7892

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
JingsongLi merged 1 commit into from
May 19, 2026
+70 −0
Merged

[core] Reject per level avro format with high precision timestamps #7892

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
29 changes: 29 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 @@ -186,6 +186,35 @@ public static void validateTableSchema(TableSchema schema) {
}
fileFormat.validateDataFields(new RowType(fieldsInNormalFile));

for (Map.Entry<Integer, String> entry : options.fileFormatPerLevel().entrySet()) {
if (!"avro".equalsIgnoreCase(entry.getValue())) {
continue;
}
for (DataField field : fieldsInNormalFile) {
DataType type = field.type();
int precision = -1;
if (type instanceof TimestampType) {
precision = ((TimestampType) type).getPrecision();
} else if (type instanceof LocalZonedTimestampType) {
precision = ((LocalZonedTimestampType) type).getPrecision();
}
if (precision > 6) {
throw new IllegalArgumentException(
String.format(
"'%s' entry '%d:avro' is incompatible with column '%s' of type %s: "
+ "Avro supports timestamp precision up to 6, got %d. "
+ "Either lower the column precision, drop the per-level mapping for level %d, "
+ "or use a different format (parquet or orc) for that level.",
CoreOptions.FILE_FORMAT_PER_LEVEL.key(),
entry.getKey(),
field.name(),
type,
precision,
entry.getKey()));
}
}
}

// Check column names in schema
schema.fieldNames()
.forEach(
Expand Down
41 changes: 41 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 @@ -444,4 +444,45 @@ private void validateTableSchemaWithMapField(Map<String, String> options) {
validateTableSchema(
new TableSchema(1, fields, 10, emptyList(), singletonList("f1"), options, ""));
}

@Test
public void testFileFormatPerLevelRejectsIncompatibleSchema() {
List<DataField> fields =
Arrays.asList(
new DataField(0, "k", DataTypes.INT()),
new DataField(1, "v", DataTypes.TIMESTAMP(9)));
Map<String, String> options = new HashMap<>();
options.put(BUCKET.key(), String.valueOf(-1));
options.put(CoreOptions.FILE_FORMAT_PER_LEVEL.key(), "0:avro");

assertThatThrownBy(
() ->
validateTableSchema(
new TableSchema(
1,
fields,
10,
emptyList(),
singletonList("k"),
options,
"")))
.isInstanceOf(IllegalArgumentException.class)
.hasMessageContaining("file.format.per.level")
.hasMessageContaining("0:avro")
.hasMessageContaining("TIMESTAMP");
}

@Test
public void testFileFormatPerLevelAcceptsCompatibleSchema() {
List<DataField> fields =
Arrays.asList(
new DataField(0, "k", DataTypes.INT()),
new DataField(1, "v", DataTypes.TIMESTAMP(9)));
Map<String, String> options = new HashMap<>();
options.put(BUCKET.key(), String.valueOf(-1));
options.put(CoreOptions.FILE_FORMAT_PER_LEVEL.key(), "0:parquet");

validateTableSchema(
new TableSchema(1, fields, 10, emptyList(), singletonList("k"), options, ""));
}
}