Skip to content

Fix inconsistent data type in GenericRecord and AvroSchema for AvroWriter #36839

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
Abacn merged 2 commits into from
Nov 18, 2025
Merged

Fix inconsistent data type in GenericRecord and AvroSchema for AvroWriter #36839

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3060350
Fix inconsist data type in GenericRecord and AvroSchema for AvroWriter
Abacn Nov 17, 2025
58b3c00
clean code
Abacn Nov 18, 2025
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
16 changes: 16 additions & 0 deletions ...sions/avro/src/main/java/org/apache/beam/sdk/extensions/avro/schemas/utils/AvroUtils.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,7 @@
import java.util.Objects;
import java.util.UUID;
import java.util.concurrent.TimeUnit;
import java.util.function.Function;
import java.util.stream.Collectors;
import javax.annotation.Nonnull;
import net.bytebuddy.description.type.TypeDescription.ForLoadedType;
Expand Down Expand Up @@ -97,6 +98,7 @@
import org.apache.beam.sdk.values.Row;
import org.apache.beam.sdk.values.TypeDescriptor;
import org.apache.beam.vendor.guava.v32_1_2_jre.com.google.common.base.CaseFormat;
import org.apache.beam.vendor.guava.v32_1_2_jre.com.google.common.collect.ImmutableMap;
import org.apache.beam.vendor.guava.v32_1_2_jre.com.google.common.collect.Iterables;
import org.apache.beam.vendor.guava.v32_1_2_jre.com.google.common.collect.Lists;
import org.apache.beam.vendor.guava.v32_1_2_jre.com.google.common.collect.Maps;
Expand Down Expand Up @@ -1214,6 +1216,15 @@ private static org.apache.avro.Schema getFieldSchema(
return fieldType.getNullable() ? ReflectData.makeNullable(baseType) : baseType;
}

private static final Map<org.apache.avro.Schema, Function<Number, ? extends Number>>
NUMERIC_CONVERTERS =
ImmutableMap.of(
org.apache.avro.Schema.create(Type.INT), Number::intValue,
org.apache.avro.Schema.create(Type.LONG), Number::longValue,
org.apache.avro.Schema.create(Type.FLOAT), Number::floatValue,
org.apache.avro.Schema.create(Type.DOUBLE), Number::doubleValue);

/** Convert a value from Beam Row to a vlue used for Avro GenericRecord. */
private static @Nullable Object genericFromBeamField(
FieldType fieldType, org.apache.avro.Schema avroSchema, @Nullable Object value) {
TypeWithNullability typeWithNullability = new TypeWithNullability(avroSchema);
Expand All @@ -1230,6 +1241,11 @@ private static org.apache.avro.Schema getFieldSchema(
return value;
}

if (NUMERIC_CONVERTERS.containsKey(typeWithNullability.type)) {
return NUMERIC_CONVERTERS.get(typeWithNullability.type).apply((Number) value);
}

// TODO: should we use Avro Schema as the source-of-truth in general?
switch (fieldType.getTypeName()) {
case BYTE:
case INT16:
Expand Down
2 changes: 1 addition & 1 deletion ...main/java/org/apache/beam/sdk/io/gcp/bigquery/providers/PortableBigQueryDestinations.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -122,7 +122,7 @@ public SerializableFunction<AvroWriteRequest<Row>, GenericRecord> getAvroFilterF
row = checkStateNotNull(row.getRow(RECORD));
}
Row filtered = rowFilter.filter(row);
return AvroUtils.toGenericRecord(filtered);
return AvroUtils.toGenericRecord(filtered, request.getSchema());
};
}
}
23 changes: 19 additions & 4 deletions ...ache/beam/sdk/io/gcp/bigquery/providers/BigQueryFileLoadsSchemaTransformProviderTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -70,13 +70,28 @@ public class BigQueryFileLoadsSchemaTransformProviderTest {
new TableReference().setProjectId(PROJECT).setDatasetId(DATASET).setTableId(TABLE_ID);

private static final Schema SCHEMA =
Schema.of(Field.of("name", FieldType.STRING), Field.of("number", FieldType.INT64));
Schema.of(
Field.of("name", FieldType.STRING),
Field.of("number", FieldType.INT64),
Field.of("age", FieldType.INT32).withNullable(true));

private static final List<Row> ROWS =
Arrays.asList(
Row.withSchema(SCHEMA).withFieldValue("name", "a").withFieldValue("number", 1L).build(),
Row.withSchema(SCHEMA).withFieldValue("name", "b").withFieldValue("number", 2L).build(),
Row.withSchema(SCHEMA).withFieldValue("name", "c").withFieldValue("number", 3L).build());
Row.withSchema(SCHEMA)
.withFieldValue("name", "a")
.withFieldValue("number", 1L)
.withFieldValue("age", 10)
.build(),
Row.withSchema(SCHEMA)
.withFieldValue("name", "b")
.withFieldValue("number", 2L)
.withFieldValue("age", 20)
.build(),
Row.withSchema(SCHEMA)
.withFieldValue("name", "c")
.withFieldValue("number", 3L)
.withFieldValue("age", null)
.build());

private static final BigQueryOptions OPTIONS =
TestPipeline.testingPipelineOptions().as(BigQueryOptions.class);
Expand Down
Loading