[HUDI-3549] Removing dependency on "spark-avro" (#4955)
Hudi will be taking on promise for it bundles to stay compatible with Spark minor versions (for ex 2.4, 3.1, 3.2): meaning that single build of Hudi (for ex "hudi-spark3.2-bundle") will be compatible with ALL patch versions in that minor branch (in that case 3.2.1, 3.2.0, etc) To achieve that we'll have to remove (and ban) "spark-avro" as a dependency, which on a few occasions was the root-cause of incompatibility b/w consecutive Spark patch versions (most recently 3.2.1 and 3.2.0, due to this PR). Instead of bundling "spark-avro" as dependency, we will be copying over some of the classes Hudi depends on and maintain them along the Hudi code-base to make sure we're able to provide for the aforementioned guarantee. To workaround arising compatibility issues we will be applying local patches to guarantee compatibility of Hudi bundles w/in the Spark minor version branches. Following Hudi modules to Spark minor branches is currently maintained: "hudi-spark3" -> 3.2.x "hudi-spark3.1.x" -> 3.1.x "hudi-spark2" -> 2.4.x Following classes hierarchies (borrowed from "spark-avro") are maintained w/in these Spark-specific modules to guarantee compatibility with respective minor version branches: AvroSerializer AvroDeserializer AvroUtils Each of these classes has been correspondingly copied from Spark 3.2.1 (for 3.2.x branch), 3.1.2 (for 3.1.x branch), 2.4.4 (for 2.4.x branch) into their respective modules. SchemaConverters class in turn is shared across all those modules given its relative stability (there're only cosmetical changes from 2.4.4 to 3.2.1). All of the aforementioned classes have their corresponding scope of visibility limited to corresponding packages (org.apache.spark.sql.avro, org.apache.spark.sql) to make sure broader code-base does not become dependent on them and instead relies on facades abstracting them. Additionally, given that Hudi plans on supporting all the patch versions of Spark w/in aforementioned minor versions branches of Spark, additional build steps were added to validate that Hudi could be properly compiled against those versions. Testing, however, is performed against the most recent patch versions of Spark with the help of Azure CI. Brief change log: - Removing spark-avro bundling from Hudi by default - Scaffolded Spark 3.2.x hierarchy - Bootstrapped Spark 3.1.x Avro serializer/deserializer hierarchy - Bootstrapped Spark 2.4.x Avro serializer/deserializer hierarchy - Moved ExpressionCodeGen,ExpressionPayload into hudi-spark module - Fixed AvroDeserializer to stay compatible w/ both Spark 3.2.1 and 3.2.0 - Modified bot.yml to build full matrix of support Spark versions - Removed "spark-avro" dependency from all modules - Fixed relocation of spark-avro classes in bundles to assist in running integ-tests.
This commit is contained in:
Alexey Kudinkin
@@ -1,67 +0,0 @@
|
||||
/*
|
||||
* Licensed to the Apache Software Foundation (ASF) under one
|
||||
* or more contributor license agreements. See the NOTICE file
|
||||
* distributed with this work for additional information
|
||||
* regarding copyright ownership. The ASF licenses this file
|
||||
* to you under the Apache License, Version 2.0 (the
|
||||
* "License"); you may not use this file except in compliance
|
||||
* with the License. You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.hudi.index.bucket;
|
||||
|
||||
import org.apache.hudi.common.model.HoodieAvroRecord;
|
||||
import org.apache.hudi.common.model.HoodieKey;
|
||||
import org.apache.hudi.common.model.HoodieRecord;
|
||||
import org.apache.hudi.keygen.KeyGenUtils;
|
||||
import org.apache.hudi.testutils.KeyGeneratorTestUtilities;
|
||||
|
||||
import org.apache.avro.generic.GenericRecord;
|
||||
import org.junit.jupiter.api.Test;
|
||||
|
||||
import java.util.Arrays;
|
||||
import java.util.List;
|
||||
|
||||
public class TestBucketIdentifier {
|
||||
|
||||
@Test
|
||||
public void testBucketFileId() {
|
||||
for (int i = 0; i < 1000; i++) {
|
||||
String bucketId = BucketIdentifier.bucketIdStr(i);
|
||||
String fileId = BucketIdentifier.newBucketFileIdPrefix(bucketId);
|
||||
assert BucketIdentifier.bucketIdFromFileId(fileId) == i;
|
||||
}
|
||||
}
|
||||
|
||||
@Test
|
||||
public void testBucketIdWithSimpleRecordKey() {
|
||||
String recordKeyField = "_row_key";
|
||||
String indexKeyField = "_row_key";
|
||||
GenericRecord record = KeyGeneratorTestUtilities.getRecord();
|
||||
HoodieRecord hoodieRecord = new HoodieAvroRecord(
|
||||
new HoodieKey(KeyGenUtils.getRecordKey(record, recordKeyField, false), ""), null);
|
||||
int bucketId = BucketIdentifier.getBucketId(hoodieRecord, indexKeyField, 8);
|
||||
assert bucketId == BucketIdentifier.getBucketId(
|
||||
Arrays.asList(record.get(indexKeyField).toString()), 8);
|
||||
}
|
||||
|
||||
@Test
|
||||
public void testBucketIdWithComplexRecordKey() {
|
||||
List<String> recordKeyField = Arrays.asList("_row_key","ts_ms");
|
||||
String indexKeyField = "_row_key";
|
||||
GenericRecord record = KeyGeneratorTestUtilities.getRecord();
|
||||
HoodieRecord hoodieRecord = new HoodieAvroRecord(
|
||||
new HoodieKey(KeyGenUtils.getRecordKey(record, recordKeyField, false), ""), null);
|
||||
int bucketId = BucketIdentifier.getBucketId(hoodieRecord, indexKeyField, 8);
|
||||
assert bucketId == BucketIdentifier.getBucketId(
|
||||
Arrays.asList(record.get(indexKeyField).toString()), 8);
|
||||
}
|
||||
}
|
||||
@@ -1,129 +0,0 @@
|
||||
/*
|
||||
* Licensed to the Apache Software Foundation (ASF) under one
|
||||
* or more contributor license agreements. See the NOTICE file
|
||||
* distributed with this work for additional information
|
||||
* regarding copyright ownership. The ASF licenses this file
|
||||
* to you under the Apache License, Version 2.0 (the
|
||||
* "License"); you may not use this file except in compliance
|
||||
* with the License. You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.hudi.testutils;
|
||||
|
||||
import org.apache.avro.Schema;
|
||||
import org.apache.avro.generic.GenericData;
|
||||
import org.apache.avro.generic.GenericRecord;
|
||||
import org.apache.hudi.AvroConversionUtils;
|
||||
import org.apache.spark.package$;
|
||||
import org.apache.spark.sql.Row;
|
||||
import org.apache.spark.sql.catalyst.InternalRow;
|
||||
import org.apache.spark.sql.catalyst.analysis.SimpleAnalyzer$;
|
||||
import org.apache.spark.sql.catalyst.encoders.ExpressionEncoder;
|
||||
import org.apache.spark.sql.catalyst.encoders.RowEncoder;
|
||||
import org.apache.spark.sql.catalyst.expressions.Attribute;
|
||||
import org.apache.spark.sql.catalyst.expressions.GenericRowWithSchema;
|
||||
import org.apache.spark.sql.types.StructType;
|
||||
import scala.Function1;
|
||||
import scala.collection.JavaConversions;
|
||||
import scala.collection.JavaConverters;
|
||||
|
||||
import java.lang.reflect.InvocationTargetException;
|
||||
import java.lang.reflect.Method;
|
||||
import java.util.List;
|
||||
import java.util.stream.Collectors;
|
||||
|
||||
public class KeyGeneratorTestUtilities {
|
||||
|
||||
public static final String NESTED_COL_SCHEMA = "{\"type\":\"record\", \"name\":\"nested_col\",\"fields\": ["
|
||||
+ "{\"name\": \"prop1\",\"type\": \"string\"},{\"name\": \"prop2\", \"type\": \"long\"}]}";
|
||||
public static final String EXAMPLE_SCHEMA = "{\"type\": \"record\",\"name\": \"testrec\",\"fields\": [ "
|
||||
+ "{\"name\": \"timestamp\",\"type\": \"long\"},{\"name\": \"_row_key\", \"type\": \"string\"},"
|
||||
+ "{\"name\": \"ts_ms\", \"type\": \"string\"},"
|
||||
+ "{\"name\": \"pii_col\", \"type\": \"string\"},"
|
||||
+ "{\"name\": \"nested_col\",\"type\": [\"null\", " + NESTED_COL_SCHEMA + "]}"
|
||||
+ "]}";
|
||||
|
||||
public static final String TEST_STRUCTNAME = "test_struct_name";
|
||||
public static final String TEST_RECORD_NAMESPACE = "test_record_namespace";
|
||||
public static Schema schema = new Schema.Parser().parse(EXAMPLE_SCHEMA);
|
||||
public static StructType structType = AvroConversionUtils.convertAvroSchemaToStructType(schema);
|
||||
|
||||
public static GenericRecord getRecord() {
|
||||
return getRecord(getNestedColRecord("val1", 10L));
|
||||
}
|
||||
|
||||
public static GenericRecord getNestedColRecord(String prop1Value, Long prop2Value) {
|
||||
GenericRecord nestedColRecord = new GenericData.Record(new Schema.Parser().parse(NESTED_COL_SCHEMA));
|
||||
nestedColRecord.put("prop1", prop1Value);
|
||||
nestedColRecord.put("prop2", prop2Value);
|
||||
return nestedColRecord;
|
||||
}
|
||||
|
||||
public static GenericRecord getRecord(GenericRecord nestedColRecord) {
|
||||
GenericRecord record = new GenericData.Record(new Schema.Parser().parse(EXAMPLE_SCHEMA));
|
||||
record.put("timestamp", 4357686L);
|
||||
record.put("_row_key", "key1");
|
||||
record.put("ts_ms", "2020-03-21");
|
||||
record.put("pii_col", "pi");
|
||||
record.put("nested_col", nestedColRecord);
|
||||
return record;
|
||||
}
|
||||
|
||||
public static Row getRow(GenericRecord record) {
|
||||
return getRow(record, schema, structType);
|
||||
}
|
||||
|
||||
public static Row getRow(GenericRecord record, Schema schema, StructType structType) {
|
||||
Function1<GenericRecord, Row> converterFn = AvroConversionUtils.createConverterToRow(schema, structType);
|
||||
Row row = converterFn.apply(record);
|
||||
int fieldCount = structType.fieldNames().length;
|
||||
Object[] values = new Object[fieldCount];
|
||||
for (int i = 0; i < fieldCount; i++) {
|
||||
values[i] = row.get(i);
|
||||
}
|
||||
return new GenericRowWithSchema(values, structType);
|
||||
}
|
||||
|
||||
public static InternalRow getInternalRow(Row row) {
|
||||
try {
|
||||
return getInternalRow(row, getEncoder(row.schema()));
|
||||
} catch (Exception e) {
|
||||
throw new IllegalStateException("Exception thrown while converting Row to InternalRow", e);
|
||||
}
|
||||
}
|
||||
|
||||
private static ExpressionEncoder getEncoder(StructType schema) {
|
||||
List<Attribute> attributes = JavaConversions.asJavaCollection(schema.toAttributes()).stream()
|
||||
.map(Attribute::toAttribute).collect(Collectors.toList());
|
||||
return RowEncoder.apply(schema)
|
||||
.resolveAndBind(JavaConverters.asScalaBufferConverter(attributes).asScala().toSeq(),
|
||||
SimpleAnalyzer$.MODULE$);
|
||||
}
|
||||
|
||||
public static InternalRow getInternalRow(Row row, ExpressionEncoder<Row> encoder) throws ClassNotFoundException, InvocationTargetException, IllegalAccessException, NoSuchMethodException {
|
||||
return serializeRow(encoder, row);
|
||||
}
|
||||
|
||||
private static InternalRow serializeRow(ExpressionEncoder encoder, Row row)
|
||||
throws InvocationTargetException, IllegalAccessException, NoSuchMethodException, ClassNotFoundException {
|
||||
// TODO remove reflection if Spark 2.x support is dropped
|
||||
if (package$.MODULE$.SPARK_VERSION().startsWith("2.")) {
|
||||
Method spark2method = encoder.getClass().getMethod("toRow", Object.class);
|
||||
return (InternalRow) spark2method.invoke(encoder, row);
|
||||
} else {
|
||||
Class<?> serializerClass = Class.forName("org.apache.spark.sql.catalyst.encoders.ExpressionEncoder$Serializer");
|
||||
Object serializer = encoder.getClass().getMethod("createSerializer").invoke(encoder);
|
||||
Method aboveSpark2method = serializerClass.getMethod("apply", Object.class);
|
||||
return (InternalRow) aboveSpark2method.invoke(serializer, row);
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
Reference in New Issue
Block a user