-
Notifications
You must be signed in to change notification settings - Fork 946
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
[spark] Support migrate database procedure for spark
- Loading branch information
Showing
5 changed files
with
276 additions
and
18 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
136 changes: 136 additions & 0 deletions
136
...park-common/src/main/java/org/apache/paimon/spark/procedure/MigrateDatabaseProcedure.java
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,136 @@ | ||
| /* | ||
| * 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.paimon.spark.procedure; | ||
|
|
||
| import org.apache.paimon.catalog.Catalog; | ||
| import org.apache.paimon.migrate.Migrator; | ||
| import org.apache.paimon.spark.catalog.WithPaimonCatalog; | ||
| import org.apache.paimon.spark.utils.TableMigrationUtils; | ||
| import org.apache.paimon.utils.ParameterUtils; | ||
|
|
||
| import org.apache.spark.sql.catalyst.InternalRow; | ||
| import org.apache.spark.sql.catalyst.util.MapData; | ||
| import org.apache.spark.sql.connector.catalog.TableCatalog; | ||
| import org.apache.spark.sql.types.DataTypes; | ||
| import org.apache.spark.sql.types.Metadata; | ||
| import org.apache.spark.sql.types.StructField; | ||
| import org.apache.spark.sql.types.StructType; | ||
|
|
||
| import java.util.HashMap; | ||
| import java.util.List; | ||
| import java.util.Map; | ||
|
|
||
| import static org.apache.spark.sql.types.DataTypes.*; | ||
|
|
||
| /** | ||
| * Migrate database procedure. Usage: | ||
| * | ||
| * <pre><code> | ||
| * CALL sys.migrate_database(source_type => 'hive', database => 'db01', options => 'x1=y1,x2=y2') | ||
| * </code></pre> | ||
| */ | ||
| public class MigrateDatabaseProcedure extends BaseProcedure { | ||
|
|
||
| private static final ProcedureParameter[] PARAMETERS = | ||
| new ProcedureParameter[] { | ||
| ProcedureParameter.required("source_type", StringType), | ||
| ProcedureParameter.required("database", StringType), | ||
| ProcedureParameter.optional("options", StringType), | ||
| ProcedureParameter.optional( | ||
| "options_map", DataTypes.createMapType(StringType, StringType)), | ||
| ProcedureParameter.optional("parallelism", IntegerType), | ||
| }; | ||
|
|
||
| private static final StructType OUTPUT_TYPE = | ||
| new StructType( | ||
| new StructField[] { | ||
| new StructField("result", DataTypes.BooleanType, true, Metadata.empty()) | ||
| }); | ||
|
|
||
| protected MigrateDatabaseProcedure(TableCatalog tableCatalog) { | ||
| super(tableCatalog); | ||
| } | ||
|
|
||
| @Override | ||
| public ProcedureParameter[] parameters() { | ||
| return PARAMETERS; | ||
| } | ||
|
|
||
| @Override | ||
| public StructType outputType() { | ||
| return OUTPUT_TYPE; | ||
| } | ||
|
|
||
| @Override | ||
| public InternalRow[] call(InternalRow args) { | ||
| String format = args.getString(0); | ||
| String database = args.getString(1); | ||
| String properties = args.isNullAt(2) ? null : args.getString(2); | ||
| MapData mapData = args.isNullAt(3) ? null : args.getMap(3); | ||
| Map<String, String> optionMap = mapDataToHashMap(mapData); | ||
| int parallelism = | ||
| args.isNullAt(4) ? Runtime.getRuntime().availableProcessors() : args.getInt(4); | ||
|
|
||
| Catalog paimonCatalog = ((WithPaimonCatalog) tableCatalog()).paimonCatalog(); | ||
|
|
||
| Map<String, String> options = ParameterUtils.parseCommaSeparatedKeyValues(properties); | ||
| options.putAll(optionMap); | ||
|
|
||
| try { | ||
| List<Migrator> migrators = | ||
| TableMigrationUtils.getImporters( | ||
| format, paimonCatalog, database, parallelism, options); | ||
|
|
||
| for (Migrator migrator : migrators) { | ||
| migrator.executeMigrate(); | ||
| migrator.renameTable(false); | ||
| } | ||
| } catch (Exception e) { | ||
| throw new RuntimeException("Call migrate_database error: " + e.getMessage(), e); | ||
| } | ||
|
|
||
| return new InternalRow[] {newInternalRow(true)}; | ||
| } | ||
|
|
||
| public static Map<String, String> mapDataToHashMap(MapData mapData) { | ||
| HashMap<String, String> map = new HashMap<>(); | ||
| if (mapData != null) { | ||
| for (int index = 0; index < mapData.numElements(); index++) { | ||
| map.put( | ||
| mapData.keyArray().getUTF8String(index).toString(), | ||
| mapData.valueArray().getUTF8String(index).toString()); | ||
| } | ||
| } | ||
| return map; | ||
| } | ||
|
|
||
| public static ProcedureBuilder builder() { | ||
| return new BaseProcedure.Builder<MigrateDatabaseProcedure>() { | ||
| @Override | ||
| public MigrateDatabaseProcedure doBuild() { | ||
| return new MigrateDatabaseProcedure(tableCatalog()); | ||
| } | ||
| }; | ||
| } | ||
|
|
||
| @Override | ||
| public String description() { | ||
| return "MigrateDatabaseProcedure"; | ||
| } | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
104 changes: 104 additions & 0 deletions
104
...ommon/src/test/scala/org/apache/paimon/spark/procedure/MigrateDatabaseProcedureTest.scala
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,104 @@ | ||
| /* | ||
| * 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.paimon.spark.procedure | ||
|
|
||
| import org.apache.paimon.spark.PaimonHiveTestBase | ||
|
|
||
| import org.apache.spark.sql.Row | ||
| class MigrateDatabaseProcedureTest extends PaimonHiveTestBase { | ||
| Seq("parquet", "orc", "avro").foreach( | ||
| format => { | ||
| test(s"Paimon migrate database procedure: migrate $format non-partitioned database") { | ||
| withTable("hive_tbl", "hive_tbl1") { | ||
| // create hive table | ||
| spark.sql(s""" | ||
| |CREATE TABLE hive_tbl (id STRING, name STRING, pt STRING) | ||
| |USING $format | ||
| |""".stripMargin) | ||
|
|
||
| spark.sql(s""" | ||
| |CREATE TABLE hive_tbl1 (id STRING, name STRING, pt STRING) | ||
| |USING $format | ||
| |""".stripMargin) | ||
|
|
||
| var rows0 = spark.sql("SHOW CREATE TABLE hive_tbl").collect() | ||
| assert(!rows0.apply(0).toString().contains("USING paimon")) | ||
|
|
||
| rows0 = spark.sql("SHOW CREATE TABLE hive_tbl1").collect() | ||
| assert(!rows0.apply(0).toString().contains("USING paimon")) | ||
|
|
||
| spark.sql(s"INSERT INTO hive_tbl VALUES ('1', 'a', 'p1'), ('2', 'b', 'p2')") | ||
|
|
||
| spark.sql( | ||
| s"CALL sys.migrate_database(source_type => 'hive', database => '$hiveDbName', options => 'file.format=$format')") | ||
|
|
||
| checkAnswer( | ||
| spark.sql(s"SELECT * FROM hive_tbl ORDER BY id"), | ||
| Row("1", "a", "p1") :: Row("2", "b", "p2") :: Nil) | ||
|
|
||
| var rows1 = spark.sql("SHOW CREATE TABLE hive_tbl").collect() | ||
| assert(rows1.apply(0).toString().contains("USING paimon")) | ||
|
|
||
| rows1 = spark.sql("SHOW CREATE TABLE hive_tbl1").collect() | ||
| assert(rows1.apply(0).toString().contains("USING paimon")) | ||
|
|
||
| } | ||
| } | ||
| }) | ||
|
|
||
| Seq("parquet", "orc", "avro").foreach( | ||
| format => { | ||
| test( | ||
| s"Paimon migrate database procedure: migrate $format database with setting parallelism") { | ||
| withTable("hive_tbl_01", "hive_tbl_02") { | ||
| // create hive table | ||
| spark.sql(s""" | ||
| |CREATE TABLE hive_tbl_01 (id STRING, name STRING, pt STRING) | ||
| |USING $format | ||
| |""".stripMargin) | ||
|
|
||
| spark.sql(s""" | ||
| |CREATE TABLE hive_tbl_02 (id STRING, name STRING, pt STRING) | ||
| |USING $format | ||
| |""".stripMargin) | ||
|
|
||
| var rows0 = spark.sql("SHOW CREATE TABLE hive_tbl_01").collect() | ||
| assert(!rows0.apply(0).toString().contains("USING paimon")) | ||
|
|
||
| rows0 = spark.sql("SHOW CREATE TABLE hive_tbl_02").collect() | ||
| assert(!rows0.apply(0).toString().contains("USING paimon")) | ||
|
|
||
| spark.sql(s"INSERT INTO hive_tbl_01 VALUES ('1', 'a', 'p1'), ('2', 'b', 'p2')") | ||
|
|
||
| spark.sql( | ||
| s"CALL sys.migrate_database(source_type => 'hive', database => '$hiveDbName', options => 'file.format=$format', parallelism => 6)") | ||
|
|
||
| checkAnswer( | ||
| spark.sql(s"SELECT * FROM hive_tbl_01 ORDER BY id"), | ||
| Row("1", "a", "p1") :: Row("2", "b", "p2") :: Nil) | ||
|
|
||
| var rows1 = spark.sql("SHOW CREATE TABLE hive_tbl_01").collect() | ||
| assert(rows1.apply(0).toString().contains("USING paimon")) | ||
|
|
||
| rows1 = spark.sql("SHOW CREATE TABLE hive_tbl_02").collect() | ||
| assert(rows1.apply(0).toString().contains("USING paimon")) | ||
| } | ||
| } | ||
| }) | ||
| } |