zhangjun0x01 commented on a change in pull request #2217: URL: https://github.com/apache/iceberg/pull/2217#discussion_r578977060
########## File path: flink/src/main/java/org/apache/iceberg/flink/actions/MigrateAction.java ########## @@ -0,0 +1,406 @@ +/* + * 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.iceberg.flink.actions; + +import java.io.IOException; +import java.io.UncheckedIOException; +import java.util.Arrays; +import java.util.List; +import java.util.Map; +import java.util.stream.Collectors; +import org.apache.flink.api.common.functions.RichFlatMapFunction; +import org.apache.flink.configuration.GlobalConfiguration; +import org.apache.flink.runtime.util.HadoopUtils; +import org.apache.flink.streaming.api.datastream.DataStream; +import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment; +import org.apache.flink.table.catalog.CatalogPartitionSpec; +import org.apache.flink.table.catalog.ObjectPath; +import org.apache.flink.table.catalog.exceptions.TableNotExistException; +import org.apache.flink.table.catalog.hive.HiveCatalog; +import org.apache.flink.util.ArrayUtils; +import org.apache.flink.util.Collector; +import org.apache.hadoop.conf.Configuration; +import org.apache.hadoop.fs.FileStatus; +import org.apache.hadoop.fs.FileSystem; +import org.apache.hadoop.fs.Path; +import org.apache.hadoop.hive.common.FileUtils; +import org.apache.hadoop.hive.metastore.api.FieldSchema; +import org.apache.hadoop.hive.metastore.api.Partition; +import org.apache.iceberg.AppendFiles; +import org.apache.iceberg.DataFile; +import org.apache.iceberg.DataFiles; +import org.apache.iceberg.FileFormat; +import org.apache.iceberg.ManifestFile; +import org.apache.iceberg.ManifestFiles; +import org.apache.iceberg.ManifestWriter; +import org.apache.iceberg.Metrics; +import org.apache.iceberg.MetricsConfig; +import org.apache.iceberg.PartitionField; +import org.apache.iceberg.PartitionSpec; +import org.apache.iceberg.Schema; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableProperties; +import org.apache.iceberg.actions.Action; +import org.apache.iceberg.catalog.Catalog; +import org.apache.iceberg.catalog.Namespace; +import org.apache.iceberg.catalog.TableIdentifier; +import org.apache.iceberg.flink.FlinkCatalogFactory; +import org.apache.iceberg.hadoop.HadoopCatalog; +import org.apache.iceberg.hadoop.HadoopFileIO; +import org.apache.iceberg.hadoop.HadoopInputFile; +import org.apache.iceberg.hive.HiveSchemaUtil; +import org.apache.iceberg.io.FileIO; +import org.apache.iceberg.io.InputFile; +import org.apache.iceberg.io.OutputFile; +import org.apache.iceberg.mapping.NameMapping; +import org.apache.iceberg.mapping.NameMappingParser; +import org.apache.iceberg.orc.OrcMetrics; +import org.apache.iceberg.parquet.ParquetUtil; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.relocated.com.google.common.collect.Maps; +import org.apache.iceberg.util.PropertyUtil; +import org.apache.iceberg.util.Tasks; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +public class MigrateAction implements Action<List<ManifestFile>> { + private static final Logger LOGGER = LoggerFactory.getLogger(MigrateAction.class); + + private static final String PARQUET_INPUT_FORMAT = "org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat"; + private static final String ORC_INPUT_FORMAT = "org.apache.hadoop.hive.ql.io.orc.OrcInputFormat"; + + private static final String ICEBERG_METADATA_FOLDER = "metadata"; + + private final StreamExecutionEnvironment env; + private final HiveCatalog flinkHiveCatalog; // the HiveCatalog of flink + private final String hiveSourceDatabaseName; + private final String hiveSourceTableName; + private final Catalog icebergCatalog; + private final Namespace baseNamespace; + private final String icebergDatabaseName; + private final String icebergTableName; + private int maxParallelism; + + public MigrateAction(StreamExecutionEnvironment env, HiveCatalog flinkHiveCatalog, String hiveSourceDatabaseName, + String hiveSourceTableName, Catalog icebergCatalog, Namespace baseNamespace, + String icebergDatabaseName, + String icebergTableName) { + this.env = env; + this.flinkHiveCatalog = flinkHiveCatalog; + this.hiveSourceDatabaseName = hiveSourceDatabaseName; + this.hiveSourceTableName = hiveSourceTableName; + this.icebergCatalog = icebergCatalog; + this.baseNamespace = baseNamespace; + this.icebergDatabaseName = icebergDatabaseName; + this.icebergTableName = icebergTableName; + this.maxParallelism = env.getParallelism(); + } + + @Override + public List<ManifestFile> execute() { + flinkHiveCatalog.open(); + // hive source table + ObjectPath tableSource = new ObjectPath(hiveSourceDatabaseName, hiveSourceTableName); + org.apache.hadoop.hive.metastore.api.Table hiveTable; + try { + hiveTable = flinkHiveCatalog.getHiveTable(tableSource); + } catch (TableNotExistException e) { + throw new RuntimeException(String.format("The source table %s not exists ! ", hiveSourceTableName)); + } + + List<FieldSchema> fieldSchemaList = hiveTable.getSd().getCols(); + List<FieldSchema> partitionList = hiveTable.getPartitionKeys(); + fieldSchemaList.addAll(partitionList); + Schema icebergSchema = HiveSchemaUtil.convert(fieldSchemaList); + PartitionSpec spec = HiveSchemaUtil.spec(icebergSchema, partitionList); + + FileFormat fileFormat = getHiveFileFormat(hiveTable); + + Namespace namespace = Namespace.of(ArrayUtils.concat(baseNamespace.levels(), new String[] {icebergDatabaseName})); + TableIdentifier identifier = TableIdentifier.of(namespace, icebergTableName); + String hiveLocation = hiveTable.getSd().getLocation(); + + Map<String, String> properties = Maps.newHashMap(); + properties.put(TableProperties.DEFAULT_FILE_FORMAT, fileFormat.name()); + if (!baseNamespace.isEmpty()) { + properties.put(FlinkCatalogFactory.BASE_NAMESPACE, baseNamespace.toString()); + } + + Table icebergTable; + if (icebergCatalog instanceof HadoopCatalog) { + icebergTable = icebergCatalog.createTable(identifier, icebergSchema, spec, properties); + } else { + icebergTable = icebergCatalog.createTable(identifier, icebergSchema, spec, hiveLocation, properties); + } + + String metadataLocation = getMetadataLocation(icebergTable); + + String nameMapping = + PropertyUtil.propertyAsString(icebergTable.properties(), TableProperties.DEFAULT_NAME_MAPPING, null); + MetricsConfig metricsConfig = MetricsConfig.fromProperties(icebergTable.properties()); + + List<ManifestFile> manifestFiles = null; + try { + if (spec.isUnpartitioned()) { + manifestFiles = + migrateUnpartitionedTable(spec, fileFormat, hiveLocation, nameMapping, metricsConfig, metadataLocation); + } else { + manifestFiles = + migratePartitionedTable(spec, tableSource, nameMapping, fileFormat, metricsConfig, metadataLocation); + } + + AppendFiles append = icebergTable.newAppend(); + manifestFiles.forEach(append::appendManifest); + append.commit(); + } catch (Exception e) { + LOGGER.error("Migrate hive table to iceberg table failed.", e); + deleteManifests(icebergTable.io(), manifestFiles); + } finally { + flinkHiveCatalog.close(); + } + + return manifestFiles; + } + + private static void deleteManifests(FileIO io, List<ManifestFile> manifests) { + Tasks.foreach(manifests) + .noRetry() + .suppressFailureWhenFinished() + .run(item -> io.deleteFile(item.path())); + } + + private static FileFormat getHiveFileFormat(org.apache.hadoop.hive.metastore.api.Table hiveTable) { + String hiveFormat = hiveTable.getSd().getInputFormat(); + FileFormat fileFormat; + switch (hiveFormat) { + case PARQUET_INPUT_FORMAT: + fileFormat = FileFormat.PARQUET; + break; + + case ORC_INPUT_FORMAT: + fileFormat = FileFormat.ORC; + break; + + default: + throw new UnsupportedOperationException("Unsupported file format"); + } + + return fileFormat; + } + + private String getMetadataLocation(Table table) { + return table.properties() + .getOrDefault(TableProperties.WRITE_METADATA_LOCATION, table.location() + "/" + ICEBERG_METADATA_FOLDER); + } + + private List<ManifestFile> migrateUnpartitionedTable(PartitionSpec spec, FileFormat fileFormat, String hiveLocation, Review comment: I read the code of `Spark3MigrateAction`, but I am not familiar with spark, I don’t know if I understand it correctly. In `Spark3MigrateAction`, source catalog and destination catalog, source table name and destination table name are the same, so after we had migrated a non-iceberg table to the iceberg table, the read and write operations using spark may not require any changes. But for hive table and iceberg table, some changes will be needed. For example, we are using flink to read and write hive table, the sql like this: `SELECT * FROM hivecatalog.hivedb.hivetable;` After the migration is completed, the sql needs to be modified to `select * from iceberg_catalog.iceberg_db.iceberg_table`, so when users migrate the hive table to iceberg, they need to stop the writing hive job first, then migrate, and finally modify the logic to reading and writing iceberg table. So I think even if we renamed the source hive table, it does not make much sence to the user, because the user still needs to manually stop and modify the job of writing hive to write iceberg. ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org For additional commands, e-mail: issues-h...@iceberg.apache.org
