[GitHub] [iceberg] aokolnychyi commented on a change in pull request #2437: Spark: Refactor snapshot and migrate actions

[GitBox <gi...@apache.org>]

aokolnychyi commented on a change in pull request #2437:
URL: https://github.com/apache/iceberg/pull/2437#discussion_r609112776



##########
File path: spark3/src/main/java/org/apache/iceberg/spark/actions/BaseMigrateTableSparkAction.java
##########
@@ -0,0 +1,192 @@
+/*
+ * 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.spark.actions;
+
+import java.util.Map;
+import org.apache.iceberg.Snapshot;
+import org.apache.iceberg.SnapshotSummary;
+import org.apache.iceberg.Table;
+import org.apache.iceberg.actions.BaseMigrateTableActionResult;
+import org.apache.iceberg.actions.MigrateTable;
+import org.apache.iceberg.exceptions.AlreadyExistsException;
+import org.apache.iceberg.exceptions.NoSuchTableException;
+import org.apache.iceberg.relocated.com.google.common.base.Preconditions;
+import org.apache.iceberg.relocated.com.google.common.collect.Maps;
+import org.apache.iceberg.spark.JobGroupInfo;
+import org.apache.iceberg.spark.SparkSessionCatalog;
+import org.apache.iceberg.spark.SparkTableUtil;
+import org.apache.iceberg.spark.source.StagedSparkTable;
+import org.apache.spark.sql.SparkSession;
+import org.apache.spark.sql.catalyst.TableIdentifier;
+import org.apache.spark.sql.connector.catalog.CatalogPlugin;
+import org.apache.spark.sql.connector.catalog.Identifier;
+import org.apache.spark.sql.connector.catalog.TableCatalog;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+import scala.Some;
+import scala.collection.JavaConverters;
+
+/**
+ * Takes a Spark table in the source catalog and attempts to transform it into an Iceberg
+ * table in the same location with the same identifier. Once complete the identifier which
+ * previously referred to a non-Iceberg table will refer to the newly migrated Iceberg
+ * table.
+ */
+public class BaseMigrateTableSparkAction
+    extends BaseTableMigrationSparkAction<MigrateTable, MigrateTable.Result>
+    implements MigrateTable {
+
+  private static final Logger LOG = LoggerFactory.getLogger(BaseMigrateTableSparkAction.class);
+  private static final String BACKUP_SUFFIX = "_BACKUP_";
+
+  private final Identifier backupIdent;
+
+  public BaseMigrateTableSparkAction(SparkSession spark, CatalogPlugin sourceCatalog, Identifier sourceTableIdent) {
+    super(spark, sourceCatalog, sourceTableIdent, sourceCatalog, sourceTableIdent);
+    String backupName = sourceTableIdent().name() + BACKUP_SUFFIX;
+    this.backupIdent = Identifier.of(sourceTableIdent().namespace(), backupName);
+  }
+
+  @Override
+  protected MigrateTable self() {
+    return this;
+  }
+
+  @Override
+  public MigrateTable tableProperties(Map<String, String> properties) {
+    setProperties(properties);
+    return this;
+  }
+
+  @Override
+  public MigrateTable tableProperty(String property, String value) {
+    setProperty(property, value);
+    return this;
+  }
+
+  @Override
+  public MigrateTable.Result execute() {
+    JobGroupInfo info = newJobGroupInfo("MIGRATE-TABLE", "MIGRATE-TABLE");
+    return withJobGroupInfo(info, this::doExecute);
+  }
+
+  private MigrateTable.Result doExecute() {
+    LOG.info("Starting the migration of {} to Iceberg", sourceTableIdent());
+
+    // move the source table to a new name, halting all modifications and allowing us to stage
+    // the creation of a new Iceberg table in its place
+    renameAndBackupSourceTable();
+
+    StagedSparkTable stagedTable = null;
+    Table icebergTable;
+    boolean threw = true;
+    try {
+      LOG.info("Staging a new Iceberg table {}", destTableIdent());
+      stagedTable = stageDestTable();
+      icebergTable = stagedTable.table();
+
+      LOG.info("Ensuring {} has a valid name mapping", destTableIdent());
+      ensureNameMappingPresent(icebergTable);
+
+      Some<String> backupNamespace = Some.apply(backupIdent.namespace()[0]);
+      TableIdentifier v1BackupIdent = new TableIdentifier(backupIdent.name(), backupNamespace);
+      String stagingLocation = getMetadataLocation(icebergTable);
+      LOG.info("Generating Iceberg metadata for {} in {}", destTableIdent(), stagingLocation);
+      SparkTableUtil.importSparkTable(spark(), v1BackupIdent, icebergTable, stagingLocation);
+
+      LOG.info("Committing staged changes to {}", destTableIdent());
+      stagedTable.commitStagedChanges();
+      threw = false;
+    } finally {
+      if (threw) {
+        LOG.error("Failed to perform the migration, aborting table creation and restoring the original table");
+
+        restoreSourceTable();
+
+        if (stagedTable != null) {
+          try {
+            stagedTable.abortStagedChanges();
+          } catch (Exception abortException) {
+            LOG.error("Cannot abort staged changes", abortException);
+          }
+        }
+      }
+    }
+
+    Snapshot snapshot = icebergTable.currentSnapshot();
+    long migratedDataFilesCount = Long.parseLong(snapshot.summary().get(SnapshotSummary.TOTAL_DATA_FILES_PROP));
+    LOG.info("Successfully loaded Iceberg metadata for {} files to {}", migratedDataFilesCount, destTableIdent());
+    return new BaseMigrateTableActionResult(migratedDataFilesCount);
+  }
+
+  @Override
+  protected Map<String, String> targetTableProps() {

Review comment:
       I kept the existing behavior without changes in #2420.




-- 
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:
users@infra.apache.org



---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@iceberg.apache.org
For additional commands, e-mail: issues-help@iceberg.apache.org