You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@iceberg.apache.org by GitBox <gi...@apache.org> on 2022/05/18 19:57:41 UTC

[GitHub] [iceberg] flyrain commented on a diff in pull request #4810: Spark: Provide Procedure for Catalog Register Procedure

flyrain commented on code in PR #4810:
URL: https://github.com/apache/iceberg/pull/4810#discussion_r876318204


##########
spark/v3.2/spark/src/main/java/org/apache/iceberg/spark/procedures/RegisterTableProcedure.java:
##########
@@ -0,0 +1,93 @@
+/*
+ * 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.procedures;
+
+import org.apache.iceberg.Table;
+import org.apache.iceberg.catalog.Catalog;
+import org.apache.iceberg.catalog.TableIdentifier;
+import org.apache.iceberg.relocated.com.google.common.base.Preconditions;
+import org.apache.iceberg.spark.Spark3Util;
+import org.apache.iceberg.spark.procedures.SparkProcedures.ProcedureBuilder;
+import org.apache.iceberg.spark.source.HasIcebergCatalog;
+import org.apache.spark.sql.catalyst.InternalRow;
+import org.apache.spark.sql.connector.catalog.TableCatalog;
+import org.apache.spark.sql.connector.iceberg.catalog.ProcedureParameter;
+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;
+
+class RegisterTableProcedure extends BaseProcedure {
+  private static final ProcedureParameter[] PARAMETERS = new ProcedureParameter[]{
+      ProcedureParameter.required("table", DataTypes.StringType),
+      ProcedureParameter.required("metadata_file", DataTypes.StringType)
+  };
+
+  private static final StructType OUTPUT_TYPE = new StructType(new StructField[]{
+      new StructField("Current Snapshot", DataTypes.LongType, false, Metadata.empty()),
+      new StructField("Manifests Registered", DataTypes.LongType, false, Metadata.empty()),
+      new StructField("Datafiles Registered", DataTypes.LongType, false, Metadata.empty())
+  });
+
+  private RegisterTableProcedure(TableCatalog tableCatalog) {
+    super(tableCatalog);
+  }
+
+  public static ProcedureBuilder builder() {
+    return new BaseProcedure.Builder<RegisterTableProcedure>() {
+      @Override
+      protected RegisterTableProcedure doBuild() {
+        return new RegisterTableProcedure(tableCatalog());
+      }
+    };
+  }
+
+  @Override
+  public ProcedureParameter[] parameters() {
+    return PARAMETERS;
+  }
+
+  @Override
+  public StructType outputType() {
+    return OUTPUT_TYPE;
+  }
+
+  @Override
+  public InternalRow[] call(InternalRow args) {
+    TableIdentifier tableName = Spark3Util.identifierToTableIdentifier(toIdentifier(args.getString(0), "table"));
+    String metadataFile = args.getString(1);
+    Preconditions.checkArgument(metadataFile != null && !metadataFile.isEmpty(),
+        "Cannot handle an empty argument metadata_file");
+
+    Catalog icebergCatalog = ((HasIcebergCatalog) tableCatalog()).icebergCatalog();

Review Comment:
   Should we check if the tableCatalog is an instance of `HasIcebergCatalog`?



-- 
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.

To unsubscribe, e-mail: issues-unsubscribe@iceberg.apache.org

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