[GitHub] [iceberg] flyrain commented on a diff in pull request #7038: Spark 3.3: Add ProcedureInput to simplify procedures

["flyrain (via GitHub)" <gi...@apache.org>]

flyrain commented on code in PR #7038:
URL: https://github.com/apache/iceberg/pull/7038#discussion_r1130196296


##########
spark/v3.3/spark/src/main/java/org/apache/iceberg/spark/procedures/ProcedureInput.java:
##########
@@ -0,0 +1,201 @@
+/*
+ * 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 java.lang.reflect.Array;
+import java.util.Map;
+import java.util.function.BiFunction;
+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.Spark3Util;
+import org.apache.iceberg.spark.Spark3Util.CatalogAndIdentifier;
+import org.apache.spark.sql.SparkSession;
+import org.apache.spark.sql.catalyst.InternalRow;
+import org.apache.spark.sql.catalyst.util.ArrayData;
+import org.apache.spark.sql.catalyst.util.MapData;
+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.apache.spark.sql.connector.iceberg.catalog.ProcedureParameter;
+import org.apache.spark.sql.types.DataType;
+import org.apache.spark.sql.types.DataTypes;
+
+/** A class that abstracts common logic for working with input to a procedure. */
+class ProcedureInput {
+
+  private static final DataType STRING_ARRAY = DataTypes.createArrayType(DataTypes.StringType);
+  private static final DataType STRING_MAP =
+      DataTypes.createMapType(DataTypes.StringType, DataTypes.StringType);
+
+  private final SparkSession spark;
+  private final TableCatalog catalog;
+  private final Map<String, Integer> paramOrdinals;
+  private final InternalRow args;
+
+  ProcedureInput(
+      SparkSession spark, TableCatalog catalog, ProcedureParameter[] params, InternalRow args) {
+    this.spark = spark;
+    this.catalog = catalog;
+    this.paramOrdinals = computeParamOrdinals(params);
+    this.args = args;
+  }
+
+  public boolean isProvided(ProcedureParameter param) {
+    int ordinal = ordinal(param);
+    return !args.isNullAt(ordinal);
+  }
+
+  public boolean bool(ProcedureParameter param, boolean defaultValue) {
+    validateParamType(param, DataTypes.BooleanType);
+    int ordinal = ordinal(param);
+    return args.isNullAt(ordinal) ? defaultValue : args.getBoolean(ordinal);
+  }
+
+  public String string(ProcedureParameter param, String defaultValue) {
+    validateParamType(param, DataTypes.StringType);
+    int ordinal = ordinal(param);
+    return args.isNullAt(ordinal) ? defaultValue : args.getString(ordinal);
+  }
+
+  public String[] stringArray(ProcedureParameter param) {
+    String[] value = stringArray(param, null);
+    Preconditions.checkArgument(value != null, "Param %s is not set", param.name());
+    return value;
+  }
+
+  public String[] stringArray(ProcedureParameter param, String[] defaultValue) {
+    validateParamType(param, STRING_ARRAY);
+    return array(
+        param,
+        (array, ordinal) -> array.getUTF8String(ordinal).toString(),
+        String.class,
+        defaultValue);
+  }

Review Comment:
   Can we use method overloading for all these get value methods? It could be like followings:
   ```
   boolean get(ProcedureParameter param, boolean defaultValue) 
   String get(ProcedureParameter param, String defaultValue)
   String[] get(ProcedureParameter param)
   ...
   ```
   
   Method name could be `get` or `getValue`.  I feel like developer know its return type, and don't have to be different names for these methods. 



-- 
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