[GitHub] [incubator-iceberg] aokolnychyi commented on a change in pull request #224: Change Spark data source option style

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

aokolnychyi commented on a change in pull request #224: Change Spark data source option style
URL: https://github.com/apache/incubator-iceberg/pull/224#discussion_r294892708
 
 

 ##########
 File path: spark/src/test/java/org/apache/iceberg/spark/source/TestDataSourceOptions.java
 ##########
 @@ -0,0 +1,128 @@
+/*
+ * 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.source;
+
+import com.google.common.collect.Lists;
+import com.google.common.collect.Maps;
+import java.io.IOException;
+import java.util.List;
+import java.util.Map;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.iceberg.FileFormat;
+import org.apache.iceberg.FileScanTask;
+import org.apache.iceberg.PartitionSpec;
+import org.apache.iceberg.Schema;
+import org.apache.iceberg.Table;
+import org.apache.iceberg.TableProperties;
+import org.apache.iceberg.hadoop.HadoopTables;
+import org.apache.iceberg.io.CloseableIterable;
+import org.apache.iceberg.types.Types;
+import org.apache.spark.sql.Dataset;
+import org.apache.spark.sql.Row;
+import org.apache.spark.sql.SparkSession;
+import org.junit.AfterClass;
+import org.junit.Assert;
+import org.junit.BeforeClass;
+import org.junit.Rule;
+import org.junit.Test;
+import org.junit.rules.TemporaryFolder;
+
+import static org.apache.iceberg.types.Types.NestedField.optional;
+
+public class TestDataSourceOptions {
+
+  private static final Configuration CONF = new Configuration();
+  private static final Schema SCHEMA = new Schema(
+      optional(1, "id", Types.IntegerType.get()),
+      optional(2, "data", Types.StringType.get())
+  );
+  private static SparkSession spark = null;
+
+  @Rule
+  public TemporaryFolder temp = new TemporaryFolder();
+
+  @BeforeClass
+  public static void startSpark() {
+    TestDataSourceOptions.spark = SparkSession.builder().master("local[2]").getOrCreate();
+  }
+
+  @AfterClass
+  public static void stopSpark() {
+    SparkSession currentSpark = TestDataSourceOptions.spark;
+    TestDataSourceOptions.spark = null;
+    currentSpark.stop();
+  }
+
+  @Test
+  public void testWriteFormatOptionOverridesTableProperties() throws IOException {
+    String tableLocation = temp.newFolder("iceberg-table").toString();
+
+    HadoopTables tables = new HadoopTables(CONF);
+    PartitionSpec spec = PartitionSpec.unpartitioned();
+    Map<String, String> options = Maps.newHashMap();
+    options.put(TableProperties.DEFAULT_FILE_FORMAT, "avro");
+    Table table = tables.create(SCHEMA, spec, options, tableLocation);
+
+    List<SimpleRecord> expectedRecords = Lists.newArrayList(
+        new SimpleRecord(1, "a"),
+        new SimpleRecord(2, "b"),
+        new SimpleRecord(3, "c")
+    );
+    Dataset<Row> df = spark.createDataFrame(expectedRecords, SimpleRecord.class);
+    df.select("id", "data").write()
+        .format("iceberg")
+        .option("write-format", "parquet")
+        .mode("append")
+        .save(tableLocation);
+
+    try (CloseableIterable<FileScanTask> tasks = table.newScan().planFiles()) {
+      tasks.forEach(task -> {
+        FileFormat fileFormat = FileFormat.fromFileName(task.file().path());
+        Assert.assertEquals(FileFormat.PARQUET, fileFormat);
+      });
+    }
+  }
+
+  @Test
+  public void testNoWriteFormatOption() throws IOException {
+    String tableLocation = temp.newFolder("iceberg-table").toString();
+
+    HadoopTables tables = new HadoopTables(CONF);
+    PartitionSpec spec = PartitionSpec.unpartitioned();
+    Map<String, String> options = Maps.newHashMap();
+    options.put(TableProperties.DEFAULT_FILE_FORMAT, "avro");
 
 Review comment:
   This is a test where we verify that if `write-format` is not set, it is inherited from table properties. The previous test verifies that `write-format` overrides table properties.

----------------------------------------------------------------
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


With regards,
Apache Git Services

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