[GitHub] [iceberg] RussellSpitzer commented on a change in pull request #2757: Add support for reading/writing timestamps without timezone.

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

RussellSpitzer commented on a change in pull request #2757:
URL: https://github.com/apache/iceberg/pull/2757#discussion_r664647453



##########
File path: spark/src/test/java/org/apache/iceberg/spark/source/TestTimestampWithoutZone.java
##########
@@ -0,0 +1,284 @@
+/*
+ * 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 java.io.File;
+import java.io.IOException;
+import java.time.LocalDateTime;
+import java.util.List;
+import java.util.Locale;
+import java.util.UUID;
+import java.util.stream.Collectors;
+import java.util.stream.Stream;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.iceberg.AssertHelpers;
+import org.apache.iceberg.DataFile;
+import org.apache.iceberg.DataFiles;
+import org.apache.iceberg.FileFormat;
+import org.apache.iceberg.PartitionSpec;
+import org.apache.iceberg.Schema;
+import org.apache.iceberg.Table;
+import org.apache.iceberg.data.GenericAppenderFactory;
+import org.apache.iceberg.data.GenericRecord;
+import org.apache.iceberg.data.Record;
+import org.apache.iceberg.hadoop.HadoopTables;
+import org.apache.iceberg.io.FileAppender;
+import org.apache.iceberg.relocated.com.google.common.collect.Lists;
+import org.apache.iceberg.spark.SparkUtil;
+import org.apache.iceberg.spark.data.GenericsHelpers;
+import org.apache.iceberg.types.Types;
+import org.apache.spark.sql.Dataset;
+import org.apache.spark.sql.Row;
+import org.apache.spark.sql.SaveMode;
+import org.apache.spark.sql.SparkSession;
+import org.junit.AfterClass;
+import org.junit.Assert;
+import org.junit.Before;
+import org.junit.BeforeClass;
+import org.junit.Rule;
+import org.junit.Test;
+import org.junit.rules.ExpectedException;
+import org.junit.rules.TemporaryFolder;
+import org.junit.runner.RunWith;
+import org.junit.runners.Parameterized;
+
+import static org.apache.iceberg.Files.localOutput;
+
+@RunWith(Parameterized.class)
+public abstract class TestTimestampWithoutZone {
+  private static final Configuration CONF = new Configuration();
+  private static final HadoopTables TABLES = new HadoopTables(CONF);
+
+  private static final Schema SCHEMA = new Schema(
+      Types.NestedField.required(1, "id", Types.LongType.get()),
+      Types.NestedField.optional(2, "ts", Types.TimestampType.withoutZone()),
+      Types.NestedField.optional(3, "data", Types.StringType.get())
+  );
+
+  private static SparkSession spark = null;
+
+  @BeforeClass
+  public static void startSpark() {
+    TestTimestampWithoutZone.spark = SparkSession.builder().master("local[2]").getOrCreate();
+  }
+
+  @AfterClass
+  public static void stopSpark() {
+    SparkSession currentSpark = TestTimestampWithoutZone.spark;
+    TestTimestampWithoutZone.spark = null;
+    currentSpark.stop();
+  }
+
+  @Rule
+  public TemporaryFolder temp = new TemporaryFolder();
+
+  private final String format;
+  private final boolean vectorized;
+
+  @Parameterized.Parameters(name = "format = {0}, vectorized = {1}")
+  public static Object[][] parameters() {
+    return new Object[][] {
+        { "parquet", false },
+        { "parquet", true },
+        { "avro", false }
+    };
+  }
+
+  public TestTimestampWithoutZone(String format, boolean vectorized) {
+    this.format = format;
+    this.vectorized = vectorized;
+  }
+
+  private File parent = null;
+  private File unpartitioned = null;
+  private List<Record> records = null;
+
+  @Before
+  public void writeUnpartitionedTable() throws IOException {
+    this.parent = temp.newFolder("TestTimestampWithoutZone");
+    this.unpartitioned = new File(parent, "unpartitioned");
+    File dataFolder = new File(unpartitioned, "data");
+    Assert.assertTrue("Mkdir should succeed", dataFolder.mkdirs());
+
+    Table table = TABLES.create(SCHEMA, PartitionSpec.unpartitioned(), unpartitioned.toString());
+    Schema tableSchema = table.schema(); // use the table schema because ids are reassigned
+
+    FileFormat fileFormat = FileFormat.valueOf(format.toUpperCase(Locale.ENGLISH));
+
+    File testFile = new File(dataFolder, fileFormat.addExtension(UUID.randomUUID().toString()));
+
+    // create records using the table's schema
+    this.records = testRecords(tableSchema);
+
+    try (FileAppender<Record> writer = new GenericAppenderFactory(tableSchema).newAppender(
+        localOutput(testFile), fileFormat)) {
+      writer.addAll(records);
+    }
+
+    DataFile file = DataFiles.builder(PartitionSpec.unpartitioned())
+        .withRecordCount(records.size())
+        .withFileSizeInBytes(testFile.length())
+        .withPath(testFile.toString())
+        .build();
+
+    table.newAppend().appendFile(file).commit();
+  }
+
+  @Test
+  public void testUnpartitionedTimestampWithoutZone() {
+    assertEqualsSafe(SCHEMA.asStruct(), records, read(unpartitioned.toString(), vectorized));
+  }
+
+  @Test
+  public void testUnpartitionedTimestampWithoutZoneProjection() {
+    Schema projection = SCHEMA.select("id", "ts");
+    assertEqualsSafe(projection.asStruct(),
+        records.stream().map(r -> projectFlat(projection, r)).collect(Collectors.toList()),
+        read(unpartitioned.toString(), vectorized, "id", "ts"));
+  }
+
+  @Rule
+  public ExpectedException exception = ExpectedException.none();
+
+  @Test
+  public void testUnpartitionedTimestampWithoutZoneError() {
+    AssertHelpers.assertThrows(String.format("Read operation performed on a timestamp without timezone field while " +
+                    "'%s' set to false should throw exception",
+            SparkUtil.HANDLE_TIMESTAMP_WITHOUT_TIMEZONE),
+            IllegalArgumentException.class, SparkUtil.TIMESTAMP_WITHOUT_TIMEZONE_ERROR, () -> spark.read()
+                    .format("iceberg")
+            .option("vectorization-enabled", String.valueOf(vectorized))
+            .option(SparkUtil.HANDLE_TIMESTAMP_WITHOUT_TIMEZONE, "false")
+            .load(unpartitioned.toString())
+            .collectAsList());
+  }
+
+  @Test
+  public void testUnpartitionedTimestampWithoutZoneAppend() {
+    spark.read().format("iceberg")
+            .option(SparkUtil.HANDLE_TIMESTAMP_WITHOUT_TIMEZONE, "true")
+            .option("vectorization-enabled", String.valueOf(vectorized))
+            .load(unpartitioned.toString())
+

Review comment:
       nit: Empty Line




-- 
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