[GitHub] [iceberg] rdblue commented on a change in pull request #1487: Spark: add E2E test on partition pruning for filter pushdown

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

rdblue commented on a change in pull request #1487:
URL: https://github.com/apache/iceberg/pull/1487#discussion_r493983892



##########
File path: spark/src/test/java/org/apache/iceberg/spark/source/TestPartitionPruning.java
##########
@@ -0,0 +1,354 @@
+/*
+ * 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.net.URI;
+import java.sql.Timestamp;
+import java.util.Arrays;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Map;
+import java.util.Random;
+import java.util.Set;
+import java.util.concurrent.ConcurrentHashMap;
+import java.util.function.Predicate;
+import java.util.stream.Collectors;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.FSDataInputStream;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.fs.RawLocalFileSystem;
+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.relocated.com.google.common.collect.ImmutableList;
+import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap;
+import org.apache.iceberg.relocated.com.google.common.collect.Sets;
+import org.apache.iceberg.transforms.Transform;
+import org.apache.iceberg.transforms.Transforms;
+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.apache.spark.sql.types.DataTypes;
+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.TemporaryFolder;
+import org.junit.runner.RunWith;
+import org.junit.runners.Parameterized;
+
+@RunWith(Parameterized.class)
+public abstract class TestPartitionPruning {
+
+  private static final Configuration CONF = new Configuration();
+  private static final HadoopTables TABLES = new HadoopTables(CONF);
+
+  @Parameterized.Parameters
+  public static Object[][] parameters() {
+    return new Object[][] {
+        new Object[] { "parquet", false },
+        new Object[] { "parquet", true },
+        new Object[] { "avro", false },
+        new Object[] { "orc", false },
+        new Object[] { "orc", true },
+    };
+  }
+
+  private final String format;
+  private final boolean vectorized;
+
+  public TestPartitionPruning(String format, boolean vectorized) {
+    this.format = format;
+    this.vectorized = vectorized;
+  }
+
+  private static SparkSession spark = null;
+
+  private static Transform<Object, Integer> bucketTransform = Transforms.bucket(Types.IntegerType.get(), 3);
+  private static Transform<Object, Object> truncateTransform = Transforms.truncate(Types.StringType.get(), 5);
+  private static Transform<Object, Integer> hourTransform = Transforms.hour(Types.TimestampType.withZone());
+
+  @BeforeClass
+  public static void startSpark() {
+    TestPartitionPruning.spark = SparkSession.builder().master("local[2]").getOrCreate();
+    String optionKey = String.format("fs.%s.impl", CountOpenLocalFileSystem.scheme);
+
+    CONF.set(optionKey, CountOpenLocalFileSystem.class.getName());
+    spark.conf().set(optionKey, CountOpenLocalFileSystem.class.getName());
+    spark.udf().register("bucket3", (Integer num) -> bucketTransform.apply(num), DataTypes.IntegerType);
+    spark.udf().register("truncate5", (String str) -> truncateTransform.apply(str), DataTypes.StringType);
+    // NOTE: date transforms take the type long, not Timestamp
+    spark.udf().register("hour", (Timestamp ts) -> hourTransform.apply(
+        (Long) org.apache.spark.sql.catalyst.util.DateTimeUtils.fromJavaTimestamp(ts)),
+        DataTypes.IntegerType);
+  }
+
+  @AfterClass
+  public static void stopSpark() {
+    SparkSession currentSpark = TestPartitionPruning.spark;
+    TestPartitionPruning.spark = null;
+    currentSpark.stop();
+  }
+
+  private static final Schema LOG_SCHEMA = new Schema(
+      Types.NestedField.optional(1, "id", Types.IntegerType.get()),
+      Types.NestedField.optional(2, "date", Types.StringType.get()),
+      Types.NestedField.optional(3, "level", Types.StringType.get()),
+      Types.NestedField.optional(4, "message", Types.StringType.get()),
+      Types.NestedField.optional(5, "timestamp", Types.TimestampType.withZone())
+  );
+
+  private static final List<LogMessage> LOGS = ImmutableList.of(
+      LogMessage.debug("2020-02-02", "debug event 1", Timestamp.valueOf("2020-02-02 00:00:00")),

Review comment:
       I don't think it is a good idea for tests to create `Timestamp` or `Date` objects because those representations are tied to a time zone in the JVM implementation. If you have to use them, then pass an instant in milliseconds or microseconds that is produced by Iceberg's literals: `Literal.of("2020-02-02 01:00:00").to(TimestampType.withoutZone()).value()`




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