[GitHub] [iceberg] openinx commented on a change in pull request #2582: Add support for Parquet BloomFilter

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

openinx commented on a change in pull request #2582:
URL: https://github.com/apache/iceberg/pull/2582#discussion_r666800498



##########
File path: parquet/src/test/java/org/apache/iceberg/parquet/TestBloomRowGroupFilter.java
##########
@@ -0,0 +1,1073 @@
+/*
+ * 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.parquet;
+
+import java.io.File;
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.List;
+import java.util.UUID;
+import java.util.stream.Collectors;
+import java.util.stream.IntStream;
+import org.apache.avro.generic.GenericData.Record;
+import org.apache.avro.generic.GenericRecordBuilder;
+import org.apache.iceberg.Files;
+import org.apache.iceberg.Schema;
+import org.apache.iceberg.TestHelpers;
+import org.apache.iceberg.avro.AvroSchemaUtil;
+import org.apache.iceberg.exceptions.ValidationException;
+import org.apache.iceberg.expressions.Expression;
+import org.apache.iceberg.io.FileAppender;
+import org.apache.iceberg.io.InputFile;
+import org.apache.iceberg.io.OutputFile;
+import org.apache.iceberg.types.Types;
+import org.apache.iceberg.types.Types.DoubleType;
+import org.apache.iceberg.types.Types.FloatType;
+import org.apache.iceberg.types.Types.IntegerType;
+import org.apache.iceberg.types.Types.LongType;
+import org.apache.iceberg.types.Types.StringType;
+import org.apache.parquet.column.values.bloomfilter.BloomFilter;
+import org.apache.parquet.hadoop.BloomFilterReader;
+import org.apache.parquet.hadoop.ParquetFileReader;
+import org.apache.parquet.hadoop.metadata.BlockMetaData;
+import org.apache.parquet.hadoop.metadata.ColumnChunkMetaData;
+import org.apache.parquet.schema.MessageType;
+import org.junit.Assert;
+import org.junit.Before;
+import org.junit.Rule;
+import org.junit.Test;
+import org.junit.rules.TemporaryFolder;
+
+import static org.apache.iceberg.TableProperties.PARQUET_BLOOM_FILTER_ENABLED;
+import static org.apache.iceberg.avro.AvroSchemaUtil.convert;
+import static org.apache.iceberg.expressions.Expressions.and;
+import static org.apache.iceberg.expressions.Expressions.equal;
+import static org.apache.iceberg.expressions.Expressions.greaterThan;
+import static org.apache.iceberg.expressions.Expressions.greaterThanOrEqual;
+import static org.apache.iceberg.expressions.Expressions.in;
+import static org.apache.iceberg.expressions.Expressions.isNaN;
+import static org.apache.iceberg.expressions.Expressions.isNull;
+import static org.apache.iceberg.expressions.Expressions.lessThan;
+import static org.apache.iceberg.expressions.Expressions.lessThanOrEqual;
+import static org.apache.iceberg.expressions.Expressions.not;
+import static org.apache.iceberg.expressions.Expressions.notEqual;
+import static org.apache.iceberg.expressions.Expressions.notIn;
+import static org.apache.iceberg.expressions.Expressions.notNaN;
+import static org.apache.iceberg.expressions.Expressions.notNull;
+import static org.apache.iceberg.expressions.Expressions.or;
+import static org.apache.iceberg.expressions.Expressions.startsWith;
+import static org.apache.iceberg.types.Types.NestedField.optional;
+import static org.apache.iceberg.types.Types.NestedField.required;
+
+public class TestBloomRowGroupFilter {
+
+  private static final Types.StructType structFieldType =
+      Types.StructType.of(Types.NestedField.required(16, "int_field", IntegerType.get()));
+
+  private static final Schema SCHEMA = new Schema(
+      required(1, "id", IntegerType.get()),
+      required(2, "id_long", LongType.get()),
+      required(3, "id_double", DoubleType.get()),
+      required(4, "id_float", FloatType.get()),
+      required(5, "id_binary", StringType.get()),
+      required(6, "random_binary", StringType.get()),
+      required(7, "required", StringType.get()),
+      optional(8, "non_bloom", StringType.get()),
+      optional(9, "all_nulls", LongType.get()),
+      optional(10, "some_nulls", StringType.get()),
+      optional(11, "no_nulls", StringType.get()),
+      optional(12, "all_nans", DoubleType.get()),
+      optional(13, "some_nans", FloatType.get()),
+      optional(14, "no_nans", DoubleType.get()),
+      optional(15, "struct_not_null", structFieldType),
+      optional(17, "not_in_file", FloatType.get()),
+      optional(18, "no_stats", StringType.get())
+  );
+
+  private static final Types.StructType _structFieldType =
+      Types.StructType.of(Types.NestedField.required(16, "_int_field", IntegerType.get()));
+
+  private static final Schema FILE_SCHEMA = new Schema(
+      required(1, "_id", IntegerType.get()),
+      required(2, "_id_long", LongType.get()),
+      required(3, "_id_double", DoubleType.get()),
+      required(4, "_id_float", FloatType.get()),
+      required(5, "_id_binary", StringType.get()),
+      required(6, "_random_binary", StringType.get()),
+      required(7, "_required", StringType.get()),
+      required(8, "_non_bloom", StringType.get()),
+      optional(9, "_all_nulls", LongType.get()),
+      optional(10, "_some_nulls", StringType.get()),
+      optional(11, "_no_nulls", StringType.get()),
+      optional(12, "_all_nans", DoubleType.get()),
+      optional(13, "_some_nans", FloatType.get()),
+      optional(14, "_no_nans", DoubleType.get()),
+      optional(15, "_struct_not_null", _structFieldType),

Review comment:
       I think  we will need a fully covered test which address all the data types from [Type.java](https://github.com/apache/iceberg/blob/90225d6c9413016d611e2ce5eff37db1bc1b4fc5/api/src/main/java/org/apache/iceberg/types/Type.java#L30),  the selected `Integer`, `Double`, `String`, `Float` are not enough.




-- 
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