[GitHub] [parquet-mr] yabola commented on a diff in pull request #1033: PARQUET-2251 Avoid generating Bloomfilter when all pages of a column are encoded by dictionary in parquet v1

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

yabola commented on code in PR #1033:
URL: https://github.com/apache/parquet-mr/pull/1033#discussion_r1116549921


##########
parquet-hadoop/src/test/java/org/apache/parquet/hadoop/TestStoreBloomFilter.java:
##########
@@ -0,0 +1,132 @@
+/*
+ * 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.parquet.hadoop;
+
+import static org.apache.parquet.hadoop.ParquetFileWriter.Mode.OVERWRITE;
+import static org.apache.parquet.hadoop.TestBloomFiltering.generateDictionaryData;
+
+import java.io.IOException;
+import java.nio.file.Files;
+import java.util.Arrays;
+import java.util.Collection;
+import java.util.Collections;
+import java.util.List;
+
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.Path;
+import org.junit.AfterClass;
+import org.junit.Assert;
+import org.junit.BeforeClass;
+import org.junit.Test;
+import org.junit.runner.RunWith;
+import org.junit.runners.Parameterized;
+
+import org.apache.parquet.ParquetReadOptions;
+import org.apache.parquet.column.EncodingStats;
+import org.apache.parquet.column.ParquetProperties;
+import org.apache.parquet.filter2.recordlevel.PhoneBookWriter;
+import org.apache.parquet.hadoop.example.ExampleParquetWriter;
+import org.apache.parquet.hadoop.metadata.BlockMetaData;
+import org.apache.parquet.hadoop.metadata.ColumnChunkMetaData;
+import org.apache.parquet.hadoop.util.HadoopInputFile;
+
+@RunWith(Parameterized.class)
+public class TestStoreBloomFilter {
+  private static final Path FILE_V1 = createTempFile("v1");
+  private static final Path FILE_V2 = createTempFile("v2");
+  private static final List<PhoneBookWriter.User> DATA = Collections.unmodifiableList(generateDictionaryData(10000));
+  private final Path file;
+  private final String pageVersion;
+
+  public TestStoreBloomFilter(Path file, String pageVersion) {
+    this.file = file;
+    this.pageVersion = pageVersion;
+  }
+
+  @Parameterized.Parameters(name = "Run {index}: parquet {1}")
+  public static Collection<Object[]> params() {
+    return Arrays.asList(
+      new Object[]{FILE_V1, "pageV1"},

Review Comment:
   thanks, I modified the description



-- 
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: dev-unsubscribe@parquet.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org