[HUDI-4319] Fixed Parquet's PLAIN_DICTIONARY encoding not being applied when bulk-inserting (#5966)

* Fixed Dictionary encoding config not being properly propagated to Parquet writer (making it unable to apply it, substantially bloating the storage footprint)

hudi-cli/src/main/scala/org/apache/hudi/cli/SparkHelpers.scala

@@ -23,12 +23,11 @@ import org.apache.hadoop.conf.Configuration
 import org.apache.hadoop.fs.{FileSystem, Path}
 import org.apache.hudi.avro.HoodieAvroWriteSupport
 import org.apache.hudi.client.SparkTaskContextSupplier
-import org.apache.hudi.common.HoodieJsonPayload
 import org.apache.hudi.common.bloom.{BloomFilter, BloomFilterFactory}
 import org.apache.hudi.common.model.{HoodieFileFormat, HoodieRecord}
 import org.apache.hudi.common.util.BaseFileUtils
 import org.apache.hudi.config.{HoodieIndexConfig, HoodieStorageConfig}
-import org.apache.hudi.io.storage.{HoodieAvroParquetConfig, HoodieAvroParquetWriter}
+import org.apache.hudi.io.storage.{HoodieAvroParquetWriter, HoodieParquetConfig}
 import org.apache.parquet.avro.AvroSchemaConverter
 import org.apache.parquet.hadoop.metadata.CompressionCodecName
 import org.apache.spark.sql.{DataFrame, SQLContext}
@@ -45,7 +44,7 @@ object SparkHelpers {
     val filter: BloomFilter = BloomFilterFactory.createBloomFilter(HoodieIndexConfig.BLOOM_FILTER_NUM_ENTRIES_VALUE.defaultValue.toInt, HoodieIndexConfig.BLOOM_FILTER_FPP_VALUE.defaultValue.toDouble,
       HoodieIndexConfig.BLOOM_INDEX_FILTER_DYNAMIC_MAX_ENTRIES.defaultValue.toInt, HoodieIndexConfig.BLOOM_FILTER_TYPE.defaultValue);
     val writeSupport: HoodieAvroWriteSupport = new HoodieAvroWriteSupport(new AvroSchemaConverter(fs.getConf).convert(schema), schema, org.apache.hudi.common.util.Option.of(filter))
-    val parquetConfig: HoodieAvroParquetConfig = new HoodieAvroParquetConfig(writeSupport, CompressionCodecName.GZIP, HoodieStorageConfig.PARQUET_BLOCK_SIZE.defaultValue.toInt, HoodieStorageConfig.PARQUET_PAGE_SIZE.defaultValue.toInt, HoodieStorageConfig.PARQUET_MAX_FILE_SIZE.defaultValue.toInt, fs.getConf, HoodieStorageConfig.PARQUET_COMPRESSION_RATIO_FRACTION.defaultValue.toDouble)
+    val parquetConfig: HoodieParquetConfig[HoodieAvroWriteSupport] = new HoodieParquetConfig(writeSupport, CompressionCodecName.GZIP, HoodieStorageConfig.PARQUET_BLOCK_SIZE.defaultValue.toInt, HoodieStorageConfig.PARQUET_PAGE_SIZE.defaultValue.toInt, HoodieStorageConfig.PARQUET_MAX_FILE_SIZE.defaultValue.toInt, fs.getConf, HoodieStorageConfig.PARQUET_COMPRESSION_RATIO_FRACTION.defaultValue.toDouble)
 
     // Add current classLoad for config, if not will throw classNotFound of 'HoodieWrapperFileSystem'.
     parquetConfig.getHadoopConf().setClassLoader(Thread.currentThread.getContextClassLoader)

hudi-client/hudi-client-common/src/main/java/org/apache/hudi/io/storage/HoodieAvroParquetWriter.java

@@ -47,11 +47,11 @@ public class HoodieAvroParquetWriter<R extends IndexedRecord>
 
   @SuppressWarnings({"unchecked", "rawtypes"})
   public HoodieAvroParquetWriter(Path file,
-                                 HoodieAvroParquetConfig parquetConfig,
+                                 HoodieParquetConfig<HoodieAvroWriteSupport> parquetConfig,
                                  String instantTime,
                                  TaskContextSupplier taskContextSupplier,
                                  boolean populateMetaFields) throws IOException {
-    super(file, (HoodieBaseParquetConfig) parquetConfig);
+    super(file, (HoodieParquetConfig) parquetConfig);
     this.fileName = file.getName();
     this.writeSupport = parquetConfig.getWriteSupport();
     this.instantTime = instantTime;

hudi-client/hudi-client-common/src/main/java/org/apache/hudi/io/storage/HoodieBaseParquetWriter.java

@@ -43,7 +43,7 @@ public abstract class HoodieBaseParquetWriter<R> extends ParquetWriter<R> {
   private long lastCachedDataSize = -1;
 
   public HoodieBaseParquetWriter(Path file,
-                                 HoodieBaseParquetConfig<? extends WriteSupport<R>> parquetConfig) throws IOException {
+                                 HoodieParquetConfig<? extends WriteSupport<R>> parquetConfig) throws IOException {
     super(HoodieWrapperFileSystem.convertToHoodiePath(file, parquetConfig.getHadoopConf()),
         ParquetFileWriter.Mode.CREATE,
         parquetConfig.getWriteSupport(),

hudi-client/hudi-client-common/src/main/java/org/apache/hudi/io/storage/HoodieFileWriterFactory.java

@@ -77,7 +77,7 @@ public class HoodieFileWriterFactory {
     Option<BloomFilter> filter = enableBloomFilter ? Option.of(createBloomFilter(config)) : Option.empty();
     HoodieAvroWriteSupport writeSupport = new HoodieAvroWriteSupport(new AvroSchemaConverter(conf).convert(schema), schema, filter);
 
-    HoodieAvroParquetConfig parquetConfig = new HoodieAvroParquetConfig(writeSupport, config.getParquetCompressionCodec(),
+    HoodieParquetConfig<HoodieAvroWriteSupport> parquetConfig = new HoodieParquetConfig<>(writeSupport, config.getParquetCompressionCodec(),
         config.getParquetBlockSize(), config.getParquetPageSize(), config.getParquetMaxFileSize(),
         conf, config.getParquetCompressionRatio(), config.parquetDictionaryEnabled());
 

hudi-client/hudi-client-common/src/test/java/org/apache/hudi/testutils/HoodieWriteableTestTable.java

@@ -19,6 +19,12 @@
 
 package org.apache.hudi.testutils;
 
+import org.apache.avro.Schema;
+import org.apache.avro.generic.GenericRecord;
+import org.apache.avro.generic.IndexedRecord;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
 import org.apache.hudi.avro.HoodieAvroUtils;
 import org.apache.hudi.avro.HoodieAvroWriteSupport;
 import org.apache.hudi.common.bloom.BloomFilter;
@@ -38,18 +44,11 @@ import org.apache.hudi.common.testutils.HoodieMetadataTestTable;
 import org.apache.hudi.common.util.Option;
 import org.apache.hudi.common.util.collection.Pair;
 import org.apache.hudi.config.HoodieStorageConfig;
-import org.apache.hudi.io.storage.HoodieAvroParquetConfig;
+import org.apache.hudi.io.storage.HoodieAvroParquetWriter;
+import org.apache.hudi.io.storage.HoodieParquetConfig;
 import org.apache.hudi.io.storage.HoodieOrcConfig;
 import org.apache.hudi.io.storage.HoodieOrcWriter;
-import org.apache.hudi.io.storage.HoodieAvroParquetWriter;
 import org.apache.hudi.metadata.HoodieTableMetadataWriter;
-
-import org.apache.avro.Schema;
-import org.apache.avro.generic.GenericRecord;
-import org.apache.avro.generic.IndexedRecord;
-import org.apache.hadoop.conf.Configuration;
-import org.apache.hadoop.fs.FileSystem;
-import org.apache.hadoop.fs.Path;
 import org.apache.log4j.LogManager;
 import org.apache.log4j.Logger;
 import org.apache.orc.CompressionKind;
@@ -110,7 +109,7 @@ public class HoodieWriteableTestTable extends HoodieMetadataTestTable {
     if (HoodieTableConfig.BASE_FILE_FORMAT.defaultValue().equals(HoodieFileFormat.PARQUET)) {
       HoodieAvroWriteSupport writeSupport = new HoodieAvroWriteSupport(
           new AvroSchemaConverter().convert(schema), schema, Option.of(filter));
-      HoodieAvroParquetConfig config = new HoodieAvroParquetConfig(writeSupport, CompressionCodecName.GZIP,
+      HoodieParquetConfig<HoodieAvroWriteSupport> config = new HoodieParquetConfig<>(writeSupport, CompressionCodecName.GZIP,
           ParquetWriter.DEFAULT_BLOCK_SIZE, ParquetWriter.DEFAULT_PAGE_SIZE, 120 * 1024 * 1024,
           new Configuration(), Double.parseDouble(HoodieStorageConfig.PARQUET_COMPRESSION_RATIO_FRACTION.defaultValue()));
       try (HoodieAvroParquetWriter writer = new HoodieAvroParquetWriter<>(

hudi-client/hudi-flink-client/src/main/java/org/apache/hudi/io/storage/row/HoodieRowDataFileWriterFactory.java

@@ -22,6 +22,7 @@ import org.apache.hudi.common.bloom.BloomFilter;
 import org.apache.hudi.common.bloom.BloomFilterFactory;
 import org.apache.hudi.common.fs.FSUtils;
 import org.apache.hudi.config.HoodieWriteConfig;
+import org.apache.hudi.io.storage.HoodieParquetConfig;
 import org.apache.hudi.table.HoodieTable;
 
 import org.apache.flink.table.types.logical.RowType;
@@ -67,7 +68,7 @@ public class HoodieRowDataFileWriterFactory {
     HoodieRowDataParquetWriteSupport writeSupport =
         new HoodieRowDataParquetWriteSupport(table.getHadoopConf(), rowType, filter);
     return new HoodieRowDataParquetWriter(
-        path, new HoodieRowDataParquetConfig(
+        path, new HoodieParquetConfig<>(
         writeSupport,
         writeConfig.getParquetCompressionCodec(),
         writeConfig.getParquetBlockSize(),

hudi-client/hudi-flink-client/src/main/java/org/apache/hudi/io/storage/row/HoodieRowDataParquetConfig.java

@@ -1,36 +0,0 @@
-/*
- * 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.hudi.io.storage.row;
-
-import org.apache.hudi.io.storage.HoodieBaseParquetConfig;
-
-import org.apache.hadoop.conf.Configuration;
-import org.apache.parquet.hadoop.metadata.CompressionCodecName;
-
-/**
- * ParquetConfig for datasource implementation with {@link org.apache.flink.table.data.RowData}.
- */
-public class HoodieRowDataParquetConfig extends HoodieBaseParquetConfig<HoodieRowDataParquetWriteSupport> {
-
-  public HoodieRowDataParquetConfig(HoodieRowDataParquetWriteSupport writeSupport, CompressionCodecName compressionCodecName,
-                                    int blockSize, int pageSize, long maxFileSize, Configuration hadoopConf,
-                                    double compressionRatio) {
-    super(writeSupport, compressionCodecName, blockSize, pageSize, maxFileSize, hadoopConf, compressionRatio);
-  }
-}

hudi-client/hudi-flink-client/src/main/java/org/apache/hudi/io/storage/row/HoodieRowDataParquetWriter.java

@@ -23,6 +23,7 @@ import org.apache.hudi.common.fs.HoodieWrapperFileSystem;
 
 import org.apache.flink.table.data.RowData;
 import org.apache.hadoop.fs.Path;
+import org.apache.hudi.io.storage.HoodieParquetConfig;
 import org.apache.parquet.hadoop.ParquetFileWriter;
 import org.apache.parquet.hadoop.ParquetWriter;
 
@@ -39,7 +40,7 @@ public class HoodieRowDataParquetWriter extends ParquetWriter<RowData>
   private final long maxFileSize;
   private final HoodieRowDataParquetWriteSupport writeSupport;
 
-  public HoodieRowDataParquetWriter(Path file, HoodieRowDataParquetConfig parquetConfig)
+  public HoodieRowDataParquetWriter(Path file, HoodieParquetConfig<HoodieRowDataParquetWriteSupport> parquetConfig)
       throws IOException {
     super(HoodieWrapperFileSystem.convertToHoodiePath(file, parquetConfig.getHadoopConf()),
         ParquetFileWriter.Mode.CREATE, parquetConfig.getWriteSupport(), parquetConfig.getCompressionCodecName(),

hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/io/storage/row/HoodieInternalRowFileWriterFactory.java

@@ -23,6 +23,7 @@ import org.apache.hudi.common.bloom.BloomFilterFactory;
 import org.apache.hudi.common.fs.FSUtils;
 import org.apache.hudi.config.HoodieWriteConfig;
 import org.apache.hudi.exception.HoodieIOException;
+import org.apache.hudi.io.storage.HoodieParquetConfig;
 import org.apache.hudi.table.HoodieTable;
 
 import org.apache.hadoop.fs.Path;
@@ -68,14 +69,17 @@ public class HoodieInternalRowFileWriterFactory {
     HoodieRowParquetWriteSupport writeSupport =
             new HoodieRowParquetWriteSupport(table.getHadoopConf(), structType, filter, writeConfig);
     return new HoodieInternalRowParquetWriter(
-        path, new HoodieRowParquetConfig(
+        path,
+        new HoodieParquetConfig<>(
             writeSupport,
             writeConfig.getParquetCompressionCodec(),
             writeConfig.getParquetBlockSize(),
             writeConfig.getParquetPageSize(),
             writeConfig.getParquetMaxFileSize(),
             writeSupport.getHadoopConf(),
-            writeConfig.getParquetCompressionRatio()));
+            writeConfig.getParquetCompressionRatio(),
+            writeConfig.parquetDictionaryEnabled()
+        ));
   }
 
   public static HoodieInternalRowFileWriter getInternalRowFileWriterWithoutMetaFields(
@@ -93,13 +97,15 @@ public class HoodieInternalRowFileWriterFactory {
     HoodieRowParquetWriteSupport writeSupport =
         new HoodieRowParquetWriteSupport(table.getHadoopConf(), structType, null, writeConfig);
     return new HoodieInternalRowParquetWriter(
-        path, new HoodieRowParquetConfig(
+        path, new HoodieParquetConfig<>(
         writeSupport,
         writeConfig.getParquetCompressionCodec(),
         writeConfig.getParquetBlockSize(),
         writeConfig.getParquetPageSize(),
         writeConfig.getParquetMaxFileSize(),
         writeSupport.getHadoopConf(),
-        writeConfig.getParquetCompressionRatio()));
+        writeConfig.getParquetCompressionRatio(),
+        writeConfig.parquetDictionaryEnabled())
+    );
   }
 }

hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/io/storage/row/HoodieInternalRowParquetWriter.java

@@ -19,6 +19,7 @@
 package org.apache.hudi.io.storage.row;
 
 import org.apache.hadoop.fs.Path;
+import org.apache.hudi.io.storage.HoodieParquetConfig;
 import org.apache.hudi.io.storage.HoodieBaseParquetWriter;
 import org.apache.spark.sql.catalyst.InternalRow;
 
@@ -32,7 +33,7 @@ public class HoodieInternalRowParquetWriter extends HoodieBaseParquetWriter<Inte
 
   private final HoodieRowParquetWriteSupport writeSupport;
 
-  public HoodieInternalRowParquetWriter(Path file, HoodieRowParquetConfig parquetConfig)
+  public HoodieInternalRowParquetWriter(Path file, HoodieParquetConfig<HoodieRowParquetWriteSupport> parquetConfig)
       throws IOException {
     super(file, parquetConfig);
 

hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/io/storage/row/HoodieRowParquetConfig.java

@@ -1,36 +0,0 @@
-/*
- * 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.hudi.io.storage.row;
-
-import org.apache.hudi.io.storage.HoodieBaseParquetConfig;
-
-import org.apache.hadoop.conf.Configuration;
-import org.apache.parquet.hadoop.metadata.CompressionCodecName;
-
-/**
- * ParquetConfig for datasource implementation with {@link org.apache.hudi.client.model.HoodieInternalRow}.
- */
-public class HoodieRowParquetConfig extends HoodieBaseParquetConfig<HoodieRowParquetWriteSupport> {
-
-  public HoodieRowParquetConfig(HoodieRowParquetWriteSupport writeSupport, CompressionCodecName compressionCodecName,
-                                int blockSize, int pageSize, long maxFileSize, Configuration hadoopConf,
-                                double compressionRatio) {
-    super(writeSupport, compressionCodecName, blockSize, pageSize, maxFileSize, hadoopConf, compressionRatio);
-  }
-}

hudi-client/hudi-spark-client/src/test/java/org/apache/hudi/io/storage/row/TestHoodieInternalRowParquetWriter.java

@@ -23,6 +23,7 @@ import org.apache.hudi.common.bloom.BloomFilterFactory;
 import org.apache.hudi.common.testutils.HoodieTestDataGenerator;
 import org.apache.hudi.config.HoodieStorageConfig;
 import org.apache.hudi.config.HoodieWriteConfig;
+import org.apache.hudi.io.storage.HoodieParquetConfig;
 import org.apache.hudi.testutils.HoodieClientTestHarness;
 import org.apache.hudi.testutils.SparkDatasetTestUtils;
 
@@ -73,9 +74,9 @@ public class TestHoodieInternalRowParquetWriter extends HoodieClientTestHarness
       // init write support and parquet config
       HoodieRowParquetWriteSupport writeSupport = getWriteSupport(writeConfigBuilder, hadoopConf, parquetWriteLegacyFormatEnabled);
       HoodieWriteConfig cfg = writeConfigBuilder.build();
-      HoodieRowParquetConfig parquetConfig = new HoodieRowParquetConfig(writeSupport,
+      HoodieParquetConfig<HoodieRowParquetWriteSupport> parquetConfig = new HoodieParquetConfig<>(writeSupport,
           CompressionCodecName.SNAPPY, cfg.getParquetBlockSize(), cfg.getParquetPageSize(), cfg.getParquetMaxFileSize(),
-          writeSupport.getHadoopConf(), cfg.getParquetCompressionRatio());
+          writeSupport.getHadoopConf(), cfg.getParquetCompressionRatio(), cfg.parquetDictionaryEnabled());
 
       // prepare path
       String fileId = UUID.randomUUID().toString();

hudi-common/src/main/java/org/apache/hudi/common/table/log/block/HoodieParquetDataBlock.java

@@ -18,21 +18,20 @@
 
 package org.apache.hudi.common.table.log.block;
 
-import org.apache.hudi.avro.HoodieAvroWriteSupport;
-import org.apache.hudi.common.fs.inline.InLineFSUtils;
-import org.apache.hudi.common.fs.inline.InLineFileSystem;
-import org.apache.hudi.common.util.ClosableIterator;
-import org.apache.hudi.common.util.Option;
-import org.apache.hudi.common.util.ParquetReaderIterator;
-import org.apache.hudi.io.storage.HoodieAvroParquetConfig;
-import org.apache.hudi.io.storage.HoodieParquetStreamWriter;
-
 import org.apache.avro.Schema;
 import org.apache.avro.generic.IndexedRecord;
 import org.apache.hadoop.conf.Configuration;
 import org.apache.hadoop.fs.FSDataInputStream;
 import org.apache.hadoop.fs.FSDataOutputStream;
 import org.apache.hadoop.fs.Path;
+import org.apache.hudi.avro.HoodieAvroWriteSupport;
+import org.apache.hudi.common.fs.inline.InLineFSUtils;
+import org.apache.hudi.common.fs.inline.InLineFileSystem;
+import org.apache.hudi.common.util.ClosableIterator;
+import org.apache.hudi.common.util.Option;
+import org.apache.hudi.common.util.ParquetReaderIterator;
+import org.apache.hudi.io.storage.HoodieParquetConfig;
+import org.apache.hudi.io.storage.HoodieParquetStreamWriter;
 import org.apache.parquet.avro.AvroParquetReader;
 import org.apache.parquet.avro.AvroReadSupport;
 import org.apache.parquet.avro.AvroSchemaConverter;
@@ -43,7 +42,6 @@ import org.apache.parquet.hadoop.util.HadoopInputFile;
 import org.apache.parquet.io.InputFile;
 
 import javax.annotation.Nonnull;
-
 import java.io.ByteArrayOutputStream;
 import java.io.IOException;
 import java.util.HashMap;
@@ -97,8 +95,8 @@ public class HoodieParquetDataBlock extends HoodieDataBlock {
     HoodieAvroWriteSupport writeSupport = new HoodieAvroWriteSupport(
         new AvroSchemaConverter().convert(writerSchema), writerSchema, Option.empty());
 
-    HoodieAvroParquetConfig avroParquetConfig =
+    HoodieParquetConfig<HoodieAvroWriteSupport> avroParquetConfig =
-        new HoodieAvroParquetConfig(
+        new HoodieParquetConfig<>(
             writeSupport,
             compressionCodecName.get(),
             ParquetWriter.DEFAULT_BLOCK_SIZE,

hudi-common/src/main/java/org/apache/hudi/io/storage/HoodieAvroParquetConfig.java

@@ -1,42 +0,0 @@
-/*
- * 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.hudi.io.storage;
-
-import org.apache.hudi.avro.HoodieAvroWriteSupport;
-
-import org.apache.hadoop.conf.Configuration;
-import org.apache.parquet.hadoop.metadata.CompressionCodecName;
-
-/**
- * ParquetConfig for writing avro records in Parquet files.
- */
-public class HoodieAvroParquetConfig extends HoodieBaseParquetConfig<HoodieAvroWriteSupport> {
-
-  public HoodieAvroParquetConfig(HoodieAvroWriteSupport writeSupport, CompressionCodecName compressionCodecName,
-                                 int blockSize, int pageSize, long maxFileSize, Configuration hadoopConf,
-                                 double compressionRatio) {
-    super(writeSupport, compressionCodecName, blockSize, pageSize, maxFileSize, hadoopConf, compressionRatio);
-  }
-
-  public HoodieAvroParquetConfig(HoodieAvroWriteSupport writeSupport, CompressionCodecName compressionCodecName,
-      int blockSize, int pageSize, long maxFileSize, Configuration hadoopConf,
-      double compressionRatio, boolean directoryEnabled) {
-    super(writeSupport, compressionCodecName, blockSize, pageSize, maxFileSize, hadoopConf, compressionRatio, directoryEnabled);
-  }
-}

hudi-common/src/main/java/org/apache/hudi/io/storage/HoodieParquetConfig.java

@@ -25,7 +25,7 @@ import org.apache.parquet.hadoop.metadata.CompressionCodecName;
  * Base ParquetConfig to hold config params for writing to Parquet.
  * @param <T>
  */
-public class HoodieBaseParquetConfig<T> {
+public class HoodieParquetConfig<T> {
   private final T writeSupport;
   private final CompressionCodecName compressionCodecName;
   private final int blockSize;
@@ -35,13 +35,13 @@ public class HoodieBaseParquetConfig<T> {
   private final double compressionRatio;
   private final boolean dictionaryEnabled;
 
-  public HoodieBaseParquetConfig(T writeSupport, CompressionCodecName compressionCodecName, int blockSize,
+  public HoodieParquetConfig(T writeSupport, CompressionCodecName compressionCodecName, int blockSize,
-      int pageSize, long maxFileSize, Configuration hadoopConf, double compressionRatio) {
+                             int pageSize, long maxFileSize, Configuration hadoopConf, double compressionRatio) {
     this(writeSupport, compressionCodecName, blockSize, pageSize, maxFileSize, hadoopConf, compressionRatio, false);
   }
 
-  public HoodieBaseParquetConfig(T writeSupport, CompressionCodecName compressionCodecName, int blockSize,
+  public HoodieParquetConfig(T writeSupport, CompressionCodecName compressionCodecName, int blockSize,
-                                 int pageSize, long maxFileSize, Configuration hadoopConf, double compressionRatio, boolean dictionaryEnabled) {
+                             int pageSize, long maxFileSize, Configuration hadoopConf, double compressionRatio, boolean dictionaryEnabled) {
     this.writeSupport = writeSupport;
     this.compressionCodecName = compressionCodecName;
     this.blockSize = blockSize;

hudi-common/src/main/java/org/apache/hudi/io/storage/HoodieParquetStreamWriter.java

@@ -38,7 +38,7 @@ public class HoodieParquetStreamWriter<R extends IndexedRecord> implements AutoC
   private final HoodieAvroWriteSupport writeSupport;
 
   public HoodieParquetStreamWriter(FSDataOutputStream outputStream,
-                                   HoodieAvroParquetConfig parquetConfig) throws IOException {
+                                   HoodieParquetConfig<HoodieAvroWriteSupport> parquetConfig) throws IOException {
     this.writeSupport = parquetConfig.getWriteSupport();
     this.writer = new Builder<R>(new OutputStreamBackedOutputFile(outputStream), writeSupport)
         .withWriteMode(ParquetFileWriter.Mode.CREATE)