/**
* Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
* SPDX-License-Identifier: Apache-2.0.
*/
#pragma once
#include A serializer to use for converting data to the Parquet format before storing
* it in Amazon S3. For more information, see Apache
* Parquet.See Also:
AWS
* API Reference
The Hadoop Distributed File System (HDFS) block size. This is useful if you * intend to copy the data from Amazon S3 to HDFS before querying. The default is * 256 MiB and the minimum is 64 MiB. Kinesis Data Firehose uses this value for * padding calculations.
*/ inline int GetBlockSizeBytes() const{ return m_blockSizeBytes; } /** *The Hadoop Distributed File System (HDFS) block size. This is useful if you * intend to copy the data from Amazon S3 to HDFS before querying. The default is * 256 MiB and the minimum is 64 MiB. Kinesis Data Firehose uses this value for * padding calculations.
*/ inline bool BlockSizeBytesHasBeenSet() const { return m_blockSizeBytesHasBeenSet; } /** *The Hadoop Distributed File System (HDFS) block size. This is useful if you * intend to copy the data from Amazon S3 to HDFS before querying. The default is * 256 MiB and the minimum is 64 MiB. Kinesis Data Firehose uses this value for * padding calculations.
*/ inline void SetBlockSizeBytes(int value) { m_blockSizeBytesHasBeenSet = true; m_blockSizeBytes = value; } /** *The Hadoop Distributed File System (HDFS) block size. This is useful if you * intend to copy the data from Amazon S3 to HDFS before querying. The default is * 256 MiB and the minimum is 64 MiB. Kinesis Data Firehose uses this value for * padding calculations.
*/ inline ParquetSerDe& WithBlockSizeBytes(int value) { SetBlockSizeBytes(value); return *this;} /** *The Parquet page size. Column chunks are divided into pages. A page is * conceptually an indivisible unit (in terms of compression and encoding). The * minimum value is 64 KiB and the default is 1 MiB.
*/ inline int GetPageSizeBytes() const{ return m_pageSizeBytes; } /** *The Parquet page size. Column chunks are divided into pages. A page is * conceptually an indivisible unit (in terms of compression and encoding). The * minimum value is 64 KiB and the default is 1 MiB.
*/ inline bool PageSizeBytesHasBeenSet() const { return m_pageSizeBytesHasBeenSet; } /** *The Parquet page size. Column chunks are divided into pages. A page is * conceptually an indivisible unit (in terms of compression and encoding). The * minimum value is 64 KiB and the default is 1 MiB.
*/ inline void SetPageSizeBytes(int value) { m_pageSizeBytesHasBeenSet = true; m_pageSizeBytes = value; } /** *The Parquet page size. Column chunks are divided into pages. A page is * conceptually an indivisible unit (in terms of compression and encoding). The * minimum value is 64 KiB and the default is 1 MiB.
*/ inline ParquetSerDe& WithPageSizeBytes(int value) { SetPageSizeBytes(value); return *this;} /** *The compression code to use over data blocks. The possible values are
* UNCOMPRESSED
, SNAPPY
, and GZIP
, with the
* default being SNAPPY
. Use SNAPPY
for higher
* decompression speed. Use GZIP
if the compression ratio is more
* important than speed.
The compression code to use over data blocks. The possible values are
* UNCOMPRESSED
, SNAPPY
, and GZIP
, with the
* default being SNAPPY
. Use SNAPPY
for higher
* decompression speed. Use GZIP
if the compression ratio is more
* important than speed.
The compression code to use over data blocks. The possible values are
* UNCOMPRESSED
, SNAPPY
, and GZIP
, with the
* default being SNAPPY
. Use SNAPPY
for higher
* decompression speed. Use GZIP
if the compression ratio is more
* important than speed.
The compression code to use over data blocks. The possible values are
* UNCOMPRESSED
, SNAPPY
, and GZIP
, with the
* default being SNAPPY
. Use SNAPPY
for higher
* decompression speed. Use GZIP
if the compression ratio is more
* important than speed.
The compression code to use over data blocks. The possible values are
* UNCOMPRESSED
, SNAPPY
, and GZIP
, with the
* default being SNAPPY
. Use SNAPPY
for higher
* decompression speed. Use GZIP
if the compression ratio is more
* important than speed.
The compression code to use over data blocks. The possible values are
* UNCOMPRESSED
, SNAPPY
, and GZIP
, with the
* default being SNAPPY
. Use SNAPPY
for higher
* decompression speed. Use GZIP
if the compression ratio is more
* important than speed.
Indicates whether to enable dictionary compression.
*/ inline bool GetEnableDictionaryCompression() const{ return m_enableDictionaryCompression; } /** *Indicates whether to enable dictionary compression.
*/ inline bool EnableDictionaryCompressionHasBeenSet() const { return m_enableDictionaryCompressionHasBeenSet; } /** *Indicates whether to enable dictionary compression.
*/ inline void SetEnableDictionaryCompression(bool value) { m_enableDictionaryCompressionHasBeenSet = true; m_enableDictionaryCompression = value; } /** *Indicates whether to enable dictionary compression.
*/ inline ParquetSerDe& WithEnableDictionaryCompression(bool value) { SetEnableDictionaryCompression(value); return *this;} /** *The maximum amount of padding to apply. This is useful if you intend to copy * the data from Amazon S3 to HDFS before querying. The default is 0.
*/ inline int GetMaxPaddingBytes() const{ return m_maxPaddingBytes; } /** *The maximum amount of padding to apply. This is useful if you intend to copy * the data from Amazon S3 to HDFS before querying. The default is 0.
*/ inline bool MaxPaddingBytesHasBeenSet() const { return m_maxPaddingBytesHasBeenSet; } /** *The maximum amount of padding to apply. This is useful if you intend to copy * the data from Amazon S3 to HDFS before querying. The default is 0.
*/ inline void SetMaxPaddingBytes(int value) { m_maxPaddingBytesHasBeenSet = true; m_maxPaddingBytes = value; } /** *The maximum amount of padding to apply. This is useful if you intend to copy * the data from Amazon S3 to HDFS before querying. The default is 0.
*/ inline ParquetSerDe& WithMaxPaddingBytes(int value) { SetMaxPaddingBytes(value); return *this;} /** *Indicates the version of row format to output. The possible values are
* V1
and V2
. The default is V1
.
Indicates the version of row format to output. The possible values are
* V1
and V2
. The default is V1
.
Indicates the version of row format to output. The possible values are
* V1
and V2
. The default is V1
.
Indicates the version of row format to output. The possible values are
* V1
and V2
. The default is V1
.
Indicates the version of row format to output. The possible values are
* V1
and V2
. The default is V1
.
Indicates the version of row format to output. The possible values are
* V1
and V2
. The default is V1
.